From f35f5603f4f07c939754743b2a6cf61bb3a4694e Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 3 Apr 2008 02:12:06 -0700 Subject: [PATCH 001/295] revision traversal: --children option This adds a new --children option to the revision machinery. In addition to the list of parents, child commits of each commit are computed and stored as a decoration to each commit. Signed-off-by: Junio C Hamano --- revision.c | 40 +++++++++++++++++++++++++++++++++++++--- revision.h | 1 + 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/revision.c b/revision.c index ffbed3fbf2..979241eb0d 100644 --- a/revision.c +++ b/revision.c @@ -9,6 +9,7 @@ #include "grep.h" #include "reflog-walk.h" #include "patch-ids.h" +#include "decorate.h" volatile show_early_output_fn_t show_early_output; @@ -1310,6 +1311,11 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch revs->no_walk = 0; continue; } + if (!strcmp(arg, "--children")) { + revs->children.name = "children"; + revs->limited = 1; + continue; + } opts = diff_opt_parse(&revs->diffopt, argv+i, argc-i); if (opts > 0) { @@ -1395,10 +1401,31 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch if (revs->reverse && revs->reflog_info) die("cannot combine --reverse with --walk-reflogs"); - + if (revs->parents && revs->children.name) + die("cannot combine --parents and --children"); return left; } +static void add_child(struct rev_info *revs, struct commit *parent, struct commit *child) +{ + struct commit_list *l = xcalloc(1, sizeof(*l)); + + l->item = child; + l->next = add_decoration(&revs->children, &parent->object, l); +} + +static void set_children(struct rev_info *revs) +{ + struct commit_list *l; + for (l = revs->commits; l; l = l->next) { + struct commit *commit = l->item; + struct commit_list *p; + + for (p = commit->parents; p; p = p->next) + add_child(revs, p->item, commit); + } +} + int prepare_revision_walk(struct rev_info *revs) { int nr = revs->pending.nr; @@ -1427,6 +1454,8 @@ int prepare_revision_walk(struct rev_info *revs) return -1; if (revs->topo_order) sort_in_topological_order(&revs->commits, revs->lifo); + if (revs->children.name) + set_children(revs); return 0; } @@ -1504,6 +1533,11 @@ static int commit_match(struct commit *commit, struct rev_info *opt) commit->buffer, strlen(commit->buffer)); } +static inline int want_ancestry(struct rev_info *revs) +{ + return (revs->parents || revs->children.name); +} + enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit) { if (commit->object.flags & SHOWN) @@ -1524,13 +1558,13 @@ enum commit_action simplify_commit(struct rev_info *revs, struct commit *commit) /* Commit without changes? */ if (commit->object.flags & TREESAME) { /* drop merges unless we want parenthood */ - if (!revs->parents) + if (!want_ancestry(revs)) return commit_ignore; /* non-merge - always ignore it */ if (!commit->parents || !commit->parents->next) return commit_ignore; } - if (revs->parents && rewrite_parents(revs, commit) < 0) + if (want_ancestry(revs) && rewrite_parents(revs, commit) < 0) return commit_error; } return commit_show; diff --git a/revision.h b/revision.h index c8b3b948ec..966116cd5b 100644 --- a/revision.h +++ b/revision.h @@ -98,6 +98,7 @@ struct rev_info { struct diff_options pruning; struct reflog_walk_info *reflog_info; + struct decoration children; }; #define REV_TREE_SAME 0 From 72276a3ecbe6353b83ab37e0ce96cc21c94cf6ee Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 3 Apr 2008 23:01:47 -0700 Subject: [PATCH 002/295] rev-list --children Just like --parents option shows the parents of commits, this shows the children of commits. Signed-off-by: Junio C Hamano --- Documentation/rev-list-options.txt | 4 ++++ builtin-rev-list.c | 10 ++++++++++ 2 files changed, 14 insertions(+) diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt index 2648a55085..e5823950e2 100644 --- a/Documentation/rev-list-options.txt +++ b/Documentation/rev-list-options.txt @@ -42,6 +42,10 @@ format, often found in E-mail messages. Print the parents of the commit. +--children:: + + Print the children of the commit. + --timestamp:: Print the raw commit timestamp. diff --git a/builtin-rev-list.c b/builtin-rev-list.c index edc0bd35bb..9da2f76375 100644 --- a/builtin-rev-list.c +++ b/builtin-rev-list.c @@ -36,6 +36,7 @@ static const char rev_list_usage[] = " --reverse\n" " formatting output:\n" " --parents\n" +" --children\n" " --objects | --objects-edge\n" " --unpacked\n" " --header | --pretty\n" @@ -84,6 +85,15 @@ static void show_commit(struct commit *commit) parents = parents->next; } } + if (revs.children.name) { + struct commit_list *children; + + children = lookup_decoration(&revs.children, &commit->object); + while (children) { + printf(" %s", sha1_to_hex(children->item->object.sha1)); + children = children->next; + } + } show_decorations(commit); if (revs.commit_format == CMIT_FMT_ONELINE) putchar(' '); From f6c07d7d475ffaa67b817beb2635fd73a5e0e962 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 2 Apr 2008 22:17:53 -0700 Subject: [PATCH 003/295] builtin-blame.c: move prepare_final() into a separate function. After parsing the command line, we have a long loop to compute the commit object to start annotating from. Move the logic to a separate function, so that later patches become easier to read. It also makes fill_origin_blob() return void; the check is always done on !file->ptr, and nobody looks at the return value from the function. Signed-off-by: Junio C Hamano --- builtin-blame.c | 56 +++++++++++++++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 23 deletions(-) diff --git a/builtin-blame.c b/builtin-blame.c index bfd562d7d2..996f535767 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -91,7 +91,7 @@ struct origin { * Given an origin, prepare mmfile_t structure to be used by the * diff machinery */ -static char *fill_origin_blob(struct origin *o, mmfile_t *file) +static void fill_origin_blob(struct origin *o, mmfile_t *file) { if (!o->file.ptr) { enum object_type type; @@ -106,7 +106,6 @@ static char *fill_origin_blob(struct origin *o, mmfile_t *file) } else *file = o->file; - return file->ptr; } /* @@ -2006,6 +2005,10 @@ static int git_blame_config(const char *var, const char *value) return git_default_config(var, value); } +/* + * Prepare a dummy commit that represents the work tree (or staged) item. + * Note that annotating work tree item never works in the reverse. + */ static struct commit *fake_working_tree_commit(const char *path, const char *contents_from) { struct commit *commit; @@ -2122,6 +2125,33 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con return commit; } +static const char *prepare_final(struct scoreboard *sb, struct rev_info *revs) +{ + int i; + const char *final_commit_name = NULL; + + /* + * There must be one and only one positive commit in the + * revs->pending array. + */ + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (obj->flags & UNINTERESTING) + continue; + while (obj->type == OBJ_TAG) + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (sb->final) + die("More than one commit to dig from %s and %s?", + revs->pending.objects[i].name, + final_commit_name); + sb->final = (struct commit *) obj; + final_commit_name = revs->pending.objects[i].name; + } + return final_commit_name; +} + int cmd_blame(int argc, const char **argv, const char *prefix) { struct rev_info revs; @@ -2327,27 +2357,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix) setup_revisions(unk, argv, &revs, NULL); memset(&sb, 0, sizeof(sb)); - /* - * There must be one and only one positive commit in the - * revs->pending array. - */ - for (i = 0; i < revs.pending.nr; i++) { - struct object *obj = revs.pending.objects[i].item; - if (obj->flags & UNINTERESTING) - continue; - while (obj->type == OBJ_TAG) - obj = deref_tag(obj, NULL, 0); - if (obj->type != OBJ_COMMIT) - die("Non commit %s?", - revs.pending.objects[i].name); - if (sb.final) - die("More than one commit to dig from %s and %s?", - revs.pending.objects[i].name, - final_commit_name); - sb.final = (struct commit *) obj; - final_commit_name = revs.pending.objects[i].name; - } - + final_commit_name = prepare_final(&sb, &revs); if (!sb.final) { /* * "--not A B -- path" without anything positive; From 69264f46a193ae9dec5761984b4bae32f4810916 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 3 Apr 2008 00:56:23 -0700 Subject: [PATCH 004/295] builtin-blame.c: allow more than 16 parents This removes the hardcoded 16 parents limit from git-blame by allowing the parent array to be allocated dynamically. As the ultimate objective is not about allowing dodecapus, but about annotating the history upside down, it also renames "parent" in the code to "scapegoat"; the name of the game used to be "pass blame to your parents", but now it is "find a scapegoat to pass blame on". Signed-off-by: Junio C Hamano --- builtin-blame.c | 91 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 60 insertions(+), 31 deletions(-) diff --git a/builtin-blame.c b/builtin-blame.c index 996f535767..fbc441fb9f 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -1191,18 +1191,45 @@ static void pass_whole_blame(struct scoreboard *sb, } } -#define MAXPARENT 16 +/* + * We pass blame from the current commit to its parents. We keep saying + * "parent" (and "porigin"), but what we mean is to find scapegoat to + * exonerate ourselves. + */ +static struct commit_list *first_scapegoat(struct commit *commit) +{ + return commit->parents; +} + +static int num_scapegoats(struct commit *commit) +{ + int cnt; + struct commit_list *l = first_scapegoat(commit); + for (cnt = 0; l; l = l->next) + cnt++; + return cnt; +} + +#define MAXSG 16 static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) { - int i, pass; + int i, pass, num_sg; struct commit *commit = origin->commit; - struct commit_list *parent; - struct origin *parent_origin[MAXPARENT], *porigin; + struct commit_list *sg; + struct origin *sg_buf[MAXSG]; + struct origin *porigin, **sg_origin = sg_buf; - memset(parent_origin, 0, sizeof(parent_origin)); + num_sg = num_scapegoats(commit); + if (!num_sg) + goto finish; + else if (num_sg < ARRAY_SIZE(sg_buf)) + memset(sg_buf, 0, sizeof(sg_buf)); + else + sg_origin = xcalloc(num_sg, sizeof(*sg_origin)); - /* The first pass looks for unrenamed path to optimize for + /* + * The first pass looks for unrenamed path to optimize for * common cases, then we look for renames in the second pass. */ for (pass = 0; pass < 2; pass++) { @@ -1210,13 +1237,13 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) struct commit *, struct origin *); find = pass ? find_rename : find_origin; - for (i = 0, parent = commit->parents; - i < MAXPARENT && parent; - parent = parent->next, i++) { - struct commit *p = parent->item; + for (i = 0, sg = first_scapegoat(commit); + i < num_sg && sg; + sg = sg->next, i++) { + struct commit *p = sg->item; int j, same; - if (parent_origin[i]) + if (sg_origin[i]) continue; if (parse_commit(p)) continue; @@ -1229,24 +1256,24 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) goto finish; } for (j = same = 0; j < i; j++) - if (parent_origin[j] && - !hashcmp(parent_origin[j]->blob_sha1, + if (sg_origin[j] && + !hashcmp(sg_origin[j]->blob_sha1, porigin->blob_sha1)) { same = 1; break; } if (!same) - parent_origin[i] = porigin; + sg_origin[i] = porigin; else origin_decref(porigin); } } num_commits++; - for (i = 0, parent = commit->parents; - i < MAXPARENT && parent; - parent = parent->next, i++) { - struct origin *porigin = parent_origin[i]; + for (i = 0, sg = first_scapegoat(commit); + i < num_sg && sg; + sg = sg->next, i++) { + struct origin *porigin = sg_origin[i]; if (!porigin) continue; if (pass_blame_to_parent(sb, origin, porigin)) @@ -1257,10 +1284,10 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) * Optionally find moves in parents' files. */ if (opt & PICKAXE_BLAME_MOVE) - for (i = 0, parent = commit->parents; - i < MAXPARENT && parent; - parent = parent->next, i++) { - struct origin *porigin = parent_origin[i]; + for (i = 0, sg = first_scapegoat(commit); + i < num_sg && sg; + sg = sg->next, i++) { + struct origin *porigin = sg_origin[i]; if (!porigin) continue; if (find_move_in_parent(sb, origin, porigin)) @@ -1271,23 +1298,25 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) * Optionally find copies from parents' files. */ if (opt & PICKAXE_BLAME_COPY) - for (i = 0, parent = commit->parents; - i < MAXPARENT && parent; - parent = parent->next, i++) { - struct origin *porigin = parent_origin[i]; - if (find_copy_in_parent(sb, origin, parent->item, + for (i = 0, sg = first_scapegoat(commit); + i < num_sg && sg; + sg = sg->next, i++) { + struct origin *porigin = sg_origin[i]; + if (find_copy_in_parent(sb, origin, sg->item, porigin, opt)) goto finish; } finish: - for (i = 0; i < MAXPARENT; i++) { - if (parent_origin[i]) { - drop_origin_blob(parent_origin[i]); - origin_decref(parent_origin[i]); + for (i = 0; i < num_sg; i++) { + if (sg_origin[i]) { + drop_origin_blob(sg_origin[i]); + origin_decref(sg_origin[i]); } } drop_origin_blob(origin); + if (sg_buf != sg_origin) + free(sg_origin); } /* From 85af7929ee125385c2771fa4eaccfa2f29dc63c9 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 2 Apr 2008 22:17:53 -0700 Subject: [PATCH 005/295] git-blame --reverse This new option allows "git blame" to read an old version of the file, and up to which commit each line survived (i.e. their children rewrote the line out of the contents). The previous revision machinery update to decorate each commit with its children was leading to this change. When the --reverse option is given, we read the old version and pass blame to the children of the current suspect, instead of the usual order of starting from the latest and passing blame to parents. The standard yardstick of "blame" in git.git history is "rev-list.c" which was refactored heavily in its existence. For example: git blame -C -C -w --reverse 9de48752..master -- rev-list.c begins like this: 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 1) #include "cache... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 2) #include "commi... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 3) #include "tree.... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 4) #include "blob.... 213523f4 rev-list.c (JC Hamano 2006-03-01 5) #include "epoch... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 6) ab57c8dd rev-list.c (JC Hamano 2006-02-24 7) #define SEEN ab57c8dd rev-list.c (JC Hamano 2006-02-24 8) #define INTERES... 213523f4 rev-list.c (JC Hamano 2006-03-01 9) #define COUNTED... 7e21c29b rev-list.c (LTorvalds 2005-07-06 10) #define SHOWN ... 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 11) 6c41b801 builtin-rev-list.c (JC Hamano 2008-04-02 12) static const ch... b1349229 rev-list.c (LTorvalds 2005-07-26 13) "usage: git-... This reveals that the original first four lines survived until now in builtin-rev-list.c , inclusion of "epoch.h" was removed after 213523f4 while the contents was still in rev-list.c. This mode probably needs more tweaking so that the commit that removed the line (i.e. the children of the commits listed in the above sample output) is shown instead to be useful, but then there is a little matter of which child of a fork point to show. For now, you can find the diff that rewrote the fifth line above by doing: $ git log --children 213523f4^.. to find its child, which is 1025fe5 (Merge branch 'lt/rev-list' into next, 2006-03-01), and then look at that child with: $ git show 1025fe5 Signed-off-by: Junio C Hamano --- builtin-blame.c | 81 +++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 65 insertions(+), 16 deletions(-) diff --git a/builtin-blame.c b/builtin-blame.c index fbc441fb9f..5c7546db25 100644 --- a/builtin-blame.c +++ b/builtin-blame.c @@ -43,6 +43,7 @@ static int max_orig_digits; static int max_digits; static int max_score_digits; static int show_root; +static int reverse; static int blank_boundary; static int incremental; static int cmd_is_annotate; @@ -177,7 +178,7 @@ struct blame_entry { struct scoreboard { /* the final commit (i.e. where we started digging from) */ struct commit *final; - + struct rev_info *revs; const char *path; /* @@ -1196,15 +1197,17 @@ static void pass_whole_blame(struct scoreboard *sb, * "parent" (and "porigin"), but what we mean is to find scapegoat to * exonerate ourselves. */ -static struct commit_list *first_scapegoat(struct commit *commit) +static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit) { - return commit->parents; + if (!reverse) + return commit->parents; + return lookup_decoration(&revs->children, &commit->object); } -static int num_scapegoats(struct commit *commit) +static int num_scapegoats(struct rev_info *revs, struct commit *commit) { int cnt; - struct commit_list *l = first_scapegoat(commit); + struct commit_list *l = first_scapegoat(revs, commit); for (cnt = 0; l; l = l->next) cnt++; return cnt; @@ -1214,13 +1217,14 @@ static int num_scapegoats(struct commit *commit) static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) { + struct rev_info *revs = sb->revs; int i, pass, num_sg; struct commit *commit = origin->commit; struct commit_list *sg; struct origin *sg_buf[MAXSG]; struct origin *porigin, **sg_origin = sg_buf; - num_sg = num_scapegoats(commit); + num_sg = num_scapegoats(revs, commit); if (!num_sg) goto finish; else if (num_sg < ARRAY_SIZE(sg_buf)) @@ -1237,7 +1241,7 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) struct commit *, struct origin *); find = pass ? find_rename : find_origin; - for (i = 0, sg = first_scapegoat(commit); + for (i = 0, sg = first_scapegoat(revs, commit); i < num_sg && sg; sg = sg->next, i++) { struct commit *p = sg->item; @@ -1270,7 +1274,7 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) } num_commits++; - for (i = 0, sg = first_scapegoat(commit); + for (i = 0, sg = first_scapegoat(revs, commit); i < num_sg && sg; sg = sg->next, i++) { struct origin *porigin = sg_origin[i]; @@ -1284,7 +1288,7 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) * Optionally find moves in parents' files. */ if (opt & PICKAXE_BLAME_MOVE) - for (i = 0, sg = first_scapegoat(commit); + for (i = 0, sg = first_scapegoat(revs, commit); i < num_sg && sg; sg = sg->next, i++) { struct origin *porigin = sg_origin[i]; @@ -1298,7 +1302,7 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt) * Optionally find copies from parents' files. */ if (opt & PICKAXE_BLAME_COPY) - for (i = 0, sg = first_scapegoat(commit); + for (i = 0, sg = first_scapegoat(revs, commit); i < num_sg && sg; sg = sg->next, i++) { struct origin *porigin = sg_origin[i]; @@ -1515,8 +1519,10 @@ static void found_guilty_entry(struct blame_entry *ent) * is still unknown, pick one blame_entry, and allow its current * suspect to pass blames to its parents. */ -static void assign_blame(struct scoreboard *sb, struct rev_info *revs, int opt) +static void assign_blame(struct scoreboard *sb, int opt) { + struct rev_info *revs = sb->revs; + while (1) { struct blame_entry *ent; struct commit *commit; @@ -1537,8 +1543,9 @@ static void assign_blame(struct scoreboard *sb, struct rev_info *revs, int opt) commit = suspect->commit; if (!commit->object.parsed) parse_commit(commit); - if (!(commit->object.flags & UNINTERESTING) && - !(revs->max_age != -1 && commit->date < revs->max_age)) + if (reverse || + (!(commit->object.flags & UNINTERESTING) && + !(revs->max_age != -1 && commit->date < revs->max_age))) pass_blame(sb, suspect, opt); else { commit->object.flags |= UNINTERESTING; @@ -2154,10 +2161,11 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con return commit; } -static const char *prepare_final(struct scoreboard *sb, struct rev_info *revs) +static const char *prepare_final(struct scoreboard *sb) { int i; const char *final_commit_name = NULL; + struct rev_info *revs = sb->revs; /* * There must be one and only one positive commit in the @@ -2181,6 +2189,36 @@ static const char *prepare_final(struct scoreboard *sb, struct rev_info *revs) return final_commit_name; } +static const char *prepare_initial(struct scoreboard *sb) +{ + int i; + const char *final_commit_name = NULL; + struct rev_info *revs = sb->revs; + + /* + * There must be one and only one negative commit, and it must be + * the boundary. + */ + for (i = 0; i < revs->pending.nr; i++) { + struct object *obj = revs->pending.objects[i].item; + if (!(obj->flags & UNINTERESTING)) + continue; + while (obj->type == OBJ_TAG) + obj = deref_tag(obj, NULL, 0); + if (obj->type != OBJ_COMMIT) + die("Non commit %s?", revs->pending.objects[i].name); + if (sb->final) + die("More than one commit to dig down to %s and %s?", + revs->pending.objects[i].name, + final_commit_name); + sb->final = (struct commit *) obj; + final_commit_name = revs->pending.objects[i].name; + } + if (!final_commit_name) + die("No commit to dig down to?"); + return final_commit_name; +} + int cmd_blame(int argc, const char **argv, const char *prefix) { struct rev_info revs; @@ -2213,6 +2251,10 @@ int cmd_blame(int argc, const char **argv, const char *prefix) blank_boundary = 1; else if (!strcmp("--root", arg)) show_root = 1; + else if (!strcmp("--reverse", arg)) { + argv[unk++] = "--children"; + reverse = 1; + } else if (!strcmp(arg, "--show-stats")) show_stats = 1; else if (!strcmp("-c", arg)) @@ -2386,7 +2428,14 @@ int cmd_blame(int argc, const char **argv, const char *prefix) setup_revisions(unk, argv, &revs, NULL); memset(&sb, 0, sizeof(sb)); - final_commit_name = prepare_final(&sb, &revs); + sb.revs = &revs; + if (!reverse) + final_commit_name = prepare_final(&sb); + else if (contents_from) + die("--contents and --children do not blend well."); + else + final_commit_name = prepare_initial(&sb); + if (!sb.final) { /* * "--not A B -- path" without anything positive; @@ -2464,7 +2513,7 @@ int cmd_blame(int argc, const char **argv, const char *prefix) if (!incremental) setup_pager(); - assign_blame(&sb, &revs, opt); + assign_blame(&sb, opt); if (incremental) return 0; From ae299be0e5e610027e6492d48d70c1cbb0e9edd8 Mon Sep 17 00:00:00 2001 From: David Reiss Date: Mon, 19 May 2008 23:48:54 -0700 Subject: [PATCH 006/295] Implement normalize_absolute_path normalize_absolute_path removes several oddities form absolute paths, giving nice clean paths like "/dir/sub1/sub2". Also add a test case for this utility, based on a new test program (in the style of test-sha1). Signed-off-by: David Reiss Signed-off-by: Junio C Hamano --- .gitignore | 1 + Makefile | 2 +- cache.h | 1 + path.c | 53 +++++++++++++++++++++++++++++++++++++++++++ t/t0060-path-utils.sh | 40 ++++++++++++++++++++++++++++++++ test-path-utils.c | 13 +++++++++++ 6 files changed, 109 insertions(+), 1 deletion(-) create mode 100755 t/t0060-path-utils.sh create mode 100644 test-path-utils.c diff --git a/.gitignore b/.gitignore index 4ff2fec278..c54c473e94 100644 --- a/.gitignore +++ b/.gitignore @@ -150,6 +150,7 @@ test-dump-cache-tree test-genrandom test-match-trees test-parse-options +test-path-utils test-sha1 common-cmds.h *.tar.gz diff --git a/Makefile b/Makefile index a2de075799..ada85686ea 100644 --- a/Makefile +++ b/Makefile @@ -1186,7 +1186,7 @@ endif ### Testing rules -TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-absolute-path$X test-parse-options$X +TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-absolute-path$X test-parse-options$X test-path-utils$X all:: $(TEST_PROGRAMS) diff --git a/cache.h b/cache.h index 093f04cec0..88c390d9f1 100644 --- a/cache.h +++ b/cache.h @@ -514,6 +514,7 @@ static inline int is_absolute_path(const char *path) return path[0] == '/'; } const char *make_absolute_path(const char *path); +int normalize_absolute_path(char *buf, const char *path); /* Read and unpack a sha1 file into memory, write memory to a sha1 file */ extern int sha1_object_info(const unsigned char *, unsigned long *); diff --git a/path.c b/path.c index b7c24a2aac..7175a06ed8 100644 --- a/path.c +++ b/path.c @@ -357,3 +357,56 @@ const char *make_absolute_path(const char *path) return buf; } + +/* + * path = absolute path + * buf = buffer of at least max(2, strlen(path)+1) bytes + * It is okay if buf == path, but they should not overlap otherwise. + * + * Performs the following normalizations on path, storing the result in buf: + * - Removes trailing slashes. + * - Removes empty components. + * - Removes "." components. + * - Removes ".." components, and the components the precede them. + * "" and paths that contain only slashes are normalized to "/". + * Returns the length of the output. + * + * Note that this function is purely textual. It does not follow symlinks, + * verify the existence of the path, or make any system calls. + */ +int normalize_absolute_path(char *buf, const char *path) +{ + const char *comp_start = path, *comp_end = path; + char *dst = buf; + int comp_len; + assert(buf); + assert(path); + + while (*comp_start) { + assert(*comp_start == '/'); + while (*++comp_end && *comp_end != '/') + ; /* nothing */ + comp_len = comp_end - comp_start; + + if (!strncmp("/", comp_start, comp_len) || + !strncmp("/.", comp_start, comp_len)) + goto next; + + if (!strncmp("/..", comp_start, comp_len)) { + while (dst > buf && *--dst != '/') + ; /* nothing */ + goto next; + } + + memcpy(dst, comp_start, comp_len); + dst += comp_len; + next: + comp_start = comp_end; + } + + if (dst == buf) + *dst++ = '/'; + + *dst = '\0'; + return dst - buf; +} diff --git a/t/t0060-path-utils.sh b/t/t0060-path-utils.sh new file mode 100755 index 0000000000..9076b3bd81 --- /dev/null +++ b/t/t0060-path-utils.sh @@ -0,0 +1,40 @@ +#!/bin/sh +# +# Copyright (c) 2008 David Reiss +# + +test_description='Test various path utilities' + +. ./test-lib.sh + +norm_abs() { + test_expect_success "normalize absolute" \ + "test \$(test-path-utils normalize_absolute_path '$1') = '$2'" +} + +norm_abs "" / +norm_abs / / +norm_abs // / +norm_abs /// / +norm_abs /. / +norm_abs /./ / +norm_abs /./.. / +norm_abs /../. / +norm_abs /./../.// / +norm_abs /dir/.. / +norm_abs /dir/sub/../.. / +norm_abs /dir /dir +norm_abs /dir// /dir +norm_abs /./dir /dir +norm_abs /dir/. /dir +norm_abs /dir///./ /dir +norm_abs /dir//sub/.. /dir +norm_abs /dir/sub/../ /dir +norm_abs //dir/sub/../. /dir +norm_abs /dir/s1/../s2/ /dir/s2 +norm_abs /d1/s1///s2/..//../s3/ /d1/s3 +norm_abs /d1/s1//../s2/../../d2 /d2 +norm_abs /d1/.../d2 /d1/.../d2 +norm_abs /d1/..././../d2 /d1/d2 + +test_done diff --git a/test-path-utils.c b/test-path-utils.c new file mode 100644 index 0000000000..1bd43216f6 --- /dev/null +++ b/test-path-utils.c @@ -0,0 +1,13 @@ +#include "cache.h" + +int main(int argc, char **argv) +{ + if (argc == 3 && !strcmp(argv[1], "normalize_absolute_path")) { + char *buf = xmalloc(strlen(argv[2])+1); + int rv = normalize_absolute_path(buf, argv[2]); + assert(strlen(buf) == rv); + puts(buf); + } + + return 0; +} From d553e737897e8edbbc2092bf345fc58b2dae5251 Mon Sep 17 00:00:00 2001 From: David Reiss Date: Mon, 19 May 2008 23:49:00 -0700 Subject: [PATCH 007/295] Fold test-absolute-path into test-path-utils Signed-off-by: David Reiss Signed-off-by: Junio C Hamano --- .gitignore | 1 - Makefile | 2 +- t/t0000-basic.sh | 8 ++++---- test-absolute-path.c | 11 ----------- test-path-utils.c | 8 ++++++++ 5 files changed, 13 insertions(+), 17 deletions(-) delete mode 100644 test-absolute-path.c diff --git a/.gitignore b/.gitignore index c54c473e94..31ea9f13ba 100644 --- a/.gitignore +++ b/.gitignore @@ -142,7 +142,6 @@ git-write-tree git-core-*/?* gitk-wish gitweb/gitweb.cgi -test-absolute-path test-chmtime test-date test-delta diff --git a/Makefile b/Makefile index ada85686ea..c1903b68a8 100644 --- a/Makefile +++ b/Makefile @@ -1186,7 +1186,7 @@ endif ### Testing rules -TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-absolute-path$X test-parse-options$X test-path-utils$X +TEST_PROGRAMS = test-chmtime$X test-genrandom$X test-date$X test-delta$X test-sha1$X test-match-trees$X test-parse-options$X test-path-utils$X all:: $(TEST_PROGRAMS) diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh index 690f80ab27..d7cbc5c6da 100755 --- a/t/t0000-basic.sh +++ b/t/t0000-basic.sh @@ -301,14 +301,14 @@ test_expect_success 'absolute path works as expected' ' mkdir third && dir="$(cd .git; pwd -P)" && dir2=third/../second/other/.git && - test "$dir" = "$(test-absolute-path $dir2)" && + test "$dir" = "$(test-path-utils make_absolute_path $dir2)" && file="$dir"/index && - test "$file" = "$(test-absolute-path $dir2/index)" && + test "$file" = "$(test-path-utils make_absolute_path $dir2/index)" && basename=blub && - test "$dir/$basename" = "$(cd .git && test-absolute-path "$basename")" && + test "$dir/$basename" = "$(cd .git && test-path-utils make_absolute_path "$basename")" && ln -s ../first/file .git/syml && sym="$(cd first; pwd -P)"/file && - test "$sym" = "$(test-absolute-path "$dir2/syml")" + test "$sym" = "$(test-path-utils make_absolute_path "$dir2/syml")" ' test_expect_success 'very long name in the index handled sanely' ' diff --git a/test-absolute-path.c b/test-absolute-path.c deleted file mode 100644 index c959ea20d3..0000000000 --- a/test-absolute-path.c +++ /dev/null @@ -1,11 +0,0 @@ -#include "cache.h" - -int main(int argc, char **argv) -{ - while (argc > 1) { - puts(make_absolute_path(argv[1])); - argc--; - argv++; - } - return 0; -} diff --git a/test-path-utils.c b/test-path-utils.c index 1bd43216f6..842b58018f 100644 --- a/test-path-utils.c +++ b/test-path-utils.c @@ -9,5 +9,13 @@ int main(int argc, char **argv) puts(buf); } + if (argc >= 2 && !strcmp(argv[1], "make_absolute_path")) { + while (argc > 2) { + puts(make_absolute_path(argv[2])); + argc--; + argv++; + } + } + return 0; } From 0454dd93bfb2334355ec62fff670d8c6cb3570a1 Mon Sep 17 00:00:00 2001 From: David Reiss Date: Mon, 19 May 2008 23:49:26 -0700 Subject: [PATCH 008/295] Add support for GIT_CEILING_DIRECTORIES Make git recognize a new environment variable that prevents it from chdir'ing up into specified directories when looking for a GIT_DIR. Useful for avoiding slow network directories. For example, I use git in an environment where homedirs are automounted and "ls /home/nonexistent" takes about 9 seconds. Setting GIT_CEILING_DIRS="/home" allows "git help -a" (for bash completion) and "git symbolic-ref" (for my shell prompt) to run in a reasonable time. Signed-off-by: David Reiss Signed-off-by: Junio C Hamano --- Documentation/git.txt | 8 ++ cache.h | 2 + path.c | 43 +++++++++++ setup.c | 24 +++--- t/t0060-path-utils.sh | 47 ++++++++++++ t/t1504-ceiling-dirs.sh | 163 ++++++++++++++++++++++++++++++++++++++++ t/test-lib.sh | 1 + test-path-utils.c | 5 ++ 8 files changed, 282 insertions(+), 11 deletions(-) create mode 100755 t/t1504-ceiling-dirs.sh diff --git a/Documentation/git.txt b/Documentation/git.txt index adcd3e00b2..4ffe802371 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -415,6 +415,14 @@ git so take care if using Cogito etc. This can also be controlled by the '--work-tree' command line option and the core.worktree configuration variable. +'GIT_CEILING_DIRECTORIES':: + This should be a colon-separated list of absolute paths. + If set, it is a list of directories that git should not chdir + up into while looking for a repository directory. + It will not exclude the current working directory or + a GIT_DIR set on the command line or in the environment. + (Useful for excluding slow-loading network directories.) + git Commits ~~~~~~~~~~~ 'GIT_AUTHOR_NAME':: diff --git a/cache.h b/cache.h index 88c390d9f1..833f4cd982 100644 --- a/cache.h +++ b/cache.h @@ -300,6 +300,7 @@ static inline enum object_type object_type(unsigned int mode) #define CONFIG_ENVIRONMENT "GIT_CONFIG" #define CONFIG_LOCAL_ENVIRONMENT "GIT_CONFIG_LOCAL" #define EXEC_PATH_ENVIRONMENT "GIT_EXEC_PATH" +#define CEILING_DIRECTORIES_ENVIRONMENT "GIT_CEILING_DIRECTORIES" #define GITATTRIBUTES_FILE ".gitattributes" #define INFOATTRIBUTES_FILE "info/attributes" #define ATTRIBUTE_MACRO_PREFIX "[attr]" @@ -515,6 +516,7 @@ static inline int is_absolute_path(const char *path) } const char *make_absolute_path(const char *path); int normalize_absolute_path(char *buf, const char *path); +int longest_ancestor_length(const char *path, const char *prefix_list); /* Read and unpack a sha1 file into memory, write memory to a sha1 file */ extern int sha1_object_info(const unsigned char *, unsigned long *); diff --git a/path.c b/path.c index 7175a06ed8..0c4330486b 100644 --- a/path.c +++ b/path.c @@ -410,3 +410,46 @@ int normalize_absolute_path(char *buf, const char *path) *dst = '\0'; return dst - buf; } + +/* + * path = Canonical absolute path + * prefix_list = Colon-separated list of absolute paths + * + * Determines, for each path in parent_list, whether the "prefix" really + * is an ancestor directory of path. Returns the length of the longest + * ancestor directory, excluding any trailing slashes, or -1 if no prefix + * is an ancestor. (Note that this means 0 is returned if prefix_list is + * "/".) "/foo" is not considered an ancestor of "/foobar". Directories + * are not considered to be their own ancestors. path must be in a + * canonical form: empty components, or "." or ".." components are not + * allowed. prefix_list may be null, which is like "". + */ +int longest_ancestor_length(const char *path, const char *prefix_list) +{ + char buf[PATH_MAX+1]; + const char *ceil, *colon; + int len, max_len = -1; + + if (prefix_list == NULL || !strcmp(path, "/")) + return -1; + + for (colon = ceil = prefix_list; *colon; ceil = colon+1) { + for (colon = ceil; *colon && *colon != ':'; colon++); + len = colon - ceil; + if (len == 0 || len > PATH_MAX || !is_absolute_path(ceil)) + continue; + strlcpy(buf, ceil, len+1); + len = normalize_absolute_path(buf, buf); + /* Strip "trailing slashes" from "/". */ + if (len == 1) + len = 0; + + if (!strncmp(path, buf, len) && + path[len] == '/' && + len > max_len) { + max_len = len; + } + } + + return max_len; +} diff --git a/setup.c b/setup.c index b8fd476395..c14b10636f 100644 --- a/setup.c +++ b/setup.c @@ -359,10 +359,11 @@ const char *read_gitfile_gently(const char *path) const char *setup_git_directory_gently(int *nongit_ok) { const char *work_tree_env = getenv(GIT_WORK_TREE_ENVIRONMENT); + const char *env_ceiling_dirs = getenv(CEILING_DIRECTORIES_ENVIRONMENT); static char cwd[PATH_MAX+1]; const char *gitdirenv; const char *gitfile_dir; - int len, offset; + int len, offset, ceil_offset; /* * Let's assume that we are in a git repository. @@ -414,6 +415,8 @@ const char *setup_git_directory_gently(int *nongit_ok) if (!getcwd(cwd, sizeof(cwd)-1)) die("Unable to read current working directory"); + ceil_offset = longest_ancestor_length(cwd, env_ceiling_dirs); + /* * Test in the following order (relative to the cwd): * - .git (file containing "gitdir: ") @@ -444,17 +447,16 @@ const char *setup_git_directory_gently(int *nongit_ok) return NULL; } chdir(".."); - do { - if (!offset) { - if (nongit_ok) { - if (chdir(cwd)) - die("Cannot come back to cwd"); - *nongit_ok = 1; - return NULL; - } - die("Not a git repository"); + while (--offset > ceil_offset && cwd[offset] != '/'); + if (offset <= ceil_offset) { + if (nongit_ok) { + if (chdir(cwd)) + die("Cannot come back to cwd"); + *nongit_ok = 1; + return NULL; } - } while (cwd[--offset] != '/'); + die("Not a git repository"); + } } inside_git_dir = 0; diff --git a/t/t0060-path-utils.sh b/t/t0060-path-utils.sh index 9076b3bd81..6e7501f352 100755 --- a/t/t0060-path-utils.sh +++ b/t/t0060-path-utils.sh @@ -12,6 +12,11 @@ norm_abs() { "test \$(test-path-utils normalize_absolute_path '$1') = '$2'" } +ancestor() { + test_expect_success "longest ancestor" \ + "test \$(test-path-utils longest_ancestor_length '$1' '$2') = '$3'" +} + norm_abs "" / norm_abs / / norm_abs // / @@ -37,4 +42,46 @@ norm_abs /d1/s1//../s2/../../d2 /d2 norm_abs /d1/.../d2 /d1/.../d2 norm_abs /d1/..././../d2 /d1/d2 +ancestor / "" -1 +ancestor / / -1 +ancestor /foo "" -1 +ancestor /foo : -1 +ancestor /foo ::. -1 +ancestor /foo ::..:: -1 +ancestor /foo / 0 +ancestor /foo /fo -1 +ancestor /foo /foo -1 +ancestor /foo /foo/ -1 +ancestor /foo /bar -1 +ancestor /foo /bar/ -1 +ancestor /foo /foo/bar -1 +ancestor /foo /foo:/bar/ -1 +ancestor /foo /foo/:/bar/ -1 +ancestor /foo /foo::/bar/ -1 +ancestor /foo /:/foo:/bar/ 0 +ancestor /foo /foo:/:/bar/ 0 +ancestor /foo /:/bar/:/foo 0 +ancestor /foo/bar "" -1 +ancestor /foo/bar / 0 +ancestor /foo/bar /fo -1 +ancestor /foo/bar foo -1 +ancestor /foo/bar /foo 4 +ancestor /foo/bar /foo/ 4 +ancestor /foo/bar /foo/ba -1 +ancestor /foo/bar /:/fo 0 +ancestor /foo/bar /foo:/foo/ba 4 +ancestor /foo/bar /bar -1 +ancestor /foo/bar /bar/ -1 +ancestor /foo/bar /fo: -1 +ancestor /foo/bar :/fo -1 +ancestor /foo/bar /foo:/bar/ 4 +ancestor /foo/bar /:/foo:/bar/ 4 +ancestor /foo/bar /foo:/:/bar/ 4 +ancestor /foo/bar /:/bar/:/fo 0 +ancestor /foo/bar /:/bar/ 0 +ancestor /foo/bar :://foo/. 4 +ancestor /foo/bar :://foo/.:: 4 +ancestor /foo/bar //foo/./::/bar 4 +ancestor /foo/bar ::/bar -1 + test_done diff --git a/t/t1504-ceiling-dirs.sh b/t/t1504-ceiling-dirs.sh new file mode 100755 index 0000000000..91b704a3a4 --- /dev/null +++ b/t/t1504-ceiling-dirs.sh @@ -0,0 +1,163 @@ +#!/bin/sh + +test_description='test GIT_CEILING_DIRECTORIES' +. ./test-lib.sh + +test_prefix() { + test_expect_success "$1" \ + "test '$2' = \"\$(git rev-parse --show-prefix)\"" +} + +test_fail() { + test_expect_code 128 "$1: prefix" \ + "git rev-parse --show-prefix" +} + +TRASH_ROOT="$(pwd)" +ROOT_PARENT=$(dirname "$TRASH_ROOT") + + +unset GIT_CEILING_DIRECTORIES +test_prefix no_ceil "" + +export GIT_CEILING_DIRECTORIES + +GIT_CEILING_DIRECTORIES="" +test_prefix ceil_empty "" + +GIT_CEILING_DIRECTORIES="$ROOT_PARENT" +test_prefix ceil_at_parent "" + +GIT_CEILING_DIRECTORIES="$ROOT_PARENT/" +test_prefix ceil_at_parent_slash "" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT" +test_prefix ceil_at_trash "" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/" +test_prefix ceil_at_trash_slash "" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub" +test_prefix ceil_at_sub "" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/" +test_prefix ceil_at_sub_slash "" + + +mkdir -p sub/dir || exit 1 +cd sub/dir || exit 1 + +unset GIT_CEILING_DIRECTORIES +test_prefix subdir_no_ceil "sub/dir/" + +export GIT_CEILING_DIRECTORIES + +GIT_CEILING_DIRECTORIES="" +test_prefix subdir_ceil_empty "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT" +test_fail subdir_ceil_at_trash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/" +test_fail subdir_ceil_at_trash_slash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub" +test_fail subdir_ceil_at_sub + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/" +test_fail subdir_ceil_at_sub_slash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/dir" +test_prefix subdir_ceil_at_subdir "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/dir/" +test_prefix subdir_ceil_at_subdir_slash "sub/dir/" + + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/su" +test_prefix subdir_ceil_at_su "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/su/" +test_prefix subdir_ceil_at_su_slash "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/di" +test_prefix subdir_ceil_at_sub_di "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub/di" +test_prefix subdir_ceil_at_sub_di_slash "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/subdi" +test_prefix subdir_ceil_at_subdi "sub/dir/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/subdi" +test_prefix subdir_ceil_at_subdi_slash "sub/dir/" + + +GIT_CEILING_DIRECTORIES="foo:$TRASH_ROOT/sub" +test_fail second_of_two + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub:bar" +test_fail first_of_two + +GIT_CEILING_DIRECTORIES="foo:$TRASH_ROOT/sub:bar" +test_fail second_of_three + + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sub" +GIT_DIR=../../.git +export GIT_DIR +test_prefix git_dir_specified "" +unset GIT_DIR + + +cd ../.. || exit 1 +mkdir -p s/d || exit 1 +cd s/d || exit 1 + +unset GIT_CEILING_DIRECTORIES +test_prefix sd_no_ceil "s/d/" + +export GIT_CEILING_DIRECTORIES + +GIT_CEILING_DIRECTORIES="" +test_prefix sd_ceil_empty "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT" +test_fail sd_ceil_at_trash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/" +test_fail sd_ceil_at_trash_slash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s" +test_fail sd_ceil_at_s + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s/" +test_fail sd_ceil_at_s_slash + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s/d" +test_prefix sd_ceil_at_sd "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s/d/" +test_prefix sd_ceil_at_sd_slash "s/d/" + + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/su" +test_prefix sd_ceil_at_su "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/su/" +test_prefix sd_ceil_at_su_slash "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s/di" +test_prefix sd_ceil_at_s_di "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/s/di" +test_prefix sd_ceil_at_s_di_slash "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sdi" +test_prefix sd_ceil_at_sdi "s/d/" + +GIT_CEILING_DIRECTORIES="$TRASH_ROOT/sdi" +test_prefix sd_ceil_at_sdi_slash "s/d/" + + +test_done diff --git a/t/test-lib.sh b/t/test-lib.sh index 5002fb04b5..c3a3167382 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -35,6 +35,7 @@ unset GIT_WORK_TREE unset GIT_EXTERNAL_DIFF unset GIT_INDEX_FILE unset GIT_OBJECT_DIRECTORY +unset GIT_CEILING_DIRECTORIES unset SHA1_FILE_DIRECTORIES unset SHA1_FILE_DIRECTORY GIT_MERGE_VERBOSITY=5 diff --git a/test-path-utils.c b/test-path-utils.c index 842b58018f..a0bcb0e210 100644 --- a/test-path-utils.c +++ b/test-path-utils.c @@ -17,5 +17,10 @@ int main(int argc, char **argv) } } + if (argc == 4 && !strcmp(argv[1], "longest_ancestor_length")) { + int len = longest_ancestor_length(argv[2], argv[3]); + printf("%d\n", len); + } + return 0; } From 450f437fb0fe276a6e946c281c768118e39dc9e7 Mon Sep 17 00:00:00 2001 From: David Reiss Date: Mon, 19 May 2008 23:49:34 -0700 Subject: [PATCH 009/295] Eliminate an unnecessary chdir("..") In the case where setup_git_directory_gently fails, avoid the last chdir("..") by moving it after the ceil_offset check. Signed-off-by: David Reiss Signed-off-by: Junio C Hamano --- setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.c b/setup.c index c14b10636f..045ca20b32 100644 --- a/setup.c +++ b/setup.c @@ -446,7 +446,6 @@ const char *setup_git_directory_gently(int *nongit_ok) check_repository_format_gently(nongit_ok); return NULL; } - chdir(".."); while (--offset > ceil_offset && cwd[offset] != '/'); if (offset <= ceil_offset) { if (nongit_ok) { @@ -457,6 +456,7 @@ const char *setup_git_directory_gently(int *nongit_ok) } die("Not a git repository"); } + chdir(".."); } inside_git_dir = 0; From 973a70ea4d9fc98e9ed20c261c5f6c8f1c1df2b0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Karl=20Hasselstr=C3=B6m?= Date: Tue, 3 Jun 2008 01:34:48 +0200 Subject: [PATCH 010/295] Clean up builtin-update-ref's option parsing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit builtin-update-ref's option parsing was somewhat tricky to follow, especially if the -d option was given. This patch cleans it upp a bit, at the expense of making it a bit longer. Signed-off-by: Karl Hasselström Signed-off-by: Junio C Hamano --- builtin-update-ref.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/builtin-update-ref.c b/builtin-update-ref.c index 93c127196d..1e714a3c93 100644 --- a/builtin-update-ref.c +++ b/builtin-update-ref.c @@ -11,7 +11,7 @@ static const char * const git_update_ref_usage[] = { int cmd_update_ref(int argc, const char **argv, const char *prefix) { - const char *refname, *value, *oldval, *msg=NULL; + const char *refname, *oldval, *msg=NULL; unsigned char sha1[20], oldsha1[20]; int delete = 0, no_deref = 0; struct option options[] = { @@ -27,25 +27,29 @@ int cmd_update_ref(int argc, const char **argv, const char *prefix) if (msg && !*msg) die("Refusing to perform update with empty message."); - if (argc < 2 || argc > 3) - usage_with_options(git_update_ref_usage, options); - refname = argv[0]; - value = argv[1]; - oldval = argv[2]; - - if (get_sha1(value, sha1)) - die("%s: not a valid SHA1", value); - if (delete) { - if (oldval) + if (argc != 2) usage_with_options(git_update_ref_usage, options); - return delete_ref(refname, sha1); + refname = argv[0]; + oldval = argv[1]; + } else { + const char *value; + if (argc < 2 || argc > 3) + usage_with_options(git_update_ref_usage, options); + refname = argv[0]; + value = argv[1]; + oldval = argv[2]; + if (get_sha1(value, sha1)) + die("%s: not a valid SHA1", value); } - hashclr(oldsha1); + hashclr(oldsha1); /* all-zero hash in case oldval is the empty string */ if (oldval && *oldval && get_sha1(oldval, oldsha1)) die("%s: not a valid old SHA1", oldval); - return update_ref(msg, refname, sha1, oldval ? oldsha1 : NULL, - no_deref ? REF_NODEREF : 0, DIE_ON_ERR); + if (delete) + return delete_ref(refname, oldsha1); + else + return update_ref(msg, refname, sha1, oldval ? oldsha1 : NULL, + no_deref ? REF_NODEREF : 0, DIE_ON_ERR); } From 3fe8dce6fc5b1d0bffba8fdb4e075fcd16cf5619 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Karl=20Hasselstr=C3=B6m?= Date: Tue, 3 Jun 2008 01:34:53 +0200 Subject: [PATCH 011/295] Make old sha1 optional with git update-ref -d MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Giving the old sha1 is already optional when changing a ref, and it's quite handy when running update-ref manually. So make it optional for deleting a ref too. Signed-off-by: Karl Hasselström Signed-off-by: Junio C Hamano --- Documentation/git-update-ref.txt | 2 +- builtin-update-ref.c | 6 +++--- t/t1400-update-ref.sh | 8 ++++++++ 3 files changed, 12 insertions(+), 4 deletions(-) diff --git a/Documentation/git-update-ref.txt b/Documentation/git-update-ref.txt index 4dc475992e..80b94c36d9 100644 --- a/Documentation/git-update-ref.txt +++ b/Documentation/git-update-ref.txt @@ -7,7 +7,7 @@ git-update-ref - Update the object name stored in a ref safely SYNOPSIS -------- -'git-update-ref' [-m ] (-d | [--no-deref] []) +'git-update-ref' [-m ] (-d [] | [--no-deref] []) DESCRIPTION ----------- diff --git a/builtin-update-ref.c b/builtin-update-ref.c index 1e714a3c93..d90d11d2e3 100644 --- a/builtin-update-ref.c +++ b/builtin-update-ref.c @@ -4,7 +4,7 @@ #include "parse-options.h" static const char * const git_update_ref_usage[] = { - "git-update-ref [options] -d ", + "git-update-ref [options] -d []", "git-update-ref [options] []", NULL }; @@ -28,7 +28,7 @@ int cmd_update_ref(int argc, const char **argv, const char *prefix) die("Refusing to perform update with empty message."); if (delete) { - if (argc != 2) + if (argc < 1 || argc > 2) usage_with_options(git_update_ref_usage, options); refname = argv[0]; oldval = argv[1]; @@ -48,7 +48,7 @@ int cmd_update_ref(int argc, const char **argv, const char *prefix) die("%s: not a valid old SHA1", oldval); if (delete) - return delete_ref(refname, oldsha1); + return delete_ref(refname, oldval ? oldsha1 : NULL); else return update_ref(msg, refname, sha1, oldval ? oldsha1 : NULL, no_deref ? REF_NODEREF : 0, DIE_ON_ERR); diff --git a/t/t1400-update-ref.sh b/t/t1400-update-ref.sh index b8b7ab4103..f387d46f1a 100755 --- a/t/t1400-update-ref.sh +++ b/t/t1400-update-ref.sh @@ -42,6 +42,14 @@ test_expect_success "delete $m" ' ' rm -f .git/$m +test_expect_success "delete $m without oldvalue verification" " + git update-ref $m $A && + test $A = \$(cat .git/$m) && + git update-ref -d $m && + ! test -f .git/$m +" +rm -f .git/$m + test_expect_success \ "fail to create $n" \ "touch .git/$n_dir From 2d84e9fb6d281ed039bd67aafcdd8516a2b5226e Mon Sep 17 00:00:00 2001 From: Sverre Rabbelier Date: Sun, 8 Jun 2008 16:04:33 +0200 Subject: [PATCH 012/295] Modify test-lib.sh to output stats to t/test-results/* This change is needed order to aggregate data on the test run later on. Signed-off-by: Sverre Rabbelier Signed-off-by: Junio C Hamano --- t/Makefile | 2 +- t/test-lib.sh | 15 ++++++++++++++- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/t/Makefile b/t/Makefile index c6a60ab165..dfa90ace1a 100644 --- a/t/Makefile +++ b/t/Makefile @@ -20,7 +20,7 @@ $(T): @echo "*** $@ ***"; GIT_CONFIG=.git/config '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) clean: - $(RM) -r 'trash directory' + $(RM) -r 'trash directory' test-results # we can test NO_OPTIMIZE_COMMITS independently of LC_ALL full-svn-test: diff --git a/t/test-lib.sh b/t/test-lib.sh index 7a8bd27abc..2ad3f4a126 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -152,6 +152,7 @@ test_failure=0 test_count=0 test_fixed=0 test_broken=0 +test_success=0 die () { echo >&5 "FATAL: Unexpected exit with code $?" @@ -193,6 +194,7 @@ test_tick () { test_ok_ () { test_count=$(expr "$test_count" + 1) + test_success=$(expr "$test_success" + 1) say_color "" " ok $test_count: $@" } @@ -353,6 +355,16 @@ test_create_repo () { test_done () { trap - exit + test_results_dir="$TEST_DIRECTORY/test-results" + mkdir -p "$test_results_dir" + test_results_path="$test_results_dir/${0%-*}-$$" + + echo "total $test_count" >> $test_results_path + echo "success $test_success" >> $test_results_path + echo "fixed $test_fixed" >> $test_results_path + echo "broken $test_broken" >> $test_results_path + echo "failed $test_failure" >> $test_results_path + echo "" >> $test_results_path if test "$test_fixed" != 0 then @@ -387,7 +399,8 @@ test_done () { # Test the binaries we have just built. The tests are kept in # t/ subdirectory and are run in trash subdirectory. -PATH=$(pwd)/..:$PATH +TEST_DIRECTORY=$(pwd) +PATH=$TEST_DIRECTORY/..:$PATH GIT_EXEC_PATH=$(pwd)/.. GIT_TEMPLATE_DIR=$(pwd)/../templates/blt unset GIT_CONFIG From 0a392cb8cb4df41a82ac75e1052587b9a2c6f393 Mon Sep 17 00:00:00 2001 From: Miklos Vajna Date: Sun, 8 Jun 2008 16:04:34 +0200 Subject: [PATCH 013/295] A simple script to parse the results from the testcases This is a simple script that aggregates key:value pairs in a file. Signed-off-by: Miklos Vajna Signed-off-by: Junio C Hamano --- t/aggregate-results.sh | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) create mode 100755 t/aggregate-results.sh diff --git a/t/aggregate-results.sh b/t/aggregate-results.sh new file mode 100755 index 0000000000..52e88e3046 --- /dev/null +++ b/t/aggregate-results.sh @@ -0,0 +1,34 @@ +#!/bin/sh + +fixed=0 +success=0 +failed=0 +broken=0 +total=0 + +for file +do + while read type value + do + case $type in + '') + continue ;; + fixed) + fixed=$(($fixed + $value)) ;; + success) + success=$(($success + $value)) ;; + failed) + failed=$(($failed + $value)) ;; + broken) + broken=$(( $broken + $value)) ;; + total) + total=$(( $total + $value)) ;; + esac + done <"$file" +done + +printf "%-8s%d\n" fixed $fixed +printf "%-8s%d\n" success $success +printf "%-8s%d\n" failed $failed +printf "%-8s%d\n" broken $broken +printf "%-8s%d\n" total $total From f8d5ffc2c7c002cebb8842afcf58cbd4cea481b8 Mon Sep 17 00:00:00 2001 From: Sverre Rabbelier Date: Sun, 8 Jun 2008 16:04:35 +0200 Subject: [PATCH 014/295] Hook up the result aggregation in the test makefile. This patch makes 'make' output the aggregated results at the end of each build. The 'git-test-result' file is removed both before and after each build. Signed-off-by: Sverre Rabbelier Signed-off-by: Junio C Hamano --- t/Makefile | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/t/Makefile b/t/Makefile index dfa90ace1a..a778865ae7 100644 --- a/t/Makefile +++ b/t/Makefile @@ -14,18 +14,24 @@ SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) T = $(wildcard t[0-9][0-9][0-9][0-9]-*.sh) TSVN = $(wildcard t91[0-9][0-9]-*.sh) -all: $(T) clean +all: pre-clean $(T) aggregate-results clean $(T): @echo "*** $@ ***"; GIT_CONFIG=.git/config '$(SHELL_PATH_SQ)' $@ $(GIT_TEST_OPTS) +pre-clean: + $(RM) -r test-results + clean: $(RM) -r 'trash directory' test-results +aggregate-results: + ./aggregate-results.sh test-results/t*-* + # we can test NO_OPTIMIZE_COMMITS independently of LC_ALL full-svn-test: $(MAKE) $(TSVN) GIT_SVN_NO_OPTIMIZE_COMMITS=1 LC_ALL=C $(MAKE) $(TSVN) GIT_SVN_NO_OPTIMIZE_COMMITS=0 LC_ALL=en_US.UTF-8 -.PHONY: $(T) clean +.PHONY: pre-clean $(T) aggregate-results clean .NOTPARALLEL: From 008d896df5deaa967d4d86306b408333e8ef34c3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ren=C3=A9=20Scharfe?= Date: Sun, 8 Jun 2008 18:42:33 +0200 Subject: [PATCH 015/295] Teach new attribute 'export-ignore' to git-archive Paths marked with this attribute are not output to git-archive output. Signed-off-by: Rene Scharfe Signed-off-by: Junio C Hamano --- Documentation/gitattributes.txt | 6 ++++++ archive-tar.c | 2 ++ archive-zip.c | 2 ++ archive.c | 13 +++++++++++++ archive.h | 1 + t/t5000-tar-tree.sh | 9 +++++++++ 6 files changed, 33 insertions(+) diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt index 471754eb12..6e67990f64 100644 --- a/Documentation/gitattributes.txt +++ b/Documentation/gitattributes.txt @@ -502,6 +502,12 @@ frotz unspecified Creating an archive ~~~~~~~~~~~~~~~~~~~ +`export-ignore` +^^^^^^^^^^^^^^^ + +Files and directories with the attribute `export-ignore` won't be added to +archive files. + `export-subst` ^^^^^^^^^^^^^^ diff --git a/archive-tar.c b/archive-tar.c index d7598f907d..99db58f1cf 100644 --- a/archive-tar.c +++ b/archive-tar.c @@ -247,6 +247,8 @@ static int write_tar_entry(const unsigned char *sha1, strbuf_grow(&path, PATH_MAX); strbuf_add(&path, base, baselen); strbuf_addstr(&path, filename); + if (is_archive_path_ignored(path.buf + base_len)) + return 0; if (S_ISDIR(mode) || S_ISGITLINK(mode)) { strbuf_addch(&path, '/'); buffer = NULL; diff --git a/archive-zip.c b/archive-zip.c index 18c0f8710c..5742762ac3 100644 --- a/archive-zip.c +++ b/archive-zip.c @@ -176,6 +176,8 @@ static int write_zip_entry(const unsigned char *sha1, crc = crc32(0, NULL, 0); path = construct_path(base, baselen, filename, S_ISDIR(mode), &pathlen); + if (is_archive_path_ignored(path + base_len)) + return 0; if (verbose) fprintf(stderr, "%s\n", path); if (pathlen > 0xffff) { diff --git a/archive.c b/archive.c index 7a32c19d3c..6502b76ef1 100644 --- a/archive.c +++ b/archive.c @@ -82,3 +82,16 @@ void *sha1_file_to_archive(const char *path, const unsigned char *sha1, return buffer; } +int is_archive_path_ignored(const char *path) +{ + static struct git_attr *attr_export_ignore; + struct git_attr_check check[1]; + + if (!attr_export_ignore) + attr_export_ignore = git_attr("export-ignore", 13); + + check[0].attr = attr_export_ignore; + if (git_checkattr(path, ARRAY_SIZE(check), check)) + return 0; + return ATTR_TRUE(check[0].value); +} diff --git a/archive.h b/archive.h index 5791e657e9..ddf004acdf 100644 --- a/archive.h +++ b/archive.h @@ -44,5 +44,6 @@ extern int write_zip_archive(struct archiver_args *); extern void *parse_extra_zip_args(int argc, const char **argv); extern void *sha1_file_to_archive(const char *path, const unsigned char *sha1, unsigned int mode, enum object_type *type, unsigned long *size, const struct commit *commit); +extern int is_archive_path_ignored(const char *path); #endif /* ARCHIVE_H */ diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh index 9b0baac8db..3f1e25d921 100755 --- a/t/t5000-tar-tree.sh +++ b/t/t5000-tar-tree.sh @@ -44,6 +44,11 @@ test_expect_success \ echo text >file_with_long_path) && (cd a && find .) | sort >a.lst' +test_expect_success \ + 'add ignored file' \ + 'echo ignore me >a/ignored && + echo ignored export-ignore >.gitattributes' + test_expect_success \ 'add files to repository' \ 'find a -type f | xargs git update-index --add && @@ -53,6 +58,10 @@ test_expect_success \ git update-ref HEAD $(TZ=GMT GIT_COMMITTER_DATE="2005-05-27 22:00:00" \ git commit-tree $treeid b.tar' From 3a5b919cf220651b681b5f036bf3bd1c61e36ef2 Mon Sep 17 00:00:00 2001 From: Rafael Garcia-Suarez Date: Fri, 6 Jun 2008 09:53:32 +0200 Subject: [PATCH 016/295] gitweb: remove git_blame and rename git_blame2 to git_blame git_blame is dead code. It's possible to plug it in place of git_blame2, but I don't know whether anyone does still that, because git_blame2 can now be considered stable enough, I think. Signed-off-by: Rafael Garcia-Suarez Signed-off-by: Junio C Hamano --- gitweb/gitweb.perl | 101 +-------------------------------------------- 1 file changed, 2 insertions(+), 99 deletions(-) diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 198772c210..8d1f3e0547 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -539,7 +539,7 @@ $git_dir = "$projectroot/$project" if $project; # dispatch my %actions = ( - "blame" => \&git_blame2, + "blame" => \&git_blame, "blobdiff" => \&git_blobdiff, "blobdiff_plain" => \&git_blobdiff_plain, "blob" => \&git_blob, @@ -4152,7 +4152,7 @@ sub git_tag { git_footer_html(); } -sub git_blame2 { +sub git_blame { my $fd; my $ftype; @@ -4260,103 +4260,6 @@ HTML git_footer_html(); } -sub git_blame { - my $fd; - - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); - } - die_error('404 Not Found', "File name not defined") if (!$file_name); - $hash_base ||= git_get_head_hash($project); - die_error(undef, "Couldn't find base commit") unless ($hash_base); - my %co = parse_commit($hash_base) - or die_error(undef, "Reading commit failed"); - if (!defined $hash) { - $hash = git_get_hash_by_path($hash_base, $file_name, "blob") - or die_error(undef, "Error lookup file"); - } - open ($fd, "-|", git_cmd(), "annotate", '-l', '-t', '-r', $file_name, $hash_base) - or die_error(undef, "Open git-annotate failed"); - git_header_html(); - my $formats_nav = - $cgi->a({-href => href(action=>"blob", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "blob") . - " | " . - $cgi->a({-href => href(action=>"history", hash=>$hash, hash_base=>$hash_base, file_name=>$file_name)}, - "history") . - " | " . - $cgi->a({-href => href(action=>"blame", file_name=>$file_name)}, - "HEAD"); - git_print_page_nav('','', $hash_base,$co{'tree'},$hash_base, $formats_nav); - git_print_header_div('commit', esc_html($co{'title'}), $hash_base); - git_print_page_path($file_name, 'blob', $hash_base); - print "
\n"; - print < - - Commit - Age - Author - Line - Data - -HTML - my @line_class = (qw(light dark)); - my $line_class_len = scalar (@line_class); - my $line_class_num = $#line_class; - while (my $line = <$fd>) { - my $long_rev; - my $short_rev; - my $author; - my $time; - my $lineno; - my $data; - my $age; - my $age_str; - my $age_class; - - chomp $line; - $line_class_num = ($line_class_num + 1) % $line_class_len; - - if ($line =~ m/^([0-9a-fA-F]{40})\t\(\s*([^\t]+)\t(\d+) [+-]\d\d\d\d\t(\d+)\)(.*)$/) { - $long_rev = $1; - $author = $2; - $time = $3; - $lineno = $4; - $data = $5; - } else { - print qq( Unable to parse: $line\n); - next; - } - $short_rev = substr ($long_rev, 0, 8); - $age = time () - $time; - $age_str = age_string ($age); - $age_str =~ s/ / /g; - $age_class = age_class($age); - $author = esc_html ($author); - $author =~ s/ / /g; - - $data = untabify($data); - $data = esc_html ($data); - - print < - $long_rev)}" class="text">$short_rev.. - $age_str - $author - $lineno - $data - -HTML - } # while (my $line = <$fd>) - print "\n\n"; - close $fd - or print "Reading blob failed.\n"; - print "
"; - git_footer_html(); -} - sub git_tags { my $head = git_get_head_hash($project); git_header_html(); From 4bfee30a98783f7987c395e6006a2a6717344c04 Mon Sep 17 00:00:00 2001 From: Marius Storm-Olsen Date: Thu, 5 Jun 2008 10:31:19 +0200 Subject: [PATCH 017/295] Add an optional argument to commit/status -u|--untracked-files option This lets you specify how you want untracked files to be listed. The possible options are: normal - Show untracked files and directories all - Show all untracked files The 'all' mode is used, if the mode is not specified. Signed-off-by: Marius Storm-Olsen --- Documentation/git-commit.txt | 18 ++++++----- builtin-commit.c | 16 ++++++++-- t/t7502-status.sh | 61 ++++++++++++++++++++++++++++++++++++ wt-status.c | 1 + wt-status.h | 6 ++++ 5 files changed, 92 insertions(+), 10 deletions(-) diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index 02d4baab6d..e600e14be5 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -8,7 +8,7 @@ git-commit - Record changes to the repository SYNOPSIS -------- [verse] -'git-commit' [-a | --interactive] [-s] [-v] [-u] +'git-commit' [-a | --interactive] [-s] [-v] [-u[]] [(-c | -C) | -F | -m | --amend] [--allow-empty] [--no-verify] [-e] [--author ] [--cleanup=] [--] [[-i | -o ]...] @@ -150,12 +150,16 @@ but can be used to amend a merge commit. the last commit without committing changes that have already been staged. --u|--untracked-files:: - Show all untracked files, also those in uninteresting - directories, in the "Untracked files:" section of commit - message template. Without this option only its name and - a trailing slash are displayed for each untracked - directory. +-u[]|--untracked-files[=]:: + Show untracked files (Default: 'all'). ++ +The mode parameter is optional, and is used to specify +the handling of untracked files. The possible options are: ++ +-- + - 'normal' - Shows untracked files and directories + - 'all' - Also shows individual files in untracked directories. +-- -v|--verbose:: Show unified diff between the HEAD commit and what diff --git a/builtin-commit.c b/builtin-commit.c index 90200ed643..446a1086fd 100644 --- a/builtin-commit.c +++ b/builtin-commit.c @@ -49,7 +49,8 @@ static char *logfile, *force_author, *template_file; static char *edit_message, *use_message; static char *author_name, *author_email, *author_date; static int all, edit_flag, also, interactive, only, amend, signoff; -static int quiet, verbose, untracked_files, no_verify, allow_empty; +static int quiet, verbose, no_verify, allow_empty; +static char *untracked_files_arg; /* * The default commit message cleanup mode will remove the lines * beginning with # (shell comments) and leading and trailing @@ -102,7 +103,7 @@ static struct option builtin_commit_options[] = { OPT_BOOLEAN('o', "only", &only, "commit only specified files"), OPT_BOOLEAN('n', "no-verify", &no_verify, "bypass pre-commit hook"), OPT_BOOLEAN(0, "amend", &amend, "amend previous commit"), - OPT_BOOLEAN('u', "untracked-files", &untracked_files, "show all untracked files"), + { OPTION_STRING, 'u', "untracked-files", &untracked_files_arg, "mode", "show untracked files, optional modes: all, normal. (Default: all)", PARSE_OPT_OPTARG, NULL, (intptr_t)"all" }, OPT_BOOLEAN(0, "allow-empty", &allow_empty, "ok to record an empty change"), OPT_STRING(0, "cleanup", &cleanup_arg, "default", "how to strip spaces and #comments from message"), @@ -347,7 +348,7 @@ static int run_status(FILE *fp, const char *index_file, const char *prefix, int s.reference = "HEAD^1"; } s.verbose = verbose; - s.untracked = untracked_files; + s.untracked = (show_untracked_files == SHOW_ALL_UNTRACKED_FILES); s.index_file = index_file; s.fp = fp; s.nowarn = nowarn; @@ -795,6 +796,15 @@ static int parse_and_validate_options(int argc, const char *argv[], else die("Invalid cleanup mode %s", cleanup_arg); + if (!untracked_files_arg) + ; /* default already initialized */ + else if (!strcmp(untracked_files_arg, "normal")) + show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES; + else if (!strcmp(untracked_files_arg, "all")) + show_untracked_files = SHOW_ALL_UNTRACKED_FILES; + else + die("Invalid untracked files mode '%s'", untracked_files_arg); + if (all && argc > 0) die("Paths with -a does not make sense."); else if (interactive && argc > 0) diff --git a/t/t7502-status.sh b/t/t7502-status.sh index 80a438d4d9..0d24e259fb 100755 --- a/t/t7502-status.sh +++ b/t/t7502-status.sh @@ -67,6 +67,67 @@ test_expect_success 'status (2)' ' ' +cat >expect <..." to unstage) +# +# new file: dir2/added +# +# Changed but not updated: +# (use "git add ..." to update what will be committed) +# +# modified: dir1/modified +# +# Untracked files: +# (use "git add ..." to include in what will be committed) +# +# dir1/untracked +# dir2/modified +# dir2/untracked +# dir3/ +# expect +# output +# untracked +EOF +test_expect_success 'status -unormal' ' + mkdir dir3 && + : > dir3/untracked1 && + : > dir3/untracked2 && + git status -unormal >output && + test_cmp expect output +' + +cat >expect <..." to unstage) +# +# new file: dir2/added +# +# Changed but not updated: +# (use "git add ..." to update what will be committed) +# +# modified: dir1/modified +# +# Untracked files: +# (use "git add ..." to include in what will be committed) +# +# dir1/untracked +# dir2/modified +# dir2/untracked +# dir3/untracked1 +# dir3/untracked2 +# expect +# output +# untracked +EOF +test_expect_success 'status -uall' ' + git status -uall >output && + rm -rf dir3 && + test_cmp expect output +' + cat > expect << \EOF # On branch master # Changes to be committed: diff --git a/wt-status.c b/wt-status.c index 5b4d74c1f3..25d998513e 100644 --- a/wt-status.c +++ b/wt-status.c @@ -27,6 +27,7 @@ static const char use_add_rm_msg[] = "use \"git add/rm ...\" to update what will be committed"; static const char use_add_to_include_msg[] = "use \"git add ...\" to include in what will be committed"; +enum untracked_status_type show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES; static int parse_status_slot(const char *var, int offset) { diff --git a/wt-status.h b/wt-status.h index 597c7ea988..54f756de2b 100644 --- a/wt-status.h +++ b/wt-status.h @@ -11,6 +11,12 @@ enum color_wt_status { WT_STATUS_NOBRANCH, }; +enum untracked_status_type { + SHOW_NORMAL_UNTRACKED_FILES = 1, + SHOW_ALL_UNTRACKED_FILES +}; +extern enum untracked_status_type show_untracked_files; + struct wt_status { int is_initial; char *branch; From 6c2ce048bbfc6fbc2bdd86a3e586cb8881eb2dc2 Mon Sep 17 00:00:00 2001 From: Marius Storm-Olsen Date: Thu, 5 Jun 2008 14:22:56 +0200 Subject: [PATCH 018/295] Add argument 'no' commit/status option -u|--untracked-files This new argument teaches Git to not look for any untracked files, saving cycles on slow file systems, or large repos. Signed-off-by: Marius Storm-Olsen --- Documentation/git-commit.txt | 1 + builtin-commit.c | 4 +++- t/t7502-status.sh | 25 ++++++++++++++++++++++--- wt-status.c | 7 ++++++- wt-status.h | 3 ++- 5 files changed, 34 insertions(+), 6 deletions(-) diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index e600e14be5..a6f41f3663 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -157,6 +157,7 @@ The mode parameter is optional, and is used to specify the handling of untracked files. The possible options are: + -- + - 'no' - Show no untracked files - 'normal' - Shows untracked files and directories - 'all' - Also shows individual files in untracked directories. -- diff --git a/builtin-commit.c b/builtin-commit.c index 446a1086fd..0a70808280 100644 --- a/builtin-commit.c +++ b/builtin-commit.c @@ -103,7 +103,7 @@ static struct option builtin_commit_options[] = { OPT_BOOLEAN('o', "only", &only, "commit only specified files"), OPT_BOOLEAN('n', "no-verify", &no_verify, "bypass pre-commit hook"), OPT_BOOLEAN(0, "amend", &amend, "amend previous commit"), - { OPTION_STRING, 'u', "untracked-files", &untracked_files_arg, "mode", "show untracked files, optional modes: all, normal. (Default: all)", PARSE_OPT_OPTARG, NULL, (intptr_t)"all" }, + { OPTION_STRING, 'u', "untracked-files", &untracked_files_arg, "mode", "show untracked files, optional modes: all, normal, no. (Default: all)", PARSE_OPT_OPTARG, NULL, (intptr_t)"all" }, OPT_BOOLEAN(0, "allow-empty", &allow_empty, "ok to record an empty change"), OPT_STRING(0, "cleanup", &cleanup_arg, "default", "how to strip spaces and #comments from message"), @@ -798,6 +798,8 @@ static int parse_and_validate_options(int argc, const char *argv[], if (!untracked_files_arg) ; /* default already initialized */ + else if (!strcmp(untracked_files_arg, "no")) + show_untracked_files = SHOW_NO_UNTRACKED_FILES; else if (!strcmp(untracked_files_arg, "normal")) show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES; else if (!strcmp(untracked_files_arg, "all")) diff --git a/t/t7502-status.sh b/t/t7502-status.sh index 0d24e259fb..d84bda1dda 100755 --- a/t/t7502-status.sh +++ b/t/t7502-status.sh @@ -67,6 +67,28 @@ test_expect_success 'status (2)' ' ' +cat >expect <..." to unstage) +# +# new file: dir2/added +# +# Changed but not updated: +# (use "git add ..." to update what will be committed) +# +# modified: dir1/modified +# +# Untracked files not listed (use -u option to show untracked files) +EOF +test_expect_success 'status -uno' ' + mkdir dir3 && + : > dir3/untracked1 && + : > dir3/untracked2 && + git status -uno >output && + test_cmp expect output +' + cat >expect <expect < dir3/untracked1 && - : > dir3/untracked2 && git status -unormal >output && test_cmp expect output ' diff --git a/wt-status.c b/wt-status.c index 25d998513e..23017e4d46 100644 --- a/wt-status.c +++ b/wt-status.c @@ -348,7 +348,10 @@ void wt_status_print(struct wt_status *s) wt_status_print_changed(s); if (wt_status_submodule_summary) wt_status_print_submodule_summary(s); - wt_status_print_untracked(s); + if (show_untracked_files) + wt_status_print_untracked(s); + else if (s->commitable) + fprintf(s->fp, "# Untracked files not listed (use -u option to show untracked files)\n"); if (s->verbose && !s->is_initial) wt_status_print_verbose(s); @@ -363,6 +366,8 @@ void wt_status_print(struct wt_status *s) printf("nothing added to commit but untracked files present (use \"git add\" to track)\n"); else if (s->is_initial) printf("nothing to commit (create/copy files and use \"git add\" to track)\n"); + else if (!show_untracked_files) + printf("nothing to commit (use -u to show untracked files)\n"); else printf("nothing to commit (working directory clean)\n"); } diff --git a/wt-status.h b/wt-status.h index 54f756de2b..78add09bd6 100644 --- a/wt-status.h +++ b/wt-status.h @@ -12,7 +12,8 @@ enum color_wt_status { }; enum untracked_status_type { - SHOW_NORMAL_UNTRACKED_FILES = 1, + SHOW_NO_UNTRACKED_FILES, + SHOW_NORMAL_UNTRACKED_FILES, SHOW_ALL_UNTRACKED_FILES }; extern enum untracked_status_type show_untracked_files; From d6293d1f2cadcdf45f8ada7847a32b51fa5bf0a6 Mon Sep 17 00:00:00 2001 From: Marius Storm-Olsen Date: Thu, 5 Jun 2008 14:47:50 +0200 Subject: [PATCH 019/295] Add configuration option for default untracked files mode By default, the untracked files mode for commit/status is 'normal' Signed-off-by: Marius Storm-Olsen --- Documentation/config.txt | 19 +++++++++++++++++++ Documentation/git-commit.txt | 4 ++++ t/t7502-status.sh | 18 ++++++++++++++++++ wt-status.c | 13 +++++++++++++ 4 files changed, 54 insertions(+) diff --git a/Documentation/config.txt b/Documentation/config.txt index 5331b450ea..1e09a57c8c 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -1013,6 +1013,25 @@ status.relativePaths:: relative to the repository root (this was the default for git prior to v1.5.4). +status.showUntrackedFiles:: + By default, linkgit:git-status[1] and linkgit:git-commit[1] show + files which are not currently tracked by Git. Directories which + contain only untracked files, are shown with the directory name + only. Showing untracked files means that Git needs to lstat() all + all the files in the whole repository, which might be slow on some + systems. So, this variable controls how the commands displays + the untracked files. Possible values are: ++ +-- + - 'no' - Show no untracked files + - 'normal' - Shows untracked files and directories + - 'all' - Shows also individual files in untracked directories. +-- ++ +If this variable is not specified, it defaults to 'normal'. +This variable can be overridden with the -u|--untracked-files option +of linkgit:git-status[1] and linkgit:git-commit[1]. + tar.umask:: This variable can be used to restrict the permission bits of tar archive entries. The default is 0002, which turns off the diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index a6f41f3663..2e5ea22a40 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -161,6 +161,10 @@ the handling of untracked files. The possible options are: - 'normal' - Shows untracked files and directories - 'all' - Also shows individual files in untracked directories. -- ++ +See linkgit:git-config[1] for configuration variable +used to change the default for when the option is not +specified. -v|--verbose:: Show unified diff between the HEAD commit and what diff --git a/t/t7502-status.sh b/t/t7502-status.sh index d84bda1dda..38a48b57c7 100755 --- a/t/t7502-status.sh +++ b/t/t7502-status.sh @@ -89,6 +89,12 @@ test_expect_success 'status -uno' ' test_cmp expect output ' +test_expect_success 'status (status.showUntrackedFiles no)' ' + git config status.showuntrackedfiles no + git status >output && + test_cmp expect output +' + cat >expect <output && + test_cmp expect output +' + cat >expect <expect <output && + test_cmp expect output +' +test_expect_success 'status (status.showUntrackedFiles all)' ' + git config status.showuntrackedfiles all + git status >output && rm -rf dir3 && + git config --unset status.showuntrackedfiles && test_cmp expect output ' diff --git a/wt-status.c b/wt-status.c index 23017e4d46..28c9e637e3 100644 --- a/wt-status.c +++ b/wt-status.c @@ -397,5 +397,18 @@ int git_status_config(const char *k, const char *v, void *cb) wt_status_relative_paths = git_config_bool(k, v); return 0; } + if (!strcmp(k, "status.showuntrackedfiles")) { + if (!v) + return config_error_nonbool(v); + else if (!strcmp(v, "no")) + show_untracked_files = SHOW_NO_UNTRACKED_FILES; + else if (!strcmp(v, "normal")) + show_untracked_files = SHOW_NORMAL_UNTRACKED_FILES; + else if (!strcmp(v, "all")) + show_untracked_files = SHOW_ALL_UNTRACKED_FILES; + else + return error("Invalid untracked files mode '%s'", v); + return 0; + } return git_color_default_config(k, v, cb); } From 69913415655839b3add5d930ebbea1be8a5b60a9 Mon Sep 17 00:00:00 2001 From: Jakub Narebski Date: Tue, 10 Jun 2008 19:21:01 +0200 Subject: [PATCH 020/295] gitweb: Separate filling list of projects info Extract filling project list info, i.e. adding age, description, owner and forks information, into fill_project_list_info() subroutine. This is preparation for smart pagination and smart searching (to make it possible to calculate/generate info only for those projects which will be shown). Small changes compared to original version to improve readability (comments, names of variables, named loops). Additionally, store both full ('descr_long') and shortened ('descr') project description in Perl's internal form (using to_utf8). Signed-off-by: Jakub Narebski Signed-off-by: Junio C Hamano --- gitweb/gitweb.perl | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 198772c210..d7a9809027 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -3559,21 +3559,24 @@ sub git_patchset_body { # . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . -sub git_project_list_body { - my ($projlist, $order, $from, $to, $extra, $no_header) = @_; - - my ($check_forks) = gitweb_check_feature('forks'); - +# fills project list info (age, description, owner, forks) for each +# project in the list, removing invalid projects from returned list +# NOTE: modifies $projlist, but does not remove entries from it +sub fill_project_list_info { + my ($projlist, $check_forks) = @_; my @projects; + + PROJECT: foreach my $pr (@$projlist) { - my (@aa) = git_get_last_activity($pr->{'path'}); - unless (@aa) { - next; + my (@activity) = git_get_last_activity($pr->{'path'}); + unless (@activity) { + next PROJECT; } - ($pr->{'age'}, $pr->{'age_string'}) = @aa; + ($pr->{'age'}, $pr->{'age_string'}) = @activity; if (!defined $pr->{'descr'}) { my $descr = git_get_project_description($pr->{'path'}) || ""; - $pr->{'descr_long'} = to_utf8($descr); + $descr = to_utf8($descr); + $pr->{'descr_long'} = $descr; $pr->{'descr'} = chop_str($descr, $projects_list_description_width, 5); } if (!defined $pr->{'owner'}) { @@ -3585,14 +3588,22 @@ sub git_project_list_body { ($pname !~ /\/$/) && (-d "$projectroot/$pname")) { $pr->{'forks'} = "-d $projectroot/$pname"; - } - else { + } else { $pr->{'forks'} = 0; } } push @projects, $pr; } + return @projects; +} + +sub git_project_list_body { + my ($projlist, $order, $from, $to, $extra, $no_header) = @_; + + my ($check_forks) = gitweb_check_feature('forks'); + my @projects = fill_project_list_info($projlist, $check_forks); + $order ||= $default_projects_order; $from = 0 unless defined $from; $to = $#projects if (!defined $to || $#projects < $to); From 7da0f3a46daac50782a71e8a6eb12355d49c419d Mon Sep 17 00:00:00 2001 From: Jakub Narebski Date: Tue, 10 Jun 2008 19:21:44 +0200 Subject: [PATCH 021/295] gitweb: Separate generating 'sort by' table header Extract generating table header cell, for tables which can be sorted by its columns, into print_sort_th_str() and print_sort_th_num() subroutines, and print_sort_th() driver subroutine. This avoids repetition, and should make further improvements (like JavaScript sorting) easier. The subroutine uses now "replay" link, so it is generic enough to be able to use it for other tables which can be sorted by column, like for example 'heads' and 'tags' view (sort by name, or sort by age). Signed-off-by: Jakub Narebski Signed-off-by: Junio C Hamano --- gitweb/gitweb.perl | 76 ++++++++++++++++++++++++---------------------- 1 file changed, 39 insertions(+), 37 deletions(-) diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index d7a9809027..c7882f24f7 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -3598,6 +3598,36 @@ sub fill_project_list_info { return @projects; } +# print 'sort by' element, either sorting by $key if $name eq $order +# (changing $list), or generating 'sort by $name' replay link otherwise +sub print_sort_th { + my ($str_sort, $name, $order, $key, $header, $list) = @_; + $key ||= $name; + $header ||= ucfirst($name); + + if ($order eq $name) { + if ($str_sort) { + @$list = sort {$a->{$key} cmp $b->{$key}} @$list; + } else { + @$list = sort {$a->{$key} <=> $b->{$key}} @$list; + } + print "$header\n"; + } else { + print "" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "\n"; + } +} + +sub print_sort_th_str { + print_sort_th(1, @_); +} + +sub print_sort_th_num { + print_sort_th(0, @_); +} + sub git_project_list_body { my ($projlist, $order, $from, $to, $extra, $no_header) = @_; @@ -3614,43 +3644,15 @@ sub git_project_list_body { if ($check_forks) { print "\n"; } - if ($order eq "project") { - @projects = sort {$a->{'path'} cmp $b->{'path'}} @projects; - print "Project\n"; - } else { - print "" . - $cgi->a({-href => href(project=>undef, order=>'project'), - -class => "header"}, "Project") . - "\n"; - } - if ($order eq "descr") { - @projects = sort {$a->{'descr'} cmp $b->{'descr'}} @projects; - print "Description\n"; - } else { - print "" . - $cgi->a({-href => href(project=>undef, order=>'descr'), - -class => "header"}, "Description") . - "\n"; - } - if ($order eq "owner") { - @projects = sort {$a->{'owner'} cmp $b->{'owner'}} @projects; - print "Owner\n"; - } else { - print "" . - $cgi->a({-href => href(project=>undef, order=>'owner'), - -class => "header"}, "Owner") . - "\n"; - } - if ($order eq "age") { - @projects = sort {$a->{'age'} <=> $b->{'age'}} @projects; - print "Last Change\n"; - } else { - print "" . - $cgi->a({-href => href(project=>undef, order=>'age'), - -class => "header"}, "Last Change") . - "\n"; - } - print "\n" . + print_sort_th_str('project', $order, 'path', + 'Project', \@projects); + print_sort_th_str('descr', $order, 'descr_long', + 'Description', \@projects); + print_sort_th_str('owner', $order, 'owner', + 'Owner', \@projects); + print_sort_th_num('age', $order, 'age', + 'Last Change', \@projects); + print "\n" . # for links "\n"; } my $alternate = 1; From 8a965b8ee28bedc58641453e13d03f80180320dd Mon Sep 17 00:00:00 2001 From: Abhijit Menon-Sen Date: Fri, 13 Jun 2008 03:42:10 +0530 Subject: [PATCH 022/295] git-gui: Move on to the next filename after staging/unstaging a change Suppose the "Unstaged Changes" pane contains a list of files, and one of them is selected (i.e., that diff is currently being displayed). If one clicks on the icon to stage the change, git-gui clears the diff and one has to click on another filename to see the next diff in the list. This patch changes that behaviour. If one clicks on the icon to stage (or unstage) the file whose diff is being displayed, git-gui will move on to the next filename in the list and display that diff instead of a blank diff pane. If the selected file was at the end of the list, the diff pane will display the previous diff instead; if the selected file was the only one listed, the diff pane will become blank. If no diff is currently being displayed, this patch changes nothing. Signed-off-by: Abhijit Menon-Sen Signed-off-by: Shawn O. Pearce --- git-gui.sh | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) diff --git a/git-gui.sh b/git-gui.sh index e6e88902f1..23d7dfec79 100755 --- a/git-gui.sh +++ b/git-gui.sh @@ -1774,6 +1774,11 @@ proc do_commit {} { commit_tree } +proc next_diff {} { + global next_diff_p next_diff_w next_diff_i + show_diff $next_diff_p $next_diff_w $next_diff_i +} + proc toggle_or_diff {w x y} { global file_states file_lists current_diff_path ui_index ui_workdir global last_clicked selected_paths @@ -1793,11 +1798,31 @@ proc toggle_or_diff {w x y} { $ui_workdir tag remove in_sel 0.0 end if {$col == 0} { - if {$current_diff_path eq $path} { + set i [expr {$lno-1}] + set ll [expr {[llength $file_lists($w)]-1}] + + if {$i == $ll && $i == 0} { set after {reshow_diff;} } else { - set after {} + global next_diff_p next_diff_w next_diff_i + + if {$i < $ll} { + set i [expr {$i + 1}] + } else { + set i [expr {$i - 1}] + } + + set next_diff_i $i + set next_diff_w $w + set next_diff_p [lindex $file_lists($w) $i] + + if {$next_diff_p ne {} && $current_diff_path ne {}} { + set after {next_diff;} + } else { + set after {} + } } + if {$w eq $ui_index} { update_indexinfo \ "Unstaging [short_path $path] from commit" \ From 3b2eb186bb738a374d9325b18710b19ec270e55f Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 14 Jun 2008 03:25:56 -0400 Subject: [PATCH 023/295] fix whitespace violations in test scripts These violations are simply wrong, but were never caught because whitespace policy checking is turned off in the test scripts. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- t/t3903-stash.sh | 2 +- t/t4014-format-patch.sh | 6 +++--- t/t4150-am.sh | 2 +- t/t5540-http-push.sh | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/t/t3903-stash.sh b/t/t3903-stash.sh index 2d3ee3b78c..54d99ed0c3 100755 --- a/t/t3903-stash.sh +++ b/t/t3903-stash.sh @@ -41,7 +41,7 @@ test_expect_success 'apply needs clean working directory' ' echo 4 > other-file && git add other-file && echo 5 > other-file && - test_must_fail git stash apply + test_must_fail git stash apply ' test_expect_success 'apply stashed changes' ' diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh index 3583e68e92..7fe853c20d 100755 --- a/t/t4014-format-patch.sh +++ b/t/t4014-format-patch.sh @@ -98,7 +98,7 @@ test_expect_success 'extra headers' ' sed -e "/^$/q" patch2 > hdrs2 && grep "^To: R. E. Cipient $" hdrs2 && grep "^Cc: S. E. Cipient $" hdrs2 - + ' test_expect_success 'extra headers without newlines' ' @@ -109,7 +109,7 @@ test_expect_success 'extra headers without newlines' ' sed -e "/^$/q" patch3 > hdrs3 && grep "^To: R. E. Cipient $" hdrs3 && grep "^Cc: S. E. Cipient $" hdrs3 - + ' test_expect_success 'extra headers with multiple To:s' ' @@ -170,7 +170,7 @@ test_expect_success 'thread cover-letter' ' git checkout side && git format-patch --cover-letter --thread -o patches/ master && FIRST_MID=$(grep "Message-Id:" patches/0000-* | sed "s/^[^<]*\(<[^>]*>\).*$/\1/") && - for i in patches/0001-* patches/0002-* patches/0003-* + for i in patches/0001-* patches/0002-* patches/0003-* do grep "References: $FIRST_MID" $i && grep "In-Reply-To: $FIRST_MID" $i || break diff --git a/t/t4150-am.sh b/t/t4150-am.sh index 722ae96cd5..bc982607d0 100755 --- a/t/t4150-am.sh +++ b/t/t4150-am.sh @@ -110,7 +110,7 @@ test_expect_success 'am applies patch correctly' ' GIT_AUTHOR_NAME="Another Thor" GIT_AUTHOR_EMAIL="a.thor@example.com" -GIT_COMMITTER_NAME="Co M Miter" +GIT_COMMITTER_NAME="Co M Miter" GIT_COMMITTER_EMAIL="c.miter@example.com" export GIT_AUTHOR_NAME GIT_AUTHOR_EMAIL GIT_COMMITTER_NAME GIT_COMMITTER_EMAIL diff --git a/t/t5540-http-push.sh b/t/t5540-http-push.sh index 7372439164..f15dd03e4d 100755 --- a/t/t5540-http-push.sh +++ b/t/t5540-http-push.sh @@ -38,7 +38,7 @@ test_expect_success 'setup remote repository' ' cd - && mv test_repo.git $HTTPD_DOCUMENT_ROOT_PATH ' - + test_expect_success 'clone remote repository' ' cd "$ROOT_PATH" && git clone $HTTPD_URL/test_repo.git test_repo_clone From 74f16b0c6fece88f585f9556fa1d3a7406e7a42e Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 14 Jun 2008 03:26:37 -0400 Subject: [PATCH 024/295] mask necessary whitespace policy violations in test scripts All of these violations are necessary parts of the tests (which are generally checking the behavior of trailing whitespace, or contain diff fragments with empty lines). Our solution is two-fold: 1. Process input with whitespace problems using tr. This has the added bonus that it becomes very obvious where the bogus whitespace is intended to go. 2. Move large diff fragments into their own supplemental files. This gets rid of the whitespace problem, since supplemental files are not checked, and it also makes the test script a bit easier to read. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- t/t3800-mktag.sh | 4 +- t/t4015-diff-whitespace.sh | 8 +-- t/t4109-apply-multifrag.sh | 132 ++----------------------------------- t/t4109/patch1.patch | 28 ++++++++ t/t4109/patch2.patch | 30 +++++++++ t/t4109/patch3.patch | 31 +++++++++ t/t4109/patch4.patch | 30 +++++++++ t/t4119-apply-config.sh | 4 +- 8 files changed, 131 insertions(+), 136 deletions(-) create mode 100644 t/t4109/patch1.patch create mode 100644 t/t4109/patch2.patch create mode 100644 t/t4109/patch3.patch create mode 100644 t/t4109/patch4.patch diff --git a/t/t3800-mktag.sh b/t/t3800-mktag.sh index df1fd6f86f..c851db8ca9 100755 --- a/t/t3800-mktag.sh +++ b/t/t3800-mktag.sh @@ -241,11 +241,11 @@ check_verify_failure 'disallow spaces in tag email' \ ############################################################ # 17. disallow missing tag timestamp -cat >tag.sig <tag.sig < +tagger T A Gger __ EOF diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh index ca0302f41b..b7cc6b28e6 100755 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@ -62,16 +62,16 @@ EOF git update-index x -cat << EOF > x +tr '_' ' ' << EOF > x whitespace at beginning whitespace change white space in the middle -whitespace at end +whitespace at end__ unchanged line CR at end EOF -tr 'Q' '\015' << EOF > expect +tr 'Q_' '\015 ' << EOF > expect diff --git a/x b/x index d99af23..8b32fb5 100644 --- a/x @@ -84,7 +84,7 @@ index d99af23..8b32fb5 100644 + whitespace at beginning +whitespace change +white space in the middle -+whitespace at end ++whitespace at end__ unchanged line -CR at endQ +CR at end diff --git a/t/t4109-apply-multifrag.sh b/t/t4109-apply-multifrag.sh index bd40a218cd..ff5fdf35f9 100755 --- a/t/t4109-apply-multifrag.sh +++ b/t/t4109-apply-multifrag.sh @@ -9,134 +9,10 @@ test_description='git apply test patches with multiple fragments. ' . ./test-lib.sh -# setup - -cat > patch1.patch <<\EOF -diff --git a/main.c b/main.c -new file mode 100644 ---- /dev/null -+++ b/main.c -@@ -0,0 +1,23 @@ -+#include -+ -+int func(int num); -+void print_int(int num); -+ -+int main() { -+ int i; -+ -+ for (i = 0; i < 10; i++) { -+ print_int(func(i)); -+ } -+ -+ return 0; -+} -+ -+int func(int num) { -+ return num * num; -+} -+ -+void print_int(int num) { -+ printf("%d", num); -+} -+ -EOF -cat > patch2.patch <<\EOF -diff --git a/main.c b/main.c ---- a/main.c -+++ b/main.c -@@ -1,7 +1,9 @@ -+#include - #include - - int func(int num); - void print_int(int num); -+void print_ln(); - - int main() { - int i; -@@ -10,6 +12,8 @@ - print_int(func(i)); - } - -+ print_ln(); -+ - return 0; - } - -@@ -21,3 +25,7 @@ - printf("%d", num); - } - -+void print_ln() { -+ printf("\n"); -+} -+ -EOF -cat > patch3.patch <<\EOF -diff --git a/main.c b/main.c ---- a/main.c -+++ b/main.c -@@ -1,9 +1,7 @@ --#include - #include - - int func(int num); - void print_int(int num); --void print_ln(); - - int main() { - int i; -@@ -12,8 +10,6 @@ - print_int(func(i)); - } - -- print_ln(); -- - return 0; - } - -@@ -25,7 +21,3 @@ - printf("%d", num); - } - --void print_ln() { -- printf("\n"); --} -- -EOF -cat > patch4.patch <<\EOF -diff --git a/main.c b/main.c ---- a/main.c -+++ b/main.c -@@ -1,13 +1,14 @@ - #include - - int func(int num); --void print_int(int num); -+int func2(int num); - - int main() { - int i; - - for (i = 0; i < 10; i++) { -- print_int(func(i)); -+ printf("%d", func(i)); -+ printf("%d", func3(i)); - } - - return 0; -@@ -17,7 +18,7 @@ - return num * num; - } - --void print_int(int num) { -- printf("%d", num); -+int func2(int num) { -+ return num * num * num; - } - -EOF +cp ../t4109/patch1.patch . +cp ../t4109/patch2.patch . +cp ../t4109/patch3.patch . +cp ../t4109/patch4.patch . test_expect_success "S = git apply (1)" \ 'git apply patch1.patch patch2.patch' diff --git a/t/t4109/patch1.patch b/t/t4109/patch1.patch new file mode 100644 index 0000000000..1d411fc3cc --- /dev/null +++ b/t/t4109/patch1.patch @@ -0,0 +1,28 @@ +diff --git a/main.c b/main.c +new file mode 100644 +--- /dev/null ++++ b/main.c +@@ -0,0 +1,23 @@ ++#include ++ ++int func(int num); ++void print_int(int num); ++ ++int main() { ++ int i; ++ ++ for (i = 0; i < 10; i++) { ++ print_int(func(i)); ++ } ++ ++ return 0; ++} ++ ++int func(int num) { ++ return num * num; ++} ++ ++void print_int(int num) { ++ printf("%d", num); ++} ++ diff --git a/t/t4109/patch2.patch b/t/t4109/patch2.patch new file mode 100644 index 0000000000..8c6b06d536 --- /dev/null +++ b/t/t4109/patch2.patch @@ -0,0 +1,30 @@ +diff --git a/main.c b/main.c +--- a/main.c ++++ b/main.c +@@ -1,7 +1,9 @@ ++#include + #include + + int func(int num); + void print_int(int num); ++void print_ln(); + + int main() { + int i; +@@ -10,6 +12,8 @@ + print_int(func(i)); + } + ++ print_ln(); ++ + return 0; + } + +@@ -21,3 +25,7 @@ + printf("%d", num); + } + ++void print_ln() { ++ printf("\n"); ++} ++ diff --git a/t/t4109/patch3.patch b/t/t4109/patch3.patch new file mode 100644 index 0000000000..d696c55a75 --- /dev/null +++ b/t/t4109/patch3.patch @@ -0,0 +1,31 @@ +cat > patch3.patch <<\EOF +diff --git a/main.c b/main.c +--- a/main.c ++++ b/main.c +@@ -1,9 +1,7 @@ +-#include + #include + + int func(int num); + void print_int(int num); +-void print_ln(); + + int main() { + int i; +@@ -12,8 +10,6 @@ + print_int(func(i)); + } + +- print_ln(); +- + return 0; + } + +@@ -25,7 +21,3 @@ + printf("%d", num); + } + +-void print_ln() { +- printf("\n"); +-} +- diff --git a/t/t4109/patch4.patch b/t/t4109/patch4.patch new file mode 100644 index 0000000000..4b085909b1 --- /dev/null +++ b/t/t4109/patch4.patch @@ -0,0 +1,30 @@ +diff --git a/main.c b/main.c +--- a/main.c ++++ b/main.c +@@ -1,13 +1,14 @@ + #include + + int func(int num); +-void print_int(int num); ++int func2(int num); + + int main() { + int i; + + for (i = 0; i < 10; i++) { +- print_int(func(i)); ++ printf("%d", func(i)); ++ printf("%d", func3(i)); + } + + return 0; +@@ -17,7 +18,7 @@ + return num * num; + } + +-void print_int(int num) { +- printf("%d", num); ++int func2(int num) { ++ return num * num * num; + } + diff --git a/t/t4119-apply-config.sh b/t/t4119-apply-config.sh index b540f7295a..3c73a783a7 100755 --- a/t/t4119-apply-config.sh +++ b/t/t4119-apply-config.sh @@ -19,12 +19,12 @@ test_expect_success setup ' ' # Also handcraft GNU diff output; note this has trailing whitespace. -cat >gpatch.file <<\EOF && +tr '_' ' ' >gpatch.file <<\EOF && --- file1 2007-02-21 01:04:24.000000000 -0800 +++ file1+ 2007-02-21 01:07:44.000000000 -0800 @@ -1 +1 @@ -A -+B ++B_ EOF sed -e 's|file1|sub/&|' gpatch.file >gpatch-sub.file && From 44d86e910d61dab4f059d86705599bbb2747b10f Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 14 Jun 2008 03:27:21 -0400 Subject: [PATCH 025/295] avoid whitespace on empty line in automatic usage message When outputting a usage message with a blank line in the header, we would output a line with four spaces. Make this truly a blank line. This helps us remove trailing whitespace from a test vector. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- parse-options.c | 8 ++++++-- t/t1502-rev-parse-parseopt.sh | 2 +- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/parse-options.c b/parse-options.c index acf3fe3a1a..8071711e5d 100644 --- a/parse-options.c +++ b/parse-options.c @@ -312,8 +312,12 @@ void usage_with_options_internal(const char * const *usagestr, fprintf(stderr, "usage: %s\n", *usagestr++); while (*usagestr && **usagestr) fprintf(stderr, " or: %s\n", *usagestr++); - while (*usagestr) - fprintf(stderr, " %s\n", *usagestr++); + while (*usagestr) { + fprintf(stderr, "%s%s\n", + **usagestr ? " " : "", + *usagestr); + usagestr++; + } if (opts->type != OPTION_GROUP) fputc('\n', stderr); diff --git a/t/t1502-rev-parse-parseopt.sh b/t/t1502-rev-parse-parseopt.sh index d24a47d114..7cdd70a188 100755 --- a/t/t1502-rev-parse-parseopt.sh +++ b/t/t1502-rev-parse-parseopt.sh @@ -5,7 +5,7 @@ test_description='test git rev-parse --parseopt' cat > expect.err <... - + some-command does foo and bar! -h, --help show the help From 4d9b53591f64a11da0af4c2b8f11fd4730ce52dd Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 14 Jun 2008 03:27:45 -0400 Subject: [PATCH 026/295] avoid trailing whitespace in zero-change diffstat lines In some cases, we produce a diffstat line even though no lines have changed (e.g., because of an exact rename). In this case, there is no +/- "graph" after the number of changed lines. However, we output the space separator unconditionally, meaning that these lines contained a trailing space character. This isn't a huge problem, but in cleaning up the output we are able to eliminate some trailing whitespace from a test vector. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- diff.c | 3 ++- t/t4016-diff-quote.sh | 14 +++++++------- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/diff.c b/diff.c index 62fdc5492b..f77f9e9447 100644 --- a/diff.c +++ b/diff.c @@ -922,7 +922,8 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options) total = add + del; } show_name(options->file, prefix, name, len, reset, set); - fprintf(options->file, "%5d ", added + deleted); + fprintf(options->file, "%5d%s", added + deleted, + added + deleted ? " " : ""); show_graph(options->file, '+', add, add_c, reset); show_graph(options->file, '-', del, del_c, reset); fprintf(options->file, "\n"); diff --git a/t/t4016-diff-quote.sh b/t/t4016-diff-quote.sh index 0950250c9b..f07035ab7e 100755 --- a/t/t4016-diff-quote.sh +++ b/t/t4016-diff-quote.sh @@ -53,13 +53,13 @@ test_expect_success 'git diff --summary -M HEAD' ' ' cat >expect <<\EOF - pathname.1 => "Rpathname\twith HT.0" | 0 - pathname.3 => "Rpathname\nwith LF.0" | 0 - "pathname\twith HT.3" => "Rpathname\nwith LF.1" | 0 - pathname.2 => Rpathname with SP.0 | 0 - "pathname\twith HT.2" => Rpathname with SP.1 | 0 - pathname.0 => Rpathname.0 | 0 - "pathname\twith HT.0" => Rpathname.1 | 0 + pathname.1 => "Rpathname\twith HT.0" | 0 + pathname.3 => "Rpathname\nwith LF.0" | 0 + "pathname\twith HT.3" => "Rpathname\nwith LF.1" | 0 + pathname.2 => Rpathname with SP.0 | 0 + "pathname\twith HT.2" => Rpathname with SP.1 | 0 + pathname.0 => Rpathname.0 | 0 + "pathname\twith HT.0" => Rpathname.1 | 0 7 files changed, 0 insertions(+), 0 deletions(-) EOF test_expect_success 'git diff --stat -M HEAD' ' From 9197240de82cb5bc45897860e0e93dc7c0b1a08f Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sat, 14 Jun 2008 03:28:07 -0400 Subject: [PATCH 027/295] enable whitespace checking of test scripts Now that all of the policy violations have been cleaned up, we can turn this on and start checking incoming patches. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- t/.gitattributes | 1 - 1 file changed, 1 deletion(-) diff --git a/t/.gitattributes b/t/.gitattributes index ab6edbf19e..1b97c5465b 100644 --- a/t/.gitattributes +++ b/t/.gitattributes @@ -1,2 +1 @@ -t[0-9][0-9][0-9][0-9]-*.sh -whitespace t[0-9][0-9][0-9][0-9]/* -whitespace From 806e2ad7fe2d94e1ecae904c33b822b3dfac57f6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 18 Jun 2008 14:37:18 -0700 Subject: [PATCH 028/295] Split up default "core" config parsing into helper routine It makes the code a bit easier to read, and in theory a bit faster too (no need to compare all the different "core.*" strings against non-core config options). The config system really should get something of a complete overhaul, but in the absense of that, this at least improves on it a tiny bit. Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- config.c | 42 ++++++++++++++++++++++++++---------------- 1 file changed, 26 insertions(+), 16 deletions(-) diff --git a/config.c b/config.c index c2f2bbb000..c3597e0432 100644 --- a/config.c +++ b/config.c @@ -332,7 +332,7 @@ int git_config_string(const char **dest, const char *var, const char *value) return 0; } -int git_default_config(const char *var, const char *value, void *dummy) +static int git_default_core_config(const char *var, const char *value) { /* This needs a better name */ if (!strcmp(var, "core.filemode")) { @@ -444,6 +444,31 @@ int git_default_config(const char *var, const char *value, void *dummy) return 0; } + if (!strcmp(var, "core.pager")) + return git_config_string(&pager_program, var, value); + + if (!strcmp(var, "core.editor")) + return git_config_string(&editor_program, var, value); + + if (!strcmp(var, "core.excludesfile")) + return git_config_string(&excludes_file, var, value); + + if (!strcmp(var, "core.whitespace")) { + if (!value) + return config_error_nonbool(var); + whitespace_rule_cfg = parse_whitespace_rule(value); + return 0; + } + + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int git_default_config(const char *var, const char *value, void *dummy) +{ + if (!prefixcmp(var, "core.")) + return git_default_core_config(var, value); + if (!strcmp(var, "user.name")) { if (!value) return config_error_nonbool(var); @@ -473,21 +498,6 @@ int git_default_config(const char *var, const char *value, void *dummy) return 0; } - if (!strcmp(var, "core.pager")) - return git_config_string(&pager_program, var, value); - - if (!strcmp(var, "core.editor")) - return git_config_string(&editor_program, var, value); - - if (!strcmp(var, "core.excludesfile")) - return git_config_string(&excludes_file, var, value); - - if (!strcmp(var, "core.whitespace")) { - if (!value) - return config_error_nonbool(var); - whitespace_rule_cfg = parse_whitespace_rule(value); - return 0; - } if (!strcmp(var, "branch.autosetupmerge")) { if (value && !strcasecmp(value, "always")) { git_branch_track = BRANCH_TRACK_ALWAYS; From d1364529d06e5fa3bc054396299944a7a4861776 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 18 Jun 2008 14:40:35 -0700 Subject: [PATCH 029/295] Split up default "user" config parsing into helper routine This follows the example of the "core" config, and splits out the default "user" config option parsing into a helper routine. Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- config.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/config.c b/config.c index c3597e0432..ee7642bf6c 100644 --- a/config.c +++ b/config.c @@ -464,11 +464,8 @@ static int git_default_core_config(const char *var, const char *value) return 0; } -int git_default_config(const char *var, const char *value, void *dummy) +static int git_default_user_config(const char *var, const char *value) { - if (!prefixcmp(var, "core.")) - return git_default_core_config(var, value); - if (!strcmp(var, "user.name")) { if (!value) return config_error_nonbool(var); @@ -487,6 +484,18 @@ int git_default_config(const char *var, const char *value, void *dummy) return 0; } + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + +int git_default_config(const char *var, const char *value, void *dummy) +{ + if (!prefixcmp(var, "core.")) + return git_default_core_config(var, value); + + if (!prefixcmp(var, "user.")) + return git_default_user_config(var, value); + if (!strcmp(var, "i18n.commitencoding")) return git_config_string(&git_commit_encoding, var, value); From 1141f4925c3f1d7c8cc476b10107209e56909c6d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 18 Jun 2008 15:00:11 -0700 Subject: [PATCH 030/295] Split up default "i18n" and "branch" config parsing into helper routines .. just to finish it off. We'll leave the pager color config alone, since it is such an odd-ball special case anyway. Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- config.c | 40 +++++++++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 11 deletions(-) diff --git a/config.c b/config.c index ee7642bf6c..9d14a74f82 100644 --- a/config.c +++ b/config.c @@ -488,25 +488,20 @@ static int git_default_user_config(const char *var, const char *value) return 0; } -int git_default_config(const char *var, const char *value, void *dummy) +static int git_default_i18n_config(const char *var, const char *value) { - if (!prefixcmp(var, "core.")) - return git_default_core_config(var, value); - - if (!prefixcmp(var, "user.")) - return git_default_user_config(var, value); - if (!strcmp(var, "i18n.commitencoding")) return git_config_string(&git_commit_encoding, var, value); if (!strcmp(var, "i18n.logoutputencoding")) return git_config_string(&git_log_output_encoding, var, value); - if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) { - pager_use_color = git_config_bool(var,value); - return 0; - } + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} +static int git_default_branch_config(const char *var, const char *value) +{ if (!strcmp(var, "branch.autosetupmerge")) { if (value && !strcasecmp(value, "always")) { git_branch_track = BRANCH_TRACK_ALWAYS; @@ -535,6 +530,29 @@ int git_default_config(const char *var, const char *value, void *dummy) return 0; } +int git_default_config(const char *var, const char *value, void *dummy) +{ + if (!prefixcmp(var, "core.")) + return git_default_core_config(var, value); + + if (!prefixcmp(var, "user.")) + return git_default_user_config(var, value); + + if (!prefixcmp(var, "i18n.")) + return git_default_i18n_config(var, value); + + if (!prefixcmp(var, "branch.")) + return git_default_branch_config(var, value); + + if (!strcmp(var, "pager.color") || !strcmp(var, "color.pager")) { + pager_use_color = git_config_bool(var,value); + return 0; + } + + /* Add other config variables here and to Documentation/config.txt. */ + return 0; +} + int git_config_from_file(config_fn_t fn, const char *filename, void *data) { int ret; From aafe9fbaf4f1d1f27a6f6e3eb3e246fff81240ef Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 18 Jun 2008 15:18:44 -0700 Subject: [PATCH 031/295] Add config option to enable 'fsync()' of object files As explained in the documentation[*] this is totally useless on filesystems that do ordered/journalled data writes, but it can be a useful safety feature on filesystems like HFS+ that only journal the metadata, not the actual file contents. It defaults to off, although we could presumably in theory some day auto-enable it on a per-filesystem basis. [*] Yes, I updated the docs for the thing. Hell really _has_ frozen over, and the four horsemen are probably just beyond the horizon. EVERYBODY PANIC! Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- Documentation/config.txt | 8 ++++++++ cache.h | 1 + config.c | 5 +++++ environment.c | 1 + sha1_file.c | 3 ++- 5 files changed, 17 insertions(+), 1 deletion(-) diff --git a/Documentation/config.txt b/Documentation/config.txt index 5331b450ea..2466ecfc6b 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -372,6 +372,14 @@ core.whitespace:: does not trigger if the character before such a carriage-return is not a whitespace (not enabled by default). +core.fsyncobjectfiles:: + This boolean will enable 'fsync()' when writing object files. ++ +This is a total waste of time and effort on a filesystem that orders +data writes properly, but can be useful for filesystems that do not use +journalling (traditional UNIX filesystems) or that only journal metadata +and not file contents (OS X's HFS+, or Linux ext3 with "data=writeback"). + alias.*:: Command aliases for the linkgit:git[1] command wrapper - e.g. after defining "alias.last = cat-file commit HEAD", the invocation diff --git a/cache.h b/cache.h index 81b7e17de2..01c8502afb 100644 --- a/cache.h +++ b/cache.h @@ -435,6 +435,7 @@ extern size_t packed_git_window_size; extern size_t packed_git_limit; extern size_t delta_base_cache_limit; extern int auto_crlf; +extern int fsync_object_files; enum safe_crlf { SAFE_CRLF_FALSE = 0, diff --git a/config.c b/config.c index 9d14a74f82..b2d5b4e4e3 100644 --- a/config.c +++ b/config.c @@ -460,6 +460,11 @@ static int git_default_core_config(const char *var, const char *value) return 0; } + if (!strcmp(var, "core.fsyncobjectfiles")) { + fsync_object_files = git_config_bool(var, value); + return 0; + } + /* Add other config variables here and to Documentation/config.txt. */ return 0; } diff --git a/environment.c b/environment.c index 73feb2d03a..d5c3e29e97 100644 --- a/environment.c +++ b/environment.c @@ -29,6 +29,7 @@ const char *apply_default_whitespace; int zlib_compression_level = Z_BEST_SPEED; int core_compression_level; int core_compression_seen; +int fsync_object_files; size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE; size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT; size_t delta_base_cache_limit = 16 * 1024 * 1024; diff --git a/sha1_file.c b/sha1_file.c index 191f814e09..fe4ee3ece5 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -2083,7 +2083,8 @@ int hash_sha1_file(const void *buf, unsigned long len, const char *type, /* Finalize a file on disk, and close it. */ static void close_sha1_file(int fd) { - /* For safe-mode, we could fsync_or_die(fd, "sha1 file") here */ + if (fsync_object_files) + fsync_or_die(fd, "sha1 file"); fchmod(fd, 0444); if (close(fd) != 0) die("unable to write sha1 file"); From 641dba49bf819dc5f4874a75b206bc7f51dc14e6 Mon Sep 17 00:00:00 2001 From: Patrick Higgins Date: Mon, 16 Jun 2008 17:33:41 -0600 Subject: [PATCH 032/295] Remove the use of '--' in merge program invocation Put a "./" at the beginning of all paths given to the merge program so that filenames beginning with a '-' character don't get interpreted as options. This deals with a problem where kdiff3 can be compiled with or without support for the '--' separator between options and filenames. Signed-off-by: Patrick Higgins Signed-off-by: Junio C Hamano --- git-mergetool.sh | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/git-mergetool.sh b/git-mergetool.sh index fcdec4a504..94187c306c 100755 --- a/git-mergetool.sh +++ b/git-mergetool.sh @@ -141,10 +141,10 @@ merge_file () { fi ext="$$$(expr "$MERGED" : '.*\(\.[^/]*\)$')" - BACKUP="$MERGED.BACKUP.$ext" - LOCAL="$MERGED.LOCAL.$ext" - REMOTE="$MERGED.REMOTE.$ext" - BASE="$MERGED.BASE.$ext" + BACKUP="./$MERGED.BACKUP.$ext" + LOCAL="./$MERGED.LOCAL.$ext" + REMOTE="./$MERGED.REMOTE.$ext" + BASE="./$MERGED.BASE.$ext" mv -- "$MERGED" "$BACKUP" cp -- "$BACKUP" "$MERGED" @@ -183,29 +183,29 @@ merge_file () { kdiff3) if base_present ; then ("$merge_tool_path" --auto --L1 "$MERGED (Base)" --L2 "$MERGED (Local)" --L3 "$MERGED (Remote)" \ - -o "$MERGED" -- "$BASE" "$LOCAL" "$REMOTE" > /dev/null 2>&1) + -o "$MERGED" "$BASE" "$LOCAL" "$REMOTE" > /dev/null 2>&1) else ("$merge_tool_path" --auto --L1 "$MERGED (Local)" --L2 "$MERGED (Remote)" \ - -o "$MERGED" -- "$LOCAL" "$REMOTE" > /dev/null 2>&1) + -o "$MERGED" "$LOCAL" "$REMOTE" > /dev/null 2>&1) fi status=$? ;; tkdiff) if base_present ; then - "$merge_tool_path" -a "$BASE" -o "$MERGED" -- "$LOCAL" "$REMOTE" + "$merge_tool_path" -a "$BASE" -o "$MERGED" "$LOCAL" "$REMOTE" else - "$merge_tool_path" -o "$MERGED" -- "$LOCAL" "$REMOTE" + "$merge_tool_path" -o "$MERGED" "$LOCAL" "$REMOTE" fi status=$? ;; meld|vimdiff) touch "$BACKUP" - "$merge_tool_path" -- "$LOCAL" "$MERGED" "$REMOTE" + "$merge_tool_path" "$LOCAL" "$MERGED" "$REMOTE" check_unchanged ;; gvimdiff) touch "$BACKUP" - "$merge_tool_path" -f -- "$LOCAL" "$MERGED" "$REMOTE" + "$merge_tool_path" -f "$LOCAL" "$MERGED" "$REMOTE" check_unchanged ;; xxdiff) @@ -215,13 +215,13 @@ merge_file () { -R 'Accel.SaveAsMerged: "Ctrl-S"' \ -R 'Accel.Search: "Ctrl+F"' \ -R 'Accel.SearchForward: "Ctrl-G"' \ - --merged-file "$MERGED" -- "$LOCAL" "$BASE" "$REMOTE" + --merged-file "$MERGED" "$LOCAL" "$BASE" "$REMOTE" else "$merge_tool_path" -X --show-merged-pane \ -R 'Accel.SaveAsMerged: "Ctrl-S"' \ -R 'Accel.Search: "Ctrl+F"' \ -R 'Accel.SearchForward: "Ctrl-G"' \ - --merged-file "$MERGED" -- "$LOCAL" "$REMOTE" + --merged-file "$MERGED" "$LOCAL" "$REMOTE" fi check_unchanged ;; From f49c2c22fef520fd69ff26869c26dc58a834de2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 10 Jun 2008 10:44:43 -0700 Subject: [PATCH 033/295] racy-git: an empty blob has a fixed object name We use size=0 as the magic token to say the entry is known to be racily clean, but a sequence that does: - update the path with a non-empty blob and write the index; - update an unrelated path and write the index -- this smudges the above entry; - truncate the path to size zero. would make both the size field for the path in the index and the size on the filesystem zero. We should not mistake it as a clean index entry. Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- read-cache.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/read-cache.c b/read-cache.c index a92b25b59b..6fa3c21148 100644 --- a/read-cache.c +++ b/read-cache.c @@ -197,6 +197,16 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st) return 0; } +static int is_empty_blob_sha1(const unsigned char *sha1) +{ + static const unsigned char empty_blob_sha1[20] = { + 0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b, + 0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91 + }; + + return !hashcmp(sha1, empty_blob_sha1); +} + static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) { unsigned int changed = 0; @@ -252,6 +262,12 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st) if (ce->ce_size != (unsigned int) st->st_size) changed |= DATA_CHANGED; + /* Racily smudged entry? */ + if (!ce->ce_size) { + if (!is_empty_blob_sha1(ce->sha1)) + changed |= DATA_CHANGED; + } + return changed; } From 5e2c08c6f0209e94b36d0770abae1a2b571cb0f1 Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Tue, 17 Jun 2008 03:29:02 +0200 Subject: [PATCH 034/295] test-lib.sh: add --long-tests option Add a --long-tests option to test-lib.sh, which enables tests to selectively run more exhaustive (longer running, potentially brute-force) tests. Such exhaustive tests would only be useful if one works on the specific module that is being tested -- for a general "cd t/; make" to check whether everything is OK, such exhaustive tests shouldn't be run by default since the longer it takes to run the tests, the less often they are actually run. Signed-off-by: Lea Wiemann Signed-off-by: Junio C Hamano --- t/README | 4 ++++ t/test-lib.sh | 2 ++ 2 files changed, 6 insertions(+) diff --git a/t/README b/t/README index 70841a4645..dc892631e0 100644 --- a/t/README +++ b/t/README @@ -54,6 +54,10 @@ You can pass --verbose (or -v), --debug (or -d), and --immediate This causes the test to immediately exit upon the first failed test. +--long-tests:: + This causes additional long-running tests to be run (where + available), for more exhaustive testing. + Naming Tests ------------ diff --git a/t/test-lib.sh b/t/test-lib.sh index c861141667..e331cadcff 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -80,6 +80,8 @@ do debug=t; shift ;; -i|--i|--im|--imm|--imme|--immed|--immedi|--immedia|--immediat|--immediate) immediate=t; shift ;; + -l|--l|--lo|--lon|--long|--long-|--long-t|--long-te|--long-tes|--long-test|--long-tests) + export GIT_TEST_LONG=t; shift ;; -h|--h|--he|--hel|--help) help=t; shift ;; -v|--v|--ve|--ver|--verb|--verbo|--verbos|--verbose) From fb32c410087e68d650b31f68e66b3d9cbcce4a56 Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Thu, 19 Jun 2008 20:18:03 +0200 Subject: [PATCH 035/295] t/test-lib.sh: add test_external and test_external_without_stderr This is for running external test scripts in other programming languages that provide continuous output about their tests. Using test_expect_success (like "test_expect_success 'description' 'perl test-script.pl'") doesn't suffice here because test_expect_success eats stdout in non-verbose mode, which is not fixable without major file descriptor trickery. Signed-off-by: Lea Wiemann Signed-off-by: Junio C Hamano --- t/test-lib.sh | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/t/test-lib.sh b/t/test-lib.sh index c861141667..4be466edb7 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -302,6 +302,64 @@ test_expect_code () { echo >&3 "" } +# test_external runs external test scripts that provide continuous +# test output about their progress, and succeeds/fails on +# zero/non-zero exit code. It outputs the test output on stdout even +# in non-verbose mode, and announces the external script with "* run +# : ..." before running it. When providing relative paths, keep in +# mind that all scripts run in "trash directory". +# Usage: test_external description command arguments... +# Example: test_external 'Perl API' perl ../path/to/test.pl +test_external () { + test "$#" -eq 3 || + error >&5 "bug in the test script: not 3 parameters to test_external" + descr="$1" + shift + if ! test_skip "$descr" "$@" + then + # Announce the script to reduce confusion about the + # test output that follows. + say_color "" " run $(expr "$test_count" + 1): $descr ($*)" + # Run command; redirect its stderr to &4 as in + # test_run_, but keep its stdout on our stdout even in + # non-verbose mode. + "$@" 2>&4 + if [ "$?" = 0 ] + then + test_ok_ "$descr" + else + test_failure_ "$descr" "$@" + fi + fi +} + +# Like test_external, but in addition tests that the command generated +# no output on stderr. +test_external_without_stderr () { + # The temporary file has no (and must have no) security + # implications. + tmp="$TMPDIR"; if [ -z "$tmp" ]; then tmp=/tmp; fi + stderr="$tmp/git-external-stderr.$$.tmp" + test_external "$@" 4> "$stderr" + [ -f "$stderr" ] || error "Internal error: $stderr disappeared." + descr="no stderr: $1" + shift + say >&3 "expecting no stderr from previous command" + if [ ! -s "$stderr" ]; then + rm "$stderr" + test_ok_ "$descr" + else + if [ "$verbose" = t ]; then + output=`echo; echo Stderr is:; cat "$stderr"` + else + output= + fi + # rm first in case test_failure exits. + rm "$stderr" + test_failure_ "$descr" "$@" "$output" + fi +} + # This is not among top-level (test_expect_success | test_expect_failure) # but is a prefix that can be used in the test script, like: # From b4780d725c673db26692e11c56539381d60ad17c Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Thu, 19 Jun 2008 22:32:49 +0200 Subject: [PATCH 036/295] Git.pm: add test suite Add a shell script (t/t9700-perl-git.sh) that sets up a git repository and a perl script (t/t9700/test.pl) that runs the actual tests. Signed-off-by: Lea Wiemann Signed-off-by: Junio C Hamano --- t/t9700-perl-git.sh | 39 +++++++++++++++++ t/t9700/test.pl | 100 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 139 insertions(+) create mode 100755 t/t9700-perl-git.sh create mode 100755 t/t9700/test.pl diff --git a/t/t9700-perl-git.sh b/t/t9700-perl-git.sh new file mode 100755 index 0000000000..b2fb9ece9c --- /dev/null +++ b/t/t9700-perl-git.sh @@ -0,0 +1,39 @@ +#!/bin/sh +# +# Copyright (c) 2008 Lea Wiemann +# + +test_description='perl interface (Git.pm)' +. ./test-lib.sh + +# set up test repository + +test_expect_success \ + 'set up test repository' \ + 'echo "test file 1" > file1 && + echo "test file 2" > file2 && + mkdir directory1 && + echo "in directory1" >> directory1/file && + mkdir directory2 && + echo "in directory2" >> directory2/file && + git add . && + git commit -m "first commit" && + + echo "changed file 1" > file1 && + git commit -a -m "second commit" && + + git-config --add color.test.slot1 green && + git-config --add test.string value && + git-config --add test.dupstring value1 && + git-config --add test.dupstring value2 && + git-config --add test.booltrue true && + git-config --add test.boolfalse no && + git-config --add test.boolother other && + git-config --add test.int 2k + ' + +test_external_without_stderr \ + 'Perl API' \ + perl ../t9700/test.pl + +test_done diff --git a/t/t9700/test.pl b/t/t9700/test.pl new file mode 100755 index 0000000000..4d2312548a --- /dev/null +++ b/t/t9700/test.pl @@ -0,0 +1,100 @@ +#!/usr/bin/perl +use lib (split(/:/, $ENV{GITPERLLIB})); + +use 5.006002; +use warnings; +use strict; + +use Test::More qw(no_plan); + +use Cwd; +use File::Basename; +use File::Temp; + +BEGIN { use_ok('Git') } + +# set up +our $repo_dir = "trash directory"; +our $abs_repo_dir = Cwd->cwd; +die "this must be run by calling the t/t97* shell script(s)\n" + if basename(Cwd->cwd) ne $repo_dir; +ok(our $r = Git->repository(Directory => "."), "open repository"); + +# config +is($r->config("test.string"), "value", "config scalar: string"); +is_deeply([$r->config("test.dupstring")], ["value1", "value2"], + "config array: string"); +is($r->config("test.nonexistent"), undef, "config scalar: nonexistent"); +is_deeply([$r->config("test.nonexistent")], [], "config array: nonexistent"); +is($r->config_int("test.int"), 2048, "config_int: integer"); +is($r->config_int("test.nonexistent"), undef, "config_int: nonexistent"); +ok($r->config_bool("test.booltrue"), "config_bool: true"); +ok(!$r->config_bool("test.boolfalse"), "config_bool: false"); +our $ansi_green = "\x1b[32m"; +is($r->get_color("color.test.slot1", "red"), $ansi_green, "get_color"); +# Cannot test $r->get_colorbool("color.foo")) because we do not +# control whether our STDOUT is a terminal. + +# Failure cases for config: +# Save and restore STDERR; we will probably extract this into a +# "dies_ok" method and possibly move the STDERR handling to Git.pm. +open our $tmpstderr, ">&", STDERR or die "cannot save STDERR"; close STDERR; +eval { $r->config("test.dupstring") }; +ok($@, "config: duplicate entry in scalar context fails"); +eval { $r->config_bool("test.boolother") }; +ok($@, "config_bool: non-boolean values fail"); +open STDERR, ">&", $tmpstderr or die "cannot restore STDERR"; + +# ident +like($r->ident("aUthor"), qr/^A U Thor [0-9]+ \+0000$/, + "ident scalar: author (type)"); +like($r->ident("cOmmitter"), qr/^C O Mitter [0-9]+ \+0000$/, + "ident scalar: committer (type)"); +is($r->ident("invalid"), "invalid", "ident scalar: invalid ident string (no parsing)"); +my ($name, $email, $time_tz) = $r->ident('author'); +is_deeply([$name, $email], ["A U Thor", "author\@example.com"], + "ident array: author"); +like($time_tz, qr/[0-9]+ \+0000/, "ident array: author"); +is_deeply([$r->ident("Name 123 +0000")], ["Name", "email", "123 +0000"], + "ident array: ident string"); +is_deeply([$r->ident("invalid")], [], "ident array: invalid ident string"); + +# ident_person +is($r->ident_person("aUthor"), "A U Thor ", + "ident_person: author (type)"); +is($r->ident_person("Name 123 +0000"), "Name ", + "ident_person: ident string"); +is($r->ident_person("Name", "email", "123 +0000"), "Name ", + "ident_person: array"); + +# objects and hashes +ok(our $file1hash = $r->command_oneline('rev-parse', "HEAD:file1"), "(get file hash)"); +our $tmpfile = File::Temp->new; +is($r->cat_blob($file1hash, $tmpfile), 15, "cat_blob: size"); +our $blobcontents; +{ local $/; seek $tmpfile, 0, 0; $blobcontents = <$tmpfile>; } +is($blobcontents, "changed file 1\n", "cat_blob: data"); +seek $tmpfile, 0, 0; +is(Git::hash_object("blob", $tmpfile), $file1hash, "hash_object: roundtrip"); +$tmpfile = File::Temp->new(); +print $tmpfile my $test_text = "test blob, to be inserted\n"; +like(our $newhash = $r->hash_and_insert_object($tmpfile), qr/[0-9a-fA-F]{40}/, + "hash_and_insert_object: returns hash"); +$tmpfile = File::Temp->new; +is($r->cat_blob($newhash, $tmpfile), length $test_text, "cat_blob: roundtrip size"); +{ local $/; seek $tmpfile, 0, 0; $blobcontents = <$tmpfile>; } +is($blobcontents, $test_text, "cat_blob: roundtrip data"); + +# paths +is($r->repo_path, "./.git", "repo_path"); +is($r->wc_path, $abs_repo_dir . "/", "wc_path"); +is($r->wc_subdir, "", "wc_subdir initial"); +$r->wc_chdir("directory1"); +is($r->wc_subdir, "directory1", "wc_subdir after wc_chdir"); +TODO: { + local $TODO = "commands do not work after wc_chdir"; + # Failure output is active even in non-verbose mode and thus + # annoying. Hence we skip these tests as long as they fail. + todo_skip 'config after wc_chdir', 1; + is($r->config("color.string"), "value", "config after wc_chdir"); +} From df6a7ff7ac55d320afa1b8a59393122d6ca0f6c4 Mon Sep 17 00:00:00 2001 From: Pieter de Bie Date: Wed, 11 Jun 2008 13:17:04 +0200 Subject: [PATCH 037/295] builtin-fast-export: Add importing and exporting of revision marks This adds the --import-marks and --export-marks to fast-export. These import and export the marks used to for all revisions exported in a similar fashion to what fast-import does. The format is the same as fast-import, so you can create a bidirectional importer / exporter by using the same marks file on both sides. Signed-off-by: Pieter de Bie Signed-off-by: Junio C Hamano --- Documentation/git-fast-export.txt | 20 +++++++ builtin-fast-export.c | 99 +++++++++++++++++++++++++++++-- t/t9301-fast-export.sh | 24 ++++++++ 3 files changed, 137 insertions(+), 6 deletions(-) diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt index 332346cc5d..277a547a02 100644 --- a/Documentation/git-fast-export.txt +++ b/Documentation/git-fast-export.txt @@ -36,6 +36,26 @@ when encountering a signed tag. With 'strip', the tags will be made unsigned, with 'verbatim', they will be silently exported and with 'warn', they will be exported, but you will see a warning. +--export-marks=:: + Dumps the internal marks table to when complete. + Marks are written one per line as `:markid SHA-1`. Only marks + for revisions are dumped; marks for blobs are ignored. + Backends can use this file to validate imports after they + have been completed, or to save the marks table across + incremental runs. As is only opened and truncated + at completion, the same path can also be safely given to + \--import-marks. + +--import-marks=:: + Before processing any input, load the marks specified in + . The input file must exist, must be readable, and + must use the same format as produced by \--export-marks. ++ +Any commits that have already been marked will not be exported again. +If the backend uses a similar \--import-marks file, this allows for +incremental bidirectional exporting of the repository by keeping the +marks the same across runs. + EXAMPLES -------- diff --git a/builtin-fast-export.c b/builtin-fast-export.c index d0a462ff8b..45786ef1b7 100644 --- a/builtin-fast-export.c +++ b/builtin-fast-export.c @@ -56,10 +56,24 @@ static int has_unshown_parent(struct commit *commit) } /* Since intptr_t is C99, we do not use it here */ -static void mark_object(struct object *object) +static inline uint32_t *mark_to_ptr(uint32_t mark) { - last_idnum++; - add_decoration(&idnums, object, ((uint32_t *)NULL) + last_idnum); + return ((uint32_t *)NULL) + mark; +} + +static inline uint32_t ptr_to_mark(void * mark) +{ + return (uint32_t *)mark - (uint32_t *)NULL; +} + +static inline void mark_object(struct object *object, uint32_t mark) +{ + add_decoration(&idnums, object, mark_to_ptr(mark)); +} + +static inline void mark_next_object(struct object *object) +{ + mark_object(object, ++last_idnum); } static int get_object_mark(struct object *object) @@ -67,7 +81,7 @@ static int get_object_mark(struct object *object) void *decoration = lookup_decoration(&idnums, object); if (!decoration) return 0; - return (uint32_t *)decoration - (uint32_t *)NULL; + return ptr_to_mark(decoration); } static void show_progress(void) @@ -100,7 +114,7 @@ static void handle_object(const unsigned char *sha1) if (!buf) die ("Could not read blob %s", sha1_to_hex(sha1)); - mark_object(object); + mark_next_object(object); printf("blob\nmark :%d\ndata %lu\n", last_idnum, size); if (size && fwrite(buf, size, 1, stdout) != 1) @@ -185,7 +199,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev) for (i = 0; i < diff_queued_diff.nr; i++) handle_object(diff_queued_diff.queue[i]->two->sha1); - mark_object(&commit->object); + mark_next_object(&commit->object); if (!is_encoding_utf8(encoding)) reencoded = reencode_string(message, "UTF-8", encoding); if (!commit->parents) @@ -354,18 +368,85 @@ static void handle_tags_and_duplicates(struct path_list *extra_refs) } } +static void export_marks(char *file) +{ + unsigned int i; + uint32_t mark; + struct object_decoration *deco = idnums.hash; + FILE *f; + + f = fopen(file, "w"); + if (!f) + error("Unable to open marks file %s for writing", file); + + for (i = 0; i < idnums.size; ++i) { + deco++; + if (deco && deco->base && deco->base->type == 1) { + mark = ptr_to_mark(deco->decoration); + fprintf(f, ":%u %s\n", mark, sha1_to_hex(deco->base->sha1)); + } + } + + if (ferror(f) || fclose(f)) + error("Unable to write marks file %s.", file); +} + +static void import_marks(char * input_file) +{ + char line[512]; + FILE *f = fopen(input_file, "r"); + if (!f) + die("cannot read %s: %s", input_file, strerror(errno)); + + while (fgets(line, sizeof(line), f)) { + uint32_t mark; + char *line_end, *mark_end; + unsigned char sha1[20]; + struct object *object; + + line_end = strchr(line, '\n'); + if (line[0] != ':' || !line_end) + die("corrupt mark line: %s", line); + *line_end = 0; + + mark = strtoumax(line + 1, &mark_end, 10); + if (!mark || mark_end == line + 1 + || *mark_end != ' ' || get_sha1(mark_end + 1, sha1)) + die("corrupt mark line: %s", line); + + object = parse_object(sha1); + if (!object) + die ("Could not read blob %s", sha1_to_hex(sha1)); + + if (object->flags & SHOWN) + error("Object %s already has a mark", sha1); + + mark_object(object, mark); + if (last_idnum < mark) + last_idnum = mark; + + object->flags |= SHOWN; + } + fclose(f); +} + int cmd_fast_export(int argc, const char **argv, const char *prefix) { struct rev_info revs; struct object_array commits = { 0, 0, NULL }; struct path_list extra_refs = { NULL, 0, 0, 0 }; struct commit *commit; + char *export_filename = NULL, *import_filename = NULL; struct option options[] = { OPT_INTEGER(0, "progress", &progress, "show progress after objects"), OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode", "select handling of signed tags", parse_opt_signed_tag_mode), + OPT_STRING(0, "export-marks", &export_filename, "FILE", + "Dump marks to this file"), + OPT_STRING(0, "import-marks", &import_filename, "FILE", + "Import marks from this file"), OPT_END() }; @@ -378,6 +459,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) if (argc > 1) usage_with_options (fast_export_usage, options); + if (import_filename) + import_marks(import_filename); + get_tags_and_duplicates(&revs.pending, &extra_refs); if (prepare_revision_walk(&revs)) @@ -400,5 +484,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix) handle_tags_and_duplicates(&extra_refs); + if (export_filename) + export_marks(export_filename); + return 0; } diff --git a/t/t9301-fast-export.sh b/t/t9301-fast-export.sh index f09bfb1117..60b5ee3979 100755 --- a/t/t9301-fast-export.sh +++ b/t/t9301-fast-export.sh @@ -77,6 +77,30 @@ test_expect_success 'iso-8859-1' ' git fast-import && git cat-file commit i18n | grep "Áéí óú") +' +test_expect_success 'import/export-marks' ' + + git checkout -b marks master && + git fast-export --export-marks=tmp-marks HEAD && + test -s tmp-marks && + cp tmp-marks ~ && + test $(wc -l < tmp-marks) -eq 3 && + test $( + git fast-export --import-marks=tmp-marks\ + --export-marks=tmp-marks HEAD | + grep ^commit | + wc -l) \ + -eq 0 && + echo change > file && + git commit -m "last commit" file && + test $( + git fast-export --import-marks=tmp-marks \ + --export-marks=tmp-marks HEAD | + grep ^commit\ | + wc -l) \ + -eq 1 && + test $(wc -l < tmp-marks) -eq 4 + ' cat > signed-tag-import << EOF From 48ec3e5c073e97c15842ac16523444786b37774e Mon Sep 17 00:00:00 2001 From: Johan Herland Date: Sun, 15 Jun 2008 16:04:20 +0200 Subject: [PATCH 038/295] Incorporate fetched packs in future object traversal Immediately after fetching a pack, we should call reprepare_packed_git() to make sure the objects in the pack are reachable. Otherwise, we will fail to look up objects that are present only in the fetched pack. Signed-off-by: Johan Herland Signed-off-by: Junio C Hamano --- builtin-fetch-pack.c | 1 + 1 file changed, 1 insertion(+) diff --git a/builtin-fetch-pack.c b/builtin-fetch-pack.c index de1e8d1365..f4dbcf069e 100644 --- a/builtin-fetch-pack.c +++ b/builtin-fetch-pack.c @@ -820,5 +820,6 @@ struct ref *fetch_pack(struct fetch_pack_args *my_args, } } + reprepare_packed_git(); return ref_cpy; } From 94e724a741590e741a540075c07a961082e3c80a Mon Sep 17 00:00:00 2001 From: Johan Herland Date: Sun, 15 Jun 2008 16:05:06 +0200 Subject: [PATCH 039/295] Move pack_refs() and friends into libgit This moves pack_refs() and underlying functionality into the library, to make pack-refs functionality easily available to all git programs. Most of builtin-pack-refs.c has been moved verbatim into a new file pack-refs.c that is compiled into libgit.a. A corresponding header file, pack-refs.h, has also been added, declaring pack_refs() and the #defines associated with the flags parameter to pack_refs(). This patch introduces no other changes in functionality. Signed-off-by: Johan Herland Signed-off-by: Junio C Hamano --- Makefile | 2 + builtin-pack-refs.c | 121 +------------------------------------------- pack-refs.c | 117 ++++++++++++++++++++++++++++++++++++++++++ pack-refs.h | 18 +++++++ 4 files changed, 138 insertions(+), 120 deletions(-) create mode 100644 pack-refs.c create mode 100644 pack-refs.h diff --git a/Makefile b/Makefile index b003e3e60a..adbe44213a 100644 --- a/Makefile +++ b/Makefile @@ -354,6 +354,7 @@ LIB_H += log-tree.h LIB_H += mailmap.h LIB_H += object.h LIB_H += pack.h +LIB_H += pack-refs.h LIB_H += pack-revindex.h LIB_H += parse-options.h LIB_H += patch-ids.h @@ -429,6 +430,7 @@ LIB_OBJS += merge-file.o LIB_OBJS += name-hash.o LIB_OBJS += object.o LIB_OBJS += pack-check.o +LIB_OBJS += pack-refs.o LIB_OBJS += pack-revindex.o LIB_OBJS += pack-write.o LIB_OBJS += pager.o diff --git a/builtin-pack-refs.c b/builtin-pack-refs.c index 1aaa76dd1f..ff90aefa1c 100644 --- a/builtin-pack-refs.c +++ b/builtin-pack-refs.c @@ -1,125 +1,6 @@ -#include "builtin.h" #include "cache.h" -#include "refs.h" -#include "object.h" -#include "tag.h" #include "parse-options.h" - -struct ref_to_prune { - struct ref_to_prune *next; - unsigned char sha1[20]; - char name[FLEX_ARRAY]; -}; - -#define PACK_REFS_PRUNE 0x0001 -#define PACK_REFS_ALL 0x0002 - -struct pack_refs_cb_data { - unsigned int flags; - struct ref_to_prune *ref_to_prune; - FILE *refs_file; -}; - -static int do_not_prune(int flags) -{ - /* If it is already packed or if it is a symref, - * do not prune it. - */ - return (flags & (REF_ISSYMREF|REF_ISPACKED)); -} - -static int handle_one_ref(const char *path, const unsigned char *sha1, - int flags, void *cb_data) -{ - struct pack_refs_cb_data *cb = cb_data; - int is_tag_ref; - - /* Do not pack the symbolic refs */ - if ((flags & REF_ISSYMREF)) - return 0; - is_tag_ref = !prefixcmp(path, "refs/tags/"); - - /* ALWAYS pack refs that were already packed or are tags */ - if (!(cb->flags & PACK_REFS_ALL) && !is_tag_ref && !(flags & REF_ISPACKED)) - return 0; - - fprintf(cb->refs_file, "%s %s\n", sha1_to_hex(sha1), path); - if (is_tag_ref) { - struct object *o = parse_object(sha1); - if (o->type == OBJ_TAG) { - o = deref_tag(o, path, 0); - if (o) - fprintf(cb->refs_file, "^%s\n", - sha1_to_hex(o->sha1)); - } - } - - if ((cb->flags & PACK_REFS_PRUNE) && !do_not_prune(flags)) { - int namelen = strlen(path) + 1; - struct ref_to_prune *n = xcalloc(1, sizeof(*n) + namelen); - hashcpy(n->sha1, sha1); - strcpy(n->name, path); - n->next = cb->ref_to_prune; - cb->ref_to_prune = n; - } - return 0; -} - -/* make sure nobody touched the ref, and unlink */ -static void prune_ref(struct ref_to_prune *r) -{ - struct ref_lock *lock = lock_ref_sha1(r->name + 5, r->sha1); - - if (lock) { - unlink(git_path("%s", r->name)); - unlock_ref(lock); - } -} - -static void prune_refs(struct ref_to_prune *r) -{ - while (r) { - prune_ref(r); - r = r->next; - } -} - -static struct lock_file packed; - -static int pack_refs(unsigned int flags) -{ - int fd; - struct pack_refs_cb_data cbdata; - - memset(&cbdata, 0, sizeof(cbdata)); - cbdata.flags = flags; - - fd = hold_lock_file_for_update(&packed, git_path("packed-refs"), 1); - cbdata.refs_file = fdopen(fd, "w"); - if (!cbdata.refs_file) - die("unable to create ref-pack file structure (%s)", - strerror(errno)); - - /* perhaps other traits later as well */ - fprintf(cbdata.refs_file, "# pack-refs with: peeled \n"); - - for_each_ref(handle_one_ref, &cbdata); - if (ferror(cbdata.refs_file)) - die("failed to write ref-pack file"); - if (fflush(cbdata.refs_file) || fsync(fd) || fclose(cbdata.refs_file)) - die("failed to write ref-pack file (%s)", strerror(errno)); - /* - * Since the lock file was fdopen()'ed and then fclose()'ed above, - * assign -1 to the lock file descriptor so that commit_lock_file() - * won't try to close() it. - */ - packed.fd = -1; - if (commit_lock_file(&packed) < 0) - die("unable to overwrite old ref-pack file (%s)", strerror(errno)); - if (cbdata.flags & PACK_REFS_PRUNE) - prune_refs(cbdata.ref_to_prune); - return 0; -} +#include "pack-refs.h" static char const * const pack_refs_usage[] = { "git-pack-refs [options]", diff --git a/pack-refs.c b/pack-refs.c new file mode 100644 index 0000000000..848d311c2b --- /dev/null +++ b/pack-refs.c @@ -0,0 +1,117 @@ +#include "cache.h" +#include "refs.h" +#include "tag.h" +#include "pack-refs.h" + +struct ref_to_prune { + struct ref_to_prune *next; + unsigned char sha1[20]; + char name[FLEX_ARRAY]; +}; + +struct pack_refs_cb_data { + unsigned int flags; + struct ref_to_prune *ref_to_prune; + FILE *refs_file; +}; + +static int do_not_prune(int flags) +{ + /* If it is already packed or if it is a symref, + * do not prune it. + */ + return (flags & (REF_ISSYMREF|REF_ISPACKED)); +} + +static int handle_one_ref(const char *path, const unsigned char *sha1, + int flags, void *cb_data) +{ + struct pack_refs_cb_data *cb = cb_data; + int is_tag_ref; + + /* Do not pack the symbolic refs */ + if ((flags & REF_ISSYMREF)) + return 0; + is_tag_ref = !prefixcmp(path, "refs/tags/"); + + /* ALWAYS pack refs that were already packed or are tags */ + if (!(cb->flags & PACK_REFS_ALL) && !is_tag_ref && !(flags & REF_ISPACKED)) + return 0; + + fprintf(cb->refs_file, "%s %s\n", sha1_to_hex(sha1), path); + if (is_tag_ref) { + struct object *o = parse_object(sha1); + if (o->type == OBJ_TAG) { + o = deref_tag(o, path, 0); + if (o) + fprintf(cb->refs_file, "^%s\n", + sha1_to_hex(o->sha1)); + } + } + + if ((cb->flags & PACK_REFS_PRUNE) && !do_not_prune(flags)) { + int namelen = strlen(path) + 1; + struct ref_to_prune *n = xcalloc(1, sizeof(*n) + namelen); + hashcpy(n->sha1, sha1); + strcpy(n->name, path); + n->next = cb->ref_to_prune; + cb->ref_to_prune = n; + } + return 0; +} + +/* make sure nobody touched the ref, and unlink */ +static void prune_ref(struct ref_to_prune *r) +{ + struct ref_lock *lock = lock_ref_sha1(r->name + 5, r->sha1); + + if (lock) { + unlink(git_path("%s", r->name)); + unlock_ref(lock); + } +} + +static void prune_refs(struct ref_to_prune *r) +{ + while (r) { + prune_ref(r); + r = r->next; + } +} + +static struct lock_file packed; + +int pack_refs(unsigned int flags) +{ + int fd; + struct pack_refs_cb_data cbdata; + + memset(&cbdata, 0, sizeof(cbdata)); + cbdata.flags = flags; + + fd = hold_lock_file_for_update(&packed, git_path("packed-refs"), 1); + cbdata.refs_file = fdopen(fd, "w"); + if (!cbdata.refs_file) + die("unable to create ref-pack file structure (%s)", + strerror(errno)); + + /* perhaps other traits later as well */ + fprintf(cbdata.refs_file, "# pack-refs with: peeled \n"); + + for_each_ref(handle_one_ref, &cbdata); + if (ferror(cbdata.refs_file)) + die("failed to write ref-pack file"); + if (fflush(cbdata.refs_file) || fsync(fd) || fclose(cbdata.refs_file)) + die("failed to write ref-pack file (%s)", strerror(errno)); + /* + * Since the lock file was fdopen()'ed and then fclose()'ed above, + * assign -1 to the lock file descriptor so that commit_lock_file() + * won't try to close() it. + */ + packed.fd = -1; + if (commit_lock_file(&packed) < 0) + die("unable to overwrite old ref-pack file (%s)", strerror(errno)); + if (cbdata.flags & PACK_REFS_PRUNE) + prune_refs(cbdata.ref_to_prune); + return 0; +} diff --git a/pack-refs.h b/pack-refs.h new file mode 100644 index 0000000000..518acfb370 --- /dev/null +++ b/pack-refs.h @@ -0,0 +1,18 @@ +#ifndef PACK_REFS_H +#define PACK_REFS_H + +/* + * Flags for controlling behaviour of pack_refs() + * PACK_REFS_PRUNE: Prune loose refs after packing + * PACK_REFS_ALL: Pack _all_ refs, not just tags and already packed refs + */ +#define PACK_REFS_PRUNE 0x0001 +#define PACK_REFS_ALL 0x0002 + +/* + * Write a packed-refs file for the current repository. + * flags: Combination of the above PACK_REFS_* flags. + */ +int pack_refs(unsigned int flags); + +#endif /* PACK_REFS_H */ From d0d12b476822bb8686ee883bd44b799563069a48 Mon Sep 17 00:00:00 2001 From: Johan Herland Date: Mon, 16 Jun 2008 01:16:53 +0200 Subject: [PATCH 040/295] Prepare testsuite for a "git clone" that packs refs t5515-fetch-merge-logic removes many, but not all, refs between each test. This is done by removing the corresponding refs/foo/* files in the .git/refs hierarchy. However, once "git clone" starts producing packed refs, these refs will no longer be in the .git/refs hierarchy, but rather listed in .git/packed-refs. This patch teaches t5515-fetch-merge-logic to remove the refs using "git update-ref -d" which properly handles packed refs. Signed-off-by: Johan Herland Signed-off-by: Junio C Hamano --- t/t5515-fetch-merge-logic.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/t/t5515-fetch-merge-logic.sh b/t/t5515-fetch-merge-logic.sh index 3def75eeb2..8becbc3f38 100755 --- a/t/t5515-fetch-merge-logic.sh +++ b/t/t5515-fetch-merge-logic.sh @@ -142,9 +142,12 @@ do set x $cmd; shift git symbolic-ref HEAD refs/heads/$1 ; shift rm -f .git/FETCH_HEAD - rm -f .git/refs/heads/* - rm -f .git/refs/remotes/rem/* - rm -f .git/refs/tags/* + git for-each-ref \ + refs/heads refs/remotes/rem refs/tags | + while read val type refname + do + git update-ref -d "$refname" "$val" + done git fetch "$@" >/dev/null cat .git/FETCH_HEAD } >"$actual_f" && From 3e8aded20329bef35470eb469281f6b275d19dea Mon Sep 17 00:00:00 2001 From: Johan Herland Date: Sun, 15 Jun 2008 16:06:16 +0200 Subject: [PATCH 041/295] Teach "git clone" to pack refs In repos with many refs, it is unlikely that most refs will ever change. This fact is already exploited by "git gc" by executing "git pack-refs" to consolidate all refs into a single file. When cloning a repo with many refs, it does not make sense to create the loose refs in the first place, just to have the next "git gc" consolidate them into one file. Instead, make "git clone" create the packed refs file immediately, and forego the loose refs completely. Signed-off-by: Johan Herland Acked-by: Daniel Barkalow Signed-off-by: Junio C Hamano --- builtin-clone.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/builtin-clone.c b/builtin-clone.c index 7190952071..5c5acb4bb1 100644 --- a/builtin-clone.c +++ b/builtin-clone.c @@ -18,6 +18,7 @@ #include "transport.h" #include "strbuf.h" #include "dir.h" +#include "pack-refs.h" /* * Overall FIXMEs: @@ -321,8 +322,11 @@ static struct ref *write_remote_refs(const struct ref *refs, get_fetch_map(refs, tag_refspec, &tail, 0); for (r = local_refs; r; r = r->next) - update_ref(reflog, - r->peer_ref->name, r->old_sha1, NULL, 0, DIE_ON_ERR); + add_extra_ref(r->peer_ref->name, r->old_sha1, 0); + + pack_refs(PACK_REFS_ALL); + clear_extra_refs(); + return local_refs; } From f28ac70f48aa36f0d6ea1cbaa967b56802549016 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nguy=E1=BB=85n=20Th=C3=A1i=20Ng=E1=BB=8Dc=20Duy?= Date: Wed, 28 Nov 2007 23:21:57 +0700 Subject: [PATCH 042/295] Move all dashed-form commands to libexecdir MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Nguyễn Thái Ngọc Duy Signed-off-by: Junio C Hamano --- Makefile | 3 ++- check_bindir | 13 +++++++++++++ config.mak.in | 2 +- git.spec.in | 13 +++++++------ 4 files changed, 23 insertions(+), 8 deletions(-) create mode 100755 check_bindir diff --git a/Makefile b/Makefile index b003e3e60a..929136ba39 100644 --- a/Makefile +++ b/Makefile @@ -174,7 +174,7 @@ prefix = $(HOME) bindir = $(prefix)/bin mandir = $(prefix)/share/man infodir = $(prefix)/share/info -gitexecdir = $(bindir) +gitexecdir = $(prefix)/libexec/git-core sharedir = $(prefix)/share template_dir = $(sharedir)/git-core/templates htmldir=$(sharedir)/doc/git-doc @@ -1286,6 +1286,7 @@ endif ifneq (,$X) $(foreach p,$(patsubst %$X,%,$(filter %$X,$(ALL_PROGRAMS) $(BUILT_INS) git$X)), $(RM) '$(DESTDIR_SQ)$(gitexecdir_SQ)/$p';) endif + ./check_bindir 'z$(bindir_SQ)' 'z$(gitexecdir_SQ)' '$(DESTDIR_SQ)$(bindir_SQ)/git-shell$X' install-doc: $(MAKE) -C Documentation install diff --git a/check_bindir b/check_bindir new file mode 100755 index 0000000000..a1c4c3e8d8 --- /dev/null +++ b/check_bindir @@ -0,0 +1,13 @@ +#!/bin/sh +bindir="$1" +gitexecdir="$2" +gitcmd="$3" +if test "$bindir" != "$gitexecdir" -a -x "$gitcmd" +then + echo + echo "!! You have installed git-* commands to new gitexecdir." + echo "!! Old version git-* commands still remain in bindir." + echo "!! Mixing two versions of Git will lead to problems." + echo "!! Please remove old version commands in bindir now." + echo +fi diff --git a/config.mak.in b/config.mak.in index 7868dfd93a..b776149531 100644 --- a/config.mak.in +++ b/config.mak.in @@ -11,7 +11,7 @@ TCLTK_PATH = @TCLTK_PATH@ prefix = @prefix@ exec_prefix = @exec_prefix@ bindir = @bindir@ -#gitexecdir = @libexecdir@/git-core/ +gitexecdir = @libexecdir@/git-core/ datarootdir = @datarootdir@ template_dir = @datadir@/git-core/templates/ diff --git a/git.spec.in b/git.spec.in index 3d7f3ef4af..c6492e5be2 100644 --- a/git.spec.in +++ b/git.spec.in @@ -117,6 +117,7 @@ find $RPM_BUILD_ROOT -type f -name '*.bs' -empty -exec rm -f {} ';' find $RPM_BUILD_ROOT -type f -name perllocal.pod -exec rm -f {} ';' (find $RPM_BUILD_ROOT%{_bindir} -type f | grep -vE "archimport|svn|cvs|email|gitk|git-gui|git-citool" | sed -e s@^$RPM_BUILD_ROOT@@) > bin-man-doc-files +(find $RPM_BUILD_ROOT%{_libexecdir}/git-core -type f | grep -vE "archimport|svn|cvs|email|gitk|git-gui|git-citool" | sed -e s@^$RPM_BUILD_ROOT@@) >> bin-man-doc-files (find $RPM_BUILD_ROOT%{perl_vendorlib} -type f | sed -e s@^$RPM_BUILD_ROOT@@) >> perl-files %if %{!?_without_docs:1}0 (find $RPM_BUILD_ROOT%{_mandir} $RPM_BUILD_ROOT/Documentation -type f | grep -vE "archimport|svn|git-cvs|email|gitk|git-gui|git-citool" | sed -e s@^$RPM_BUILD_ROOT@@ -e 's/$/*/' ) >> bin-man-doc-files @@ -136,7 +137,7 @@ rm -rf $RPM_BUILD_ROOT %files svn %defattr(-,root,root) -%{_bindir}/*svn* +%{_libexecdir}/git-core/*svn* %doc Documentation/*svn*.txt %{!?_without_docs: %{_mandir}/man1/*svn*.1*} %{!?_without_docs: %doc Documentation/*svn*.html } @@ -144,28 +145,28 @@ rm -rf $RPM_BUILD_ROOT %files cvs %defattr(-,root,root) %doc Documentation/*git-cvs*.txt -%{_bindir}/*cvs* +%{_libexecdir}/git-core/*cvs* %{!?_without_docs: %{_mandir}/man1/*cvs*.1*} %{!?_without_docs: %doc Documentation/*git-cvs*.html } %files arch %defattr(-,root,root) %doc Documentation/git-archimport.txt -%{_bindir}/git-archimport +%{_libexecdir}/git-core/git-archimport %{!?_without_docs: %{_mandir}/man1/git-archimport.1*} %{!?_without_docs: %doc Documentation/git-archimport.html } %files email %defattr(-,root,root) %doc Documentation/*email*.txt -%{_bindir}/*email* +%{_libexecdir}/git-core/*email* %{!?_without_docs: %{_mandir}/man1/*email*.1*} %{!?_without_docs: %doc Documentation/*email*.html } %files gui %defattr(-,root,root) -%{_bindir}/git-gui -%{_bindir}/git-citool +%{_libexecdir}/git-core/git-gui +%{_libexecdir}/git-core/git-citool %{_datadir}/git-gui/ %{!?_without_docs: %{_mandir}/man1/git-gui.1*} %{!?_without_docs: %doc Documentation/git-gui.html} From 78d0f5d210bc053d961185be6cfb0e248a0bdda3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E3=81=97=E3=82=89=E3=81=84=E3=81=97=E3=81=AA=E3=81=AA?= =?UTF-8?q?=E3=81=93?= Date: Thu, 19 Jun 2008 08:21:09 +0900 Subject: [PATCH 043/295] environment.c: remove unused function get_refs_directory() is not used anywhere. Signed-off-by: Nanako Shiraishi Signed-off-by: Junio C Hamano --- cache.h | 1 - environment.c | 7 ------- 2 files changed, 8 deletions(-) diff --git a/cache.h b/cache.h index 81b7e17de2..feb49b788f 100644 --- a/cache.h +++ b/cache.h @@ -311,7 +311,6 @@ extern char *git_work_tree_cfg; extern int is_inside_work_tree(void); extern const char *get_git_dir(void); extern char *get_object_directory(void); -extern char *get_refs_directory(void); extern char *get_index_file(void); extern char *get_graft_file(void); extern int set_git_dir(const char *path); diff --git a/environment.c b/environment.c index 73feb2d03a..187248bf5d 100644 --- a/environment.c +++ b/environment.c @@ -129,13 +129,6 @@ char *get_object_directory(void) return git_object_dir; } -char *get_refs_directory(void) -{ - if (!git_refs_dir) - setup_git_env(); - return git_refs_dir; -} - char *get_index_file(void) { if (!git_index_file) From e4bffb5a1d9ab3c9c0ef0541a395d47516480d97 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E3=81=97=E3=82=89=E3=81=84=E3=81=97=E3=81=AA=E3=81=AA?= =?UTF-8?q?=E3=81=93?= Date: Thu, 19 Jun 2008 08:21:11 +0900 Subject: [PATCH 044/295] config.c: make git_env_bool() static This function is not used by any other file. Signed-off-by: Nanako Shiraishi Signed-off-by: Junio C Hamano --- cache.h | 1 - config.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/cache.h b/cache.h index feb49b788f..8140763008 100644 --- a/cache.h +++ b/cache.h @@ -734,7 +734,6 @@ extern int git_config_set_multivar(const char *, const char *, const char *, int extern int git_config_rename_section(const char *, const char *); extern const char *git_etc_gitconfig(void); extern int check_repository_format_version(const char *var, const char *value, void *cb); -extern int git_env_bool(const char *, int); extern int git_config_system(void); extern int git_config_global(void); extern int config_error_nonbool(const char *); diff --git a/config.c b/config.c index c2f2bbb000..04d97e3d0b 100644 --- a/config.c +++ b/config.c @@ -549,7 +549,7 @@ const char *git_etc_gitconfig(void) return system_wide; } -int git_env_bool(const char *k, int def) +static int git_env_bool(const char *k, int def) { const char *v = getenv(k); return v ? git_config_bool(k, v) : def; From 074afaa0cf69e7d49bc00d969f57893c9ddea748 Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Thu, 19 Jun 2008 22:03:21 +0200 Subject: [PATCH 045/295] gitweb: standarize HTTP status codes Many error status codes simply default to 403 Forbidden, which is not correct in most cases. This patch makes gitweb return semantically correct status codes. For convenience the die_error function now only takes the status code without reason as first parameter (e.g. 404 instead of "404 Not Found"), and it now defaults to 500 (Internal Server Error), even though the default is not used anywhere. Also documented status code conventions in die_error. Signed-off-by: Lea Wiemann Acked-by: Jakub Narebski Signed-off-by: Junio C Hamano --- gitweb/gitweb.perl | 209 ++++++++++++++++++++++----------------------- 1 file changed, 104 insertions(+), 105 deletions(-) diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 49b01d8c25..5351da2c11 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -386,7 +386,7 @@ $projects_list ||= $projectroot; our $action = $cgi->param('a'); if (defined $action) { if ($action =~ m/[^0-9a-zA-Z\.\-_]/) { - die_error(undef, "Invalid action parameter"); + die_error(400, "Invalid action parameter"); } } @@ -399,21 +399,21 @@ if (defined $project) { ($export_ok && !(-e "$projectroot/$project/$export_ok")) || ($strict_export && !project_in_list($project))) { undef $project; - die_error(undef, "No such project"); + die_error(404, "No such project"); } } our $file_name = $cgi->param('f'); if (defined $file_name) { if (!validate_pathname($file_name)) { - die_error(undef, "Invalid file parameter"); + die_error(400, "Invalid file parameter"); } } our $file_parent = $cgi->param('fp'); if (defined $file_parent) { if (!validate_pathname($file_parent)) { - die_error(undef, "Invalid file parent parameter"); + die_error(400, "Invalid file parent parameter"); } } @@ -421,21 +421,21 @@ if (defined $file_parent) { our $hash = $cgi->param('h'); if (defined $hash) { if (!validate_refname($hash)) { - die_error(undef, "Invalid hash parameter"); + die_error(400, "Invalid hash parameter"); } } our $hash_parent = $cgi->param('hp'); if (defined $hash_parent) { if (!validate_refname($hash_parent)) { - die_error(undef, "Invalid hash parent parameter"); + die_error(400, "Invalid hash parent parameter"); } } our $hash_base = $cgi->param('hb'); if (defined $hash_base) { if (!validate_refname($hash_base)) { - die_error(undef, "Invalid hash base parameter"); + die_error(400, "Invalid hash base parameter"); } } @@ -447,10 +447,10 @@ our @extra_options = $cgi->param('opt'); if (defined @extra_options) { foreach my $opt (@extra_options) { if (not exists $allowed_options{$opt}) { - die_error(undef, "Invalid option parameter"); + die_error(400, "Invalid option parameter"); } if (not grep(/^$action$/, @{$allowed_options{$opt}})) { - die_error(undef, "Invalid option parameter for this action"); + die_error(400, "Invalid option parameter for this action"); } } } @@ -458,7 +458,7 @@ if (defined @extra_options) { our $hash_parent_base = $cgi->param('hpb'); if (defined $hash_parent_base) { if (!validate_refname($hash_parent_base)) { - die_error(undef, "Invalid hash parent base parameter"); + die_error(400, "Invalid hash parent base parameter"); } } @@ -466,14 +466,14 @@ if (defined $hash_parent_base) { our $page = $cgi->param('pg'); if (defined $page) { if ($page =~ m/[^0-9]/) { - die_error(undef, "Invalid page parameter"); + die_error(400, "Invalid page parameter"); } } our $searchtype = $cgi->param('st'); if (defined $searchtype) { if ($searchtype =~ m/[^a-z]/) { - die_error(undef, "Invalid searchtype parameter"); + die_error(400, "Invalid searchtype parameter"); } } @@ -483,7 +483,7 @@ our $searchtext = $cgi->param('s'); our $search_regexp; if (defined $searchtext) { if (length($searchtext) < 2) { - die_error(undef, "At least two characters are required for search parameter"); + die_error(403, "At least two characters are required for search parameter"); } $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } @@ -580,11 +580,11 @@ if (!defined $action) { } } if (!defined($actions{$action})) { - die_error(undef, "Unknown action"); + die_error(400, "Unknown action"); } if ($action !~ m/^(opml|project_list|project_index)$/ && !$project) { - die_error(undef, "Project needed"); + die_error(400, "Project needed"); } $actions{$action}->(); exit; @@ -1665,7 +1665,7 @@ sub git_get_hash_by_path { $path =~ s,/+$,,; open my $fd, "-|", git_cmd(), "ls-tree", $base, "--", $path - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd or return undef; @@ -2127,7 +2127,7 @@ sub parse_commit { "--max-count=1", $commit_id, "--", - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); %co = parse_commit_text(<$fd>, 1); close $fd; @@ -2152,7 +2152,7 @@ sub parse_commits { $commit_id, "--", ($filename ? ($filename) : ()) - or die_error(undef, "Open git-rev-list failed"); + or die_error(500, "Open git-rev-list failed"); while (my $line = <$fd>) { my %co = parse_commit_text($line); push @cos, \%co; @@ -2672,11 +2672,26 @@ sub git_footer_html { ""; } +# die_error(, ) +# Example: die_error(404, 'Hash not found') +# By convention, use the following status codes (as defined in RFC 2616): +# 400: Invalid or missing CGI parameters, or +# requested object exists but has wrong type. +# 403: Requested feature (like "pickaxe" or "snapshot") not enabled on +# this server or project. +# 404: Requested object/revision/project doesn't exist. +# 500: The server isn't configured properly, or +# an internal error occurred (e.g. failed assertions caused by bugs), or +# an unknown error occurred (e.g. the git binary died unexpectedly). sub die_error { - my $status = shift || "403 Forbidden"; - my $error = shift || "Malformed query, file missing or permission denied"; + my $status = shift || 500; + my $error = shift || "Internal server error"; - git_header_html($status); + my %http_responses = (400 => '400 Bad Request', + 403 => '403 Forbidden', + 404 => '404 Not Found', + 500 => '500 Internal Server Error'); + git_header_html($http_responses{$status}); print <

@@ -3924,12 +3939,12 @@ sub git_search_grep_body { sub git_project_list { my $order = $cgi->param('o'); if (defined $order && $order !~ m/none|project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + die_error(400, "Unknown order parameter"); } my @list = git_get_projects_list(); if (!@list) { - die_error(undef, "No projects found"); + die_error(404, "No projects found"); } git_header_html(); @@ -3947,12 +3962,12 @@ sub git_project_list { sub git_forks { my $order = $cgi->param('o'); if (defined $order && $order !~ m/none|project|descr|owner|age/) { - die_error(undef, "Unknown order parameter"); + die_error(400, "Unknown order parameter"); } my @list = git_get_projects_list($project); if (!@list) { - die_error(undef, "No forks found"); + die_error(404, "No forks found"); } git_header_html(); @@ -4081,7 +4096,7 @@ sub git_tag { my %tag = parse_tag($hash); if (! %tag) { - die_error(undef, "Unknown tag object"); + die_error(404, "Unknown tag object"); } git_print_header_div('commit', esc_html($tag{'name'}), $hash); @@ -4117,26 +4132,25 @@ sub git_blame2 { my $fd; my $ftype; - my ($have_blame) = gitweb_check_feature('blame'); - if (!$have_blame) { - die_error('403 Permission denied', "Permission denied"); - } - die_error('404 Not Found', "File name not defined") if (!$file_name); + gitweb_check_feature('blame') + or die_error(403, "Blame view not allowed"); + + die_error(400, "No file name given") unless $file_name; $hash_base ||= git_get_head_hash($project); - die_error(undef, "Couldn't find base commit") unless ($hash_base); + die_error(404, "Couldn't find base commit") unless ($hash_base); my %co = parse_commit($hash_base) - or die_error(undef, "Reading commit failed"); + or die_error(404, "Commit not found"); if (!defined $hash) { $hash = git_get_hash_by_path($hash_base, $file_name, "blob") - or die_error(undef, "Error looking up file"); + or die_error(404, "Error looking up file"); } $ftype = git_get_type($hash); if ($ftype !~ "blob") { - die_error('400 Bad Request', "Object is not a blob"); + die_error(400, "Object is not a blob"); } open ($fd, "-|", git_cmd(), "blame", '-p', '--', $file_name, $hash_base) - or die_error(undef, "Open git-blame failed"); + or die_error(500, "Open git-blame failed"); git_header_html(); my $formats_nav = $cgi->a({-href => href(action=>"blob", -replay=>1)}, @@ -4198,7 +4212,7 @@ HTML print "\n"; } open (my $dd, "-|", git_cmd(), "rev-parse", "$full_rev^") - or die_error(undef, "Open git-rev-parse failed"); + or die_error(500, "Open git-rev-parse failed"); my $parent_commit = <$dd>; close $dd; chomp($parent_commit); @@ -4352,9 +4366,9 @@ sub git_blob_plain { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached @@ -4362,7 +4376,7 @@ sub git_blob_plain { } open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Open git-cat-file blob '$hash' failed"); + or die_error(500, "Open git-cat-file blob '$hash' failed"); # content-type (can include charset) $type = blob_contenttype($fd, $file_name, $type); @@ -4394,9 +4408,9 @@ sub git_blob { if (defined $file_name) { my $base = $hash_base || git_get_head_hash($project); $hash = git_get_hash_by_path($base, $file_name, "blob") - or die_error(undef, "Error lookup file"); + or die_error(404, "Cannot find file"); } else { - die_error(undef, "No file name defined"); + die_error(400, "No file name defined"); } } elsif ($hash =~ m/^[0-9a-fA-F]{40}$/) { # blobs defined by non-textual hash id's can be cached @@ -4405,7 +4419,7 @@ sub git_blob { my ($have_blame) = gitweb_check_feature('blame'); open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash - or die_error(undef, "Couldn't cat $file_name, $hash"); + or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; @@ -4486,9 +4500,9 @@ sub git_tree { } $/ = "\0"; open my $fd, "-|", git_cmd(), "ls-tree", '-z', $hash - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my @entries = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading tree failed"); + close $fd or die_error(404, "Reading tree failed"); $/ = "\n"; my $refs = git_get_references(); @@ -4578,16 +4592,16 @@ sub git_snapshot { my $format = $cgi->param('sf'); if (!@supported_fmts) { - die_error('403 Permission denied', "Permission denied"); + die_error(403, "Snapshots not allowed"); } # default to first supported snapshot format $format ||= $supported_fmts[0]; if ($format !~ m/^[a-z0-9]+$/) { - die_error(undef, "Invalid snapshot format parameter"); + die_error(400, "Invalid snapshot format parameter"); } elsif (!exists($known_snapshot_formats{$format})) { - die_error(undef, "Unknown snapshot format"); + die_error(400, "Unknown snapshot format"); } elsif (!grep($_ eq $format, @supported_fmts)) { - die_error(undef, "Unsupported snapshot format"); + die_error(403, "Unsupported snapshot format"); } if (!defined $hash) { @@ -4615,7 +4629,7 @@ sub git_snapshot { -status => '200 OK'); open my $fd, "-|", $cmd - or die_error(undef, "Execute git-archive failed"); + or die_error(500, "Execute git-archive failed"); binmode STDOUT, ':raw'; print <$fd>; binmode STDOUT, ':utf8'; # as set at the beginning of gitweb.cgi @@ -4683,10 +4697,8 @@ sub git_log { sub git_commit { $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); - } + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); my %ad = parse_date($co{'author_epoch'}, $co{'author_tz'}); my %cd = parse_date($co{'committer_epoch'}, $co{'committer_tz'}); @@ -4726,9 +4738,9 @@ sub git_commit { @diff_opts, (@$parents <= 1 ? $parent : '-c'), $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = map { chomp; $_ } <$fd>; - close $fd or die_error(undef, "Reading git-diff-tree failed"); + close $fd or die_error(404, "Reading git-diff-tree failed"); # non-textual hash id's can be cached my $expires; @@ -4821,33 +4833,33 @@ sub git_object { open my $fd, "-|", quote_command( git_cmd(), 'cat-file', '-t', $object_id) . ' 2> /dev/null' - or die_error('404 Not Found', "Object does not exist"); + or die_error(404, "Object does not exist"); $type = <$fd>; chomp $type; close $fd - or die_error('404 Not Found', "Object does not exist"); + or die_error(404, "Object does not exist"); # - hash_base and file_name } elsif ($hash_base && defined $file_name) { $file_name =~ s,/+$,,; system(git_cmd(), "cat-file", '-e', $hash_base) == 0 - or die_error('404 Not Found', "Base object does not exist"); + or die_error(404, "Base object does not exist"); # here errors should not hapen open my $fd, "-|", git_cmd(), "ls-tree", $hash_base, "--", $file_name - or die_error(undef, "Open git-ls-tree failed"); + or die_error(500, "Open git-ls-tree failed"); my $line = <$fd>; close $fd; #'100644 blob 0fa3f3a66fb6a137f6ec2c19351ed4d807070ffa panic.c' unless ($line && $line =~ m/^([0-9]+) (.+) ([0-9a-fA-F]{40})\t/) { - die_error('404 Not Found', "File or directory for given base does not exist"); + die_error(404, "File or directory for given base does not exist"); } $type = $2; $hash = $3; } else { - die_error('404 Not Found', "Not enough information to find object"); + die_error(400, "Not enough information to find object"); } print $cgi->redirect(-uri => href(action=>$type, -full=>1, @@ -4872,12 +4884,12 @@ sub git_blobdiff { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, "--", (defined $file_parent ? $file_parent : ()), $file_name - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } elsif (defined $hash && $hash =~ /[0-9a-fA-F]{40}/) { @@ -4886,23 +4898,23 @@ sub git_blobdiff { # read filtered raw output open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, $hash_parent_base, $hash_base, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); @difftree = # ':100644 100644 03b21826... 3b93d5e7... M ls-files.c' # $hash == to_id grep { /^:[0-7]{6} [0-7]{6} [0-9a-fA-F]{40} $hash/ } map { chomp; $_ } <$fd>; close $fd - or die_error(undef, "Reading git-diff-tree failed"); + or die_error(404, "Reading git-diff-tree failed"); @difftree - or die_error('404 Not Found', "Blob diff not found"); + or die_error(404, "Blob diff not found"); } else { - die_error('404 Not Found', "Missing one of the blob diff parameters"); + die_error(400, "Missing one of the blob diff parameters"); } if (@difftree > 1) { - die_error('404 Not Found', "Ambiguous blob diff specification"); + die_error(400, "Ambiguous blob diff specification"); } %diffinfo = parse_difftree_raw_line($difftree[0]); @@ -4923,7 +4935,7 @@ sub git_blobdiff { '-p', ($format eq 'html' ? "--full-index" : ()), $hash_parent_base, $hash_base, "--", (defined $file_parent ? $file_parent : ()), $file_name - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); } # old/legacy style URI @@ -4959,9 +4971,9 @@ sub git_blobdiff { open $fd, "-|", git_cmd(), "diff", @diff_opts, '-p', ($format eq 'html' ? "--full-index" : ()), $hash_parent, $hash, "--" - or die_error(undef, "Open git-diff failed"); + or die_error(500, "Open git-diff failed"); } else { - die_error('404 Not Found', "Missing one of the blob diff parameters") + die_error(400, "Missing one of the blob diff parameters") unless %diffinfo; } @@ -4994,7 +5006,7 @@ sub git_blobdiff { print "X-Git-Url: " . $cgi->self_url() . "\n\n"; } else { - die_error(undef, "Unknown blobdiff format"); + die_error(400, "Unknown blobdiff format"); } # patch @@ -5029,10 +5041,8 @@ sub git_blobdiff_plain { sub git_commitdiff { my $format = shift || 'html'; $hash ||= $hash_base || "HEAD"; - my %co = parse_commit($hash); - if (!%co) { - die_error(undef, "Unknown commit object"); - } + my %co = parse_commit($hash) + or die_error(404, "Unknown commit object"); # choose format for commitdiff for merge if (! defined $hash_parent && @{$co{'parents'}} > 1) { @@ -5114,7 +5124,7 @@ sub git_commitdiff { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, "--no-commit-id", "--patch-with-raw", "--full-index", $hash_parent_param, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); while (my $line = <$fd>) { chomp $line; @@ -5126,10 +5136,10 @@ sub git_commitdiff { } elsif ($format eq 'plain') { open $fd, "-|", git_cmd(), "diff-tree", '-r', @diff_opts, '-p', $hash_parent_param, $hash, "--" - or die_error(undef, "Open git-diff-tree failed"); + or die_error(500, "Open git-diff-tree failed"); } else { - die_error(undef, "Unknown commitdiff format"); + die_error(400, "Unknown commitdiff format"); } # non-textual hash id's can be cached @@ -5212,19 +5222,15 @@ sub git_history { $page = 0; } my $ftype; - my %co = parse_commit($hash_base); - if (!%co) { - die_error(undef, "Unknown commit object"); - } + my %co = parse_commit($hash_base) + or die_error(404, "Unknown commit object"); my $refs = git_get_references(); my $limit = sprintf("--max-count=%i", (100 * ($page+1))); my @commitlist = parse_commits($hash_base, 101, (100 * $page), - $file_name, "--full-history"); - if (!@commitlist) { - die_error('404 Not Found', "No such file or directory on given branch"); - } + $file_name, "--full-history") + or die_error(404, "No such file or directory on given branch"); if (!defined $hash && defined $file_name) { # some commits could have deleted file in question, @@ -5238,7 +5244,7 @@ sub git_history { $ftype = git_get_type($hash); } if (!defined $ftype) { - die_error(undef, "Unknown type of object"); + die_error(500, "Unknown type of object"); } my $paging_nav = ''; @@ -5276,19 +5282,16 @@ sub git_history { } sub git_search { - my ($have_search) = gitweb_check_feature('search'); - if (!$have_search) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('search') or die_error(403, "Search is disabled"); if (!defined $searchtext) { - die_error(undef, "Text field empty"); + die_error(400, "Text field is empty"); } if (!defined $hash) { $hash = git_get_head_hash($project); } my %co = parse_commit($hash); if (!%co) { - die_error(undef, "Unknown commit object"); + die_error(404, "Unknown commit object"); } if (!defined $page) { $page = 0; @@ -5298,16 +5301,12 @@ sub git_search { if ($searchtype eq 'pickaxe') { # pickaxe may take all resources of your box and run for several minutes # with every query - so decide by yourself how public you make this feature - my ($have_pickaxe) = gitweb_check_feature('pickaxe'); - if (!$have_pickaxe) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('pickaxe') + or die_error(403, "Pickaxe is disabled"); } if ($searchtype eq 'grep') { - my ($have_grep) = gitweb_check_feature('grep'); - if (!$have_grep) { - die_error('403 Permission denied', "Permission denied"); - } + gitweb_check_feature('grep') + or die_error(403, "Grep is disabled"); } git_header_html(); @@ -5581,7 +5580,7 @@ sub git_feed { # Atom: http://www.atomenabled.org/developers/syndication/ # RSS: http://www.notestips.com/80256B3A007F2692/1/NAMO5P9UPQ if ($format ne 'rss' && $format ne 'atom') { - die_error(undef, "Unknown web feed format"); + die_error(400, "Unknown web feed format"); } # log/feed of current (HEAD) branch, log of given branch, history of file/directory From 0c3d26d24ab913a8cc6f478d176f5896af28c03c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lukas=20Sandstr=C3=B6m?= Date: Fri, 20 Jun 2008 01:21:33 +0200 Subject: [PATCH 046/295] Add a helper script to send patches with Mozilla Thunderbird MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The script appp.sh can be used with the External Editor extension for Mozilla Thunderbird in order to be able to send inline patches in an easy way. Signed-off-by: Lukas Sandström Signed-off-by: Junio C Hamano --- Documentation/SubmittingPatches | 5 +++ contrib/thunderbird-patch-inline/README | 20 +++++++++ contrib/thunderbird-patch-inline/appp.sh | 55 ++++++++++++++++++++++++ 3 files changed, 80 insertions(+) create mode 100644 contrib/thunderbird-patch-inline/README create mode 100755 contrib/thunderbird-patch-inline/appp.sh diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 0e155c936c..b1164753e1 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -419,6 +419,11 @@ settings but I haven't tried, yet. mail.identity.default.compose_html => false mail.identity.id?.compose_html => false +(Lukas Sandström) + +There is a script in contrib/thunderbird-patch-inline which can help +you include patches with Thunderbird in an easy way. To use it, do the +steps above and then use the script as the external editor. Gnus ---- diff --git a/contrib/thunderbird-patch-inline/README b/contrib/thunderbird-patch-inline/README new file mode 100644 index 0000000000..39f96aa115 --- /dev/null +++ b/contrib/thunderbird-patch-inline/README @@ -0,0 +1,20 @@ +appp.sh is a script that is supposed to be used together with ExternalEditor +for Mozilla Thundebird. It will let you include patches inline in e-mails +in an easy way. + +Usage: +- Generate the patch with git format-patch. +- Start writing a new e-mail in Thunderbird. +- Press the external editor button (or Ctrl-E) to run appp.sh +- Select the previosly generated patch file. +- Finish editing the e-mail. + +Any text that is entered into the message editor before appp.sh is called +will be moved to the section between the --- and the diffstat. + +All S-O-B:s and Cc:s in the patch will be added to the CC list. + +To set it up, just install External Editor and tell it to use appp.sh as the +editor. + +Zenity is a required dependency. diff --git a/contrib/thunderbird-patch-inline/appp.sh b/contrib/thunderbird-patch-inline/appp.sh new file mode 100755 index 0000000000..cc518f3c89 --- /dev/null +++ b/contrib/thunderbird-patch-inline/appp.sh @@ -0,0 +1,55 @@ +#!/bin/bash +# Copyright 2008 Lukas Sandström +# +# AppendPatch - A script to be used together with ExternalEditor +# for Mozilla Thunderbird to properly include pathes inline i e-mails. + +# ExternalEditor can be downloaded at http://globs.org/articles.php?lng=en&pg=2 + +CONFFILE=~/.appprc + +SEP="-=-=-=-=-=-=-=-=-=# Don't remove this line #=-=-=-=-=-=-=-=-=-" +if [ -e "$CONFFILE" ] ; then + LAST_DIR=`grep -m 1 "^LAST_DIR=" "${CONFFILE}"|sed -e 's/^LAST_DIR=//'` + cd "${LAST_DIR}" +else + cd > /dev/null +fi + +PATCH=$(zenity --file-selection) + +if [ "$?" != "0" ] ; then + #zenity --error --text "No patchfile given." + exit 1 +fi + +cd - > /dev/null + +SUBJECT=`sed -n -e '/^Subject: /p' "${PATCH}"` +HEADERS=`sed -e '/^'"${SEP}"'$/,$d' $1` +BODY=`sed -e "1,/${SEP}/d" $1` +CMT_MSG=`sed -e '1,/^$/d' -e '/^---$/,$d' "${PATCH}"` +DIFF=`sed -e '1,/^---$/d' "${PATCH}"` + +CCS=`echo -e "$CMT_MSG\n$HEADERS" | sed -n -e 's/^Cc: \(.*\)$/\1,/gp' \ + -e 's/^Signed-off-by: \(.*\)/\1,/gp'` + +echo "$SUBJECT" > $1 +echo "Cc: $CCS" >> $1 +echo "$HEADERS" | sed -e '/^Subject: /d' -e '/^Cc: /d' >> $1 +echo "$SEP" >> $1 + +echo "$CMT_MSG" >> $1 +echo "---" >> $1 +if [ "x${BODY}x" != "xx" ] ; then + echo >> $1 + echo "$BODY" >> $1 + echo >> $1 +fi +echo "$DIFF" >> $1 + +LAST_DIR=`dirname "${PATCH}"` + +grep -v "^LAST_DIR=" "${CONFFILE}" > "${CONFFILE}_" +echo "LAST_DIR=${LAST_DIR}" >> "${CONFFILE}_" +mv "${CONFFILE}_" "${CONFFILE}" From 66aafad5e43815e5f54634e4ef787cd759388880 Mon Sep 17 00:00:00 2001 From: Teemu Likonen Date: Fri, 20 Jun 2008 16:02:10 +0300 Subject: [PATCH 047/295] bash: Add more option completions for 'git log' Options added: --walk-reflogs --stat --numstat --shortstat --decorate --diff-filter= --color-words Signed-off-by: Teemu Likonen Signed-off-by: Junio C Hamano --- contrib/completion/git-completion.bash | 3 +++ 1 file changed, 3 insertions(+) diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index 0eb8df020b..ebf7cde5c0 100755 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -762,6 +762,9 @@ _git_log () --not --all --left-right --cherry-pick --graph + --stat --numstat --shortstat + --decorate --diff-filter= + --color-words --walk-reflogs " return ;; From cead78edef6a2f1339f699cd7d656b6834707b94 Mon Sep 17 00:00:00 2001 From: Richard Quirk Date: Fri, 20 Jun 2008 16:58:15 +0200 Subject: [PATCH 048/295] git-gui: Fix accidental staged state toggle when clicking top pixel row If a text widget is asked the index at x,y with y == 0 or y == 1 it will always return 1.0 as the nearest index, regardless of the x position. This means that clicking the top 2 pixels of the Unstaged/Staged Changes lists caused the state of the file there to be toggled. This patch checks that the pixel clicked is greater than 1, so there is less chance of accidentally staging or unstaging changes. Signed-off-by: Richard Quirk Signed-off-by: Shawn O. Pearce --- git-gui.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/git-gui.sh b/git-gui.sh index 23d7dfec79..980dc0b373 100755 --- a/git-gui.sh +++ b/git-gui.sh @@ -1797,7 +1797,7 @@ proc toggle_or_diff {w x y} { $ui_index tag remove in_sel 0.0 end $ui_workdir tag remove in_sel 0.0 end - if {$col == 0} { + if {$col == 0 && $y > 1} { set i [expr {$lno-1}] set ll [expr {[llength $file_lists($w)]-1}] From ae081f3ebd5f65c453051b2db7b83d2a7c280827 Mon Sep 17 00:00:00 2001 From: Teemu Likonen Date: Tue, 10 Jun 2008 11:34:25 +0300 Subject: [PATCH 049/295] Add target "install-html" the the top level Makefile This makes it possible to install html documents from the top level directory. Previously such target was only in Documentation/Makefile. Signed-off-by: Teemu Likonen Signed-off-by: Junio C Hamano --- Makefile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Makefile b/Makefile index b003e3e60a..6a31c9feda 100644 --- a/Makefile +++ b/Makefile @@ -1290,6 +1290,9 @@ endif install-doc: $(MAKE) -C Documentation install +install-html: + $(MAKE) -C Documentation install-html + install-info: $(MAKE) -C Documentation install-info From cdeaf10f7e2754054c7be5d74227c698d2a71890 Mon Sep 17 00:00:00 2001 From: Cristian Peraferrer Date: Fri, 20 Jun 2008 17:24:20 +0200 Subject: [PATCH 050/295] Print errno upon failure to open the COMMIT_EDITMSG file When the COMMIT_EDITMSG cannot be opened, give more information to the user by giving the 'errno' information. Signed-off-by: Cristian Peraferrer Signed-off-by: Junio C Hamano --- builtin-commit.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/builtin-commit.c b/builtin-commit.c index 90200ed643..a33f43a209 100644 --- a/builtin-commit.c +++ b/builtin-commit.c @@ -502,7 +502,8 @@ static int prepare_to_commit(const char *index_file, const char *prefix) fp = fopen(git_path(commit_editmsg), "w"); if (fp == NULL) - die("could not open %s", git_path(commit_editmsg)); + die("could not open %s: %s", + git_path(commit_editmsg), strerror(errno)); if (cleanup_mode != CLEANUP_NONE) stripspace(&sb, 0); From fbd458a3f6bf2ba94380e2170ebfe2f53c2dec6d Mon Sep 17 00:00:00 2001 From: Jakub Narebski Date: Fri, 20 Jun 2008 23:10:50 +0200 Subject: [PATCH 051/295] t/README: Add 'Skipping Tests' section below 'Running Tests' Add description of GIT_SKIP_TESTS variable, taken almost verbatim (adjusting for conventions in t/README) from the commit message in 04ece59 (GIT_SKIP_TESTS: allow users to omit tests that are known to break) Signed-off-by: Junio C Hamano Signed-off-by: Jakub Narebski Signed-off-by: Junio C Hamano --- t/README | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/t/README b/t/README index dc892631e0..8f12d48fe8 100644 --- a/t/README +++ b/t/README @@ -59,6 +59,34 @@ You can pass --verbose (or -v), --debug (or -d), and --immediate available), for more exhaustive testing. +Skipping Tests +-------------- + +In some environments, certain tests have no way of succeeding +due to platform limitation, such as lack of 'unzip' program, or +filesystem that do not allow arbitrary sequence of non-NUL bytes +as pathnames. + +You should be able to say something like + + $ GIT_SKIP_TESTS=t9200.8 sh ./t9200-git-cvsexport-commit.sh + +and even: + + $ GIT_SKIP_TESTS='t[0-4]??? t91?? t9200.8' make + +to omit such tests. The value of the environment variable is a +SP separated list of patterns that tells which tests to skip, +and either can match the "t[0-9]{4}" part to skip the whole +test, or t[0-9]{4} followed by ".$number" to say which +particular test to skip. + +Note that some tests in the existing test suite rely on previous +test item, so you cannot arbitrarily disable one and expect the +remainder of test to check what the test originally was intended +to check. + + Naming Tests ------------ From 73f03627f4f1b0f66b30fa96a25537f3600cce0b Mon Sep 17 00:00:00 2001 From: "Shawn O. Pearce" Date: Fri, 20 Jun 2008 23:25:25 -0400 Subject: [PATCH 052/295] Correct documentation for git-push --mirror This option behaves more like: git push $url +refs/*:refs/* than it does like: git push $url +refs/heads/*:refs/heads/* +refs/tags/*:refs/tags/* so we should document it to be more clear about that. Suggested-by: Marek Zawirski Signed-off-by: Shawn O. Pearce Signed-off-by: Junio C Hamano --- Documentation/git-push.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/git-push.txt b/Documentation/git-push.txt index 89e0049bce..f3d5d883a7 100644 --- a/Documentation/git-push.txt +++ b/Documentation/git-push.txt @@ -67,7 +67,8 @@ nor in any Push line of the corresponding remotes file---see below). --mirror:: Instead of naming each ref to push, specifies that all - refs under `$GIT_DIR/refs/heads/` and `$GIT_DIR/refs/tags/` + refs under `$GIT_DIR/refs/` (which includes but is not + limited to `refs/heads/`, `refs/remotes/`, and `refs/tags/`) be mirrored to the remote repository. Newly created local refs will be pushed to the remote end, locally updated refs will be force updated on the remote end, and deleted refs From 9022a495a3c407859560d4ac4a278c0d6ad58837 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sat, 21 Jun 2008 23:28:58 -0700 Subject: [PATCH 053/295] rerere: rerere_created_at() and has_resolution() abstraction There were too many places in the code how an entry in the rerere database looks like, and the garbage_collect() function that iterates over subdirectories of the rr-cache directory was the worse offender. Introduce two helper functions, rerere_created_at() and has_resolution(), to abstract out the logic a bit better. Incidentally this fixes a small memory leak in garbage_collect() function. The path list to collect the entries to be pruned were defined to strdup the paths but the caller was feeding a path after doing an extra copy. Because the list does not have to be sorted by conflict signature hash, we use path_list_append() instead of path_list_insert(). While we are at it, make a conflicted hunk comparision in handle_file() a bit easier to read. Signed-off-by: Junio C Hamano --- builtin-rerere.c | 57 ++++++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 31 deletions(-) diff --git a/builtin-rerere.c b/builtin-rerere.c index 85222d9bc5..610b96a120 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -23,6 +23,18 @@ static const char *rr_path(const char *name, const char *file) return git_path("rr-cache/%s/%s", name, file); } +static time_t rerere_created_at(const char *name) +{ + struct stat st; + return stat(rr_path(name, "preimage"), &st) ? (time_t) 0 : st.st_mtime; +} + +static int has_resolution(const char *name) +{ + struct stat st; + return !stat(rr_path(name, "postimage"), &st); +} + static void read_rr(struct path_list *rr) { unsigned char sha1[20]; @@ -98,13 +110,10 @@ static int handle_file(const char *path, else if (!prefixcmp(buf, "=======")) hunk = 2; else if (!prefixcmp(buf, ">>>>>>> ")) { - int cmp = strbuf_cmp(&one, &two); - + if (strbuf_cmp(&one, &two) > 0) + strbuf_swap(&one, &two); hunk_no++; hunk = 0; - if (cmp > 0) { - strbuf_swap(&one, &two); - } if (out) { fputs("<<<<<<<\n", out); fwrite(one.buf, one.len, 1, out); @@ -201,33 +210,24 @@ static void unlink_rr_item(const char *name) static void garbage_collect(struct path_list *rr) { struct path_list to_remove = { NULL, 0, 0, 1 }; - char buf[1024]; DIR *dir; struct dirent *e; - int len, i, cutoff; + int i, cutoff; time_t now = time(NULL), then; - strlcpy(buf, git_path("rr-cache"), sizeof(buf)); - len = strlen(buf); - dir = opendir(buf); - strcpy(buf + len++, "/"); + dir = opendir(git_path("rr-cache")); while ((e = readdir(dir))) { const char *name = e->d_name; - struct stat st; - if (name[0] == '.' && (name[1] == '\0' || - (name[1] == '.' && name[2] == '\0'))) + if (name[0] == '.' && + (name[1] == '\0' || (name[1] == '.' && name[2] == '\0'))) continue; - i = snprintf(buf + len, sizeof(buf) - len, "%s", name); - strlcpy(buf + len + i, "/preimage", sizeof(buf) - len - i); - if (stat(buf, &st)) + then = rerere_created_at(name); + if (!then) continue; - then = st.st_mtime; - strlcpy(buf + len + i, "/postimage", sizeof(buf) - len - i); - cutoff = stat(buf, &st) ? cutoff_noresolve : cutoff_resolve; - if (then < now - cutoff * 86400) { - buf[len + i] = '\0'; - path_list_insert(xstrdup(name), &to_remove); - } + cutoff = (has_resolution(name) + ? cutoff_resolve : cutoff_noresolve); + if (then < now - cutoff * 86400) + path_list_append(name, &to_remove); } for (i = 0; i < to_remove.nr; i++) unlink_rr_item(to_remove.items[i].path); @@ -306,13 +306,11 @@ static int do_plain_rerere(struct path_list *rr, int fd) */ for (i = 0; i < rr->nr; i++) { - struct stat st; int ret; const char *path = rr->items[i].path; const char *name = (const char *)rr->items[i].util; - if (!stat(rr_path(name, "preimage"), &st) && - !stat(rr_path(name, "postimage"), &st)) { + if (has_resolution(name)) { if (!merge(name, path)) { fprintf(stderr, "Resolved '%s' using " "previous resolution.\n", path); @@ -410,11 +408,8 @@ int cmd_rerere(int argc, const char **argv, const char *prefix) return do_plain_rerere(&merge_rr, fd); else if (!strcmp(argv[1], "clear")) { for (i = 0; i < merge_rr.nr; i++) { - struct stat st; const char *name = (const char *)merge_rr.items[i].util; - if (!stat(git_path("rr-cache/%s", name), &st) && - S_ISDIR(st.st_mode) && - stat(rr_path(name, "postimage"), &st)) + if (!has_resolution(name)) unlink_rr_item(name); } unlink(merge_rr_path); From a1b32fdc3d1d05395f186bfa06e92174519dab8d Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 22 Jun 2008 00:21:28 -0700 Subject: [PATCH 054/295] git-rerere: detect unparsable conflicts rerere did not detect the case where <<< === >>> markers did not match. Signed-off-by: Junio C Hamano --- builtin-rerere.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/builtin-rerere.c b/builtin-rerere.c index 610b96a120..addc5c73df 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -144,6 +144,11 @@ static int handle_file(const char *path, fclose(out); if (sha1) SHA1_Final(sha1, &ctx); + if (hunk) { + if (output) + unlink(output); + return error("Could not parse conflict hunks in %s", path); + } return hunk_no; } From 51e0d0a67b8d31e92d52e15b577afb079359ec63 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 22 Jun 2008 00:27:46 -0700 Subject: [PATCH 055/295] rerere: remove dubious "tail_optimization" It is dubious if it is cheaper to shift entries repeatedly using memmove() to collect entries that needs to be written out in front of an array than simply marking the entries to be skipped. In addition, the label called this "tail optimization", but this obviously is not what people usually call with that name. Signed-off-by: Junio C Hamano --- builtin-rerere.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/builtin-rerere.c b/builtin-rerere.c index addc5c73df..0eec1f9373 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -66,8 +66,12 @@ static int write_rr(struct path_list *rr, int out_fd) { int i; for (i = 0; i < rr->nr; i++) { - const char *path = rr->items[i].path; - int length = strlen(path) + 1; + const char *path; + int length; + if (!rr->items[i].util) + continue; + path = rr->items[i].path; + length = strlen(path) + 1; if (write_in_full(out_fd, rr->items[i].util, 40) != 40 || write_in_full(out_fd, "\t", 1) != 1 || write_in_full(out_fd, path, length) != length) @@ -319,7 +323,7 @@ static int do_plain_rerere(struct path_list *rr, int fd) if (!merge(name, path)) { fprintf(stderr, "Resolved '%s' using " "previous resolution.\n", path); - goto tail_optimization; + goto mark_resolved; } } @@ -330,13 +334,8 @@ static int do_plain_rerere(struct path_list *rr, int fd) fprintf(stderr, "Recorded resolution for '%s'.\n", path); copy_file(rr_path(name, "postimage"), path, 0666); -tail_optimization: - if (i < rr->nr - 1) - memmove(rr->items + i, - rr->items + i + 1, - sizeof(rr->items[0]) * (rr->nr - i - 1)); - rr->nr--; - i--; + mark_resolved: + rr->items[i].util = NULL; } return write_rr(rr, fd); From 7f8365f894d60f240edd356f32e3c1bda994ed41 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 22 Jun 2008 02:03:26 -0700 Subject: [PATCH 056/295] t4200: fix rerere test The test used "diff-files -q" which is not about reporting if there is a difference at all. Instead, make sure that the path remains as conflicting in the index after rerere autoresolves it, as we will be adding rerere.autoupdate configuration with the next patch. --- t/t4200-rerere.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh index 85d7e3edcd..afb3e3d176 100755 --- a/t/t4200-rerere.sh +++ b/t/t4200-rerere.sh @@ -193,9 +193,9 @@ test_expect_success 'resolution was recorded properly' ' echo Bello > file3 && git add file3 && git commit -m version2 && - ! git merge fifth && - git diff-files -q && - test Cello = "$(cat file3)" + test_must_fail git merge fifth && + test Cello = "$(cat file3)" && + test 0 != $(git ls-files -u | wc -l) ' test_done From 121c813f8d6054dbee25c03301599c0f8d645d7f Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 22 Jun 2008 02:04:31 -0700 Subject: [PATCH 057/295] rerere.autoupdate When this configuration is set, paths that are autoresolved by git-rerere are updated in the index as well. --- Documentation/config.txt | 5 +++++ builtin-rerere.c | 37 +++++++++++++++++++++++++++++++++++++ t/t4200-rerere.sh | 10 ++++++++++ 3 files changed, 52 insertions(+) diff --git a/Documentation/config.txt b/Documentation/config.txt index 5331b450ea..0c7cf618ed 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -650,6 +650,11 @@ gc.rerereunresolved:: kept for this many days when `git rerere gc` is run. The default is 15 days. See linkgit:git-rerere[1]. +rerere.autoupdate:: + When set to true, `git-rerere` updates the index with the + resulting contents after it cleanly resolves conflicts using + previously recorded resolution. Defaults to false. + rerere.enabled:: Activate recording of resolved conflicts, so that identical conflict hunks can be resolved automatically, should they diff --git a/builtin-rerere.c b/builtin-rerere.c index 0eec1f9373..839b26e8e0 100644 --- a/builtin-rerere.c +++ b/builtin-rerere.c @@ -16,6 +16,9 @@ static int cutoff_resolve = 60; /* if rerere_enabled == -1, fall back to detection of .git/rr-cache */ static int rerere_enabled = -1; +/* automatically update cleanly resolved paths to the index */ +static int rerere_autoupdate; + static char *merge_rr_path; static const char *rr_path(const char *name, const char *file) @@ -276,9 +279,36 @@ static int diff_two(const char *file1, const char *label1, return 0; } +static struct lock_file index_lock; + +static int update_paths(struct path_list *update) +{ + int i; + int fd = hold_locked_index(&index_lock, 0); + int status = 0; + + if (fd < 0) + return -1; + + for (i = 0; i < update->nr; i++) { + struct path_list_item *item = &update->items[i]; + if (add_file_to_cache(item->path, ADD_CACHE_IGNORE_ERRORS)) + status = -1; + } + + if (!status && active_cache_changed) { + if (write_cache(fd, active_cache, active_nr) || + commit_locked_index(&index_lock)) + die("Unable to write new index file"); + } else if (fd >= 0) + rollback_lock_file(&index_lock); + return status; +} + static int do_plain_rerere(struct path_list *rr, int fd) { struct path_list conflict = { NULL, 0, 0, 1 }; + struct path_list update = { NULL, 0, 0, 1 }; int i; find_conflict(&conflict); @@ -323,6 +353,8 @@ static int do_plain_rerere(struct path_list *rr, int fd) if (!merge(name, path)) { fprintf(stderr, "Resolved '%s' using " "previous resolution.\n", path); + if (rerere_autoupdate) + path_list_insert(path, &update); goto mark_resolved; } } @@ -338,6 +370,9 @@ static int do_plain_rerere(struct path_list *rr, int fd) rr->items[i].util = NULL; } + if (update.nr) + update_paths(&update); + return write_rr(rr, fd); } @@ -349,6 +384,8 @@ static int git_rerere_config(const char *var, const char *value, void *cb) cutoff_noresolve = git_config_int(var, value); else if (!strcmp(var, "rerere.enabled")) rerere_enabled = git_config_bool(var, value); + else if (!strcmp(var, "rerere.autoupdate")) + rerere_autoupdate = git_config_bool(var, value); else return git_default_config(var, value, cb); return 0; diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh index afb3e3d176..a64727d5ad 100755 --- a/t/t4200-rerere.sh +++ b/t/t4200-rerere.sh @@ -193,9 +193,19 @@ test_expect_success 'resolution was recorded properly' ' echo Bello > file3 && git add file3 && git commit -m version2 && + git tag version2 && test_must_fail git merge fifth && test Cello = "$(cat file3)" && test 0 != $(git ls-files -u | wc -l) ' +test_expect_success 'rerere.autoupdate' ' + git config rerere.autoupdate true + git reset --hard && + git checkout version2 && + test_must_fail git merge fifth && + test 0 = $(git ls-files -u | wc -l) + +' + test_done From f05951fe3ffe461eb9cb715bf7cd08535657f29c Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sun, 9 Dec 2007 15:43:34 +0100 Subject: [PATCH 058/295] Add compat/regex.[ch] and compat/fnmatch.[ch]. We don't have fnmatch and regular expressions on Windows. We borrow fnmatch.[ch] from the GNU C library (license is LGPL 2 or later) and GNU regexp (regexp.c[ch], license is GPL 2 or later). Note that regexp.c was changed slightly to avoid warnings with gcc. We make the addition of these files an extra commit so as not to clutter the next commits. Signed-off-by: Johannes Sixt --- compat/fnmatch.c | 488 +++++ compat/fnmatch.h | 84 + compat/regex.c | 4927 ++++++++++++++++++++++++++++++++++++++++++++++ compat/regex.h | 490 +++++ 4 files changed, 5989 insertions(+) create mode 100644 compat/fnmatch.c create mode 100644 compat/fnmatch.h create mode 100644 compat/regex.c create mode 100644 compat/regex.h diff --git a/compat/fnmatch.c b/compat/fnmatch.c new file mode 100644 index 0000000000..1f4ead5f98 --- /dev/null +++ b/compat/fnmatch.c @@ -0,0 +1,488 @@ +/* Copyright (C) 1991, 92, 93, 96, 97, 98, 99 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + This library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + This library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with this library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#if HAVE_CONFIG_H +# include +#endif + +/* Enable GNU extensions in fnmatch.h. */ +#ifndef _GNU_SOURCE +# define _GNU_SOURCE 1 +#endif + +#include +#include +#include + +#if HAVE_STRING_H || defined _LIBC +# include +#else +# include +#endif + +#if defined STDC_HEADERS || defined _LIBC +# include +#endif + +/* For platform which support the ISO C amendement 1 functionality we + support user defined character classes. */ +#if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) +/* Solaris 2.5 has a bug: must be included before . */ +# include +# include +#endif + +/* Comment out all this code if we are using the GNU C Library, and are not + actually compiling the library itself. This code is part of the GNU C + Library, but also included in many other GNU distributions. Compiling + and linking in this code is a waste when using the GNU C library + (especially if it is a shared library). Rather than having every GNU + program understand `configure --with-gnu-libc' and omit the object files, + it is simpler to just do this in the source for each such file. */ + +#if defined _LIBC || !defined __GNU_LIBRARY__ + + +# if defined STDC_HEADERS || !defined isascii +# define ISASCII(c) 1 +# else +# define ISASCII(c) isascii(c) +# endif + +# ifdef isblank +# define ISBLANK(c) (ISASCII (c) && isblank (c)) +# else +# define ISBLANK(c) ((c) == ' ' || (c) == '\t') +# endif +# ifdef isgraph +# define ISGRAPH(c) (ISASCII (c) && isgraph (c)) +# else +# define ISGRAPH(c) (ISASCII (c) && isprint (c) && !isspace (c)) +# endif + +# define ISPRINT(c) (ISASCII (c) && isprint (c)) +# define ISDIGIT(c) (ISASCII (c) && isdigit (c)) +# define ISALNUM(c) (ISASCII (c) && isalnum (c)) +# define ISALPHA(c) (ISASCII (c) && isalpha (c)) +# define ISCNTRL(c) (ISASCII (c) && iscntrl (c)) +# define ISLOWER(c) (ISASCII (c) && islower (c)) +# define ISPUNCT(c) (ISASCII (c) && ispunct (c)) +# define ISSPACE(c) (ISASCII (c) && isspace (c)) +# define ISUPPER(c) (ISASCII (c) && isupper (c)) +# define ISXDIGIT(c) (ISASCII (c) && isxdigit (c)) + +# define STREQ(s1, s2) ((strcmp (s1, s2) == 0)) + +# if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) +/* The GNU C library provides support for user-defined character classes + and the functions from ISO C amendement 1. */ +# ifdef CHARCLASS_NAME_MAX +# define CHAR_CLASS_MAX_LENGTH CHARCLASS_NAME_MAX +# else +/* This shouldn't happen but some implementation might still have this + problem. Use a reasonable default value. */ +# define CHAR_CLASS_MAX_LENGTH 256 +# endif + +# ifdef _LIBC +# define IS_CHAR_CLASS(string) __wctype (string) +# else +# define IS_CHAR_CLASS(string) wctype (string) +# endif +# else +# define CHAR_CLASS_MAX_LENGTH 6 /* Namely, `xdigit'. */ + +# define IS_CHAR_CLASS(string) \ + (STREQ (string, "alpha") || STREQ (string, "upper") \ + || STREQ (string, "lower") || STREQ (string, "digit") \ + || STREQ (string, "alnum") || STREQ (string, "xdigit") \ + || STREQ (string, "space") || STREQ (string, "print") \ + || STREQ (string, "punct") || STREQ (string, "graph") \ + || STREQ (string, "cntrl") || STREQ (string, "blank")) +# endif + +/* Avoid depending on library functions or files + whose names are inconsistent. */ + +# if !defined _LIBC && !defined getenv +extern char *getenv (); +# endif + +# ifndef errno +extern int errno; +# endif + +/* This function doesn't exist on most systems. */ + +# if !defined HAVE___STRCHRNUL && !defined _LIBC +static char * +__strchrnul (s, c) + const char *s; + int c; +{ + char *result = strchr (s, c); + if (result == NULL) + result = strchr (s, '\0'); + return result; +} +# endif + +# ifndef internal_function +/* Inside GNU libc we mark some function in a special way. In other + environments simply ignore the marking. */ +# define internal_function +# endif + +/* Match STRING against the filename pattern PATTERN, returning zero if + it matches, nonzero if not. */ +static int internal_fnmatch __P ((const char *pattern, const char *string, + int no_leading_period, int flags)) + internal_function; +static int +internal_function +internal_fnmatch (pattern, string, no_leading_period, flags) + const char *pattern; + const char *string; + int no_leading_period; + int flags; +{ + register const char *p = pattern, *n = string; + register unsigned char c; + +/* Note that this evaluates C many times. */ +# ifdef _LIBC +# define FOLD(c) ((flags & FNM_CASEFOLD) ? tolower (c) : (c)) +# else +# define FOLD(c) ((flags & FNM_CASEFOLD) && ISUPPER (c) ? tolower (c) : (c)) +# endif + + while ((c = *p++) != '\0') + { + c = FOLD (c); + + switch (c) + { + case '?': + if (*n == '\0') + return FNM_NOMATCH; + else if (*n == '/' && (flags & FNM_FILE_NAME)) + return FNM_NOMATCH; + else if (*n == '.' && no_leading_period + && (n == string + || (n[-1] == '/' && (flags & FNM_FILE_NAME)))) + return FNM_NOMATCH; + break; + + case '\\': + if (!(flags & FNM_NOESCAPE)) + { + c = *p++; + if (c == '\0') + /* Trailing \ loses. */ + return FNM_NOMATCH; + c = FOLD (c); + } + if (FOLD ((unsigned char) *n) != c) + return FNM_NOMATCH; + break; + + case '*': + if (*n == '.' && no_leading_period + && (n == string + || (n[-1] == '/' && (flags & FNM_FILE_NAME)))) + return FNM_NOMATCH; + + for (c = *p++; c == '?' || c == '*'; c = *p++) + { + if (*n == '/' && (flags & FNM_FILE_NAME)) + /* A slash does not match a wildcard under FNM_FILE_NAME. */ + return FNM_NOMATCH; + else if (c == '?') + { + /* A ? needs to match one character. */ + if (*n == '\0') + /* There isn't another character; no match. */ + return FNM_NOMATCH; + else + /* One character of the string is consumed in matching + this ? wildcard, so *??? won't match if there are + less than three characters. */ + ++n; + } + } + + if (c == '\0') + /* The wildcard(s) is/are the last element of the pattern. + If the name is a file name and contains another slash + this does mean it cannot match. */ + return ((flags & FNM_FILE_NAME) && strchr (n, '/') != NULL + ? FNM_NOMATCH : 0); + else + { + const char *endp; + + endp = __strchrnul (n, (flags & FNM_FILE_NAME) ? '/' : '\0'); + + if (c == '[') + { + int flags2 = ((flags & FNM_FILE_NAME) + ? flags : (flags & ~FNM_PERIOD)); + + for (--p; n < endp; ++n) + if (internal_fnmatch (p, n, + (no_leading_period + && (n == string + || (n[-1] == '/' + && (flags + & FNM_FILE_NAME)))), + flags2) + == 0) + return 0; + } + else if (c == '/' && (flags & FNM_FILE_NAME)) + { + while (*n != '\0' && *n != '/') + ++n; + if (*n == '/' + && (internal_fnmatch (p, n + 1, flags & FNM_PERIOD, + flags) == 0)) + return 0; + } + else + { + int flags2 = ((flags & FNM_FILE_NAME) + ? flags : (flags & ~FNM_PERIOD)); + + if (c == '\\' && !(flags & FNM_NOESCAPE)) + c = *p; + c = FOLD (c); + for (--p; n < endp; ++n) + if (FOLD ((unsigned char) *n) == c + && (internal_fnmatch (p, n, + (no_leading_period + && (n == string + || (n[-1] == '/' + && (flags + & FNM_FILE_NAME)))), + flags2) == 0)) + return 0; + } + } + + /* If we come here no match is possible with the wildcard. */ + return FNM_NOMATCH; + + case '[': + { + /* Nonzero if the sense of the character class is inverted. */ + static int posixly_correct; + register int not; + char cold; + + if (posixly_correct == 0) + posixly_correct = getenv ("POSIXLY_CORRECT") != NULL ? 1 : -1; + + if (*n == '\0') + return FNM_NOMATCH; + + if (*n == '.' && no_leading_period && (n == string + || (n[-1] == '/' + && (flags + & FNM_FILE_NAME)))) + return FNM_NOMATCH; + + if (*n == '/' && (flags & FNM_FILE_NAME)) + /* `/' cannot be matched. */ + return FNM_NOMATCH; + + not = (*p == '!' || (posixly_correct < 0 && *p == '^')); + if (not) + ++p; + + c = *p++; + for (;;) + { + unsigned char fn = FOLD ((unsigned char) *n); + + if (!(flags & FNM_NOESCAPE) && c == '\\') + { + if (*p == '\0') + return FNM_NOMATCH; + c = FOLD ((unsigned char) *p); + ++p; + + if (c == fn) + goto matched; + } + else if (c == '[' && *p == ':') + { + /* Leave room for the null. */ + char str[CHAR_CLASS_MAX_LENGTH + 1]; + size_t c1 = 0; +# if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) + wctype_t wt; +# endif + const char *startp = p; + + for (;;) + { + if (c1 == CHAR_CLASS_MAX_LENGTH) + /* The name is too long and therefore the pattern + is ill-formed. */ + return FNM_NOMATCH; + + c = *++p; + if (c == ':' && p[1] == ']') + { + p += 2; + break; + } + if (c < 'a' || c >= 'z') + { + /* This cannot possibly be a character class name. + Match it as a normal range. */ + p = startp; + c = '['; + goto normal_bracket; + } + str[c1++] = c; + } + str[c1] = '\0'; + +# if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H) + wt = IS_CHAR_CLASS (str); + if (wt == 0) + /* Invalid character class name. */ + return FNM_NOMATCH; + + if (__iswctype (__btowc ((unsigned char) *n), wt)) + goto matched; +# else + if ((STREQ (str, "alnum") && ISALNUM ((unsigned char) *n)) + || (STREQ (str, "alpha") && ISALPHA ((unsigned char) *n)) + || (STREQ (str, "blank") && ISBLANK ((unsigned char) *n)) + || (STREQ (str, "cntrl") && ISCNTRL ((unsigned char) *n)) + || (STREQ (str, "digit") && ISDIGIT ((unsigned char) *n)) + || (STREQ (str, "graph") && ISGRAPH ((unsigned char) *n)) + || (STREQ (str, "lower") && ISLOWER ((unsigned char) *n)) + || (STREQ (str, "print") && ISPRINT ((unsigned char) *n)) + || (STREQ (str, "punct") && ISPUNCT ((unsigned char) *n)) + || (STREQ (str, "space") && ISSPACE ((unsigned char) *n)) + || (STREQ (str, "upper") && ISUPPER ((unsigned char) *n)) + || (STREQ (str, "xdigit") && ISXDIGIT ((unsigned char) *n))) + goto matched; +# endif + } + else if (c == '\0') + /* [ (unterminated) loses. */ + return FNM_NOMATCH; + else + { + normal_bracket: + if (FOLD (c) == fn) + goto matched; + + cold = c; + c = *p++; + + if (c == '-' && *p != ']') + { + /* It is a range. */ + unsigned char cend = *p++; + if (!(flags & FNM_NOESCAPE) && cend == '\\') + cend = *p++; + if (cend == '\0') + return FNM_NOMATCH; + + if (cold <= fn && fn <= FOLD (cend)) + goto matched; + + c = *p++; + } + } + + if (c == ']') + break; + } + + if (!not) + return FNM_NOMATCH; + break; + + matched: + /* Skip the rest of the [...] that already matched. */ + while (c != ']') + { + if (c == '\0') + /* [... (unterminated) loses. */ + return FNM_NOMATCH; + + c = *p++; + if (!(flags & FNM_NOESCAPE) && c == '\\') + { + if (*p == '\0') + return FNM_NOMATCH; + /* XXX 1003.2d11 is unclear if this is right. */ + ++p; + } + else if (c == '[' && *p == ':') + { + do + if (*++p == '\0') + return FNM_NOMATCH; + while (*p != ':' || p[1] == ']'); + p += 2; + c = *p; + } + } + if (not) + return FNM_NOMATCH; + } + break; + + default: + if (c != FOLD ((unsigned char) *n)) + return FNM_NOMATCH; + } + + ++n; + } + + if (*n == '\0') + return 0; + + if ((flags & FNM_LEADING_DIR) && *n == '/') + /* The FNM_LEADING_DIR flag says that "foo*" matches "foobar/frobozz". */ + return 0; + + return FNM_NOMATCH; + +# undef FOLD +} + + +int +fnmatch (pattern, string, flags) + const char *pattern; + const char *string; + int flags; +{ + return internal_fnmatch (pattern, string, flags & FNM_PERIOD, flags); +} + +#endif /* _LIBC or not __GNU_LIBRARY__. */ diff --git a/compat/fnmatch.h b/compat/fnmatch.h new file mode 100644 index 0000000000..cc3ec37940 --- /dev/null +++ b/compat/fnmatch.h @@ -0,0 +1,84 @@ +/* Copyright (C) 1991, 92, 93, 96, 97, 98, 99 Free Software Foundation, Inc. + This file is part of the GNU C Library. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#ifndef _FNMATCH_H +#define _FNMATCH_H 1 + +#ifdef __cplusplus +extern "C" { +#endif + +#if defined __cplusplus || (defined __STDC__ && __STDC__) || defined WINDOWS32 +# if !defined __GLIBC__ || !defined __P +# undef __P +# define __P(protos) protos +# endif +#else /* Not C++ or ANSI C. */ +# undef __P +# define __P(protos) () +/* We can get away without defining `const' here only because in this file + it is used only inside the prototype for `fnmatch', which is elided in + non-ANSI C where `const' is problematical. */ +#endif /* C++ or ANSI C. */ + +#ifndef const +# if (defined __STDC__ && __STDC__) || defined __cplusplus +# define __const const +# else +# define __const +# endif +#endif + +/* We #undef these before defining them because some losing systems + (HP-UX A.08.07 for example) define these in . */ +#undef FNM_PATHNAME +#undef FNM_NOESCAPE +#undef FNM_PERIOD + +/* Bits set in the FLAGS argument to `fnmatch'. */ +#define FNM_PATHNAME (1 << 0) /* No wildcard can ever match `/'. */ +#define FNM_NOESCAPE (1 << 1) /* Backslashes don't quote special chars. */ +#define FNM_PERIOD (1 << 2) /* Leading `.' is matched only explicitly. */ + +#if !defined _POSIX_C_SOURCE || _POSIX_C_SOURCE < 2 || defined _GNU_SOURCE +# define FNM_FILE_NAME FNM_PATHNAME /* Preferred GNU name. */ +# define FNM_LEADING_DIR (1 << 3) /* Ignore `/...' after a match. */ +# define FNM_CASEFOLD (1 << 4) /* Compare without regard to case. */ +#endif + +/* Value returned by `fnmatch' if STRING does not match PATTERN. */ +#define FNM_NOMATCH 1 + +/* This value is returned if the implementation does not support + `fnmatch'. Since this is not the case here it will never be + returned but the conformance test suites still require the symbol + to be defined. */ +#ifdef _XOPEN_SOURCE +# define FNM_NOSYS (-1) +#endif + +/* Match NAME against the filename pattern PATTERN, + returning zero if it matches, FNM_NOMATCH if not. */ +extern int fnmatch __P ((__const char *__pattern, __const char *__name, + int __flags)); + +#ifdef __cplusplus +} +#endif + +#endif /* fnmatch.h */ diff --git a/compat/regex.c b/compat/regex.c new file mode 100644 index 0000000000..87b33e4669 --- /dev/null +++ b/compat/regex.c @@ -0,0 +1,4927 @@ +/* Extended regular expression matching and search library, + version 0.12. + (Implements POSIX draft P10003.2/D11.2, except for + internationalization features.) + + Copyright (C) 1993 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ + +/* AIX requires this to be the first thing in the file. */ +#if defined (_AIX) && !defined (REGEX_MALLOC) + #pragma alloca +#endif + +#define _GNU_SOURCE + +/* We need this for `regex.h', and perhaps for the Emacs include files. */ +#include + +/* We used to test for `BSTRING' here, but only GCC and Emacs define + `BSTRING', as far as I know, and neither of them use this code. */ +#include +#ifndef bcmp +#define bcmp(s1, s2, n) memcmp ((s1), (s2), (n)) +#endif +#ifndef bcopy +#define bcopy(s, d, n) memcpy ((d), (s), (n)) +#endif +#ifndef bzero +#define bzero(s, n) memset ((s), 0, (n)) +#endif + +#include + + +/* Define the syntax stuff for \<, \>, etc. */ + +/* This must be nonzero for the wordchar and notwordchar pattern + commands in re_match_2. */ +#ifndef Sword +#define Sword 1 +#endif + +#ifdef SYNTAX_TABLE + +extern char *re_syntax_table; + +#else /* not SYNTAX_TABLE */ + +/* How many characters in the character set. */ +#define CHAR_SET_SIZE 256 + +static char re_syntax_table[CHAR_SET_SIZE]; + +static void +init_syntax_once () +{ + register int c; + static int done = 0; + + if (done) + return; + + bzero (re_syntax_table, sizeof re_syntax_table); + + for (c = 'a'; c <= 'z'; c++) + re_syntax_table[c] = Sword; + + for (c = 'A'; c <= 'Z'; c++) + re_syntax_table[c] = Sword; + + for (c = '0'; c <= '9'; c++) + re_syntax_table[c] = Sword; + + re_syntax_table['_'] = Sword; + + done = 1; +} + +#endif /* not SYNTAX_TABLE */ + +#define SYNTAX(c) re_syntax_table[c] + + +/* Get the interface, including the syntax bits. */ +#include "regex.h" + +/* isalpha etc. are used for the character classes. */ +#include + +#ifndef isascii +#define isascii(c) 1 +#endif + +#ifdef isblank +#define ISBLANK(c) (isascii (c) && isblank (c)) +#else +#define ISBLANK(c) ((c) == ' ' || (c) == '\t') +#endif +#ifdef isgraph +#define ISGRAPH(c) (isascii (c) && isgraph (c)) +#else +#define ISGRAPH(c) (isascii (c) && isprint (c) && !isspace (c)) +#endif + +#define ISPRINT(c) (isascii (c) && isprint (c)) +#define ISDIGIT(c) (isascii (c) && isdigit (c)) +#define ISALNUM(c) (isascii (c) && isalnum (c)) +#define ISALPHA(c) (isascii (c) && isalpha (c)) +#define ISCNTRL(c) (isascii (c) && iscntrl (c)) +#define ISLOWER(c) (isascii (c) && islower (c)) +#define ISPUNCT(c) (isascii (c) && ispunct (c)) +#define ISSPACE(c) (isascii (c) && isspace (c)) +#define ISUPPER(c) (isascii (c) && isupper (c)) +#define ISXDIGIT(c) (isascii (c) && isxdigit (c)) + +#ifndef NULL +#define NULL 0 +#endif + +/* We remove any previous definition of `SIGN_EXTEND_CHAR', + since ours (we hope) works properly with all combinations of + machines, compilers, `char' and `unsigned char' argument types. + (Per Bothner suggested the basic approach.) */ +#undef SIGN_EXTEND_CHAR +#if __STDC__ +#define SIGN_EXTEND_CHAR(c) ((signed char) (c)) +#else /* not __STDC__ */ +/* As in Harbison and Steele. */ +#define SIGN_EXTEND_CHAR(c) ((((unsigned char) (c)) ^ 128) - 128) +#endif + +/* Should we use malloc or alloca? If REGEX_MALLOC is not defined, we + use `alloca' instead of `malloc'. This is because using malloc in + re_search* or re_match* could cause memory leaks when C-g is used in + Emacs; also, malloc is slower and causes storage fragmentation. On + the other hand, malloc is more portable, and easier to debug. + + Because we sometimes use alloca, some routines have to be macros, + not functions -- `alloca'-allocated space disappears at the end of the + function it is called in. */ + +#ifdef REGEX_MALLOC + +#define REGEX_ALLOCATE malloc +#define REGEX_REALLOCATE(source, osize, nsize) realloc (source, nsize) + +#else /* not REGEX_MALLOC */ + +/* Emacs already defines alloca, sometimes. */ +#ifndef alloca + +/* Make alloca work the best possible way. */ +#ifdef __GNUC__ +#define alloca __builtin_alloca +#else /* not __GNUC__ */ +#if HAVE_ALLOCA_H +#include +#else /* not __GNUC__ or HAVE_ALLOCA_H */ +#ifndef _AIX /* Already did AIX, up at the top. */ +char *alloca (); +#endif /* not _AIX */ +#endif /* not HAVE_ALLOCA_H */ +#endif /* not __GNUC__ */ + +#endif /* not alloca */ + +#define REGEX_ALLOCATE alloca + +/* Assumes a `char *destination' variable. */ +#define REGEX_REALLOCATE(source, osize, nsize) \ + (destination = (char *) alloca (nsize), \ + bcopy (source, destination, osize), \ + destination) + +#endif /* not REGEX_MALLOC */ + + +/* True if `size1' is non-NULL and PTR is pointing anywhere inside + `string1' or just past its end. This works if PTR is NULL, which is + a good thing. */ +#define FIRST_STRING_P(ptr) \ + (size1 && string1 <= (ptr) && (ptr) <= string1 + size1) + +/* (Re)Allocate N items of type T using malloc, or fail. */ +#define TALLOC(n, t) ((t *) malloc ((n) * sizeof (t))) +#define RETALLOC(addr, n, t) ((addr) = (t *) realloc (addr, (n) * sizeof (t))) +#define REGEX_TALLOC(n, t) ((t *) REGEX_ALLOCATE ((n) * sizeof (t))) + +#define BYTEWIDTH 8 /* In bits. */ + +#define STREQ(s1, s2) ((strcmp (s1, s2) == 0)) + +#define MAX(a, b) ((a) > (b) ? (a) : (b)) +#define MIN(a, b) ((a) < (b) ? (a) : (b)) + +typedef char boolean; +#define false 0 +#define true 1 + +/* These are the command codes that appear in compiled regular + expressions. Some opcodes are followed by argument bytes. A + command code can specify any interpretation whatsoever for its + arguments. Zero bytes may appear in the compiled regular expression. + + The value of `exactn' is needed in search.c (search_buffer) in Emacs. + So regex.h defines a symbol `RE_EXACTN_VALUE' to be 1; the value of + `exactn' we use here must also be 1. */ + +typedef enum +{ + no_op = 0, + + /* Followed by one byte giving n, then by n literal bytes. */ + exactn = 1, + + /* Matches any (more or less) character. */ + anychar, + + /* Matches any one char belonging to specified set. First + following byte is number of bitmap bytes. Then come bytes + for a bitmap saying which chars are in. Bits in each byte + are ordered low-bit-first. A character is in the set if its + bit is 1. A character too large to have a bit in the map is + automatically not in the set. */ + charset, + + /* Same parameters as charset, but match any character that is + not one of those specified. */ + charset_not, + + /* Start remembering the text that is matched, for storing in a + register. Followed by one byte with the register number, in + the range 0 to one less than the pattern buffer's re_nsub + field. Then followed by one byte with the number of groups + inner to this one. (This last has to be part of the + start_memory only because we need it in the on_failure_jump + of re_match_2.) */ + start_memory, + + /* Stop remembering the text that is matched and store it in a + memory register. Followed by one byte with the register + number, in the range 0 to one less than `re_nsub' in the + pattern buffer, and one byte with the number of inner groups, + just like `start_memory'. (We need the number of inner + groups here because we don't have any easy way of finding the + corresponding start_memory when we're at a stop_memory.) */ + stop_memory, + + /* Match a duplicate of something remembered. Followed by one + byte containing the register number. */ + duplicate, + + /* Fail unless at beginning of line. */ + begline, + + /* Fail unless at end of line. */ + endline, + + /* Succeeds if at beginning of buffer (if emacs) or at beginning + of string to be matched (if not). */ + begbuf, + + /* Analogously, for end of buffer/string. */ + endbuf, + + /* Followed by two byte relative address to which to jump. */ + jump, + + /* Same as jump, but marks the end of an alternative. */ + jump_past_alt, + + /* Followed by two-byte relative address of place to resume at + in case of failure. */ + on_failure_jump, + + /* Like on_failure_jump, but pushes a placeholder instead of the + current string position when executed. */ + on_failure_keep_string_jump, + + /* Throw away latest failure point and then jump to following + two-byte relative address. */ + pop_failure_jump, + + /* Change to pop_failure_jump if know won't have to backtrack to + match; otherwise change to jump. This is used to jump + back to the beginning of a repeat. If what follows this jump + clearly won't match what the repeat does, such that we can be + sure that there is no use backtracking out of repetitions + already matched, then we change it to a pop_failure_jump. + Followed by two-byte address. */ + maybe_pop_jump, + + /* Jump to following two-byte address, and push a dummy failure + point. This failure point will be thrown away if an attempt + is made to use it for a failure. A `+' construct makes this + before the first repeat. Also used as an intermediary kind + of jump when compiling an alternative. */ + dummy_failure_jump, + + /* Push a dummy failure point and continue. Used at the end of + alternatives. */ + push_dummy_failure, + + /* Followed by two-byte relative address and two-byte number n. + After matching N times, jump to the address upon failure. */ + succeed_n, + + /* Followed by two-byte relative address, and two-byte number n. + Jump to the address N times, then fail. */ + jump_n, + + /* Set the following two-byte relative address to the + subsequent two-byte number. The address *includes* the two + bytes of number. */ + set_number_at, + + wordchar, /* Matches any word-constituent character. */ + notwordchar, /* Matches any char that is not a word-constituent. */ + + wordbeg, /* Succeeds if at word beginning. */ + wordend, /* Succeeds if at word end. */ + + wordbound, /* Succeeds if at a word boundary. */ + notwordbound /* Succeeds if not at a word boundary. */ + +#ifdef emacs + ,before_dot, /* Succeeds if before point. */ + at_dot, /* Succeeds if at point. */ + after_dot, /* Succeeds if after point. */ + + /* Matches any character whose syntax is specified. Followed by + a byte which contains a syntax code, e.g., Sword. */ + syntaxspec, + + /* Matches any character whose syntax is not that specified. */ + notsyntaxspec +#endif /* emacs */ +} re_opcode_t; + +/* Common operations on the compiled pattern. */ + +/* Store NUMBER in two contiguous bytes starting at DESTINATION. */ + +#define STORE_NUMBER(destination, number) \ + do { \ + (destination)[0] = (number) & 0377; \ + (destination)[1] = (number) >> 8; \ + } while (0) + +/* Same as STORE_NUMBER, except increment DESTINATION to + the byte after where the number is stored. Therefore, DESTINATION + must be an lvalue. */ + +#define STORE_NUMBER_AND_INCR(destination, number) \ + do { \ + STORE_NUMBER (destination, number); \ + (destination) += 2; \ + } while (0) + +/* Put into DESTINATION a number stored in two contiguous bytes starting + at SOURCE. */ + +#define EXTRACT_NUMBER(destination, source) \ + do { \ + (destination) = *(source) & 0377; \ + (destination) += SIGN_EXTEND_CHAR (*((source) + 1)) << 8; \ + } while (0) + +#ifdef DEBUG +static void +extract_number (dest, source) + int *dest; + unsigned char *source; +{ + int temp = SIGN_EXTEND_CHAR (*(source + 1)); + *dest = *source & 0377; + *dest += temp << 8; +} + +#ifndef EXTRACT_MACROS /* To debug the macros. */ +#undef EXTRACT_NUMBER +#define EXTRACT_NUMBER(dest, src) extract_number (&dest, src) +#endif /* not EXTRACT_MACROS */ + +#endif /* DEBUG */ + +/* Same as EXTRACT_NUMBER, except increment SOURCE to after the number. + SOURCE must be an lvalue. */ + +#define EXTRACT_NUMBER_AND_INCR(destination, source) \ + do { \ + EXTRACT_NUMBER (destination, source); \ + (source) += 2; \ + } while (0) + +#ifdef DEBUG +static void +extract_number_and_incr (destination, source) + int *destination; + unsigned char **source; +{ + extract_number (destination, *source); + *source += 2; +} + +#ifndef EXTRACT_MACROS +#undef EXTRACT_NUMBER_AND_INCR +#define EXTRACT_NUMBER_AND_INCR(dest, src) \ + extract_number_and_incr (&dest, &src) +#endif /* not EXTRACT_MACROS */ + +#endif /* DEBUG */ + +/* If DEBUG is defined, Regex prints many voluminous messages about what + it is doing (if the variable `debug' is nonzero). If linked with the + main program in `iregex.c', you can enter patterns and strings + interactively. And if linked with the main program in `main.c' and + the other test files, you can run the already-written tests. */ + +#ifdef DEBUG + +/* We use standard I/O for debugging. */ +#include + +/* It is useful to test things that ``must'' be true when debugging. */ +#include + +static int debug = 0; + +#define DEBUG_STATEMENT(e) e +#define DEBUG_PRINT1(x) if (debug) printf (x) +#define DEBUG_PRINT2(x1, x2) if (debug) printf (x1, x2) +#define DEBUG_PRINT3(x1, x2, x3) if (debug) printf (x1, x2, x3) +#define DEBUG_PRINT4(x1, x2, x3, x4) if (debug) printf (x1, x2, x3, x4) +#define DEBUG_PRINT_COMPILED_PATTERN(p, s, e) \ + if (debug) print_partial_compiled_pattern (s, e) +#define DEBUG_PRINT_DOUBLE_STRING(w, s1, sz1, s2, sz2) \ + if (debug) print_double_string (w, s1, sz1, s2, sz2) + + +extern void printchar (); + +/* Print the fastmap in human-readable form. */ + +void +print_fastmap (fastmap) + char *fastmap; +{ + unsigned was_a_range = 0; + unsigned i = 0; + + while (i < (1 << BYTEWIDTH)) + { + if (fastmap[i++]) + { + was_a_range = 0; + printchar (i - 1); + while (i < (1 << BYTEWIDTH) && fastmap[i]) + { + was_a_range = 1; + i++; + } + if (was_a_range) + { + printf ("-"); + printchar (i - 1); + } + } + } + putchar ('\n'); +} + + +/* Print a compiled pattern string in human-readable form, starting at + the START pointer into it and ending just before the pointer END. */ + +void +print_partial_compiled_pattern (start, end) + unsigned char *start; + unsigned char *end; +{ + int mcnt, mcnt2; + unsigned char *p = start; + unsigned char *pend = end; + + if (start == NULL) + { + printf ("(null)\n"); + return; + } + + /* Loop over pattern commands. */ + while (p < pend) + { + switch ((re_opcode_t) *p++) + { + case no_op: + printf ("/no_op"); + break; + + case exactn: + mcnt = *p++; + printf ("/exactn/%d", mcnt); + do + { + putchar ('/'); + printchar (*p++); + } + while (--mcnt); + break; + + case start_memory: + mcnt = *p++; + printf ("/start_memory/%d/%d", mcnt, *p++); + break; + + case stop_memory: + mcnt = *p++; + printf ("/stop_memory/%d/%d", mcnt, *p++); + break; + + case duplicate: + printf ("/duplicate/%d", *p++); + break; + + case anychar: + printf ("/anychar"); + break; + + case charset: + case charset_not: + { + register int c; + + printf ("/charset%s", + (re_opcode_t) *(p - 1) == charset_not ? "_not" : ""); + + assert (p + *p < pend); + + for (c = 0; c < *p; c++) + { + unsigned bit; + unsigned char map_byte = p[1 + c]; + + putchar ('/'); + + for (bit = 0; bit < BYTEWIDTH; bit++) + if (map_byte & (1 << bit)) + printchar (c * BYTEWIDTH + bit); + } + p += 1 + *p; + break; + } + + case begline: + printf ("/begline"); + break; + + case endline: + printf ("/endline"); + break; + + case on_failure_jump: + extract_number_and_incr (&mcnt, &p); + printf ("/on_failure_jump/0/%d", mcnt); + break; + + case on_failure_keep_string_jump: + extract_number_and_incr (&mcnt, &p); + printf ("/on_failure_keep_string_jump/0/%d", mcnt); + break; + + case dummy_failure_jump: + extract_number_and_incr (&mcnt, &p); + printf ("/dummy_failure_jump/0/%d", mcnt); + break; + + case push_dummy_failure: + printf ("/push_dummy_failure"); + break; + + case maybe_pop_jump: + extract_number_and_incr (&mcnt, &p); + printf ("/maybe_pop_jump/0/%d", mcnt); + break; + + case pop_failure_jump: + extract_number_and_incr (&mcnt, &p); + printf ("/pop_failure_jump/0/%d", mcnt); + break; + + case jump_past_alt: + extract_number_and_incr (&mcnt, &p); + printf ("/jump_past_alt/0/%d", mcnt); + break; + + case jump: + extract_number_and_incr (&mcnt, &p); + printf ("/jump/0/%d", mcnt); + break; + + case succeed_n: + extract_number_and_incr (&mcnt, &p); + extract_number_and_incr (&mcnt2, &p); + printf ("/succeed_n/0/%d/0/%d", mcnt, mcnt2); + break; + + case jump_n: + extract_number_and_incr (&mcnt, &p); + extract_number_and_incr (&mcnt2, &p); + printf ("/jump_n/0/%d/0/%d", mcnt, mcnt2); + break; + + case set_number_at: + extract_number_and_incr (&mcnt, &p); + extract_number_and_incr (&mcnt2, &p); + printf ("/set_number_at/0/%d/0/%d", mcnt, mcnt2); + break; + + case wordbound: + printf ("/wordbound"); + break; + + case notwordbound: + printf ("/notwordbound"); + break; + + case wordbeg: + printf ("/wordbeg"); + break; + + case wordend: + printf ("/wordend"); + +#ifdef emacs + case before_dot: + printf ("/before_dot"); + break; + + case at_dot: + printf ("/at_dot"); + break; + + case after_dot: + printf ("/after_dot"); + break; + + case syntaxspec: + printf ("/syntaxspec"); + mcnt = *p++; + printf ("/%d", mcnt); + break; + + case notsyntaxspec: + printf ("/notsyntaxspec"); + mcnt = *p++; + printf ("/%d", mcnt); + break; +#endif /* emacs */ + + case wordchar: + printf ("/wordchar"); + break; + + case notwordchar: + printf ("/notwordchar"); + break; + + case begbuf: + printf ("/begbuf"); + break; + + case endbuf: + printf ("/endbuf"); + break; + + default: + printf ("?%d", *(p-1)); + } + } + printf ("/\n"); +} + + +void +print_compiled_pattern (bufp) + struct re_pattern_buffer *bufp; +{ + unsigned char *buffer = bufp->buffer; + + print_partial_compiled_pattern (buffer, buffer + bufp->used); + printf ("%d bytes used/%d bytes allocated.\n", bufp->used, bufp->allocated); + + if (bufp->fastmap_accurate && bufp->fastmap) + { + printf ("fastmap: "); + print_fastmap (bufp->fastmap); + } + + printf ("re_nsub: %d\t", bufp->re_nsub); + printf ("regs_alloc: %d\t", bufp->regs_allocated); + printf ("can_be_null: %d\t", bufp->can_be_null); + printf ("newline_anchor: %d\n", bufp->newline_anchor); + printf ("no_sub: %d\t", bufp->no_sub); + printf ("not_bol: %d\t", bufp->not_bol); + printf ("not_eol: %d\t", bufp->not_eol); + printf ("syntax: %d\n", bufp->syntax); + /* Perhaps we should print the translate table? */ +} + + +void +print_double_string (where, string1, size1, string2, size2) + const char *where; + const char *string1; + const char *string2; + int size1; + int size2; +{ + unsigned this_char; + + if (where == NULL) + printf ("(null)"); + else + { + if (FIRST_STRING_P (where)) + { + for (this_char = where - string1; this_char < size1; this_char++) + printchar (string1[this_char]); + + where = string2; + } + + for (this_char = where - string2; this_char < size2; this_char++) + printchar (string2[this_char]); + } +} + +#else /* not DEBUG */ + +#undef assert +#define assert(e) + +#define DEBUG_STATEMENT(e) +#define DEBUG_PRINT1(x) +#define DEBUG_PRINT2(x1, x2) +#define DEBUG_PRINT3(x1, x2, x3) +#define DEBUG_PRINT4(x1, x2, x3, x4) +#define DEBUG_PRINT_COMPILED_PATTERN(p, s, e) +#define DEBUG_PRINT_DOUBLE_STRING(w, s1, sz1, s2, sz2) + +#endif /* not DEBUG */ + +/* Set by `re_set_syntax' to the current regexp syntax to recognize. Can + also be assigned to arbitrarily: each pattern buffer stores its own + syntax, so it can be changed between regex compilations. */ +reg_syntax_t re_syntax_options = RE_SYNTAX_EMACS; + + +/* Specify the precise syntax of regexps for compilation. This provides + for compatibility for various utilities which historically have + different, incompatible syntaxes. + + The argument SYNTAX is a bit mask comprised of the various bits + defined in regex.h. We return the old syntax. */ + +reg_syntax_t +re_set_syntax (syntax) + reg_syntax_t syntax; +{ + reg_syntax_t ret = re_syntax_options; + + re_syntax_options = syntax; + return ret; +} + +/* This table gives an error message for each of the error codes listed + in regex.h. Obviously the order here has to be same as there. */ + +static const char *re_error_msg[] = + { NULL, /* REG_NOERROR */ + "No match", /* REG_NOMATCH */ + "Invalid regular expression", /* REG_BADPAT */ + "Invalid collation character", /* REG_ECOLLATE */ + "Invalid character class name", /* REG_ECTYPE */ + "Trailing backslash", /* REG_EESCAPE */ + "Invalid back reference", /* REG_ESUBREG */ + "Unmatched [ or [^", /* REG_EBRACK */ + "Unmatched ( or \\(", /* REG_EPAREN */ + "Unmatched \\{", /* REG_EBRACE */ + "Invalid content of \\{\\}", /* REG_BADBR */ + "Invalid range end", /* REG_ERANGE */ + "Memory exhausted", /* REG_ESPACE */ + "Invalid preceding regular expression", /* REG_BADRPT */ + "Premature end of regular expression", /* REG_EEND */ + "Regular expression too big", /* REG_ESIZE */ + "Unmatched ) or \\)", /* REG_ERPAREN */ + }; + +/* Subroutine declarations and macros for regex_compile. */ + +static void store_op1 (), store_op2 (); +static void insert_op1 (), insert_op2 (); +static boolean at_begline_loc_p (), at_endline_loc_p (); +static boolean group_in_compile_stack (); +static reg_errcode_t compile_range (); + +/* Fetch the next character in the uncompiled pattern---translating it + if necessary. Also cast from a signed character in the constant + string passed to us by the user to an unsigned char that we can use + as an array index (in, e.g., `translate'). */ +#define PATFETCH(c) \ + do {if (p == pend) return REG_EEND; \ + c = (unsigned char) *p++; \ + if (translate) c = translate[c]; \ + } while (0) + +/* Fetch the next character in the uncompiled pattern, with no + translation. */ +#define PATFETCH_RAW(c) \ + do {if (p == pend) return REG_EEND; \ + c = (unsigned char) *p++; \ + } while (0) + +/* Go backwards one character in the pattern. */ +#define PATUNFETCH p-- + + +/* If `translate' is non-null, return translate[D], else just D. We + cast the subscript to translate because some data is declared as + `char *', to avoid warnings when a string constant is passed. But + when we use a character as a subscript we must make it unsigned. */ +#define TRANSLATE(d) (translate ? translate[(unsigned char) (d)] : (d)) + + +/* Macros for outputting the compiled pattern into `buffer'. */ + +/* If the buffer isn't allocated when it comes in, use this. */ +#define INIT_BUF_SIZE 32 + +/* Make sure we have at least N more bytes of space in buffer. */ +#define GET_BUFFER_SPACE(n) \ + while (b - bufp->buffer + (n) > bufp->allocated) \ + EXTEND_BUFFER () + +/* Make sure we have one more byte of buffer space and then add C to it. */ +#define BUF_PUSH(c) \ + do { \ + GET_BUFFER_SPACE (1); \ + *b++ = (unsigned char) (c); \ + } while (0) + + +/* Ensure we have two more bytes of buffer space and then append C1 and C2. */ +#define BUF_PUSH_2(c1, c2) \ + do { \ + GET_BUFFER_SPACE (2); \ + *b++ = (unsigned char) (c1); \ + *b++ = (unsigned char) (c2); \ + } while (0) + + +/* As with BUF_PUSH_2, except for three bytes. */ +#define BUF_PUSH_3(c1, c2, c3) \ + do { \ + GET_BUFFER_SPACE (3); \ + *b++ = (unsigned char) (c1); \ + *b++ = (unsigned char) (c2); \ + *b++ = (unsigned char) (c3); \ + } while (0) + + +/* Store a jump with opcode OP at LOC to location TO. We store a + relative address offset by the three bytes the jump itself occupies. */ +#define STORE_JUMP(op, loc, to) \ + store_op1 (op, loc, (to) - (loc) - 3) + +/* Likewise, for a two-argument jump. */ +#define STORE_JUMP2(op, loc, to, arg) \ + store_op2 (op, loc, (to) - (loc) - 3, arg) + +/* Like `STORE_JUMP', but for inserting. Assume `b' is the buffer end. */ +#define INSERT_JUMP(op, loc, to) \ + insert_op1 (op, loc, (to) - (loc) - 3, b) + +/* Like `STORE_JUMP2', but for inserting. Assume `b' is the buffer end. */ +#define INSERT_JUMP2(op, loc, to, arg) \ + insert_op2 (op, loc, (to) - (loc) - 3, arg, b) + + +/* This is not an arbitrary limit: the arguments which represent offsets + into the pattern are two bytes long. So if 2^16 bytes turns out to + be too small, many things would have to change. */ +#define MAX_BUF_SIZE (1L << 16) + + +/* Extend the buffer by twice its current size via realloc and + reset the pointers that pointed into the old block to point to the + correct places in the new one. If extending the buffer results in it + being larger than MAX_BUF_SIZE, then flag memory exhausted. */ +#define EXTEND_BUFFER() \ + do { \ + unsigned char *old_buffer = bufp->buffer; \ + if (bufp->allocated == MAX_BUF_SIZE) \ + return REG_ESIZE; \ + bufp->allocated <<= 1; \ + if (bufp->allocated > MAX_BUF_SIZE) \ + bufp->allocated = MAX_BUF_SIZE; \ + bufp->buffer = (unsigned char *) realloc (bufp->buffer, bufp->allocated);\ + if (bufp->buffer == NULL) \ + return REG_ESPACE; \ + /* If the buffer moved, move all the pointers into it. */ \ + if (old_buffer != bufp->buffer) \ + { \ + b = (b - old_buffer) + bufp->buffer; \ + begalt = (begalt - old_buffer) + bufp->buffer; \ + if (fixup_alt_jump) \ + fixup_alt_jump = (fixup_alt_jump - old_buffer) + bufp->buffer;\ + if (laststart) \ + laststart = (laststart - old_buffer) + bufp->buffer; \ + if (pending_exact) \ + pending_exact = (pending_exact - old_buffer) + bufp->buffer; \ + } \ + } while (0) + + +/* Since we have one byte reserved for the register number argument to + {start,stop}_memory, the maximum number of groups we can report + things about is what fits in that byte. */ +#define MAX_REGNUM 255 + +/* But patterns can have more than `MAX_REGNUM' registers. We just + ignore the excess. */ +typedef unsigned regnum_t; + + +/* Macros for the compile stack. */ + +/* Since offsets can go either forwards or backwards, this type needs to + be able to hold values from -(MAX_BUF_SIZE - 1) to MAX_BUF_SIZE - 1. */ +typedef int pattern_offset_t; + +typedef struct +{ + pattern_offset_t begalt_offset; + pattern_offset_t fixup_alt_jump; + pattern_offset_t inner_group_offset; + pattern_offset_t laststart_offset; + regnum_t regnum; +} compile_stack_elt_t; + + +typedef struct +{ + compile_stack_elt_t *stack; + unsigned size; + unsigned avail; /* Offset of next open position. */ +} compile_stack_type; + + +#define INIT_COMPILE_STACK_SIZE 32 + +#define COMPILE_STACK_EMPTY (compile_stack.avail == 0) +#define COMPILE_STACK_FULL (compile_stack.avail == compile_stack.size) + +/* The next available element. */ +#define COMPILE_STACK_TOP (compile_stack.stack[compile_stack.avail]) + + +/* Set the bit for character C in a list. */ +#define SET_LIST_BIT(c) \ + (b[((unsigned char) (c)) / BYTEWIDTH] \ + |= 1 << (((unsigned char) c) % BYTEWIDTH)) + + +/* Get the next unsigned number in the uncompiled pattern. */ +#define GET_UNSIGNED_NUMBER(num) \ + { if (p != pend) \ + { \ + PATFETCH (c); \ + while (ISDIGIT (c)) \ + { \ + if (num < 0) \ + num = 0; \ + num = num * 10 + c - '0'; \ + if (p == pend) \ + break; \ + PATFETCH (c); \ + } \ + } \ + } + +#define CHAR_CLASS_MAX_LENGTH 6 /* Namely, `xdigit'. */ + +#define IS_CHAR_CLASS(string) \ + (STREQ (string, "alpha") || STREQ (string, "upper") \ + || STREQ (string, "lower") || STREQ (string, "digit") \ + || STREQ (string, "alnum") || STREQ (string, "xdigit") \ + || STREQ (string, "space") || STREQ (string, "print") \ + || STREQ (string, "punct") || STREQ (string, "graph") \ + || STREQ (string, "cntrl") || STREQ (string, "blank")) + +/* `regex_compile' compiles PATTERN (of length SIZE) according to SYNTAX. + Returns one of error codes defined in `regex.h', or zero for success. + + Assumes the `allocated' (and perhaps `buffer') and `translate' + fields are set in BUFP on entry. + + If it succeeds, results are put in BUFP (if it returns an error, the + contents of BUFP are undefined): + `buffer' is the compiled pattern; + `syntax' is set to SYNTAX; + `used' is set to the length of the compiled pattern; + `fastmap_accurate' is zero; + `re_nsub' is the number of subexpressions in PATTERN; + `not_bol' and `not_eol' are zero; + + The `fastmap' and `newline_anchor' fields are neither + examined nor set. */ + +static reg_errcode_t +regex_compile (pattern, size, syntax, bufp) + const char *pattern; + int size; + reg_syntax_t syntax; + struct re_pattern_buffer *bufp; +{ + /* We fetch characters from PATTERN here. Even though PATTERN is + `char *' (i.e., signed), we declare these variables as unsigned, so + they can be reliably used as array indices. */ + register unsigned char c, c1; + + /* A random tempory spot in PATTERN. */ + const char *p1; + + /* Points to the end of the buffer, where we should append. */ + register unsigned char *b; + + /* Keeps track of unclosed groups. */ + compile_stack_type compile_stack; + + /* Points to the current (ending) position in the pattern. */ + const char *p = pattern; + const char *pend = pattern + size; + + /* How to translate the characters in the pattern. */ + char *translate = bufp->translate; + + /* Address of the count-byte of the most recently inserted `exactn' + command. This makes it possible to tell if a new exact-match + character can be added to that command or if the character requires + a new `exactn' command. */ + unsigned char *pending_exact = 0; + + /* Address of start of the most recently finished expression. + This tells, e.g., postfix * where to find the start of its + operand. Reset at the beginning of groups and alternatives. */ + unsigned char *laststart = 0; + + /* Address of beginning of regexp, or inside of last group. */ + unsigned char *begalt; + + /* Place in the uncompiled pattern (i.e., the {) to + which to go back if the interval is invalid. */ + const char *beg_interval; + + /* Address of the place where a forward jump should go to the end of + the containing expression. Each alternative of an `or' -- except the + last -- ends with a forward jump of this sort. */ + unsigned char *fixup_alt_jump = 0; + + /* Counts open-groups as they are encountered. Remembered for the + matching close-group on the compile stack, so the same register + number is put in the stop_memory as the start_memory. */ + regnum_t regnum = 0; + +#ifdef DEBUG + DEBUG_PRINT1 ("\nCompiling pattern: "); + if (debug) + { + unsigned debug_count; + + for (debug_count = 0; debug_count < size; debug_count++) + printchar (pattern[debug_count]); + putchar ('\n'); + } +#endif /* DEBUG */ + + /* Initialize the compile stack. */ + compile_stack.stack = TALLOC (INIT_COMPILE_STACK_SIZE, compile_stack_elt_t); + if (compile_stack.stack == NULL) + return REG_ESPACE; + + compile_stack.size = INIT_COMPILE_STACK_SIZE; + compile_stack.avail = 0; + + /* Initialize the pattern buffer. */ + bufp->syntax = syntax; + bufp->fastmap_accurate = 0; + bufp->not_bol = bufp->not_eol = 0; + + /* Set `used' to zero, so that if we return an error, the pattern + printer (for debugging) will think there's no pattern. We reset it + at the end. */ + bufp->used = 0; + + /* Always count groups, whether or not bufp->no_sub is set. */ + bufp->re_nsub = 0; + +#if !defined (emacs) && !defined (SYNTAX_TABLE) + /* Initialize the syntax table. */ + init_syntax_once (); +#endif + + if (bufp->allocated == 0) + { + if (bufp->buffer) + { /* If zero allocated, but buffer is non-null, try to realloc + enough space. This loses if buffer's address is bogus, but + that is the user's responsibility. */ + RETALLOC (bufp->buffer, INIT_BUF_SIZE, unsigned char); + } + else + { /* Caller did not allocate a buffer. Do it for them. */ + bufp->buffer = TALLOC (INIT_BUF_SIZE, unsigned char); + } + if (!bufp->buffer) return REG_ESPACE; + + bufp->allocated = INIT_BUF_SIZE; + } + + begalt = b = bufp->buffer; + + /* Loop through the uncompiled pattern until we're at the end. */ + while (p != pend) + { + PATFETCH (c); + + switch (c) + { + case '^': + { + if ( /* If at start of pattern, it's an operator. */ + p == pattern + 1 + /* If context independent, it's an operator. */ + || syntax & RE_CONTEXT_INDEP_ANCHORS + /* Otherwise, depends on what's come before. */ + || at_begline_loc_p (pattern, p, syntax)) + BUF_PUSH (begline); + else + goto normal_char; + } + break; + + + case '$': + { + if ( /* If at end of pattern, it's an operator. */ + p == pend + /* If context independent, it's an operator. */ + || syntax & RE_CONTEXT_INDEP_ANCHORS + /* Otherwise, depends on what's next. */ + || at_endline_loc_p (p, pend, syntax)) + BUF_PUSH (endline); + else + goto normal_char; + } + break; + + + case '+': + case '?': + if ((syntax & RE_BK_PLUS_QM) + || (syntax & RE_LIMITED_OPS)) + goto normal_char; + handle_plus: + case '*': + /* If there is no previous pattern... */ + if (!laststart) + { + if (syntax & RE_CONTEXT_INVALID_OPS) + return REG_BADRPT; + else if (!(syntax & RE_CONTEXT_INDEP_OPS)) + goto normal_char; + } + + { + /* Are we optimizing this jump? */ + boolean keep_string_p = false; + + /* 1 means zero (many) matches is allowed. */ + char zero_times_ok = 0, many_times_ok = 0; + + /* If there is a sequence of repetition chars, collapse it + down to just one (the right one). We can't combine + interval operators with these because of, e.g., `a{2}*', + which should only match an even number of `a's. */ + + for (;;) + { + zero_times_ok |= c != '+'; + many_times_ok |= c != '?'; + + if (p == pend) + break; + + PATFETCH (c); + + if (c == '*' + || (!(syntax & RE_BK_PLUS_QM) && (c == '+' || c == '?'))) + ; + + else if (syntax & RE_BK_PLUS_QM && c == '\\') + { + if (p == pend) return REG_EESCAPE; + + PATFETCH (c1); + if (!(c1 == '+' || c1 == '?')) + { + PATUNFETCH; + PATUNFETCH; + break; + } + + c = c1; + } + else + { + PATUNFETCH; + break; + } + + /* If we get here, we found another repeat character. */ + } + + /* Star, etc. applied to an empty pattern is equivalent + to an empty pattern. */ + if (!laststart) + break; + + /* Now we know whether or not zero matches is allowed + and also whether or not two or more matches is allowed. */ + if (many_times_ok) + { /* More than one repetition is allowed, so put in at the + end a backward relative jump from `b' to before the next + jump we're going to put in below (which jumps from + laststart to after this jump). + + But if we are at the `*' in the exact sequence `.*\n', + insert an unconditional jump backwards to the ., + instead of the beginning of the loop. This way we only + push a failure point once, instead of every time + through the loop. */ + assert (p - 1 > pattern); + + /* Allocate the space for the jump. */ + GET_BUFFER_SPACE (3); + + /* We know we are not at the first character of the pattern, + because laststart was nonzero. And we've already + incremented `p', by the way, to be the character after + the `*'. Do we have to do something analogous here + for null bytes, because of RE_DOT_NOT_NULL? */ + if (TRANSLATE (*(p - 2)) == TRANSLATE ('.') + && zero_times_ok + && p < pend && TRANSLATE (*p) == TRANSLATE ('\n') + && !(syntax & RE_DOT_NEWLINE)) + { /* We have .*\n. */ + STORE_JUMP (jump, b, laststart); + keep_string_p = true; + } + else + /* Anything else. */ + STORE_JUMP (maybe_pop_jump, b, laststart - 3); + + /* We've added more stuff to the buffer. */ + b += 3; + } + + /* On failure, jump from laststart to b + 3, which will be the + end of the buffer after this jump is inserted. */ + GET_BUFFER_SPACE (3); + INSERT_JUMP (keep_string_p ? on_failure_keep_string_jump + : on_failure_jump, + laststart, b + 3); + pending_exact = 0; + b += 3; + + if (!zero_times_ok) + { + /* At least one repetition is required, so insert a + `dummy_failure_jump' before the initial + `on_failure_jump' instruction of the loop. This + effects a skip over that instruction the first time + we hit that loop. */ + GET_BUFFER_SPACE (3); + INSERT_JUMP (dummy_failure_jump, laststart, laststart + 6); + b += 3; + } + } + break; + + + case '.': + laststart = b; + BUF_PUSH (anychar); + break; + + + case '[': + { + boolean had_char_class = false; + + if (p == pend) return REG_EBRACK; + + /* Ensure that we have enough space to push a charset: the + opcode, the length count, and the bitset; 34 bytes in all. */ + GET_BUFFER_SPACE (34); + + laststart = b; + + /* We test `*p == '^' twice, instead of using an if + statement, so we only need one BUF_PUSH. */ + BUF_PUSH (*p == '^' ? charset_not : charset); + if (*p == '^') + p++; + + /* Remember the first position in the bracket expression. */ + p1 = p; + + /* Push the number of bytes in the bitmap. */ + BUF_PUSH ((1 << BYTEWIDTH) / BYTEWIDTH); + + /* Clear the whole map. */ + bzero (b, (1 << BYTEWIDTH) / BYTEWIDTH); + + /* charset_not matches newline according to a syntax bit. */ + if ((re_opcode_t) b[-2] == charset_not + && (syntax & RE_HAT_LISTS_NOT_NEWLINE)) + SET_LIST_BIT ('\n'); + + /* Read in characters and ranges, setting map bits. */ + for (;;) + { + if (p == pend) return REG_EBRACK; + + PATFETCH (c); + + /* \ might escape characters inside [...] and [^...]. */ + if ((syntax & RE_BACKSLASH_ESCAPE_IN_LISTS) && c == '\\') + { + if (p == pend) return REG_EESCAPE; + + PATFETCH (c1); + SET_LIST_BIT (c1); + continue; + } + + /* Could be the end of the bracket expression. If it's + not (i.e., when the bracket expression is `[]' so + far), the ']' character bit gets set way below. */ + if (c == ']' && p != p1 + 1) + break; + + /* Look ahead to see if it's a range when the last thing + was a character class. */ + if (had_char_class && c == '-' && *p != ']') + return REG_ERANGE; + + /* Look ahead to see if it's a range when the last thing + was a character: if this is a hyphen not at the + beginning or the end of a list, then it's the range + operator. */ + if (c == '-' + && !(p - 2 >= pattern && p[-2] == '[') + && !(p - 3 >= pattern && p[-3] == '[' && p[-2] == '^') + && *p != ']') + { + reg_errcode_t ret + = compile_range (&p, pend, translate, syntax, b); + if (ret != REG_NOERROR) return ret; + } + + else if (p[0] == '-' && p[1] != ']') + { /* This handles ranges made up of characters only. */ + reg_errcode_t ret; + + /* Move past the `-'. */ + PATFETCH (c1); + + ret = compile_range (&p, pend, translate, syntax, b); + if (ret != REG_NOERROR) return ret; + } + + /* See if we're at the beginning of a possible character + class. */ + + else if (syntax & RE_CHAR_CLASSES && c == '[' && *p == ':') + { /* Leave room for the null. */ + char str[CHAR_CLASS_MAX_LENGTH + 1]; + + PATFETCH (c); + c1 = 0; + + /* If pattern is `[[:'. */ + if (p == pend) return REG_EBRACK; + + for (;;) + { + PATFETCH (c); + if (c == ':' || c == ']' || p == pend + || c1 == CHAR_CLASS_MAX_LENGTH) + break; + str[c1++] = c; + } + str[c1] = '\0'; + + /* If isn't a word bracketed by `[:' and:`]': + undo the ending character, the letters, and leave + the leading `:' and `[' (but set bits for them). */ + if (c == ':' && *p == ']') + { + int ch; + boolean is_alnum = STREQ (str, "alnum"); + boolean is_alpha = STREQ (str, "alpha"); + boolean is_blank = STREQ (str, "blank"); + boolean is_cntrl = STREQ (str, "cntrl"); + boolean is_digit = STREQ (str, "digit"); + boolean is_graph = STREQ (str, "graph"); + boolean is_lower = STREQ (str, "lower"); + boolean is_print = STREQ (str, "print"); + boolean is_punct = STREQ (str, "punct"); + boolean is_space = STREQ (str, "space"); + boolean is_upper = STREQ (str, "upper"); + boolean is_xdigit = STREQ (str, "xdigit"); + + if (!IS_CHAR_CLASS (str)) return REG_ECTYPE; + + /* Throw away the ] at the end of the character + class. */ + PATFETCH (c); + + if (p == pend) return REG_EBRACK; + + for (ch = 0; ch < 1 << BYTEWIDTH; ch++) + { + if ( (is_alnum && ISALNUM (ch)) + || (is_alpha && ISALPHA (ch)) + || (is_blank && ISBLANK (ch)) + || (is_cntrl && ISCNTRL (ch)) + || (is_digit && ISDIGIT (ch)) + || (is_graph && ISGRAPH (ch)) + || (is_lower && ISLOWER (ch)) + || (is_print && ISPRINT (ch)) + || (is_punct && ISPUNCT (ch)) + || (is_space && ISSPACE (ch)) + || (is_upper && ISUPPER (ch)) + || (is_xdigit && ISXDIGIT (ch))) + SET_LIST_BIT (ch); + } + had_char_class = true; + } + else + { + c1++; + while (c1--) + PATUNFETCH; + SET_LIST_BIT ('['); + SET_LIST_BIT (':'); + had_char_class = false; + } + } + else + { + had_char_class = false; + SET_LIST_BIT (c); + } + } + + /* Discard any (non)matching list bytes that are all 0 at the + end of the map. Decrease the map-length byte too. */ + while ((int) b[-1] > 0 && b[b[-1] - 1] == 0) + b[-1]--; + b += b[-1]; + } + break; + + + case '(': + if (syntax & RE_NO_BK_PARENS) + goto handle_open; + else + goto normal_char; + + + case ')': + if (syntax & RE_NO_BK_PARENS) + goto handle_close; + else + goto normal_char; + + + case '\n': + if (syntax & RE_NEWLINE_ALT) + goto handle_alt; + else + goto normal_char; + + + case '|': + if (syntax & RE_NO_BK_VBAR) + goto handle_alt; + else + goto normal_char; + + + case '{': + if (syntax & RE_INTERVALS && syntax & RE_NO_BK_BRACES) + goto handle_interval; + else + goto normal_char; + + + case '\\': + if (p == pend) return REG_EESCAPE; + + /* Do not translate the character after the \, so that we can + distinguish, e.g., \B from \b, even if we normally would + translate, e.g., B to b. */ + PATFETCH_RAW (c); + + switch (c) + { + case '(': + if (syntax & RE_NO_BK_PARENS) + goto normal_backslash; + + handle_open: + bufp->re_nsub++; + regnum++; + + if (COMPILE_STACK_FULL) + { + RETALLOC (compile_stack.stack, compile_stack.size << 1, + compile_stack_elt_t); + if (compile_stack.stack == NULL) return REG_ESPACE; + + compile_stack.size <<= 1; + } + + /* These are the values to restore when we hit end of this + group. They are all relative offsets, so that if the + whole pattern moves because of realloc, they will still + be valid. */ + COMPILE_STACK_TOP.begalt_offset = begalt - bufp->buffer; + COMPILE_STACK_TOP.fixup_alt_jump + = fixup_alt_jump ? fixup_alt_jump - bufp->buffer + 1 : 0; + COMPILE_STACK_TOP.laststart_offset = b - bufp->buffer; + COMPILE_STACK_TOP.regnum = regnum; + + /* We will eventually replace the 0 with the number of + groups inner to this one. But do not push a + start_memory for groups beyond the last one we can + represent in the compiled pattern. */ + if (regnum <= MAX_REGNUM) + { + COMPILE_STACK_TOP.inner_group_offset = b - bufp->buffer + 2; + BUF_PUSH_3 (start_memory, regnum, 0); + } + + compile_stack.avail++; + + fixup_alt_jump = 0; + laststart = 0; + begalt = b; + /* If we've reached MAX_REGNUM groups, then this open + won't actually generate any code, so we'll have to + clear pending_exact explicitly. */ + pending_exact = 0; + break; + + + case ')': + if (syntax & RE_NO_BK_PARENS) goto normal_backslash; + + if (COMPILE_STACK_EMPTY) + { + if (syntax & RE_UNMATCHED_RIGHT_PAREN_ORD) + goto normal_backslash; + else + return REG_ERPAREN; + } + + handle_close: + if (fixup_alt_jump) + { /* Push a dummy failure point at the end of the + alternative for a possible future + `pop_failure_jump' to pop. See comments at + `push_dummy_failure' in `re_match_2'. */ + BUF_PUSH (push_dummy_failure); + + /* We allocated space for this jump when we assigned + to `fixup_alt_jump', in the `handle_alt' case below. */ + STORE_JUMP (jump_past_alt, fixup_alt_jump, b - 1); + } + + /* See similar code for backslashed left paren above. */ + if (COMPILE_STACK_EMPTY) + { + if (syntax & RE_UNMATCHED_RIGHT_PAREN_ORD) + goto normal_char; + else + return REG_ERPAREN; + } + + /* Since we just checked for an empty stack above, this + ``can't happen''. */ + assert (compile_stack.avail != 0); + { + /* We don't just want to restore into `regnum', because + later groups should continue to be numbered higher, + as in `(ab)c(de)' -- the second group is #2. */ + regnum_t this_group_regnum; + + compile_stack.avail--; + begalt = bufp->buffer + COMPILE_STACK_TOP.begalt_offset; + fixup_alt_jump + = COMPILE_STACK_TOP.fixup_alt_jump + ? bufp->buffer + COMPILE_STACK_TOP.fixup_alt_jump - 1 + : 0; + laststart = bufp->buffer + COMPILE_STACK_TOP.laststart_offset; + this_group_regnum = COMPILE_STACK_TOP.regnum; + /* If we've reached MAX_REGNUM groups, then this open + won't actually generate any code, so we'll have to + clear pending_exact explicitly. */ + pending_exact = 0; + + /* We're at the end of the group, so now we know how many + groups were inside this one. */ + if (this_group_regnum <= MAX_REGNUM) + { + unsigned char *inner_group_loc + = bufp->buffer + COMPILE_STACK_TOP.inner_group_offset; + + *inner_group_loc = regnum - this_group_regnum; + BUF_PUSH_3 (stop_memory, this_group_regnum, + regnum - this_group_regnum); + } + } + break; + + + case '|': /* `\|'. */ + if (syntax & RE_LIMITED_OPS || syntax & RE_NO_BK_VBAR) + goto normal_backslash; + handle_alt: + if (syntax & RE_LIMITED_OPS) + goto normal_char; + + /* Insert before the previous alternative a jump which + jumps to this alternative if the former fails. */ + GET_BUFFER_SPACE (3); + INSERT_JUMP (on_failure_jump, begalt, b + 6); + pending_exact = 0; + b += 3; + + /* The alternative before this one has a jump after it + which gets executed if it gets matched. Adjust that + jump so it will jump to this alternative's analogous + jump (put in below, which in turn will jump to the next + (if any) alternative's such jump, etc.). The last such + jump jumps to the correct final destination. A picture: + _____ _____ + | | | | + | v | v + a | b | c + + If we are at `b', then fixup_alt_jump right now points to a + three-byte space after `a'. We'll put in the jump, set + fixup_alt_jump to right after `b', and leave behind three + bytes which we'll fill in when we get to after `c'. */ + + if (fixup_alt_jump) + STORE_JUMP (jump_past_alt, fixup_alt_jump, b); + + /* Mark and leave space for a jump after this alternative, + to be filled in later either by next alternative or + when know we're at the end of a series of alternatives. */ + fixup_alt_jump = b; + GET_BUFFER_SPACE (3); + b += 3; + + laststart = 0; + begalt = b; + break; + + + case '{': + /* If \{ is a literal. */ + if (!(syntax & RE_INTERVALS) + /* If we're at `\{' and it's not the open-interval + operator. */ + || ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) + || (p - 2 == pattern && p == pend)) + goto normal_backslash; + + handle_interval: + { + /* If got here, then the syntax allows intervals. */ + + /* At least (most) this many matches must be made. */ + int lower_bound = -1, upper_bound = -1; + + beg_interval = p - 1; + + if (p == pend) + { + if (syntax & RE_NO_BK_BRACES) + goto unfetch_interval; + else + return REG_EBRACE; + } + + GET_UNSIGNED_NUMBER (lower_bound); + + if (c == ',') + { + GET_UNSIGNED_NUMBER (upper_bound); + if (upper_bound < 0) upper_bound = RE_DUP_MAX; + } + else + /* Interval such as `{1}' => match exactly once. */ + upper_bound = lower_bound; + + if (lower_bound < 0 || upper_bound > RE_DUP_MAX + || lower_bound > upper_bound) + { + if (syntax & RE_NO_BK_BRACES) + goto unfetch_interval; + else + return REG_BADBR; + } + + if (!(syntax & RE_NO_BK_BRACES)) + { + if (c != '\\') return REG_EBRACE; + + PATFETCH (c); + } + + if (c != '}') + { + if (syntax & RE_NO_BK_BRACES) + goto unfetch_interval; + else + return REG_BADBR; + } + + /* We just parsed a valid interval. */ + + /* If it's invalid to have no preceding re. */ + if (!laststart) + { + if (syntax & RE_CONTEXT_INVALID_OPS) + return REG_BADRPT; + else if (syntax & RE_CONTEXT_INDEP_OPS) + laststart = b; + else + goto unfetch_interval; + } + + /* If the upper bound is zero, don't want to succeed at + all; jump from `laststart' to `b + 3', which will be + the end of the buffer after we insert the jump. */ + if (upper_bound == 0) + { + GET_BUFFER_SPACE (3); + INSERT_JUMP (jump, laststart, b + 3); + b += 3; + } + + /* Otherwise, we have a nontrivial interval. When + we're all done, the pattern will look like: + set_number_at + set_number_at + succeed_n + + jump_n + (The upper bound and `jump_n' are omitted if + `upper_bound' is 1, though.) */ + else + { /* If the upper bound is > 1, we need to insert + more at the end of the loop. */ + unsigned nbytes = 10 + (upper_bound > 1) * 10; + + GET_BUFFER_SPACE (nbytes); + + /* Initialize lower bound of the `succeed_n', even + though it will be set during matching by its + attendant `set_number_at' (inserted next), + because `re_compile_fastmap' needs to know. + Jump to the `jump_n' we might insert below. */ + INSERT_JUMP2 (succeed_n, laststart, + b + 5 + (upper_bound > 1) * 5, + lower_bound); + b += 5; + + /* Code to initialize the lower bound. Insert + before the `succeed_n'. The `5' is the last two + bytes of this `set_number_at', plus 3 bytes of + the following `succeed_n'. */ + insert_op2 (set_number_at, laststart, 5, lower_bound, b); + b += 5; + + if (upper_bound > 1) + { /* More than one repetition is allowed, so + append a backward jump to the `succeed_n' + that starts this interval. + + When we've reached this during matching, + we'll have matched the interval once, so + jump back only `upper_bound - 1' times. */ + STORE_JUMP2 (jump_n, b, laststart + 5, + upper_bound - 1); + b += 5; + + /* The location we want to set is the second + parameter of the `jump_n'; that is `b-2' as + an absolute address. `laststart' will be + the `set_number_at' we're about to insert; + `laststart+3' the number to set, the source + for the relative address. But we are + inserting into the middle of the pattern -- + so everything is getting moved up by 5. + Conclusion: (b - 2) - (laststart + 3) + 5, + i.e., b - laststart. + + We insert this at the beginning of the loop + so that if we fail during matching, we'll + reinitialize the bounds. */ + insert_op2 (set_number_at, laststart, b - laststart, + upper_bound - 1, b); + b += 5; + } + } + pending_exact = 0; + beg_interval = NULL; + } + break; + + unfetch_interval: + /* If an invalid interval, match the characters as literals. */ + assert (beg_interval); + p = beg_interval; + beg_interval = NULL; + + /* normal_char and normal_backslash need `c'. */ + PATFETCH (c); + + if (!(syntax & RE_NO_BK_BRACES)) + { + if (p > pattern && p[-1] == '\\') + goto normal_backslash; + } + goto normal_char; + +#ifdef emacs + /* There is no way to specify the before_dot and after_dot + operators. rms says this is ok. --karl */ + case '=': + BUF_PUSH (at_dot); + break; + + case 's': + laststart = b; + PATFETCH (c); + BUF_PUSH_2 (syntaxspec, syntax_spec_code[c]); + break; + + case 'S': + laststart = b; + PATFETCH (c); + BUF_PUSH_2 (notsyntaxspec, syntax_spec_code[c]); + break; +#endif /* emacs */ + + + case 'w': + laststart = b; + BUF_PUSH (wordchar); + break; + + + case 'W': + laststart = b; + BUF_PUSH (notwordchar); + break; + + + case '<': + BUF_PUSH (wordbeg); + break; + + case '>': + BUF_PUSH (wordend); + break; + + case 'b': + BUF_PUSH (wordbound); + break; + + case 'B': + BUF_PUSH (notwordbound); + break; + + case '`': + BUF_PUSH (begbuf); + break; + + case '\'': + BUF_PUSH (endbuf); + break; + + case '1': case '2': case '3': case '4': case '5': + case '6': case '7': case '8': case '9': + if (syntax & RE_NO_BK_REFS) + goto normal_char; + + c1 = c - '0'; + + if (c1 > regnum) + return REG_ESUBREG; + + /* Can't back reference to a subexpression if inside of it. */ + if (group_in_compile_stack (compile_stack, c1)) + goto normal_char; + + laststart = b; + BUF_PUSH_2 (duplicate, c1); + break; + + + case '+': + case '?': + if (syntax & RE_BK_PLUS_QM) + goto handle_plus; + else + goto normal_backslash; + + default: + normal_backslash: + /* You might think it would be useful for \ to mean + not to translate; but if we don't translate it + it will never match anything. */ + c = TRANSLATE (c); + goto normal_char; + } + break; + + + default: + /* Expects the character in `c'. */ + normal_char: + /* If no exactn currently being built. */ + if (!pending_exact + + /* If last exactn not at current position. */ + || pending_exact + *pending_exact + 1 != b + + /* We have only one byte following the exactn for the count. */ + || *pending_exact == (1 << BYTEWIDTH) - 1 + + /* If followed by a repetition operator. */ + || *p == '*' || *p == '^' + || ((syntax & RE_BK_PLUS_QM) + ? *p == '\\' && (p[1] == '+' || p[1] == '?') + : (*p == '+' || *p == '?')) + || ((syntax & RE_INTERVALS) + && ((syntax & RE_NO_BK_BRACES) + ? *p == '{' + : (p[0] == '\\' && p[1] == '{')))) + { + /* Start building a new exactn. */ + + laststart = b; + + BUF_PUSH_2 (exactn, 0); + pending_exact = b - 1; + } + + BUF_PUSH (c); + (*pending_exact)++; + break; + } /* switch (c) */ + } /* while p != pend */ + + + /* Through the pattern now. */ + + if (fixup_alt_jump) + STORE_JUMP (jump_past_alt, fixup_alt_jump, b); + + if (!COMPILE_STACK_EMPTY) + return REG_EPAREN; + + free (compile_stack.stack); + + /* We have succeeded; set the length of the buffer. */ + bufp->used = b - bufp->buffer; + +#ifdef DEBUG + if (debug) + { + DEBUG_PRINT1 ("\nCompiled pattern: "); + print_compiled_pattern (bufp); + } +#endif /* DEBUG */ + + return REG_NOERROR; +} /* regex_compile */ + +/* Subroutines for `regex_compile'. */ + +/* Store OP at LOC followed by two-byte integer parameter ARG. */ + +static void +store_op1 (op, loc, arg) + re_opcode_t op; + unsigned char *loc; + int arg; +{ + *loc = (unsigned char) op; + STORE_NUMBER (loc + 1, arg); +} + + +/* Like `store_op1', but for two two-byte parameters ARG1 and ARG2. */ + +static void +store_op2 (op, loc, arg1, arg2) + re_opcode_t op; + unsigned char *loc; + int arg1, arg2; +{ + *loc = (unsigned char) op; + STORE_NUMBER (loc + 1, arg1); + STORE_NUMBER (loc + 3, arg2); +} + + +/* Copy the bytes from LOC to END to open up three bytes of space at LOC + for OP followed by two-byte integer parameter ARG. */ + +static void +insert_op1 (op, loc, arg, end) + re_opcode_t op; + unsigned char *loc; + int arg; + unsigned char *end; +{ + register unsigned char *pfrom = end; + register unsigned char *pto = end + 3; + + while (pfrom != loc) + *--pto = *--pfrom; + + store_op1 (op, loc, arg); +} + + +/* Like `insert_op1', but for two two-byte parameters ARG1 and ARG2. */ + +static void +insert_op2 (op, loc, arg1, arg2, end) + re_opcode_t op; + unsigned char *loc; + int arg1, arg2; + unsigned char *end; +{ + register unsigned char *pfrom = end; + register unsigned char *pto = end + 5; + + while (pfrom != loc) + *--pto = *--pfrom; + + store_op2 (op, loc, arg1, arg2); +} + + +/* P points to just after a ^ in PATTERN. Return true if that ^ comes + after an alternative or a begin-subexpression. We assume there is at + least one character before the ^. */ + +static boolean +at_begline_loc_p (pattern, p, syntax) + const char *pattern, *p; + reg_syntax_t syntax; +{ + const char *prev = p - 2; + boolean prev_prev_backslash = prev > pattern && prev[-1] == '\\'; + + return + /* After a subexpression? */ + (*prev == '(' && (syntax & RE_NO_BK_PARENS || prev_prev_backslash)) + /* After an alternative? */ + || (*prev == '|' && (syntax & RE_NO_BK_VBAR || prev_prev_backslash)); +} + + +/* The dual of at_begline_loc_p. This one is for $. We assume there is + at least one character after the $, i.e., `P < PEND'. */ + +static boolean +at_endline_loc_p (p, pend, syntax) + const char *p, *pend; + int syntax; +{ + const char *next = p; + boolean next_backslash = *next == '\\'; + const char *next_next = p + 1 < pend ? p + 1 : NULL; + + return + /* Before a subexpression? */ + (syntax & RE_NO_BK_PARENS ? *next == ')' + : next_backslash && next_next && *next_next == ')') + /* Before an alternative? */ + || (syntax & RE_NO_BK_VBAR ? *next == '|' + : next_backslash && next_next && *next_next == '|'); +} + + +/* Returns true if REGNUM is in one of COMPILE_STACK's elements and + false if it's not. */ + +static boolean +group_in_compile_stack (compile_stack, regnum) + compile_stack_type compile_stack; + regnum_t regnum; +{ + int this_element; + + for (this_element = compile_stack.avail - 1; + this_element >= 0; + this_element--) + if (compile_stack.stack[this_element].regnum == regnum) + return true; + + return false; +} + + +/* Read the ending character of a range (in a bracket expression) from the + uncompiled pattern *P_PTR (which ends at PEND). We assume the + starting character is in `P[-2]'. (`P[-1]' is the character `-'.) + Then we set the translation of all bits between the starting and + ending characters (inclusive) in the compiled pattern B. + + Return an error code. + + We use these short variable names so we can use the same macros as + `regex_compile' itself. */ + +static reg_errcode_t +compile_range (p_ptr, pend, translate, syntax, b) + const char **p_ptr, *pend; + char *translate; + reg_syntax_t syntax; + unsigned char *b; +{ + unsigned this_char; + + const char *p = *p_ptr; + int range_start, range_end; + + if (p == pend) + return REG_ERANGE; + + /* Even though the pattern is a signed `char *', we need to fetch + with unsigned char *'s; if the high bit of the pattern character + is set, the range endpoints will be negative if we fetch using a + signed char *. + + We also want to fetch the endpoints without translating them; the + appropriate translation is done in the bit-setting loop below. */ + range_start = ((unsigned char *) p)[-2]; + range_end = ((unsigned char *) p)[0]; + + /* Have to increment the pointer into the pattern string, so the + caller isn't still at the ending character. */ + (*p_ptr)++; + + /* If the start is after the end, the range is empty. */ + if (range_start > range_end) + return syntax & RE_NO_EMPTY_RANGES ? REG_ERANGE : REG_NOERROR; + + /* Here we see why `this_char' has to be larger than an `unsigned + char' -- the range is inclusive, so if `range_end' == 0xff + (assuming 8-bit characters), we would otherwise go into an infinite + loop, since all characters <= 0xff. */ + for (this_char = range_start; this_char <= range_end; this_char++) + { + SET_LIST_BIT (TRANSLATE (this_char)); + } + + return REG_NOERROR; +} + +/* Failure stack declarations and macros; both re_compile_fastmap and + re_match_2 use a failure stack. These have to be macros because of + REGEX_ALLOCATE. */ + + +/* Number of failure points for which to initially allocate space + when matching. If this number is exceeded, we allocate more + space, so it is not a hard limit. */ +#ifndef INIT_FAILURE_ALLOC +#define INIT_FAILURE_ALLOC 5 +#endif + +/* Roughly the maximum number of failure points on the stack. Would be + exactly that if always used MAX_FAILURE_SPACE each time we failed. + This is a variable only so users of regex can assign to it; we never + change it ourselves. */ +int re_max_failures = 2000; + +typedef const unsigned char *fail_stack_elt_t; + +typedef struct +{ + fail_stack_elt_t *stack; + unsigned size; + unsigned avail; /* Offset of next open position. */ +} fail_stack_type; + +#define FAIL_STACK_EMPTY() (fail_stack.avail == 0) +#define FAIL_STACK_PTR_EMPTY() (fail_stack_ptr->avail == 0) +#define FAIL_STACK_FULL() (fail_stack.avail == fail_stack.size) +#define FAIL_STACK_TOP() (fail_stack.stack[fail_stack.avail]) + + +/* Initialize `fail_stack'. Do `return -2' if the alloc fails. */ + +#define INIT_FAIL_STACK() \ + do { \ + fail_stack.stack = (fail_stack_elt_t *) \ + REGEX_ALLOCATE (INIT_FAILURE_ALLOC * sizeof (fail_stack_elt_t)); \ + \ + if (fail_stack.stack == NULL) \ + return -2; \ + \ + fail_stack.size = INIT_FAILURE_ALLOC; \ + fail_stack.avail = 0; \ + } while (0) + + +/* Double the size of FAIL_STACK, up to approximately `re_max_failures' items. + + Return 1 if succeeds, and 0 if either ran out of memory + allocating space for it or it was already too large. + + REGEX_REALLOCATE requires `destination' be declared. */ + +#define DOUBLE_FAIL_STACK(fail_stack) \ + ((fail_stack).size > re_max_failures * MAX_FAILURE_ITEMS \ + ? 0 \ + : ((fail_stack).stack = (fail_stack_elt_t *) \ + REGEX_REALLOCATE ((fail_stack).stack, \ + (fail_stack).size * sizeof (fail_stack_elt_t), \ + ((fail_stack).size << 1) * sizeof (fail_stack_elt_t)), \ + \ + (fail_stack).stack == NULL \ + ? 0 \ + : ((fail_stack).size <<= 1, \ + 1))) + + +/* Push PATTERN_OP on FAIL_STACK. + + Return 1 if was able to do so and 0 if ran out of memory allocating + space to do so. */ +#define PUSH_PATTERN_OP(pattern_op, fail_stack) \ + ((FAIL_STACK_FULL () \ + && !DOUBLE_FAIL_STACK (fail_stack)) \ + ? 0 \ + : ((fail_stack).stack[(fail_stack).avail++] = pattern_op, \ + 1)) + +/* This pushes an item onto the failure stack. Must be a four-byte + value. Assumes the variable `fail_stack'. Probably should only + be called from within `PUSH_FAILURE_POINT'. */ +#define PUSH_FAILURE_ITEM(item) \ + fail_stack.stack[fail_stack.avail++] = (fail_stack_elt_t) item + +/* The complement operation. Assumes `fail_stack' is nonempty. */ +#define POP_FAILURE_ITEM() fail_stack.stack[--fail_stack.avail] + +/* Used to omit pushing failure point id's when we're not debugging. */ +#ifdef DEBUG +#define DEBUG_PUSH PUSH_FAILURE_ITEM +#define DEBUG_POP(item_addr) *(item_addr) = POP_FAILURE_ITEM () +#else +#define DEBUG_PUSH(item) +#define DEBUG_POP(item_addr) +#endif + + +/* Push the information about the state we will need + if we ever fail back to it. + + Requires variables fail_stack, regstart, regend, reg_info, and + num_regs be declared. DOUBLE_FAIL_STACK requires `destination' be + declared. + + Does `return FAILURE_CODE' if runs out of memory. */ + +#define PUSH_FAILURE_POINT(pattern_place, string_place, failure_code) \ + do { \ + char *destination; \ + /* Must be int, so when we don't save any registers, the arithmetic \ + of 0 + -1 isn't done as unsigned. */ \ + int this_reg; \ + \ + DEBUG_STATEMENT (failure_id++); \ + DEBUG_STATEMENT (nfailure_points_pushed++); \ + DEBUG_PRINT2 ("\nPUSH_FAILURE_POINT #%u:\n", failure_id); \ + DEBUG_PRINT2 (" Before push, next avail: %d\n", (fail_stack).avail);\ + DEBUG_PRINT2 (" size: %d\n", (fail_stack).size);\ + \ + DEBUG_PRINT2 (" slots needed: %d\n", NUM_FAILURE_ITEMS); \ + DEBUG_PRINT2 (" available: %d\n", REMAINING_AVAIL_SLOTS); \ + \ + /* Ensure we have enough space allocated for what we will push. */ \ + while (REMAINING_AVAIL_SLOTS < NUM_FAILURE_ITEMS) \ + { \ + if (!DOUBLE_FAIL_STACK (fail_stack)) \ + return failure_code; \ + \ + DEBUG_PRINT2 ("\n Doubled stack; size now: %d\n", \ + (fail_stack).size); \ + DEBUG_PRINT2 (" slots available: %d\n", REMAINING_AVAIL_SLOTS);\ + } \ + \ + /* Push the info, starting with the registers. */ \ + DEBUG_PRINT1 ("\n"); \ + \ + for (this_reg = lowest_active_reg; this_reg <= highest_active_reg; \ + this_reg++) \ + { \ + DEBUG_PRINT2 (" Pushing reg: %d\n", this_reg); \ + DEBUG_STATEMENT (num_regs_pushed++); \ + \ + DEBUG_PRINT2 (" start: 0x%x\n", regstart[this_reg]); \ + PUSH_FAILURE_ITEM (regstart[this_reg]); \ + \ + DEBUG_PRINT2 (" end: 0x%x\n", regend[this_reg]); \ + PUSH_FAILURE_ITEM (regend[this_reg]); \ + \ + DEBUG_PRINT2 (" info: 0x%x\n ", reg_info[this_reg]); \ + DEBUG_PRINT2 (" match_null=%d", \ + REG_MATCH_NULL_STRING_P (reg_info[this_reg])); \ + DEBUG_PRINT2 (" active=%d", IS_ACTIVE (reg_info[this_reg])); \ + DEBUG_PRINT2 (" matched_something=%d", \ + MATCHED_SOMETHING (reg_info[this_reg])); \ + DEBUG_PRINT2 (" ever_matched=%d", \ + EVER_MATCHED_SOMETHING (reg_info[this_reg])); \ + DEBUG_PRINT1 ("\n"); \ + PUSH_FAILURE_ITEM (reg_info[this_reg].word); \ + } \ + \ + DEBUG_PRINT2 (" Pushing low active reg: %d\n", lowest_active_reg);\ + PUSH_FAILURE_ITEM (lowest_active_reg); \ + \ + DEBUG_PRINT2 (" Pushing high active reg: %d\n", highest_active_reg);\ + PUSH_FAILURE_ITEM (highest_active_reg); \ + \ + DEBUG_PRINT2 (" Pushing pattern 0x%x: ", pattern_place); \ + DEBUG_PRINT_COMPILED_PATTERN (bufp, pattern_place, pend); \ + PUSH_FAILURE_ITEM (pattern_place); \ + \ + DEBUG_PRINT2 (" Pushing string 0x%x: `", string_place); \ + DEBUG_PRINT_DOUBLE_STRING (string_place, string1, size1, string2, \ + size2); \ + DEBUG_PRINT1 ("'\n"); \ + PUSH_FAILURE_ITEM (string_place); \ + \ + DEBUG_PRINT2 (" Pushing failure id: %u\n", failure_id); \ + DEBUG_PUSH (failure_id); \ + } while (0) + +/* This is the number of items that are pushed and popped on the stack + for each register. */ +#define NUM_REG_ITEMS 3 + +/* Individual items aside from the registers. */ +#ifdef DEBUG +#define NUM_NONREG_ITEMS 5 /* Includes failure point id. */ +#else +#define NUM_NONREG_ITEMS 4 +#endif + +/* We push at most this many items on the stack. */ +#define MAX_FAILURE_ITEMS ((num_regs - 1) * NUM_REG_ITEMS + NUM_NONREG_ITEMS) + +/* We actually push this many items. */ +#define NUM_FAILURE_ITEMS \ + ((highest_active_reg - lowest_active_reg + 1) * NUM_REG_ITEMS \ + + NUM_NONREG_ITEMS) + +/* How many items can still be added to the stack without overflowing it. */ +#define REMAINING_AVAIL_SLOTS ((fail_stack).size - (fail_stack).avail) + + +/* Pops what PUSH_FAIL_STACK pushes. + + We restore into the parameters, all of which should be lvalues: + STR -- the saved data position. + PAT -- the saved pattern position. + LOW_REG, HIGH_REG -- the highest and lowest active registers. + REGSTART, REGEND -- arrays of string positions. + REG_INFO -- array of information about each subexpression. + + Also assumes the variables `fail_stack' and (if debugging), `bufp', + `pend', `string1', `size1', `string2', and `size2'. */ + +#define POP_FAILURE_POINT(str, pat, low_reg, high_reg, regstart, regend, reg_info)\ +{ \ + DEBUG_STATEMENT (fail_stack_elt_t failure_id;) \ + int this_reg; \ + const unsigned char *string_temp; \ + \ + assert (!FAIL_STACK_EMPTY ()); \ + \ + /* Remove failure points and point to how many regs pushed. */ \ + DEBUG_PRINT1 ("POP_FAILURE_POINT:\n"); \ + DEBUG_PRINT2 (" Before pop, next avail: %d\n", fail_stack.avail); \ + DEBUG_PRINT2 (" size: %d\n", fail_stack.size); \ + \ + assert (fail_stack.avail >= NUM_NONREG_ITEMS); \ + \ + DEBUG_POP (&failure_id); \ + DEBUG_PRINT2 (" Popping failure id: %u\n", failure_id); \ + \ + /* If the saved string location is NULL, it came from an \ + on_failure_keep_string_jump opcode, and we want to throw away the \ + saved NULL, thus retaining our current position in the string. */ \ + string_temp = POP_FAILURE_ITEM (); \ + if (string_temp != NULL) \ + str = (const char *) string_temp; \ + \ + DEBUG_PRINT2 (" Popping string 0x%x: `", str); \ + DEBUG_PRINT_DOUBLE_STRING (str, string1, size1, string2, size2); \ + DEBUG_PRINT1 ("'\n"); \ + \ + pat = (unsigned char *) POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" Popping pattern 0x%x: ", pat); \ + DEBUG_PRINT_COMPILED_PATTERN (bufp, pat, pend); \ + \ + /* Restore register info. */ \ + high_reg = (unsigned) POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" Popping high active reg: %d\n", high_reg); \ + \ + low_reg = (unsigned) POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" Popping low active reg: %d\n", low_reg); \ + \ + for (this_reg = high_reg; this_reg >= low_reg; this_reg--) \ + { \ + DEBUG_PRINT2 (" Popping reg: %d\n", this_reg); \ + \ + reg_info[this_reg].word = POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" info: 0x%x\n", reg_info[this_reg]); \ + \ + regend[this_reg] = (const char *) POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" end: 0x%x\n", regend[this_reg]); \ + \ + regstart[this_reg] = (const char *) POP_FAILURE_ITEM (); \ + DEBUG_PRINT2 (" start: 0x%x\n", regstart[this_reg]); \ + } \ + \ + DEBUG_STATEMENT (nfailure_points_popped++); \ +} /* POP_FAILURE_POINT */ + +/* re_compile_fastmap computes a ``fastmap'' for the compiled pattern in + BUFP. A fastmap records which of the (1 << BYTEWIDTH) possible + characters can start a string that matches the pattern. This fastmap + is used by re_search to skip quickly over impossible starting points. + + The caller must supply the address of a (1 << BYTEWIDTH)-byte data + area as BUFP->fastmap. + + We set the `fastmap', `fastmap_accurate', and `can_be_null' fields in + the pattern buffer. + + Returns 0 if we succeed, -2 if an internal error. */ + +int +re_compile_fastmap (bufp) + struct re_pattern_buffer *bufp; +{ + int j, k; + fail_stack_type fail_stack; +#ifndef REGEX_MALLOC + char *destination; +#endif + /* We don't push any register information onto the failure stack. */ + unsigned num_regs = 0; + + register char *fastmap = bufp->fastmap; + unsigned char *pattern = bufp->buffer; + unsigned long size = bufp->used; + const unsigned char *p = pattern; + register unsigned char *pend = pattern + size; + + /* Assume that each path through the pattern can be null until + proven otherwise. We set this false at the bottom of switch + statement, to which we get only if a particular path doesn't + match the empty string. */ + boolean path_can_be_null = true; + + /* We aren't doing a `succeed_n' to begin with. */ + boolean succeed_n_p = false; + + assert (fastmap != NULL && p != NULL); + + INIT_FAIL_STACK (); + bzero (fastmap, 1 << BYTEWIDTH); /* Assume nothing's valid. */ + bufp->fastmap_accurate = 1; /* It will be when we're done. */ + bufp->can_be_null = 0; + + while (p != pend || !FAIL_STACK_EMPTY ()) + { + if (p == pend) + { + bufp->can_be_null |= path_can_be_null; + + /* Reset for next path. */ + path_can_be_null = true; + + p = fail_stack.stack[--fail_stack.avail]; + } + + /* We should never be about to go beyond the end of the pattern. */ + assert (p < pend); + +#ifdef SWITCH_ENUM_BUG + switch ((int) ((re_opcode_t) *p++)) +#else + switch ((re_opcode_t) *p++) +#endif + { + + /* I guess the idea here is to simply not bother with a fastmap + if a backreference is used, since it's too hard to figure out + the fastmap for the corresponding group. Setting + `can_be_null' stops `re_search_2' from using the fastmap, so + that is all we do. */ + case duplicate: + bufp->can_be_null = 1; + return 0; + + + /* Following are the cases which match a character. These end + with `break'. */ + + case exactn: + fastmap[p[1]] = 1; + break; + + + case charset: + for (j = *p++ * BYTEWIDTH - 1; j >= 0; j--) + if (p[j / BYTEWIDTH] & (1 << (j % BYTEWIDTH))) + fastmap[j] = 1; + break; + + + case charset_not: + /* Chars beyond end of map must be allowed. */ + for (j = *p * BYTEWIDTH; j < (1 << BYTEWIDTH); j++) + fastmap[j] = 1; + + for (j = *p++ * BYTEWIDTH - 1; j >= 0; j--) + if (!(p[j / BYTEWIDTH] & (1 << (j % BYTEWIDTH)))) + fastmap[j] = 1; + break; + + + case wordchar: + for (j = 0; j < (1 << BYTEWIDTH); j++) + if (SYNTAX (j) == Sword) + fastmap[j] = 1; + break; + + + case notwordchar: + for (j = 0; j < (1 << BYTEWIDTH); j++) + if (SYNTAX (j) != Sword) + fastmap[j] = 1; + break; + + + case anychar: + /* `.' matches anything ... */ + for (j = 0; j < (1 << BYTEWIDTH); j++) + fastmap[j] = 1; + + /* ... except perhaps newline. */ + if (!(bufp->syntax & RE_DOT_NEWLINE)) + fastmap['\n'] = 0; + + /* Return if we have already set `can_be_null'; if we have, + then the fastmap is irrelevant. Something's wrong here. */ + else if (bufp->can_be_null) + return 0; + + /* Otherwise, have to check alternative paths. */ + break; + + +#ifdef emacs + case syntaxspec: + k = *p++; + for (j = 0; j < (1 << BYTEWIDTH); j++) + if (SYNTAX (j) == (enum syntaxcode) k) + fastmap[j] = 1; + break; + + + case notsyntaxspec: + k = *p++; + for (j = 0; j < (1 << BYTEWIDTH); j++) + if (SYNTAX (j) != (enum syntaxcode) k) + fastmap[j] = 1; + break; + + + /* All cases after this match the empty string. These end with + `continue'. */ + + + case before_dot: + case at_dot: + case after_dot: + continue; +#endif /* not emacs */ + + + case no_op: + case begline: + case endline: + case begbuf: + case endbuf: + case wordbound: + case notwordbound: + case wordbeg: + case wordend: + case push_dummy_failure: + continue; + + + case jump_n: + case pop_failure_jump: + case maybe_pop_jump: + case jump: + case jump_past_alt: + case dummy_failure_jump: + EXTRACT_NUMBER_AND_INCR (j, p); + p += j; + if (j > 0) + continue; + + /* Jump backward implies we just went through the body of a + loop and matched nothing. Opcode jumped to should be + `on_failure_jump' or `succeed_n'. Just treat it like an + ordinary jump. For a * loop, it has pushed its failure + point already; if so, discard that as redundant. */ + if ((re_opcode_t) *p != on_failure_jump + && (re_opcode_t) *p != succeed_n) + continue; + + p++; + EXTRACT_NUMBER_AND_INCR (j, p); + p += j; + + /* If what's on the stack is where we are now, pop it. */ + if (!FAIL_STACK_EMPTY () + && fail_stack.stack[fail_stack.avail - 1] == p) + fail_stack.avail--; + + continue; + + + case on_failure_jump: + case on_failure_keep_string_jump: + handle_on_failure_jump: + EXTRACT_NUMBER_AND_INCR (j, p); + + /* For some patterns, e.g., `(a?)?', `p+j' here points to the + end of the pattern. We don't want to push such a point, + since when we restore it above, entering the switch will + increment `p' past the end of the pattern. We don't need + to push such a point since we obviously won't find any more + fastmap entries beyond `pend'. Such a pattern can match + the null string, though. */ + if (p + j < pend) + { + if (!PUSH_PATTERN_OP (p + j, fail_stack)) + return -2; + } + else + bufp->can_be_null = 1; + + if (succeed_n_p) + { + EXTRACT_NUMBER_AND_INCR (k, p); /* Skip the n. */ + succeed_n_p = false; + } + + continue; + + + case succeed_n: + /* Get to the number of times to succeed. */ + p += 2; + + /* Increment p past the n for when k != 0. */ + EXTRACT_NUMBER_AND_INCR (k, p); + if (k == 0) + { + p -= 4; + succeed_n_p = true; /* Spaghetti code alert. */ + goto handle_on_failure_jump; + } + continue; + + + case set_number_at: + p += 4; + continue; + + + case start_memory: + case stop_memory: + p += 2; + continue; + + + default: + abort (); /* We have listed all the cases. */ + } /* switch *p++ */ + + /* Getting here means we have found the possible starting + characters for one path of the pattern -- and that the empty + string does not match. We need not follow this path further. + Instead, look at the next alternative (remembered on the + stack), or quit if no more. The test at the top of the loop + does these things. */ + path_can_be_null = false; + p = pend; + } /* while p */ + + /* Set `can_be_null' for the last path (also the first path, if the + pattern is empty). */ + bufp->can_be_null |= path_can_be_null; + return 0; +} /* re_compile_fastmap */ + +/* Set REGS to hold NUM_REGS registers, storing them in STARTS and + ENDS. Subsequent matches using PATTERN_BUFFER and REGS will use + this memory for recording register information. STARTS and ENDS + must be allocated using the malloc library routine, and must each + be at least NUM_REGS * sizeof (regoff_t) bytes long. + + If NUM_REGS == 0, then subsequent matches should allocate their own + register data. + + Unless this function is called, the first search or match using + PATTERN_BUFFER will allocate its own register data, without + freeing the old data. */ + +void +re_set_registers (bufp, regs, num_regs, starts, ends) + struct re_pattern_buffer *bufp; + struct re_registers *regs; + unsigned num_regs; + regoff_t *starts, *ends; +{ + if (num_regs) + { + bufp->regs_allocated = REGS_REALLOCATE; + regs->num_regs = num_regs; + regs->start = starts; + regs->end = ends; + } + else + { + bufp->regs_allocated = REGS_UNALLOCATED; + regs->num_regs = 0; + regs->start = regs->end = (regoff_t) 0; + } +} + +/* Searching routines. */ + +/* Like re_search_2, below, but only one string is specified, and + doesn't let you say where to stop matching. */ + +int +re_search (bufp, string, size, startpos, range, regs) + struct re_pattern_buffer *bufp; + const char *string; + int size, startpos, range; + struct re_registers *regs; +{ + return re_search_2 (bufp, NULL, 0, string, size, startpos, range, + regs, size); +} + + +/* Using the compiled pattern in BUFP->buffer, first tries to match the + virtual concatenation of STRING1 and STRING2, starting first at index + STARTPOS, then at STARTPOS + 1, and so on. + + STRING1 and STRING2 have length SIZE1 and SIZE2, respectively. + + RANGE is how far to scan while trying to match. RANGE = 0 means try + only at STARTPOS; in general, the last start tried is STARTPOS + + RANGE. + + In REGS, return the indices of the virtual concatenation of STRING1 + and STRING2 that matched the entire BUFP->buffer and its contained + subexpressions. + + Do not consider matching one past the index STOP in the virtual + concatenation of STRING1 and STRING2. + + We return either the position in the strings at which the match was + found, -1 if no match, or -2 if error (such as failure + stack overflow). */ + +int +re_search_2 (bufp, string1, size1, string2, size2, startpos, range, regs, stop) + struct re_pattern_buffer *bufp; + const char *string1, *string2; + int size1, size2; + int startpos; + int range; + struct re_registers *regs; + int stop; +{ + int val; + register char *fastmap = bufp->fastmap; + register char *translate = bufp->translate; + int total_size = size1 + size2; + int endpos = startpos + range; + + /* Check for out-of-range STARTPOS. */ + if (startpos < 0 || startpos > total_size) + return -1; + + /* Fix up RANGE if it might eventually take us outside + the virtual concatenation of STRING1 and STRING2. */ + if (endpos < -1) + range = -1 - startpos; + else if (endpos > total_size) + range = total_size - startpos; + + /* If the search isn't to be a backwards one, don't waste time in a + search for a pattern that must be anchored. */ + if (bufp->used > 0 && (re_opcode_t) bufp->buffer[0] == begbuf && range > 0) + { + if (startpos > 0) + return -1; + else + range = 1; + } + + /* Update the fastmap now if not correct already. */ + if (fastmap && !bufp->fastmap_accurate) + if (re_compile_fastmap (bufp) == -2) + return -2; + + /* Loop through the string, looking for a place to start matching. */ + for (;;) + { + /* If a fastmap is supplied, skip quickly over characters that + cannot be the start of a match. If the pattern can match the + null string, however, we don't need to skip characters; we want + the first null string. */ + if (fastmap && startpos < total_size && !bufp->can_be_null) + { + if (range > 0) /* Searching forwards. */ + { + register const char *d; + register int lim = 0; + int irange = range; + + if (startpos < size1 && startpos + range >= size1) + lim = range - (size1 - startpos); + + d = (startpos >= size1 ? string2 - size1 : string1) + startpos; + + /* Written out as an if-else to avoid testing `translate' + inside the loop. */ + if (translate) + while (range > lim + && !fastmap[(unsigned char) + translate[(unsigned char) *d++]]) + range--; + else + while (range > lim && !fastmap[(unsigned char) *d++]) + range--; + + startpos += irange - range; + } + else /* Searching backwards. */ + { + register char c = (size1 == 0 || startpos >= size1 + ? string2[startpos - size1] + : string1[startpos]); + + if (!fastmap[(unsigned char) TRANSLATE (c)]) + goto advance; + } + } + + /* If can't match the null string, and that's all we have left, fail. */ + if (range >= 0 && startpos == total_size && fastmap + && !bufp->can_be_null) + return -1; + + val = re_match_2 (bufp, string1, size1, string2, size2, + startpos, regs, stop); + if (val >= 0) + return startpos; + + if (val == -2) + return -2; + + advance: + if (!range) + break; + else if (range > 0) + { + range--; + startpos++; + } + else + { + range++; + startpos--; + } + } + return -1; +} /* re_search_2 */ + +/* Declarations and macros for re_match_2. */ + +static int bcmp_translate (); +static boolean alt_match_null_string_p (), + common_op_match_null_string_p (), + group_match_null_string_p (); + +/* Structure for per-register (a.k.a. per-group) information. + This must not be longer than one word, because we push this value + onto the failure stack. Other register information, such as the + starting and ending positions (which are addresses), and the list of + inner groups (which is a bits list) are maintained in separate + variables. + + We are making a (strictly speaking) nonportable assumption here: that + the compiler will pack our bit fields into something that fits into + the type of `word', i.e., is something that fits into one item on the + failure stack. */ +typedef union +{ + fail_stack_elt_t word; + struct + { + /* This field is one if this group can match the empty string, + zero if not. If not yet determined, `MATCH_NULL_UNSET_VALUE'. */ +#define MATCH_NULL_UNSET_VALUE 3 + unsigned match_null_string_p : 2; + unsigned is_active : 1; + unsigned matched_something : 1; + unsigned ever_matched_something : 1; + } bits; +} register_info_type; + +#define REG_MATCH_NULL_STRING_P(R) ((R).bits.match_null_string_p) +#define IS_ACTIVE(R) ((R).bits.is_active) +#define MATCHED_SOMETHING(R) ((R).bits.matched_something) +#define EVER_MATCHED_SOMETHING(R) ((R).bits.ever_matched_something) + + +/* Call this when have matched a real character; it sets `matched' flags + for the subexpressions which we are currently inside. Also records + that those subexprs have matched. */ +#define SET_REGS_MATCHED() \ + do \ + { \ + unsigned r; \ + for (r = lowest_active_reg; r <= highest_active_reg; r++) \ + { \ + MATCHED_SOMETHING (reg_info[r]) \ + = EVER_MATCHED_SOMETHING (reg_info[r]) \ + = 1; \ + } \ + } \ + while (0) + + +/* This converts PTR, a pointer into one of the search strings `string1' + and `string2' into an offset from the beginning of that string. */ +#define POINTER_TO_OFFSET(ptr) \ + (FIRST_STRING_P (ptr) ? (ptr) - string1 : (ptr) - string2 + size1) + +/* Registers are set to a sentinel when they haven't yet matched. */ +#define REG_UNSET_VALUE ((char *) -1) +#define REG_UNSET(e) ((e) == REG_UNSET_VALUE) + + +/* Macros for dealing with the split strings in re_match_2. */ + +#define MATCHING_IN_FIRST_STRING (dend == end_match_1) + +/* Call before fetching a character with *d. This switches over to + string2 if necessary. */ +#define PREFETCH() \ + while (d == dend) \ + { \ + /* End of string2 => fail. */ \ + if (dend == end_match_2) \ + goto fail; \ + /* End of string1 => advance to string2. */ \ + d = string2; \ + dend = end_match_2; \ + } + + +/* Test if at very beginning or at very end of the virtual concatenation + of `string1' and `string2'. If only one string, it's `string2'. */ +#define AT_STRINGS_BEG(d) ((d) == (size1 ? string1 : string2) || !size2) +#define AT_STRINGS_END(d) ((d) == end2) + + +/* Test if D points to a character which is word-constituent. We have + two special cases to check for: if past the end of string1, look at + the first character in string2; and if before the beginning of + string2, look at the last character in string1. */ +#define WORDCHAR_P(d) \ + (SYNTAX ((d) == end1 ? *string2 \ + : (d) == string2 - 1 ? *(end1 - 1) : *(d)) \ + == Sword) + +/* Test if the character before D and the one at D differ with respect + to being word-constituent. */ +#define AT_WORD_BOUNDARY(d) \ + (AT_STRINGS_BEG (d) || AT_STRINGS_END (d) \ + || WORDCHAR_P (d - 1) != WORDCHAR_P (d)) + + +/* Free everything we malloc. */ +#ifdef REGEX_MALLOC +#define FREE_VAR(var) if (var) free (var); var = NULL +#define FREE_VARIABLES() \ + do { \ + FREE_VAR (fail_stack.stack); \ + FREE_VAR (regstart); \ + FREE_VAR (regend); \ + FREE_VAR (old_regstart); \ + FREE_VAR (old_regend); \ + FREE_VAR (best_regstart); \ + FREE_VAR (best_regend); \ + FREE_VAR (reg_info); \ + FREE_VAR (reg_dummy); \ + FREE_VAR (reg_info_dummy); \ + } while (0) +#else /* not REGEX_MALLOC */ +/* Some MIPS systems (at least) want this to free alloca'd storage. */ +#define FREE_VARIABLES() alloca (0) +#endif /* not REGEX_MALLOC */ + + +/* These values must meet several constraints. They must not be valid + register values; since we have a limit of 255 registers (because + we use only one byte in the pattern for the register number), we can + use numbers larger than 255. They must differ by 1, because of + NUM_FAILURE_ITEMS above. And the value for the lowest register must + be larger than the value for the highest register, so we do not try + to actually save any registers when none are active. */ +#define NO_HIGHEST_ACTIVE_REG (1 << BYTEWIDTH) +#define NO_LOWEST_ACTIVE_REG (NO_HIGHEST_ACTIVE_REG + 1) + +/* Matching routines. */ + +#ifndef emacs /* Emacs never uses this. */ +/* re_match is like re_match_2 except it takes only a single string. */ + +int +re_match (bufp, string, size, pos, regs) + struct re_pattern_buffer *bufp; + const char *string; + int size, pos; + struct re_registers *regs; + { + return re_match_2 (bufp, NULL, 0, string, size, pos, regs, size); +} +#endif /* not emacs */ + + +/* re_match_2 matches the compiled pattern in BUFP against the + the (virtual) concatenation of STRING1 and STRING2 (of length SIZE1 + and SIZE2, respectively). We start matching at POS, and stop + matching at STOP. + + If REGS is non-null and the `no_sub' field of BUFP is nonzero, we + store offsets for the substring each group matched in REGS. See the + documentation for exactly how many groups we fill. + + We return -1 if no match, -2 if an internal error (such as the + failure stack overflowing). Otherwise, we return the length of the + matched substring. */ + +int +re_match_2 (bufp, string1, size1, string2, size2, pos, regs, stop) + struct re_pattern_buffer *bufp; + const char *string1, *string2; + int size1, size2; + int pos; + struct re_registers *regs; + int stop; +{ + /* General temporaries. */ + int mcnt; + unsigned char *p1; + + /* Just past the end of the corresponding string. */ + const char *end1, *end2; + + /* Pointers into string1 and string2, just past the last characters in + each to consider matching. */ + const char *end_match_1, *end_match_2; + + /* Where we are in the data, and the end of the current string. */ + const char *d, *dend; + + /* Where we are in the pattern, and the end of the pattern. */ + unsigned char *p = bufp->buffer; + register unsigned char *pend = p + bufp->used; + + /* We use this to map every character in the string. */ + char *translate = bufp->translate; + + /* Failure point stack. Each place that can handle a failure further + down the line pushes a failure point on this stack. It consists of + restart, regend, and reg_info for all registers corresponding to + the subexpressions we're currently inside, plus the number of such + registers, and, finally, two char *'s. The first char * is where + to resume scanning the pattern; the second one is where to resume + scanning the strings. If the latter is zero, the failure point is + a ``dummy''; if a failure happens and the failure point is a dummy, + it gets discarded and the next next one is tried. */ + fail_stack_type fail_stack; +#ifdef DEBUG + static unsigned failure_id = 0; + unsigned nfailure_points_pushed = 0, nfailure_points_popped = 0; +#endif + + /* We fill all the registers internally, independent of what we + return, for use in backreferences. The number here includes + an element for register zero. */ + unsigned num_regs = bufp->re_nsub + 1; + + /* The currently active registers. */ + unsigned lowest_active_reg = NO_LOWEST_ACTIVE_REG; + unsigned highest_active_reg = NO_HIGHEST_ACTIVE_REG; + + /* Information on the contents of registers. These are pointers into + the input strings; they record just what was matched (on this + attempt) by a subexpression part of the pattern, that is, the + regnum-th regstart pointer points to where in the pattern we began + matching and the regnum-th regend points to right after where we + stopped matching the regnum-th subexpression. (The zeroth register + keeps track of what the whole pattern matches.) */ + const char **regstart = NULL, **regend = NULL; + + /* If a group that's operated upon by a repetition operator fails to + match anything, then the register for its start will need to be + restored because it will have been set to wherever in the string we + are when we last see its open-group operator. Similarly for a + register's end. */ + const char **old_regstart = NULL, **old_regend = NULL; + + /* The is_active field of reg_info helps us keep track of which (possibly + nested) subexpressions we are currently in. The matched_something + field of reg_info[reg_num] helps us tell whether or not we have + matched any of the pattern so far this time through the reg_num-th + subexpression. These two fields get reset each time through any + loop their register is in. */ + register_info_type *reg_info = NULL; + + /* The following record the register info as found in the above + variables when we find a match better than any we've seen before. + This happens as we backtrack through the failure points, which in + turn happens only if we have not yet matched the entire string. */ + unsigned best_regs_set = false; + const char **best_regstart = NULL, **best_regend = NULL; + + /* Logically, this is `best_regend[0]'. But we don't want to have to + allocate space for that if we're not allocating space for anything + else (see below). Also, we never need info about register 0 for + any of the other register vectors, and it seems rather a kludge to + treat `best_regend' differently than the rest. So we keep track of + the end of the best match so far in a separate variable. We + initialize this to NULL so that when we backtrack the first time + and need to test it, it's not garbage. */ + const char *match_end = NULL; + + /* Used when we pop values we don't care about. */ + const char **reg_dummy = NULL; + register_info_type *reg_info_dummy = NULL; + +#ifdef DEBUG + /* Counts the total number of registers pushed. */ + unsigned num_regs_pushed = 0; +#endif + + DEBUG_PRINT1 ("\n\nEntering re_match_2.\n"); + + INIT_FAIL_STACK (); + + /* Do not bother to initialize all the register variables if there are + no groups in the pattern, as it takes a fair amount of time. If + there are groups, we include space for register 0 (the whole + pattern), even though we never use it, since it simplifies the + array indexing. We should fix this. */ + if (bufp->re_nsub) + { + regstart = REGEX_TALLOC (num_regs, const char *); + regend = REGEX_TALLOC (num_regs, const char *); + old_regstart = REGEX_TALLOC (num_regs, const char *); + old_regend = REGEX_TALLOC (num_regs, const char *); + best_regstart = REGEX_TALLOC (num_regs, const char *); + best_regend = REGEX_TALLOC (num_regs, const char *); + reg_info = REGEX_TALLOC (num_regs, register_info_type); + reg_dummy = REGEX_TALLOC (num_regs, const char *); + reg_info_dummy = REGEX_TALLOC (num_regs, register_info_type); + + if (!(regstart && regend && old_regstart && old_regend && reg_info + && best_regstart && best_regend && reg_dummy && reg_info_dummy)) + { + FREE_VARIABLES (); + return -2; + } + } +#ifdef REGEX_MALLOC + else + { + /* We must initialize all our variables to NULL, so that + `FREE_VARIABLES' doesn't try to free them. */ + regstart = regend = old_regstart = old_regend = best_regstart + = best_regend = reg_dummy = NULL; + reg_info = reg_info_dummy = (register_info_type *) NULL; + } +#endif /* REGEX_MALLOC */ + + /* The starting position is bogus. */ + if (pos < 0 || pos > size1 + size2) + { + FREE_VARIABLES (); + return -1; + } + + /* Initialize subexpression text positions to -1 to mark ones that no + start_memory/stop_memory has been seen for. Also initialize the + register information struct. */ + for (mcnt = 1; mcnt < num_regs; mcnt++) + { + regstart[mcnt] = regend[mcnt] + = old_regstart[mcnt] = old_regend[mcnt] = REG_UNSET_VALUE; + + REG_MATCH_NULL_STRING_P (reg_info[mcnt]) = MATCH_NULL_UNSET_VALUE; + IS_ACTIVE (reg_info[mcnt]) = 0; + MATCHED_SOMETHING (reg_info[mcnt]) = 0; + EVER_MATCHED_SOMETHING (reg_info[mcnt]) = 0; + } + + /* We move `string1' into `string2' if the latter's empty -- but not if + `string1' is null. */ + if (size2 == 0 && string1 != NULL) + { + string2 = string1; + size2 = size1; + string1 = 0; + size1 = 0; + } + end1 = string1 + size1; + end2 = string2 + size2; + + /* Compute where to stop matching, within the two strings. */ + if (stop <= size1) + { + end_match_1 = string1 + stop; + end_match_2 = string2; + } + else + { + end_match_1 = end1; + end_match_2 = string2 + stop - size1; + } + + /* `p' scans through the pattern as `d' scans through the data. + `dend' is the end of the input string that `d' points within. `d' + is advanced into the following input string whenever necessary, but + this happens before fetching; therefore, at the beginning of the + loop, `d' can be pointing at the end of a string, but it cannot + equal `string2'. */ + if (size1 > 0 && pos <= size1) + { + d = string1 + pos; + dend = end_match_1; + } + else + { + d = string2 + pos - size1; + dend = end_match_2; + } + + DEBUG_PRINT1 ("The compiled pattern is: "); + DEBUG_PRINT_COMPILED_PATTERN (bufp, p, pend); + DEBUG_PRINT1 ("The string to match is: `"); + DEBUG_PRINT_DOUBLE_STRING (d, string1, size1, string2, size2); + DEBUG_PRINT1 ("'\n"); + + /* This loops over pattern commands. It exits by returning from the + function if the match is complete, or it drops through if the match + fails at this starting point in the input data. */ + for (;;) + { + DEBUG_PRINT2 ("\n0x%x: ", p); + + if (p == pend) + { /* End of pattern means we might have succeeded. */ + DEBUG_PRINT1 ("end of pattern ... "); + + /* If we haven't matched the entire string, and we want the + longest match, try backtracking. */ + if (d != end_match_2) + { + DEBUG_PRINT1 ("backtracking.\n"); + + if (!FAIL_STACK_EMPTY ()) + { /* More failure points to try. */ + boolean same_str_p = (FIRST_STRING_P (match_end) + == MATCHING_IN_FIRST_STRING); + + /* If exceeds best match so far, save it. */ + if (!best_regs_set + || (same_str_p && d > match_end) + || (!same_str_p && !MATCHING_IN_FIRST_STRING)) + { + best_regs_set = true; + match_end = d; + + DEBUG_PRINT1 ("\nSAVING match as best so far.\n"); + + for (mcnt = 1; mcnt < num_regs; mcnt++) + { + best_regstart[mcnt] = regstart[mcnt]; + best_regend[mcnt] = regend[mcnt]; + } + } + goto fail; + } + + /* If no failure points, don't restore garbage. */ + else if (best_regs_set) + { + restore_best_regs: + /* Restore best match. It may happen that `dend == + end_match_1' while the restored d is in string2. + For example, the pattern `x.*y.*z' against the + strings `x-' and `y-z-', if the two strings are + not consecutive in memory. */ + DEBUG_PRINT1 ("Restoring best registers.\n"); + + d = match_end; + dend = ((d >= string1 && d <= end1) + ? end_match_1 : end_match_2); + + for (mcnt = 1; mcnt < num_regs; mcnt++) + { + regstart[mcnt] = best_regstart[mcnt]; + regend[mcnt] = best_regend[mcnt]; + } + } + } /* d != end_match_2 */ + + DEBUG_PRINT1 ("Accepting match.\n"); + + /* If caller wants register contents data back, do it. */ + if (regs && !bufp->no_sub) + { + /* Have the register data arrays been allocated? */ + if (bufp->regs_allocated == REGS_UNALLOCATED) + { /* No. So allocate them with malloc. We need one + extra element beyond `num_regs' for the `-1' marker + GNU code uses. */ + regs->num_regs = MAX (RE_NREGS, num_regs + 1); + regs->start = TALLOC (regs->num_regs, regoff_t); + regs->end = TALLOC (regs->num_regs, regoff_t); + if (regs->start == NULL || regs->end == NULL) + return -2; + bufp->regs_allocated = REGS_REALLOCATE; + } + else if (bufp->regs_allocated == REGS_REALLOCATE) + { /* Yes. If we need more elements than were already + allocated, reallocate them. If we need fewer, just + leave it alone. */ + if (regs->num_regs < num_regs + 1) + { + regs->num_regs = num_regs + 1; + RETALLOC (regs->start, regs->num_regs, regoff_t); + RETALLOC (regs->end, regs->num_regs, regoff_t); + if (regs->start == NULL || regs->end == NULL) + return -2; + } + } + else + assert (bufp->regs_allocated == REGS_FIXED); + + /* Convert the pointer data in `regstart' and `regend' to + indices. Register zero has to be set differently, + since we haven't kept track of any info for it. */ + if (regs->num_regs > 0) + { + regs->start[0] = pos; + regs->end[0] = (MATCHING_IN_FIRST_STRING ? d - string1 + : d - string2 + size1); + } + + /* Go through the first `min (num_regs, regs->num_regs)' + registers, since that is all we initialized. */ + for (mcnt = 1; mcnt < MIN (num_regs, regs->num_regs); mcnt++) + { + if (REG_UNSET (regstart[mcnt]) || REG_UNSET (regend[mcnt])) + regs->start[mcnt] = regs->end[mcnt] = -1; + else + { + regs->start[mcnt] = POINTER_TO_OFFSET (regstart[mcnt]); + regs->end[mcnt] = POINTER_TO_OFFSET (regend[mcnt]); + } + } + + /* If the regs structure we return has more elements than + were in the pattern, set the extra elements to -1. If + we (re)allocated the registers, this is the case, + because we always allocate enough to have at least one + -1 at the end. */ + for (mcnt = num_regs; mcnt < regs->num_regs; mcnt++) + regs->start[mcnt] = regs->end[mcnt] = -1; + } /* regs && !bufp->no_sub */ + + FREE_VARIABLES (); + DEBUG_PRINT4 ("%u failure points pushed, %u popped (%u remain).\n", + nfailure_points_pushed, nfailure_points_popped, + nfailure_points_pushed - nfailure_points_popped); + DEBUG_PRINT2 ("%u registers pushed.\n", num_regs_pushed); + + mcnt = d - pos - (MATCHING_IN_FIRST_STRING + ? string1 + : string2 - size1); + + DEBUG_PRINT2 ("Returning %d from re_match_2.\n", mcnt); + + return mcnt; + } + + /* Otherwise match next pattern command. */ +#ifdef SWITCH_ENUM_BUG + switch ((int) ((re_opcode_t) *p++)) +#else + switch ((re_opcode_t) *p++) +#endif + { + /* Ignore these. Used to ignore the n of succeed_n's which + currently have n == 0. */ + case no_op: + DEBUG_PRINT1 ("EXECUTING no_op.\n"); + break; + + + /* Match the next n pattern characters exactly. The following + byte in the pattern defines n, and the n bytes after that + are the characters to match. */ + case exactn: + mcnt = *p++; + DEBUG_PRINT2 ("EXECUTING exactn %d.\n", mcnt); + + /* This is written out as an if-else so we don't waste time + testing `translate' inside the loop. */ + if (translate) + { + do + { + PREFETCH (); + if (translate[(unsigned char) *d++] != (char) *p++) + goto fail; + } + while (--mcnt); + } + else + { + do + { + PREFETCH (); + if (*d++ != (char) *p++) goto fail; + } + while (--mcnt); + } + SET_REGS_MATCHED (); + break; + + + /* Match any character except possibly a newline or a null. */ + case anychar: + DEBUG_PRINT1 ("EXECUTING anychar.\n"); + + PREFETCH (); + + if ((!(bufp->syntax & RE_DOT_NEWLINE) && TRANSLATE (*d) == '\n') + || (bufp->syntax & RE_DOT_NOT_NULL && TRANSLATE (*d) == '\000')) + goto fail; + + SET_REGS_MATCHED (); + DEBUG_PRINT2 (" Matched `%d'.\n", *d); + d++; + break; + + + case charset: + case charset_not: + { + register unsigned char c; + boolean not = (re_opcode_t) *(p - 1) == charset_not; + + DEBUG_PRINT2 ("EXECUTING charset%s.\n", not ? "_not" : ""); + + PREFETCH (); + c = TRANSLATE (*d); /* The character to match. */ + + /* Cast to `unsigned' instead of `unsigned char' in case the + bit list is a full 32 bytes long. */ + if (c < (unsigned) (*p * BYTEWIDTH) + && p[1 + c / BYTEWIDTH] & (1 << (c % BYTEWIDTH))) + not = !not; + + p += 1 + *p; + + if (!not) goto fail; + + SET_REGS_MATCHED (); + d++; + break; + } + + + /* The beginning of a group is represented by start_memory. + The arguments are the register number in the next byte, and the + number of groups inner to this one in the next. The text + matched within the group is recorded (in the internal + registers data structure) under the register number. */ + case start_memory: + DEBUG_PRINT3 ("EXECUTING start_memory %d (%d):\n", *p, p[1]); + + /* Find out if this group can match the empty string. */ + p1 = p; /* To send to group_match_null_string_p. */ + + if (REG_MATCH_NULL_STRING_P (reg_info[*p]) == MATCH_NULL_UNSET_VALUE) + REG_MATCH_NULL_STRING_P (reg_info[*p]) + = group_match_null_string_p (&p1, pend, reg_info); + + /* Save the position in the string where we were the last time + we were at this open-group operator in case the group is + operated upon by a repetition operator, e.g., with `(a*)*b' + against `ab'; then we want to ignore where we are now in + the string in case this attempt to match fails. */ + old_regstart[*p] = REG_MATCH_NULL_STRING_P (reg_info[*p]) + ? REG_UNSET (regstart[*p]) ? d : regstart[*p] + : regstart[*p]; + DEBUG_PRINT2 (" old_regstart: %d\n", + POINTER_TO_OFFSET (old_regstart[*p])); + + regstart[*p] = d; + DEBUG_PRINT2 (" regstart: %d\n", POINTER_TO_OFFSET (regstart[*p])); + + IS_ACTIVE (reg_info[*p]) = 1; + MATCHED_SOMETHING (reg_info[*p]) = 0; + + /* This is the new highest active register. */ + highest_active_reg = *p; + + /* If nothing was active before, this is the new lowest active + register. */ + if (lowest_active_reg == NO_LOWEST_ACTIVE_REG) + lowest_active_reg = *p; + + /* Move past the register number and inner group count. */ + p += 2; + break; + + + /* The stop_memory opcode represents the end of a group. Its + arguments are the same as start_memory's: the register + number, and the number of inner groups. */ + case stop_memory: + DEBUG_PRINT3 ("EXECUTING stop_memory %d (%d):\n", *p, p[1]); + + /* We need to save the string position the last time we were at + this close-group operator in case the group is operated + upon by a repetition operator, e.g., with `((a*)*(b*)*)*' + against `aba'; then we want to ignore where we are now in + the string in case this attempt to match fails. */ + old_regend[*p] = REG_MATCH_NULL_STRING_P (reg_info[*p]) + ? REG_UNSET (regend[*p]) ? d : regend[*p] + : regend[*p]; + DEBUG_PRINT2 (" old_regend: %d\n", + POINTER_TO_OFFSET (old_regend[*p])); + + regend[*p] = d; + DEBUG_PRINT2 (" regend: %d\n", POINTER_TO_OFFSET (regend[*p])); + + /* This register isn't active anymore. */ + IS_ACTIVE (reg_info[*p]) = 0; + + /* If this was the only register active, nothing is active + anymore. */ + if (lowest_active_reg == highest_active_reg) + { + lowest_active_reg = NO_LOWEST_ACTIVE_REG; + highest_active_reg = NO_HIGHEST_ACTIVE_REG; + } + else + { /* We must scan for the new highest active register, since + it isn't necessarily one less than now: consider + (a(b)c(d(e)f)g). When group 3 ends, after the f), the + new highest active register is 1. */ + unsigned char r = *p - 1; + while (r > 0 && !IS_ACTIVE (reg_info[r])) + r--; + + /* If we end up at register zero, that means that we saved + the registers as the result of an `on_failure_jump', not + a `start_memory', and we jumped to past the innermost + `stop_memory'. For example, in ((.)*) we save + registers 1 and 2 as a result of the *, but when we pop + back to the second ), we are at the stop_memory 1. + Thus, nothing is active. */ + if (r == 0) + { + lowest_active_reg = NO_LOWEST_ACTIVE_REG; + highest_active_reg = NO_HIGHEST_ACTIVE_REG; + } + else + highest_active_reg = r; + } + + /* If just failed to match something this time around with a + group that's operated on by a repetition operator, try to + force exit from the ``loop'', and restore the register + information for this group that we had before trying this + last match. */ + if ((!MATCHED_SOMETHING (reg_info[*p]) + || (re_opcode_t) p[-3] == start_memory) + && (p + 2) < pend) + { + boolean is_a_jump_n = false; + + p1 = p + 2; + mcnt = 0; + switch ((re_opcode_t) *p1++) + { + case jump_n: + is_a_jump_n = true; + case pop_failure_jump: + case maybe_pop_jump: + case jump: + case dummy_failure_jump: + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + if (is_a_jump_n) + p1 += 2; + break; + + default: + /* do nothing */ ; + } + p1 += mcnt; + + /* If the next operation is a jump backwards in the pattern + to an on_failure_jump right before the start_memory + corresponding to this stop_memory, exit from the loop + by forcing a failure after pushing on the stack the + on_failure_jump's jump in the pattern, and d. */ + if (mcnt < 0 && (re_opcode_t) *p1 == on_failure_jump + && (re_opcode_t) p1[3] == start_memory && p1[4] == *p) + { + /* If this group ever matched anything, then restore + what its registers were before trying this last + failed match, e.g., with `(a*)*b' against `ab' for + regstart[1], and, e.g., with `((a*)*(b*)*)*' + against `aba' for regend[3]. + + Also restore the registers for inner groups for, + e.g., `((a*)(b*))*' against `aba' (register 3 would + otherwise get trashed). */ + + if (EVER_MATCHED_SOMETHING (reg_info[*p])) + { + unsigned r; + + EVER_MATCHED_SOMETHING (reg_info[*p]) = 0; + + /* Restore this and inner groups' (if any) registers. */ + for (r = *p; r < *p + *(p + 1); r++) + { + regstart[r] = old_regstart[r]; + + /* xx why this test? */ + if ((int) old_regend[r] >= (int) regstart[r]) + regend[r] = old_regend[r]; + } + } + p1++; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + PUSH_FAILURE_POINT (p1 + mcnt, d, -2); + + goto fail; + } + } + + /* Move past the register number and the inner group count. */ + p += 2; + break; + + + /* \ has been turned into a `duplicate' command which is + followed by the numeric value of as the register number. */ + case duplicate: + { + register const char *d2, *dend2; + int regno = *p++; /* Get which register to match against. */ + DEBUG_PRINT2 ("EXECUTING duplicate %d.\n", regno); + + /* Can't back reference a group which we've never matched. */ + if (REG_UNSET (regstart[regno]) || REG_UNSET (regend[regno])) + goto fail; + + /* Where in input to try to start matching. */ + d2 = regstart[regno]; + + /* Where to stop matching; if both the place to start and + the place to stop matching are in the same string, then + set to the place to stop, otherwise, for now have to use + the end of the first string. */ + + dend2 = ((FIRST_STRING_P (regstart[regno]) + == FIRST_STRING_P (regend[regno])) + ? regend[regno] : end_match_1); + for (;;) + { + /* If necessary, advance to next segment in register + contents. */ + while (d2 == dend2) + { + if (dend2 == end_match_2) break; + if (dend2 == regend[regno]) break; + + /* End of string1 => advance to string2. */ + d2 = string2; + dend2 = regend[regno]; + } + /* At end of register contents => success */ + if (d2 == dend2) break; + + /* If necessary, advance to next segment in data. */ + PREFETCH (); + + /* How many characters left in this segment to match. */ + mcnt = dend - d; + + /* Want how many consecutive characters we can match in + one shot, so, if necessary, adjust the count. */ + if (mcnt > dend2 - d2) + mcnt = dend2 - d2; + + /* Compare that many; failure if mismatch, else move + past them. */ + if (translate + ? bcmp_translate (d, d2, mcnt, translate) + : bcmp (d, d2, mcnt)) + goto fail; + d += mcnt, d2 += mcnt; + } + } + break; + + + /* begline matches the empty string at the beginning of the string + (unless `not_bol' is set in `bufp'), and, if + `newline_anchor' is set, after newlines. */ + case begline: + DEBUG_PRINT1 ("EXECUTING begline.\n"); + + if (AT_STRINGS_BEG (d)) + { + if (!bufp->not_bol) break; + } + else if (d[-1] == '\n' && bufp->newline_anchor) + { + break; + } + /* In all other cases, we fail. */ + goto fail; + + + /* endline is the dual of begline. */ + case endline: + DEBUG_PRINT1 ("EXECUTING endline.\n"); + + if (AT_STRINGS_END (d)) + { + if (!bufp->not_eol) break; + } + + /* We have to ``prefetch'' the next character. */ + else if ((d == end1 ? *string2 : *d) == '\n' + && bufp->newline_anchor) + { + break; + } + goto fail; + + + /* Match at the very beginning of the data. */ + case begbuf: + DEBUG_PRINT1 ("EXECUTING begbuf.\n"); + if (AT_STRINGS_BEG (d)) + break; + goto fail; + + + /* Match at the very end of the data. */ + case endbuf: + DEBUG_PRINT1 ("EXECUTING endbuf.\n"); + if (AT_STRINGS_END (d)) + break; + goto fail; + + + /* on_failure_keep_string_jump is used to optimize `.*\n'. It + pushes NULL as the value for the string on the stack. Then + `pop_failure_point' will keep the current value for the + string, instead of restoring it. To see why, consider + matching `foo\nbar' against `.*\n'. The .* matches the foo; + then the . fails against the \n. But the next thing we want + to do is match the \n against the \n; if we restored the + string value, we would be back at the foo. + + Because this is used only in specific cases, we don't need to + check all the things that `on_failure_jump' does, to make + sure the right things get saved on the stack. Hence we don't + share its code. The only reason to push anything on the + stack at all is that otherwise we would have to change + `anychar's code to do something besides goto fail in this + case; that seems worse than this. */ + case on_failure_keep_string_jump: + DEBUG_PRINT1 ("EXECUTING on_failure_keep_string_jump"); + + EXTRACT_NUMBER_AND_INCR (mcnt, p); + DEBUG_PRINT3 (" %d (to 0x%x):\n", mcnt, p + mcnt); + + PUSH_FAILURE_POINT (p + mcnt, NULL, -2); + break; + + + /* Uses of on_failure_jump: + + Each alternative starts with an on_failure_jump that points + to the beginning of the next alternative. Each alternative + except the last ends with a jump that in effect jumps past + the rest of the alternatives. (They really jump to the + ending jump of the following alternative, because tensioning + these jumps is a hassle.) + + Repeats start with an on_failure_jump that points past both + the repetition text and either the following jump or + pop_failure_jump back to this on_failure_jump. */ + case on_failure_jump: + on_failure: + DEBUG_PRINT1 ("EXECUTING on_failure_jump"); + + EXTRACT_NUMBER_AND_INCR (mcnt, p); + DEBUG_PRINT3 (" %d (to 0x%x)", mcnt, p + mcnt); + + /* If this on_failure_jump comes right before a group (i.e., + the original * applied to a group), save the information + for that group and all inner ones, so that if we fail back + to this point, the group's information will be correct. + For example, in \(a*\)*\1, we need the preceding group, + and in \(\(a*\)b*\)\2, we need the inner group. */ + + /* We can't use `p' to check ahead because we push + a failure point to `p + mcnt' after we do this. */ + p1 = p; + + /* We need to skip no_op's before we look for the + start_memory in case this on_failure_jump is happening as + the result of a completed succeed_n, as in \(a\)\{1,3\}b\1 + against aba. */ + while (p1 < pend && (re_opcode_t) *p1 == no_op) + p1++; + + if (p1 < pend && (re_opcode_t) *p1 == start_memory) + { + /* We have a new highest active register now. This will + get reset at the start_memory we are about to get to, + but we will have saved all the registers relevant to + this repetition op, as described above. */ + highest_active_reg = *(p1 + 1) + *(p1 + 2); + if (lowest_active_reg == NO_LOWEST_ACTIVE_REG) + lowest_active_reg = *(p1 + 1); + } + + DEBUG_PRINT1 (":\n"); + PUSH_FAILURE_POINT (p + mcnt, d, -2); + break; + + + /* A smart repeat ends with `maybe_pop_jump'. + We change it to either `pop_failure_jump' or `jump'. */ + case maybe_pop_jump: + EXTRACT_NUMBER_AND_INCR (mcnt, p); + DEBUG_PRINT2 ("EXECUTING maybe_pop_jump %d.\n", mcnt); + { + register unsigned char *p2 = p; + + /* Compare the beginning of the repeat with what in the + pattern follows its end. If we can establish that there + is nothing that they would both match, i.e., that we + would have to backtrack because of (as in, e.g., `a*a') + then we can change to pop_failure_jump, because we'll + never have to backtrack. + + This is not true in the case of alternatives: in + `(a|ab)*' we do need to backtrack to the `ab' alternative + (e.g., if the string was `ab'). But instead of trying to + detect that here, the alternative has put on a dummy + failure point which is what we will end up popping. */ + + /* Skip over open/close-group commands. */ + while (p2 + 2 < pend + && ((re_opcode_t) *p2 == stop_memory + || (re_opcode_t) *p2 == start_memory)) + p2 += 3; /* Skip over args, too. */ + + /* If we're at the end of the pattern, we can change. */ + if (p2 == pend) + { + /* Consider what happens when matching ":\(.*\)" + against ":/". I don't really understand this code + yet. */ + p[-3] = (unsigned char) pop_failure_jump; + DEBUG_PRINT1 + (" End of pattern: change to `pop_failure_jump'.\n"); + } + + else if ((re_opcode_t) *p2 == exactn + || (bufp->newline_anchor && (re_opcode_t) *p2 == endline)) + { + register unsigned char c + = *p2 == (unsigned char) endline ? '\n' : p2[2]; + p1 = p + mcnt; + + /* p1[0] ... p1[2] are the `on_failure_jump' corresponding + to the `maybe_finalize_jump' of this case. Examine what + follows. */ + if ((re_opcode_t) p1[3] == exactn && p1[5] != c) + { + p[-3] = (unsigned char) pop_failure_jump; + DEBUG_PRINT3 (" %c != %c => pop_failure_jump.\n", + c, p1[5]); + } + + else if ((re_opcode_t) p1[3] == charset + || (re_opcode_t) p1[3] == charset_not) + { + int not = (re_opcode_t) p1[3] == charset_not; + + if (c < (unsigned char) (p1[4] * BYTEWIDTH) + && p1[5 + c / BYTEWIDTH] & (1 << (c % BYTEWIDTH))) + not = !not; + + /* `not' is equal to 1 if c would match, which means + that we can't change to pop_failure_jump. */ + if (!not) + { + p[-3] = (unsigned char) pop_failure_jump; + DEBUG_PRINT1 (" No match => pop_failure_jump.\n"); + } + } + } + } + p -= 2; /* Point at relative address again. */ + if ((re_opcode_t) p[-1] != pop_failure_jump) + { + p[-1] = (unsigned char) jump; + DEBUG_PRINT1 (" Match => jump.\n"); + goto unconditional_jump; + } + /* Note fall through. */ + + + /* The end of a simple repeat has a pop_failure_jump back to + its matching on_failure_jump, where the latter will push a + failure point. The pop_failure_jump takes off failure + points put on by this pop_failure_jump's matching + on_failure_jump; we got through the pattern to here from the + matching on_failure_jump, so didn't fail. */ + case pop_failure_jump: + { + /* We need to pass separate storage for the lowest and + highest registers, even though we don't care about the + actual values. Otherwise, we will restore only one + register from the stack, since lowest will == highest in + `pop_failure_point'. */ + unsigned dummy_low_reg, dummy_high_reg; + unsigned char *pdummy; + const char *sdummy; + + DEBUG_PRINT1 ("EXECUTING pop_failure_jump.\n"); + POP_FAILURE_POINT (sdummy, pdummy, + dummy_low_reg, dummy_high_reg, + reg_dummy, reg_dummy, reg_info_dummy); + } + /* Note fall through. */ + + + /* Unconditionally jump (without popping any failure points). */ + case jump: + unconditional_jump: + EXTRACT_NUMBER_AND_INCR (mcnt, p); /* Get the amount to jump. */ + DEBUG_PRINT2 ("EXECUTING jump %d ", mcnt); + p += mcnt; /* Do the jump. */ + DEBUG_PRINT2 ("(to 0x%x).\n", p); + break; + + + /* We need this opcode so we can detect where alternatives end + in `group_match_null_string_p' et al. */ + case jump_past_alt: + DEBUG_PRINT1 ("EXECUTING jump_past_alt.\n"); + goto unconditional_jump; + + + /* Normally, the on_failure_jump pushes a failure point, which + then gets popped at pop_failure_jump. We will end up at + pop_failure_jump, also, and with a pattern of, say, `a+', we + are skipping over the on_failure_jump, so we have to push + something meaningless for pop_failure_jump to pop. */ + case dummy_failure_jump: + DEBUG_PRINT1 ("EXECUTING dummy_failure_jump.\n"); + /* It doesn't matter what we push for the string here. What + the code at `fail' tests is the value for the pattern. */ + PUSH_FAILURE_POINT (0, 0, -2); + goto unconditional_jump; + + + /* At the end of an alternative, we need to push a dummy failure + point in case we are followed by a `pop_failure_jump', because + we don't want the failure point for the alternative to be + popped. For example, matching `(a|ab)*' against `aab' + requires that we match the `ab' alternative. */ + case push_dummy_failure: + DEBUG_PRINT1 ("EXECUTING push_dummy_failure.\n"); + /* See comments just above at `dummy_failure_jump' about the + two zeroes. */ + PUSH_FAILURE_POINT (0, 0, -2); + break; + + /* Have to succeed matching what follows at least n times. + After that, handle like `on_failure_jump'. */ + case succeed_n: + EXTRACT_NUMBER (mcnt, p + 2); + DEBUG_PRINT2 ("EXECUTING succeed_n %d.\n", mcnt); + + assert (mcnt >= 0); + /* Originally, this is how many times we HAVE to succeed. */ + if (mcnt > 0) + { + mcnt--; + p += 2; + STORE_NUMBER_AND_INCR (p, mcnt); + DEBUG_PRINT3 (" Setting 0x%x to %d.\n", p, mcnt); + } + else if (mcnt == 0) + { + DEBUG_PRINT2 (" Setting two bytes from 0x%x to no_op.\n", p+2); + p[2] = (unsigned char) no_op; + p[3] = (unsigned char) no_op; + goto on_failure; + } + break; + + case jump_n: + EXTRACT_NUMBER (mcnt, p + 2); + DEBUG_PRINT2 ("EXECUTING jump_n %d.\n", mcnt); + + /* Originally, this is how many times we CAN jump. */ + if (mcnt) + { + mcnt--; + STORE_NUMBER (p + 2, mcnt); + goto unconditional_jump; + } + /* If don't have to jump any more, skip over the rest of command. */ + else + p += 4; + break; + + case set_number_at: + { + DEBUG_PRINT1 ("EXECUTING set_number_at.\n"); + + EXTRACT_NUMBER_AND_INCR (mcnt, p); + p1 = p + mcnt; + EXTRACT_NUMBER_AND_INCR (mcnt, p); + DEBUG_PRINT3 (" Setting 0x%x to %d.\n", p1, mcnt); + STORE_NUMBER (p1, mcnt); + break; + } + + case wordbound: + DEBUG_PRINT1 ("EXECUTING wordbound.\n"); + if (AT_WORD_BOUNDARY (d)) + break; + goto fail; + + case notwordbound: + DEBUG_PRINT1 ("EXECUTING notwordbound.\n"); + if (AT_WORD_BOUNDARY (d)) + goto fail; + break; + + case wordbeg: + DEBUG_PRINT1 ("EXECUTING wordbeg.\n"); + if (WORDCHAR_P (d) && (AT_STRINGS_BEG (d) || !WORDCHAR_P (d - 1))) + break; + goto fail; + + case wordend: + DEBUG_PRINT1 ("EXECUTING wordend.\n"); + if (!AT_STRINGS_BEG (d) && WORDCHAR_P (d - 1) + && (!WORDCHAR_P (d) || AT_STRINGS_END (d))) + break; + goto fail; + +#ifdef emacs +#ifdef emacs19 + case before_dot: + DEBUG_PRINT1 ("EXECUTING before_dot.\n"); + if (PTR_CHAR_POS ((unsigned char *) d) >= point) + goto fail; + break; + + case at_dot: + DEBUG_PRINT1 ("EXECUTING at_dot.\n"); + if (PTR_CHAR_POS ((unsigned char *) d) != point) + goto fail; + break; + + case after_dot: + DEBUG_PRINT1 ("EXECUTING after_dot.\n"); + if (PTR_CHAR_POS ((unsigned char *) d) <= point) + goto fail; + break; +#else /* not emacs19 */ + case at_dot: + DEBUG_PRINT1 ("EXECUTING at_dot.\n"); + if (PTR_CHAR_POS ((unsigned char *) d) + 1 != point) + goto fail; + break; +#endif /* not emacs19 */ + + case syntaxspec: + DEBUG_PRINT2 ("EXECUTING syntaxspec %d.\n", mcnt); + mcnt = *p++; + goto matchsyntax; + + case wordchar: + DEBUG_PRINT1 ("EXECUTING Emacs wordchar.\n"); + mcnt = (int) Sword; + matchsyntax: + PREFETCH (); + if (SYNTAX (*d++) != (enum syntaxcode) mcnt) + goto fail; + SET_REGS_MATCHED (); + break; + + case notsyntaxspec: + DEBUG_PRINT2 ("EXECUTING notsyntaxspec %d.\n", mcnt); + mcnt = *p++; + goto matchnotsyntax; + + case notwordchar: + DEBUG_PRINT1 ("EXECUTING Emacs notwordchar.\n"); + mcnt = (int) Sword; + matchnotsyntax: + PREFETCH (); + if (SYNTAX (*d++) == (enum syntaxcode) mcnt) + goto fail; + SET_REGS_MATCHED (); + break; + +#else /* not emacs */ + case wordchar: + DEBUG_PRINT1 ("EXECUTING non-Emacs wordchar.\n"); + PREFETCH (); + if (!WORDCHAR_P (d)) + goto fail; + SET_REGS_MATCHED (); + d++; + break; + + case notwordchar: + DEBUG_PRINT1 ("EXECUTING non-Emacs notwordchar.\n"); + PREFETCH (); + if (WORDCHAR_P (d)) + goto fail; + SET_REGS_MATCHED (); + d++; + break; +#endif /* not emacs */ + + default: + abort (); + } + continue; /* Successfully executed one pattern command; keep going. */ + + + /* We goto here if a matching operation fails. */ + fail: + if (!FAIL_STACK_EMPTY ()) + { /* A restart point is known. Restore to that state. */ + DEBUG_PRINT1 ("\nFAIL:\n"); + POP_FAILURE_POINT (d, p, + lowest_active_reg, highest_active_reg, + regstart, regend, reg_info); + + /* If this failure point is a dummy, try the next one. */ + if (!p) + goto fail; + + /* If we failed to the end of the pattern, don't examine *p. */ + assert (p <= pend); + if (p < pend) + { + boolean is_a_jump_n = false; + + /* If failed to a backwards jump that's part of a repetition + loop, need to pop this failure point and use the next one. */ + switch ((re_opcode_t) *p) + { + case jump_n: + is_a_jump_n = true; + case maybe_pop_jump: + case pop_failure_jump: + case jump: + p1 = p + 1; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + p1 += mcnt; + + if ((is_a_jump_n && (re_opcode_t) *p1 == succeed_n) + || (!is_a_jump_n + && (re_opcode_t) *p1 == on_failure_jump)) + goto fail; + break; + default: + /* do nothing */ ; + } + } + + if (d >= string1 && d <= end1) + dend = end_match_1; + } + else + break; /* Matching at this starting point really fails. */ + } /* for (;;) */ + + if (best_regs_set) + goto restore_best_regs; + + FREE_VARIABLES (); + + return -1; /* Failure to match. */ +} /* re_match_2 */ + +/* Subroutine definitions for re_match_2. */ + + +/* We are passed P pointing to a register number after a start_memory. + + Return true if the pattern up to the corresponding stop_memory can + match the empty string, and false otherwise. + + If we find the matching stop_memory, sets P to point to one past its number. + Otherwise, sets P to an undefined byte less than or equal to END. + + We don't handle duplicates properly (yet). */ + +static boolean +group_match_null_string_p (p, end, reg_info) + unsigned char **p, *end; + register_info_type *reg_info; +{ + int mcnt; + /* Point to after the args to the start_memory. */ + unsigned char *p1 = *p + 2; + + while (p1 < end) + { + /* Skip over opcodes that can match nothing, and return true or + false, as appropriate, when we get to one that can't, or to the + matching stop_memory. */ + + switch ((re_opcode_t) *p1) + { + /* Could be either a loop or a series of alternatives. */ + case on_failure_jump: + p1++; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + + /* If the next operation is not a jump backwards in the + pattern. */ + + if (mcnt >= 0) + { + /* Go through the on_failure_jumps of the alternatives, + seeing if any of the alternatives cannot match nothing. + The last alternative starts with only a jump, + whereas the rest start with on_failure_jump and end + with a jump, e.g., here is the pattern for `a|b|c': + + /on_failure_jump/0/6/exactn/1/a/jump_past_alt/0/6 + /on_failure_jump/0/6/exactn/1/b/jump_past_alt/0/3 + /exactn/1/c + + So, we have to first go through the first (n-1) + alternatives and then deal with the last one separately. */ + + + /* Deal with the first (n-1) alternatives, which start + with an on_failure_jump (see above) that jumps to right + past a jump_past_alt. */ + + while ((re_opcode_t) p1[mcnt-3] == jump_past_alt) + { + /* `mcnt' holds how many bytes long the alternative + is, including the ending `jump_past_alt' and + its number. */ + + if (!alt_match_null_string_p (p1, p1 + mcnt - 3, + reg_info)) + return false; + + /* Move to right after this alternative, including the + jump_past_alt. */ + p1 += mcnt; + + /* Break if it's the beginning of an n-th alternative + that doesn't begin with an on_failure_jump. */ + if ((re_opcode_t) *p1 != on_failure_jump) + break; + + /* Still have to check that it's not an n-th + alternative that starts with an on_failure_jump. */ + p1++; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + if ((re_opcode_t) p1[mcnt-3] != jump_past_alt) + { + /* Get to the beginning of the n-th alternative. */ + p1 -= 3; + break; + } + } + + /* Deal with the last alternative: go back and get number + of the `jump_past_alt' just before it. `mcnt' contains + the length of the alternative. */ + EXTRACT_NUMBER (mcnt, p1 - 2); + + if (!alt_match_null_string_p (p1, p1 + mcnt, reg_info)) + return false; + + p1 += mcnt; /* Get past the n-th alternative. */ + } /* if mcnt > 0 */ + break; + + + case stop_memory: + assert (p1[1] == **p); + *p = p1 + 2; + return true; + + + default: + if (!common_op_match_null_string_p (&p1, end, reg_info)) + return false; + } + } /* while p1 < end */ + + return false; +} /* group_match_null_string_p */ + + +/* Similar to group_match_null_string_p, but doesn't deal with alternatives: + It expects P to be the first byte of a single alternative and END one + byte past the last. The alternative can contain groups. */ + +static boolean +alt_match_null_string_p (p, end, reg_info) + unsigned char *p, *end; + register_info_type *reg_info; +{ + int mcnt; + unsigned char *p1 = p; + + while (p1 < end) + { + /* Skip over opcodes that can match nothing, and break when we get + to one that can't. */ + + switch ((re_opcode_t) *p1) + { + /* It's a loop. */ + case on_failure_jump: + p1++; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + p1 += mcnt; + break; + + default: + if (!common_op_match_null_string_p (&p1, end, reg_info)) + return false; + } + } /* while p1 < end */ + + return true; +} /* alt_match_null_string_p */ + + +/* Deals with the ops common to group_match_null_string_p and + alt_match_null_string_p. + + Sets P to one after the op and its arguments, if any. */ + +static boolean +common_op_match_null_string_p (p, end, reg_info) + unsigned char **p, *end; + register_info_type *reg_info; +{ + int mcnt; + boolean ret; + int reg_no; + unsigned char *p1 = *p; + + switch ((re_opcode_t) *p1++) + { + case no_op: + case begline: + case endline: + case begbuf: + case endbuf: + case wordbeg: + case wordend: + case wordbound: + case notwordbound: +#ifdef emacs + case before_dot: + case at_dot: + case after_dot: +#endif + break; + + case start_memory: + reg_no = *p1; + assert (reg_no > 0 && reg_no <= MAX_REGNUM); + ret = group_match_null_string_p (&p1, end, reg_info); + + /* Have to set this here in case we're checking a group which + contains a group and a back reference to it. */ + + if (REG_MATCH_NULL_STRING_P (reg_info[reg_no]) == MATCH_NULL_UNSET_VALUE) + REG_MATCH_NULL_STRING_P (reg_info[reg_no]) = ret; + + if (!ret) + return false; + break; + + /* If this is an optimized succeed_n for zero times, make the jump. */ + case jump: + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + if (mcnt >= 0) + p1 += mcnt; + else + return false; + break; + + case succeed_n: + /* Get to the number of times to succeed. */ + p1 += 2; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + + if (mcnt == 0) + { + p1 -= 4; + EXTRACT_NUMBER_AND_INCR (mcnt, p1); + p1 += mcnt; + } + else + return false; + break; + + case duplicate: + if (!REG_MATCH_NULL_STRING_P (reg_info[*p1])) + return false; + break; + + case set_number_at: + p1 += 4; + + default: + /* All other opcodes mean we cannot match the empty string. */ + return false; + } + + *p = p1; + return true; +} /* common_op_match_null_string_p */ + + +/* Return zero if TRANSLATE[S1] and TRANSLATE[S2] are identical for LEN + bytes; nonzero otherwise. */ + +static int +bcmp_translate( + unsigned char *s1, + unsigned char *s2, + int len, + char *translate +) +{ + register unsigned char *p1 = s1, *p2 = s2; + while (len) + { + if (translate[*p1++] != translate[*p2++]) return 1; + len--; + } + return 0; +} + +/* Entry points for GNU code. */ + +/* re_compile_pattern is the GNU regular expression compiler: it + compiles PATTERN (of length SIZE) and puts the result in BUFP. + Returns 0 if the pattern was valid, otherwise an error string. + + Assumes the `allocated' (and perhaps `buffer') and `translate' fields + are set in BUFP on entry. + + We call regex_compile to do the actual compilation. */ + +const char * +re_compile_pattern (pattern, length, bufp) + const char *pattern; + int length; + struct re_pattern_buffer *bufp; +{ + reg_errcode_t ret; + + /* GNU code is written to assume at least RE_NREGS registers will be set + (and at least one extra will be -1). */ + bufp->regs_allocated = REGS_UNALLOCATED; + + /* And GNU code determines whether or not to get register information + by passing null for the REGS argument to re_match, etc., not by + setting no_sub. */ + bufp->no_sub = 0; + + /* Match anchors at newline. */ + bufp->newline_anchor = 1; + + ret = regex_compile (pattern, length, re_syntax_options, bufp); + + return re_error_msg[(int) ret]; +} + +/* Entry points compatible with 4.2 BSD regex library. We don't define + them if this is an Emacs or POSIX compilation. */ + +#if !defined (emacs) && !defined (_POSIX_SOURCE) + +/* BSD has one and only one pattern buffer. */ +static struct re_pattern_buffer re_comp_buf; + +char * +re_comp (s) + const char *s; +{ + reg_errcode_t ret; + + if (!s) + { + if (!re_comp_buf.buffer) + return "No previous regular expression"; + return 0; + } + + if (!re_comp_buf.buffer) + { + re_comp_buf.buffer = (unsigned char *) malloc (200); + if (re_comp_buf.buffer == NULL) + return "Memory exhausted"; + re_comp_buf.allocated = 200; + + re_comp_buf.fastmap = (char *) malloc (1 << BYTEWIDTH); + if (re_comp_buf.fastmap == NULL) + return "Memory exhausted"; + } + + /* Since `re_exec' always passes NULL for the `regs' argument, we + don't need to initialize the pattern buffer fields which affect it. */ + + /* Match anchors at newlines. */ + re_comp_buf.newline_anchor = 1; + + ret = regex_compile (s, strlen (s), re_syntax_options, &re_comp_buf); + + /* Yes, we're discarding `const' here. */ + return (char *) re_error_msg[(int) ret]; +} + + +int +re_exec (s) + const char *s; +{ + const int len = strlen (s); + return + 0 <= re_search (&re_comp_buf, s, len, 0, len, (struct re_registers *) 0); +} +#endif /* not emacs and not _POSIX_SOURCE */ + +/* POSIX.2 functions. Don't define these for Emacs. */ + +#ifndef emacs + +/* regcomp takes a regular expression as a string and compiles it. + + PREG is a regex_t *. We do not expect any fields to be initialized, + since POSIX says we shouldn't. Thus, we set + + `buffer' to the compiled pattern; + `used' to the length of the compiled pattern; + `syntax' to RE_SYNTAX_POSIX_EXTENDED if the + REG_EXTENDED bit in CFLAGS is set; otherwise, to + RE_SYNTAX_POSIX_BASIC; + `newline_anchor' to REG_NEWLINE being set in CFLAGS; + `fastmap' and `fastmap_accurate' to zero; + `re_nsub' to the number of subexpressions in PATTERN. + + PATTERN is the address of the pattern string. + + CFLAGS is a series of bits which affect compilation. + + If REG_EXTENDED is set, we use POSIX extended syntax; otherwise, we + use POSIX basic syntax. + + If REG_NEWLINE is set, then . and [^...] don't match newline. + Also, regexec will try a match beginning after every newline. + + If REG_ICASE is set, then we considers upper- and lowercase + versions of letters to be equivalent when matching. + + If REG_NOSUB is set, then when PREG is passed to regexec, that + routine will report only success or failure, and nothing about the + registers. + + It returns 0 if it succeeds, nonzero if it doesn't. (See regex.h for + the return codes and their meanings.) */ + +int +regcomp (preg, pattern, cflags) + regex_t *preg; + const char *pattern; + int cflags; +{ + reg_errcode_t ret; + unsigned syntax + = (cflags & REG_EXTENDED) ? + RE_SYNTAX_POSIX_EXTENDED : RE_SYNTAX_POSIX_BASIC; + + /* regex_compile will allocate the space for the compiled pattern. */ + preg->buffer = 0; + preg->allocated = 0; + + /* Don't bother to use a fastmap when searching. This simplifies the + REG_NEWLINE case: if we used a fastmap, we'd have to put all the + characters after newlines into the fastmap. This way, we just try + every character. */ + preg->fastmap = 0; + + if (cflags & REG_ICASE) + { + unsigned i; + + preg->translate = (char *) malloc (CHAR_SET_SIZE); + if (preg->translate == NULL) + return (int) REG_ESPACE; + + /* Map uppercase characters to corresponding lowercase ones. */ + for (i = 0; i < CHAR_SET_SIZE; i++) + preg->translate[i] = ISUPPER (i) ? tolower (i) : i; + } + else + preg->translate = NULL; + + /* If REG_NEWLINE is set, newlines are treated differently. */ + if (cflags & REG_NEWLINE) + { /* REG_NEWLINE implies neither . nor [^...] match newline. */ + syntax &= ~RE_DOT_NEWLINE; + syntax |= RE_HAT_LISTS_NOT_NEWLINE; + /* It also changes the matching behavior. */ + preg->newline_anchor = 1; + } + else + preg->newline_anchor = 0; + + preg->no_sub = !!(cflags & REG_NOSUB); + + /* POSIX says a null character in the pattern terminates it, so we + can use strlen here in compiling the pattern. */ + ret = regex_compile (pattern, strlen (pattern), syntax, preg); + + /* POSIX doesn't distinguish between an unmatched open-group and an + unmatched close-group: both are REG_EPAREN. */ + if (ret == REG_ERPAREN) ret = REG_EPAREN; + + return (int) ret; +} + + +/* regexec searches for a given pattern, specified by PREG, in the + string STRING. + + If NMATCH is zero or REG_NOSUB was set in the cflags argument to + `regcomp', we ignore PMATCH. Otherwise, we assume PMATCH has at + least NMATCH elements, and we set them to the offsets of the + corresponding matched substrings. + + EFLAGS specifies `execution flags' which affect matching: if + REG_NOTBOL is set, then ^ does not match at the beginning of the + string; if REG_NOTEOL is set, then $ does not match at the end. + + We return 0 if we find a match and REG_NOMATCH if not. */ + +int +regexec (preg, string, nmatch, pmatch, eflags) + const regex_t *preg; + const char *string; + size_t nmatch; + regmatch_t pmatch[]; + int eflags; +{ + int ret; + struct re_registers regs; + regex_t private_preg; + int len = strlen (string); + boolean want_reg_info = !preg->no_sub && nmatch > 0; + + private_preg = *preg; + + private_preg.not_bol = !!(eflags & REG_NOTBOL); + private_preg.not_eol = !!(eflags & REG_NOTEOL); + + /* The user has told us exactly how many registers to return + information about, via `nmatch'. We have to pass that on to the + matching routines. */ + private_preg.regs_allocated = REGS_FIXED; + + if (want_reg_info) + { + regs.num_regs = nmatch; + regs.start = TALLOC (nmatch, regoff_t); + regs.end = TALLOC (nmatch, regoff_t); + if (regs.start == NULL || regs.end == NULL) + return (int) REG_NOMATCH; + } + + /* Perform the searching operation. */ + ret = re_search (&private_preg, string, len, + /* start: */ 0, /* range: */ len, + want_reg_info ? ®s : (struct re_registers *) 0); + + /* Copy the register information to the POSIX structure. */ + if (want_reg_info) + { + if (ret >= 0) + { + unsigned r; + + for (r = 0; r < nmatch; r++) + { + pmatch[r].rm_so = regs.start[r]; + pmatch[r].rm_eo = regs.end[r]; + } + } + + /* If we needed the temporary register info, free the space now. */ + free (regs.start); + free (regs.end); + } + + /* We want zero return to mean success, unlike `re_search'. */ + return ret >= 0 ? (int) REG_NOERROR : (int) REG_NOMATCH; +} + + +/* Returns a message corresponding to an error code, ERRCODE, returned + from either regcomp or regexec. We don't use PREG here. */ + +size_t +regerror (errcode, preg, errbuf, errbuf_size) + int errcode; + const regex_t *preg; + char *errbuf; + size_t errbuf_size; +{ + const char *msg; + size_t msg_size; + + if (errcode < 0 + || errcode >= (sizeof (re_error_msg) / sizeof (re_error_msg[0]))) + /* Only error codes returned by the rest of the code should be passed + to this routine. If we are given anything else, or if other regex + code generates an invalid error code, then the program has a bug. + Dump core so we can fix it. */ + abort (); + + msg = re_error_msg[errcode]; + + /* POSIX doesn't require that we do anything in this case, but why + not be nice. */ + if (! msg) + msg = "Success"; + + msg_size = strlen (msg) + 1; /* Includes the null. */ + + if (errbuf_size != 0) + { + if (msg_size > errbuf_size) + { + strncpy (errbuf, msg, errbuf_size - 1); + errbuf[errbuf_size - 1] = 0; + } + else + strcpy (errbuf, msg); + } + + return msg_size; +} + + +/* Free dynamically allocated space used by PREG. */ + +void +regfree (preg) + regex_t *preg; +{ + if (preg->buffer != NULL) + free (preg->buffer); + preg->buffer = NULL; + + preg->allocated = 0; + preg->used = 0; + + if (preg->fastmap != NULL) + free (preg->fastmap); + preg->fastmap = NULL; + preg->fastmap_accurate = 0; + + if (preg->translate != NULL) + free (preg->translate); + preg->translate = NULL; +} + +#endif /* not emacs */ + +/* +Local variables: +make-backup-files: t +version-control: t +trim-versions-without-asking: nil +End: +*/ diff --git a/compat/regex.h b/compat/regex.h new file mode 100644 index 0000000000..6eb64f1402 --- /dev/null +++ b/compat/regex.h @@ -0,0 +1,490 @@ +/* Definitions for data structures and routines for the regular + expression library, version 0.12. + + Copyright (C) 1985, 1989, 1990, 1991, 1992, 1993 Free Software Foundation, Inc. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2, or (at your option) + any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ + +#ifndef __REGEXP_LIBRARY_H__ +#define __REGEXP_LIBRARY_H__ + +/* POSIX says that must be included (by the caller) before + . */ + +#ifdef VMS +/* VMS doesn't have `size_t' in , even though POSIX says it + should be there. */ +#include +#endif + + +/* The following bits are used to determine the regexp syntax we + recognize. The set/not-set meanings are chosen so that Emacs syntax + remains the value 0. The bits are given in alphabetical order, and + the definitions shifted by one from the previous bit; thus, when we + add or remove a bit, only one other definition need change. */ +typedef unsigned reg_syntax_t; + +/* If this bit is not set, then \ inside a bracket expression is literal. + If set, then such a \ quotes the following character. */ +#define RE_BACKSLASH_ESCAPE_IN_LISTS (1) + +/* If this bit is not set, then + and ? are operators, and \+ and \? are + literals. + If set, then \+ and \? are operators and + and ? are literals. */ +#define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1) + +/* If this bit is set, then character classes are supported. They are: + [:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:], + [:space:], [:print:], [:punct:], [:graph:], and [:cntrl:]. + If not set, then character classes are not supported. */ +#define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1) + +/* If this bit is set, then ^ and $ are always anchors (outside bracket + expressions, of course). + If this bit is not set, then it depends: + ^ is an anchor if it is at the beginning of a regular + expression or after an open-group or an alternation operator; + $ is an anchor if it is at the end of a regular expression, or + before a close-group or an alternation operator. + + This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because + POSIX draft 11.2 says that * etc. in leading positions is undefined. + We already implemented a previous draft which made those constructs + invalid, though, so we haven't changed the code back. */ +#define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1) + +/* If this bit is set, then special characters are always special + regardless of where they are in the pattern. + If this bit is not set, then special characters are special only in + some contexts; otherwise they are ordinary. Specifically, + * + ? and intervals are only special when not after the beginning, + open-group, or alternation operator. */ +#define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1) + +/* If this bit is set, then *, +, ?, and { cannot be first in an re or + immediately after an alternation or begin-group operator. */ +#define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1) + +/* If this bit is set, then . matches newline. + If not set, then it doesn't. */ +#define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1) + +/* If this bit is set, then . doesn't match NUL. + If not set, then it does. */ +#define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1) + +/* If this bit is set, nonmatching lists [^...] do not match newline. + If not set, they do. */ +#define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1) + +/* If this bit is set, either \{...\} or {...} defines an + interval, depending on RE_NO_BK_BRACES. + If not set, \{, \}, {, and } are literals. */ +#define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1) + +/* If this bit is set, +, ? and | aren't recognized as operators. + If not set, they are. */ +#define RE_LIMITED_OPS (RE_INTERVALS << 1) + +/* If this bit is set, newline is an alternation operator. + If not set, newline is literal. */ +#define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1) + +/* If this bit is set, then `{...}' defines an interval, and \{ and \} + are literals. + If not set, then `\{...\}' defines an interval. */ +#define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1) + +/* If this bit is set, (...) defines a group, and \( and \) are literals. + If not set, \(...\) defines a group, and ( and ) are literals. */ +#define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1) + +/* If this bit is set, then \ matches . + If not set, then \ is a back-reference. */ +#define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1) + +/* If this bit is set, then | is an alternation operator, and \| is literal. + If not set, then \| is an alternation operator, and | is literal. */ +#define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1) + +/* If this bit is set, then an ending range point collating higher + than the starting range point, as in [z-a], is invalid. + If not set, then when ending range point collates higher than the + starting range point, the range is ignored. */ +#define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1) + +/* If this bit is set, then an unmatched ) is ordinary. + If not set, then an unmatched ) is invalid. */ +#define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1) + +/* This global variable defines the particular regexp syntax to use (for + some interfaces). When a regexp is compiled, the syntax used is + stored in the pattern buffer, so changing this does not affect + already-compiled regexps. */ +extern reg_syntax_t re_syntax_options; + +/* Define combinations of the above bits for the standard possibilities. + (The [[[ comments delimit what gets put into the Texinfo file, so + don't delete them!) */ +/* [[[begin syntaxes]]] */ +#define RE_SYNTAX_EMACS 0 + +#define RE_SYNTAX_AWK \ + (RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \ + | RE_NO_BK_PARENS | RE_NO_BK_REFS \ + | RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \ + | RE_UNMATCHED_RIGHT_PAREN_ORD) + +#define RE_SYNTAX_POSIX_AWK \ + (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS) + +#define RE_SYNTAX_GREP \ + (RE_BK_PLUS_QM | RE_CHAR_CLASSES \ + | RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \ + | RE_NEWLINE_ALT) + +#define RE_SYNTAX_EGREP \ + (RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \ + | RE_NEWLINE_ALT | RE_NO_BK_PARENS \ + | RE_NO_BK_VBAR) + +#define RE_SYNTAX_POSIX_EGREP \ + (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES) + +/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */ +#define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC + +#define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC + +/* Syntax bits common to both basic and extended POSIX regex syntax. */ +#define _RE_SYNTAX_POSIX_COMMON \ + (RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \ + | RE_INTERVALS | RE_NO_EMPTY_RANGES) + +#define RE_SYNTAX_POSIX_BASIC \ + (_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM) + +/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes + RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this + isn't minimal, since other operators, such as \`, aren't disabled. */ +#define RE_SYNTAX_POSIX_MINIMAL_BASIC \ + (_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS) + +#define RE_SYNTAX_POSIX_EXTENDED \ + (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \ + | RE_NO_BK_PARENS | RE_NO_BK_VBAR \ + | RE_UNMATCHED_RIGHT_PAREN_ORD) + +/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INVALID_OPS + replaces RE_CONTEXT_INDEP_OPS and RE_NO_BK_REFS is added. */ +#define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \ + (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \ + | RE_NO_BK_PARENS | RE_NO_BK_REFS \ + | RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD) +/* [[[end syntaxes]]] */ + +/* Maximum number of duplicates an interval can allow. Some systems + (erroneously) define this in other header files, but we want our + value, so remove any previous define. */ +#ifdef RE_DUP_MAX +#undef RE_DUP_MAX +#endif +#define RE_DUP_MAX ((1 << 15) - 1) + + +/* POSIX `cflags' bits (i.e., information for `regcomp'). */ + +/* If this bit is set, then use extended regular expression syntax. + If not set, then use basic regular expression syntax. */ +#define REG_EXTENDED 1 + +/* If this bit is set, then ignore case when matching. + If not set, then case is significant. */ +#define REG_ICASE (REG_EXTENDED << 1) + +/* If this bit is set, then anchors do not match at newline + characters in the string. + If not set, then anchors do match at newlines. */ +#define REG_NEWLINE (REG_ICASE << 1) + +/* If this bit is set, then report only success or fail in regexec. + If not set, then returns differ between not matching and errors. */ +#define REG_NOSUB (REG_NEWLINE << 1) + + +/* POSIX `eflags' bits (i.e., information for regexec). */ + +/* If this bit is set, then the beginning-of-line operator doesn't match + the beginning of the string (presumably because it's not the + beginning of a line). + If not set, then the beginning-of-line operator does match the + beginning of the string. */ +#define REG_NOTBOL 1 + +/* Like REG_NOTBOL, except for the end-of-line. */ +#define REG_NOTEOL (1 << 1) + + +/* If any error codes are removed, changed, or added, update the + `re_error_msg' table in regex.c. */ +typedef enum +{ + REG_NOERROR = 0, /* Success. */ + REG_NOMATCH, /* Didn't find a match (for regexec). */ + + /* POSIX regcomp return error codes. (In the order listed in the + standard.) */ + REG_BADPAT, /* Invalid pattern. */ + REG_ECOLLATE, /* Not implemented. */ + REG_ECTYPE, /* Invalid character class name. */ + REG_EESCAPE, /* Trailing backslash. */ + REG_ESUBREG, /* Invalid back reference. */ + REG_EBRACK, /* Unmatched left bracket. */ + REG_EPAREN, /* Parenthesis imbalance. */ + REG_EBRACE, /* Unmatched \{. */ + REG_BADBR, /* Invalid contents of \{\}. */ + REG_ERANGE, /* Invalid range end. */ + REG_ESPACE, /* Ran out of memory. */ + REG_BADRPT, /* No preceding re for repetition op. */ + + /* Error codes we've added. */ + REG_EEND, /* Premature end. */ + REG_ESIZE, /* Compiled pattern bigger than 2^16 bytes. */ + REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */ +} reg_errcode_t; + +/* This data structure represents a compiled pattern. Before calling + the pattern compiler, the fields `buffer', `allocated', `fastmap', + `translate', and `no_sub' can be set. After the pattern has been + compiled, the `re_nsub' field is available. All other fields are + private to the regex routines. */ + +struct re_pattern_buffer +{ +/* [[[begin pattern_buffer]]] */ + /* Space that holds the compiled pattern. It is declared as + `unsigned char *' because its elements are + sometimes used as array indexes. */ + unsigned char *buffer; + + /* Number of bytes to which `buffer' points. */ + unsigned long allocated; + + /* Number of bytes actually used in `buffer'. */ + unsigned long used; + + /* Syntax setting with which the pattern was compiled. */ + reg_syntax_t syntax; + + /* Pointer to a fastmap, if any, otherwise zero. re_search uses + the fastmap, if there is one, to skip over impossible + starting points for matches. */ + char *fastmap; + + /* Either a translate table to apply to all characters before + comparing them, or zero for no translation. The translation + is applied to a pattern when it is compiled and to a string + when it is matched. */ + char *translate; + + /* Number of subexpressions found by the compiler. */ + size_t re_nsub; + + /* Zero if this pattern cannot match the empty string, one else. + Well, in truth it's used only in `re_search_2', to see + whether or not we should use the fastmap, so we don't set + this absolutely perfectly; see `re_compile_fastmap' (the + `duplicate' case). */ + unsigned can_be_null : 1; + + /* If REGS_UNALLOCATED, allocate space in the `regs' structure + for `max (RE_NREGS, re_nsub + 1)' groups. + If REGS_REALLOCATE, reallocate space if necessary. + If REGS_FIXED, use what's there. */ +#define REGS_UNALLOCATED 0 +#define REGS_REALLOCATE 1 +#define REGS_FIXED 2 + unsigned regs_allocated : 2; + + /* Set to zero when `regex_compile' compiles a pattern; set to one + by `re_compile_fastmap' if it updates the fastmap. */ + unsigned fastmap_accurate : 1; + + /* If set, `re_match_2' does not return information about + subexpressions. */ + unsigned no_sub : 1; + + /* If set, a beginning-of-line anchor doesn't match at the + beginning of the string. */ + unsigned not_bol : 1; + + /* Similarly for an end-of-line anchor. */ + unsigned not_eol : 1; + + /* If true, an anchor at a newline matches. */ + unsigned newline_anchor : 1; + +/* [[[end pattern_buffer]]] */ +}; + +typedef struct re_pattern_buffer regex_t; + + +/* search.c (search_buffer) in Emacs needs this one opcode value. It is + defined both in `regex.c' and here. */ +#define RE_EXACTN_VALUE 1 + +/* Type for byte offsets within the string. POSIX mandates this. */ +typedef int regoff_t; + + +/* This is the structure we store register match data in. See + regex.texinfo for a full description of what registers match. */ +struct re_registers +{ + unsigned num_regs; + regoff_t *start; + regoff_t *end; +}; + + +/* If `regs_allocated' is REGS_UNALLOCATED in the pattern buffer, + `re_match_2' returns information about at least this many registers + the first time a `regs' structure is passed. */ +#ifndef RE_NREGS +#define RE_NREGS 30 +#endif + + +/* POSIX specification for registers. Aside from the different names than + `re_registers', POSIX uses an array of structures, instead of a + structure of arrays. */ +typedef struct +{ + regoff_t rm_so; /* Byte offset from string's start to substring's start. */ + regoff_t rm_eo; /* Byte offset from string's start to substring's end. */ +} regmatch_t; + +/* Declarations for routines. */ + +/* To avoid duplicating every routine declaration -- once with a + prototype (if we are ANSI), and once without (if we aren't) -- we + use the following macro to declare argument types. This + unfortunately clutters up the declarations a bit, but I think it's + worth it. */ + +#if __STDC__ + +#define _RE_ARGS(args) args + +#else /* not __STDC__ */ + +#define _RE_ARGS(args) () + +#endif /* not __STDC__ */ + +/* Sets the current default syntax to SYNTAX, and return the old syntax. + You can also simply assign to the `re_syntax_options' variable. */ +extern reg_syntax_t re_set_syntax _RE_ARGS ((reg_syntax_t syntax)); + +/* Compile the regular expression PATTERN, with length LENGTH + and syntax given by the global `re_syntax_options', into the buffer + BUFFER. Return NULL if successful, and an error string if not. */ +extern const char *re_compile_pattern + _RE_ARGS ((const char *pattern, int length, + struct re_pattern_buffer *buffer)); + + +/* Compile a fastmap for the compiled pattern in BUFFER; used to + accelerate searches. Return 0 if successful and -2 if was an + internal error. */ +extern int re_compile_fastmap _RE_ARGS ((struct re_pattern_buffer *buffer)); + + +/* Search in the string STRING (with length LENGTH) for the pattern + compiled into BUFFER. Start searching at position START, for RANGE + characters. Return the starting position of the match, -1 for no + match, or -2 for an internal error. Also return register + information in REGS (if REGS and BUFFER->no_sub are nonzero). */ +extern int re_search + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, int range, struct re_registers *regs)); + + +/* Like `re_search', but search in the concatenation of STRING1 and + STRING2. Also, stop searching at index START + STOP. */ +extern int re_search_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, int range, struct re_registers *regs, int stop)); + + +/* Like `re_search', but return how many characters in STRING the regexp + in BUFFER matched, starting at position START. */ +extern int re_match + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, struct re_registers *regs)); + + +/* Relates to `re_match' as `re_search_2' relates to `re_search'. */ +extern int re_match_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, struct re_registers *regs, int stop)); + + +/* Set REGS to hold NUM_REGS registers, storing them in STARTS and + ENDS. Subsequent matches using BUFFER and REGS will use this memory + for recording register information. STARTS and ENDS must be + allocated with malloc, and must each be at least `NUM_REGS * sizeof + (regoff_t)' bytes long. + + If NUM_REGS == 0, then subsequent matches should allocate their own + register data. + + Unless this function is called, the first search or match using + PATTERN_BUFFER will allocate its own register data, without + freeing the old data. */ +extern void re_set_registers + _RE_ARGS ((struct re_pattern_buffer *buffer, struct re_registers *regs, + unsigned num_regs, regoff_t *starts, regoff_t *ends)); + +/* 4.2 bsd compatibility. */ +extern char *re_comp _RE_ARGS ((const char *)); +extern int re_exec _RE_ARGS ((const char *)); + +/* POSIX compatibility. */ +extern int regcomp _RE_ARGS ((regex_t *preg, const char *pattern, int cflags)); +extern int regexec + _RE_ARGS ((const regex_t *preg, const char *string, size_t nmatch, + regmatch_t pmatch[], int eflags)); +extern size_t regerror + _RE_ARGS ((int errcode, const regex_t *preg, char *errbuf, + size_t errbuf_size)); +extern void regfree _RE_ARGS ((regex_t *preg)); + +#endif /* not __REGEXP_LIBRARY_H__ */ + +/* +Local variables: +make-backup-files: t +version-control: t +trim-versions-without-asking: nil +End: +*/ From 58eda02257a89df6e05f504bdf87e578d90f3b5e Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Dec 2007 11:10:54 +0100 Subject: [PATCH 059/295] Compile some programs only conditionally. These programs depend on difficult to emulate POSIX functionality. On Windows, we won't compile them. Signed-off-by: Johannes Sixt --- Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index b003e3e60a..95572efee5 100644 --- a/Makefile +++ b/Makefile @@ -273,11 +273,9 @@ EXTRA_PROGRAMS = # ... and all the rest that could be moved out of bindir to gitexecdir PROGRAMS += $(EXTRA_PROGRAMS) -PROGRAMS += git-daemon$X PROGRAMS += git-fast-import$X PROGRAMS += git-fetch-pack$X PROGRAMS += git-hash-object$X -PROGRAMS += git-imap-send$X PROGRAMS += git-index-pack$X PROGRAMS += git-merge-index$X PROGRAMS += git-merge-tree$X @@ -773,6 +771,10 @@ ifdef ZLIB_PATH endif EXTLIBS += -lz +ifndef NO_POSIX_ONLY_PROGRAMS + PROGRAMS += git-daemon$X + PROGRAMS += git-imap-send$X +endif ifndef NO_OPENSSL OPENSSL_LIBSSL = -lssl ifdef OPENSSLDIR From f4626df51f63d53b89ff01de54cbf7558217ea2b Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Dec 2007 21:24:59 +0100 Subject: [PATCH 060/295] Add target architecture MinGW. With this change GIT can be compiled and linked using MinGW. Builtins that only read the repository such as the log family and grep already work. Simple stubs are provided for a number of functions that the Windows C runtime does not offer. They will be completed in later patches. However, a fix for the snprintf/vsnprintf replacement is applied here to avoid buffer overflows. Dmitry Kakurin pointed out that access(..., X_OK) would always fails on Vista and suggested the -D__USE_MINGW_ACCESS workaround. Signed-off-by: Johannes Sixt --- Makefile | 28 ++++++++++ compat/mingw.c | 57 ++++++++++++++++++++ compat/mingw.h | 134 ++++++++++++++++++++++++++++++++++++++++++++++ compat/snprintf.c | 19 +++++-- git-compat-util.h | 13 +++-- 5 files changed, 244 insertions(+), 7 deletions(-) create mode 100644 compat/mingw.c create mode 100644 compat/mingw.h diff --git a/Makefile b/Makefile index 95572efee5..a7dafa7586 100644 --- a/Makefile +++ b/Makefile @@ -335,6 +335,7 @@ LIB_H += builtin.h LIB_H += cache.h LIB_H += cache-tree.h LIB_H += commit.h +LIB_H += compat/mingw.h LIB_H += csum-file.h LIB_H += decorate.h LIB_H += delta.h @@ -711,6 +712,33 @@ ifeq ($(uname_S),HP-UX) NO_HSTRERROR = YesPlease NO_SYS_SELECT_H = YesPlease endif +ifneq (,$(findstring MINGW,$(uname_S))) + NO_MMAP = YesPlease + NO_PREAD = YesPlease + NO_OPENSSL = YesPlease + NO_CURL = YesPlease + NO_SYMLINK_HEAD = YesPlease + NO_IPV6 = YesPlease + NO_SETENV = YesPlease + NO_UNSETENV = YesPlease + NO_STRCASESTR = YesPlease + NO_STRLCPY = YesPlease + NO_MEMMEM = YesPlease + NEEDS_LIBICONV = YesPlease + OLD_ICONV = YesPlease + NO_C99_FORMAT = YesPlease + NO_STRTOUMAX = YesPlease + NO_MKDTEMP = YesPlease + SNPRINTF_RETURNS_BOGUS = YesPlease + NO_SVN_TESTS = YesPlease + NO_PERL_MAKEMAKER = YesPlease + NO_POSIX_ONLY_PROGRAMS = YesPlease + COMPAT_CFLAGS += -D__USE_MINGW_ACCESS -DNOGDI -Icompat + COMPAT_CFLAGS += -DSNPRINTF_SIZE_CORR=1 + COMPAT_OBJS += compat/mingw.o compat/fnmatch.o compat/regex.o + EXTLIBS += -lws2_32 + X = .exe +endif ifneq (,$(findstring arm,$(uname_M))) ARM_SHA1 = YesPlease endif diff --git a/compat/mingw.c b/compat/mingw.c new file mode 100644 index 0000000000..075448d245 --- /dev/null +++ b/compat/mingw.c @@ -0,0 +1,57 @@ +#include "../git-compat-util.h" + +unsigned int _CRT_fmode = _O_BINARY; + +unsigned int sleep (unsigned int seconds) +{ + Sleep(seconds*1000); + return 0; +} + +int mkstemp(char *template) +{ + char *filename = mktemp(template); + if (filename == NULL) + return -1; + return open(filename, O_RDWR | O_CREAT, 0600); +} + +int gettimeofday(struct timeval *tv, void *tz) +{ + return -1; +} + +int poll(struct pollfd *ufds, unsigned int nfds, int timeout) +{ + return -1; +} + +struct tm *gmtime_r(const time_t *timep, struct tm *result) +{ + /* gmtime() in MSVCRT.DLL is thread-safe, but not reentrant */ + memcpy(result, gmtime(timep), sizeof(struct tm)); + return result; +} + +struct tm *localtime_r(const time_t *timep, struct tm *result) +{ + /* localtime() in MSVCRT.DLL is thread-safe, but not reentrant */ + memcpy(result, localtime(timep), sizeof(struct tm)); + return result; +} + +struct passwd *getpwuid(int uid) +{ + static struct passwd p; + return &p; +} + +int setitimer(int type, struct itimerval *in, struct itimerval *out) +{ + return -1; +} + +int sigaction(int sig, struct sigaction *in, struct sigaction *out) +{ + return -1; +} diff --git a/compat/mingw.h b/compat/mingw.h new file mode 100644 index 0000000000..e5c0c6ba21 --- /dev/null +++ b/compat/mingw.h @@ -0,0 +1,134 @@ +#include + +/* + * things that are not available in header files + */ + +typedef int pid_t; +#define hstrerror strerror + +#define S_IFLNK 0120000 /* Symbolic link */ +#define S_ISLNK(x) (((x) & S_IFMT) == S_IFLNK) +#define S_ISSOCK(x) 0 +#define S_IRGRP 0 +#define S_IWGRP 0 +#define S_IXGRP 0 +#define S_ISGID 0 +#define S_IROTH 0 +#define S_IXOTH 0 + +#define WIFEXITED(x) ((unsigned)(x) < 259) /* STILL_ACTIVE */ +#define WEXITSTATUS(x) ((x) & 0xff) +#define WIFSIGNALED(x) ((unsigned)(x) > 259) + +#define SIGKILL 0 +#define SIGCHLD 0 +#define SIGPIPE 0 +#define SIGHUP 0 +#define SIGQUIT 0 +#define SIGALRM 100 + +#define F_GETFD 1 +#define F_SETFD 2 +#define FD_CLOEXEC 0x1 + +struct passwd { + char *pw_name; + char *pw_gecos; + char *pw_dir; +}; + +struct pollfd { + int fd; /* file descriptor */ + short events; /* requested events */ + short revents; /* returned events */ +}; +#define POLLIN 1 +#define POLLHUP 2 + +typedef void (__cdecl *sig_handler_t)(int); +struct sigaction { + sig_handler_t sa_handler; + unsigned sa_flags; +}; +#define sigemptyset(x) (void)0 +#define SA_RESTART 0 + +struct itimerval { + struct timeval it_value, it_interval; +}; +#define ITIMER_REAL 0 + +#define st_blocks st_size/512 /* will be cleaned up later */ +#define lstat stat + +/* + * trivial stubs + */ + +static inline int readlink(const char *path, char *buf, size_t bufsiz) +{ errno = ENOSYS; return -1; } +static inline int symlink(const char *oldpath, const char *newpath) +{ errno = ENOSYS; return -1; } +static inline int link(const char *oldpath, const char *newpath) +{ errno = ENOSYS; return -1; } +static inline int fchmod(int fildes, mode_t mode) +{ errno = ENOSYS; return -1; } +static inline int fork(void) +{ errno = ENOSYS; return -1; } +static inline unsigned int alarm(unsigned int seconds) +{ return 0; } +static inline int fsync(int fd) +{ return 0; } +static inline int getppid(void) +{ return 1; } +static inline void sync(void) +{} +static inline int getuid() +{ return 1; } +static inline struct passwd *getpwnam(const char *name) +{ return NULL; } +static inline int fcntl(int fd, int cmd, long arg) +{ + if (cmd == F_GETFD || cmd == F_SETFD) + return 0; + errno = EINVAL; + return -1; +} + +/* + * simple adaptors + */ + +static inline int mingw_mkdir(const char *path, int mode) +{ + return mkdir(path); +} +#define mkdir mingw_mkdir + +static inline int waitpid(pid_t pid, unsigned *status, unsigned options) +{ + if (options == 0) + return _cwait(status, pid, 0); + errno = EINVAL; + return -1; +} + + +static inline int pipe(int filedes[2]) +{ return _pipe(filedes, 8192, 0); } + +/* + * implementations of missing functions + */ + +unsigned int sleep (unsigned int seconds); +int mkstemp(char *template); +int gettimeofday(struct timeval *tv, void *tz); +int poll(struct pollfd *ufds, unsigned int nfds, int timeout); +struct tm *gmtime_r(const time_t *timep, struct tm *result); +struct tm *localtime_r(const time_t *timep, struct tm *result); +int getpagesize(void); /* defined in MinGW's libgcc.a */ +struct passwd *getpwuid(int uid); +int setitimer(int type, struct itimerval *in, struct itimerval *out); +int sigaction(int sig, struct sigaction *in, struct sigaction *out); diff --git a/compat/snprintf.c b/compat/snprintf.c index dbfc2d6b6e..580966e56a 100644 --- a/compat/snprintf.c +++ b/compat/snprintf.c @@ -1,12 +1,25 @@ #include "../git-compat-util.h" +/* + * The size parameter specifies the available space, i.e. includes + * the trailing NUL byte; but Windows's vsnprintf expects the + * number of characters to write without the trailing NUL. + */ +#ifndef SNPRINTF_SIZE_CORR +#define SNPRINTF_SIZE_CORR 0 +#endif + #undef vsnprintf int git_vsnprintf(char *str, size_t maxsize, const char *format, va_list ap) { char *s; - int ret; + int ret = -1; - ret = vsnprintf(str, maxsize, format, ap); + if (maxsize > 0) { + ret = vsnprintf(str, maxsize-SNPRINTF_SIZE_CORR, format, ap); + /* Windows does not NUL-terminate if result fills buffer */ + str[maxsize-1] = 0; + } if (ret != -1) return ret; @@ -20,7 +33,7 @@ int git_vsnprintf(char *str, size_t maxsize, const char *format, va_list ap) if (! str) break; s = str; - ret = vsnprintf(str, maxsize, format, ap); + ret = vsnprintf(str, maxsize-SNPRINTF_SIZE_CORR, format, ap); } free(s); return ret; diff --git a/git-compat-util.h b/git-compat-util.h index c04e8baa87..da7249ac1c 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -63,17 +63,18 @@ #include #include #include -#include #include +#include +#include +#include +#ifndef __MINGW32__ +#include #include #include #include -#include #ifndef NO_SYS_SELECT_H #include #endif -#include -#include #include #include #include @@ -89,6 +90,10 @@ #include #define _ALL_SOURCE 1 #endif +#else /* __MINGW32__ */ +/* pull in Windows compatibility stuff */ +#include "compat/mingw.h" +#endif /* __MINGW32__ */ #ifndef NO_ICONV #include From 80ba074f4163dc8ee4232d64e73a8521edcadc1d Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Mon, 3 Dec 2007 21:55:57 +0100 Subject: [PATCH 061/295] Windows: Use the Windows style PATH separator ';'. Signed-off-by: Johannes Sixt --- Documentation/git.txt | 6 +++--- compat/mingw.h | 6 ++++++ exec_cmd.c | 2 +- git-compat-util.h | 4 ++++ sha1_file.c | 2 +- 5 files changed, 15 insertions(+), 5 deletions(-) diff --git a/Documentation/git.txt b/Documentation/git.txt index 7414238fe5..4e4bd6ddb1 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -409,9 +409,9 @@ git so take care if using Cogito etc. 'GIT_ALTERNATE_OBJECT_DIRECTORIES':: Due to the immutable nature of git objects, old objects can be archived into shared, read-only directories. This variable - specifies a ":" separated list of git object directories which - can be used to search for git objects. New objects will not be - written to these directories. + specifies a ":" separated (on Windows ";" separated) list + of git object directories which can be used to search for git + objects. New objects will not be written to these directories. 'GIT_DIR':: If the 'GIT_DIR' environment variable is set then it diff --git a/compat/mingw.h b/compat/mingw.h index e5c0c6ba21..22aae0077e 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -132,3 +132,9 @@ int getpagesize(void); /* defined in MinGW's libgcc.a */ struct passwd *getpwuid(int uid); int setitimer(int type, struct itimerval *in, struct itimerval *out); int sigaction(int sig, struct sigaction *in, struct sigaction *out); + +/* + * git specific compatibility + */ + +#define PATH_SEP ';' diff --git a/exec_cmd.c b/exec_cmd.c index e189caca62..a1bc4e04bf 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -37,7 +37,7 @@ static void add_path(struct strbuf *out, const char *path) else strbuf_addstr(out, make_absolute_path(path)); - strbuf_addch(out, ':'); + strbuf_addch(out, PATH_SEP); } } diff --git a/git-compat-util.h b/git-compat-util.h index da7249ac1c..9dc733e56c 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -110,6 +110,10 @@ #define PRIuMAX "llu" #endif +#ifndef PATH_SEP +#define PATH_SEP ':' +#endif + #ifdef __GNUC__ #define NORETURN __attribute__((__noreturn__)) #else diff --git a/sha1_file.c b/sha1_file.c index 191f814e09..6f004ffd09 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -392,7 +392,7 @@ void prepare_alt_odb(void) if (!alt) alt = ""; alt_odb_tail = &alt_odb_list; - link_alt_odb_entries(alt, alt + strlen(alt), ':', NULL, 0); + link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0); read_info_alternates(get_object_directory(), 0); } From 8c6cfcddce80381a61a4cc0460ca497a271bfbff Mon Sep 17 00:00:00 2001 From: Stephan Beyer Date: Sun, 22 Jun 2008 01:54:36 +0200 Subject: [PATCH 062/295] api-builtin.txt: update and fix typo Mention NEED_WORK_TREE flag and command-list.txt. Fix "bulit-in" typo and AsciiDoc-formatting of a paragraph. Signed-off-by: Stephan Beyer Signed-off-by: Junio C Hamano --- Documentation/technical/api-builtin.txt | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/Documentation/technical/api-builtin.txt b/Documentation/technical/api-builtin.txt index 52cdb4c520..7ede1e64e5 100644 --- a/Documentation/technical/api-builtin.txt +++ b/Documentation/technical/api-builtin.txt @@ -4,7 +4,7 @@ builtin API Adding a new built-in --------------------- -There are 4 things to do to add a bulit-in command implementation to +There are 4 things to do to add a built-in command implementation to git: . Define the implementation of the built-in command `foo` with @@ -18,8 +18,8 @@ git: defined in `git.c`. The entry should look like: { "foo", cmd_foo, }, - - where options is the bitwise-or of: ++ +where options is the bitwise-or of: `RUN_SETUP`:: @@ -33,6 +33,12 @@ git: If the standard output is connected to a tty, spawn a pager and feed our output to it. +`NEED_WORK_TREE`:: + + Make sure there is a work tree, i.e. the command cannot act + on bare repositories. + This makes only sense when `RUN_SETUP` is also set. + . Add `builtin-foo.o` to `BUILTIN_OBJS` in `Makefile`. Additionally, if `foo` is a new command, there are 3 more things to do: @@ -41,8 +47,7 @@ Additionally, if `foo` is a new command, there are 3 more things to do: . Write documentation in `Documentation/git-foo.txt`. -. Add an entry for `git-foo` to the list at the end of - `Documentation/cmd-list.perl`. +. Add an entry for `git-foo` to `command-list.txt`. How a built-in is called From ab7367929f69c8b0f2f59d89225f211253ff57ef Mon Sep 17 00:00:00 2001 From: Stephan Beyer Date: Sun, 22 Jun 2008 01:55:50 +0200 Subject: [PATCH 063/295] t3404: stricter tests for git-rebase--interactive Signed-off-by: Stephan Beyer Signed-off-by: Junio C Hamano --- t/t3404-rebase-interactive.sh | 43 +++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 9 deletions(-) diff --git a/t/t3404-rebase-interactive.sh b/t/t3404-rebase-interactive.sh index b9e3dbd242..1c80148dd5 100755 --- a/t/t3404-rebase-interactive.sh +++ b/t/t3404-rebase-interactive.sh @@ -96,6 +96,7 @@ chmod a+x fake-editor.sh test_expect_success 'no changes are a nop' ' git rebase -i F && + test "$(git symbolic-ref -q HEAD)" = "refs/heads/branch2" && test $(git rev-parse I) = $(git rev-parse HEAD) ' @@ -104,14 +105,26 @@ test_expect_success 'test the [branch] option' ' git rm file6 && git commit -m "stop here" && git rebase -i F branch2 && + test "$(git symbolic-ref -q HEAD)" = "refs/heads/branch2" && + test $(git rev-parse I) = $(git rev-parse branch2) && test $(git rev-parse I) = $(git rev-parse HEAD) ' +test_expect_success 'test --onto ' ' + git checkout -b test-onto branch2 && + git rebase -i --onto branch1 F && + test "$(git symbolic-ref -q HEAD)" = "refs/heads/test-onto" && + test $(git rev-parse HEAD^) = $(git rev-parse branch1) && + test $(git rev-parse I) = $(git rev-parse branch2) +' + test_expect_success 'rebase on top of a non-conflicting commit' ' git checkout branch1 && git tag original-branch1 && git rebase -i branch2 && test file6 = $(git diff --name-only original-branch1) && + test "$(git symbolic-ref -q HEAD)" = "refs/heads/branch1" && + test $(git rev-parse I) = $(git rev-parse branch2) && test $(git rev-parse I) = $(git rev-parse HEAD~2) ' @@ -144,9 +157,12 @@ EOF test_expect_success 'stop on conflicting pick' ' git tag new-branch1 && - ! git rebase -i master && + test_must_fail git rebase -i master && + test "$(git rev-parse HEAD~3)" = "$(git rev-parse master)" && test_cmp expect .git/.dotest-merge/patch && test_cmp expect2 file1 && + test "$(git-diff --name-status | + sed -n -e "/^U/s/^U[^a-z]*//p")" = file1 && test 4 = $(grep -v "^#" < .git/.dotest-merge/done | wc -l) && test 0 = $(grep -c "^[^#]" < .git/.dotest-merge/git-rebase-todo) ' @@ -154,6 +170,7 @@ test_expect_success 'stop on conflicting pick' ' test_expect_success 'abort' ' git rebase --abort && test $(git rev-parse new-branch1) = $(git rev-parse HEAD) && + test "$(git symbolic-ref -q HEAD)" = "refs/heads/branch1" && ! test -d .git/.dotest-merge ' @@ -213,7 +230,7 @@ test_expect_success 'preserve merges with -p' ' test_expect_success '--continue tries to commit' ' test_tick && - ! git rebase -i --onto new-branch1 HEAD^ && + test_must_fail git rebase -i --onto new-branch1 HEAD^ && echo resolved > file1 && git add file1 && FAKE_COMMIT_MESSAGE="chouette!" git rebase --continue && @@ -224,7 +241,7 @@ test_expect_success '--continue tries to commit' ' test_expect_success 'verbose flag is heeded, even after --continue' ' git reset --hard HEAD@{1} && test_tick && - ! git rebase -v -i --onto new-branch1 HEAD^ && + test_must_fail git rebase -v -i --onto new-branch1 HEAD^ && echo resolved > file1 && git add file1 && git rebase --continue > output && @@ -259,10 +276,14 @@ test_expect_success 'interrupted squash works as expected' ' git commit -m $n done && one=$(git rev-parse HEAD~3) && - ! FAKE_LINES="1 squash 3 2" git rebase -i HEAD~3 && + ( + FAKE_LINES="1 squash 3 2" && + export FAKE_LINES && + test_must_fail git rebase -i HEAD~3 + ) && (echo one; echo two; echo four) > conflict && git add conflict && - ! git rebase --continue && + test_must_fail git rebase --continue && echo resolved > conflict && git add conflict && git rebase --continue && @@ -277,13 +298,17 @@ test_expect_success 'interrupted squash works as expected (case 2)' ' git commit -m $n done && one=$(git rev-parse HEAD~3) && - ! FAKE_LINES="3 squash 1 2" git rebase -i HEAD~3 && + ( + FAKE_LINES="3 squash 1 2" && + export FAKE_LINES && + test_must_fail git rebase -i HEAD~3 + ) && (echo one; echo four) > conflict && git add conflict && - ! git rebase --continue && + test_must_fail git rebase --continue && (echo one; echo two; echo four) > conflict && git add conflict && - ! git rebase --continue && + test_must_fail git rebase --continue && echo resolved > conflict && git add conflict && git rebase --continue && @@ -331,7 +356,7 @@ test_expect_success 'rebase a commit violating pre-commit' ' chmod a+x $PRE_COMMIT && echo "monde! " >> file1 && test_tick && - ! git commit -m doesnt-verify file1 && + test_must_fail git commit -m doesnt-verify file1 && git commit -m doesnt-verify --no-verify file1 && test_tick && FAKE_LINES=2 git rebase -i HEAD~2 From 112db553b0db4c4f2b39e5e3e433b2102be10085 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 22 Jun 2008 12:19:25 -0700 Subject: [PATCH 064/295] Shrink the git binary a bit by avoiding unnecessary inline functions So I was looking at the disgusting size of the git binary, and even with the debugging removed, and using -Os instead of -O2, the size of the text section was pretty high. In this day and age I guess almost a megabyte of text isn't really all that surprising, but it still doesn't exactly make me think "lean and mean". With -Os, a surprising amount of text space is wasted on inline functions that end up just being replicated multiple times, and where performance really isn't a valid reason to inline them. In particular, the trivial wrapper functions like "xmalloc()" are used _everywhere_, and making them inline just duplicates the text (and the string we use to 'die()' on failure) unnecessarily. So this just moves them into a "wrapper.c" file, getting rid of a tiny bit of unnecessary bloat. The following numbers are both with "CFLAGS=-Os": Before: [torvalds@woody git]$ size git text data bss dec hex filename 700460 15160 292184 1007804 f60bc git After: [torvalds@woody git]$ size git text data bss dec hex filename 670540 15160 292184 977884 eebdc git so it saves almost 30k of text-space (it actually saves more than that with the default -O2, but I don't think that's necessarily a very relevant number from a "try to shrink git" standpoint). It might conceivably have a performance impact, but none of this should be _that_ performance critical. The real cost is not generally in the wrapper anyway, but in the code it wraps (ie the cost of "xread()" is all in the read itself, not in the trivial wrapping of it). Signed-off-by: Linus Torvalds Signed-off-by: Junio C Hamano --- Makefile | 1 + git-compat-util.h | 167 ++++------------------------------------------ wrapper.c | 160 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 173 insertions(+), 155 deletions(-) create mode 100644 wrapper.c diff --git a/Makefile b/Makefile index 6a31c9feda..314339d7e0 100644 --- a/Makefile +++ b/Makefile @@ -467,6 +467,7 @@ LIB_OBJS += unpack-trees.o LIB_OBJS += usage.o LIB_OBJS += utf8.o LIB_OBJS += walker.o +LIB_OBJS += wrapper.o LIB_OBJS += write_or_die.o LIB_OBJS += ws.o LIB_OBJS += wt-status.o diff --git a/git-compat-util.h b/git-compat-util.h index c04e8baa87..6f94a8197f 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -240,161 +240,18 @@ static inline char *gitstrchrnul(const char *s, int c) extern void release_pack_memory(size_t, int); -static inline char* xstrdup(const char *str) -{ - char *ret = strdup(str); - if (!ret) { - release_pack_memory(strlen(str) + 1, -1); - ret = strdup(str); - if (!ret) - die("Out of memory, strdup failed"); - } - return ret; -} - -static inline void *xmalloc(size_t size) -{ - void *ret = malloc(size); - if (!ret && !size) - ret = malloc(1); - if (!ret) { - release_pack_memory(size, -1); - ret = malloc(size); - if (!ret && !size) - ret = malloc(1); - if (!ret) - die("Out of memory, malloc failed"); - } -#ifdef XMALLOC_POISON - memset(ret, 0xA5, size); -#endif - return ret; -} - -/* - * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of - * "data" to the allocated memory, zero terminates the allocated memory, - * and returns a pointer to the allocated memory. If the allocation fails, - * the program dies. - */ -static inline void *xmemdupz(const void *data, size_t len) -{ - char *p = xmalloc(len + 1); - memcpy(p, data, len); - p[len] = '\0'; - return p; -} - -static inline char *xstrndup(const char *str, size_t len) -{ - char *p = memchr(str, '\0', len); - return xmemdupz(str, p ? p - str : len); -} - -static inline void *xrealloc(void *ptr, size_t size) -{ - void *ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) { - release_pack_memory(size, -1); - ret = realloc(ptr, size); - if (!ret && !size) - ret = realloc(ptr, 1); - if (!ret) - die("Out of memory, realloc failed"); - } - return ret; -} - -static inline void *xcalloc(size_t nmemb, size_t size) -{ - void *ret = calloc(nmemb, size); - if (!ret && (!nmemb || !size)) - ret = calloc(1, 1); - if (!ret) { - release_pack_memory(nmemb * size, -1); - ret = calloc(nmemb, size); - if (!ret && (!nmemb || !size)) - ret = calloc(1, 1); - if (!ret) - die("Out of memory, calloc failed"); - } - return ret; -} - -static inline void *xmmap(void *start, size_t length, - int prot, int flags, int fd, off_t offset) -{ - void *ret = mmap(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED) { - if (!length) - return NULL; - release_pack_memory(length, fd); - ret = mmap(start, length, prot, flags, fd, offset); - if (ret == MAP_FAILED) - die("Out of memory? mmap failed: %s", strerror(errno)); - } - return ret; -} - -/* - * xread() is the same a read(), but it automatically restarts read() - * operations with a recoverable error (EAGAIN and EINTR). xread() - * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. - */ -static inline ssize_t xread(int fd, void *buf, size_t len) -{ - ssize_t nr; - while (1) { - nr = read(fd, buf, len); - if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) - continue; - return nr; - } -} - -/* - * xwrite() is the same a write(), but it automatically restarts write() - * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT - * GUARANTEE that "len" bytes is written even if the operation is successful. - */ -static inline ssize_t xwrite(int fd, const void *buf, size_t len) -{ - ssize_t nr; - while (1) { - nr = write(fd, buf, len); - if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) - continue; - return nr; - } -} - -static inline int xdup(int fd) -{ - int ret = dup(fd); - if (ret < 0) - die("dup failed: %s", strerror(errno)); - return ret; -} - -static inline FILE *xfdopen(int fd, const char *mode) -{ - FILE *stream = fdopen(fd, mode); - if (stream == NULL) - die("Out of memory? fdopen failed: %s", strerror(errno)); - return stream; -} - -static inline int xmkstemp(char *template) -{ - int fd; - - fd = mkstemp(template); - if (fd < 0) - die("Unable to create temporary file: %s", strerror(errno)); - return fd; -} +extern char *xstrdup(const char *str); +extern void *xmalloc(size_t size); +extern void *xmemdupz(const void *data, size_t len); +extern char *xstrndup(const char *str, size_t len); +extern void *xrealloc(void *ptr, size_t size); +extern void *xcalloc(size_t nmemb, size_t size); +extern void *xmmap(void *start, size_t length, int prot, int flags, int fd, off_t offset); +extern ssize_t xread(int fd, void *buf, size_t len); +extern ssize_t xwrite(int fd, const void *buf, size_t len); +extern int xdup(int fd); +extern FILE *xfdopen(int fd, const char *mode); +extern int xmkstemp(char *template); static inline size_t xsize_t(off_t len) { diff --git a/wrapper.c b/wrapper.c new file mode 100644 index 0000000000..4e04f7661b --- /dev/null +++ b/wrapper.c @@ -0,0 +1,160 @@ +/* + * Various trivial helper wrappers around standard functions + */ +#include "cache.h" + +char *xstrdup(const char *str) +{ + char *ret = strdup(str); + if (!ret) { + release_pack_memory(strlen(str) + 1, -1); + ret = strdup(str); + if (!ret) + die("Out of memory, strdup failed"); + } + return ret; +} + +void *xmalloc(size_t size) +{ + void *ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) { + release_pack_memory(size, -1); + ret = malloc(size); + if (!ret && !size) + ret = malloc(1); + if (!ret) + die("Out of memory, malloc failed"); + } +#ifdef XMALLOC_POISON + memset(ret, 0xA5, size); +#endif + return ret; +} + +/* + * xmemdupz() allocates (len + 1) bytes of memory, duplicates "len" bytes of + * "data" to the allocated memory, zero terminates the allocated memory, + * and returns a pointer to the allocated memory. If the allocation fails, + * the program dies. + */ +void *xmemdupz(const void *data, size_t len) +{ + char *p = xmalloc(len + 1); + memcpy(p, data, len); + p[len] = '\0'; + return p; +} + +char *xstrndup(const char *str, size_t len) +{ + char *p = memchr(str, '\0', len); + return xmemdupz(str, p ? p - str : len); +} + +void *xrealloc(void *ptr, size_t size) +{ + void *ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) { + release_pack_memory(size, -1); + ret = realloc(ptr, size); + if (!ret && !size) + ret = realloc(ptr, 1); + if (!ret) + die("Out of memory, realloc failed"); + } + return ret; +} + +void *xcalloc(size_t nmemb, size_t size) +{ + void *ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) { + release_pack_memory(nmemb * size, -1); + ret = calloc(nmemb, size); + if (!ret && (!nmemb || !size)) + ret = calloc(1, 1); + if (!ret) + die("Out of memory, calloc failed"); + } + return ret; +} + +void *xmmap(void *start, size_t length, + int prot, int flags, int fd, off_t offset) +{ + void *ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) { + if (!length) + return NULL; + release_pack_memory(length, fd); + ret = mmap(start, length, prot, flags, fd, offset); + if (ret == MAP_FAILED) + die("Out of memory? mmap failed: %s", strerror(errno)); + } + return ret; +} + +/* + * xread() is the same a read(), but it automatically restarts read() + * operations with a recoverable error (EAGAIN and EINTR). xread() + * DOES NOT GUARANTEE that "len" bytes is read even if the data is available. + */ +ssize_t xread(int fd, void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = read(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +/* + * xwrite() is the same a write(), but it automatically restarts write() + * operations with a recoverable error (EAGAIN and EINTR). xwrite() DOES NOT + * GUARANTEE that "len" bytes is written even if the operation is successful. + */ +ssize_t xwrite(int fd, const void *buf, size_t len) +{ + ssize_t nr; + while (1) { + nr = write(fd, buf, len); + if ((nr < 0) && (errno == EAGAIN || errno == EINTR)) + continue; + return nr; + } +} + +int xdup(int fd) +{ + int ret = dup(fd); + if (ret < 0) + die("dup failed: %s", strerror(errno)); + return ret; +} + +FILE *xfdopen(int fd, const char *mode) +{ + FILE *stream = fdopen(fd, mode); + if (stream == NULL) + die("Out of memory? fdopen failed: %s", strerror(errno)); + return stream; +} + +int xmkstemp(char *template) +{ + int fd; + + fd = mkstemp(template); + if (fd < 0) + die("Unable to create temporary file: %s", strerror(errno)); + return fd; +} From 4cd148d83f852363363e921c4925e67601654ff6 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Mar 2008 21:11:14 +0100 Subject: [PATCH 065/295] setup.c: Prepare for Windows directory separators. This turns two switch/case statements into an if-else-if cascade because we later do not want to have case '/': #ifdef __MINGW32__ case '\\': #endif but use a predicate is_dir_sep(foo) in order to check for the directory separator. Signed-off-by: Johannes Sixt --- setup.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/setup.c b/setup.c index d630e374e7..5fc89fd7da 100644 --- a/setup.c +++ b/setup.c @@ -26,24 +26,21 @@ static int sanitary_path_copy(char *dst, const char *src) * (4) "../" -- strip one, eat slash and continue. */ if (c == '.') { - switch (src[1]) { - case '\0': + if (!src[1]) { /* (1) */ src++; - break; - case '/': + } else if (src[1] == '/') { /* (2) */ src += 2; while (*src == '/') src++; continue; - case '.': - switch (src[2]) { - case '\0': + } else if (src[1] == '.') { + if (!src[2]) { /* (3) */ src += 2; goto up_one; - case '/': + } else if (src[2] == '/') { /* (4) */ src += 3; while (*src == '/') From 25fe217b86ca40c53e710d776e120dfa0d81f60b Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Wed, 5 Mar 2008 21:51:27 +0100 Subject: [PATCH 066/295] Windows: Treat Windows style path names. GIT's guts work with a forward slash as a path separators. We do not change that. Rather we make sure that only "normalized" paths enter the depths of the machinery. We have to translate backslashes to forward slashes in the prefix and in command line arguments. Fortunately, all of them are passed through functions in setup.c. A macro has_dos_drive_path() is defined that checks whether a path begins with a drive letter+colon combination. This predicate is always false on Unix. Another macro is_dir_sep() abstracts that a backslash is also a directory separator on Windows. Signed-off-by: Johannes Sixt --- cache.h | 2 +- compat/mingw.c | 13 ++++++++++++ compat/mingw.h | 9 +++++++++ git-compat-util.h | 8 ++++++++ setup.c | 50 ++++++++++++++++++++++++++++++++++------------- 5 files changed, 67 insertions(+), 15 deletions(-) diff --git a/cache.h b/cache.h index 81b7e17de2..72544de4ce 100644 --- a/cache.h +++ b/cache.h @@ -521,7 +521,7 @@ int safe_create_leading_directories(char *path); char *enter_repo(char *path, int strict); static inline int is_absolute_path(const char *path) { - return path[0] == '/'; + return path[0] == '/' || has_dos_drive_prefix(path); } const char *make_absolute_path(const char *path); const char *make_nonrelative_path(const char *path); diff --git a/compat/mingw.c b/compat/mingw.c index 075448d245..4e559bdc93 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -40,6 +40,19 @@ struct tm *localtime_r(const time_t *timep, struct tm *result) return result; } +#undef getcwd +char *mingw_getcwd(char *pointer, int len) +{ + int i; + char *ret = getcwd(pointer, len); + if (!ret) + return ret; + for (i = 0; pointer[i]; i++) + if (pointer[i] == '\\') + pointer[i] = '/'; + return ret; +} + struct passwd *getpwuid(int uid) { static struct passwd p; diff --git a/compat/mingw.h b/compat/mingw.h index 22aae0077e..a954014ff2 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -133,8 +133,17 @@ struct passwd *getpwuid(int uid); int setitimer(int type, struct itimerval *in, struct itimerval *out); int sigaction(int sig, struct sigaction *in, struct sigaction *out); +/* + * replacements of existing functions + */ + +char *mingw_getcwd(char *pointer, int len); +#define getcwd mingw_getcwd + /* * git specific compatibility */ +#define has_dos_drive_prefix(path) (isalpha(*(path)) && (path)[1] == ':') +#define is_dir_sep(c) ((c) == '/' || (c) == '\\') #define PATH_SEP ';' diff --git a/git-compat-util.h b/git-compat-util.h index 9dc733e56c..ab762c79ee 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -114,6 +114,14 @@ #define PATH_SEP ':' #endif +#ifndef has_dos_drive_prefix +#define has_dos_drive_prefix(path) 0 +#endif + +#ifndef is_dir_sep +#define is_dir_sep(c) ((c) == '/') +#endif + #ifdef __GNUC__ #define NORETURN __attribute__((__noreturn__)) #else diff --git a/setup.c b/setup.c index 5fc89fd7da..8bb7b10174 100644 --- a/setup.c +++ b/setup.c @@ -6,11 +6,17 @@ static int inside_work_tree = -1; static int sanitary_path_copy(char *dst, const char *src) { - char *dst0 = dst; + char *dst0; - if (*src == '/') { + if (has_dos_drive_prefix(src)) { + *dst++ = *src++; + *dst++ = *src++; + } + dst0 = dst; + + if (is_dir_sep(*src)) { *dst++ = '/'; - while (*src == '/') + while (is_dir_sep(*src)) src++; } @@ -29,10 +35,10 @@ static int sanitary_path_copy(char *dst, const char *src) if (!src[1]) { /* (1) */ src++; - } else if (src[1] == '/') { + } else if (is_dir_sep(src[1])) { /* (2) */ src += 2; - while (*src == '/') + while (is_dir_sep(*src)) src++; continue; } else if (src[1] == '.') { @@ -40,10 +46,10 @@ static int sanitary_path_copy(char *dst, const char *src) /* (3) */ src += 2; goto up_one; - } else if (src[2] == '/') { + } else if (is_dir_sep(src[2])) { /* (4) */ src += 3; - while (*src == '/') + while (is_dir_sep(*src)) src++; goto up_one; } @@ -51,11 +57,11 @@ static int sanitary_path_copy(char *dst, const char *src) } /* copy up to the next '/', and eat all '/' */ - while ((c = *src++) != '\0' && c != '/') + while ((c = *src++) != '\0' && !is_dir_sep(c)) *dst++ = c; - if (c == '/') { - *dst++ = c; - while (c == '/') + if (is_dir_sep(c)) { + *dst++ = '/'; + while (is_dir_sep(c)) c = *src++; src--; } else if (!c) @@ -74,7 +80,7 @@ static int sanitary_path_copy(char *dst, const char *src) if (dst <= dst0) break; c = *dst--; - if (c == '/') { + if (c == '/') { /* MinGW: cannot be '\\' anymore */ dst += 2; break; } @@ -123,10 +129,23 @@ const char *prefix_path(const char *prefix, int len, const char *path) const char *prefix_filename(const char *pfx, int pfx_len, const char *arg) { static char path[PATH_MAX]; +#ifndef __MINGW32__ if (!pfx || !*pfx || is_absolute_path(arg)) return arg; memcpy(path, pfx, pfx_len); strcpy(path + pfx_len, arg); +#else + char *p; + /* don't add prefix to absolute paths, but still replace '\' by '/' */ + if (is_absolute_path(arg)) + pfx_len = 0; + else + memcpy(path, pfx, pfx_len); + strcpy(path + pfx_len, arg); + for (p = path + pfx_len; *p; p++) + if (*p == '\\') + *p = '/'; +#endif return path; } @@ -360,6 +379,7 @@ const char *setup_git_directory_gently(int *nongit_ok) const char *gitdirenv; const char *gitfile_dir; int len, offset; + int minoffset = 0; /* * Let's assume that we are in a git repository. @@ -410,6 +430,8 @@ const char *setup_git_directory_gently(int *nongit_ok) if (!getcwd(cwd, sizeof(cwd)-1)) die("Unable to read current working directory"); + if (has_dos_drive_prefix(cwd)) + minoffset = 2; /* * Test in the following order (relative to the cwd): @@ -442,7 +464,7 @@ const char *setup_git_directory_gently(int *nongit_ok) } chdir(".."); do { - if (!offset) { + if (offset <= minoffset) { if (nongit_ok) { if (chdir(cwd)) die("Cannot come back to cwd"); @@ -451,7 +473,7 @@ const char *setup_git_directory_gently(int *nongit_ok) } die("Not a git repository"); } - } while (cwd[--offset] != '/'); + } while (offset > minoffset && cwd[--offset] != '/'); } inside_git_dir = 0; From 8385abfda533819be9fbec436230ccd7be4bcda8 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 30 Nov 2007 21:36:00 +0100 Subject: [PATCH 067/295] Windows: Handle absolute paths in safe_create_leading_directories(). In this function we must be careful to handle drive-local paths else there is a danger that it runs into an infinite loop. Signed-off-by: Johannes Sixt --- sha1_file.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/sha1_file.c b/sha1_file.c index 6f004ffd09..0a54eed761 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -83,14 +83,18 @@ int get_sha1_hex(const char *hex, unsigned char *sha1) return 0; } +static inline int offset_1st_component(const char *path) +{ + if (has_dos_drive_prefix(path)) + return 2 + (path[2] == '/'); + return *path == '/'; +} + int safe_create_leading_directories(char *path) { - char *pos = path; + char *pos = path + offset_1st_component(path); struct stat st; - if (is_absolute_path(path)) - pos++; - while (pos) { pos = strchr(pos, '/'); if (!pos) From 23326d14edbd16469453f6c3ecdd98ab90e6efb7 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 8 Dec 2007 20:57:25 +0100 Subject: [PATCH 068/295] Windows: Strip ".exe" from the program name. Before we can successfully parse a builtin command from the program name we must strip off unneeded parts, that is, the file extension. Furthermore, we must take Windows style path names into account when we parse the program name. Signed-off-by: Johannes Sixt --- Makefile | 1 + git-compat-util.h | 4 ++++ git.c | 19 ++++++++++++++++--- 3 files changed, 21 insertions(+), 3 deletions(-) diff --git a/Makefile b/Makefile index a7dafa7586..9c5aae03bb 100644 --- a/Makefile +++ b/Makefile @@ -735,6 +735,7 @@ ifneq (,$(findstring MINGW,$(uname_S))) NO_POSIX_ONLY_PROGRAMS = YesPlease COMPAT_CFLAGS += -D__USE_MINGW_ACCESS -DNOGDI -Icompat COMPAT_CFLAGS += -DSNPRINTF_SIZE_CORR=1 + COMPAT_CFLAGS += -DSTRIP_EXTENSION=\".exe\" COMPAT_OBJS += compat/mingw.o compat/fnmatch.o compat/regex.o EXTLIBS += -lws2_32 X = .exe diff --git a/git-compat-util.h b/git-compat-util.h index ab762c79ee..a9a85be89d 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -114,6 +114,10 @@ #define PATH_SEP ':' #endif +#ifndef STRIP_EXTENSION +#define STRIP_EXTENSION "" +#endif + #ifndef has_dos_drive_prefix #define has_dos_drive_prefix(path) 0 #endif diff --git a/git.c b/git.c index 59f0fcc1f2..871b93ca7e 100644 --- a/git.c +++ b/git.c @@ -369,6 +369,16 @@ static void handle_internal_command(int argc, const char **argv) { "pack-refs", cmd_pack_refs, RUN_SETUP }, }; int i; + static const char ext[] = STRIP_EXTENSION; + + if (sizeof(ext) > 1) { + i = strlen(argv[0]) - strlen(ext); + if (i > 0 && !strcmp(argv[0] + i, ext)) { + char *argv0 = strdup(argv[0]); + argv[0] = cmd = argv0; + argv0[i] = '\0'; + } + } /* Turn "git cmd --help" into "git help cmd" */ if (argc > 1 && !strcmp(argv[1], "--help")) { @@ -386,8 +396,8 @@ static void handle_internal_command(int argc, const char **argv) int main(int argc, const char **argv) { - const char *cmd = argv[0] ? argv[0] : "git-help"; - char *slash = strrchr(cmd, '/'); + const char *cmd = argv[0] && *argv[0] ? argv[0] : "git-help"; + char *slash = (char *)cmd + strlen(cmd); const char *cmd_path = NULL; int done_alias = 0; @@ -396,7 +406,10 @@ int main(int argc, const char **argv) * name, and the dirname as the default exec_path * if we don't have anything better. */ - if (slash) { + do + --slash; + while (cmd <= slash && !is_dir_sep(*slash)); + if (cmd <= slash) { *slash++ = 0; cmd_path = cmd; cmd = slash; From 3e4a1ba07b65506c36f7f40fa76fcee26c400a5c Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Thu, 15 Nov 2007 22:22:47 +0100 Subject: [PATCH 069/295] Windows: Implement a wrapper of the open() function. The wrapper does two things: - Requests to open /dev/null are redirected to open the nul pseudo file. - A request to open a file that currently exists as a directory on Windows fails with EACCES; this is changed to EISDIR. Signed-off-by: Johannes Sixt --- compat/mingw.c | 20 ++++++++++++++++++++ compat/mingw.h | 3 +++ 2 files changed, 23 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 4e559bdc93..f869999a5d 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -2,6 +2,26 @@ unsigned int _CRT_fmode = _O_BINARY; +#undef open +int mingw_open (const char *filename, int oflags, ...) +{ + va_list args; + unsigned mode; + va_start(args, oflags); + mode = va_arg(args, int); + va_end(args); + + if (!strcmp(filename, "/dev/null")) + filename = "nul"; + int fd = open(filename, oflags, mode); + if (fd < 0 && (oflags & O_CREAT) && errno == EACCES) { + DWORD attrs = GetFileAttributes(filename); + if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY)) + errno = EISDIR; + } + return fd; +} + unsigned int sleep (unsigned int seconds) { Sleep(seconds*1000); diff --git a/compat/mingw.h b/compat/mingw.h index a954014ff2..901cfa7c82 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -137,6 +137,9 @@ int sigaction(int sig, struct sigaction *in, struct sigaction *out); * replacements of existing functions */ +int mingw_open (const char *filename, int oflags, ...); +#define open mingw_open + char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd From f7597acac069bbaad8887cb315a4e5420222971a Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Dec 2007 22:09:17 +0100 Subject: [PATCH 070/295] Windows: A minimal implemention of getpwuid(). getpwuid() is implemented just enough that GIT does not issue errors. Since the information that it returns is not very useful, users are required to set up user.name and user.email configuration. All uses of getpwuid() are like getpwuid(getuid()), hence, the return value of getuid() is irrelevant and the uid parameter is not even looked at. Side note: getpwnam() is only used to resolve '~' and '~username' paths, which is an idiom not known on Windows, hence, we don't implement it. Signed-off-by: Johannes Sixt --- compat/mingw.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index f869999a5d..0e1ddbe4df 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -75,7 +75,15 @@ char *mingw_getcwd(char *pointer, int len) struct passwd *getpwuid(int uid) { + static char user_name[100]; static struct passwd p; + + DWORD len = sizeof(user_name); + if (!GetUserName(user_name, &len)) + return NULL; + p.pw_name = user_name; + p.pw_gecos = "unknown"; + p.pw_dir = NULL; return &p; } From 132a6e903fd912d02392db55c407267103766f19 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Tue, 23 Jan 2007 13:39:09 +0100 Subject: [PATCH 071/295] Windows: always chmod(, 0666) before unlink(). On Windows, read-only files cannot be deleted. To make sure that deletion does not fail because of this, always call chmod() before unlink(). Signed-off-by: Johannes Schindelin Signed-off-by: Johannes Sixt --- compat/mingw.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/compat/mingw.h b/compat/mingw.h index 901cfa7c82..95a08b4128 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -106,6 +106,14 @@ static inline int mingw_mkdir(const char *path, int mode) } #define mkdir mingw_mkdir +static inline int mingw_unlink(const char *pathname) +{ + /* read-only files cannot be removed */ + chmod(pathname, 0666); + return unlink(pathname); +} +#define unlink mingw_unlink + static inline int waitpid(pid_t pid, unsigned *status, unsigned options) { if (options == 0) From ea9e98c3a54d3b693367fbb8c87812b17ad95869 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 7 Dec 2007 22:19:40 +0100 Subject: [PATCH 072/295] Windows: Work around misbehaved rename(). Windows's rename() is based on the MoveFile() API, which fails if the destination exists. Here we work around the problem by using MoveFileEx(). Furthermore, the posixly correct error is returned if the destination is a directory. The implementation is still slightly incomplete, however, because of the missing error code translation: We assume that the failure is due to permissions. Signed-off-by: Johannes Sixt --- compat/mingw.c | 25 +++++++++++++++++++++++++ compat/mingw.h | 3 +++ 2 files changed, 28 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 0e1ddbe4df..c6a5c1b218 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -73,6 +73,31 @@ char *mingw_getcwd(char *pointer, int len) return ret; } +#undef rename +int mingw_rename(const char *pold, const char *pnew) +{ + /* + * Try native rename() first to get errno right. + * It is based on MoveFile(), which cannot overwrite existing files. + */ + if (!rename(pold, pnew)) + return 0; + if (errno != EEXIST) + return -1; + if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING)) + return 0; + /* TODO: translate more errors */ + if (GetLastError() == ERROR_ACCESS_DENIED) { + DWORD attrs = GetFileAttributes(pnew); + if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY)) { + errno = EISDIR; + return -1; + } + } + errno = EACCES; + return -1; +} + struct passwd *getpwuid(int uid) { static char user_name[100]; diff --git a/compat/mingw.h b/compat/mingw.h index 95a08b4128..46fd8da06e 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -151,6 +151,9 @@ int mingw_open (const char *filename, int oflags, ...); char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd +int mingw_rename(const char*, const char*); +#define rename mingw_rename + /* * git specific compatibility */ From bb5799d6ef3ad7ee70a138b82e67b93e3aaa8017 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Mon, 23 Jun 2008 08:31:41 +0200 Subject: [PATCH 073/295] Make my_mktime() public and rename it to tm_to_time_t() We will use it from the MinGW port's gettimeofday() substitution. Signed-off-by: Johannes Sixt --- date.c | 13 ++++++++----- git-compat-util.h | 1 + 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/date.c b/date.c index 1a4eb87b01..35a52576c5 100644 --- a/date.c +++ b/date.c @@ -6,7 +6,10 @@ #include "cache.h" -static time_t my_mktime(struct tm *tm) +/* + * This is like mktime, but without normalization of tm_wday and tm_yday. + */ +time_t tm_to_time_t(const struct tm *tm) { static const int mdays[] = { 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334 @@ -67,7 +70,7 @@ static int local_tzoffset(unsigned long time) t = time; localtime_r(&t, &tm); - t_local = my_mktime(&tm); + t_local = tm_to_time_t(&tm); if (t_local < t) { eastwest = -1; @@ -322,7 +325,7 @@ static int is_date(int year, int month, int day, struct tm *now_tm, time_t now, if (!now_tm) return 1; - specified = my_mktime(r); + specified = tm_to_time_t(r); /* Be it commit time or author time, it does not make * sense to specify timestamp way into the future. Make @@ -572,7 +575,7 @@ int parse_date(const char *date, char *result, int maxlen) } /* mktime uses local timezone */ - then = my_mktime(&tm); + then = tm_to_time_t(&tm); if (offset == -1) offset = (then - mktime(&tm)) / 60; @@ -611,7 +614,7 @@ void datestamp(char *buf, int bufsize) time(&now); - offset = my_mktime(localtime(&now)) - now; + offset = tm_to_time_t(localtime(&now)) - now; offset /= 60; date_string(now, offset, buf, bufsize); diff --git a/git-compat-util.h b/git-compat-util.h index a9a85be89d..58cdc087fa 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -147,6 +147,7 @@ extern void set_error_routine(void (*routine)(const char *err, va_list params)); extern void set_warn_routine(void (*routine)(const char *warn, va_list params)); extern int prefixcmp(const char *str, const char *prefix); +extern time_t tm_to_time_t(const struct tm *tm); #ifdef NO_MMAP From a42a0c2e715d6783a6f9b75a8f2c9a48bf499c47 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Dec 2007 21:51:20 +0100 Subject: [PATCH 074/295] Windows: Implement gettimeofday(). Signed-off-by: Johannes Sixt --- compat/mingw.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/compat/mingw.c b/compat/mingw.c index c6a5c1b218..57af486b7a 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -38,7 +38,20 @@ int mkstemp(char *template) int gettimeofday(struct timeval *tv, void *tz) { - return -1; + SYSTEMTIME st; + struct tm tm; + GetSystemTime(&st); + tm.tm_year = st.wYear-1900; + tm.tm_mon = st.wMonth-1; + tm.tm_mday = st.wDay; + tm.tm_hour = st.wHour; + tm.tm_min = st.wMinute; + tm.tm_sec = st.wSecond; + tv->tv_sec = tm_to_time_t(&tm); + if (tv->tv_sec < 0) + return -1; + tv->tv_usec = st.wMilliseconds*1000; + return 0; } int poll(struct pollfd *ufds, unsigned int nfds, int timeout) From 82f8d969f581c4bd4a782565709466046d962d81 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 23 Mar 2007 10:57:05 +0100 Subject: [PATCH 075/295] Windows: Fix PRIuMAX definition. Since GIT calls into Microsoft's MSVCRT.DLL, it must use the printf format that this DLL uses for 64-bit integers, which is %I64u instead of %llu. Signed-off-by: Johannes Sixt --- compat/mingw.h | 1 + 1 file changed, 1 insertion(+) diff --git a/compat/mingw.h b/compat/mingw.h index 46fd8da06e..fad855ef99 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -161,3 +161,4 @@ int mingw_rename(const char*, const char*); #define has_dos_drive_prefix(path) (isalpha(*(path)) && (path)[1] == ':') #define is_dir_sep(c) ((c) == '/' || (c) == '\\') #define PATH_SEP ';' +#define PRIuMAX "I64u" From 6072fc314e87d53bec7266df5b6c3db2c2c82829 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Tue, 13 Nov 2007 10:14:45 +0100 Subject: [PATCH 076/295] Windows: Implement setitimer() and sigaction(). The timer is implemented using a thread that calls the signal handler at regular intervals. We also replace Windows's signal() function because we must intercept that SIGALRM is set (which is used when a timer is canceled). Signed-off-by: Johannes Sixt --- compat/mingw.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++- compat/mingw.h | 3 ++ 2 files changed, 113 insertions(+), 2 deletions(-) diff --git a/compat/mingw.c b/compat/mingw.c index 57af486b7a..3ffff75ba6 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -125,12 +125,120 @@ struct passwd *getpwuid(int uid) return &p; } +static HANDLE timer_event; +static HANDLE timer_thread; +static int timer_interval; +static int one_shot; +static sig_handler_t timer_fn = SIG_DFL; + +/* The timer works like this: + * The thread, ticktack(), is a trivial routine that most of the time + * only waits to receive the signal to terminate. The main thread tells + * the thread to terminate by setting the timer_event to the signalled + * state. + * But ticktack() interrupts the wait state after the timer's interval + * length to call the signal handler. + */ + +static __stdcall unsigned ticktack(void *dummy) +{ + while (WaitForSingleObject(timer_event, timer_interval) == WAIT_TIMEOUT) { + if (timer_fn == SIG_DFL) + die("Alarm"); + if (timer_fn != SIG_IGN) + timer_fn(SIGALRM); + if (one_shot) + break; + } + return 0; +} + +static int start_timer_thread(void) +{ + timer_event = CreateEvent(NULL, FALSE, FALSE, NULL); + if (timer_event) { + timer_thread = (HANDLE) _beginthreadex(NULL, 0, ticktack, NULL, 0, NULL); + if (!timer_thread ) + return errno = ENOMEM, + error("cannot start timer thread"); + } else + return errno = ENOMEM, + error("cannot allocate resources for timer"); + return 0; +} + +static void stop_timer_thread(void) +{ + if (timer_event) + SetEvent(timer_event); /* tell thread to terminate */ + if (timer_thread) { + int rc = WaitForSingleObject(timer_thread, 1000); + if (rc == WAIT_TIMEOUT) + error("timer thread did not terminate timely"); + else if (rc != WAIT_OBJECT_0) + error("waiting for timer thread failed: %lu", + GetLastError()); + CloseHandle(timer_thread); + } + if (timer_event) + CloseHandle(timer_event); + timer_event = NULL; + timer_thread = NULL; +} + +static inline int is_timeval_eq(const struct timeval *i1, const struct timeval *i2) +{ + return i1->tv_sec == i2->tv_sec && i1->tv_usec == i2->tv_usec; +} + int setitimer(int type, struct itimerval *in, struct itimerval *out) { - return -1; + static const struct timeval zero; + static int atexit_done; + + if (out != NULL) + return errno = EINVAL, + error("setitimer param 3 != NULL not implemented"); + if (!is_timeval_eq(&in->it_interval, &zero) && + !is_timeval_eq(&in->it_interval, &in->it_value)) + return errno = EINVAL, + error("setitimer: it_interval must be zero or eq it_value"); + + if (timer_thread) + stop_timer_thread(); + + if (is_timeval_eq(&in->it_value, &zero) && + is_timeval_eq(&in->it_interval, &zero)) + return 0; + + timer_interval = in->it_value.tv_sec * 1000 + in->it_value.tv_usec / 1000; + one_shot = is_timeval_eq(&in->it_interval, &zero); + if (!atexit_done) { + atexit(stop_timer_thread); + atexit_done = 1; + } + return start_timer_thread(); } int sigaction(int sig, struct sigaction *in, struct sigaction *out) { - return -1; + if (sig != SIGALRM) + return errno = EINVAL, + error("sigaction only implemented for SIGALRM"); + if (out != NULL) + return errno = EINVAL, + error("sigaction: param 3 != NULL not implemented"); + + timer_fn = in->sa_handler; + return 0; +} + +#undef signal +sig_handler_t mingw_signal(int sig, sig_handler_t handler) +{ + if (sig != SIGALRM) + return signal(sig, handler); + sig_handler_t old = timer_fn; + timer_fn = handler; + return old; } diff --git a/compat/mingw.h b/compat/mingw.h index fad855ef99..a369ade9e2 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -154,6 +154,9 @@ char *mingw_getcwd(char *pointer, int len); int mingw_rename(const char*, const char*); #define rename mingw_rename +sig_handler_t mingw_signal(int sig, sig_handler_t handler); +#define signal mingw_signal + /* * git specific compatibility */ From f1a4dfb85a432ae338d162179eaac5d50154fbeb Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Tue, 4 Dec 2007 12:38:32 +0100 Subject: [PATCH 077/295] Windows: Wrap execve so that shell scripts can be invoked. When an external git command is invoked, it can be a Bourne shell script. This patch looks into the command file to see whether it is one. In this case, the command line is rearranged to invoke the shell with the proper arguments. With this change, scripted git commands work. Command line arguments to those scripts cannot be complex (contain spaces or double-quotes), yet. Signed-off-by: Johannes Sixt --- compat/mingw.c | 184 +++++++++++++++++++++++++++++++++++++++++++++++++ compat/mingw.h | 3 + 2 files changed, 187 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 3ffff75ba6..89b29c55e5 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -86,6 +86,190 @@ char *mingw_getcwd(char *pointer, int len) return ret; } +static const char *parse_interpreter(const char *cmd) +{ + static char buf[100]; + char *p, *opt; + int n, fd; + + /* don't even try a .exe */ + n = strlen(cmd); + if (n >= 4 && !strcasecmp(cmd+n-4, ".exe")) + return NULL; + + fd = open(cmd, O_RDONLY); + if (fd < 0) + return NULL; + n = read(fd, buf, sizeof(buf)-1); + close(fd); + if (n < 4) /* at least '#!/x' and not error */ + return NULL; + + if (buf[0] != '#' || buf[1] != '!') + return NULL; + buf[n] = '\0'; + p = strchr(buf, '\n'); + if (!p) + return NULL; + + *p = '\0'; + if (!(p = strrchr(buf+2, '/')) && !(p = strrchr(buf+2, '\\'))) + return NULL; + /* strip options */ + if ((opt = strchr(p+1, ' '))) + *opt = '\0'; + return p+1; +} + +/* + * Splits the PATH into parts. + */ +static char **get_path_split(void) +{ + char *p, **path, *envpath = getenv("PATH"); + int i, n = 0; + + if (!envpath || !*envpath) + return NULL; + + envpath = xstrdup(envpath); + p = envpath; + while (p) { + char *dir = p; + p = strchr(p, ';'); + if (p) *p++ = '\0'; + if (*dir) { /* not earlier, catches series of ; */ + ++n; + } + } + if (!n) + return NULL; + + path = xmalloc((n+1)*sizeof(char*)); + p = envpath; + i = 0; + do { + if (*p) + path[i++] = xstrdup(p); + p = p+strlen(p)+1; + } while (i < n); + path[i] = NULL; + + free(envpath); + + return path; +} + +static void free_path_split(char **path) +{ + if (!path) + return; + + char **p = path; + while (*p) + free(*p++); + free(path); +} + +/* + * exe_only means that we only want to detect .exe files, but not scripts + * (which do not have an extension) + */ +static char *lookup_prog(const char *dir, const char *cmd, int isexe, int exe_only) +{ + char path[MAX_PATH]; + snprintf(path, sizeof(path), "%s/%s.exe", dir, cmd); + + if (!isexe && access(path, F_OK) == 0) + return xstrdup(path); + path[strlen(path)-4] = '\0'; + if ((!exe_only || isexe) && access(path, F_OK) == 0) + return xstrdup(path); + return NULL; +} + +/* + * Determines the absolute path of cmd using the the split path in path. + * If cmd contains a slash or backslash, no lookup is performed. + */ +static char *path_lookup(const char *cmd, char **path, int exe_only) +{ + char *prog = NULL; + int len = strlen(cmd); + int isexe = len >= 4 && !strcasecmp(cmd+len-4, ".exe"); + + if (strchr(cmd, '/') || strchr(cmd, '\\')) + prog = xstrdup(cmd); + + while (!prog && *path) + prog = lookup_prog(*path++, cmd, isexe, exe_only); + + return prog; +} + +static int try_shell_exec(const char *cmd, char *const *argv, char **env) +{ + const char *interpr = parse_interpreter(cmd); + char **path; + char *prog; + int pid = 0; + + if (!interpr) + return 0; + path = get_path_split(); + prog = path_lookup(interpr, path, 1); + if (prog) { + int argc = 0; + const char **argv2; + while (argv[argc]) argc++; + argv2 = xmalloc(sizeof(*argv) * (argc+2)); + argv2[0] = (char *)interpr; + argv2[1] = (char *)cmd; /* full path to the script file */ + memcpy(&argv2[2], &argv[1], sizeof(*argv) * argc); + pid = spawnve(_P_NOWAIT, prog, argv2, (const char **)env); + if (pid >= 0) { + int status; + if (waitpid(pid, &status, 0) < 0) + status = 255; + exit(status); + } + pid = 1; /* indicate that we tried but failed */ + free(prog); + free(argv2); + } + free_path_split(path); + return pid; +} + +static void mingw_execve(const char *cmd, char *const *argv, char *const *env) +{ + /* check if git_command is a shell script */ + if (!try_shell_exec(cmd, argv, (char **)env)) { + int pid, status; + + pid = spawnve(_P_NOWAIT, cmd, (const char **)argv, (const char **)env); + if (pid < 0) + return; + if (waitpid(pid, &status, 0) < 0) + status = 255; + exit(status); + } +} + +void mingw_execvp(const char *cmd, char *const *argv) +{ + char **path = get_path_split(); + char *prog = path_lookup(cmd, path, 0); + + if (prog) { + mingw_execve(prog, argv, environ); + free(prog); + } else + errno = ENOENT; + + free_path_split(path); +} + #undef rename int mingw_rename(const char *pold, const char *pnew) { diff --git a/compat/mingw.h b/compat/mingw.h index a369ade9e2..3ddef11eda 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -154,6 +154,9 @@ char *mingw_getcwd(char *pointer, int len); int mingw_rename(const char*, const char*); #define rename mingw_rename +void mingw_execvp(const char *cmd, char *const *argv); +#define execvp mingw_execvp + sig_handler_t mingw_signal(int sig, sig_handler_t handler); #define signal mingw_signal From 897bb8cb2c2ce6b73038bd8d4106fde079a09cf6 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 7 Dec 2007 22:05:36 +0100 Subject: [PATCH 078/295] Windows: A pipe() replacement whose ends are not inherited to children. On Unix the idiom to use a pipe is as follows: pipe(fd); pid = fork(); if (!pid) { dup2(fd[1], 1); close(fd[1]); close(fd[0]); ... } close(fd[1]); i.e. the child process closes the both pipe ends after duplicating one to the file descriptors where they are needed. On Windows, which does not have fork(), we never have an opportunity to (1) duplicate a pipe end in the child, (2) close unused pipe ends. Instead, we must use this idiom: save1 = dup(1); pipe(fd); dup2(fd[1], 1); spawn(...); dup2(save1, 1); close(fd[1]); i.e. save away the descriptor at the destination slot, replace by the pipe end, spawn process, restore the saved file. But there is a problem: Notice that the child did not only inherit the dup2()ed descriptor, but also *both* original pipe ends. Although the one end that was dup()ed could be closed before the spawn(), we cannot close the other end - the child inherits it, no matter what. The solution is to generate non-inheritable pipes. At the first glance, this looks strange: The purpose of pipes is usually to be inherited to child processes. But notice that in the course of actions as outlined above, the pipe descriptor that we want to inherit to the child is dup2()ed, and as it so happens, Windows's dup2() creates inheritable duplicates. Signed-off-by: Johannes Sixt --- compat/mingw.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ compat/mingw.h | 5 +---- 2 files changed, 46 insertions(+), 4 deletions(-) diff --git a/compat/mingw.c b/compat/mingw.c index 89b29c55e5..31a9b9e251 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -54,6 +54,51 @@ int gettimeofday(struct timeval *tv, void *tz) return 0; } +int pipe(int filedes[2]) +{ + int fd; + HANDLE h[2], parent; + + if (_pipe(filedes, 8192, 0) < 0) + return -1; + + parent = GetCurrentProcess(); + + if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[0]), + parent, &h[0], 0, FALSE, DUPLICATE_SAME_ACCESS)) { + close(filedes[0]); + close(filedes[1]); + return -1; + } + if (!DuplicateHandle (parent, (HANDLE)_get_osfhandle(filedes[1]), + parent, &h[1], 0, FALSE, DUPLICATE_SAME_ACCESS)) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[0]); + return -1; + } + fd = _open_osfhandle((int)h[0], O_NOINHERIT); + if (fd < 0) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[0]); + CloseHandle(h[1]); + return -1; + } + close(filedes[0]); + filedes[0] = fd; + fd = _open_osfhandle((int)h[1], O_NOINHERIT); + if (fd < 0) { + close(filedes[0]); + close(filedes[1]); + CloseHandle(h[1]); + return -1; + } + close(filedes[1]); + filedes[1] = fd; + return 0; +} + int poll(struct pollfd *ufds, unsigned int nfds, int timeout) { return -1; diff --git a/compat/mingw.h b/compat/mingw.h index 3ddef11eda..0ce9c96f93 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -122,14 +122,11 @@ static inline int waitpid(pid_t pid, unsigned *status, unsigned options) return -1; } - -static inline int pipe(int filedes[2]) -{ return _pipe(filedes, 8192, 0); } - /* * implementations of missing functions */ +int pipe(int filedes[2]); unsigned int sleep (unsigned int seconds); int mkstemp(char *template); int gettimeofday(struct timeval *tv, void *tz); From ba26f296f9ddc694fc42683132bc328dffd777ec Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 7 Dec 2007 22:08:59 +0100 Subject: [PATCH 079/295] Windows: Implement start_command(). On Windows, we have spawnv() variants to run a child process instead of fork()/exec(). In order to attach pipe ends to stdin, stdout, and stderr, we have to use this idiom: save1 = dup(1); dup2(pipe[1], 1); spawnv(); dup2(save1, 1); close(pipe[1]); assuming that the descriptors created by pipe() are not inheritable. Signed-off-by: Johannes Sixt --- compat/mingw.c | 62 ++++++++++++++++++++++++++++++++ compat/mingw.h | 8 +++++ run-command.c | 97 ++++++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 153 insertions(+), 14 deletions(-) diff --git a/compat/mingw.c b/compat/mingw.c index 31a9b9e251..7f89a6cb87 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -315,6 +315,68 @@ void mingw_execvp(const char *cmd, char *const *argv) free_path_split(path); } +char **copy_environ() +{ + char **env; + int i = 0; + while (environ[i]) + i++; + env = xmalloc((i+1)*sizeof(*env)); + for (i = 0; environ[i]; i++) + env[i] = xstrdup(environ[i]); + env[i] = NULL; + return env; +} + +void free_environ(char **env) +{ + int i; + for (i = 0; env[i]; i++) + free(env[i]); + free(env); +} + +static int lookup_env(char **env, const char *name, size_t nmln) +{ + int i; + + for (i = 0; env[i]; i++) { + if (0 == strncmp(env[i], name, nmln) + && '=' == env[i][nmln]) + /* matches */ + return i; + } + return -1; +} + +/* + * If name contains '=', then sets the variable, otherwise it unsets it + */ +char **env_setenv(char **env, const char *name) +{ + char *eq = strchrnul(name, '='); + int i = lookup_env(env, name, eq-name); + + if (i < 0) { + if (*eq) { + for (i = 0; env[i]; i++) + ; + env = xrealloc(env, (i+2)*sizeof(*env)); + env[i] = xstrdup(name); + env[i+1] = NULL; + } + } + else { + free(env[i]); + if (*eq) + env[i] = xstrdup(name); + else + for (; env[i]; i++) + env[i] = env[i+1]; + } + return env; +} + #undef rename int mingw_rename(const char *pold, const char *pnew) { diff --git a/compat/mingw.h b/compat/mingw.h index 0ce9c96f93..0879894c68 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -165,3 +165,11 @@ sig_handler_t mingw_signal(int sig, sig_handler_t handler); #define is_dir_sep(c) ((c) == '/' || (c) == '\\') #define PATH_SEP ';' #define PRIuMAX "I64u" + +/* + * helpers + */ + +char **copy_environ(void); +void free_environ(char **env); +char **env_setenv(char **env, const char *name); diff --git a/run-command.c b/run-command.c index 44100a749b..dd8b7751ce 100644 --- a/run-command.c +++ b/run-command.c @@ -65,21 +65,8 @@ int start_command(struct child_process *cmd) cmd->err = fderr[0]; } +#ifndef __MINGW32__ cmd->pid = fork(); - if (cmd->pid < 0) { - if (need_in) - close_pair(fdin); - else if (cmd->in) - close(cmd->in); - if (need_out) - close_pair(fdout); - else if (cmd->out) - close(cmd->out); - if (need_err) - close_pair(fderr); - return -ERR_RUN_COMMAND_FORK; - } - if (!cmd->pid) { if (cmd->no_stdin) dup_devnull(0); @@ -128,6 +115,88 @@ int start_command(struct child_process *cmd) } die("exec %s failed.", cmd->argv[0]); } +#else + int s0 = -1, s1 = -1, s2 = -1; /* backups of stdin, stdout, stderr */ + const char *sargv0 = cmd->argv[0]; + char **env = environ; + struct strbuf git_cmd; + + if (cmd->no_stdin) { + s0 = dup(0); + dup_devnull(0); + } else if (need_in) { + s0 = dup(0); + dup2(fdin[0], 0); + } else if (cmd->in) { + s0 = dup(0); + dup2(cmd->in, 0); + } + + if (cmd->no_stderr) { + s2 = dup(2); + dup_devnull(2); + } else if (need_err) { + s2 = dup(2); + dup2(fderr[1], 2); + } + + if (cmd->no_stdout) { + s1 = dup(1); + dup_devnull(1); + } else if (cmd->stdout_to_stderr) { + s1 = dup(1); + dup2(2, 1); + } else if (need_out) { + s1 = dup(1); + dup2(fdout[1], 1); + } else if (cmd->out > 1) { + s1 = dup(1); + dup2(cmd->out, 1); + } + + if (cmd->dir) + die("chdir in start_command() not implemented"); + if (cmd->env) { + env = copy_environ(); + for (; *cmd->env; cmd->env++) + env = env_setenv(env, *cmd->env); + } + + if (cmd->git_cmd) { + strbuf_init(&git_cmd, 0); + strbuf_addf(&git_cmd, "git-%s", cmd->argv[0]); + cmd->argv[0] = git_cmd.buf; + } + + cmd->pid = spawnvpe(_P_NOWAIT, cmd->argv[0], cmd->argv, (const char **)env); + + if (cmd->env) + free_environ(env); + if (cmd->git_cmd) + strbuf_release(&git_cmd); + + cmd->argv[0] = sargv0; + if (s0 >= 0) + dup2(s0, 0), close(s0); + if (s1 >= 0) + dup2(s1, 1), close(s1); + if (s2 >= 0) + dup2(s2, 2), close(s2); +#endif + + if (cmd->pid < 0) { + if (need_in) + close_pair(fdin); + else if (cmd->in) + close(cmd->in); + if (need_out) + close_pair(fdout); + else if (cmd->out) + close(cmd->out); + if (need_err) + close_pair(fderr); + return -ERR_RUN_COMMAND_FORK; + } if (need_in) close(fdin[0]); From f2ab7f82b7bd8f0147f656e7d279236d1bd68921 Mon Sep 17 00:00:00 2001 From: Michele Ballabio Date: Mon, 23 Jun 2008 18:19:23 +0200 Subject: [PATCH 080/295] t9301-fast-export.sh: Remove debug line Signed-off-by: Michele Ballabio Signed-off-by: Junio C Hamano --- t/t9301-fast-export.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/t/t9301-fast-export.sh b/t/t9301-fast-export.sh index 60b5ee3979..f1bc5ceef0 100755 --- a/t/t9301-fast-export.sh +++ b/t/t9301-fast-export.sh @@ -83,7 +83,6 @@ test_expect_success 'import/export-marks' ' git checkout -b marks master && git fast-export --export-marks=tmp-marks HEAD && test -s tmp-marks && - cp tmp-marks ~ && test $(wc -l < tmp-marks) -eq 3 && test $( git fast-export --import-marks=tmp-marks\ From 1f5c74f6cf918d317c73b328dcd4cf6f55c44d8a Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 23 Jun 2008 21:22:14 -0400 Subject: [PATCH 081/295] call init_pack_revindex() lazily This makes life much easier for next patch, as well as being more efficient when the revindex is actually not used. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- builtin-pack-objects.c | 2 -- pack-check.c | 1 - pack-revindex.c | 6 ++++-- pack-revindex.h | 1 - 4 files changed, 4 insertions(+), 6 deletions(-) diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c index 447d492dbb..827673ce4e 100644 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@ -1148,8 +1148,6 @@ static void get_object_details(void) sorted_by_offset[i] = objects + i; qsort(sorted_by_offset, nr_objects, sizeof(*sorted_by_offset), pack_offset_sort); - init_pack_revindex(); - for (i = 0; i < nr_objects; i++) check_object(sorted_by_offset[i]); diff --git a/pack-check.c b/pack-check.c index f4898732dd..b99a9171c0 100644 --- a/pack-check.c +++ b/pack-check.c @@ -107,7 +107,6 @@ static void show_pack_info(struct packed_git *p) nr_objects = p->num_objects; memset(chain_histogram, 0, sizeof(chain_histogram)); - init_pack_revindex(); for (i = 0; i < nr_objects; i++) { const unsigned char *sha1; diff --git a/pack-revindex.c b/pack-revindex.c index a8aa2cd6ca..cd300bdff5 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -40,7 +40,7 @@ static int pack_revindex_ix(struct packed_git *p) return -1 - i; } -void init_pack_revindex(void) +static void init_pack_revindex(void) { int num; struct packed_git *p; @@ -118,9 +118,11 @@ struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs) struct pack_revindex *rix; struct revindex_entry *revindex; + if (!pack_revindex_hashsz) + init_pack_revindex(); num = pack_revindex_ix(p); if (num < 0) - die("internal error: pack revindex uninitialized"); + die("internal error: pack revindex fubar"); rix = &pack_revindex[num]; if (!rix->revindex) diff --git a/pack-revindex.h b/pack-revindex.h index c3527a7565..36a514a6cf 100644 --- a/pack-revindex.h +++ b/pack-revindex.h @@ -6,7 +6,6 @@ struct revindex_entry { unsigned int nr; }; -void init_pack_revindex(void); struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs); #endif From 8eca0b47ff1598a6d163df9358c0e0c9bd92d4c8 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 23 Jun 2008 21:23:39 -0400 Subject: [PATCH 082/295] implement some resilience against pack corruptions We should be able to fall back to loose objects or alternative packs when a pack becomes corrupted. This is especially true when an object exists in one pack only as a delta but its base object is corrupted. Currently there is no way to retrieve the former object even if the later is available in another pack or loose. This patch allows for a delta to be resolved (with a performance cost) using a base object from a source other than the pack where that delta is located. Same thing for non-delta objects: rather than failing outright, a search is made in other packs or used loose when the currently active pack has it but corrupted. Of course git will become extremely noisy with error messages when that happens. However, if the operation succeeds nevertheless, a simple 'git repack -a -f -d' will "fix" the corrupted repository given that all corrupted objects have a good duplicate somewhere in the object store, possibly manually copied from another source. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- cache.h | 2 ++ sha1_file.c | 92 +++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 78 insertions(+), 16 deletions(-) diff --git a/cache.h b/cache.h index d12ee7d0f5..a68866c1b4 100644 --- a/cache.h +++ b/cache.h @@ -641,6 +641,8 @@ extern struct packed_git { const void *index_data; size_t index_size; uint32_t num_objects; + uint32_t num_bad_objects; + unsigned char *bad_object_sha1; int index_version; time_t mtime; int pack_fd; diff --git a/sha1_file.c b/sha1_file.c index 92299ed622..9330bc4920 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -818,6 +818,8 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local) p->index_data = NULL; p->index_size = 0; p->num_objects = 0; + p->num_bad_objects = 0; + p->bad_object_sha1 = NULL; p->pack_size = st.st_size; p->next = NULL; p->windows = NULL; @@ -982,6 +984,18 @@ void reprepare_packed_git(void) prepare_packed_git(); } +static void mark_bad_packed_object(struct packed_git *p, + const unsigned char *sha1) +{ + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + return; + p->bad_object_sha1 = xrealloc(p->bad_object_sha1, 20 * (p->num_bad_objects + 1)); + hashcpy(p->bad_object_sha1 + 20 * p->num_bad_objects, sha1); + p->num_bad_objects++; +} + int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type) { unsigned char real_sha1[20]; @@ -1300,20 +1314,17 @@ static off_t get_delta_base(struct packed_git *p, while (c & 128) { base_offset += 1; if (!base_offset || MSB(base_offset, 7)) - die("offset value overflow for delta base object"); + return 0; /* overflow */ c = base_info[used++]; base_offset = (base_offset << 7) + (c & 127); } base_offset = delta_obj_offset - base_offset; if (base_offset >= delta_obj_offset) - die("delta base offset out of bound"); + return 0; /* out of bound */ *curpos += used; } else if (type == OBJ_REF_DELTA) { /* The base entry _must_ be in the same pack */ base_offset = find_pack_entry_one(base_info, p); - if (!base_offset) - die("failed to find delta-pack base object %s", - sha1_to_hex(base_info)); *curpos += 20; } else die("I am totally screwed"); @@ -1406,6 +1417,9 @@ const char *packed_object_info_detail(struct packed_git *p, return typename(type); case OBJ_OFS_DELTA: obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset); + if (!obj_offset) + die("pack %s contains bad delta base reference of type %s", + p->pack_name, typename(type)); if (*delta_chain_length == 0) { revidx = find_pack_revindex(p, obj_offset); hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr)); @@ -1600,17 +1614,41 @@ static void *unpack_delta_entry(struct packed_git *p, off_t base_offset; base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset); + if (!base_offset) { + error("failed to validate delta base reference " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + return NULL; + } base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0); - if (!base) - die("failed to read delta base object" - " at %"PRIuMAX" from %s", - (uintmax_t)base_offset, p->pack_name); + if (!base) { + /* + * We're probably in deep shit, but let's try to fetch + * the required base anyway from another pack or loose. + * This is costly but should happen only in the presence + * of a corrupted pack, and is better than failing outright. + */ + struct revindex_entry *revidx = find_pack_revindex(p, base_offset); + const unsigned char *base_sha1 = + nth_packed_object_sha1(p, revidx->nr); + error("failed to read delta base object %s" + " at offset %"PRIuMAX" from %s", + sha1_to_hex(base_sha1), (uintmax_t)base_offset, + p->pack_name); + mark_bad_packed_object(p, base_sha1); + base = read_sha1_file(base_sha1, type, &base_size); + if (!base) + return NULL; + } delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size); - if (!delta_data) - die("failed to unpack compressed delta" - " at %"PRIuMAX" from %s", - (uintmax_t)curpos, p->pack_name); + if (!delta_data) { + error("failed to unpack compressed delta " + "at offset %"PRIuMAX" from %s", + (uintmax_t)curpos, p->pack_name); + free(base); + return NULL; + } result = patch_delta(base, base_size, delta_data, delta_size, sizep); @@ -1642,7 +1680,9 @@ void *unpack_entry(struct packed_git *p, off_t obj_offset, data = unpack_compressed_entry(p, &w_curs, curpos, *sizep); break; default: - die("unknown object type %i in %s", *type, p->pack_name); + data = NULL; + error("unknown object type %i at offset %"PRIuMAX" in %s", + *type, (uintmax_t)obj_offset, p->pack_name); } unuse_pack(&w_curs); return data; @@ -1788,6 +1828,13 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, cons goto next; } + if (p->num_bad_objects) { + unsigned i; + for (i = 0; i < p->num_bad_objects; i++) + if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i)) + goto next; + } + offset = find_pack_entry_one(sha1, p); if (offset) { /* @@ -1872,11 +1919,24 @@ static void *read_packed_sha1(const unsigned char *sha1, enum object_type *type, unsigned long *size) { struct pack_entry e; + void *data; if (!find_pack_entry(sha1, &e, NULL)) return NULL; - else - return cache_or_unpack_entry(e.p, e.offset, size, type, 1); + data = cache_or_unpack_entry(e.p, e.offset, size, type, 1); + if (!data) { + /* + * We're probably in deep shit, but let's try to fetch + * the required object anyway from another pack or loose. + * This should happen only in the presence of a corrupted + * pack, and is better than failing outright. + */ + error("failed to read object %s at offset %"PRIuMAX" from %s", + sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name); + mark_bad_packed_object(e.p, sha1); + data = read_sha1_file(sha1, type, size); + } + return data; } /* From 29b0d01912cdf291ad2e9f6a4f143ee9e3c01ef9 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Mon, 23 Jun 2008 21:24:28 -0400 Subject: [PATCH 083/295] test case for pack resilience against corruptions Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- t/t5303-pack-corruption-resilience.sh | 194 ++++++++++++++++++++++++++ 1 file changed, 194 insertions(+) create mode 100755 t/t5303-pack-corruption-resilience.sh diff --git a/t/t5303-pack-corruption-resilience.sh b/t/t5303-pack-corruption-resilience.sh new file mode 100755 index 0000000000..b0f5693482 --- /dev/null +++ b/t/t5303-pack-corruption-resilience.sh @@ -0,0 +1,194 @@ +#!/bin/sh +# +# Copyright (c) 2008 Nicolas Pitre +# + +test_description='resilience to pack corruptions with redundant objects' +. ./test-lib.sh + +# Note: the test objects are created with knowledge of their pack encoding +# to ensure good code path coverage, and to facilitate direct alteration +# later on. The assumed characteristics are: +# +# 1) blob_2 is a delta with blob_1 for base and blob_3 is a delta with blob2 +# for base, such that blob_3 delta depth is 2; +# +# 2) the bulk of object data is uncompressible so the text part remains +# visible; +# +# 3) object header is always 2 bytes. + +create_test_files() { + test-genrandom "foo" 2000 > file_1 && + test-genrandom "foo" 1800 > file_2 && + test-genrandom "foo" 1800 > file_3 && + echo " base " >> file_1 && + echo " delta1 " >> file_2 && + echo " delta delta2 " >> file_3 && + test-genrandom "bar" 150 >> file_2 && + test-genrandom "baz" 100 >> file_3 +} + +create_new_pack() { + rm -rf .git && + git init && + blob_1=`git hash-object -t blob -w file_1` && + blob_2=`git hash-object -t blob -w file_2` && + blob_3=`git hash-object -t blob -w file_3` && + pack=`printf "$blob_1\n$blob_2\n$blob_3\n" | + git pack-objects $@ .git/objects/pack/pack` && + pack=".git/objects/pack/pack-${pack}" && + git verify-pack -v ${pack}.pack +} + +do_corrupt_object() { + ofs=`git show-index < ${pack}.idx | grep $1 | cut -f1 -d" "` && + ofs=$(($ofs + $2)) && + chmod +w ${pack}.pack && + dd if=/dev/zero of=${pack}.pack count=1 bs=1 conv=notrunc seek=$ofs && + test_must_fail git verify-pack ${pack}.pack +} + +test_expect_success \ + 'initial setup validation' \ + 'create_test_files && + create_new_pack && + git prune-packed && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'create corruption in header of first object' \ + 'do_corrupt_object $blob_1 0 && + test_must_fail git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... but having a loose copy allows for full recovery' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_1 && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... and loose copy of first delta allows for partial recovery' \ + 'git prune-packed && + test_must_fail git cat-file blob $blob_2 > /dev/null && + mv ${pack}.idx tmp && + git hash-object -t blob -w file_2 && + mv tmp ${pack}.idx && + test_must_fail git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'create corruption in data of first object' \ + 'create_new_pack && + git prune-packed && + chmod +w ${pack}.pack && + perl -i -pe "s/ base /abcdef/" ${pack}.pack && + test_must_fail git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... but having a loose copy allows for full recovery' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_1 && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... and loose copy of second object allows for partial recovery' \ + 'git prune-packed && + test_must_fail git cat-file blob $blob_2 > /dev/null && + mv ${pack}.idx tmp && + git hash-object -t blob -w file_2 && + mv tmp ${pack}.idx && + test_must_fail git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'create corruption in header of first delta' \ + 'create_new_pack && + git prune-packed && + do_corrupt_object $blob_2 0 && + git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... but having a loose copy allows for full recovery' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_2 && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'create corruption in data of first delta' \ + 'create_new_pack && + git prune-packed && + chmod +w ${pack}.pack && + perl -i -pe "s/ delta1 /abcdefgh/" ${pack}.pack && + git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... but having a loose copy allows for full recovery' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_2 && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'corruption in delta base reference of first delta (OBJ_REF_DELTA)' \ + 'create_new_pack && + git prune-packed && + do_corrupt_object $blob_2 2 && + git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... but having a loose copy allows for full recovery' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_2 && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + 'corruption in delta base reference of first delta (OBJ_OFS_DELTA)' \ + 'create_new_pack --delta-base-offset && + git prune-packed && + do_corrupt_object $blob_2 2 && + git cat-file blob $blob_1 > /dev/null && + test_must_fail git cat-file blob $blob_2 > /dev/null && + test_must_fail git cat-file blob $blob_3 > /dev/null' + +test_expect_success \ + '... and a redundant pack allows for full recovery too' \ + 'mv ${pack}.idx tmp && + git hash-object -t blob -w file_1 && + git hash-object -t blob -w file_2 && + printf "$blob_1\n$blob_2\n" | git pack-objects .git/objects/pack/pack && + git prune-packed && + mv tmp ${pack}.idx && + git cat-file blob $blob_1 > /dev/null && + git cat-file blob $blob_2 > /dev/null && + git cat-file blob $blob_3 > /dev/null' + +test_done From 0a47dc110e042b5bcc63dc94c8d517e67efe9306 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sat, 1 Dec 2007 22:16:19 -0800 Subject: [PATCH 084/295] git-shell: accept "git foo" form Signed-off-by: Junio C Hamano --- shell.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/shell.c b/shell.c index 9826109d5b..b27d01c9e4 100644 --- a/shell.c +++ b/shell.c @@ -7,6 +7,7 @@ static int do_generic_cmd(const char *me, char *arg) { const char *my_argv[4]; + setup_path(NULL); if (!arg || !(arg = sq_dequote(arg))) die("bad argument"); if (prefixcmp(me, "git-")) @@ -29,7 +30,6 @@ static int do_cvs_cmd(const char *me, char *arg) die("git-cvsserver only handles server: %s", arg); setup_path(NULL); - return execv_git_cmd(cvsserver_argv); } @@ -49,15 +49,24 @@ int main(int argc, char **argv) char *prog; struct commands *cmd; + /* + * Special hack to pretend to be a CVS server + */ if (argc == 2 && !strcmp(argv[1], "cvs server")) argv--; - /* We want to see "-c cmd args", and nothing else */ + + /* + * We do not accept anything but "-c" followed by "cmd arg", + * where "cmd" is a very limited subset of git commands. + */ else if (argc != 3 || strcmp(argv[1], "-c")) die("What do you think I am? A shell?"); prog = argv[2]; - argv += 2; - argc -= 2; + if (!strncmp(prog, "git", 3) && isspace(prog[3])) + /* Accept "git foo" as if the caller said "git-foo". */ + prog[3] = '-'; + for (cmd = cmd_list ; cmd->name ; cmd++) { int len = strlen(cmd->name); char *arg; From 7550be0a2bbf47aaa63c806bb5d7fcb8ab197cf8 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sat, 1 Dec 2007 22:09:22 -0800 Subject: [PATCH 085/295] Prepare execv_git_cmd() for removal of builtins from the filesystem Currently, execv_git_cmd() always try running the dashed form, which means we cannot easily remove the git-foo hardlinks for built-in commands. This updates the function to always exec "git foo" form, and makes sure "git" potty does not infinitely recurse to itself. Signed-off-by: Junio C Hamano --- exec_cmd.c | 31 ++++++++++++------------------- git.c | 32 +++++++++++++++++++++++++++++++- 2 files changed, 43 insertions(+), 20 deletions(-) diff --git a/exec_cmd.c b/exec_cmd.c index e189caca62..0f8f4b5b7d 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -65,32 +65,25 @@ void setup_path(const char *cmd_path) int execv_git_cmd(const char **argv) { - struct strbuf cmd; - const char *tmp; + int argc; + const char **nargv; - strbuf_init(&cmd, 0); - strbuf_addf(&cmd, "git-%s", argv[0]); + for (argc = 0; argv[argc]; argc++) + ; /* just counting */ + nargv = xmalloc(sizeof(*nargv) * (argc + 2)); - /* - * argv[0] must be the git command, but the argv array - * belongs to the caller, and may be reused in - * subsequent loop iterations. Save argv[0] and - * restore it on error. - */ - tmp = argv[0]; - argv[0] = cmd.buf; - - trace_argv_printf(argv, "trace: exec:"); + nargv[0] = "git"; + for (argc = 0; argv[argc]; argc++) + nargv[argc + 1] = argv[argc]; + nargv[argc + 1] = NULL; + trace_argv_printf(nargv, "trace: exec:"); /* execvp() can only ever return if it fails */ - execvp(cmd.buf, (char **)argv); + execvp("git", (char **)nargv); trace_printf("trace: exec failed: %s\n", strerror(errno)); - argv[0] = tmp; - - strbuf_release(&cmd); - + free(nargv); return -1; } diff --git a/git.c b/git.c index 59f0fcc1f2..22ac5226de 100644 --- a/git.c +++ b/git.c @@ -384,6 +384,36 @@ static void handle_internal_command(int argc, const char **argv) } } +static void execv_dashed_external(const char **argv) +{ + struct strbuf cmd; + const char *tmp; + + strbuf_init(&cmd, 0); + strbuf_addf(&cmd, "git-%s", argv[0]); + + /* + * argv[0] must be the git command, but the argv array + * belongs to the caller, and may be reused in + * subsequent loop iterations. Save argv[0] and + * restore it on error. + */ + tmp = argv[0]; + argv[0] = cmd.buf; + + trace_argv_printf(argv, "trace: exec:"); + + /* execvp() can only ever return if it fails */ + execvp(cmd.buf, (char **)argv); + + trace_printf("trace: exec failed: %s\n", strerror(errno)); + + argv[0] = tmp; + + strbuf_release(&cmd); +} + + int main(int argc, const char **argv) { const char *cmd = argv[0] ? argv[0] : "git-help"; @@ -448,7 +478,7 @@ int main(int argc, const char **argv) handle_internal_command(argc, argv); /* .. then try the external ones */ - execv_git_cmd(argv); + execv_dashed_external(argv); /* It could be an alias -- this works around the insanity * of overriding "git log" with "git show" by having From 27d69a465d14b516d6a1ba287edc83606f23a5a5 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 24 Jun 2008 18:58:06 -0400 Subject: [PATCH 086/295] refactor pack structure allocation New pack structures are currently allocated in 2 different places and all members have to be initialized explicitly. This is prone to errors leading to segmentation faults as found by Teemu Likonen. Let's have a common place where this structure is allocated, and have all members explicitly initialized to zero. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- sha1_file.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) diff --git a/sha1_file.c b/sha1_file.c index 9330bc4920..b858c1308f 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -792,18 +792,28 @@ unsigned char* use_pack(struct packed_git *p, return win->base + offset; } +static struct packed_git *alloc_packed_git(int extra) +{ + struct packed_git *p = xmalloc(sizeof(*p) + extra); + memset(p, 0, sizeof(*p)); + p->pack_fd = -1; + return p; +} + struct packed_git *add_packed_git(const char *path, int path_len, int local) { struct stat st; - struct packed_git *p = xmalloc(sizeof(*p) + path_len + 2); + struct packed_git *p = alloc_packed_git(path_len + 2); /* * Make sure a corresponding .pack file exists and that * the index looks sane. */ path_len -= strlen(".idx"); - if (path_len < 1) + if (path_len < 1) { + free(p); return NULL; + } memcpy(p->pack_name, path, path_len); strcpy(p->pack_name + path_len, ".pack"); if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) { @@ -814,16 +824,7 @@ struct packed_git *add_packed_git(const char *path, int path_len, int local) /* ok, it looks sane as far as we can check without * actually mapping the pack file. */ - p->index_version = 0; - p->index_data = NULL; - p->index_size = 0; - p->num_objects = 0; - p->num_bad_objects = 0; - p->bad_object_sha1 = NULL; p->pack_size = st.st_size; - p->next = NULL; - p->windows = NULL; - p->pack_fd = -1; p->pack_local = local; p->mtime = st.st_mtime; if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1)) @@ -835,19 +836,15 @@ struct packed_git *parse_pack_index(unsigned char *sha1) { const char *idx_path = sha1_pack_index_name(sha1); const char *path = sha1_pack_name(sha1); - struct packed_git *p = xmalloc(sizeof(*p) + strlen(path) + 2); + struct packed_git *p = alloc_packed_git(strlen(path) + 1); + strcpy(p->pack_name, path); + hashcpy(p->sha1, sha1); if (check_packed_git_idx(idx_path, p)) { free(p); return NULL; } - strcpy(p->pack_name, path); - p->pack_size = 0; - p->next = NULL; - p->windows = NULL; - p->pack_fd = -1; - hashcpy(p->sha1, sha1); return p; } From ba2d0f4f35beffbf715ca652d5b36df8c0ad5ceb Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Tue, 24 Jun 2008 19:05:45 -0700 Subject: [PATCH 087/295] pre-rebase hook update This hook is what I have been using to manage topic branches in git.git, but have not been updated to the Real Thing for a while. Signed-off-by: Junio C Hamano --- templates/hooks--pre-rebase | 27 +++++++++++++++++++++++---- 1 file changed, 23 insertions(+), 4 deletions(-) diff --git a/templates/hooks--pre-rebase b/templates/hooks--pre-rebase index 981c454cda..be1b06e250 100644 --- a/templates/hooks--pre-rebase +++ b/templates/hooks--pre-rebase @@ -1,7 +1,19 @@ #!/bin/sh # -# Copyright (c) 2006 Junio C Hamano +# Copyright (c) 2006, 2008 Junio C Hamano # +# The "pre-rebase" hook is run just before "git-rebase" starts doing +# its job, and can prevent the command from running by exiting with +# non-zero status. +# +# The hook is called with the following parameters: +# +# $1 -- the upstream the series was forked from. +# $2 -- the branch being rebased (or empty when rebasing the current branch). +# +# This sample shows how to prevent topic branches that are already +# merged to 'next' branch from getting rebased, because allowing it +# would result in rebasing already published history. publish=next basebranch="$1" @@ -9,11 +21,12 @@ if test "$#" = 2 then topic="refs/heads/$2" else - topic=`git symbolic-ref HEAD` + topic=`git symbolic-ref HEAD` || + exit 0 ;# we do not interrupt rebasing detached HEAD fi -case "$basebranch,$topic" in -master,refs/heads/??/*) +case "$topic" in +refs/heads/??/*) ;; *) exit 0 ;# we do not interrupt others. @@ -23,6 +36,12 @@ esac # Now we are dealing with a topic branch being rebased # on top of master. Is it OK to rebase it? +# Does the topic really exist? +git show-ref -q "$topic" || { + echo >&2 "No such branch $topic" + exit 1 +} + # Is topic fully merged to master? not_in_master=`git-rev-list --pretty=oneline ^master "$topic"` if test -z "$not_in_master" From f98f8cbac01e0d5dbb30660d7ea70af6a1439dfd Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Tue, 24 Jun 2008 18:45:21 -0700 Subject: [PATCH 088/295] Ship sample hooks with .sample suffix We used to mark hooks we ship as samples by making them unexecutable, but some filesystems cannot tell what is executable and what is not. This makes it much more explicit. The hooks are suffixed with .sample (but now are made executable), so enabling it is still one step operation (instead of "chmod +x $hook", you would do "mv $hook.sample $hook") but now they won't get accidentally enabled on systems without executable bit. Signed-off-by: Junio C Hamano --- Documentation/githooks.txt | 3 ++- ...plypatch-msg => hooks--applypatch-msg.sample} | 2 +- ...ooks--commit-msg => hooks--commit-msg.sample} | 2 +- ...ks--post-commit => hooks--post-commit.sample} | 2 +- templates/hooks--post-receive | 16 ---------------- templates/hooks--post-receive.sample | 15 +++++++++++++++ ...ks--post-update => hooks--post-update.sample} | 2 +- ...e-applypatch => hooks--pre-applypatch.sample} | 2 +- ...ooks--pre-commit => hooks--pre-commit.sample} | 2 +- ...ooks--pre-rebase => hooks--pre-rebase.sample} | 0 ...mmit-msg => hooks--prepare-commit-msg.sample} | 2 +- .../{hooks--update => hooks--update.sample} | 2 +- 12 files changed, 25 insertions(+), 25 deletions(-) rename templates/{hooks--applypatch-msg => hooks--applypatch-msg.sample} (86%) mode change 100644 => 100755 rename templates/{hooks--commit-msg => hooks--commit-msg.sample} (93%) mode change 100644 => 100755 rename templates/{hooks--post-commit => hooks--post-commit.sample} (63%) mode change 100644 => 100755 delete mode 100644 templates/hooks--post-receive create mode 100755 templates/hooks--post-receive.sample rename templates/{hooks--post-update => hooks--post-update.sample} (63%) mode change 100644 => 100755 rename templates/{hooks--pre-applypatch => hooks--pre-applypatch.sample} (84%) mode change 100644 => 100755 rename templates/{hooks--pre-commit => hooks--pre-commit.sample} (96%) mode change 100644 => 100755 rename templates/{hooks--pre-rebase => hooks--pre-rebase.sample} (100%) mode change 100644 => 100755 rename templates/{hooks--prepare-commit-msg => hooks--prepare-commit-msg.sample} (94%) mode change 100644 => 100755 rename templates/{hooks--update => hooks--update.sample} (97%) mode change 100644 => 100755 diff --git a/Documentation/githooks.txt b/Documentation/githooks.txt index 4f06ae0ed4..262a4f1626 100644 --- a/Documentation/githooks.txt +++ b/Documentation/githooks.txt @@ -17,7 +17,8 @@ Hooks are little scripts you can place in `$GIT_DIR/hooks` directory to trigger action at certain points. When `git-init` is run, a handful example hooks are copied in the `hooks` directory of the new repository, but by default they are -all disabled. To enable a hook, make it executable with `chmod +x`. +all disabled. To enable a hook, rename it by removing its `.sample` +suffix. This document describes the currently defined hooks. diff --git a/templates/hooks--applypatch-msg b/templates/hooks--applypatch-msg.sample old mode 100644 new mode 100755 similarity index 86% rename from templates/hooks--applypatch-msg rename to templates/hooks--applypatch-msg.sample index 02de1ef84c..8b2a2fe84f --- a/templates/hooks--applypatch-msg +++ b/templates/hooks--applypatch-msg.sample @@ -7,7 +7,7 @@ # appropriate message if it wants to stop the commit. The hook is # allowed to edit the commit message file. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "applypatch-msg". . git-sh-setup test -x "$GIT_DIR/hooks/commit-msg" && diff --git a/templates/hooks--commit-msg b/templates/hooks--commit-msg.sample old mode 100644 new mode 100755 similarity index 93% rename from templates/hooks--commit-msg rename to templates/hooks--commit-msg.sample index 4ef86eb244..6ef1d29d09 --- a/templates/hooks--commit-msg +++ b/templates/hooks--commit-msg.sample @@ -6,7 +6,7 @@ # status after issuing an appropriate message if it wants to stop the # commit. The hook is allowed to edit the commit message file. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "commit-msg". # Uncomment the below to add a Signed-off-by line to the message. # Doing this in a hook is a bad idea in general, but the prepare-commit-msg diff --git a/templates/hooks--post-commit b/templates/hooks--post-commit.sample old mode 100644 new mode 100755 similarity index 63% rename from templates/hooks--post-commit rename to templates/hooks--post-commit.sample index 8be6f34ad9..22668216a3 --- a/templates/hooks--post-commit +++ b/templates/hooks--post-commit.sample @@ -3,6 +3,6 @@ # An example hook script that is called after a successful # commit is made. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "post-commit". : Nothing diff --git a/templates/hooks--post-receive b/templates/hooks--post-receive deleted file mode 100644 index b70c8fd364..0000000000 --- a/templates/hooks--post-receive +++ /dev/null @@ -1,16 +0,0 @@ -#!/bin/sh -# -# An example hook script for the post-receive event -# -# This script is run after receive-pack has accepted a pack and the -# repository has been updated. It is passed arguments in through stdin -# in the form -# -# For example: -# aa453216d1b3e49e7f6f98441fa56946ddcd6a20 68f7abf4e6f922807889f52bc043ecd31b79f814 refs/heads/master -# -# see contrib/hooks/ for an sample, or uncomment the next line (on debian) -# - - -#. /usr/share/doc/git-core/contrib/hooks/post-receive-email diff --git a/templates/hooks--post-receive.sample b/templates/hooks--post-receive.sample new file mode 100755 index 0000000000..18d2e0f727 --- /dev/null +++ b/templates/hooks--post-receive.sample @@ -0,0 +1,15 @@ +#!/bin/sh +# +# An example hook script for the "post-receive" event. +# +# The "post-receive" script is run after receive-pack has accepted a pack +# and the repository has been updated. It is passed arguments in through +# stdin in the form +# +# For example: +# aa453216d1b3e49e7f6f98441fa56946ddcd6a20 68f7abf4e6f922807889f52bc043ecd31b79f814 refs/heads/master +# +# see contrib/hooks/ for an sample, or uncomment the next line and +# rename the file to "post-receive". + +#. /usr/share/doc/git-core/contrib/hooks/post-receive-email diff --git a/templates/hooks--post-update b/templates/hooks--post-update.sample old mode 100644 new mode 100755 similarity index 63% rename from templates/hooks--post-update rename to templates/hooks--post-update.sample index bcba8937bb..5323b56b81 --- a/templates/hooks--post-update +++ b/templates/hooks--post-update.sample @@ -3,6 +3,6 @@ # An example hook script to prepare a packed repository for use over # dumb transports. # -# To enable this hook, make this file executable by "chmod +x post-update". +# To enable this hook, rename this file to "post-update". exec git-update-server-info diff --git a/templates/hooks--pre-applypatch b/templates/hooks--pre-applypatch.sample old mode 100644 new mode 100755 similarity index 84% rename from templates/hooks--pre-applypatch rename to templates/hooks--pre-applypatch.sample index eeccc934ca..b1f187c2e9 --- a/templates/hooks--pre-applypatch +++ b/templates/hooks--pre-applypatch.sample @@ -6,7 +6,7 @@ # The hook should exit with non-zero status after issuing an # appropriate message if it wants to stop the commit. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "pre-applypatch". . git-sh-setup test -x "$GIT_DIR/hooks/pre-commit" && diff --git a/templates/hooks--pre-commit b/templates/hooks--pre-commit.sample old mode 100644 new mode 100755 similarity index 96% rename from templates/hooks--pre-commit rename to templates/hooks--pre-commit.sample index b25dce6bbf..71c10f25f4 --- a/templates/hooks--pre-commit +++ b/templates/hooks--pre-commit.sample @@ -5,7 +5,7 @@ # exit with non-zero status after issuing an appropriate message if # it wants to stop the commit. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "pre-commit". # This is slightly modified from Andrew Morton's Perfect Patch. # Lines you introduce should not have trailing whitespace. diff --git a/templates/hooks--pre-rebase b/templates/hooks--pre-rebase.sample old mode 100644 new mode 100755 similarity index 100% rename from templates/hooks--pre-rebase rename to templates/hooks--pre-rebase.sample diff --git a/templates/hooks--prepare-commit-msg b/templates/hooks--prepare-commit-msg.sample old mode 100644 new mode 100755 similarity index 94% rename from templates/hooks--prepare-commit-msg rename to templates/hooks--prepare-commit-msg.sample index d3c1da34d2..aa42acfd68 --- a/templates/hooks--prepare-commit-msg +++ b/templates/hooks--prepare-commit-msg.sample @@ -7,7 +7,7 @@ # message file. If the hook fails with a non-zero status, # the commit is aborted. # -# To enable this hook, make this file executable. +# To enable this hook, rename this file to "prepare-commit-msg". # This hook includes three examples. The first comments out the # "Conflicts:" part of a merge commit. diff --git a/templates/hooks--update b/templates/hooks--update.sample old mode 100644 new mode 100755 similarity index 97% rename from templates/hooks--update rename to templates/hooks--update.sample index 4b69268fd0..93c605594f --- a/templates/hooks--update +++ b/templates/hooks--update.sample @@ -3,7 +3,7 @@ # An example hook script to blocks unannotated tags from entering. # Called by git-receive-pack with arguments: refname sha1-old sha1-new # -# To enable this hook, make this file executable by "chmod +x update". +# To enable this hook, rename this file to "update". # # Config # ------ From 98db51e624f45bcfae0a183ce86e0c1f1814269e Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Tue, 24 Jun 2008 19:58:11 -0700 Subject: [PATCH 089/295] Keep some git-* programs in $(bindir) Otherwise remote executions directly over ssh won't find them as they used to. --upload-pack and --receive-pack options _could_ be used on the client side, but things should keep working out-of-box for older clients. Later versions of clients (fetch-pack and send-pack) probably could start asking for these programs with dashless form, but that is a different topic. Signed-off-by: Junio C Hamano --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 929136ba39..8534af2279 100644 --- a/Makefile +++ b/Makefile @@ -1268,7 +1268,7 @@ install: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(gitexecdir_SQ)' $(INSTALL) $(ALL_PROGRAMS) '$(DESTDIR_SQ)$(gitexecdir_SQ)' - $(INSTALL) git$X '$(DESTDIR_SQ)$(bindir_SQ)' + $(INSTALL) git$X git-upload-pack$X git-receive-pack$X git-upload-archive$X '$(DESTDIR_SQ)$(bindir_SQ)' $(MAKE) -C templates DESTDIR='$(DESTDIR_SQ)' install $(MAKE) -C perl prefix='$(prefix_SQ)' DESTDIR='$(DESTDIR_SQ)' install ifndef NO_TCLTK From 8e21d63b02f1b26f7695ca515e51e4622a995af2 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Wed, 25 Jun 2008 01:41:34 -0400 Subject: [PATCH 090/295] clone: create intermediate directories of destination repo The shell version used to use "mkdir -p" to create the repo path, but the C version just calls "mkdir". Let's replicate the old behavior. We have to create the git and worktree leading dirs separately; while most of the time, the worktree dir contains the git dir (as .git), the user can override this using GIT_WORK_TREE. We can reuse safe_create_leading_directories, but we need to make a copy of our const buffer to do so. Since merge-recursive uses the same pattern, we can factor this out into a global function. This has two other cleanup advantages for merge-recursive: 1. mkdir_p wasn't a very good name. "mkdir -p foo/bar" actually creates bar, but this function just creates the leading directories. 2. mkdir_p took a mode argument, but it was completely ignored. Acked-by: Daniel Barkalow Signed-off-by: Junio C Hamano --- builtin-clone.c | 5 +++++ builtin-merge-recursive.c | 13 ++----------- cache.h | 1 + sha1_file.c | 9 +++++++++ t/t5601-clone.sh | 22 ++++++++++++++++++++++ 5 files changed, 39 insertions(+), 11 deletions(-) diff --git a/builtin-clone.c b/builtin-clone.c index 7190952071..b2dfe1ab5c 100644 --- a/builtin-clone.c +++ b/builtin-clone.c @@ -400,6 +400,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix) if (!option_bare) { junk_work_tree = work_tree; + if (safe_create_leading_directories_const(work_tree) < 0) + die("could not create leading directories of '%s'", + work_tree); if (mkdir(work_tree, 0755)) die("could not create work tree dir '%s'.", work_tree); set_git_work_tree(work_tree); @@ -410,6 +413,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix) setenv(CONFIG_ENVIRONMENT, xstrdup(mkpath("%s/config", git_dir)), 1); + if (safe_create_leading_directories_const(git_dir) < 0) + die("could not create leading directories of '%s'", git_dir); set_git_dir(make_absolute_path(git_dir)); fprintf(stderr, "Initialize %s\n", git_dir); diff --git a/builtin-merge-recursive.c b/builtin-merge-recursive.c index 4aa28a1bab..43bf6aa45e 100644 --- a/builtin-merge-recursive.c +++ b/builtin-merge-recursive.c @@ -481,15 +481,6 @@ static char *unique_path(const char *path, const char *branch) return newpath; } -static int mkdir_p(const char *path, unsigned long mode) -{ - /* path points to cache entries, so xstrdup before messing with it */ - char *buf = xstrdup(path); - int result = safe_create_leading_directories(buf); - free(buf); - return result; -} - static void flush_buffer(int fd, const char *buf, unsigned long size) { while (size > 0) { @@ -512,7 +503,7 @@ static int make_room_for_path(const char *path) int status; const char *msg = "failed to create path '%s'%s"; - status = mkdir_p(path, 0777); + status = safe_create_leading_directories_const(path); if (status) { if (status == -3) { /* something else exists */ @@ -583,7 +574,7 @@ static void update_file_flags(const unsigned char *sha, close(fd); } else if (S_ISLNK(mode)) { char *lnk = xmemdupz(buf, size); - mkdir_p(path, 0777); + safe_create_leading_directories_const(path); unlink(path); symlink(lnk, path); free(lnk); diff --git a/cache.h b/cache.h index a68866c1b4..a9c14da7a2 100644 --- a/cache.h +++ b/cache.h @@ -517,6 +517,7 @@ enum sharedrepo { int git_config_perm(const char *var, const char *value); int adjust_shared_perm(const char *path); int safe_create_leading_directories(char *path); +int safe_create_leading_directories_const(const char *path); char *enter_repo(char *path, int strict); static inline int is_absolute_path(const char *path) { diff --git a/sha1_file.c b/sha1_file.c index b858c1308f..b2db549d8a 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -116,6 +116,15 @@ int safe_create_leading_directories(char *path) return 0; } +int safe_create_leading_directories_const(const char *path) +{ + /* path points to cache entries, so xstrdup before messing with it */ + char *buf = xstrdup(path); + int result = safe_create_leading_directories(buf); + free(buf); + return result; +} + char *sha1_to_hex(const unsigned char *sha1) { static int bufno; diff --git a/t/t5601-clone.sh b/t/t5601-clone.sh index 593d1a3877..b642fb260b 100755 --- a/t/t5601-clone.sh +++ b/t/t5601-clone.sh @@ -30,4 +30,26 @@ test_expect_success 'clone checks out files' ' ' +test_expect_success 'clone respects GIT_WORK_TREE' ' + + GIT_WORK_TREE=worktree git clone src bare && + test -f bare/config && + test -f worktree/file + +' + +test_expect_success 'clone creates intermediate directories' ' + + git clone src long/path/to/dst && + test -f long/path/to/dst/file + +' + +test_expect_success 'clone creates intermediate directories for bare repo' ' + + git clone --bare src long/path/to/bare/dst && + test -f long/path/to/bare/dst/config + +' + test_done From 99093238bbf2cd886debf7bdb91478cb405ef66d Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 24 Jun 2008 23:17:12 -0400 Subject: [PATCH 091/295] optimize verify-pack a bit Using find_pack_entry_one() to get object offsets is rather suboptimal when nth_packed_object_offset() can be used directly. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- cache.h | 1 + pack-check.c | 4 +--- sha1_file.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/cache.h b/cache.h index a9c14da7a2..c8954ef15f 100644 --- a/cache.h +++ b/cache.h @@ -712,6 +712,7 @@ extern void close_pack_windows(struct packed_git *); extern void unuse_pack(struct pack_window **); extern struct packed_git *add_packed_git(const char *, int, int); extern const unsigned char *nth_packed_object_sha1(struct packed_git *, uint32_t); +extern off_t nth_packed_object_offset(const struct packed_git *, uint32_t); extern off_t find_pack_entry_one(const unsigned char *, struct packed_git *); extern void *unpack_entry(struct packed_git *, off_t, enum object_type *, unsigned long *); extern unsigned long unpack_object_header_gently(const unsigned char *buf, unsigned long len, enum object_type *type, unsigned long *sizep); diff --git a/pack-check.c b/pack-check.c index b99a9171c0..d6dbd4b9d8 100644 --- a/pack-check.c +++ b/pack-check.c @@ -67,9 +67,7 @@ static int verify_packfile(struct packed_git *p, entries[i].sha1 = nth_packed_object_sha1(p, i); if (!entries[i].sha1) die("internal error pack-check nth-packed-object"); - entries[i].offset = find_pack_entry_one(entries[i].sha1, p); - if (!entries[i].offset) - die("internal error pack-check find-pack-entry-one"); + entries[i].offset = nth_packed_object_offset(p, i); } qsort(entries, nr_objects, sizeof(*entries), compare_entries); diff --git a/sha1_file.c b/sha1_file.c index b2db549d8a..e79b2c1145 100644 --- a/sha1_file.c +++ b/sha1_file.c @@ -1714,7 +1714,7 @@ const unsigned char *nth_packed_object_sha1(struct packed_git *p, } } -static off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) +off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) { const unsigned char *index = p->index_data; index += 4 * 256; From 77d3ecee85dbf354d2059d7ef65d788d90db3efa Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 24 Jun 2008 23:18:17 -0400 Subject: [PATCH 092/295] move show_pack_info() where it belongs This is called when verify_pack() has its verbose argument set, and verbose in this context makes sense only for the actual 'git verify-pack' command. Therefore let's move show_pack_info() to builtin-verify-pack.c instead and remove useless verbose argument from verify_pack(). Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- builtin-fsck.c | 2 +- builtin-verify-pack.c | 63 ++++++++++++++++++++++++++++++++++++++++- http-push.c | 2 +- http-walker.c | 2 +- pack-check.c | 66 +------------------------------------------ pack.h | 2 +- 6 files changed, 67 insertions(+), 70 deletions(-) diff --git a/builtin-fsck.c b/builtin-fsck.c index 78a6e1ff71..b0f9648f86 100644 --- a/builtin-fsck.c +++ b/builtin-fsck.c @@ -585,7 +585,7 @@ int cmd_fsck(int argc, const char **argv, const char *prefix) prepare_packed_git(); for (p = packed_git; p; p = p->next) /* verify gives error messages itself */ - verify_pack(p, 0); + verify_pack(p); for (p = packed_git; p; p = p->next) { uint32_t j, num; diff --git a/builtin-verify-pack.c b/builtin-verify-pack.c index 4c515a0570..222c39e7ed 100644 --- a/builtin-verify-pack.c +++ b/builtin-verify-pack.c @@ -2,6 +2,58 @@ #include "cache.h" #include "pack.h" + +#define MAX_CHAIN 50 + +static void show_pack_info(struct packed_git *p) +{ + uint32_t nr_objects, i, chain_histogram[MAX_CHAIN+1]; + + nr_objects = p->num_objects; + memset(chain_histogram, 0, sizeof(chain_histogram)); + + for (i = 0; i < nr_objects; i++) { + const unsigned char *sha1; + unsigned char base_sha1[20]; + const char *type; + unsigned long size; + unsigned long store_size; + off_t offset; + unsigned int delta_chain_length; + + sha1 = nth_packed_object_sha1(p, i); + if (!sha1) + die("internal error pack-check nth-packed-object"); + offset = nth_packed_object_offset(p, i); + type = packed_object_info_detail(p, offset, &size, &store_size, + &delta_chain_length, + base_sha1); + printf("%s ", sha1_to_hex(sha1)); + if (!delta_chain_length) + printf("%-6s %lu %lu %"PRIuMAX"\n", + type, size, store_size, (uintmax_t)offset); + else { + printf("%-6s %lu %lu %"PRIuMAX" %u %s\n", + type, size, store_size, (uintmax_t)offset, + delta_chain_length, sha1_to_hex(base_sha1)); + if (delta_chain_length <= MAX_CHAIN) + chain_histogram[delta_chain_length]++; + else + chain_histogram[0]++; + } + } + + for (i = 0; i <= MAX_CHAIN; i++) { + if (!chain_histogram[i]) + continue; + printf("chain length = %d: %d object%s\n", i, + chain_histogram[i], chain_histogram[i] > 1 ? "s" : ""); + } + if (chain_histogram[0]) + printf("chain length > %d: %d object%s\n", MAX_CHAIN, + chain_histogram[0], chain_histogram[0] > 1 ? "s" : ""); +} + static int verify_one_pack(const char *path, int verbose) { char arg[PATH_MAX]; @@ -41,7 +93,16 @@ static int verify_one_pack(const char *path, int verbose) return error("packfile %s not found.", arg); install_packed_git(pack); - err = verify_pack(pack, verbose); + err = verify_pack(pack); + + if (verbose) { + if (err) + printf("%s: bad\n", pack->pack_name); + else { + show_pack_info(pack); + printf("%s: ok\n", pack->pack_name); + } + } return err; } diff --git a/http-push.c b/http-push.c index 665712a85d..2cd068a6f1 100644 --- a/http-push.c +++ b/http-push.c @@ -783,7 +783,7 @@ static void finish_request(struct transfer_request *request) lst = &((*lst)->next); *lst = (*lst)->next; - if (!verify_pack(target, 0)) + if (!verify_pack(target)) install_packed_git(target); else remote->can_update_info_refs = 0; diff --git a/http-walker.c b/http-walker.c index 99f397e32b..51c18f2685 100644 --- a/http-walker.c +++ b/http-walker.c @@ -795,7 +795,7 @@ static int fetch_pack(struct walker *walker, struct alt_base *repo, unsigned cha lst = &((*lst)->next); *lst = (*lst)->next; - if (verify_pack(target, 0)) + if (verify_pack(target)) return -1; install_packed_git(target); diff --git a/pack-check.c b/pack-check.c index d6dbd4b9d8..5f02a65b6e 100644 --- a/pack-check.c +++ b/pack-check.c @@ -96,62 +96,7 @@ static int verify_packfile(struct packed_git *p, return err; } - -#define MAX_CHAIN 50 - -static void show_pack_info(struct packed_git *p) -{ - uint32_t nr_objects, i, chain_histogram[MAX_CHAIN+1]; - - nr_objects = p->num_objects; - memset(chain_histogram, 0, sizeof(chain_histogram)); - - for (i = 0; i < nr_objects; i++) { - const unsigned char *sha1; - unsigned char base_sha1[20]; - const char *type; - unsigned long size; - unsigned long store_size; - off_t offset; - unsigned int delta_chain_length; - - sha1 = nth_packed_object_sha1(p, i); - if (!sha1) - die("internal error pack-check nth-packed-object"); - offset = find_pack_entry_one(sha1, p); - if (!offset) - die("internal error pack-check find-pack-entry-one"); - - type = packed_object_info_detail(p, offset, &size, &store_size, - &delta_chain_length, - base_sha1); - printf("%s ", sha1_to_hex(sha1)); - if (!delta_chain_length) - printf("%-6s %lu %lu %"PRIuMAX"\n", - type, size, store_size, (uintmax_t)offset); - else { - printf("%-6s %lu %lu %"PRIuMAX" %u %s\n", - type, size, store_size, (uintmax_t)offset, - delta_chain_length, sha1_to_hex(base_sha1)); - if (delta_chain_length <= MAX_CHAIN) - chain_histogram[delta_chain_length]++; - else - chain_histogram[0]++; - } - } - - for (i = 0; i <= MAX_CHAIN; i++) { - if (!chain_histogram[i]) - continue; - printf("chain length = %d: %d object%s\n", i, - chain_histogram[i], chain_histogram[i] > 1 ? "s" : ""); - } - if (chain_histogram[0]) - printf("chain length > %d: %d object%s\n", MAX_CHAIN, - chain_histogram[0], chain_histogram[0] > 1 ? "s" : ""); -} - -int verify_pack(struct packed_git *p, int verbose) +int verify_pack(struct packed_git *p) { off_t index_size; const unsigned char *index_base; @@ -177,14 +122,5 @@ int verify_pack(struct packed_git *p, int verbose) err |= verify_packfile(p, &w_curs); unuse_pack(&w_curs); - if (verbose) { - if (err) - printf("%s: bad\n", p->pack_name); - else { - show_pack_info(p); - printf("%s: ok\n", p->pack_name); - } - } - return err; } diff --git a/pack.h b/pack.h index b31b37608d..465071cd29 100644 --- a/pack.h +++ b/pack.h @@ -57,7 +57,7 @@ struct pack_idx_entry { extern char *write_idx_file(char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1); -extern int verify_pack(struct packed_git *, int); +extern int verify_pack(struct packed_git *); extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t); extern char *index_pack_lockfile(int fd); From c41a4a9468b0c728e77ec5d97da7bfb63776ac3f Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 24 Jun 2008 23:19:02 -0400 Subject: [PATCH 093/295] verify-pack: check packed object CRC when using index version 2 To do so, check_pack_crc() moved from builtin-pack-objects.c to pack-check.c where it is more logical to share. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- builtin-pack-objects.c | 22 ---------------------- pack-check.c | 39 +++++++++++++++++++++++++++++++++++++-- pack.h | 2 +- 3 files changed, 38 insertions(+), 25 deletions(-) diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c index 827673ce4e..28207d9b3a 100644 --- a/builtin-pack-objects.c +++ b/builtin-pack-objects.c @@ -209,28 +209,6 @@ static int check_pack_inflate(struct packed_git *p, stream.total_in == len) ? 0 : -1; } -static int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, - off_t offset, off_t len, unsigned int nr) -{ - const uint32_t *index_crc; - uint32_t data_crc = crc32(0, Z_NULL, 0); - - do { - unsigned int avail; - void *data = use_pack(p, w_curs, offset, &avail); - if (avail > len) - avail = len; - data_crc = crc32(data_crc, data, avail); - offset += avail; - len -= avail; - } while (len); - - index_crc = p->index_data; - index_crc += 2 + 256 + p->num_objects * (20/4) + nr; - - return data_crc != ntohl(*index_crc); -} - static void copy_pack_data(struct sha1file *f, struct packed_git *p, struct pack_window **w_curs, diff --git a/pack-check.c b/pack-check.c index 5f02a65b6e..f596bf2db5 100644 --- a/pack-check.c +++ b/pack-check.c @@ -4,8 +4,9 @@ struct idx_entry { - const unsigned char *sha1; off_t offset; + const unsigned char *sha1; + unsigned int nr; }; static int compare_entries(const void *e1, const void *e2) @@ -19,6 +20,28 @@ static int compare_entries(const void *e1, const void *e2) return 0; } +int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, + off_t offset, off_t len, unsigned int nr) +{ + const uint32_t *index_crc; + uint32_t data_crc = crc32(0, Z_NULL, 0); + + do { + unsigned int avail; + void *data = use_pack(p, w_curs, offset, &avail); + if (avail > len) + avail = len; + data_crc = crc32(data_crc, data, avail); + offset += avail; + len -= avail; + } while (len); + + index_crc = p->index_data; + index_crc += 2 + 256 + p->num_objects * (20/4) + nr; + + return data_crc != ntohl(*index_crc); +} + static int verify_packfile(struct packed_git *p, struct pack_window **w_curs) { @@ -61,13 +84,15 @@ static int verify_packfile(struct packed_git *p, * we do not do scan-streaming check on the pack file. */ nr_objects = p->num_objects; - entries = xmalloc(nr_objects * sizeof(*entries)); + entries = xmalloc((nr_objects + 1) * sizeof(*entries)); + entries[nr_objects].offset = pack_sig_ofs; /* first sort entries by pack offset, since unpacking them is more efficient that way */ for (i = 0; i < nr_objects; i++) { entries[i].sha1 = nth_packed_object_sha1(p, i); if (!entries[i].sha1) die("internal error pack-check nth-packed-object"); entries[i].offset = nth_packed_object_offset(p, i); + entries[i].nr = i; } qsort(entries, nr_objects, sizeof(*entries), compare_entries); @@ -76,6 +101,16 @@ static int verify_packfile(struct packed_git *p, enum object_type type; unsigned long size; + if (p->index_version > 1) { + off_t offset = entries[i].offset; + off_t len = entries[i+1].offset - offset; + unsigned int nr = entries[i].nr; + if (check_pack_crc(p, w_curs, offset, len, nr)) + err = error("index CRC mismatch for object %s " + "from %s at offset %"PRIuMAX"", + sha1_to_hex(entries[i].sha1), + p->pack_name, (uintmax_t)offset); + } data = unpack_entry(p, entries[i].offset, &type, &size); if (!data) { err = error("cannot unpack %s from %s at offset %"PRIuMAX"", diff --git a/pack.h b/pack.h index 465071cd29..76e6aa2aad 100644 --- a/pack.h +++ b/pack.h @@ -56,7 +56,7 @@ struct pack_idx_entry { }; extern char *write_idx_file(char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1); - +extern int check_pack_crc(struct packed_git *p, struct pack_window **w_curs, off_t offset, off_t len, unsigned int nr); extern int verify_pack(struct packed_git *); extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t); extern char *index_pack_lockfile(int fd); From 85fe23ed2a5d88463f5362a3e4fdd6f45a0555fd Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 24 Jun 2008 23:19:44 -0400 Subject: [PATCH 094/295] verify-pack: test for detection of index v2 object CRC mismatch Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- t/t5302-pack-index.sh | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/t/t5302-pack-index.sh b/t/t5302-pack-index.sh index 09fd917672..ecec591634 100755 --- a/t/t5302-pack-index.sh +++ b/t/t5302-pack-index.sh @@ -162,4 +162,18 @@ test_expect_success \ '[index v2] 5) pack-objects refuses to reuse corrupted data' \ '! git pack-objects test-5 /dev/null || exit 1 + done &1) && + echo "$err" | grep "CRC mismatch"' + test_done From 22c79eab2956d7f47ff2495104583a25208565ac Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 25 Jun 2008 00:24:53 -0400 Subject: [PATCH 095/295] repack.usedeltabaseoffset config option now defaults to "true" As announced for 1.6.0. Access over the native protocol by old git versions is unaffected as this capability is negociated by the protocol. Otherwise setting this config option to "false" and doing a 'git repack -a -d' is enough to remain compatible with ancient git versions (older than 1.4.4). Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- Documentation/config.txt | 8 ++++++-- git-repack.sh | 6 +----- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/Documentation/config.txt b/Documentation/config.txt index 1e09a57c8c..e37b9d6bb4 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -996,8 +996,12 @@ remotes.:: ". See linkgit:git-remote[1]. repack.usedeltabaseoffset:: - Allow linkgit:git-repack[1] to create packs that uses - delta-base offset. Defaults to false. + By default, linkgit:git-repack[1] creates packs that use + delta-base offset. If you need to share your repository with + git older than version 1.4.4, either directly or via a dumb + protocol such as http, then you need to set this option to + "false" and repack. Access from old git versions over the + native protocol are unaffected by this option. show.difftree:: The default linkgit:git-diff-tree[1] arguments to be used diff --git a/git-repack.sh b/git-repack.sh index 072d1b40f7..8c3bc134ad 100755 --- a/git-repack.sh +++ b/git-repack.sh @@ -44,11 +44,7 @@ do shift done -# Later we will default repack.UseDeltaBaseOffset to true -default_dbo=false - -case "`git config --bool repack.usedeltabaseoffset || - echo $default_dbo`" in +case "`git config --bool repack.usedeltabaseoffset || echo true`" in true) extra="$extra --delta-base-offset" ;; esac From f531e463f0471ce41c51e19074a118482f36910f Mon Sep 17 00:00:00 2001 From: Abhijit Menon-Sen Date: Wed, 25 Jun 2008 16:06:50 +0530 Subject: [PATCH 096/295] git-gui: Don't select the wrong file if the last listed file is staged. Johannes Sixt noticed that if the last file in the list was staged, my earlier patch would display the diff for the penultimate file, but show the file _before_ that as being selected. This was due to my misunderstanding the lno argument to show_diff. This patch fixes the problem: lno is not decremented in the special case to handle the last item in the list (though we still need to use $lno-1 to find the right path for the next diff). Signed-off-by: Abhijit Menon-Sen Tested-by: Johannes Sixt Signed-off-by: Shawn O. Pearce --- git-gui.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/git-gui.sh b/git-gui.sh index 980dc0b373..1bbae15a50 100755 --- a/git-gui.sh +++ b/git-gui.sh @@ -1806,14 +1806,16 @@ proc toggle_or_diff {w x y} { } else { global next_diff_p next_diff_w next_diff_i + set next_diff_w $w + if {$i < $ll} { set i [expr {$i + 1}] + set next_diff_i $i } else { + set next_diff_i $i set i [expr {$i - 1}] } - set next_diff_i $i - set next_diff_w $w set next_diff_p [lindex $file_lists($w) $i] if {$next_diff_p ne {} && $current_diff_path ne {}} { From 3015fa5846c19e79f99c1d6a49fd2510ed9291b8 Mon Sep 17 00:00:00 2001 From: Alex Riesen Date: Wed, 25 Jun 2008 20:35:13 +0200 Subject: [PATCH 097/295] Fix use of "perl -i" on Windows The perldiag(1) has following to say about this: "Can't do inplace edit without backup" (F) You're on a system such as MS-DOS that gets confused if you try reading from a deleted (but still opened) file. You have to say -i.bak, or some such. Signed-off-by: Alex Riesen Signed-off-by: Junio C Hamano --- t/t5303-pack-corruption-resilience.sh | 4 ++-- t/t9106-git-svn-dcommit-clobber-series.sh | 8 ++++---- templates/hooks--prepare-commit-msg.sample | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/t/t5303-pack-corruption-resilience.sh b/t/t5303-pack-corruption-resilience.sh index b0f5693482..31b20b21d2 100755 --- a/t/t5303-pack-corruption-resilience.sh +++ b/t/t5303-pack-corruption-resilience.sh @@ -90,7 +90,7 @@ test_expect_success \ 'create_new_pack && git prune-packed && chmod +w ${pack}.pack && - perl -i -pe "s/ base /abcdef/" ${pack}.pack && + perl -i.bak -pe "s/ base /abcdef/" ${pack}.pack && test_must_fail git cat-file blob $blob_1 > /dev/null && test_must_fail git cat-file blob $blob_2 > /dev/null && test_must_fail git cat-file blob $blob_3 > /dev/null' @@ -138,7 +138,7 @@ test_expect_success \ 'create_new_pack && git prune-packed && chmod +w ${pack}.pack && - perl -i -pe "s/ delta1 /abcdefgh/" ${pack}.pack && + perl -i.bak -pe "s/ delta1 /abcdefgh/" ${pack}.pack && git cat-file blob $blob_1 > /dev/null && test_must_fail git cat-file blob $blob_2 > /dev/null && test_must_fail git cat-file blob $blob_3 > /dev/null' diff --git a/t/t9106-git-svn-dcommit-clobber-series.sh b/t/t9106-git-svn-dcommit-clobber-series.sh index a400dc7966..f8f4718c36 100755 --- a/t/t9106-git-svn-dcommit-clobber-series.sh +++ b/t/t9106-git-svn-dcommit-clobber-series.sh @@ -20,8 +20,8 @@ test_expect_success '(supposedly) non-conflicting change from SVN' ' test x"`sed -n -e 61p < file`" = x61 && svn co "$svnrepo" tmp && cd tmp && - perl -i -p -e "s/^58$/5588/" file && - perl -i -p -e "s/^61$/6611/" file && + perl -i.bak -p -e "s/^58$/5588/" file && + perl -i.bak -p -e "s/^61$/6611/" file && poke file && test x"`sed -n -e 58p < file`" = x5588 && test x"`sed -n -e 61p < file`" = x6611 && @@ -40,8 +40,8 @@ test_expect_success 'some unrelated changes to git' " test_expect_success 'change file but in unrelated area' " test x\"\`sed -n -e 4p < file\`\" = x4 && test x\"\`sed -n -e 7p < file\`\" = x7 && - perl -i -p -e 's/^4\$/4444/' file && - perl -i -p -e 's/^7\$/7777/' file && + perl -i.bak -p -e 's/^4\$/4444/' file && + perl -i.bak -p -e 's/^7\$/7777/' file && test x\"\`sed -n -e 4p < file\`\" = x4444 && test x\"\`sed -n -e 7p < file\`\" = x7777 && git commit -m '4 => 4444, 7 => 7777' file && diff --git a/templates/hooks--prepare-commit-msg.sample b/templates/hooks--prepare-commit-msg.sample index aa42acfd68..365242499d 100755 --- a/templates/hooks--prepare-commit-msg.sample +++ b/templates/hooks--prepare-commit-msg.sample @@ -22,10 +22,10 @@ case "$2,$3" in merge,) - perl -i -ne 's/^/# /, s/^# #/#/ if /^Conflicts/ .. /#/; print' "$1" ;; + perl -i.bak -ne 's/^/# /, s/^# #/#/ if /^Conflicts/ .. /#/; print' "$1" ;; # ,|template,) -# perl -i -pe ' +# perl -i.bak -pe ' # print "\n" . `git diff --cached --name-status -r` # if /^#/ && $first++ == 0' "$1" ;; From dfc8f39e4346d000052c39ef7cb6bfe8fdb48c51 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 25 Jun 2008 18:16:36 -0700 Subject: [PATCH 098/295] Allow "git-reset path" when unambiguous Resetting a selected set of index entries is done with "git reset -- paths" syntax, but we did not allow -- to be omitted even when the command is unambiguous. This updates the command to follow the general rule: * When -- appears, revs come before it, and paths come after it; * When there is no --, earlier ones are revs and the rest are paths, and we need to guess. When lack of -- marker forces us to guess, we protect from user errors and typoes by making sure what we treat as revs do not appear as filenames in the work tree, and what we treat as paths do appear as filenames in the work tree, and by erroring out if that is not the case. We tell the user to disambiguate by using -- in such a case. which is employed elsewhere in the system. When this rule is applied to "reset", because we can have only zero or one rev to the command, the check can be slightly simpler than other programs. We have to check only the first one or two tokens after the command name and options, and when they are: -- A: no explicit rev given; "A" and whatever follows it are paths. A --: explicit rev "A" given and whatever follows the "--" are paths. A B: "A" could be rev or path and we need to guess. "B" could be missing but if exists that (and everything that follows) would be paths. So we apply the guess only in the last case and only to "A" (not "B" and what comes after it). * As long as "A" is unambiguously a path, index entries for "A", "B" (and everything that follows) are reset to the HEAD revision. * If "A" is unambiguously a rev, on the other hand, the index entries for "B" (and everything that follows) are reset to the "A" revision. Signed-off-by: Junio C Hamano --- builtin-reset.c | 39 ++++++++++++++++++++++++++++++++++----- t/t7102-reset.sh | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+), 5 deletions(-) diff --git a/builtin-reset.c b/builtin-reset.c index f34acb1915..a0321694c5 100644 --- a/builtin-reset.c +++ b/builtin-reset.c @@ -194,8 +194,40 @@ int cmd_reset(int argc, const char **argv, const char *prefix) reflog_action = args_to_str(argv); setenv("GIT_REFLOG_ACTION", reflog_action, 0); - if (i < argc && strcmp(argv[i], "--")) - rev = argv[i++]; + /* + * Possible arguments are: + * + * git reset [-opts] ... + * git reset [-opts] -- ... + * git reset [-opts] -- ... + * git reset [-opts] ... + * + * At this point, argv[i] points immediately after [-opts]. + */ + + if (i < argc) { + if (!strcmp(argv[i], "--")) { + i++; /* reset to HEAD, possibly with paths */ + } else if (i + 1 < argc && !strcmp(argv[i+1], "--")) { + rev = argv[i]; + i += 2; + } + /* + * Otherwise, argv[i] could be either or and + * has to be unambigous. + */ + else if (!get_sha1(argv[i], sha1)) { + /* + * Ok, argv[i] looks like a rev; it should not + * be a filename. + */ + verify_non_filename(prefix, argv[i]); + rev = argv[i++]; + } else { + /* Otherwise we treat this as a filename */ + verify_filename(prefix, argv[i]); + } + } if (get_sha1(rev, sha1)) die("Failed to resolve '%s' as a valid ref.", rev); @@ -205,9 +237,6 @@ int cmd_reset(int argc, const char **argv, const char *prefix) die("Could not parse object '%s'.", rev); hashcpy(sha1, commit->object.sha1); - if (i < argc && !strcmp(argv[i], "--")) - i++; - /* git reset tree [--] paths... can be used to * load chosen paths from the tree into the index without * affecting the working tree nor HEAD. */ diff --git a/t/t7102-reset.sh b/t/t7102-reset.sh index 39ba14148c..96d15083fb 100755 --- a/t/t7102-reset.sh +++ b/t/t7102-reset.sh @@ -428,4 +428,51 @@ test_expect_success '--mixed refreshes the index' ' test_cmp expect output ' +test_expect_success 'disambiguation (1)' ' + + git reset --hard && + >secondfile && + git add secondfile && + test_must_fail git reset secondfile && + test -z "$(git diff --cached --name-only)" && + test -f secondfile && + test ! -s secondfile + +' + +test_expect_success 'disambiguation (2)' ' + + git reset --hard && + >secondfile && + git add secondfile && + rm -f secondfile && + test_must_fail git reset secondfile && + test -n "$(git diff --cached --name-only -- secondfile)" && + test ! -f secondfile + +' + +test_expect_success 'disambiguation (3)' ' + + git reset --hard && + >secondfile && + git add secondfile && + rm -f secondfile && + test_must_fail git reset HEAD secondfile && + test -z "$(git diff --cached --name-only)" && + test ! -f secondfile + +' + +test_expect_success 'disambiguation (4)' ' + + git reset --hard && + >secondfile && + git add secondfile && + rm -f secondfile && + test_must_fail git reset -- secondfile && + test -z "$(git diff --cached --name-only)" && + test ! -f secondfile +' + test_done From c0a5e2d477baa9d3ebf7d3303a7d2b5dbc7c2ffe Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Wed, 25 Jun 2008 00:25:53 -0400 Subject: [PATCH 099/295] pack.indexversion config option now defaults to 2 As announced for 1.6.0. Git older than version 1.5.2 (or any other git version with this option set to 1) may revert to version 1 of the pack index by manually deleting all .idx files and recreating them using 'git index-pack'. Communication over the git native protocol is unaffected since the pack index is never transferred. Signed-off-by: Nicolas Pitre Signed-off-by: Junio C Hamano --- Documentation/asciidoc.conf | 1 + Documentation/config.txt | 14 +++++++++++--- pack-write.c | 2 +- 3 files changed, 13 insertions(+), 4 deletions(-) diff --git a/Documentation/asciidoc.conf b/Documentation/asciidoc.conf index 10c1a151a4..40d43b78ee 100644 --- a/Documentation/asciidoc.conf +++ b/Documentation/asciidoc.conf @@ -8,6 +8,7 @@ # the command. [attributes] +asterisk=* plus=+ caret=^ startsb=[ diff --git a/Documentation/config.txt b/Documentation/config.txt index e37b9d6bb4..e523997e7e 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -937,9 +937,17 @@ pack.indexVersion:: legacy pack index used by Git versions prior to 1.5.2, and 2 for the new pack index with capabilities for packs larger than 4 GB as well as proper protection against the repacking of corrupted - packs. Version 2 is selected and this config option ignored - whenever the corresponding pack is larger than 2 GB. Otherwise - the default is 1. + packs. Version 2 is the default. Note that version 2 is enforced + and this config option ignored whenever the corresponding pack is + larger than 2 GB. ++ +If you have an old git that does not understand the version 2 `{asterisk}.idx` file, +cloning or fetching over a non native protocol (e.g. "http" and "rsync") +that will copy both `{asterisk}.pack` file and corresponding `{asterisk}.idx` file from the +other side may give you a repository that cannot be accessed with your +older version of git. If the `{asterisk}.pack` file is smaller than 2 GB, however, +you can use linkgit:git-index-pack[1] on the *.pack file to regenerate +the `{asterisk}.idx` file. pack.packSizeLimit:: The default maximum size of a pack. This setting only affects diff --git a/pack-write.c b/pack-write.c index f52cabe838..a8f0269936 100644 --- a/pack-write.c +++ b/pack-write.c @@ -2,7 +2,7 @@ #include "pack.h" #include "csum-file.h" -uint32_t pack_idx_default_version = 1; +uint32_t pack_idx_default_version = 2; uint32_t pack_idx_off32_limit = 0x7fffffff; static int sha1_compare(const void *_a, const void *_b) From 300913bd448def6fe2f943f534a172259725e7c6 Mon Sep 17 00:00:00 2001 From: Kevin Ballard Date: Wed, 25 Jun 2008 15:44:40 -0700 Subject: [PATCH 100/295] git-send-email: Accept fifos as well as files When a fifo is given, validation must be skipped because we can't read the fifo twice. Ideally git-send-email would cache the read data instead of attempting to read twice, but for now just skip validation. Signed-off-by: Kevin Ballard Signed-off-by: Junio C Hamano --- git-send-email.perl | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/git-send-email.perl b/git-send-email.perl index 0b04ba32f0..16d437526a 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -393,7 +393,7 @@ for my $f (@ARGV) { push @files, grep { -f $_ } map { +$f . "/" . $_ } sort readdir(DH); - } elsif (-f $f) { + } elsif (-f $f or -p $f) { push @files, $f; } else { @@ -403,8 +403,10 @@ for my $f (@ARGV) { if (!$no_validate) { foreach my $f (@files) { - my $error = validate_patch($f); - $error and die "fatal: $f: $error\nwarning: no patches were sent\n"; + unless (-p $f) { + my $error = validate_patch($f); + $error and die "fatal: $f: $error\nwarning: no patches were sent\n"; + } } } From f6bebd121ac531871c4cee576b0baf6814099425 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Wed, 25 Jun 2008 21:42:43 +0200 Subject: [PATCH 101/295] git-send-email: add support for TLS via Net::SMTP::SSL We do this by handing over the Net::SMTP instance to Net::SMTP::SSL, which avoids Net::SMTP::TLS and its weird error checking. This trick is due to Brian Evins. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- Documentation/git-send-email.txt | 16 ++++++++++++---- git-send-email.perl | 33 +++++++++++++++++++++++++++----- 2 files changed, 40 insertions(+), 9 deletions(-) diff --git a/Documentation/git-send-email.txt b/Documentation/git-send-email.txt index 251d661afd..dc7eb7bd4e 100644 --- a/Documentation/git-send-email.txt +++ b/Documentation/git-send-email.txt @@ -133,10 +133,13 @@ or on the command line. If a username has been specified (with specified (with --smtp-pass or a configuration variable), then the user is prompted for a password while the input is masked for privacy. +--smtp-encryption:: + Specify the encryption to use, either 'ssl' or 'tls'. Any other + value reverts to plain SMTP. Default is the value of + 'sendemail.smtpencryption'. + --smtp-ssl:: - If set, connects to the SMTP server using SSL. - Default is the value of the 'sendemail.smtpssl' configuration value; - if that is unspecified, does not use SSL. + Legacy alias for '--smtp-encryption=ssl'. --subject:: Specify the initial subject of the email thread. @@ -229,8 +232,13 @@ sendemail.smtpuser:: sendemail.smtppass:: Default SMTP-AUTH password. +sendemail.smtpencryption:: + Default encryption method. Use 'ssl' for SSL (and specify an + appropriate port), or 'tls' for TLS. Takes precedence over + 'smtpssl' if both are specified. + sendemail.smtpssl:: - Boolean value specifying the default to the '--smtp-ssl' parameter. + Legacy boolean that sets 'smtpencryption=ssl' if enabled. Author ------ diff --git a/git-send-email.perl b/git-send-email.perl index 0b04ba32f0..763072042d 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -84,7 +84,10 @@ Options: --smtp-pass The password for SMTP-AUTH. - --smtp-ssl If set, connects to the SMTP server using SSL. + --smtp-encryption Specify 'tls' for STARTTLS encryption, or 'ssl' for SSL. + Any other value disables the feature. + + --smtp-ssl Synonym for '--smtp-encryption=ssl'. Deprecated. --suppress-cc Suppress the specified category of auto-CC. The category can be one of 'author' for the patch author, 'self' to @@ -184,7 +187,7 @@ my ($quiet, $dry_run) = (0, 0); # Variables with corresponding config settings my ($thread, $chain_reply_to, $suppress_from, $signed_off_cc, $cc_cmd); -my ($smtp_server, $smtp_server_port, $smtp_authuser, $smtp_ssl); +my ($smtp_server, $smtp_server_port, $smtp_authuser, $smtp_encryption); my ($identity, $aliasfiletype, @alias_files, @smtp_host_parts); my ($no_validate); my (@suppress_cc); @@ -194,7 +197,6 @@ my %config_bool_settings = ( "chainreplyto" => [\$chain_reply_to, 1], "suppressfrom" => [\$suppress_from, undef], "signedoffcc" => [\$signed_off_cc, undef], - "smtpssl" => [\$smtp_ssl, 0], ); my %config_settings = ( @@ -249,7 +251,8 @@ my $rc = GetOptions("sender|from=s" => \$sender, "smtp-server-port=s" => \$smtp_server_port, "smtp-user=s" => \$smtp_authuser, "smtp-pass:s" => \$smtp_authpass, - "smtp-ssl!" => \$smtp_ssl, + "smtp-ssl" => sub { $smtp_encryption = 'ssl' }, + "smtp-encryption=s" => \$smtp_encryption, "identity=s" => \$identity, "compose" => \$compose, "quiet" => \$quiet, @@ -289,6 +292,15 @@ sub read_config { $$target = Git::config(@repo, "$prefix.$setting") unless (defined $$target); } } + + if (!defined $smtp_encryption) { + my $enc = Git::config(@repo, "$prefix.smtpencryption"); + if (defined $enc) { + $smtp_encryption = $enc; + } elsif (Git::config_bool(@repo, "$prefix.smtpssl")) { + $smtp_encryption = 'ssl'; + } + } } # read configuration from [sendemail "$identity"], fall back on [sendemail] @@ -738,7 +750,7 @@ X-Mailer: git-send-email $gitversion die "The required SMTP server is not properly defined." } - if ($smtp_ssl) { + if ($smtp_encryption eq 'ssl') { $smtp_server_port ||= 465; # ssmtp require Net::SMTP::SSL; $smtp ||= Net::SMTP::SSL->new($smtp_server, Port => $smtp_server_port); @@ -748,6 +760,17 @@ X-Mailer: git-send-email $gitversion $smtp ||= Net::SMTP->new((defined $smtp_server_port) ? "$smtp_server:$smtp_server_port" : $smtp_server); + if ($smtp_encryption eq 'tls') { + require Net::SMTP::SSL; + $smtp->command('STARTTLS'); + $smtp->response(); + if ($smtp->code == 220) { + $smtp = Net::SMTP::SSL->start_SSL($smtp) + or die "STARTTLS failed! ".$smtp->message; + } else { + die "Server does not support STARTTLS! ".$smtp->message; + } + } } if (!$smtp) { From f9a08f618f3aa586a6859283dd2d0cd5a8dc4f96 Mon Sep 17 00:00:00 2001 From: Dmitry Potapov Date: Thu, 26 Jun 2008 03:14:31 +0400 Subject: [PATCH 102/295] update-hook-example: optionally allow non-fast-forward Sometimes it is desirable to have non-fast-forward branches in a shared repository. A typical example of that is the 'pu' branch. This patch extends the format of allowed-users and allow-groups files by using the '+' sign at the beginning as the mark that non-fast-forward pushes are permitted to the branch. Signed-off-by: Dmitry Potapov Signed-off-by: Junio C Hamano --- Documentation/howto/update-hook-example.txt | 86 +++++++++++++-------- 1 file changed, 53 insertions(+), 33 deletions(-) diff --git a/Documentation/howto/update-hook-example.txt b/Documentation/howto/update-hook-example.txt index a8d3bae408..8b2ec502f4 100644 --- a/Documentation/howto/update-hook-example.txt +++ b/Documentation/howto/update-hook-example.txt @@ -65,7 +65,7 @@ function info { # Implement generic branch and tag policies. # - Tags should not be updated once created. -# - Branches should only be fast-forwarded. +# - Branches should only be fast-forwarded unless their pattern starts with '+' case "$1" in refs/tags/*) git rev-parse --verify -q "$1" && @@ -80,7 +80,7 @@ case "$1" in mb=$(git-merge-base "$2" "$3") case "$mb,$2" in "$2,$mb") info "Update is fast-forward" ;; - *) deny >/dev/null "This is not a fast-forward update." ;; + *) noff=y; info "This is not a fast-forward update.";; esac fi ;; @@ -95,21 +95,30 @@ allowed_users_file=$GIT_DIR/info/allowed-users username=$(id -u -n) info "The user is: '$username'" -if [ -f "$allowed_users_file" ]; then +if test -f "$allowed_users_file" +then rc=$(cat $allowed_users_file | grep -v '^#' | grep -v '^$' | - while read head_pattern user_patterns; do - matchlen=$(expr "$1" : "$head_pattern") - if [ "$matchlen" == "${#1}" ]; then - info "Found matching head pattern: '$head_pattern'" - for user_pattern in $user_patterns; do - info "Checking user: '$username' against pattern: '$user_pattern'" - matchlen=$(expr "$username" : "$user_pattern") - if [ "$matchlen" == "${#username}" ]; then - grant "Allowing user: '$username' with pattern: '$user_pattern'" - fi - done - deny "The user is not in the access list for this branch" - fi + while read heads user_patterns + do + # does this rule apply to us? + head_pattern=${heads#+} + matchlen=$(expr "$1" : "${head_pattern#+}") + test "$matchlen" = ${#1} || continue + + # if non-ff, $heads must be with the '+' prefix + test -n "$noff" && + test "$head_pattern" = "$heads" && continue + + info "Found matching head pattern: '$head_pattern'" + for user_pattern in $user_patterns; do + info "Checking user: '$username' against pattern: '$user_pattern'" + matchlen=$(expr "$username" : "$user_pattern") + if test "$matchlen" = "${#username}" + then + grant "Allowing user: '$username' with pattern: '$user_pattern'" + fi + done + deny "The user is not in the access list for this branch" done ) case "$rc" in @@ -124,23 +133,32 @@ groups=$(id -G -n) info "The user belongs to the following groups:" info "'$groups'" -if [ -f "$allowed_groups_file" ]; then +if test -f "$allowed_groups_file" +then rc=$(cat $allowed_groups_file | grep -v '^#' | grep -v '^$' | - while read head_pattern group_patterns; do - matchlen=$(expr "$1" : "$head_pattern") - if [ "$matchlen" == "${#1}" ]; then - info "Found matching head pattern: '$head_pattern'" - for group_pattern in $group_patterns; do - for groupname in $groups; do - info "Checking group: '$groupname' against pattern: '$group_pattern'" - matchlen=$(expr "$groupname" : "$group_pattern") - if [ "$matchlen" == "${#groupname}" ]; then - grant "Allowing group: '$groupname' with pattern: '$group_pattern'" - fi - done + while read heads group_patterns + do + # does this rule apply to us? + head_pattern=${heads#+} + matchlen=$(expr "$1" : "${head_pattern#+}") + test "$matchlen" = ${#1} || continue + + # if non-ff, $heads must be with the '+' prefix + test -n "$noff" && + test "$head_pattern" = "$heads" && continue + + info "Found matching head pattern: '$head_pattern'" + for group_pattern in $group_patterns; do + for groupname in $groups; do + info "Checking group: '$groupname' against pattern: '$group_pattern'" + matchlen=$(expr "$groupname" : "$group_pattern") + if test "$matchlen" = "${#groupname}" + then + grant "Allowing group: '$groupname' with pattern: '$group_pattern'" + fi done - deny "None of the user's groups are in the access list for this branch" - fi + done + deny "None of the user's groups are in the access list for this branch" done ) case "$rc" in @@ -159,6 +177,7 @@ allowed-groups, to describe which heads can be pushed into by whom. The format of each file would look like this: refs/heads/master junio + +refs/heads/pu junio refs/heads/cogito$ pasky refs/heads/bw/.* linus refs/heads/tmp/.* .* @@ -166,7 +185,8 @@ whom. The format of each file would look like this: With this, Linus can push or create "bw/penguin" or "bw/zebra" or "bw/panda" branches, Pasky can do only "cogito", and JC can -do master branch and make versioned tags. And anybody can do -tmp/blah branches. +do master and pu branches and make versioned tags. And anybody +can do tmp/blah branches. The '+' sign at the pu record means +that JC can make non-fast-forward pushes on it. ------------ From 6ed807f8432c558ef102c94cb2e8ae4e03c48d4e Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 1 Dec 2007 22:00:56 +0100 Subject: [PATCH 103/295] Windows: A rudimentary poll() emulation. This emulation of poll() is by far not general. It assumes that the fds that are to be waited for are connected to pipes. The pipes are polled in a loop until data becomes available in at least one of them. If only a single fd is waited for, the implementation actually does not wait at all, but assumes that a subsequent read() will block. In order not to needlessly burn CPU time, the CPU is yielded to other processes before the next round in the poll loop using Sleep(0). Note that any sleep timeout greater than zero will reduce the efficiency by a magnitude. Signed-off-by: Johannes Sixt --- compat/mingw.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 56 insertions(+), 1 deletion(-) diff --git a/compat/mingw.c b/compat/mingw.c index 7f89a6cb87..2677e78626 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -101,7 +101,62 @@ int pipe(int filedes[2]) int poll(struct pollfd *ufds, unsigned int nfds, int timeout) { - return -1; + int i, pending; + + if (timeout != -1) + return errno = EINVAL, error("poll timeout not supported"); + + /* When there is only one fd to wait for, then we pretend that + * input is available and let the actual wait happen when the + * caller invokes read(). + */ + if (nfds == 1) { + if (!(ufds[0].events & POLLIN)) + return errno = EINVAL, error("POLLIN not set"); + ufds[0].revents = POLLIN; + return 0; + } + +repeat: + pending = 0; + for (i = 0; i < nfds; i++) { + DWORD avail = 0; + HANDLE h = (HANDLE) _get_osfhandle(ufds[i].fd); + if (h == INVALID_HANDLE_VALUE) + return -1; /* errno was set */ + + if (!(ufds[i].events & POLLIN)) + return errno = EINVAL, error("POLLIN not set"); + + /* this emulation works only for pipes */ + if (!PeekNamedPipe(h, NULL, 0, NULL, &avail, NULL)) { + int err = GetLastError(); + if (err == ERROR_BROKEN_PIPE) { + ufds[i].revents = POLLHUP; + pending++; + } else { + errno = EINVAL; + return error("PeekNamedPipe failed," + " GetLastError: %u", err); + } + } else if (avail) { + ufds[i].revents = POLLIN; + pending++; + } else + ufds[i].revents = 0; + } + if (!pending) { + /* The only times that we spin here is when the process + * that is connected through the pipes is waiting for + * its own input data to become available. But since + * the process (pack-objects) is itself CPU intensive, + * it will happily pick up the time slice that we are + * relinguishing here. + */ + Sleep(0); + goto repeat; + } + return 0; } struct tm *gmtime_r(const time_t *timep, struct tm *result) From be501813d25bedc1a441940f349fb91bd9fa4ef6 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 30 Nov 2007 22:51:10 +0100 Subject: [PATCH 104/295] Windows: Disambiguate DOS style paths from SSH URLs. If on Windows a path is specified as C:/path, then this is also a valid SSH URL. To disambiguate between the two interpretations we take an URL that looks like a path with a drive letter as a local URL. Signed-off-by: Johannes Sixt --- connect.c | 2 +- transport.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/connect.c b/connect.c index e92af29735..574f42fa47 100644 --- a/connect.c +++ b/connect.c @@ -529,7 +529,7 @@ struct child_process *git_connect(int fd[2], const char *url_orig, end = host; path = strchr(end, c); - if (path) { + if (path && !has_dos_drive_prefix(end)) { if (c == ':') { protocol = PROTO_SSH; *path++ = '\0'; diff --git a/transport.c b/transport.c index 3ff851935f..4145eed979 100644 --- a/transport.c +++ b/transport.c @@ -709,7 +709,8 @@ static int is_local(const char *url) { const char *colon = strchr(url, ':'); const char *slash = strchr(url, '/'); - return !colon || (slash && slash < colon); + return !colon || (slash && slash < colon) || + has_dos_drive_prefix(url); } static int is_file(const char *url) From 618ebe9ff997d27714487c4a4232720be240badc Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 8 Dec 2007 22:19:14 +0100 Subject: [PATCH 105/295] Windows: Implement asynchronous functions as threads. In upload-pack we must explicitly close the output channel of rev-list. (On Unix, the channel is closed automatically because process that runs rev-list terminates.) Signed-off-by: Johannes Sixt --- run-command.c | 29 ++++++++++++++++++++++++++++- run-command.h | 5 +++++ upload-pack.c | 2 ++ 3 files changed, 35 insertions(+), 1 deletion(-) diff --git a/run-command.c b/run-command.c index dd8b7751ce..63238e412a 100644 --- a/run-command.c +++ b/run-command.c @@ -288,13 +288,23 @@ int run_command_v_opt_cd_env(const char **argv, int opt, const char *dir, const return run_command(&cmd); } +#ifdef __MINGW32__ +static __stdcall unsigned run_thread(void *data) +{ + struct async *async = data; + return async->proc(async->fd_for_proc, async->data); +} +#endif + int start_async(struct async *async) { int pipe_out[2]; if (pipe(pipe_out) < 0) return error("cannot create pipe: %s", strerror(errno)); + async->out = pipe_out[0]; +#ifndef __MINGW32__ async->pid = fork(); if (async->pid < 0) { error("fork (async) failed: %s", strerror(errno)); @@ -305,16 +315,33 @@ int start_async(struct async *async) close(pipe_out[0]); exit(!!async->proc(pipe_out[1], async->data)); } - async->out = pipe_out[0]; close(pipe_out[1]); +#else + async->fd_for_proc = pipe_out[1]; + async->tid = (HANDLE) _beginthreadex(NULL, 0, run_thread, async, 0, NULL); + if (!async->tid) { + error("cannot create thread: %s", strerror(errno)); + close_pair(pipe_out); + return -1; + } +#endif return 0; } int finish_async(struct async *async) { +#ifndef __MINGW32__ int ret = 0; if (wait_or_whine(async->pid)) ret = error("waitpid (async) failed"); +#else + DWORD ret = 0; + if (WaitForSingleObject(async->tid, INFINITE) != WAIT_OBJECT_0) + ret = error("waiting for thread failed: %lu", GetLastError()); + else if (!GetExitCodeThread(async->tid, &ret)) + ret = error("cannot get thread exit code: %lu", GetLastError()); + CloseHandle(async->tid); +#endif return ret; } diff --git a/run-command.h b/run-command.h index debe3074b5..5203a9ebb1 100644 --- a/run-command.h +++ b/run-command.h @@ -76,7 +76,12 @@ struct async { int (*proc)(int fd, void *data); void *data; int out; /* caller reads from here and closes it */ +#ifndef __MINGW32__ pid_t pid; +#else + HANDLE tid; + int fd_for_proc; +#endif }; int start_async(struct async *async); diff --git a/upload-pack.c b/upload-pack.c index b46dd365ea..9f82941f8b 100644 --- a/upload-pack.c +++ b/upload-pack.c @@ -135,6 +135,8 @@ static int do_rev_list(int fd, void *create_full_pack) die("revision walk setup failed"); mark_edges_uninteresting(revs.commits, &revs, show_edge); traverse_commit_list(&revs, show_commit, show_object); + fflush(pack_pipe); + fclose(pack_pipe); return 0; } From 87bddba9924045e39e988d9704714db90abd5619 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 30 Nov 2007 22:06:30 +0100 Subject: [PATCH 106/295] Windows: Work around incompatible sort and find. If the PATH lists the Windows system directories before the MSYS directories, Windows's own incompatible sort and find commands would be picked up. We implement these commands as functions and call the real tools by absolute path. Signed-off-by: Johannes Sixt --- git-sh-setup.sh | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/git-sh-setup.sh b/git-sh-setup.sh index a44b1c74a3..9cceb21a82 100755 --- a/git-sh-setup.sh +++ b/git-sh-setup.sh @@ -142,3 +142,16 @@ then } : ${GIT_OBJECT_DIRECTORY="$GIT_DIR/objects"} fi + +# Fix some commands on Windows +case $(uname -s) in +*MINGW*) + # Windows has its own (incompatible) sort and find + sort () { + /usr/bin/sort "$@" + } + find () { + /usr/bin/find "$@" + } + ;; +esac From 746fb8574459798d127e3f9cf782ccb8e31c9e45 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Wed, 26 Dec 2007 13:51:18 +0100 Subject: [PATCH 107/295] Windows: Implement wrappers for gethostbyname(), socket(), and connect(). gethostbyname() is the first function that calls into the Winsock library, and it is wrapped only to initialize the library. socket() is wrapped for two reasons: - Windows's socket() creates things that are like low-level file handles, and they must be converted into file descriptors first. - And these handles cannot be used with plain ReadFile()/WriteFile() because they are opened for "overlapped IO". We have to use WSASocket() to create non-overlapped IO sockets. connect() must be wrapped because Windows's connect() expects the low-level sockets, not file descriptors, and we must first unwrap the file descriptor before we can pass it on to Windows's connect(). Signed-off-by: Johannes Sixt --- compat/mingw.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ compat/mingw.h | 9 +++++++++ 2 files changed, 55 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 2677e78626..d184c582eb 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -432,6 +432,52 @@ char **env_setenv(char **env, const char *name) return env; } +/* this is the first function to call into WS_32; initialize it */ +#undef gethostbyname +struct hostent *mingw_gethostbyname(const char *host) +{ + WSADATA wsa; + + if (WSAStartup(MAKEWORD(2,2), &wsa)) + die("unable to initialize winsock subsystem, error %d", + WSAGetLastError()); + atexit((void(*)(void)) WSACleanup); + return gethostbyname(host); +} + +int mingw_socket(int domain, int type, int protocol) +{ + int sockfd; + SOCKET s = WSASocket(domain, type, protocol, NULL, 0, 0); + if (s == INVALID_SOCKET) { + /* + * WSAGetLastError() values are regular BSD error codes + * biased by WSABASEERR. + * However, strerror() does not know about networking + * specific errors, which are values beginning at 38 or so. + * Therefore, we choose to leave the biased error code + * in errno so that _if_ someone looks up the code somewhere, + * then it is at least the number that are usually listed. + */ + errno = WSAGetLastError(); + return -1; + } + /* convert into a file descriptor */ + if ((sockfd = _open_osfhandle(s, O_RDWR|O_BINARY)) < 0) { + closesocket(s); + return error("unable to make a socket file descriptor: %s", + strerror(errno)); + } + return sockfd; +} + +#undef connect +int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz) +{ + SOCKET s = (SOCKET)_get_osfhandle(sockfd); + return connect(s, sa, sz); +} + #undef rename int mingw_rename(const char *pold, const char *pnew) { diff --git a/compat/mingw.h b/compat/mingw.h index 0879894c68..1017632a24 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -148,6 +148,15 @@ int mingw_open (const char *filename, int oflags, ...); char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd +struct hostent *mingw_gethostbyname(const char *host); +#define gethostbyname mingw_gethostbyname + +int mingw_socket(int domain, int type, int protocol); +#define socket mingw_socket + +int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz); +#define connect mingw_connect + int mingw_rename(const char*, const char*); #define rename mingw_rename From 7e5d776854e858ae69a4cde9db8de6675ffb5de6 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 24 Nov 2007 22:49:16 +0100 Subject: [PATCH 108/295] Windows: Implement a custom spawnve(). The problem with Windows's own implementation is that it tries to be clever when a console program is invoked from a GUI application: In this case it sometimes automatically allocates a new console window. As a consequence, the IO channels of the spawned program are directed to the console, but the invoking application listens on channels that are now directed to nowhere. In this implementation we use the lowlevel facilities of CreateProcess(), which offers a flag to tell the system not to open a console. As a side effect, only stdin, stdout, and stderr channels will be accessible from C programs that are spawned. Other channels (file handles, pipe handles, etc.) are still inherited by the spawned program, but it doesn't get enough information to access them. Johannes Schindelin integrated path quoting and unified the various *execv* and *spawnv* helpers. Eric Raible suggested to also quote '{'. Signed-off-by: Johannes Sixt --- compat/mingw.c | 203 +++++++++++++++++++++++++++++++++++++++++++++++-- compat/mingw.h | 1 + run-command.c | 2 +- 3 files changed, 199 insertions(+), 7 deletions(-) diff --git a/compat/mingw.c b/compat/mingw.c index d184c582eb..1ef2a4caf2 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -1,4 +1,5 @@ #include "../git-compat-util.h" +#include "../strbuf.h" unsigned int _CRT_fmode = _O_BINARY; @@ -186,6 +187,65 @@ char *mingw_getcwd(char *pointer, int len) return ret; } +/* + * See http://msdn2.microsoft.com/en-us/library/17w5ykft(vs.71).aspx + * (Parsing C++ Command-Line Arguments) + */ +static const char *quote_arg(const char *arg) +{ + /* count chars to quote */ + int len = 0, n = 0; + int force_quotes = 0; + char *q, *d; + const char *p = arg; + if (!*p) force_quotes = 1; + while (*p) { + if (isspace(*p) || *p == '*' || *p == '?' || *p == '{') + force_quotes = 1; + else if (*p == '"') + n++; + else if (*p == '\\') { + int count = 0; + while (*p == '\\') { + count++; + p++; + len++; + } + if (*p == '"') + n += count*2 + 1; + continue; + } + len++; + p++; + } + if (!force_quotes && n == 0) + return arg; + + /* insert \ where necessary */ + d = q = xmalloc(len+n+3); + *d++ = '"'; + while (*arg) { + if (*arg == '"') + *d++ = '\\'; + else if (*arg == '\\') { + int count = 0; + while (*arg == '\\') { + count++; + *d++ = *arg++; + } + if (*arg == '"') { + while (count-- > 0) + *d++ = '\\'; + *d++ = '\\'; + } + } + *d++ = *arg++; + } + *d++ = '"'; + *d++ = 0; + return q; +} + static const char *parse_interpreter(const char *cmd) { static char buf[100]; @@ -307,6 +367,138 @@ static char *path_lookup(const char *cmd, char **path, int exe_only) return prog; } +static int env_compare(const void *a, const void *b) +{ + char *const *ea = a; + char *const *eb = b; + return strcasecmp(*ea, *eb); +} + +static pid_t mingw_spawnve(const char *cmd, const char **argv, char **env, + int prepend_cmd) +{ + STARTUPINFO si; + PROCESS_INFORMATION pi; + struct strbuf envblk, args; + unsigned flags; + BOOL ret; + + /* Determine whether or not we are associated to a console */ + HANDLE cons = CreateFile("CONOUT$", GENERIC_WRITE, + FILE_SHARE_WRITE, NULL, OPEN_EXISTING, + FILE_ATTRIBUTE_NORMAL, NULL); + if (cons == INVALID_HANDLE_VALUE) { + /* There is no console associated with this process. + * Since the child is a console process, Windows + * would normally create a console window. But + * since we'll be redirecting std streams, we do + * not need the console. + */ + flags = CREATE_NO_WINDOW; + } else { + /* There is already a console. If we specified + * CREATE_NO_WINDOW here, too, Windows would + * disassociate the child from the console. + * Go figure! + */ + flags = 0; + CloseHandle(cons); + } + memset(&si, 0, sizeof(si)); + si.cb = sizeof(si); + si.dwFlags = STARTF_USESTDHANDLES; + si.hStdInput = (HANDLE) _get_osfhandle(0); + si.hStdOutput = (HANDLE) _get_osfhandle(1); + si.hStdError = (HANDLE) _get_osfhandle(2); + + /* concatenate argv, quoting args as we go */ + strbuf_init(&args, 0); + if (prepend_cmd) { + char *quoted = (char *)quote_arg(cmd); + strbuf_addstr(&args, quoted); + if (quoted != cmd) + free(quoted); + } + for (; *argv; argv++) { + char *quoted = (char *)quote_arg(*argv); + if (*args.buf) + strbuf_addch(&args, ' '); + strbuf_addstr(&args, quoted); + if (quoted != *argv) + free(quoted); + } + + if (env) { + int count = 0; + char **e, **sorted_env; + + for (e = env; *e; e++) + count++; + + /* environment must be sorted */ + sorted_env = xmalloc(sizeof(*sorted_env) * (count + 1)); + memcpy(sorted_env, env, sizeof(*sorted_env) * (count + 1)); + qsort(sorted_env, count, sizeof(*sorted_env), env_compare); + + strbuf_init(&envblk, 0); + for (e = sorted_env; *e; e++) { + strbuf_addstr(&envblk, *e); + strbuf_addch(&envblk, '\0'); + } + free(sorted_env); + } + + memset(&pi, 0, sizeof(pi)); + ret = CreateProcess(cmd, args.buf, NULL, NULL, TRUE, flags, + env ? envblk.buf : NULL, NULL, &si, &pi); + + if (env) + strbuf_release(&envblk); + strbuf_release(&args); + + if (!ret) { + errno = ENOENT; + return -1; + } + CloseHandle(pi.hThread); + return (pid_t)pi.hProcess; +} + +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env) +{ + pid_t pid; + char **path = get_path_split(); + char *prog = path_lookup(cmd, path, 0); + + if (!prog) { + errno = ENOENT; + pid = -1; + } + else { + const char *interpr = parse_interpreter(prog); + + if (interpr) { + const char *argv0 = argv[0]; + char *iprog = path_lookup(interpr, path, 1); + argv[0] = prog; + if (!iprog) { + errno = ENOENT; + pid = -1; + } + else { + pid = mingw_spawnve(iprog, argv, env, 1); + free(iprog); + } + argv[0] = argv0; + } + else + pid = mingw_spawnve(prog, argv, env, 0); + free(prog); + } + free_path_split(path); + return pid; +} + static int try_shell_exec(const char *cmd, char *const *argv, char **env) { const char *interpr = parse_interpreter(cmd); @@ -322,11 +514,10 @@ static int try_shell_exec(const char *cmd, char *const *argv, char **env) int argc = 0; const char **argv2; while (argv[argc]) argc++; - argv2 = xmalloc(sizeof(*argv) * (argc+2)); - argv2[0] = (char *)interpr; - argv2[1] = (char *)cmd; /* full path to the script file */ - memcpy(&argv2[2], &argv[1], sizeof(*argv) * argc); - pid = spawnve(_P_NOWAIT, prog, argv2, (const char **)env); + argv2 = xmalloc(sizeof(*argv) * (argc+1)); + argv2[0] = (char *)cmd; /* full path to the script file */ + memcpy(&argv2[1], &argv[1], sizeof(*argv) * argc); + pid = mingw_spawnve(prog, argv2, env, 1); if (pid >= 0) { int status; if (waitpid(pid, &status, 0) < 0) @@ -347,7 +538,7 @@ static void mingw_execve(const char *cmd, char *const *argv, char *const *env) if (!try_shell_exec(cmd, argv, (char **)env)) { int pid, status; - pid = spawnve(_P_NOWAIT, cmd, (const char **)argv, (const char **)env); + pid = mingw_spawnve(cmd, (const char **)argv, (char **)env, 0); if (pid < 0) return; if (waitpid(pid, &status, 0) < 0) diff --git a/compat/mingw.h b/compat/mingw.h index 1017632a24..48229d538a 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -160,6 +160,7 @@ int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz); int mingw_rename(const char*, const char*); #define rename mingw_rename +pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); void mingw_execvp(const char *cmd, char *const *argv); #define execvp mingw_execvp diff --git a/run-command.c b/run-command.c index 63238e412a..2ce8c2b2f0 100644 --- a/run-command.c +++ b/run-command.c @@ -168,7 +168,7 @@ int start_command(struct child_process *cmd) cmd->argv[0] = git_cmd.buf; } - cmd->pid = spawnvpe(_P_NOWAIT, cmd->argv[0], cmd->argv, (const char **)env); + cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, env); if (cmd->env) free_environ(env); From 5411bdc4e4b170a57a61b2d486ab344896c41500 Mon Sep 17 00:00:00 2001 From: Marius Storm-Olsen Date: Mon, 3 Sep 2007 20:40:26 +0200 Subject: [PATCH 109/295] Windows: Add a new lstat and fstat implementation based on Win32 API. This gives us a significant speedup when adding, committing and stat'ing files. Also, since Windows doesn't really handle symlinks, we let stat just uses lstat. We also need to replace fstat, since our implementation and the standard stat() functions report slightly different timestamps, possibly due to timezones. We simply report UTC in our implementation, and do our FILETIME to time_t conversion based on the document at http://support.microsoft.com/kb/167296. With Moe's repo structure (100K files in 100 dirs, containing 2-4 bytes) mkdir bummer && cd bummer; for ((i=0;i<100;i++)); do mkdir $i && pushd $i; for ((j=0;j<1000;j++)); do echo "$j" >$j; done; popd; done We get the following performance boost: With normal lstat & stat Custom lstat/fstat ------------------------ ------------------------ Command: git init Command: git init ------------------------ ------------------------ real 0m 0.047s real 0m 0.063s user 0m 0.031s user 0m 0.015s sys 0m 0.000s sys 0m 0.015s ------------------------ ------------------------ Command: git add . Command: git add . ------------------------ ------------------------ real 0m19.390s real 0m12.031s 1.6x user 0m 0.015s user 0m 0.031s sys 0m 0.030s sys 0m 0.000s ------------------------ ------------------------ Command: git commit -a.. Command: git commit -a.. ------------------------ ------------------------ real 0m30.812s real 0m16.875s 1.8x user 0m 0.015s user 0m 0.015s sys 0m 0.000s sys 0m 0.015s ------------------------ ------------------------ 3x Command: git-status 3x Command: git-status ------------------------ ------------------------ real 0m11.860s real 0m 5.266s 2.2x user 0m 0.015s user 0m 0.015s sys 0m 0.015s sys 0m 0.015s real 0m11.703s real 0m 5.234s user 0m 0.015s user 0m 0.015s sys 0m 0.000s sys 0m 0.000s real 0m11.672s real 0m 5.250s user 0m 0.031s user 0m 0.015s sys 0m 0.000s sys 0m 0.000s ------------------------ ------------------------ Command: git commit... Command: git commit... (single file) (single file) ------------------------ ------------------------ real 0m14.234s real 0m 7.735s 1.8x user 0m 0.015s user 0m 0.031s sys 0m 0.000s sys 0m 0.000s Signed-off-by: Marius Storm-Olsen Signed-off-by: Johannes Sixt --- compat/mingw.c | 132 +++++++++++++++++++++++++++++++++++++++++++++++++ compat/mingw.h | 10 +++- 2 files changed, 141 insertions(+), 1 deletion(-) diff --git a/compat/mingw.c b/compat/mingw.c index 1ef2a4caf2..6b742873da 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -23,6 +23,138 @@ int mingw_open (const char *filename, int oflags, ...) return fd; } +static inline time_t filetime_to_time_t(const FILETIME *ft) +{ + long long winTime = ((long long)ft->dwHighDateTime << 32) + ft->dwLowDateTime; + winTime -= 116444736000000000LL; /* Windows to Unix Epoch conversion */ + winTime /= 10000000; /* Nano to seconds resolution */ + return (time_t)winTime; +} + +extern int _getdrive( void ); +/* We keep the do_lstat code in a separate function to avoid recursion. + * When a path ends with a slash, the stat will fail with ENOENT. In + * this case, we strip the trailing slashes and stat again. + */ +static int do_lstat(const char *file_name, struct stat *buf) +{ + WIN32_FILE_ATTRIBUTE_DATA fdata; + + if (GetFileAttributesExA(file_name, GetFileExInfoStandard, &fdata)) { + int fMode = S_IREAD; + if (fdata.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) + fMode |= S_IFDIR; + else + fMode |= S_IFREG; + if (!(fdata.dwFileAttributes & FILE_ATTRIBUTE_READONLY)) + fMode |= S_IWRITE; + + buf->st_ino = 0; + buf->st_gid = 0; + buf->st_uid = 0; + buf->st_nlink = 1; + buf->st_mode = fMode; + buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ + buf->st_dev = buf->st_rdev = (_getdrive() - 1); + buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); + buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); + buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); + errno = 0; + return 0; + } + + switch (GetLastError()) { + case ERROR_ACCESS_DENIED: + case ERROR_SHARING_VIOLATION: + case ERROR_LOCK_VIOLATION: + case ERROR_SHARING_BUFFER_EXCEEDED: + errno = EACCES; + break; + case ERROR_BUFFER_OVERFLOW: + errno = ENAMETOOLONG; + break; + case ERROR_NOT_ENOUGH_MEMORY: + errno = ENOMEM; + break; + default: + errno = ENOENT; + break; + } + return -1; +} + +/* We provide our own lstat/fstat functions, since the provided + * lstat/fstat functions are so slow. These stat functions are + * tailored for Git's usage (read: fast), and are not meant to be + * complete. Note that Git stat()s are redirected to mingw_lstat() + * too, since Windows doesn't really handle symlinks that well. + */ +int mingw_lstat(const char *file_name, struct stat *buf) +{ + int namelen; + static char alt_name[PATH_MAX]; + + if (!do_lstat(file_name, buf)) + return 0; + + /* if file_name ended in a '/', Windows returned ENOENT; + * try again without trailing slashes + */ + if (errno != ENOENT) + return -1; + + namelen = strlen(file_name); + if (namelen && file_name[namelen-1] != '/') + return -1; + while (namelen && file_name[namelen-1] == '/') + --namelen; + if (!namelen || namelen >= PATH_MAX) + return -1; + + memcpy(alt_name, file_name, namelen); + alt_name[namelen] = 0; + return do_lstat(alt_name, buf); +} + +#undef fstat +int mingw_fstat(int fd, struct stat *buf) +{ + HANDLE fh = (HANDLE)_get_osfhandle(fd); + BY_HANDLE_FILE_INFORMATION fdata; + + if (fh == INVALID_HANDLE_VALUE) { + errno = EBADF; + return -1; + } + /* direct non-file handles to MS's fstat() */ + if (GetFileType(fh) != FILE_TYPE_DISK) + return fstat(fd, buf); + + if (GetFileInformationByHandle(fh, &fdata)) { + int fMode = S_IREAD; + if (fdata.dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY) + fMode |= S_IFDIR; + else + fMode |= S_IFREG; + if (!(fdata.dwFileAttributes & FILE_ATTRIBUTE_READONLY)) + fMode |= S_IWRITE; + + buf->st_ino = 0; + buf->st_gid = 0; + buf->st_uid = 0; + buf->st_nlink = 1; + buf->st_mode = fMode; + buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ + buf->st_dev = buf->st_rdev = (_getdrive() - 1); + buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); + buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); + buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); + return 0; + } + errno = EBADF; + return -1; +} + unsigned int sleep (unsigned int seconds) { Sleep(seconds*1000); diff --git a/compat/mingw.h b/compat/mingw.h index 48229d538a..69b1dde3ca 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -60,7 +60,6 @@ struct itimerval { #define ITIMER_REAL 0 #define st_blocks st_size/512 /* will be cleaned up later */ -#define lstat stat /* * trivial stubs @@ -160,6 +159,15 @@ int mingw_connect(int sockfd, struct sockaddr *sa, size_t sz); int mingw_rename(const char*, const char*); #define rename mingw_rename +/* Use mingw_lstat() instead of lstat()/stat() and + * mingw_fstat() instead of fstat() on Windows. + */ +int mingw_lstat(const char *file_name, struct stat *buf); +int mingw_fstat(int fd, struct stat *buf); +#define fstat mingw_fstat +#define lstat mingw_lstat +#define stat(x,y) mingw_lstat(x,y) + pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); void mingw_execvp(const char *cmd, char *const *argv); #define execvp mingw_execvp From 7c0ffa1cb753f9b909dfb3bc7a5d5417b8de39c2 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 7 Sep 2007 13:05:00 +0200 Subject: [PATCH 110/295] Windows: Add a custom implementation for utime(). This is a necessary pendant to our lstat implementation: MSVCRT's implementations of lstat and utime do some adjustments if daylight saving time is in effect, but our lstat implementation doesn't do these adjustments and report the correct UTC time. With this implementation we omit the adjustments in utime() as well and always write UTC. Signed-off-by: Johannes Sixt --- compat/mingw.c | 27 +++++++++++++++++++++++++++ compat/mingw.h | 3 +++ 2 files changed, 30 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 6b742873da..2e47555443 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -155,6 +155,33 @@ int mingw_fstat(int fd, struct stat *buf) return -1; } +static inline void time_t_to_filetime(time_t t, FILETIME *ft) +{ + long long winTime = t * 10000000LL + 116444736000000000LL; + ft->dwLowDateTime = winTime; + ft->dwHighDateTime = winTime >> 32; +} + +int mingw_utime (const char *file_name, const struct utimbuf *times) +{ + FILETIME mft, aft; + int fh, rc; + + /* must have write permission */ + if ((fh = open(file_name, O_RDWR | O_BINARY)) < 0) + return -1; + + time_t_to_filetime(times->modtime, &mft); + time_t_to_filetime(times->actime, &aft); + if (!SetFileTime((HANDLE)_get_osfhandle(fh), NULL, &aft, &mft)) { + errno = EINVAL; + rc = -1; + } else + rc = 0; + close(fh); + return rc; +} + unsigned int sleep (unsigned int seconds) { Sleep(seconds*1000); diff --git a/compat/mingw.h b/compat/mingw.h index 69b1dde3ca..92e9273dd5 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -168,6 +168,9 @@ int mingw_fstat(int fd, struct stat *buf); #define lstat mingw_lstat #define stat(x,y) mingw_lstat(x,y) +int mingw_utime(const char *file_name, const struct utimbuf *times); +#define utime mingw_utime + pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); void mingw_execvp(const char *cmd, char *const *argv); #define execvp mingw_execvp From fc2ded5b08e071beed974117c0148781b1acc94a Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Mon, 12 Nov 2007 12:52:41 +0100 Subject: [PATCH 111/295] Windows: Use a customized struct stat that also has the st_blocks member. Windows's struct stat does not have a st_blocks member. Since we already have our own stat/lstat/fstat implementations, we can just as well use a customized struct stat. This patch introduces just that, and also fills in the st_blocks member. On the other hand, we don't provide members that are never used. Signed-off-by: Johannes Sixt --- compat/mingw.c | 36 ++++++++++++++++++++++++++++-------- compat/mingw.h | 18 +++++++++++++----- 2 files changed, 41 insertions(+), 13 deletions(-) diff --git a/compat/mingw.c b/compat/mingw.c index 2e47555443..28d32969b9 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -31,6 +31,11 @@ static inline time_t filetime_to_time_t(const FILETIME *ft) return (time_t)winTime; } +static inline size_t size_to_blocks(size_t s) +{ + return (s+511)/512; +} + extern int _getdrive( void ); /* We keep the do_lstat code in a separate function to avoid recursion. * When a path ends with a slash, the stat will fail with ENOENT. In @@ -52,10 +57,10 @@ static int do_lstat(const char *file_name, struct stat *buf) buf->st_ino = 0; buf->st_gid = 0; buf->st_uid = 0; - buf->st_nlink = 1; buf->st_mode = fMode; buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ - buf->st_dev = buf->st_rdev = (_getdrive() - 1); + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = _getdrive() - 1; buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); @@ -89,7 +94,7 @@ static int do_lstat(const char *file_name, struct stat *buf) * complete. Note that Git stat()s are redirected to mingw_lstat() * too, since Windows doesn't really handle symlinks that well. */ -int mingw_lstat(const char *file_name, struct stat *buf) +int mingw_lstat(const char *file_name, struct mingw_stat *buf) { int namelen; static char alt_name[PATH_MAX]; @@ -117,7 +122,8 @@ int mingw_lstat(const char *file_name, struct stat *buf) } #undef fstat -int mingw_fstat(int fd, struct stat *buf) +#undef stat +int mingw_fstat(int fd, struct mingw_stat *buf) { HANDLE fh = (HANDLE)_get_osfhandle(fd); BY_HANDLE_FILE_INFORMATION fdata; @@ -127,8 +133,22 @@ int mingw_fstat(int fd, struct stat *buf) return -1; } /* direct non-file handles to MS's fstat() */ - if (GetFileType(fh) != FILE_TYPE_DISK) - return fstat(fd, buf); + if (GetFileType(fh) != FILE_TYPE_DISK) { + struct stat st; + if (fstat(fd, &st)) + return -1; + buf->st_ino = st.st_ino; + buf->st_gid = st.st_gid; + buf->st_uid = st.st_uid; + buf->st_mode = st.st_mode; + buf->st_size = st.st_size; + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = st.st_dev; + buf->st_atime = st.st_atime; + buf->st_mtime = st.st_mtime; + buf->st_ctime = st.st_ctime; + return 0; + } if (GetFileInformationByHandle(fh, &fdata)) { int fMode = S_IREAD; @@ -142,10 +162,10 @@ int mingw_fstat(int fd, struct stat *buf) buf->st_ino = 0; buf->st_gid = 0; buf->st_uid = 0; - buf->st_nlink = 1; buf->st_mode = fMode; buf->st_size = fdata.nFileSizeLow; /* Can't use nFileSizeHigh, since it's not a stat64 */ - buf->st_dev = buf->st_rdev = (_getdrive() - 1); + buf->st_blocks = size_to_blocks(buf->st_size); + buf->st_dev = _getdrive() - 1; buf->st_atime = filetime_to_time_t(&(fdata.ftLastAccessTime)); buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime)); buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime)); diff --git a/compat/mingw.h b/compat/mingw.h index 92e9273dd5..624b32d1f4 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -59,8 +59,6 @@ struct itimerval { }; #define ITIMER_REAL 0 -#define st_blocks st_size/512 /* will be cleaned up later */ - /* * trivial stubs */ @@ -161,12 +159,22 @@ int mingw_rename(const char*, const char*); /* Use mingw_lstat() instead of lstat()/stat() and * mingw_fstat() instead of fstat() on Windows. + * struct stat is redefined because it lacks the st_blocks member. */ -int mingw_lstat(const char *file_name, struct stat *buf); -int mingw_fstat(int fd, struct stat *buf); +struct mingw_stat { + unsigned st_mode; + time_t st_mtime, st_atime, st_ctime; + unsigned st_dev, st_ino, st_uid, st_gid; + size_t st_size; + size_t st_blocks; +}; +int mingw_lstat(const char *file_name, struct mingw_stat *buf); +int mingw_fstat(int fd, struct mingw_stat *buf); #define fstat mingw_fstat #define lstat mingw_lstat -#define stat(x,y) mingw_lstat(x,y) +#define stat mingw_stat +static inline int mingw_stat(const char *file_name, struct mingw_stat *buf) +{ return mingw_lstat(file_name, buf); } int mingw_utime(const char *file_name, const struct utimbuf *times); #define utime mingw_utime From 4ec22a48c0575c8a303cd00b5ef4b3d703fbf8b3 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Wed, 11 Apr 2007 15:26:08 +0200 Subject: [PATCH 112/295] Turn builtin_exec_path into a function. builtin_exec_path returns the hard-coded installation path, which is used as the ultimate fallback to look for git commands. Making it into a function enables us in a follow-up patch to return a computed value instead of just a constant string. Signed-off-by: Johannes Sixt --- exec_cmd.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/exec_cmd.c b/exec_cmd.c index a1bc4e04bf..6618aad7ab 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -4,9 +4,13 @@ #define MAX_ARGS 32 extern char **environ; -static const char *builtin_exec_path = GIT_EXEC_PATH; static const char *argv_exec_path; +static const char *builtin_exec_path(void) +{ + return GIT_EXEC_PATH; +} + void git_set_argv_exec_path(const char *exec_path) { argv_exec_path = exec_path; @@ -26,7 +30,7 @@ const char *git_exec_path(void) return env; } - return builtin_exec_path; + return builtin_exec_path(); } static void add_path(struct strbuf *out, const char *path) @@ -50,7 +54,7 @@ void setup_path(const char *cmd_path) add_path(&new_path, argv_exec_path); add_path(&new_path, getenv(EXEC_PATH_ENVIRONMENT)); - add_path(&new_path, builtin_exec_path); + add_path(&new_path, builtin_exec_path()); add_path(&new_path, cmd_path); if (old_path) From 6fad004a37432e4378b6cce53eebe8a079104e93 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Wed, 11 Apr 2007 16:02:45 +0200 Subject: [PATCH 113/295] Windows: Compute the fallback for exec_path from the program invocation. Since on Windows the user is fairly free where to install programs, we cannot rely on a hard-coded path. We use the program name to derive the installation directory and use that as exec_path. Signed-off-by: Johannes Sixt --- exec_cmd.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) diff --git a/exec_cmd.c b/exec_cmd.c index 6618aad7ab..84db7ee664 100644 --- a/exec_cmd.c +++ b/exec_cmd.c @@ -8,7 +8,36 @@ static const char *argv_exec_path; static const char *builtin_exec_path(void) { +#ifndef __MINGW32__ return GIT_EXEC_PATH; +#else + int len; + char *p, *q, *sl; + static char *ep; + if (ep) + return ep; + + len = strlen(_pgmptr); + if (len < 2) + return ep = "."; + + p = ep = xmalloc(len+1); + q = _pgmptr; + sl = NULL; + /* copy program name, turn '\\' into '/', skip last part */ + while ((*p = *q)) { + if (*q == '\\' || *q == '/') { + *p = '/'; + sl = p; + } + p++, q++; + } + if (sl) + *sl = '\0'; + else + ep[0] = '.', ep[1] = '\0'; + return ep; +#endif } void git_set_argv_exec_path(const char *exec_path) From 8512439af25c93942d569d250d49d135d8b7062b Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 30 Nov 2007 22:28:38 +0100 Subject: [PATCH 114/295] Windows: Use a relative default template_dir and ETC_GITCONFIG With this definition the templates and system config file will be found irrespective of the installation location. Signed-off-by: Johannes Sixt --- Makefile | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Makefile b/Makefile index 9c5aae03bb..7233160743 100644 --- a/Makefile +++ b/Makefile @@ -739,6 +739,8 @@ ifneq (,$(findstring MINGW,$(uname_S))) COMPAT_OBJS += compat/mingw.o compat/fnmatch.o compat/regex.o EXTLIBS += -lws2_32 X = .exe + template_dir = ../share/git-core/templates/ + ETC_GITCONFIG = ../etc/gitconfig endif ifneq (,$(findstring arm,$(uname_M))) ARM_SHA1 = YesPlease From 0b50b860a505d4a1d6fa595a400f3968333e7128 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Tue, 1 Jan 2008 22:15:21 +0100 Subject: [PATCH 115/295] When installing, be prepared that template_dir may be relative. Since the Makefile in the template/ subdirectory is only used to install the templates, we do not simply pass down the setting of template_dir when it is relative, but construct the intended destination in a new variable: A relative template_dir is relative to gitexecdir. Signed-off-by: Johannes Sixt --- Makefile | 9 ++++++++- templates/Makefile | 8 ++++---- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/Makefile b/Makefile index 7233160743..a2a19a85f0 100644 --- a/Makefile +++ b/Makefile @@ -205,7 +205,7 @@ GITWEB_FAVICON = git-favicon.png GITWEB_SITE_HEADER = GITWEB_SITE_FOOTER = -export prefix bindir gitexecdir sharedir template_dir htmldir sysconfdir +export prefix bindir gitexecdir sharedir htmldir sysconfdir CC = gcc AR = ar @@ -1297,6 +1297,13 @@ remove-dashes: ### Installation rules +ifeq ($(firstword $(subst /, ,$(template_dir))),..) +template_instdir = $(gitexecdir)/$(template_dir) +else +template_instdir = $(template_dir) +endif +export template_instdir + install: all $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)' $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(gitexecdir_SQ)' diff --git a/templates/Makefile b/templates/Makefile index bda9d13505..9f3f1fc352 100644 --- a/templates/Makefile +++ b/templates/Makefile @@ -8,12 +8,12 @@ INSTALL ?= install TAR ?= tar RM ?= rm -f prefix ?= $(HOME) -template_dir ?= $(prefix)/share/git-core/templates +template_instdir ?= $(prefix)/share/git-core/templates # DESTDIR= # Shell quote (do not use $(call) to accommodate ancient setups); DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) -template_dir_SQ = $(subst ','\'',$(template_dir)) +template_instdir_SQ = $(subst ','\'',$(template_instdir)) all: boilerplates.made custom @@ -46,6 +46,6 @@ clean: $(RM) -r blt boilerplates.made install: all - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(template_dir_SQ)' + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(template_instdir_SQ)' (cd blt && $(TAR) cf - .) | \ - (cd '$(DESTDIR_SQ)$(template_dir_SQ)' && umask 022 && $(TAR) xf -) + (cd '$(DESTDIR_SQ)$(template_instdir_SQ)' && umask 022 && $(TAR) xf -) From bfdd9ffd2f7376ccb8b9d4c4e39e2e0fe97d6b37 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sat, 8 Dec 2007 21:28:41 +0100 Subject: [PATCH 116/295] Windows: Make the pager work. Since we have neither fork() nor exec(), we have to spawn the pager and feed it with the program's output. Signed-off-by: Johannes Sixt --- pager.c | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) diff --git a/pager.c b/pager.c index dbd941421b..6b5c9e44b4 100644 --- a/pager.c +++ b/pager.c @@ -1,12 +1,13 @@ #include "cache.h" /* - * This is split up from the rest of git so that we might do - * something different on Windows, for example. + * This is split up from the rest of git so that we can do + * something different on Windows. */ static int spawned_pager; +#ifndef __MINGW32__ static void run_pager(const char *pager) { /* @@ -22,11 +23,31 @@ static void run_pager(const char *pager) execlp(pager, pager, NULL); execl("/bin/sh", "sh", "-c", pager, NULL); } +#else +#include "run-command.h" + +static const char *pager_argv[] = { "sh", "-c", NULL, NULL }; +static struct child_process pager_process = { + .argv = pager_argv, + .in = -1 +}; +static void wait_for_pager(void) +{ + fflush(stdout); + fflush(stderr); + /* signal EOF to pager */ + close(1); + close(2); + finish_command(&pager_process); +} +#endif void setup_pager(void) { +#ifndef __MINGW32__ pid_t pid; int fd[2]; +#endif const char *pager = getenv("GIT_PAGER"); if (!isatty(1)) @@ -45,6 +66,7 @@ void setup_pager(void) spawned_pager = 1; /* means we are emitting to terminal */ +#ifndef __MINGW32__ if (pipe(fd) < 0) return; pid = fork(); @@ -72,6 +94,20 @@ void setup_pager(void) run_pager(pager); die("unable to execute pager '%s'", pager); exit(255); +#else + /* spawn the pager */ + pager_argv[2] = pager; + if (start_command(&pager_process)) + return; + + /* original process continues, but writes to the pipe */ + dup2(pager_process.in, 1); + dup2(pager_process.in, 2); + close(pager_process.in); + + /* this makes sure that the parent terminates after the pager */ + atexit(wait_for_pager); +#endif } int pager_in_use(void) From b2f5e2684da060dd821bf90f88df8b6dc9401a40 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Fri, 17 Aug 2007 18:40:36 +0200 Subject: [PATCH 117/295] Windows: Work around an oddity when a pipe with no reader is written to. On Windows, write() is implemented using WriteFile(). After the reader closed its end of the pipe, the first WriteFile() returns ERROR_BROKEN_PIPE (which translates to EPIPE), subsequent WriteFile()s return ERROR_NO_DATA, which is translated to EINVAL. Signed-off-by: Johannes Sixt --- write_or_die.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/write_or_die.c b/write_or_die.c index 630be4cb94..e4c8e225fd 100644 --- a/write_or_die.c +++ b/write_or_die.c @@ -34,7 +34,12 @@ void maybe_flush_or_die(FILE *f, const char *desc) return; } if (fflush(f)) { - if (errno == EPIPE) + /* + * On Windows, EPIPE is returned only by the first write() + * after the reading end has closed its handle; subsequent + * write()s return EINVAL. + */ + if (errno == EPIPE || errno == EINVAL) exit(0); die("write failure on %s: %s", desc, strerror(errno)); } From cc3b7a9732f940cb0249a12cb3c02e3d83723eb0 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Mon, 14 Jan 2008 14:05:33 +0100 Subject: [PATCH 118/295] Windows: Make 'git help -a' work. git help -a scans the PATH for git commands. On Windows it failed for two reasons: - The PATH separator is ';', not ':' on Windows. - stat() does not set the executable bit. We now open the file and guess whether it is executable. The result of the guess is good enough for the list of git commands, but it is of no use for a general stat() implementation because (1) it is a guess, (2) the user has no way to influence the outcome (via chmod or similar), and (3) it would reduce stat() performance by an unacceptable amount. Therefore, this strategy is a special-case local to help.c. Signed-off-by: Johannes Sixt --- help.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) diff --git a/help.c b/help.c index 8aff94c64a..6c16fb4aa1 100644 --- a/help.c +++ b/help.c @@ -391,6 +391,32 @@ static void pretty_print_string_list(struct cmdnames *cmds, int longest) } } +static int is_executable(const char *name) +{ + struct stat st; + + if (stat(name, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode)) + return 0; + +#ifdef __MINGW32__ + /* cannot trust the executable bit, peek into the file instead */ + char buf[3] = { 0 }; + int n; + int fd = open(name, O_RDONLY); + st.st_mode &= ~S_IXUSR; + if (fd >= 0) { + n = read(fd, buf, 2); + if (n == 2) + /* DOS executables start with "MZ" */ + if (!strcmp(buf, "#!") || !strcmp(buf, "MZ")) + st.st_mode |= S_IXUSR; + close(fd); + } +#endif + return st.st_mode & S_IXUSR; +} + static unsigned int list_commands_in_dir(struct cmdnames *cmds, const char *path) { @@ -404,15 +430,12 @@ static unsigned int list_commands_in_dir(struct cmdnames *cmds, return 0; while ((de = readdir(dir)) != NULL) { - struct stat st; int entlen; if (prefixcmp(de->d_name, prefix)) continue; - if (stat(de->d_name, &st) || /* stat, not lstat */ - !S_ISREG(st.st_mode) || - !(st.st_mode & S_IXUSR)) + if (!is_executable(de->d_name)) continue; entlen = strlen(de->d_name) - prefix_len; @@ -447,7 +470,7 @@ static unsigned int load_command_list(void) path = paths = xstrdup(env_path); while (1) { - if ((colon = strchr(path, ':'))) + if ((colon = strchr(path, PATH_SEP))) *colon = 0; len = list_commands_in_dir(&other_cmds, path); From 6fd6aec44fe79dff61fd37a5fec2456c5458b574 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Sun, 22 Jun 2008 11:35:21 +0200 Subject: [PATCH 119/295] Windows: TMP and TEMP environment variables specify a temporary directory. Signed-off-by: Johannes Sixt --- compat/mingw.c | 13 +++++++++++++ compat/mingw.h | 3 +++ 2 files changed, 16 insertions(+) diff --git a/compat/mingw.c b/compat/mingw.c index 28d32969b9..3a05fe7da6 100644 --- a/compat/mingw.c +++ b/compat/mingw.c @@ -366,6 +366,19 @@ char *mingw_getcwd(char *pointer, int len) return ret; } +#undef getenv +char *mingw_getenv(const char *name) +{ + char *result = getenv(name); + if (!result && !strcmp(name, "TMPDIR")) { + /* on Windows it is TMP and TEMP */ + result = getenv("TMP"); + if (!result) + result = getenv("TEMP"); + } + return result; +} + /* * See http://msdn2.microsoft.com/en-us/library/17w5ykft(vs.71).aspx * (Parsing C++ Command-Line Arguments) diff --git a/compat/mingw.h b/compat/mingw.h index 624b32d1f4..a87cc9679c 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -145,6 +145,9 @@ int mingw_open (const char *filename, int oflags, ...); char *mingw_getcwd(char *pointer, int len); #define getcwd mingw_getcwd +char *mingw_getenv(const char *name); +#define getenv mingw_getenv + struct hostent *mingw_gethostbyname(const char *host); #define gethostbyname mingw_gethostbyname From cd800eecc27ef57cb934f349f116cd7022ec71ed Mon Sep 17 00:00:00 2001 From: Steffen Prohaska Date: Sat, 17 Nov 2007 19:16:53 +0100 Subject: [PATCH 120/295] Windows: Fix ntohl() related warnings about printf formatting On Windows, ntohl() returns unsigned long. On Unix it returns uint32_t. This makes choosing a suitable printf format string hard. This commit introduces a mingw specific helper function git_ntohl() that casts to unsigned int before returning. This makes gcc's printf format check happy. It should be safe because we expect ntohl to use 32-bit numbers. Signed-off-by: Steffen Prohaska Signed-off-by: Johannes Sixt --- compat/mingw.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/compat/mingw.h b/compat/mingw.h index a87cc9679c..6bc049ad99 100644 --- a/compat/mingw.h +++ b/compat/mingw.h @@ -186,6 +186,10 @@ pid_t mingw_spawnvpe(const char *cmd, const char **argv, char **env); void mingw_execvp(const char *cmd, char *const *argv); #define execvp mingw_execvp +static inline unsigned int git_ntohl(unsigned int x) +{ return (unsigned int)ntohl(x); } +#define ntohl git_ntohl + sig_handler_t mingw_signal(int sig, sig_handler_t handler); #define signal mingw_signal From 14086b0a13f5f5ac456cb9ae16a263f92908ae61 Mon Sep 17 00:00:00 2001 From: Steffen Prohaska Date: Sat, 17 Nov 2007 20:48:14 +0100 Subject: [PATCH 121/295] compat/pread.c: Add a forward declaration to fix a warning read_in_full()'s is used in compat/pread.c. read_in_full() is declared in cache.h. But we can't include cache.h because too many macros are defined there. Using read_in_full() without including cache.h is dangerous because we wouldn't recognize if its prototyp changed. gcc issues a warning about that. This commit adds a forward declaration to git-compat-util.h. git-compat-util.h is included by compat/pread.c _and_ cache.h. Hence, changes in cache.h would be detected. Signed-off-by: Steffen Prohaska Signed-off-by: Johannes Sixt --- git-compat-util.h | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/git-compat-util.h b/git-compat-util.h index 58cdc087fa..51823ae7af 100644 --- a/git-compat-util.h +++ b/git-compat-util.h @@ -185,6 +185,12 @@ extern int git_munmap(void *start, size_t length); #define pread git_pread extern ssize_t git_pread(int fd, void *buf, size_t count, off_t offset); #endif +/* + * Forward decl that will remind us if its twin in cache.h changes. + * This function is used in compat/pread.c. But we can't include + * cache.h there. + */ +extern ssize_t read_in_full(int fd, void *buf, size_t count); #ifdef NO_SETENV #define setenv gitsetenv From de8d95703417a93bb6231f823bb82746f01e8a58 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 00:13:37 -0700 Subject: [PATCH 122/295] Start draft release notes for 1.6.0 Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.6.0.txt | 105 +++++++++++++++++++++++++++++++ RelNotes | 2 +- 2 files changed, 106 insertions(+), 1 deletion(-) create mode 100644 Documentation/RelNotes-1.6.0.txt diff --git a/Documentation/RelNotes-1.6.0.txt b/Documentation/RelNotes-1.6.0.txt new file mode 100644 index 0000000000..5292bd730c --- /dev/null +++ b/Documentation/RelNotes-1.6.0.txt @@ -0,0 +1,105 @@ +GIT v1.6.0 Release Notes +======================== + +User visible changes +-------------------- + +[[Note that none of these are not merged to 'master' as of this writing +but they will be before 1.6.0 happens]] + +With default Makefile settings, most of the programs are now installed +outside your $PATH, except for "git", "gitk", "git-gui" and some server +side programs that needs to be accessible when connecting over ssh. + +When talking to remote repository over ssh, necessary server side programs +are now invoked with "git $program" notation, not with "git-$program" +notation. This should work with both servers running older git where you +had all of these programs installed on $PATH, or newer git where you have +only "git" on $PATH. However, if the remote side is running a custom +software that restricts programs you can run over ssh, it might cause +problems. Use --upload-pack="git-upload-pack" (when using ls-remote, +fetch and pull on the client side), --receive-pack="git-receive-pack" +(when using push on the client side), or --exec="git-upload-archive" (when +using git-archive) as appropriate when talking to such a remote. + +Source changes needed for porting to MinGW environment are now all in the +main git.git codebase. + + +Updates since v1.5.6 +-------------------- + +(subsystems) + +(portability) + +* Sample hook scripts shipped in templates/ are now suffixed with + *.sample. We used to prevent them from triggering by default by + relying on the fact that we install them as unexecutable, but on + some filesystems this approach does not work. Instead of running + "chmod +x" on them, the users who want to activate these samples + as-is can now rename them dropping *.sample suffix. + +* perl's in-place edit (-i) does not work well without backup files on Windows; + some tests are rewritten to cope with this. + +(documentation) + +* Updated howto/update-hook-example + +(performance, robustness etc.) + +* reduced excessive inlining to shrink size of the "git" binary. + +* verify-pack checks the object CRC when using version 2 idx files. + +* When an object is corrupt in a pack, the object became unusable even + when the same object is available in a loose form, We now try harder to + fall back to these redundant objects when able. In particular, "git + repack -a -f" can be used to fix such a corruption as long as necessary + objects are available. + +* git-clone does not create refs in loose form anymore (it behaves as + if you immediately ran git-pack-refs after cloning). This will help + repositories with insanely large number of refs. + +* core.fsyncobjectfiles configuration can be used to ensure that the loose + objects created will be fsync'ed (this is only useful on filesystems + that does not order data writes properly). + +(usability, bells and whistles) + +* git-archive can be told to omit certain paths from its output using + export-ignore attributes. + +* fast-export learned to export and import marks file; this can be used to + interface with fast-import incrementally. + +* Original SHA-1 value for "update-ref -d" is optional now. + +* You can tell "git status -u" to even more aggressively omit checking + untracked files with --untracked-files=no. + +* Error codes from gitweb are made more descriptive where possible, rather + than "403 forbidden" as we used to issue everywhere. + +(internal) + + +Fixes since v1.5.6 +------------------ + +All of the fixes in v1.5.6 maintenance series are included in +this release, unless otherwise noted. + + * diff -c/--cc showed unnecessary "deletion" lines at the context + boundary (needs backmerge to maint). + + * "git-clone " did not create leading directories for + like the scripted version used to do (needs backport to maint). + +--- +exec >/var/tmp/1 +O=v1.5.6.1-77-gf9a08f6 +echo O=$(git describe refs/heads/master) +git shortlog --no-merges $O..refs/heads/master ^refs/heads/maint diff --git a/RelNotes b/RelNotes index ebc4b20148..b9a53c3416 120000 --- a/RelNotes +++ b/RelNotes @@ -1 +1 @@ -Documentation/RelNotes-1.5.6.1.txt \ No newline at end of file +Documentation/RelNotes-1.6.0.txt \ No newline at end of file From 4c2d5d722c4775c1efd5e63f41ba5b303ec8fb65 Mon Sep 17 00:00:00 2001 From: Jing Xue Date: Sun, 22 Jun 2008 14:12:39 -0400 Subject: [PATCH 123/295] Add 'git-p4.allowSubmit' to git-p4 I'm working with a perforce repo using git-p4. There are some config files which I need to change locally according to my environment. I'm using a 'local' git branch to park these changes. And I want to avoid accidentally checking them into p4 just by doing "git p4 submit" mindlessly without realizing which branch I'm actually on. This patch adds a new git config, 'git-p4.allowSubmit', which is a whitelist of branch names. "git p4 submit" will only allow submissions from local branches on the list. Useful for preventing inadvertently submitting from a strictly local branch. For backward compatibility, if this config is not set at all, submissions from all branches are allowed. Signed-off-by: Jing Xue Acked-By: Simon Hausmann Signed-off-by: Junio C Hamano --- contrib/fast-import/git-p4 | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/contrib/fast-import/git-p4 b/contrib/fast-import/git-p4 index d8de9f6c25..87ca51e401 100755 --- a/contrib/fast-import/git-p4 +++ b/contrib/fast-import/git-p4 @@ -687,6 +687,10 @@ class P4Submit(Command): else: return False + allowSubmit = gitConfig("git-p4.allowSubmit") + if len(allowSubmit) > 0 and not self.master in allowSubmit.split(","): + die("%s is not in git-p4.allowSubmit" % self.master) + [upstream, settings] = findUpstreamBranchPoint() self.depotPath = settings['depot-paths'][0] if len(self.origin) == 0: From d2bf48d2ad653ee8a052aa460ca5c6ef29dce41d Mon Sep 17 00:00:00 2001 From: Jeff King Date: Thu, 26 Jun 2008 04:08:41 -0400 Subject: [PATCH 124/295] improve for-each-ref test script Previously, we did a sanity check by doing for-each-ref using each possible format atom. However, we never checked the actual output produced by that atom, which recently let an obvious bug go undetected for some time. While we're at it, also clean up a few '!' into test_must_fail. Signed-off-by: Junio C Hamano --- t/t6300-for-each-ref.sh | 87 +++++++++++++++++++++++++++++++++-------- 1 file changed, 70 insertions(+), 17 deletions(-) diff --git a/t/t6300-for-each-ref.sh b/t/t6300-for-each-ref.sh index 91ea85d99b..a3c8941c72 100755 --- a/t/t6300-for-each-ref.sh +++ b/t/t6300-for-each-ref.sh @@ -26,25 +26,78 @@ test_expect_success 'Create sample commit with known timestamp' ' git tag -a -m "Tagging at $datestamp" testtag ' -test_expect_success 'Check atom names are valid' ' - bad= - for token in \ - refname objecttype objectsize objectname tree parent \ - numparent object type author authorname authoremail \ - authordate committer committername committeremail \ - committerdate tag tagger taggername taggeremail \ - taggerdate creator creatordate subject body contents - do - git for-each-ref --format="$token=%($token)" refs/heads || { - bad=$token - break - } - done - test -z "$bad" +test_atom() { + case "$1" in + head) ref=refs/heads/master ;; + tag) ref=refs/tags/testtag ;; + esac + printf '%s\n' "$3" >expected + test_expect_${4:-success} "basic atom: $1 $2" " + git for-each-ref --format='%($2)' $ref >actual && + test_cmp expected actual + " +} + +test_atom head refname refs/heads/master +test_atom head objecttype commit +test_atom head objectsize 171 +test_atom head objectname 67a36f10722846e891fbada1ba48ed035de75581 +test_atom head tree 0e51c00fcb93dffc755546f27593d511e1bdb46f +test_atom head parent '' +test_atom head numparent 0 +test_atom head object '' +test_atom head type '' +test_atom head author 'A U Thor 1151939924 +0200' +test_atom head authorname 'A U Thor' +test_atom head authoremail '' +test_atom head authordate 'Mon Jul 3 17:18:44 2006 +0200' +test_atom head committer 'C O Mitter 1151939923 +0200' +test_atom head committername 'C O Mitter' +test_atom head committeremail '' +test_atom head committerdate 'Mon Jul 3 17:18:43 2006 +0200' +test_atom head tag '' +test_atom head tagger '' +test_atom head taggername '' +test_atom head taggeremail '' +test_atom head taggerdate '' +test_atom head creator 'C O Mitter 1151939923 +0200' +test_atom head creatordate 'Mon Jul 3 17:18:43 2006 +0200' +test_atom head subject 'Initial' +test_atom head body '' +test_atom head contents 'Initial +' + +test_atom tag refname refs/tags/testtag +test_atom tag objecttype tag +test_atom tag objectsize 154 +test_atom tag objectname 98b46b1d36e5b07909de1b3886224e3e81e87322 +test_atom tag tree '' +test_atom tag parent '' +test_atom tag numparent '' +test_atom tag object '67a36f10722846e891fbada1ba48ed035de75581' +test_atom tag type 'commit' +test_atom tag author '' +test_atom tag authorname '' +test_atom tag authoremail '' +test_atom tag authordate '' +test_atom tag committer '' +test_atom tag committername '' +test_atom tag committeremail '' +test_atom tag committerdate '' +test_atom tag tag 'testtag' +test_atom tag tagger 'C O Mitter 1151939925 +0200' +test_atom tag taggername 'C O Mitter' +test_atom tag taggeremail '' +test_atom tag taggerdate 'Mon Jul 3 17:18:45 2006 +0200' +test_atom tag creator 'C O Mitter 1151939925 +0200' +test_atom tag creatordate 'Mon Jul 3 17:18:45 2006 +0200' +test_atom tag subject 'Tagging at 1151939927' +test_atom tag body '' +test_atom tag contents 'Tagging at 1151939927 ' test_expect_success 'Check invalid atoms names are errors' ' - ! git-for-each-ref --format="%(INVALID)" refs/heads + test_must_fail git-for-each-ref --format="%(INVALID)" refs/heads ' test_expect_success 'Check format specifiers are ignored in naming date atoms' ' @@ -64,7 +117,7 @@ test_expect_success 'Check valid format specifiers for date fields' ' ' test_expect_success 'Check invalid format specifiers are errors' ' - ! git-for-each-ref --format="%(authordate:INVALID)" refs/heads + test_must_fail git-for-each-ref --format="%(authordate:INVALID)" refs/heads ' cat >expected <<\EOF From 18374e584ca7a820457c1d83ee99867c216e7b75 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 13:16:33 -0700 Subject: [PATCH 125/295] diff --check: do not discard error status upon seeing a good line "git diff --check" should return non-zero when there was any whitespace error but the code only paid attention to the error status of the last new line in the patch. Signed-off-by: Junio C Hamano --- diff.c | 8 +++++--- t/t4017-diff-retval.sh | 8 ++++++++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/diff.c b/diff.c index 5262490086..f281c5b82a 100644 --- a/diff.c +++ b/diff.c @@ -1150,12 +1150,14 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) char *err; if (line[0] == '+') { + unsigned bad; data->lineno++; - data->status = check_and_emit_line(line + 1, len - 1, + bad = check_and_emit_line(line + 1, len - 1, data->ws_rule, NULL, NULL, NULL, NULL); - if (!data->status) + if (!bad) return; - err = whitespace_error_string(data->status); + data->status |= bad; + err = whitespace_error_string(bad); fprintf(data->file, "%s:%d: %s.\n", data->filename, data->lineno, err); free(err); emit_line(data->file, set, reset, line, 1); diff --git a/t/t4017-diff-retval.sh b/t/t4017-diff-retval.sh index dc0b7126cc..0d0fb87f57 100755 --- a/t/t4017-diff-retval.sh +++ b/t/t4017-diff-retval.sh @@ -105,4 +105,12 @@ test_expect_success '--check with --no-pager returns 2 for dirty difference' ' ' + +test_expect_success 'check should test not just the last line' ' + echo "" >>a && + git --no-pager diff --check + test $? = 2 + +' + test_done From bc7c73e29cfb38232b5b6b1d1e8d59e7145a9860 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sat, 1 Dec 2007 22:16:19 -0800 Subject: [PATCH 126/295] git-shell: accept "git foo" form This is a backport of 0a47dc110e042b5bcc63dc94c8d517e67efe9306 to 'maint' to be included in 1.5.6.2 so that older server side can accept dashless form of request when clients are updated. Signed-off-by: Junio C Hamano --- shell.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/shell.c b/shell.c index 9826109d5b..b27d01c9e4 100644 --- a/shell.c +++ b/shell.c @@ -7,6 +7,7 @@ static int do_generic_cmd(const char *me, char *arg) { const char *my_argv[4]; + setup_path(NULL); if (!arg || !(arg = sq_dequote(arg))) die("bad argument"); if (prefixcmp(me, "git-")) @@ -29,7 +30,6 @@ static int do_cvs_cmd(const char *me, char *arg) die("git-cvsserver only handles server: %s", arg); setup_path(NULL); - return execv_git_cmd(cvsserver_argv); } @@ -49,15 +49,24 @@ int main(int argc, char **argv) char *prog; struct commands *cmd; + /* + * Special hack to pretend to be a CVS server + */ if (argc == 2 && !strcmp(argv[1], "cvs server")) argv--; - /* We want to see "-c cmd args", and nothing else */ + + /* + * We do not accept anything but "-c" followed by "cmd arg", + * where "cmd" is a very limited subset of git commands. + */ else if (argc != 3 || strcmp(argv[1], "-c")) die("What do you think I am? A shell?"); prog = argv[2]; - argv += 2; - argc -= 2; + if (!strncmp(prog, "git", 3) && isspace(prog[3])) + /* Accept "git foo" as if the caller said "git-foo". */ + prog[3] = '-'; + for (cmd = cmd_list ; cmd->name ; cmd++) { int len = strlen(cmd->name); char *arg; From 872354dcb3ce5f34f7ddb12d2c89d26a1ea4daf0 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 17:11:21 -0700 Subject: [PATCH 127/295] GIT 1.5.4.6 Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.5.4.6.txt | 43 ++++++++++++++++++++++++++++++ GIT-VERSION-GEN | 2 +- RelNotes | 2 +- 3 files changed, 45 insertions(+), 2 deletions(-) create mode 100644 Documentation/RelNotes-1.5.4.6.txt diff --git a/Documentation/RelNotes-1.5.4.6.txt b/Documentation/RelNotes-1.5.4.6.txt new file mode 100644 index 0000000000..3e3c3e55a3 --- /dev/null +++ b/Documentation/RelNotes-1.5.4.6.txt @@ -0,0 +1,43 @@ +GIT v1.5.4.6 Release Notes +========================== + +I personally do not think there is any reason anybody should want to +run v1.5.4.X series these days, because 'master' version is always +more stable than any tagged released version of git. + +This is primarily to futureproof "git-shell" to accept requests +without a dash between "git" and subcommand name (e.g. "git +upload-pack") which the newer client will start to make sometime in +the future. + +Fixes since v1.5.4.5 +-------------------- + + * Command line option "-n" to "git-repack" was not correctly parsed. + + * Error messages from "git-apply" when the patchfile cannot be opened + have been improved. + + * Error messages from "git-bisect" when given nonsense revisions have + been improved. + + * reflog syntax that uses time e.g. "HEAD@{10 seconds ago}:path" did not + stop parsing at the closing "}". + + * "git rev-parse --symbolic-full-name ^master^2" printed solitary "^", + but it should print nothing. + + * "git apply" did not enforce "match at the beginning" correctly. + + * a path specification "a/b" in .gitattributes file should not match + "sub/a/b", but it did. + + * "git log --date-order --topo-order" did not override the earlier + date-order with topo-order as expected. + + * "git fast-export" did not export octopus merges correctly. + + * "git archive --prefix=$path/" mishandled gitattributes. + +As usual, it also comes with many documentation fixes and clarifications. + diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index 85747e000a..94da67267c 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,7 +1,7 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v1.5.4.5.GIT +DEF_VER=v1.5.4.6.GIT LF=' ' diff --git a/RelNotes b/RelNotes index e13dbd4f9f..b9aa240526 120000 --- a/RelNotes +++ b/RelNotes @@ -1 +1 @@ -Documentation/RelNotes-1.5.4.5.txt \ No newline at end of file +Documentation/RelNotes-1.5.4.6.txt \ No newline at end of file From 006f31d77f3dd5f813557c2839b39b2aaa22b925 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 17:16:50 -0700 Subject: [PATCH 128/295] GIT 1.5.5.5 Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.5.5.5.txt | 11 +++++++++++ GIT-VERSION-GEN | 2 +- RelNotes | 2 +- 3 files changed, 13 insertions(+), 2 deletions(-) create mode 100644 Documentation/RelNotes-1.5.5.5.txt diff --git a/Documentation/RelNotes-1.5.5.5.txt b/Documentation/RelNotes-1.5.5.5.txt new file mode 100644 index 0000000000..30fa3615c7 --- /dev/null +++ b/Documentation/RelNotes-1.5.5.5.txt @@ -0,0 +1,11 @@ +GIT v1.5.5.5 Release Notes +========================== + +I personally do not think there is any reason anybody should want to +run v1.5.5.X series these days, because 'master' version is always +more stable than any tagged released version of git. + +This is primarily to futureproof "git-shell" to accept requests +without a dash between "git" and subcommand name (e.g. "git +upload-pack") which the newer client will start to make sometime in +the future. diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index 98d650aa62..af9d78daea 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -1,7 +1,7 @@ #!/bin/sh GVF=GIT-VERSION-FILE -DEF_VER=v1.5.5.4.GIT +DEF_VER=v1.5.5.5.GIT LF=' ' diff --git a/RelNotes b/RelNotes index 1b9812afe7..61a6d5cf29 120000 --- a/RelNotes +++ b/RelNotes @@ -1 +1 @@ -Documentation/RelNotes-1.5.5.4.txt \ No newline at end of file +Documentation/RelNotes-1.5.5.5.txt \ No newline at end of file From 5ff10dd602f5926f0f5a73ae7de5866713428aa7 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 15:34:54 -0700 Subject: [PATCH 129/295] diff --check: explain why we do not care whether old side is binary All other codepaths refrain from running textual diff when either the old or the new side is binary, but this function only checks the new side. I was almost going to change it to check both, but that would be a bad change. Explain why to prevent future mistakes. Signed-off-by: Junio C Hamano --- diff.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/diff.c b/diff.c index 893942359b..c00d633c12 100644 --- a/diff.c +++ b/diff.c @@ -1544,8 +1544,9 @@ static void builtin_diffstat(const char *name_a, const char *name_b, static void builtin_checkdiff(const char *name_a, const char *name_b, const char *attr_path, - struct diff_filespec *one, - struct diff_filespec *two, struct diff_options *o) + struct diff_filespec *one, + struct diff_filespec *two, + struct diff_options *o) { mmfile_t mf1, mf2; struct checkdiff_t data; @@ -1564,6 +1565,12 @@ static void builtin_checkdiff(const char *name_a, const char *name_b, if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); + /* + * All the other codepaths check both sides, but not checking + * the "old" side here is deliberate. We are checking the newly + * introduced changes, and as long as the "new" side is text, we + * can and should check what it introduces. + */ if (diff_filespec_is_binary(two)) goto free_and_return; else { From 8f8841e9c8e6a26153b0cf9417c7540cf65ef09f Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 15:35:21 -0700 Subject: [PATCH 130/295] check_and_emit_line(): rename and refactor The function name was too bland and not explicit enough as to what it is checking. Split it into two, and call the one that checks if there is a whitespace breakage "ws_check()", and call the other one that checks and emits the line after color coding "ws_check_emit()". Signed-off-by: Junio C Hamano --- builtin-apply.c | 5 ++--- cache.h | 5 ++--- diff.c | 13 ++++++------- ws.c | 18 +++++++++++++++--- 4 files changed, 25 insertions(+), 16 deletions(-) diff --git a/builtin-apply.c b/builtin-apply.c index c497889312..92f00471bb 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -979,8 +979,7 @@ static int find_header(char *line, unsigned long size, int *hdrsize, struct patc static void check_whitespace(const char *line, int len, unsigned ws_rule) { char *err; - unsigned result = check_and_emit_line(line + 1, len - 1, ws_rule, - NULL, NULL, NULL, NULL); + unsigned result = ws_check(line + 1, len - 1, ws_rule); if (!result) return; @@ -991,7 +990,7 @@ static void check_whitespace(const char *line, int len, unsigned ws_rule) else { err = whitespace_error_string(result); fprintf(stderr, "%s:%d: %s.\n%.*s\n", - patch_input_file, linenr, err, len - 2, line + 1); + patch_input_file, linenr, err, len - 2, line + 1); free(err); } } diff --git a/cache.h b/cache.h index 64ef86e129..3dfa53c566 100644 --- a/cache.h +++ b/cache.h @@ -819,9 +819,8 @@ void shift_tree(const unsigned char *, const unsigned char *, unsigned char *, i extern unsigned whitespace_rule_cfg; extern unsigned whitespace_rule(const char *); extern unsigned parse_whitespace_rule(const char *); -extern unsigned check_and_emit_line(const char *line, int len, unsigned ws_rule, - FILE *stream, const char *set, - const char *reset, const char *ws); +extern unsigned ws_check(const char *line, int len, unsigned ws_rule); +extern void ws_check_emit(const char *line, int len, unsigned ws_rule, FILE *stream, const char *set, const char *reset, const char *ws); extern char *whitespace_error_string(unsigned ws); extern int ws_fix_copy(char *, const char *, int, unsigned, int *); diff --git a/diff.c b/diff.c index c00d633c12..52a34eec91 100644 --- a/diff.c +++ b/diff.c @@ -535,9 +535,9 @@ static void emit_add_line(const char *reset, struct emit_callback *ecbdata, cons else { /* Emit just the prefix, then the rest. */ emit_line(ecbdata->file, set, reset, line, ecbdata->nparents); - (void)check_and_emit_line(line + ecbdata->nparents, - len - ecbdata->nparents, ecbdata->ws_rule, - ecbdata->file, set, reset, ws); + ws_check_emit(line + ecbdata->nparents, + len - ecbdata->nparents, ecbdata->ws_rule, + ecbdata->file, set, reset, ws); } } @@ -1153,8 +1153,7 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) if (line[0] == '+') { unsigned bad; data->lineno++; - bad = check_and_emit_line(line + 1, len - 1, - data->ws_rule, NULL, NULL, NULL, NULL); + bad = ws_check(line + 1, len - 1, data->ws_rule); if (!bad) return; data->status |= bad; @@ -1162,8 +1161,8 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) fprintf(data->file, "%s:%d: %s.\n", data->filename, data->lineno, err); free(err); emit_line(data->file, set, reset, line, 1); - (void)check_and_emit_line(line + 1, len - 1, data->ws_rule, - data->file, set, reset, ws); + ws_check_emit(line + 1, len - 1, data->ws_rule, + data->file, set, reset, ws); } else if (line[0] == ' ') data->lineno++; else if (line[0] == '@') { diff --git a/ws.c b/ws.c index ba7e834ca8..24d3e3de07 100644 --- a/ws.c +++ b/ws.c @@ -117,9 +117,9 @@ char *whitespace_error_string(unsigned ws) } /* If stream is non-NULL, emits the line after checking. */ -unsigned check_and_emit_line(const char *line, int len, unsigned ws_rule, - FILE *stream, const char *set, - const char *reset, const char *ws) +static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule, + FILE *stream, const char *set, + const char *reset, const char *ws) { unsigned result = 0; int written = 0; @@ -213,6 +213,18 @@ unsigned check_and_emit_line(const char *line, int len, unsigned ws_rule, return result; } +void ws_check_emit(const char *line, int len, unsigned ws_rule, + FILE *stream, const char *set, + const char *reset, const char *ws) +{ + (void)ws_check_emit_1(line, len, ws_rule, stream, set, reset, ws); +} + +unsigned ws_check(const char *line, int len, unsigned ws_rule) +{ + return ws_check_emit_1(line, len, ws_rule, NULL, NULL, NULL, NULL); +} + /* Copy the line to the buffer while fixing whitespaces */ int ws_fix_copy(char *dst, const char *src, int len, unsigned ws_rule, int *error_count) { From 4c7ba956a32d72bb1e6645e2e3adba92a9024708 Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Thu, 26 Jun 2008 20:35:19 +0200 Subject: [PATCH 131/295] test-lib.sh: show git init output when in verbose mode Signed-off-by: Lea Wiemann Signed-off-by: Junio C Hamano --- t/test-lib.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/t/test-lib.sh b/t/test-lib.sh index 4010110010..c0c5e0e83b 100644 --- a/t/test-lib.sh +++ b/t/test-lib.sh @@ -407,7 +407,7 @@ test_create_repo () { repo="$1" mkdir "$repo" cd "$repo" || error "Cannot setup test environment" - "$GIT_EXEC_PATH/git" init "--template=$GIT_EXEC_PATH/templates/blt/" >/dev/null 2>&1 || + "$GIT_EXEC_PATH/git" init "--template=$GIT_EXEC_PATH/templates/blt/" >&3 2>&4 || error "cannot run git init -- have you built things yet?" mv .git/hooks .git/hooks-disabled cd "$owd" From d54467b8c319571b5dc433b1f7e471c4b0f21caf Mon Sep 17 00:00:00 2001 From: Ted Percival Date: Thu, 26 Jun 2008 23:22:19 +1000 Subject: [PATCH 132/295] Don't use dash commands (git-foo) in tutorial-2 Signed-off-by: Ted Percival Signed-off-by: Junio C Hamano --- Documentation/gittutorial-2.txt | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/gittutorial-2.txt b/Documentation/gittutorial-2.txt index e3d5c1fbf0..31e8a23a4f 100644 --- a/Documentation/gittutorial-2.txt +++ b/Documentation/gittutorial-2.txt @@ -61,9 +61,9 @@ from your own version. Note that you can shorten it to only a few characters to save yourself typing all 40 hex digits: ------------------------------------------------ -$ git-cat-file -t 54196cc2 +$ git cat-file -t 54196cc2 commit -$ git-cat-file commit 54196cc2 +$ git cat-file commit 54196cc2 tree 92b8b694ffb1675e5975148e1121810081dbdffe author J. Bruce Fields 1143414668 -0500 committer J. Bruce Fields 1143414668 -0500 @@ -166,7 +166,7 @@ hello world! and the "parent" object refers to the previous commit: ------------------------------------------------ -$ git-cat-file commit 54196cc2 +$ git cat-file commit 54196cc2 tree 92b8b694ffb1675e5975148e1121810081dbdffe author J. Bruce Fields 1143414668 -0500 committer J. Bruce Fields 1143414668 -0500 @@ -246,7 +246,7 @@ The last diff is empty, but no new commits have been made, and the head still doesn't contain the new line: ------------------------------------------------ -$ git-diff HEAD +$ git diff HEAD diff --git a/file.txt b/file.txt index a042389..513feba 100644 --- a/file.txt @@ -273,7 +273,7 @@ hello world, again So what our "git add" did was store a new blob and then put a reference to it in the index file. If we modify the file again, -we'll see that the new modifications are reflected in the "git-diff" +we'll see that the new modifications are reflected in the "git diff" output: ------------------------------------------------ From 1ba111d1d6bd90b2c120ceb05418e01ee304cc46 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 15:36:34 -0700 Subject: [PATCH 133/295] checkdiff: pass diff_options to the callback This way, we could later use more information from the diff_options. Signed-off-by: Junio C Hamano --- diff.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/diff.c b/diff.c index 52a34eec91..6bcbe20828 100644 --- a/diff.c +++ b/diff.c @@ -1136,18 +1136,19 @@ static void free_diffstat_info(struct diffstat_t *diffstat) struct checkdiff_t { struct xdiff_emit_state xm; const char *filename; - int lineno, color_diff; + int lineno; + struct diff_options *o; unsigned ws_rule; unsigned status; - FILE *file; }; static void checkdiff_consume(void *priv, char *line, unsigned long len) { struct checkdiff_t *data = priv; - const char *ws = diff_get_color(data->color_diff, DIFF_WHITESPACE); - const char *reset = diff_get_color(data->color_diff, DIFF_RESET); - const char *set = diff_get_color(data->color_diff, DIFF_FILE_NEW); + int color_diff = DIFF_OPT_TST(data->o, COLOR_DIFF); + const char *ws = diff_get_color(color_diff, DIFF_WHITESPACE); + const char *reset = diff_get_color(color_diff, DIFF_RESET); + const char *set = diff_get_color(color_diff, DIFF_FILE_NEW); char *err; if (line[0] == '+') { @@ -1158,11 +1159,12 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) return; data->status |= bad; err = whitespace_error_string(bad); - fprintf(data->file, "%s:%d: %s.\n", data->filename, data->lineno, err); + fprintf(data->o->file, "%s:%d: %s.\n", + data->filename, data->lineno, err); free(err); - emit_line(data->file, set, reset, line, 1); + emit_line(data->o->file, set, reset, line, 1); ws_check_emit(line + 1, len - 1, data->ws_rule, - data->file, set, reset, ws); + data->o->file, set, reset, ws); } else if (line[0] == ' ') data->lineno++; else if (line[0] == '@') { @@ -1557,9 +1559,8 @@ static void builtin_checkdiff(const char *name_a, const char *name_b, data.xm.consume = checkdiff_consume; data.filename = name_b ? name_b : name_a; data.lineno = 0; - data.color_diff = DIFF_OPT_TST(o, COLOR_DIFF); + data.o = o; data.ws_rule = whitespace_rule(attr_path); - data.file = o->file; if (fill_mmfile(&mf1, one) < 0 || fill_mmfile(&mf2, two) < 0) die("unable to read files to diff"); From 877f23ccb88227203f2576abdfb5d1c15925fcb3 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 15:36:59 -0700 Subject: [PATCH 134/295] Teach "diff --check" about new blank lines at end When a patch adds new blank lines at the end, "git apply --whitespace" warns. This teaches "diff --check" to do the same. Signed-off-by: Junio C Hamano --- cache.h | 1 + diff.c | 17 +++++++++++++++-- t/t4015-diff-whitespace.sh | 6 ++++++ ws.c | 15 +++++++++++++++ 4 files changed, 37 insertions(+), 2 deletions(-) diff --git a/cache.h b/cache.h index 3dfa53c566..188428dd26 100644 --- a/cache.h +++ b/cache.h @@ -823,6 +823,7 @@ extern unsigned ws_check(const char *line, int len, unsigned ws_rule); extern void ws_check_emit(const char *line, int len, unsigned ws_rule, FILE *stream, const char *set, const char *reset, const char *ws); extern char *whitespace_error_string(unsigned ws); extern int ws_fix_copy(char *, const char *, int, unsigned, int *); +extern int ws_blank_line(const char *line, int len, unsigned ws_rule); /* ls-files */ int pathspec_match(const char **spec, char *matched, const char *filename, int skiplen); diff --git a/diff.c b/diff.c index 6bcbe20828..f31c721168 100644 --- a/diff.c +++ b/diff.c @@ -1140,6 +1140,7 @@ struct checkdiff_t { struct diff_options *o; unsigned ws_rule; unsigned status; + int trailing_blanks_start; }; static void checkdiff_consume(void *priv, char *line, unsigned long len) @@ -1154,6 +1155,10 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) if (line[0] == '+') { unsigned bad; data->lineno++; + if (!ws_blank_line(line + 1, len - 1, data->ws_rule)) + data->trailing_blanks_start = 0; + else if (!data->trailing_blanks_start) + data->trailing_blanks_start = data->lineno; bad = ws_check(line + 1, len - 1, data->ws_rule); if (!bad) return; @@ -1165,14 +1170,16 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) emit_line(data->o->file, set, reset, line, 1); ws_check_emit(line + 1, len - 1, data->ws_rule, data->o->file, set, reset, ws); - } else if (line[0] == ' ') + } else if (line[0] == ' ') { data->lineno++; - else if (line[0] == '@') { + data->trailing_blanks_start = 0; + } else if (line[0] == '@') { char *plus = strchr(line, '+'); if (plus) data->lineno = strtol(plus, NULL, 10) - 1; else die("invalid diff"); + data->trailing_blanks_start = 0; } } @@ -1584,6 +1591,12 @@ static void builtin_checkdiff(const char *name_a, const char *name_b, ecb.outf = xdiff_outf; ecb.priv = &data; xdi_diff(&mf1, &mf2, &xpp, &xecfg, &ecb); + + if (data.trailing_blanks_start) { + fprintf(o->file, "%s:%d: ends with blank lines.\n", + data.filename, data.trailing_blanks_start); + data.status = 1; /* report errors */ + } } free_and_return: diff_free_filespec_data(one); diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh index b7cc6b28e6..0922c708f1 100755 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@ -335,4 +335,10 @@ test_expect_success 'line numbers in --check output are correct' ' ' +test_expect_success 'checkdiff detects trailing blank lines' ' + echo "foo();" >x && + echo "" >>x && + git diff --check | grep "ends with blank" +' + test_done diff --git a/ws.c b/ws.c index 24d3e3de07..7a7ff130a3 100644 --- a/ws.c +++ b/ws.c @@ -225,6 +225,21 @@ unsigned ws_check(const char *line, int len, unsigned ws_rule) return ws_check_emit_1(line, len, ws_rule, NULL, NULL, NULL, NULL); } +int ws_blank_line(const char *line, int len, unsigned ws_rule) +{ + /* + * We _might_ want to treat CR differently from other + * whitespace characters when ws_rule has WS_CR_AT_EOL, but + * for now we just use this stupid definition. + */ + while (len-- > 0) { + if (!isspace(*line)) + return 0; + line++; + } + return 1; +} + /* Copy the line to the buffer while fixing whitespaces */ int ws_fix_copy(char *dst, const char *src, int len, unsigned ws_rule, int *error_count) { From 049540435fa5f7f583b8f5af257322b17eac7375 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 15:37:21 -0700 Subject: [PATCH 135/295] diff --check: detect leftover conflict markers This teaches "diff --check" to detect and complain if the change adds lines that look like leftover conflict markers. We should be able to remove the old Perl script used in the sample pre-commit hook and modernize the script with this facility. Signed-off-by: Junio C Hamano --- diff.c | 35 +++++++++++++++++++++++++++++++++++ t/t4017-diff-retval.sh | 14 ++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/diff.c b/diff.c index f31c721168..d515b06ea3 100644 --- a/diff.c +++ b/diff.c @@ -1143,6 +1143,35 @@ struct checkdiff_t { int trailing_blanks_start; }; +static int is_conflict_marker(const char *line, unsigned long len) +{ + char firstchar; + int cnt; + + if (len < 8) + return 0; + firstchar = line[0]; + switch (firstchar) { + case '=': case '>': case '<': + break; + default: + return 0; + } + for (cnt = 1; cnt < 7; cnt++) + if (line[cnt] != firstchar) + return 0; + /* line[0] thru line[6] are same as firstchar */ + if (firstchar == '=') { + /* divider between ours and theirs? */ + if (len != 8 || line[7] != '\n') + return 0; + } else if (len < 8 || !isspace(line[7])) { + /* not divider before ours nor after theirs */ + return 0; + } + return 1; +} + static void checkdiff_consume(void *priv, char *line, unsigned long len) { struct checkdiff_t *data = priv; @@ -1159,6 +1188,12 @@ static void checkdiff_consume(void *priv, char *line, unsigned long len) data->trailing_blanks_start = 0; else if (!data->trailing_blanks_start) data->trailing_blanks_start = data->lineno; + if (is_conflict_marker(line + 1, len - 1)) { + data->status |= 1; + fprintf(data->o->file, + "%s:%d: leftover conflict marker\n", + data->filename, data->lineno); + } bad = ws_check(line + 1, len - 1, data->ws_rule); if (!bad) return; diff --git a/t/t4017-diff-retval.sh b/t/t4017-diff-retval.sh index 0d0fb87f57..d748d45dae 100755 --- a/t/t4017-diff-retval.sh +++ b/t/t4017-diff-retval.sh @@ -113,4 +113,18 @@ test_expect_success 'check should test not just the last line' ' ' +test_expect_success 'check detects leftover conflict markers' ' + git reset --hard && + git checkout HEAD^ && + echo binary >>b && + git commit -m "side" b && + test_must_fail git merge master && + git add b && ( + git --no-pager diff --cached --check >test.out + test $? = 2 + ) && + test "$(grep "conflict marker" test.out | wc -l)" = 3 && + git reset --hard +' + test_done From 03e2b630f05b88da5ff43f194fed25755de44e8b Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Thu, 26 Jun 2008 16:08:05 -0700 Subject: [PATCH 136/295] Update sample pre-commit hook to use "diff --check" Now "diff --check" can detect not just whitespace errors but also notices leftover conflict marker lines, we can use it in the sample pre-commit hook script. These days the object layer knows about the empty tree object without actually having one in the repository, so we can run the test even for the initial commit. Signed-off-by: Junio C Hamano --- templates/hooks--pre-commit.sample | 64 +++--------------------------- 1 file changed, 6 insertions(+), 58 deletions(-) diff --git a/templates/hooks--pre-commit.sample b/templates/hooks--pre-commit.sample index 71c10f25f4..0e49279c7f 100755 --- a/templates/hooks--pre-commit.sample +++ b/templates/hooks--pre-commit.sample @@ -7,64 +7,12 @@ # # To enable this hook, rename this file to "pre-commit". -# This is slightly modified from Andrew Morton's Perfect Patch. -# Lines you introduce should not have trailing whitespace. -# Also check for an indentation that has SP before a TAB. - if git-rev-parse --verify HEAD 2>/dev/null then - git-diff-index -p -M --cached HEAD -- + against=HEAD else - # NEEDSWORK: we should produce a diff with an empty tree here - # if we want to do the same verification for the initial import. - : -fi | -perl -e ' - my $found_bad = 0; - my $filename; - my $reported_filename = ""; - my $lineno; - sub bad_line { - my ($why, $line) = @_; - if (!$found_bad) { - print STDERR "*\n"; - print STDERR "* You have some suspicious patch lines:\n"; - print STDERR "*\n"; - $found_bad = 1; - } - if ($reported_filename ne $filename) { - print STDERR "* In $filename\n"; - $reported_filename = $filename; - } - print STDERR "* $why (line $lineno)\n"; - print STDERR "$filename:$lineno:$line\n"; - } - while (<>) { - if (m|^diff --git a/(.*) b/\1$|) { - $filename = $1; - next; - } - if (/^@@ -\S+ \+(\d+)/) { - $lineno = $1 - 1; - next; - } - if (/^ /) { - $lineno++; - next; - } - if (s/^\+//) { - $lineno++; - chomp; - if (/\s$/) { - bad_line("trailing whitespace", $_); - } - if (/^\s* \t/) { - bad_line("indent SP followed by a TAB", $_); - } - if (/^([<>])\1{6} |^={7}$/) { - bad_line("unresolved merge conflict", $_); - } - } - } - exit($found_bad); -' + # Initial commit: diff against an empty tree object + against=4b825dc642cb6eb9a060e54bf8d69288fbee4904 +fi + +exec git diff-index --check --cached $against -- From d0658ec6fac6b0a1830dbd2ead38facaff97fda7 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Wed, 25 Jun 2008 22:16:37 -0700 Subject: [PATCH 137/295] Document the double-dash "rev -- path" disambiguator This is a very well established command line convention that old residents of the git mailing list knew by heart and nobody even thought about documenting it explicitly, which was not very nice. Signed-off-by: Junio C Hamano --- Documentation/gitcli.txt | 37 +++++++++++++++++++++++++++++++++---- 1 file changed, 33 insertions(+), 4 deletions(-) diff --git a/Documentation/gitcli.txt b/Documentation/gitcli.txt index 8fb5d889e5..2316049865 100644 --- a/Documentation/gitcli.txt +++ b/Documentation/gitcli.txt @@ -13,8 +13,37 @@ gitcli DESCRIPTION ----------- -This manual describes best practice in how to use git CLI. Here are -the rules that you should follow when you are scripting git: +This manual describes the convention used throughout git CLI. + +Many commands take revisions (most often "commits", but sometimes +"tree-ish", depending on the context and command) and paths as their +arguments. Here are the rules: + + * Revisions come first and then paths. + E.g. in `git diff v1.0 v2.0 arch/x86 include/asm-x86`, + `v1.0` and `v2.0` are revisions and `arch/x86` and `include/asm-x86` + are paths. + + * When an argument can be misunderstood as either a revision or a path, + they can be disambiguated by placing `\--` between them. + E.g. `git diff \-- HEAD` is, "I have a file called HEAD in my work + tree. Please show changes between the version I staged in the index + and what I have in the work tree for that file". not "show difference + between the HEAD commit and the work tree as a whole". You can say + `git diff HEAD \--` to ask for the latter. + + * Without disambiguating `\--`, git makes a reasonable guess, but errors + out and asking you to disambiguate when ambiguous. E.g. if you have a + file called HEAD in your work tree, `git diff HEAD` is ambiguous, and + you have to say either `git diff HEAD \--` or `git diff \-- HEAD` to + disambiguate. + +When writing a script that is expected to handle random user-input, it is +a good practice to make it explicit which arguments are which by placing +disambiguating `\--` at appropriate places. + +Here are the rules regarding the "flags" that you should follow when you are +scripting git: * it's preferred to use the non dashed form of git commands, which means that you should prefer `"git foo"` to `"git-foo"`. @@ -34,8 +63,8 @@ the rules that you should follow when you are scripting git: if you happen to have a file called `HEAD` in the work tree. -ENHANCED CLI ------------- +ENHANCED OPTION PARSER +---------------------- From the git 1.5.4 series and further, many git commands (not all of them at the time of the writing though) come with an enhanced option parser. From bc0c0d81561bdbb8cb5e1f3af558390f1a0c86cb Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 27 Jun 2008 13:56:05 +0100 Subject: [PATCH 138/295] clone: respect url.insteadOf setting in global configs When we call "git clone" with a url that has a rewrite rule in either $HOME/.gitconfig or /etc/gitconfig, the URL can be different from what the command line expects it to be. So, let's use the URL as the remote structure has it, not the literal string from the command line. Noticed by Pieter de Bie. Signed-off-by: Johannes Schindelin Acked-by: Daniel Barkalow Signed-off-by: Junio C Hamano --- builtin-clone.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/builtin-clone.c b/builtin-clone.c index b2dfe1ab5c..9c028e76a5 100644 --- a/builtin-clone.c +++ b/builtin-clone.c @@ -452,7 +452,8 @@ int cmd_clone(int argc, const char **argv, const char *prefix) refs = clone_local(path, git_dir); else { struct remote *remote = remote_get(argv[0]); - struct transport *transport = transport_get(remote, argv[0]); + struct transport *transport = + transport_get(remote, remote->url[0]); if (!transport->get_refs_list || !transport->fetch) die("Don't know how to clone %s", transport->url); From 6315472eed9ff5f594560ddfd592ea21c665fe96 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Thu, 26 Jun 2008 23:59:50 -0400 Subject: [PATCH 139/295] fetch: report local storage errors in status table Previously, if there was an error while storing a local tracking ref, the low-level functions would report an error, but fetch's status output wouldn't indicate any problem. E.g., imagine you have an old "refs/remotes/origin/foo/bar" but upstream has deleted "foo/bar" in favor of a new branch "foo". You would get output like this: error: there are still refs under 'refs/remotes/origin/foo' From $url_of_repo * [new branch] foo -> origin/foo With this patch, the output takes into account the status of updating the local ref: error: there are still refs under 'refs/remotes/origin/foo' From $url_of_repo ! [new branch] foo -> origin/foo (unable to update local ref) Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin-fetch.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/builtin-fetch.c b/builtin-fetch.c index e81ee2d02b..7c16d38de7 100644 --- a/builtin-fetch.c +++ b/builtin-fetch.c @@ -233,10 +233,12 @@ static int update_local_ref(struct ref *ref, if (!is_null_sha1(ref->old_sha1) && !prefixcmp(ref->name, "refs/tags/")) { - sprintf(display, "- %-*s %-*s -> %s", + int r; + r = s_update_ref("updating tag", ref, 0); + sprintf(display, "%c %-*s %-*s -> %s%s", r ? '!' : '-', SUMMARY_WIDTH, "[tag update]", REFCOL_WIDTH, remote, - pretty_ref); - return s_update_ref("updating tag", ref, 0); + pretty_ref, r ? " (unable to update local ref)" : ""); + return r; } current = lookup_commit_reference_gently(ref->old_sha1, 1); @@ -244,6 +246,7 @@ static int update_local_ref(struct ref *ref, if (!current || !updated) { const char *msg; const char *what; + int r; if (!strncmp(ref->name, "refs/tags/", 10)) { msg = "storing tag"; what = "[new tag]"; @@ -253,27 +256,36 @@ static int update_local_ref(struct ref *ref, what = "[new branch]"; } - sprintf(display, "* %-*s %-*s -> %s", SUMMARY_WIDTH, what, - REFCOL_WIDTH, remote, pretty_ref); - return s_update_ref(msg, ref, 0); + r = s_update_ref(msg, ref, 0); + sprintf(display, "%c %-*s %-*s -> %s%s", r ? '!' : '*', + SUMMARY_WIDTH, what, REFCOL_WIDTH, remote, pretty_ref, + r ? " (unable to update local ref)" : ""); + return r; } if (in_merge_bases(current, &updated, 1)) { char quickref[83]; + int r; strcpy(quickref, find_unique_abbrev(current->object.sha1, DEFAULT_ABBREV)); strcat(quickref, ".."); strcat(quickref, find_unique_abbrev(ref->new_sha1, DEFAULT_ABBREV)); - sprintf(display, " %-*s %-*s -> %s", SUMMARY_WIDTH, quickref, - REFCOL_WIDTH, remote, pretty_ref); - return s_update_ref("fast forward", ref, 1); + r = s_update_ref("fast forward", ref, 1); + sprintf(display, "%c %-*s %-*s -> %s%s", r ? '!' : ' ', + SUMMARY_WIDTH, quickref, REFCOL_WIDTH, remote, + pretty_ref, r ? " (unable to update local ref)" : ""); + return r; } else if (force || ref->force) { char quickref[84]; + int r; strcpy(quickref, find_unique_abbrev(current->object.sha1, DEFAULT_ABBREV)); strcat(quickref, "..."); strcat(quickref, find_unique_abbrev(ref->new_sha1, DEFAULT_ABBREV)); - sprintf(display, "+ %-*s %-*s -> %s (forced update)", - SUMMARY_WIDTH, quickref, REFCOL_WIDTH, remote, pretty_ref); - return s_update_ref("forced-update", ref, 1); + r = s_update_ref("forced-update", ref, 1); + sprintf(display, "%c %-*s %-*s -> %s (%s)", r ? '!' : '+', + SUMMARY_WIDTH, quickref, REFCOL_WIDTH, remote, + pretty_ref, + r ? "unable to update local ref" : "forced update"); + return r; } else { sprintf(display, "! %-*s %-*s -> %s (non fast forward)", SUMMARY_WIDTH, "[rejected]", REFCOL_WIDTH, remote, From 7a07841c0ba8d791dd4c7363eaf004b4a7d11fb6 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 27 Jun 2008 14:39:12 -0400 Subject: [PATCH 140/295] git-apply: handle a patch that touches the same path more than once better When working with a lot of people who backport patches all day long, every once in a while I get a patch that modifies the same file more than once inside the same patch. git-apply either fails if the second change relies on the first change or silently drops the first change if the second change is independent. The silent part is the scary scenario for us. Also this behaviour is different from the patch-utils. I have modified git-apply to create a table of the filenames of files it modifies such that if a later patch chunk modifies a file in the table it will buffer the previously changed file instead of reading the original file from disk. Logic has been put in to handle creations/deletions/renames/copies. All the relevant tests of git-apply succeed. A new test has been added to cover the cases I addressed. The fix is relatively straight-forward. Signed-off-by: Don Zickus Signed-off-by: Junio C Hamano --- builtin-apply.c | 82 +++++++++++++++++++++++++++++++++----- t/t4127-apply-same-fn.sh | 85 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 157 insertions(+), 10 deletions(-) create mode 100755 t/t4127-apply-same-fn.sh diff --git a/builtin-apply.c b/builtin-apply.c index c497889312..318504a037 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -12,6 +12,7 @@ #include "blob.h" #include "delta.h" #include "builtin.h" +#include "path-list.h" /* * --check turns on checking that the working tree matches the @@ -185,6 +186,13 @@ struct image { struct line *line; }; +/* + * Records filenames that have been touched, in order to handle + * the case where more than one patches touch the same file. + */ + +static struct path_list fn_table; + static uint32_t hash_line(const char *cp, size_t len) { size_t i; @@ -2176,15 +2184,62 @@ static int read_file_or_gitlink(struct cache_entry *ce, struct strbuf *buf) return 0; } +static struct patch *in_fn_table(const char *name) +{ + struct path_list_item *item; + + if (name == NULL) + return NULL; + + item = path_list_lookup(name, &fn_table); + if (item != NULL) + return (struct patch *)item->util; + + return NULL; +} + +static void add_to_fn_table(struct patch *patch) +{ + struct path_list_item *item; + + /* + * Always add new_name unless patch is a deletion + * This should cover the cases for normal diffs, + * file creations and copies + */ + if (patch->new_name != NULL) { + item = path_list_insert(patch->new_name, &fn_table); + item->util = patch; + } + + /* + * store a failure on rename/deletion cases because + * later chunks shouldn't patch old names + */ + if ((patch->new_name == NULL) || (patch->is_rename)) { + item = path_list_insert(patch->old_name, &fn_table); + item->util = (struct patch *) -1; + } +} + static int apply_data(struct patch *patch, struct stat *st, struct cache_entry *ce) { struct strbuf buf; struct image image; size_t len; char *img; + struct patch *tpatch; strbuf_init(&buf, 0); - if (cached) { + + if ((tpatch = in_fn_table(patch->old_name)) != NULL) { + if (tpatch == (struct patch *) -1) { + return error("patch %s has been renamed/deleted", + patch->old_name); + } + /* We have a patched copy in memory use that */ + strbuf_add(&buf, tpatch->result, tpatch->resultsize); + } else if (cached) { if (read_file_or_gitlink(ce, &buf)) return error("read of %s failed", patch->old_name); } else if (patch->old_name) { @@ -2211,6 +2266,7 @@ static int apply_data(struct patch *patch, struct stat *st, struct cache_entry * return -1; /* note with --reject this succeeds. */ patch->result = image.buf; patch->resultsize = image.len; + add_to_fn_table(patch); free(image.line_allocated); if (0 < patch->is_delete && patch->resultsize) @@ -2255,6 +2311,7 @@ static int verify_index_match(struct cache_entry *ce, struct stat *st) static int check_preimage(struct patch *patch, struct cache_entry **ce, struct stat *st) { const char *old_name = patch->old_name; + struct patch *tpatch; int stat_ret = 0; unsigned st_mode = 0; @@ -2268,12 +2325,17 @@ static int check_preimage(struct patch *patch, struct cache_entry **ce, struct s return 0; assert(patch->is_new <= 0); - if (!cached) { + if ((tpatch = in_fn_table(old_name)) != NULL) { + if (tpatch == (struct patch *) -1) { + return error("%s: has been deleted/renamed", old_name); + } + st_mode = tpatch->new_mode; + } else if (!cached) { stat_ret = lstat(old_name, st); if (stat_ret && errno != ENOENT) return error("%s: %s", old_name, strerror(errno)); } - if (check_index) { + if (check_index && !tpatch) { int pos = cache_name_pos(old_name, strlen(old_name)); if (pos < 0) { if (patch->is_new < 0) @@ -2325,7 +2387,7 @@ static int check_preimage(struct patch *patch, struct cache_entry **ce, struct s return 0; } -static int check_patch(struct patch *patch, struct patch *prev_patch) +static int check_patch(struct patch *patch) { struct stat st; const char *old_name = patch->old_name; @@ -2342,8 +2404,7 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) return status; old_name = patch->old_name; - if (new_name && prev_patch && 0 < prev_patch->is_delete && - !strcmp(prev_patch->old_name, new_name)) + if (in_fn_table(new_name) == (struct patch *) -1) /* * A type-change diff is always split into a patch to * delete old, immediately followed by a patch to @@ -2393,15 +2454,14 @@ static int check_patch(struct patch *patch, struct patch *prev_patch) static int check_patch_list(struct patch *patch) { - struct patch *prev_patch = NULL; int err = 0; - for (prev_patch = NULL; patch ; patch = patch->next) { + while (patch) { if (apply_verbosely) say_patch_name(stderr, "Checking patch ", patch, "...\n"); - err |= check_patch(patch, prev_patch); - prev_patch = patch; + err |= check_patch(patch); + patch = patch->next; } return err; } @@ -2919,6 +2979,8 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) struct patch *list = NULL, **listp = &list; int skipped_patch = 0; + /* FIXME - memory leak when using multiple patch files as inputs */ + memset(&fn_table, 0, sizeof(struct path_list)); strbuf_init(&buf, 0); patch_input_file = filename; read_patch_file(&buf, fd); diff --git a/t/t4127-apply-same-fn.sh b/t/t4127-apply-same-fn.sh new file mode 100755 index 0000000000..2a6ed77c65 --- /dev/null +++ b/t/t4127-apply-same-fn.sh @@ -0,0 +1,85 @@ +#!/bin/sh + +test_description='apply same filename' + +. ./test-lib.sh + +test_expect_success setup ' + for i in a b c d e f g h i j k l m + do + echo $i + done >same_fn && + cp same_fn other_fn && + git add same_fn other_fn && + git commit -m initial +' +test_expect_success 'apply same filename with independent changes' ' + sed -i -e "s/^d/z/" same_fn && + git diff > patch0 && + git add same_fn && + sed -i -e "s/^i/y/" same_fn && + git diff >> patch0 && + cp same_fn same_fn2 && + git reset --hard && + git-apply patch0 && + diff same_fn same_fn2 +' + +test_expect_success 'apply same filename with overlapping changes' ' + git reset --hard + sed -i -e "s/^d/z/" same_fn && + git diff > patch0 && + git add same_fn && + sed -i -e "s/^e/y/" same_fn && + git diff >> patch0 && + cp same_fn same_fn2 && + git reset --hard && + git-apply patch0 && + diff same_fn same_fn2 +' + +test_expect_success 'apply same new filename after rename' ' + git reset --hard + git mv same_fn new_fn + sed -i -e "s/^d/z/" new_fn && + git add new_fn && + git diff -M --cached > patch1 && + sed -i -e "s/^e/y/" new_fn && + git diff >> patch1 && + cp new_fn new_fn2 && + git reset --hard && + git apply --index patch1 && + diff new_fn new_fn2 +' + +test_expect_success 'apply same old filename after rename -- should fail.' ' + git reset --hard + git mv same_fn new_fn + sed -i -e "s/^d/z/" new_fn && + git add new_fn && + git diff -M --cached > patch1 && + git mv new_fn same_fn + sed -i -e "s/^e/y/" same_fn && + git diff >> patch1 && + git reset --hard && + test_must_fail git apply patch1 +' + +test_expect_success 'apply A->B (rename), C->A (rename), A->A -- should pass.' ' + git reset --hard + git mv same_fn new_fn + sed -i -e "s/^d/z/" new_fn && + git add new_fn && + git diff -M --cached > patch1 && + git commit -m "a rename" && + git mv other_fn same_fn + sed -i -e "s/^e/y/" same_fn && + git add same_fn && + git diff -M --cached >> patch1 && + sed -i -e "s/^g/x/" same_fn && + git diff >> patch1 && + git reset --hard HEAD^ && + git apply patch1 +' + +test_done From 2dce956e397be8a769624e8693565b8a30056060 Mon Sep 17 00:00:00 2001 From: Christian Couder Date: Sat, 28 Jun 2008 06:35:03 +0200 Subject: [PATCH 141/295] help: check early if we have a command, if not try a documentation topic Before this patch, something like "git help tutorial" did not work, people had to use "git help gittutorial" which is not very intuitive. This patch uses the "is_git_command" function to test early if the argument passed to "git help" is a git command, and if this is not the case then we prefix the argument with "git" instead of "git-". This way, things like "git help tutorial" or "git help glossary" will work fine. The little downside of this patch is that the "is_git_command" is a little bit slow. Signed-off-by: Christian Couder Signed-off-by: Junio C Hamano --- help.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/help.c b/help.c index 8aff94c64a..5d1a773ad7 100644 --- a/help.c +++ b/help.c @@ -527,20 +527,26 @@ static int is_git_command(const char *s) is_in_cmdlist(&other_cmds, s); } +static const char *prepend(const char *prefix, const char *cmd) +{ + size_t pre_len = strlen(prefix); + size_t cmd_len = strlen(cmd); + char *p = xmalloc(pre_len + cmd_len + 1); + memcpy(p, prefix, pre_len); + strcpy(p + pre_len, cmd); + return p; +} + static const char *cmd_to_page(const char *git_cmd) { if (!git_cmd) return "git"; else if (!prefixcmp(git_cmd, "git")) return git_cmd; - else { - int page_len = strlen(git_cmd) + 4; - char *p = xmalloc(page_len + 1); - strcpy(p, "git-"); - strcpy(p + 4, git_cmd); - p[page_len] = 0; - return p; - } + else if (is_git_command(git_cmd)) + return prepend("git-", git_cmd); + else + return prepend("git", git_cmd); } static void setup_man_path(void) From 5b8e6f85f971dba8eeac048e7821978bbca14121 Mon Sep 17 00:00:00 2001 From: Dmitry Potapov Date: Sat, 28 Jun 2008 00:46:42 +0400 Subject: [PATCH 142/295] shrink git-shell by avoiding redundant dependencies A lot of modules that have nothing to do with git-shell functionality were linked in, bloating git-shell more than 8 times. This patch cuts off redundant dependencies by: 1. providing stubs for three functions that make no sense for git-shell; 2. moving quote_path_fully from environment.c to quote.c to make the later self sufficient; 3. moving make_absolute_path into a new separate file. The following numbers have been received with the default optimization settings on master using GCC 4.1.2: Before: text data bss dec hex filename 143915 1348 93168 238431 3a35f git-shell After: text data bss dec hex filename 17670 788 8232 26690 6842 git-shell Signed-off-by: Junio C Hamano --- Makefile | 1 + abspath.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++ environment.c | 1 - path.c | 67 -------------------------------------------------- quote.c | 2 ++ shell.c | 8 ++++++ 6 files changed, 79 insertions(+), 68 deletions(-) create mode 100644 abspath.c diff --git a/Makefile b/Makefile index 3584b8ccdf..bf77292f1c 100644 --- a/Makefile +++ b/Makefile @@ -378,6 +378,7 @@ LIB_H += unpack-trees.h LIB_H += utf8.h LIB_H += wt-status.h +LIB_OBJS += abspath.o LIB_OBJS += alias.o LIB_OBJS += alloc.o LIB_OBJS += archive.o diff --git a/abspath.c b/abspath.c new file mode 100644 index 0000000000..4f95a954d5 --- /dev/null +++ b/abspath.c @@ -0,0 +1,68 @@ +#include "cache.h" + +/* We allow "recursive" symbolic links. Only within reason, though. */ +#define MAXDEPTH 5 + +const char *make_absolute_path(const char *path) +{ + static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1]; + char cwd[1024] = ""; + int buf_index = 1, len; + + int depth = MAXDEPTH; + char *last_elem = NULL; + struct stat st; + + if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) + die ("Too long path: %.*s", 60, path); + + while (depth--) { + if (stat(buf, &st) || !S_ISDIR(st.st_mode)) { + char *last_slash = strrchr(buf, '/'); + if (last_slash) { + *last_slash = '\0'; + last_elem = xstrdup(last_slash + 1); + } else { + last_elem = xstrdup(buf); + *buf = '\0'; + } + } + + if (*buf) { + if (!*cwd && !getcwd(cwd, sizeof(cwd))) + die ("Could not get current working directory"); + + if (chdir(buf)) + die ("Could not switch to '%s'", buf); + } + if (!getcwd(buf, PATH_MAX)) + die ("Could not get current working directory"); + + if (last_elem) { + int len = strlen(buf); + if (len + strlen(last_elem) + 2 > PATH_MAX) + die ("Too long path name: '%s/%s'", + buf, last_elem); + buf[len] = '/'; + strcpy(buf + len + 1, last_elem); + free(last_elem); + last_elem = NULL; + } + + if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) { + len = readlink(buf, next_buf, PATH_MAX); + if (len < 0) + die ("Invalid symlink: %s", buf); + next_buf[len] = '\0'; + buf = next_buf; + buf_index = 1 - buf_index; + next_buf = bufs[buf_index]; + } else + break; + } + + if (*cwd && chdir(cwd)) + die ("Could not change back to '%s'", cwd); + + return buf; +} diff --git a/environment.c b/environment.c index 084ac8a436..4a88a17d54 100644 --- a/environment.c +++ b/environment.c @@ -13,7 +13,6 @@ char git_default_email[MAX_GITNAME]; char git_default_name[MAX_GITNAME]; int user_ident_explicitly_given; int trust_executable_bit = 1; -int quote_path_fully = 1; int has_symlinks = 1; int ignore_case; int assume_unchanged; diff --git a/path.c b/path.c index 6e3df18499..496123ca55 100644 --- a/path.c +++ b/path.c @@ -327,9 +327,6 @@ const char *make_nonrelative_path(const char *path) return buf; } -/* We allow "recursive" symbolic links. Only within reason, though. */ -#define MAXDEPTH 5 - const char *make_relative_path(const char *abs, const char *base) { static char buf[PATH_MAX + 1]; @@ -346,67 +343,3 @@ const char *make_relative_path(const char *abs, const char *base) strcpy(buf, abs + baselen); return buf; } - -const char *make_absolute_path(const char *path) -{ - static char bufs[2][PATH_MAX + 1], *buf = bufs[0], *next_buf = bufs[1]; - char cwd[1024] = ""; - int buf_index = 1, len; - - int depth = MAXDEPTH; - char *last_elem = NULL; - struct stat st; - - if (strlcpy(buf, path, PATH_MAX) >= PATH_MAX) - die ("Too long path: %.*s", 60, path); - - while (depth--) { - if (stat(buf, &st) || !S_ISDIR(st.st_mode)) { - char *last_slash = strrchr(buf, '/'); - if (last_slash) { - *last_slash = '\0'; - last_elem = xstrdup(last_slash + 1); - } else { - last_elem = xstrdup(buf); - *buf = '\0'; - } - } - - if (*buf) { - if (!*cwd && !getcwd(cwd, sizeof(cwd))) - die ("Could not get current working directory"); - - if (chdir(buf)) - die ("Could not switch to '%s'", buf); - } - if (!getcwd(buf, PATH_MAX)) - die ("Could not get current working directory"); - - if (last_elem) { - int len = strlen(buf); - if (len + strlen(last_elem) + 2 > PATH_MAX) - die ("Too long path name: '%s/%s'", - buf, last_elem); - buf[len] = '/'; - strcpy(buf + len + 1, last_elem); - free(last_elem); - last_elem = NULL; - } - - if (!lstat(buf, &st) && S_ISLNK(st.st_mode)) { - len = readlink(buf, next_buf, PATH_MAX); - if (len < 0) - die ("Invalid symlink: %s", buf); - next_buf[len] = '\0'; - buf = next_buf; - buf_index = 1 - buf_index; - next_buf = bufs[buf_index]; - } else - break; - } - - if (*cwd && chdir(cwd)) - die ("Could not change back to '%s'", cwd); - - return buf; -} diff --git a/quote.c b/quote.c index d5cf9d8f94..6a520855d6 100644 --- a/quote.c +++ b/quote.c @@ -1,6 +1,8 @@ #include "cache.h" #include "quote.h" +int quote_path_fully = 1; + /* Help to copy the thing properly quoted for the shell safety. * any single quote is replaced with '\'', any exclamation point * is replaced with '\!', and the whole thing is enclosed in a diff --git a/shell.c b/shell.c index b27d01c9e4..91ca7de082 100644 --- a/shell.c +++ b/shell.c @@ -3,6 +3,14 @@ #include "exec_cmd.h" #include "strbuf.h" +/* Stubs for functions that make no sense for git-shell. These stubs + * are provided here to avoid linking in external redundant modules. + */ +void release_pack_memory(size_t need, int fd){} +void trace_argv_printf(const char **argv, const char *fmt, ...){} +void trace_printf(const char *fmt, ...){} + + static int do_generic_cmd(const char *me, char *arg) { const char *my_argv[4]; From ef98c5cafb3e799b1568bb843fcd45920dc62f16 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 27 Jun 2008 13:24:47 +0100 Subject: [PATCH 143/295] commit-tree: lift completely arbitrary limit of 16 parents There is no really good reason to have a merge with more than 16 parents, but we have a history of giving our users rope. Combined with the fact that there was no good reason for that arbitrary limit in the first place, here is an all-too-easy to fix. Kind of wished-for by Len Brown. Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- builtin-commit-tree.c | 43 ++++++++++++++++++++----------------------- 1 file changed, 20 insertions(+), 23 deletions(-) diff --git a/builtin-commit-tree.c b/builtin-commit-tree.c index e5e4bdbe86..3881f6c2f5 100644 --- a/builtin-commit-tree.c +++ b/builtin-commit-tree.c @@ -24,26 +24,20 @@ static void check_valid(unsigned char *sha1, enum object_type expect) typename(expect)); } -/* - * Having more than two parents is not strange at all, and this is - * how multi-way merges are represented. - */ -#define MAXPARENT (16) -static unsigned char parent_sha1[MAXPARENT][20]; - static const char commit_tree_usage[] = "git-commit-tree [-p ]* < changelog"; -static int new_parent(int idx) +static void new_parent(struct commit *parent, struct commit_list **parents_p) { - int i; - unsigned char *sha1 = parent_sha1[idx]; - for (i = 0; i < idx; i++) { - if (!hashcmp(parent_sha1[i], sha1)) { + unsigned char *sha1 = parent->object.sha1; + struct commit_list *parents; + for (parents = *parents_p; parents; parents = parents->next) { + if (parents->item == parent) { error("duplicate parent %s ignored", sha1_to_hex(sha1)); - return 0; + return; } + parents_p = &parents->next; } - return 1; + commit_list_insert(parent, parents_p); } static const char commit_utf8_warn[] = @@ -54,7 +48,7 @@ static const char commit_utf8_warn[] = int cmd_commit_tree(int argc, const char **argv, const char *prefix) { int i; - int parents = 0; + struct commit_list *parents = NULL; unsigned char tree_sha1[20]; unsigned char commit_sha1[20]; struct strbuf buffer; @@ -69,18 +63,16 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) check_valid(tree_sha1, OBJ_TREE); for (i = 2; i < argc; i += 2) { + unsigned char sha1[20]; const char *a, *b; a = argv[i]; b = argv[i+1]; if (!b || strcmp(a, "-p")) usage(commit_tree_usage); - if (parents >= MAXPARENT) - die("Too many parents (%d max)", MAXPARENT); - if (get_sha1(b, parent_sha1[parents])) + if (get_sha1(b, sha1)) die("Not a valid object name %s", b); - check_valid(parent_sha1[parents], OBJ_COMMIT); - if (new_parent(parents)) - parents++; + check_valid(sha1, OBJ_COMMIT); + new_parent(lookup_commit(sha1), &parents); } /* Not having i18n.commitencoding is the same as having utf-8 */ @@ -94,8 +86,13 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) * different order of parents will be a _different_ changeset even * if everything else stays the same. */ - for (i = 0; i < parents; i++) - strbuf_addf(&buffer, "parent %s\n", sha1_to_hex(parent_sha1[i])); + while (parents) { + struct commit_list *next = parents->next; + strbuf_addf(&buffer, "parent %s\n", + sha1_to_hex(parents->item->object.sha1)); + free(parents); + parents = next; + } /* Person/date information */ strbuf_addf(&buffer, "author %s\n", git_author_info(IDENT_ERROR_ON_NO_NAME)); From c14b9d1e330a7f68ffd0ad7e22d6148c6097c122 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 27 Jun 2008 18:43:09 +0100 Subject: [PATCH 144/295] Allow git-apply to recount the lines in a hunk (AKA recountdiff) Sometimes, the easiest way to fix up a patch is to edit it directly, even adding or deleting lines. Now, many people are not as divine as certain benevolent dictators as to update the hunk headers correctly at the first try. So teach the tool to do it for us. [jc: with tests] Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- Documentation/git-apply.txt | 7 +++- builtin-apply.c | 75 +++++++++++++++++++++++++++++++++---- t/t4100-apply-stat.sh | 58 +++++++++++++--------------- 3 files changed, 99 insertions(+), 41 deletions(-) diff --git a/Documentation/git-apply.txt b/Documentation/git-apply.txt index c8347637da..c5ee636fa9 100644 --- a/Documentation/git-apply.txt +++ b/Documentation/git-apply.txt @@ -12,7 +12,7 @@ SYNOPSIS 'git-apply' [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--build-fake-ancestor ] [-R | --reverse] [--allow-binary-replacement | --binary] [--reject] [-z] - [-pNUM] [-CNUM] [--inaccurate-eof] [--cached] + [-pNUM] [-CNUM] [--inaccurate-eof] [--recount] [--cached] [--whitespace=] [--exclude=PATH] [--verbose] [...] @@ -177,6 +177,11 @@ behavior: current patch being applied will be printed. This option will cause additional information to be reported. +--recount:: + Do not trust the line counts in the hunk headers, but infer them + by inspecting the patch (e.g. after editing the patch without + adjusting the hunk headers appropriately). + Configuration ------------- diff --git a/builtin-apply.c b/builtin-apply.c index c497889312..64cf8af8f6 100644 --- a/builtin-apply.c +++ b/builtin-apply.c @@ -153,6 +153,7 @@ struct patch { unsigned int is_binary:1; unsigned int is_copy:1; unsigned int is_rename:1; + unsigned int recount:1; struct fragment *fragments; char *result; size_t resultsize; @@ -882,6 +883,56 @@ static int parse_range(const char *line, int len, int offset, const char *expect return offset + ex; } +static void recount_diff(char *line, int size, struct fragment *fragment) +{ + int oldlines = 0, newlines = 0, ret = 0; + + if (size < 1) { + warning("recount: ignore empty hunk"); + return; + } + + for (;;) { + int len = linelen(line, size); + size -= len; + line += len; + + if (size < 1) + break; + + switch (*line) { + case ' ': case '\n': + newlines++; + /* fall through */ + case '-': + oldlines++; + continue; + case '+': + newlines++; + continue; + case '\\': + break; + case '@': + ret = size < 3 || prefixcmp(line, "@@ "); + break; + case 'd': + ret = size < 5 || prefixcmp(line, "diff "); + break; + default: + ret = -1; + break; + } + if (ret) { + warning("recount: unexpected line: %.*s", + (int)linelen(line, size), line); + return; + } + break; + } + fragment->oldlines = oldlines; + fragment->newlines = newlines; +} + /* * Parse a unified diff fragment header of the * form "@@ -a,b +c,d @@" @@ -1013,6 +1064,8 @@ static int parse_fragment(char *line, unsigned long size, offset = parse_fragment_header(line, len, fragment); if (offset < 0) return -1; + if (offset > 0 && patch->recount) + recount_diff(line + offset, size - offset, fragment); oldlines = fragment->oldlines; newlines = fragment->newlines; leading = 0; @@ -2912,7 +2965,10 @@ static void prefix_patches(struct patch *p) } } -static int apply_patch(int fd, const char *filename, int inaccurate_eof) +#define INACCURATE_EOF (1<<0) +#define RECOUNT (1<<1) + +static int apply_patch(int fd, const char *filename, int options) { size_t offset; struct strbuf buf; @@ -2928,7 +2984,8 @@ static int apply_patch(int fd, const char *filename, int inaccurate_eof) int nr; patch = xcalloc(1, sizeof(*patch)); - patch->inaccurate_eof = inaccurate_eof; + patch->inaccurate_eof = !!(options & INACCURATE_EOF); + patch->recount = !!(options & RECOUNT); nr = parse_chunk(buf.buf + offset, buf.len - offset, patch); if (nr < 0) break; @@ -2997,7 +3054,7 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix) { int i; int read_stdin = 1; - int inaccurate_eof = 0; + int options = 0; int errs = 0; int is_not_gitdir; @@ -3015,7 +3072,7 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix) int fd; if (!strcmp(arg, "-")) { - errs |= apply_patch(0, "", inaccurate_eof); + errs |= apply_patch(0, "", options); read_stdin = 0; continue; } @@ -3115,7 +3172,11 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix) continue; } if (!strcmp(arg, "--inaccurate-eof")) { - inaccurate_eof = 1; + options |= INACCURATE_EOF; + continue; + } + if (!strcmp(arg, "--recount")) { + options |= RECOUNT; continue; } if (0 < prefix_length) @@ -3126,12 +3187,12 @@ int cmd_apply(int argc, const char **argv, const char *unused_prefix) die("can't open patch '%s': %s", arg, strerror(errno)); read_stdin = 0; set_default_whitespace_mode(whitespace_option); - errs |= apply_patch(fd, arg, inaccurate_eof); + errs |= apply_patch(fd, arg, options); close(fd); } set_default_whitespace_mode(whitespace_option); if (read_stdin) - errs |= apply_patch(0, "", inaccurate_eof); + errs |= apply_patch(0, "", options); if (whitespace_error) { if (squelch_whitespace_errors && squelch_whitespace_errors < whitespace_error) { diff --git a/t/t4100-apply-stat.sh b/t/t4100-apply-stat.sh index 8073a5a1f2..be837bb98d 100755 --- a/t/t4100-apply-stat.sh +++ b/t/t4100-apply-stat.sh @@ -3,44 +3,36 @@ # Copyright (c) 2005 Junio C Hamano # -test_description='git apply --stat --summary test. +test_description='git apply --stat --summary test, with --recount ' . ./test-lib.sh -test_expect_success \ - 'rename' \ - 'git apply --stat --summary <../t4100/t-apply-1.patch >current && - test_cmp ../t4100/t-apply-1.expect current' +UNC='s/^\(@@ -[1-9][0-9]*\),[0-9]* \(+[1-9][0-9]*\),[0-9]* @@/\1,999 \2,999 @@/' -test_expect_success \ - 'copy' \ - 'git apply --stat --summary <../t4100/t-apply-2.patch >current && - test_cmp ../t4100/t-apply-2.expect current' +num=0 +while read title +do + num=$(( $num + 1 )) + test_expect_success "$title" ' + git apply --stat --summary \ + <"$TEST_DIRECTORY/t4100/t-apply-$num.patch" >current && + test_cmp ../t4100/t-apply-$num.expect current + ' -test_expect_success \ - 'rewrite' \ - 'git apply --stat --summary <../t4100/t-apply-3.patch >current && - test_cmp ../t4100/t-apply-3.expect current' - -test_expect_success \ - 'mode' \ - 'git apply --stat --summary <../t4100/t-apply-4.patch >current && - test_cmp ../t4100/t-apply-4.expect current' - -test_expect_success \ - 'non git' \ - 'git apply --stat --summary <../t4100/t-apply-5.patch >current && - test_cmp ../t4100/t-apply-5.expect current' - -test_expect_success \ - 'non git' \ - 'git apply --stat --summary <../t4100/t-apply-6.patch >current && - test_cmp ../t4100/t-apply-6.expect current' - -test_expect_success \ - 'non git' \ - 'git apply --stat --summary <../t4100/t-apply-7.patch >current && - test_cmp ../t4100/t-apply-7.expect current' + test_expect_success "$title with recount" ' + sed -e "$UNC" <"$TEST_DIRECTORY/t4100/t-apply-$num.patch" | + git apply --recount --stat --summary >current && + test_cmp ../t4100/t-apply-$num.expect current + ' +done <<\EOF +rename +copy +rewrite +mode +non git (1) +non git (2) +non git (3) +EOF test_done From 935e247e8c0b2330afaa56e117e7a1c0120e6420 Mon Sep 17 00:00:00 2001 From: Lea Wiemann Date: Sat, 28 Jun 2008 19:13:29 +0200 Subject: [PATCH 145/295] GIT-VERSION-GEN: do not fail if a 'HEAD' file exists in the working copy Signed-off-by: Lea Wiemann Signed-off-by: Junio C Hamano --- GIT-VERSION-GEN | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN index f221447478..cb7cd4b538 100755 --- a/GIT-VERSION-GEN +++ b/GIT-VERSION-GEN @@ -16,7 +16,7 @@ elif test -d .git -o -f .git && case "$VN" in *$LF*) (exit 1) ;; v[0-9]*) - test -z "$(git diff-index --name-only HEAD)" || + test -z "$(git diff-index --name-only HEAD --)" || VN="$VN-dirty" ;; esac then From 74d817cf8cf68104564cf6c93c1361f66dad1901 Mon Sep 17 00:00:00 2001 From: Jochen Voss Date: Sat, 28 Jun 2008 17:04:24 +0100 Subject: [PATCH 146/295] avoid off-by-one error in run_upload_archive Make sure that buf has enough space to store the trailing \0 of the command line argument, too. Signed-off-by: Jochen Voss Signed-off-by: Junio C Hamano --- builtin-upload-archive.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/builtin-upload-archive.c b/builtin-upload-archive.c index 48ae09e9b5..371400d49a 100644 --- a/builtin-upload-archive.c +++ b/builtin-upload-archive.c @@ -30,7 +30,7 @@ static int run_upload_archive(int argc, const char **argv, const char *prefix) if (argc != 2) usage(upload_archive_usage); - if (strlen(argv[1]) > sizeof(buf)) + if (strlen(argv[1]) + 1 > sizeof(buf)) die("insanely long repository name"); strcpy(buf, argv[1]); /* enter-repo smudges its argument */ From 762656e03e80a77aeca6163597640d4e48eee55c Mon Sep 17 00:00:00 2001 From: Joey Hess Date: Sat, 28 Jun 2008 16:02:47 -0400 Subject: [PATCH 147/295] fix git config example syntax git-config expects a space, not '=' between option and value. Also, quote the value since it contains globs, which some shells will not pass through unchanged, or will abort if the glob doesn't expand. Signed-off-by: Joey Hess Signed-off-by: Junio C Hamano --- Documentation/git-svn.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/git-svn.txt b/Documentation/git-svn.txt index 97bed54fbd..c350ad0f83 100644 --- a/Documentation/git-svn.txt +++ b/Documentation/git-svn.txt @@ -513,7 +513,7 @@ have each person clone that repository with 'git clone': cd project git-init git remote add origin server:/pub/project - git config --add remote.origin.fetch=+refs/remotes/*:refs/remotes/* + git config --add remote.origin.fetch '+refs/remotes/*:refs/remotes/*' git fetch # Initialize git-svn locally (be sure to use the same URL and -T/-b/-t options as were used on server) git-svn init http://svn.foo.org/project From fa835cd5728411bfd8f851e7327e11ad809a59d1 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Thu, 26 Jun 2008 23:03:21 +0200 Subject: [PATCH 148/295] git-send-email: prevent undefined variable warnings if no encryption is set With the previous patch, not configuring any encryption (either on or off) would leave $smtp_encryption undefined. We simply set it to the empty string in that case. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- git-send-email.perl | 3 +++ 1 file changed, 3 insertions(+) diff --git a/git-send-email.perl b/git-send-email.perl index 763072042d..edb12c2aaa 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -313,6 +313,9 @@ foreach my $setting (values %config_bool_settings) { ${$setting->[0]} = $setting->[1] unless (defined (${$setting->[0]})); } +# 'default' encryption is none -- this only prevents a warning +$smtp_encryption = '' unless (defined $smtp_encryption); + # Set CC suppressions my(%suppress_cc); if (@suppress_cc) { From 5b8a94b1db4beba969d8cbb0e6e45033834b5913 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B6rn=20Steinbrink?= Date: Sun, 29 Jun 2008 03:21:25 +0200 Subject: [PATCH 149/295] git cat-file: Fix memory leak in batch mode MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When run in batch mode, git cat-file never frees the memory for the blob contents it is printing. This quickly adds up and causes git-svn to be hardly usable for imports of large svn repos, because it uses cat-file in batch mode and cat-file's memory usage easily reaches several hundred MB without any good reason. Signed-off-by: Björn Steinbrink Signed-off-by: Junio C Hamano --- builtin-cat-file.c | 1 + 1 file changed, 1 insertion(+) diff --git a/builtin-cat-file.c b/builtin-cat-file.c index bd343efae7..880e75af5e 100644 --- a/builtin-cat-file.c +++ b/builtin-cat-file.c @@ -181,6 +181,7 @@ static int batch_one_object(const char *obj_name, int print_contents) write_or_die(1, contents, size); printf("\n"); fflush(stdout); + free(contents); } return 0; From 29c70e0b3e3183f86f93500882177d0c74069988 Mon Sep 17 00:00:00 2001 From: Avery Pennarun Date: Sat, 28 Jun 2008 19:33:56 -0400 Subject: [PATCH 150/295] git-svn: avoid filling up the disk with temp files. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit ffe256f9bac8a40ff751a9341a5869d98f72c285 ("git-svn: Speed up fetch") introduced changes that create a temporary file for each object fetched by svn. These files should be deleted automatically, but perl apparently doesn't do this until the process exits (or perhaps when its garbage collector runs). This means that on a large fetch, especially with lots of branches, we sometimes fill up /tmp completely, which prevents the next temp file from being written completely. This is aggravated by the fact that a new temp file is created for each updated file, even if that update produces a file identical to one already in git. Thus, it can happen even if there's lots of disk space to store the finished repository. We weren't adequately checking for write errors, so this would result in an invalid file getting committed, which caused git-svn to fail later with an invalid checksum. This patch adds a check to syswrite() so similar problems don't lead to corruption in the future. It also unlink()'s each temp file explicitly when we're done with it, so the disk doesn't need to fill up. Signed-off-by: Avery Pennarun Tested-by: Björn Steinbrink Acked-by: Eric Wong Signed-off-by: Junio C Hamano --- git-svn.perl | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/git-svn.perl b/git-svn.perl index 4c9c59bc3f..50ace22da2 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -3243,7 +3243,9 @@ sub close_file { my ($tmp_fh, $tmp_filename) = File::Temp::tempfile(UNLINK => 1); my $result; while ($result = sysread($fh, my $string, 1024)) { - syswrite($tmp_fh, $string, $result); + my $wrote = syswrite($tmp_fh, $string, $result); + defined($wrote) && $wrote == $result + or croak("write $tmp_filename: $!\n"); } defined $result or croak $!; close $tmp_fh or croak $!; @@ -3251,6 +3253,7 @@ sub close_file { close $fh or croak $!; $hash = $::_repository->hash_and_insert_object($tmp_filename); + unlink($tmp_filename); $hash =~ /^[a-f\d]{40}$/ or die "not a sha1: $hash\n"; close $fb->{base} or croak $!; } else { From 8813df9066427ffe40d1d77d18f20643f396f153 Mon Sep 17 00:00:00 2001 From: Olivier Marin Date: Fri, 27 Jun 2008 02:17:55 +0200 Subject: [PATCH 151/295] Documentation: remove {show,whatchanged}.difftree config options This removes, from the documentation and the bash completion script, the two config options that were introduced by the git-whatchanged.sh script and lost in the C rewrite. Today, we can use aliases as an alternative. Signed-off-by: Olivier Marin Signed-off-by: Junio C Hamano --- Documentation/config.txt | 8 -------- contrib/completion/git-completion.bash | 2 -- 2 files changed, 10 deletions(-) diff --git a/Documentation/config.txt b/Documentation/config.txt index 90c8a45a2f..6966384cef 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -1007,10 +1007,6 @@ repack.usedeltabaseoffset:: Allow linkgit:git-repack[1] to create packs that uses delta-base offset. Defaults to false. -show.difftree:: - The default linkgit:git-diff-tree[1] arguments to be used - for linkgit:git-show[1]. - showbranch.default:: The default set of branches for linkgit:git-show-branch[1]. See linkgit:git-show-branch[1]. @@ -1075,10 +1071,6 @@ user.signingkey:: unchanged to gpg's --local-user parameter, so you may specify a key using any method that gpg supports. -whatchanged.difftree:: - The default linkgit:git-diff-tree[1] arguments to be used - for linkgit:git-whatchanged[1]. - imap:: The configuration variables in the 'imap' section are described in linkgit:git-imap-send[1]. diff --git a/contrib/completion/git-completion.bash b/contrib/completion/git-completion.bash index ebf7cde5c0..3f46149853 100755 --- a/contrib/completion/git-completion.bash +++ b/contrib/completion/git-completion.bash @@ -1041,7 +1041,6 @@ _git_config () pull.octopus pull.twohead repack.useDeltaBaseOffset - show.difftree showbranch.default tar.umask transfer.unpackLimit @@ -1050,7 +1049,6 @@ _git_config () user.name user.email user.signingkey - whatchanged.difftree branch. remote. " } From 861d1af36ae168353fc352126c0bf2d189c2324a Mon Sep 17 00:00:00 2001 From: Olivier Marin Date: Fri, 27 Jun 2008 02:18:48 +0200 Subject: [PATCH 152/295] show_stats(): fix stats width calculation Before this patch, name_width becomes negative or null for width values less than 15 and name_width values greater than 25 (default: 50). This leads to output random data. This patch checks for minimal width and name_width values. Signed-off-by: Olivier Marin Signed-off-by: Junio C Hamano --- diff.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/diff.c b/diff.c index 893942359b..66851b5647 100644 --- a/diff.c +++ b/diff.c @@ -830,12 +830,12 @@ static void show_stats(struct diffstat_t* data, struct diff_options *options) /* Sanity: give at least 5 columns to the graph, * but leave at least 10 columns for the name. */ - if (width < name_width + 15) { - if (name_width <= 25) - width = name_width + 15; - else - name_width = width - 15; - } + if (width < 25) + width = 25; + if (name_width < 10) + name_width = 10; + else if (width < name_width + 15) + name_width = width - 15; /* Find the longest filename and max number of changes */ reset = diff_get_color_opt(options, DIFF_RESET); From 7829f20f5beabe3e21866ae53109a58370571158 Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Sat, 28 Jun 2008 20:40:32 -0700 Subject: [PATCH 153/295] git-svn: don't sanitize remote names in config The original sanitization code was just taken from the remotes2config.sh shell script in contrib. Credit to Avery Pennarun for noticing this mistake, and Junio for clarifying the rules for config section names: Junio C Hamano wrote in <7vfxr23s6m.fsf@gitster.siamese.dyndns.org>: > In > > [foo "bar"] baz = value > > foo and baz must be config.c::iskeychar() (and baz must be isalpha()), but > "bar" can be almost anything. Signed-off-by: Eric Wong Signed-off-by: Junio C Hamano --- git-svn.perl | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) diff --git a/git-svn.perl b/git-svn.perl index 50ace22da2..f789a6eeca 100755 --- a/git-svn.perl +++ b/git-svn.perl @@ -1462,13 +1462,6 @@ sub verify_remotes_sanity { } } -# we allow more chars than remotes2config.sh... -sub sanitize_remote_name { - my ($name) = @_; - $name =~ tr{A-Za-z0-9:,/+-}{.}c; - $name; -} - sub find_existing_remote { my ($url, $remotes) = @_; return undef if $no_reuse_existing; @@ -2853,7 +2846,7 @@ sub _new { unless (defined $ref_id && length $ref_id) { $_[2] = $ref_id = $Git::SVN::default_ref_id; } - $_[1] = $repo_id = sanitize_remote_name($repo_id); + $_[1] = $repo_id; my $dir = "$ENV{GIT_DIR}/svn/$ref_id"; $_[3] = $path = '' unless (defined $path); mkpath(["$ENV{GIT_DIR}/svn"]); @@ -4707,8 +4700,7 @@ sub minimize_connections { # skip existing cases where we already connect to the root if (($ra->{url} eq $ra->{repos_root}) || - (Git::SVN::sanitize_remote_name($ra->{repos_root}) eq - $repo_id)) { + ($ra->{repos_root} eq $repo_id)) { $root_repos->{$ra->{url}} = $repo_id; next; } @@ -4747,8 +4739,7 @@ sub minimize_connections { foreach my $url (keys %$new_urls) { # see if we can re-use an existing [svn-remote "repo_id"] # instead of creating a(n ugly) new section: - my $repo_id = $root_repos->{$url} || - Git::SVN::sanitize_remote_name($url); + my $repo_id = $root_repos->{$url} || $url; my $fetch = $new_urls->{$url}; foreach my $path (keys %$fetch) { From 3cb22b8efe2cab60dc0ef5e265c414bd826d83ef Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 15 Jun 2008 23:48:46 -0700 Subject: [PATCH 154/295] Per-ref reflog expiry configuration In addition to gc.reflogexpireunreachable and gc.reflogexpire, this lets you set gc..reflogexpireunreachable and gc..reflogexpire variables. When "git reflog expire" expires reflog entry for $ref, the expiry timers are taken from the first that matches $ref (and if there isn't the global default value is used). For example, you could: [gc "refs/stash"] reflogexpire = never reflogexpireunreachable = never [gc "refs/remotes/*"] reflogexpire = 7 days reflogexpireunreachable = 3 days [gc] reflogexpire = 90 days reflogexpireunreachable = 30 days Signed-off-by: Junio C Hamano --- builtin-reflog.c | 145 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 126 insertions(+), 19 deletions(-) diff --git a/builtin-reflog.c b/builtin-reflog.c index b151e24ff9..0711728908 100644 --- a/builtin-reflog.c +++ b/builtin-reflog.c @@ -269,7 +269,9 @@ static int expire_reflog(const char *ref, const unsigned char *sha1, int unused, int status = 0; memset(&cb, 0, sizeof(cb)); - /* we take the lock for the ref itself to prevent it from + + /* + * we take the lock for the ref itself to prevent it from * getting updated. */ lock = lock_any_ref_for_update(ref, sha1, 0); @@ -331,21 +333,119 @@ static int collect_reflog(const char *ref, const unsigned char *sha1, int unused return 0; } +static struct reflog_expire_cfg { + struct reflog_expire_cfg *next; + unsigned long expire_total; + unsigned long expire_unreachable; + size_t len; + char pattern[FLEX_ARRAY]; +} *reflog_expire_cfg, **reflog_expire_cfg_tail; + +static struct reflog_expire_cfg *find_cfg_ent(const char *pattern, size_t len) +{ + struct reflog_expire_cfg *ent; + + if (!reflog_expire_cfg_tail) + reflog_expire_cfg_tail = &reflog_expire_cfg; + + for (ent = reflog_expire_cfg; ent; ent = ent->next) + if (ent->len == len && + !memcmp(ent->pattern, pattern, len)) + return ent; + + ent = xcalloc(1, (sizeof(*ent) + len)); + memcpy(ent->pattern, pattern, len); + ent->len = len; + *reflog_expire_cfg_tail = ent; + reflog_expire_cfg_tail = &(ent->next); + return ent; +} + +static int parse_expire_cfg_value(const char *var, const char *value, unsigned long *expire) +{ + if (!value) + return config_error_nonbool(var); + if (!strcmp(value, "never") || !strcmp(value, "false")) { + *expire = 0; + return 0; + } + *expire = approxidate(value); + return 0; +} + +/* expiry timer slot */ +#define EXPIRE_TOTAL 01 +#define EXPIRE_UNREACH 02 + static int reflog_expire_config(const char *var, const char *value, void *cb) { - if (!strcmp(var, "gc.reflogexpire")) { - if (!value) - config_error_nonbool(var); - default_reflog_expire = approxidate(value); + const char *lastdot = strrchr(var, '.'); + unsigned long expire; + int slot; + struct reflog_expire_cfg *ent; + + if (!lastdot || prefixcmp(var, "gc.")) + return git_default_config(var, value, cb); + + if (!strcmp(lastdot, ".reflogexpire")) { + slot = EXPIRE_TOTAL; + if (parse_expire_cfg_value(var, value, &expire)) + return -1; + } else if (!strcmp(lastdot, ".reflogexpireunreachable")) { + slot = EXPIRE_UNREACH; + if (parse_expire_cfg_value(var, value, &expire)) + return -1; + } else + return git_default_config(var, value, cb); + + if (lastdot == var + 2) { + switch (slot) { + case EXPIRE_TOTAL: + default_reflog_expire = expire; + break; + case EXPIRE_UNREACH: + default_reflog_expire_unreachable = expire; + break; + } return 0; } - if (!strcmp(var, "gc.reflogexpireunreachable")) { - if (!value) - config_error_nonbool(var); - default_reflog_expire_unreachable = approxidate(value); - return 0; + + ent = find_cfg_ent(var + 3, lastdot - (var+3)); + if (!ent) + return -1; + switch (slot) { + case EXPIRE_TOTAL: + ent->expire_total = expire; + break; + case EXPIRE_UNREACH: + ent->expire_unreachable = expire; + break; } - return git_default_config(var, value, cb); + return 0; +} + +static void set_reflog_expiry_param(struct cmd_reflog_expire_cb *cb, int slot, const char *ref) +{ + struct reflog_expire_cfg *ent; + + if (slot == (EXPIRE_TOTAL|EXPIRE_UNREACH)) + return; /* both given explicitly -- nothing to tweak */ + + for (ent = reflog_expire_cfg; ent; ent = ent->next) { + if (!fnmatch(ent->pattern, ref, 0)) { + if (!(slot & EXPIRE_TOTAL)) + cb->expire_total = ent->expire_total; + if (!(slot & EXPIRE_UNREACH)) + cb->expire_unreachable = ent->expire_unreachable; + return; + } + } + + /* Nothing matched -- use the default value */ + if (!(slot & EXPIRE_TOTAL)) + cb->expire_total = default_reflog_expire; + if (!(slot & EXPIRE_UNREACH)) + cb->expire_unreachable = default_reflog_expire_unreachable; } static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) @@ -353,6 +453,7 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) struct cmd_reflog_expire_cb cb; unsigned long now = time(NULL); int i, status, do_all; + int explicit_expiry = 0; git_config(reflog_expire_config, NULL); @@ -367,20 +468,18 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) cb.expire_total = default_reflog_expire; cb.expire_unreachable = default_reflog_expire_unreachable; - /* - * We can trust the commits and objects reachable from refs - * even in older repository. We cannot trust what's reachable - * from reflog if the repository was pruned with older git. - */ - for (i = 1; i < argc; i++) { const char *arg = argv[i]; if (!strcmp(arg, "--dry-run") || !strcmp(arg, "-n")) cb.dry_run = 1; - else if (!prefixcmp(arg, "--expire=")) + else if (!prefixcmp(arg, "--expire=")) { cb.expire_total = approxidate(arg + 9); - else if (!prefixcmp(arg, "--expire-unreachable=")) + explicit_expiry |= EXPIRE_TOTAL; + } + else if (!prefixcmp(arg, "--expire-unreachable=")) { cb.expire_unreachable = approxidate(arg + 21); + explicit_expiry |= EXPIRE_UNREACH; + } else if (!strcmp(arg, "--stale-fix")) cb.stalefix = 1; else if (!strcmp(arg, "--rewrite")) @@ -400,6 +499,12 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) else break; } + + /* + * We can trust the commits and objects reachable from refs + * even in older repository. We cannot trust what's reachable + * from reflog if the repository was pruned with older git. + */ if (cb.stalefix) { init_revisions(&cb.revs, prefix); if (cb.verbose) @@ -417,6 +522,7 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) for_each_reflog(collect_reflog, &collected); for (i = 0; i < collected.nr; i++) { struct collected_reflog *e = collected.e[i]; + set_reflog_expiry_param(&cb, explicit_expiry, e->reflog); status |= expire_reflog(e->reflog, e->sha1, 0, &cb); free(e); } @@ -430,6 +536,7 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix) status |= error("%s points nowhere!", ref); continue; } + set_reflog_expiry_param(&cb, explicit_expiry, ref); status |= expire_reflog(ref, sha1, 0, &cb); } return status; From 60bce2bb8b3cd5ca56f8156cbca16abee151d817 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sat, 28 Jun 2008 22:24:49 -0700 Subject: [PATCH 155/295] Make default expiration period of reflog used for stash infinite This makes the default expiration period for the reflog that implements stash infinite. The original behaviour to autoexpire old stashes can be restored by using the gc.refs/stash.{reflogexpire,reflogexpireunreachable} configration variables introduced by the previous commit. Signed-off-by: Junio C Hamano --- builtin-reflog.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/builtin-reflog.c b/builtin-reflog.c index 0711728908..125d455b97 100644 --- a/builtin-reflog.c +++ b/builtin-reflog.c @@ -441,6 +441,17 @@ static void set_reflog_expiry_param(struct cmd_reflog_expire_cb *cb, int slot, c } } + /* + * If unconfigured, make stash never expire + */ + if (!strcmp(ref, "refs/stash")) { + if (!(slot & EXPIRE_TOTAL)) + cb->expire_total = 0; + if (!(slot & EXPIRE_UNREACH)) + cb->expire_unreachable = 0; + return; + } + /* Nothing matched -- use the default value */ if (!(slot & EXPIRE_TOTAL)) cb->expire_total = default_reflog_expire; From ab20fda99236e38edf5d63f964b6b920b494aacb Mon Sep 17 00:00:00 2001 From: Brian Gernhardt Date: Sun, 29 Jun 2008 16:49:06 -0400 Subject: [PATCH 156/295] Fix t4017-diff-retval for white-space from wc Signed-off-by: Brian Gernhardt Signed-off-by: Junio C Hamano --- t/t4017-diff-retval.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/t/t4017-diff-retval.sh b/t/t4017-diff-retval.sh index d748d45dae..60dd2014d5 100755 --- a/t/t4017-diff-retval.sh +++ b/t/t4017-diff-retval.sh @@ -123,7 +123,7 @@ test_expect_success 'check detects leftover conflict markers' ' git --no-pager diff --cached --check >test.out test $? = 2 ) && - test "$(grep "conflict marker" test.out | wc -l)" = 3 && + test 3 = $(grep "conflict marker" test.out | wc -l) && git reset --hard ' From 5b8063b5b0f56f0da345e8dd7c66d3aced1af673 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 27 Jun 2008 13:55:23 +0100 Subject: [PATCH 157/295] clone: respect the settings in $HOME/.gitconfig and /etc/gitconfig After initializing the config in the newly-created repository, we need to unset GIT_CONFIG so that the global configs are read again. Noticed by Pieter de Bie. Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- builtin-clone.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/builtin-clone.c b/builtin-clone.c index 9c028e76a5..e9ecb5d21a 100644 --- a/builtin-clone.c +++ b/builtin-clone.c @@ -420,6 +420,13 @@ int cmd_clone(int argc, const char **argv, const char *prefix) fprintf(stderr, "Initialize %s\n", git_dir); init_db(option_template, option_quiet ? INIT_DB_QUIET : 0); + /* + * At this point, the config exists, so we do not need the + * environment variable. We actually need to unset it, too, to + * re-enable parsing of the global configs. + */ + unsetenv(CONFIG_ENVIRONMENT); + if (option_reference) setup_reference(git_dir); From e46f9c8161a0df4d4b9f8c8a98b1a8c0d9452cfd Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 29 Jun 2008 13:21:42 -0700 Subject: [PATCH 158/295] t9700: skip when Test::More is not available Signed-off-by: Junio C Hamano --- t/t9700-perl-git.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/t/t9700-perl-git.sh b/t/t9700-perl-git.sh index b2fb9ece9c..9706ee5773 100755 --- a/t/t9700-perl-git.sh +++ b/t/t9700-perl-git.sh @@ -6,6 +6,11 @@ test_description='perl interface (Git.pm)' . ./test-lib.sh +perl -MTest::More -e 0 2>/dev/null || { + say_color skip "Perl Test::More unavailable, skipping test" + test_done +} + # set up test repository test_expect_success \ From bd870878f81056d4349048842ad774f84461e939 Mon Sep 17 00:00:00 2001 From: "jrnieder@uchicago.edu" Date: Sun, 29 Jun 2008 11:10:20 -0500 Subject: [PATCH 159/295] Documentation: don't assume git-sh-setup and git-parse-remote are in PATH When git-parse-remote and git-sh-setup are not installed in $(bindir) anymore, the shell script library won't be found on user's $PATH in general. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/git-parse-remote.txt | 2 +- Documentation/git-sh-setup.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/git-parse-remote.txt b/Documentation/git-parse-remote.txt index 951dbd6c83..421312eca9 100644 --- a/Documentation/git-parse-remote.txt +++ b/Documentation/git-parse-remote.txt @@ -8,7 +8,7 @@ git-parse-remote - Routines to help parsing remote repository access parameters SYNOPSIS -------- -'. git-parse-remote' +'. "$(git --exec-path)/git-parse-remote"' DESCRIPTION ----------- diff --git a/Documentation/git-sh-setup.txt b/Documentation/git-sh-setup.txt index c543170342..6731f9ac4c 100644 --- a/Documentation/git-sh-setup.txt +++ b/Documentation/git-sh-setup.txt @@ -7,7 +7,7 @@ git-sh-setup - Common git shell script setup code SYNOPSIS -------- -'git-sh-setup' +'. "$(git --exec-path)/git-sh-setup"' DESCRIPTION ----------- From 0e047bd14c77859b1a43d477858347f6b233efc0 Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Sun, 29 Jun 2008 13:34:26 -0700 Subject: [PATCH 160/295] Update draft release notes for 1.6.0 Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.6.0.txt | 40 +++++++++++++++++++------------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/Documentation/RelNotes-1.6.0.txt b/Documentation/RelNotes-1.6.0.txt index 5292bd730c..03e3a59ff5 100644 --- a/Documentation/RelNotes-1.6.0.txt +++ b/Documentation/RelNotes-1.6.0.txt @@ -7,20 +7,16 @@ User visible changes [[Note that none of these are not merged to 'master' as of this writing but they will be before 1.6.0 happens]] -With default Makefile settings, most of the programs are now installed -outside your $PATH, except for "git", "gitk", "git-gui" and some server -side programs that needs to be accessible when connecting over ssh. - -When talking to remote repository over ssh, necessary server side programs -are now invoked with "git $program" notation, not with "git-$program" -notation. This should work with both servers running older git where you -had all of these programs installed on $PATH, or newer git where you have -only "git" on $PATH. However, if the remote side is running a custom -software that restricts programs you can run over ssh, it might cause -problems. Use --upload-pack="git-upload-pack" (when using ls-remote, -fetch and pull on the client side), --receive-pack="git-receive-pack" -(when using push on the client side), or --exec="git-upload-archive" (when -using git-archive) as appropriate when talking to such a remote. +With the default Makefile settings, most of the programs are now +installed outside your $PATH, except for "git", "gitk", "git-gui" and +some server side programs that need to be accessible for technical +reasons. Invoking a git subcommand as "git-xyzzy" from the command +line has been deprecated since early 2006 (and officially announced in +1.5.4 release notes); use of them from your scripts after adding +output from "git --exec-path" to the $PATH is still supported in this +release, but users are again strongly encouraged to adjust their +scripts to use "git xyzzy" form, as we will stop installing +"git-xyzzy" hardlinks for built-in commands in later releases. Source changes needed for porting to MinGW environment are now all in the main git.git codebase. @@ -31,6 +27,9 @@ Updates since v1.5.6 (subsystems) +* git-p4 in contrib learned "allowSubmit" configuration to control on + which branch to allow "submit" subcommand. + (portability) * Sample hook scripts shipped in templates/ are now suffixed with @@ -47,7 +46,13 @@ Updates since v1.5.6 * Updated howto/update-hook-example -(performance, robustness etc.) +* Got rid of usage of "git-foo" from the tutorial. + +* Disambiguating "--" between revs and paths is finally documented. + +(performance, robustness, sanity etc.) + +* even more documentation pages are now accessible via "man" and "git help". * reduced excessive inlining to shrink size of the "git" binary. @@ -67,6 +72,9 @@ Updates since v1.5.6 objects created will be fsync'ed (this is only useful on filesystems that does not order data writes properly). +* "git commit-tree" plumbing can make Octopus with more than 16 parents. + "git commit" has been capable of this for quite some time. + (usability, bells and whistles) * git-archive can be told to omit certain paths from its output using @@ -100,6 +108,6 @@ this release, unless otherwise noted. --- exec >/var/tmp/1 -O=v1.5.6.1-77-gf9a08f6 +O=v1.5.6.1-104-ga08b868 echo O=$(git describe refs/heads/master) git shortlog --no-merges $O..refs/heads/master ^refs/heads/maint From a0d2ceb2769731571cdd195582bfedf90225e712 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Sun, 29 Jun 2008 23:27:45 -0400 Subject: [PATCH 161/295] doc/rev-parse: clarify reflog vs --until for specifying revisions The rev-parse manpage introduces the branch@{date} syntax, and mentions the reflog specifically. However, new users may not be familiar with the distinction between the reflog and the commit date, so let's help them out with a "you may be interested in --until" pointer. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- Documentation/git-rev-parse.txt | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index 9e273bc5a6..59e95adf42 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -184,7 +184,10 @@ blobs contained in a commit. second ago\}' or '\{1979-02-26 18:30:00\}') to specify the value of the ref at a prior point in time. This suffix may only be used immediately following a ref name and the ref must have an - existing log ($GIT_DIR/logs/). + existing log ($GIT_DIR/logs/). Note that this looks up the state + of your *local* ref at a given time; e.g., what was in your local + `master` branch last week. If you want to look at commits made during + certain times, see `--since` and `--until`. * A ref followed by the suffix '@' with an ordinal specification enclosed in a brace pair (e.g. '\{1\}', '\{15\}') to specify From f3cb169bc9822e39a3efe637602b829cb338a213 Mon Sep 17 00:00:00 2001 From: Jeff King Date: Fri, 27 Jun 2008 00:01:41 -0400 Subject: [PATCH 162/295] fetch: give a hint to the user when local refs fail to update There are basically two categories of update failures for local refs: 1. problems outside of git, like disk full, bad permissions, etc. 2. D/F conflicts on tracking branch ref names In either case, there should already have been an error message. In case '1', hopefully enough information has already been given that the user can fix it. In the case of '2', we can hint that the user can clean up their tracking branch area by using 'git remote prune'. Note that we don't actually know _which_ case we have, so the user will receive the hint in case 1, as well. In this case the suggestion won't do any good, but hopefully the user is smart enough to figure out that it's just a hint. Signed-off-by: Jeff King Signed-off-by: Junio C Hamano --- builtin-fetch.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/builtin-fetch.c b/builtin-fetch.c index 7c16d38de7..97fdc51e31 100644 --- a/builtin-fetch.c +++ b/builtin-fetch.c @@ -181,9 +181,9 @@ static int s_update_ref(const char *action, lock = lock_any_ref_for_update(ref->name, check_old ? ref->old_sha1 : NULL, 0); if (!lock) - return 1; + return 2; if (write_ref_sha1(lock, ref->new_sha1, msg) < 0) - return 1; + return 2; return 0; } @@ -294,7 +294,8 @@ static int update_local_ref(struct ref *ref, } } -static int store_updated_refs(const char *url, struct ref *ref_map) +static int store_updated_refs(const char *url, const char *remote_name, + struct ref *ref_map) { FILE *fp; struct commit *commit; @@ -380,6 +381,10 @@ static int store_updated_refs(const char *url, struct ref *ref_map) } } fclose(fp); + if (rc & 2) + error("some local refs could not be updated; try running\n" + " 'git remote prune %s' to remove any old, conflicting " + "branches", remote_name); return rc; } @@ -450,7 +455,9 @@ static int fetch_refs(struct transport *transport, struct ref *ref_map) if (ret) ret = transport_fetch_refs(transport, ref_map); if (!ret) - ret |= store_updated_refs(transport->url, ref_map); + ret |= store_updated_refs(transport->url, + transport->remote->name, + ref_map); transport_unlock_pack(transport); return ret; } From f9d800e2074a60a009e7c670e396a379d8c46cc5 Mon Sep 17 00:00:00 2001 From: Brian Gernhardt Date: Sun, 29 Jun 2008 16:47:56 -0400 Subject: [PATCH 163/295] Add test results directory to t/.gitignore We don't need test results to be committed if we're fixing a test. Signed-off-by: Brian Gernhardt Signed-off-by: Junio C Hamano --- t/.gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/t/.gitignore b/t/.gitignore index 11ffd910c1..b27e280083 100644 --- a/t/.gitignore +++ b/t/.gitignore @@ -1 +1,2 @@ /trash directory +/test-results From 7e7bbcb4b35cbb4bbb5e65cf057c84b16dbd3d39 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 23 Jun 2008 21:59:37 +0200 Subject: [PATCH 164/295] parse-opt: have parse_options_{start,end}. Make the struct optparse_t public under the better name parse_opt_ctx_t. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 69 ++++++++++++++++++++++++++++--------------------- parse-options.h | 16 ++++++++++++ 2 files changed, 55 insertions(+), 30 deletions(-) diff --git a/parse-options.c b/parse-options.c index b8bde2b04a..9964877edf 100644 --- a/parse-options.c +++ b/parse-options.c @@ -4,14 +4,7 @@ #define OPT_SHORT 1 #define OPT_UNSET 2 -struct optparse_t { - const char **argv; - const char **out; - int argc, cpidx; - const char *opt; -}; - -static inline const char *get_arg(struct optparse_t *p) +static inline const char *get_arg(struct parse_opt_ctx_t *p) { if (p->opt) { const char *res = p->opt; @@ -37,7 +30,7 @@ static int opterror(const struct option *opt, const char *reason, int flags) return error("option `%s' %s", opt->long_name, reason); } -static int get_value(struct optparse_t *p, +static int get_value(struct parse_opt_ctx_t *p, const struct option *opt, int flags) { const char *s, *arg; @@ -131,7 +124,7 @@ static int get_value(struct optparse_t *p, } } -static int parse_short_opt(struct optparse_t *p, const struct option *options) +static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *options) { for (; options->type != OPTION_END; options++) { if (options->short_name == *p->opt) { @@ -142,7 +135,7 @@ static int parse_short_opt(struct optparse_t *p, const struct option *options) return error("unknown switch `%c'", *p->opt); } -static int parse_long_opt(struct optparse_t *p, const char *arg, +static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, const struct option *options) { const char *arg_end = strchr(arg, '='); @@ -247,45 +240,63 @@ void check_typos(const char *arg, const struct option *options) } } +void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags) +{ + memset(ctx, 0, sizeof(*ctx)); + ctx->argc = argc - 1; + ctx->argv = argv + 1; + ctx->out = argv; + ctx->flags = flags; +} + +int parse_options_end(struct parse_opt_ctx_t *ctx) +{ + memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); + ctx->out[ctx->cpidx + ctx->argc] = NULL; + return ctx->cpidx + ctx->argc; +} + static NORETURN void usage_with_options_internal(const char * const *, const struct option *, int); int parse_options(int argc, const char **argv, const struct option *options, const char * const usagestr[], int flags) { - struct optparse_t args = { argv + 1, argv, argc - 1, 0, NULL }; + struct parse_opt_ctx_t ctx; - for (; args.argc; args.argc--, args.argv++) { - const char *arg = args.argv[0]; + parse_options_start(&ctx, argc, argv, flags); + for (; ctx.argc; ctx.argc--, ctx.argv++) { + const char *arg = ctx.argv[0]; if (*arg != '-' || !arg[1]) { - if (flags & PARSE_OPT_STOP_AT_NON_OPTION) + if (ctx.flags & PARSE_OPT_STOP_AT_NON_OPTION) break; - args.out[args.cpidx++] = args.argv[0]; + ctx.out[ctx.cpidx++] = ctx.argv[0]; continue; } if (arg[1] != '-') { - args.opt = arg + 1; - if (*args.opt == 'h') + ctx.opt = arg + 1; + if (*ctx.opt == 'h') usage_with_options(usagestr, options); - if (parse_short_opt(&args, options) < 0) + if (parse_short_opt(&ctx, options) < 0) usage_with_options(usagestr, options); - if (args.opt) + if (ctx.opt) check_typos(arg + 1, options); - while (args.opt) { - if (*args.opt == 'h') + while (ctx.opt) { + if (*ctx.opt == 'h') usage_with_options(usagestr, options); - if (parse_short_opt(&args, options) < 0) + if (parse_short_opt(&ctx, options) < 0) usage_with_options(usagestr, options); } continue; } if (!arg[2]) { /* "--" */ - if (!(flags & PARSE_OPT_KEEP_DASHDASH)) { - args.argc--; - args.argv++; + if (!(ctx.flags & PARSE_OPT_KEEP_DASHDASH)) { + ctx.argc--; + ctx.argv++; } break; } @@ -294,13 +305,11 @@ int parse_options(int argc, const char **argv, const struct option *options, usage_with_options_internal(usagestr, options, 1); if (!strcmp(arg + 2, "help")) usage_with_options(usagestr, options); - if (parse_long_opt(&args, arg + 2, options)) + if (parse_long_opt(&ctx, arg + 2, options)) usage_with_options(usagestr, options); } - memmove(args.out + args.cpidx, args.argv, args.argc * sizeof(*args.out)); - args.out[args.cpidx + args.argc] = NULL; - return args.cpidx + args.argc; + return parse_options_end(&ctx); } #define USAGE_OPTS_WIDTH 24 diff --git a/parse-options.h b/parse-options.h index 4ee443dafe..72027f3c66 100644 --- a/parse-options.h +++ b/parse-options.h @@ -111,6 +111,22 @@ extern int parse_options(int argc, const char **argv, extern NORETURN void usage_with_options(const char * const *usagestr, const struct option *options); +/*----- incremantal advanced APIs -----*/ + +struct parse_opt_ctx_t { + const char **argv; + const char **out; + int argc, cpidx; + const char *opt; + int flags; +}; + +extern void parse_options_start(struct parse_opt_ctx_t *ctx, + int argc, const char **argv, int flags); + +extern int parse_options_end(struct parse_opt_ctx_t *ctx); + + /*----- some often used options -----*/ extern int parse_opt_abbrev_cb(const struct option *, const char *, int); extern int parse_opt_approxidate_cb(const struct option *, const char *, int); From ee68b87a62a245fca46374fe5132aec58d802baa Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 23 Jun 2008 22:28:04 +0200 Subject: [PATCH 165/295] parse-opt: Export a non NORETURN usage dumper. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 24 +++++++++++++++++------- parse-options.h | 9 +++++++++ 2 files changed, 26 insertions(+), 7 deletions(-) diff --git a/parse-options.c b/parse-options.c index 9964877edf..007b78eb24 100644 --- a/parse-options.c +++ b/parse-options.c @@ -257,8 +257,8 @@ int parse_options_end(struct parse_opt_ctx_t *ctx) return ctx->cpidx + ctx->argc; } -static NORETURN void usage_with_options_internal(const char * const *, - const struct option *, int); +static int usage_with_options_internal(const char * const *, + const struct option *, int, int); int parse_options(int argc, const char **argv, const struct option *options, const char * const usagestr[], int flags) @@ -302,7 +302,7 @@ int parse_options(int argc, const char **argv, const struct option *options, } if (!strcmp(arg + 2, "help-all")) - usage_with_options_internal(usagestr, options, 1); + usage_with_options_internal(usagestr, options, 1, 1); if (!strcmp(arg + 2, "help")) usage_with_options(usagestr, options); if (parse_long_opt(&ctx, arg + 2, options)) @@ -315,8 +315,8 @@ int parse_options(int argc, const char **argv, const struct option *options, #define USAGE_OPTS_WIDTH 24 #define USAGE_GAP 2 -void usage_with_options_internal(const char * const *usagestr, - const struct option *opts, int full) +int usage_with_options_internal(const char * const *usagestr, + const struct option *opts, int full, int do_exit) { fprintf(stderr, "usage: %s\n", *usagestr++); while (*usagestr && **usagestr) @@ -401,15 +401,25 @@ void usage_with_options_internal(const char * const *usagestr, } fputc('\n', stderr); - exit(129); + if (do_exit) + exit(129); + return PARSE_OPT_HELP; } void usage_with_options(const char * const *usagestr, const struct option *opts) { - usage_with_options_internal(usagestr, opts, 0); + usage_with_options_internal(usagestr, opts, 0, 1); + exit(129); /* make gcc happy */ } +int parse_options_usage(const char * const *usagestr, + const struct option *opts) +{ + return usage_with_options_internal(usagestr, opts, 0, 0); +} + + /*----- some often used options -----*/ #include "cache.h" diff --git a/parse-options.h b/parse-options.h index 72027f3c66..f66ca352dc 100644 --- a/parse-options.h +++ b/parse-options.h @@ -113,6 +113,12 @@ extern NORETURN void usage_with_options(const char * const *usagestr, /*----- incremantal advanced APIs -----*/ +enum { + PARSE_OPT_HELP = -1, + PARSE_OPT_DONE, + PARSE_OPT_UNKNOWN, +}; + struct parse_opt_ctx_t { const char **argv; const char **out; @@ -121,6 +127,9 @@ struct parse_opt_ctx_t { int flags; }; +extern int parse_options_usage(const char * const *usagestr, + const struct option *opts); + extern void parse_options_start(struct parse_opt_ctx_t *ctx, int argc, const char **argv, int flags); From ff43ec3e2d2f71482fe17ba9ba5f4e8074cc54ee Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 23 Jun 2008 22:38:58 +0200 Subject: [PATCH 166/295] parse-opt: create parse_options_step. For now it's unable to stop at unknown options, this commit merely reorganize some code around. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 117 +++++++++++++++++++++++++++--------------------- parse-options.h | 4 ++ 2 files changed, 69 insertions(+), 52 deletions(-) diff --git a/parse-options.c b/parse-options.c index 007b78eb24..04adf219ca 100644 --- a/parse-options.c +++ b/parse-options.c @@ -250,6 +250,58 @@ void parse_options_start(struct parse_opt_ctx_t *ctx, ctx->flags = flags; } +static int usage_with_options_internal(const char * const *, + const struct option *, int); + +int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]) +{ + for (; ctx->argc; ctx->argc--, ctx->argv++) { + const char *arg = ctx->argv[0]; + + if (*arg != '-' || !arg[1]) { + if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION) + break; + ctx->out[ctx->cpidx++] = ctx->argv[0]; + continue; + } + + if (arg[1] != '-') { + ctx->opt = arg + 1; + if (*ctx->opt == 'h') + return parse_options_usage(usagestr, options); + if (parse_short_opt(ctx, options) < 0) + usage_with_options(usagestr, options); + if (ctx->opt) + check_typos(arg + 1, options); + while (ctx->opt) { + if (*ctx->opt == 'h') + return parse_options_usage(usagestr, options); + if (parse_short_opt(ctx, options) < 0) + usage_with_options(usagestr, options); + } + continue; + } + + if (!arg[2]) { /* "--" */ + if (!(ctx->flags & PARSE_OPT_KEEP_DASHDASH)) { + ctx->argc--; + ctx->argv++; + } + break; + } + + if (!strcmp(arg + 2, "help-all")) + return usage_with_options_internal(usagestr, options, 1); + if (!strcmp(arg + 2, "help")) + return parse_options_usage(usagestr, options); + if (parse_long_opt(ctx, arg + 2, options)) + usage_with_options(usagestr, options); + } + return PARSE_OPT_DONE; +} + int parse_options_end(struct parse_opt_ctx_t *ctx) { memmove(ctx->out + ctx->cpidx, ctx->argv, ctx->argc * sizeof(*ctx->out)); @@ -257,56 +309,19 @@ int parse_options_end(struct parse_opt_ctx_t *ctx) return ctx->cpidx + ctx->argc; } -static int usage_with_options_internal(const char * const *, - const struct option *, int, int); - int parse_options(int argc, const char **argv, const struct option *options, - const char * const usagestr[], int flags) + const char * const usagestr[], int flags) { struct parse_opt_ctx_t ctx; parse_options_start(&ctx, argc, argv, flags); - for (; ctx.argc; ctx.argc--, ctx.argv++) { - const char *arg = ctx.argv[0]; - - if (*arg != '-' || !arg[1]) { - if (ctx.flags & PARSE_OPT_STOP_AT_NON_OPTION) - break; - ctx.out[ctx.cpidx++] = ctx.argv[0]; - continue; - } - - if (arg[1] != '-') { - ctx.opt = arg + 1; - if (*ctx.opt == 'h') - usage_with_options(usagestr, options); - if (parse_short_opt(&ctx, options) < 0) - usage_with_options(usagestr, options); - if (ctx.opt) - check_typos(arg + 1, options); - while (ctx.opt) { - if (*ctx.opt == 'h') - usage_with_options(usagestr, options); - if (parse_short_opt(&ctx, options) < 0) - usage_with_options(usagestr, options); - } - continue; - } - - if (!arg[2]) { /* "--" */ - if (!(ctx.flags & PARSE_OPT_KEEP_DASHDASH)) { - ctx.argc--; - ctx.argv++; - } - break; - } - - if (!strcmp(arg + 2, "help-all")) - usage_with_options_internal(usagestr, options, 1, 1); - if (!strcmp(arg + 2, "help")) - usage_with_options(usagestr, options); - if (parse_long_opt(&ctx, arg + 2, options)) - usage_with_options(usagestr, options); + switch (parse_options_step(&ctx, options, usagestr)) { + case PARSE_OPT_HELP: + exit(129); + case PARSE_OPT_DONE: + break; + default: /* PARSE_OPT_UNKNOWN */ + abort(); /* unreached yet */ } return parse_options_end(&ctx); @@ -316,7 +331,7 @@ int parse_options(int argc, const char **argv, const struct option *options, #define USAGE_GAP 2 int usage_with_options_internal(const char * const *usagestr, - const struct option *opts, int full, int do_exit) + const struct option *opts, int full) { fprintf(stderr, "usage: %s\n", *usagestr++); while (*usagestr && **usagestr) @@ -401,22 +416,20 @@ int usage_with_options_internal(const char * const *usagestr, } fputc('\n', stderr); - if (do_exit) - exit(129); return PARSE_OPT_HELP; } void usage_with_options(const char * const *usagestr, - const struct option *opts) + const struct option *opts) { - usage_with_options_internal(usagestr, opts, 0, 1); - exit(129); /* make gcc happy */ + usage_with_options_internal(usagestr, opts, 0); + exit(129); } int parse_options_usage(const char * const *usagestr, const struct option *opts) { - return usage_with_options_internal(usagestr, opts, 0, 0); + return usage_with_options_internal(usagestr, opts, 0); } diff --git a/parse-options.h b/parse-options.h index f66ca352dc..33c683cb54 100644 --- a/parse-options.h +++ b/parse-options.h @@ -133,6 +133,10 @@ extern int parse_options_usage(const char * const *usagestr, extern void parse_options_start(struct parse_opt_ctx_t *ctx, int argc, const char **argv, int flags); +extern int parse_options_step(struct parse_opt_ctx_t *ctx, + const struct option *options, + const char * const usagestr[]); + extern int parse_options_end(struct parse_opt_ctx_t *ctx); From 07fe54db3cdf42500ac2e893b670fd74841afdc4 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 23 Jun 2008 22:46:36 +0200 Subject: [PATCH 167/295] parse-opt: do not print errors on unknown options, return -2 intead. This way we can catch "unknown" options more easily. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 43 ++++++++++++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 13 deletions(-) diff --git a/parse-options.c b/parse-options.c index 04adf219ca..19fc849f4b 100644 --- a/parse-options.c +++ b/parse-options.c @@ -94,14 +94,14 @@ static int get_value(struct parse_opt_ctx_t *p, case OPTION_CALLBACK: if (unset) - return (*opt->callback)(opt, NULL, 1); + return (*opt->callback)(opt, NULL, 1) ? (-1) : 0; if (opt->flags & PARSE_OPT_NOARG) - return (*opt->callback)(opt, NULL, 0); + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; if (opt->flags & PARSE_OPT_OPTARG && !p->opt) - return (*opt->callback)(opt, NULL, 0); + return (*opt->callback)(opt, NULL, 0) ? (-1) : 0; if (!arg) return opterror(opt, "requires a value", flags); - return (*opt->callback)(opt, get_arg(p), 0); + return (*opt->callback)(opt, get_arg(p), 0) ? (-1) : 0; case OPTION_INTEGER: if (unset) { @@ -132,7 +132,7 @@ static int parse_short_opt(struct parse_opt_ctx_t *p, const struct option *optio return get_value(p, options, OPT_SHORT); } } - return error("unknown switch `%c'", *p->opt); + return -2; } static int parse_long_opt(struct parse_opt_ctx_t *p, const char *arg, @@ -217,7 +217,7 @@ is_abbreviated: abbrev_option->long_name); if (abbrev_option) return get_value(p, abbrev_option, abbrev_flags); - return error("unknown option `%s'", arg); + return -2; } void check_typos(const char *arg, const struct option *options) @@ -271,15 +271,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, ctx->opt = arg + 1; if (*ctx->opt == 'h') return parse_options_usage(usagestr, options); - if (parse_short_opt(ctx, options) < 0) - usage_with_options(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + return PARSE_OPT_UNKNOWN; + } if (ctx->opt) check_typos(arg + 1, options); while (ctx->opt) { if (*ctx->opt == 'h') return parse_options_usage(usagestr, options); - if (parse_short_opt(ctx, options) < 0) - usage_with_options(usagestr, options); + switch (parse_short_opt(ctx, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + return PARSE_OPT_UNKNOWN; + } } continue; } @@ -296,8 +304,12 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, return usage_with_options_internal(usagestr, options, 1); if (!strcmp(arg + 2, "help")) return parse_options_usage(usagestr, options); - if (parse_long_opt(ctx, arg + 2, options)) - usage_with_options(usagestr, options); + switch (parse_long_opt(ctx, arg + 2, options)) { + case -1: + return parse_options_usage(usagestr, options); + case -2: + return PARSE_OPT_UNKNOWN; + } } return PARSE_OPT_DONE; } @@ -321,7 +333,12 @@ int parse_options(int argc, const char **argv, const struct option *options, case PARSE_OPT_DONE: break; default: /* PARSE_OPT_UNKNOWN */ - abort(); /* unreached yet */ + if (ctx.argv[0][1] == '-') { + error("unknown option `%s'", ctx.argv[0] + 2); + } else { + error("unknown switch `%c'", *ctx.opt); + } + usage_with_options(usagestr, options); } return parse_options_end(&ctx); From 26141b5b60eea36f1d771312f6cae9e56dbbf760 Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Mon, 23 Jun 2008 22:55:11 +0200 Subject: [PATCH 168/295] parse-opt: fake short strings for callers to believe in. If we begin to parse -abc and that the parser knew about -a and -b, it will fake a -c switch for the caller to deal with. Of course in the case of -acb (supposing -c is not taking an argument) the caller will have to be especially clever to do the same thing. We could think about exposing an API to do so if it's really needed, but oh well... Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 11 +++++++++++ parse-options.h | 5 +++++ 2 files changed, 16 insertions(+) diff --git a/parse-options.c b/parse-options.c index 19fc849f4b..0d3818ab48 100644 --- a/parse-options.c +++ b/parse-options.c @@ -1,5 +1,6 @@ #include "git-compat-util.h" #include "parse-options.h" +#include "cache.h" #define OPT_SHORT 1 #define OPT_UNSET 2 @@ -257,6 +258,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, const struct option *options, const char * const usagestr[]) { + /* we must reset ->opt, unknown short option leave it dangling */ + ctx->opt = NULL; + for (; ctx->argc; ctx->argc--, ctx->argv++) { const char *arg = ctx->argv[0]; @@ -286,6 +290,13 @@ int parse_options_step(struct parse_opt_ctx_t *ctx, case -1: return parse_options_usage(usagestr, options); case -2: + /* fake a short option thing to hide the fact that we may have + * started to parse aggregated stuff + * + * This is leaky, too bad. + */ + ctx->argv[0] = xstrdup(ctx->opt - 1); + *(char *)ctx->argv[0] = '-'; return PARSE_OPT_UNKNOWN; } } diff --git a/parse-options.h b/parse-options.h index 33c683cb54..aeed627e97 100644 --- a/parse-options.h +++ b/parse-options.h @@ -119,6 +119,11 @@ enum { PARSE_OPT_UNKNOWN, }; +/* + * It's okay for the caller to consume argv/argc in the usual way. + * Other fields of that structure are private to parse-options and should not + * be modified in any way. + */ struct parse_opt_ctx_t { const char **argv; const char **out; From a32a4eaa36527ab1c9a999357f9edd5e04591a4a Mon Sep 17 00:00:00 2001 From: Pierre Habouzit Date: Tue, 24 Jun 2008 00:31:31 +0200 Subject: [PATCH 169/295] parse-opt: add PARSE_OPT_KEEP_ARGV0 parser option. This way, argv[0] isn't clobbered when parse-options filters argv[]. Signed-off-by: Pierre Habouzit Signed-off-by: Junio C Hamano --- parse-options.c | 1 + parse-options.h | 1 + 2 files changed, 2 insertions(+) diff --git a/parse-options.c b/parse-options.c index 0d3818ab48..469831d21b 100644 --- a/parse-options.c +++ b/parse-options.c @@ -248,6 +248,7 @@ void parse_options_start(struct parse_opt_ctx_t *ctx, ctx->argc = argc - 1; ctx->argv = argv + 1; ctx->out = argv; + ctx->cpidx = ((flags & PARSE_OPT_KEEP_ARGV0) != 0); ctx->flags = flags; } diff --git a/parse-options.h b/parse-options.h index aeed627e97..c5f0b4b4da 100644 --- a/parse-options.h +++ b/parse-options.h @@ -20,6 +20,7 @@ enum parse_opt_type { enum parse_opt_flags { PARSE_OPT_KEEP_DASHDASH = 1, PARSE_OPT_STOP_AT_NON_OPTION = 2, + PARSE_OPT_KEEP_ARGV0 = 4, }; enum parse_opt_option_flags { From be612c2318e87a9d32a385c7684459e9e0cd6227 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Mon, 30 Jun 2008 19:50:44 +0100 Subject: [PATCH 170/295] Add another fast-import example, this time for .zip files Signed-off-by: Johannes Schindelin Signed-off-by: Junio C Hamano --- contrib/fast-import/import-zips.py | 72 ++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100755 contrib/fast-import/import-zips.py diff --git a/contrib/fast-import/import-zips.py b/contrib/fast-import/import-zips.py new file mode 100755 index 0000000000..c674fa2d1b --- /dev/null +++ b/contrib/fast-import/import-zips.py @@ -0,0 +1,72 @@ +#!/usr/bin/python + +## zip archive frontend for git-fast-import +## +## For example: +## +## mkdir project; cd project; git init +## python import-zips.py *.zip +## git log --stat import-zips + +from os import popen, path +from sys import argv, exit +from time import mktime +from zipfile import ZipFile + +if len(argv) < 2: + print 'Usage:', argv[0], '...' + exit(1) + +branch_ref = 'refs/heads/import-zips' +committer_name = 'Z Ip Creator' +committer_email = 'zip@example.com' + +fast_import = popen('git fast-import --quiet', 'w') +def printlines(list): + for str in list: + fast_import.write(str + "\n") + +for zipfile in argv[1:]: + commit_time = 0 + next_mark = 1 + common_prefix = None + mark = dict() + + zip = ZipFile(zipfile, 'r') + for name in zip.namelist(): + if name.endswith('/'): + continue + info = zip.getinfo(name) + + if commit_time < info.date_time: + commit_time = info.date_time + if common_prefix == None: + common_prefix = name[:name.rfind('/') + 1] + else: + while not name.startswith(common_prefix): + common_prefix = name[:name.rfind('/') + 1] + + mark[name] = ':' + str(next_mark) + next_mark += 1 + + printlines(('blob', 'mark ' + mark[name], \ + 'data ' + str(info.file_size))) + fast_import.write(zip.read(name) + "\n") + + committer = committer_name + ' <' + committer_email + '> %d +0000' % \ + mktime(commit_time + (0, 0, 0)) + + printlines(('commit ' + branch_ref, 'committer ' + committer, \ + 'data < Date: Mon, 30 Jun 2008 03:37:47 -0400 Subject: [PATCH 171/295] Only use GIT_CONFIG in "git config", not other programs For everything other than using "git config" to read or write a git-style config file that isn't the current repo's config file, GIT_CONFIG was actively detrimental. Rather than argue over which programs are important enough to have work anyway, just fix all of them at the root. Also removes GIT_LOCAL_CONFIG, which would only be useful for programs that do want to use global git-specific config, but not the repo's own git-specific config, and want to use some other, presumably git-specific config. Despite being documented, I can't find any sign that it was ever used. Signed-off-by: Daniel Barkalow Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.6.0.txt | 5 ++++ Documentation/git-config.txt | 9 ------ builtin-config.c | 15 +++++----- cache.h | 2 +- config.c | 47 ++++++++++++++------------------ 5 files changed, 33 insertions(+), 45 deletions(-) diff --git a/Documentation/RelNotes-1.6.0.txt b/Documentation/RelNotes-1.6.0.txt index 03e3a59ff5..d37aa46a28 100644 --- a/Documentation/RelNotes-1.6.0.txt +++ b/Documentation/RelNotes-1.6.0.txt @@ -21,6 +21,11 @@ scripts to use "git xyzzy" form, as we will stop installing Source changes needed for porting to MinGW environment are now all in the main git.git codebase. +GIT_CONFIG, which was only documented as affecting "git config", but +actually affected all git commands, now only affects "git config". +GIT_LOCAL_CONFIG, also only documented as affecting "git config" and +not different from GIT_CONFIG in a useful way, is removed. + Updates since v1.5.6 -------------------- diff --git a/Documentation/git-config.txt b/Documentation/git-config.txt index c90421ee7f..30c8432267 100644 --- a/Documentation/git-config.txt +++ b/Documentation/git-config.txt @@ -191,11 +191,6 @@ variables. The '--global' and the '--system' options will limit the file used to the global or system-wide file respectively. The GIT_CONFIG environment variable has a similar effect, but you can specify any filename you want. -The GIT_CONFIG_LOCAL environment variable on the other hand only changes -the name used instead of the repository configuration file. The global and -the system-wide configuration files will still be read. (For writing options -this will obviously result in the same behavior as using GIT_CONFIG.) - ENVIRONMENT ----------- @@ -205,10 +200,6 @@ GIT_CONFIG:: Using the "--global" option forces this to ~/.gitconfig. Using the "--system" option forces this to $(prefix)/etc/gitconfig. -GIT_CONFIG_LOCAL:: - Take the configuration from the given file instead if .git/config. - Still read the global and the system-wide configuration files, though. - See also <>. diff --git a/builtin-config.c b/builtin-config.c index 3a441ef648..39f63d7b10 100644 --- a/builtin-config.c +++ b/builtin-config.c @@ -81,12 +81,10 @@ static int get_value(const char* key_, const char* regex_) char *global = NULL, *repo_config = NULL; const char *system_wide = NULL, *local; - local = getenv(CONFIG_ENVIRONMENT); + local = config_exclusive_filename; if (!local) { const char *home = getenv("HOME"); - local = getenv(CONFIG_LOCAL_ENVIRONMENT); - if (!local) - local = repo_config = xstrdup(git_path("config")); + local = repo_config = xstrdup(git_path("config")); if (git_config_global() && home) global = xstrdup(mkpath("%s/.gitconfig", home)); if (git_config_system()) @@ -289,6 +287,8 @@ int cmd_config(int argc, const char **argv, const char *prefix) char* value; const char *file = setup_git_directory_gently(&nongit); + config_exclusive_filename = getenv(CONFIG_ENVIRONMENT); + while (1 < argc) { if (!strcmp(argv[1], "--int")) type = T_INT; @@ -309,14 +309,13 @@ int cmd_config(int argc, const char **argv, const char *prefix) char *home = getenv("HOME"); if (home) { char *user_config = xstrdup(mkpath("%s/.gitconfig", home)); - setenv(CONFIG_ENVIRONMENT, user_config, 1); - free(user_config); + config_exclusive_filename = user_config; } else { die("$HOME not set"); } } else if (!strcmp(argv[1], "--system")) - setenv(CONFIG_ENVIRONMENT, git_etc_gitconfig(), 1); + config_exclusive_filename = git_etc_gitconfig(); else if (!strcmp(argv[1], "--file") || !strcmp(argv[1], "-f")) { if (argc < 3) usage(git_config_set_usage); @@ -325,7 +324,7 @@ int cmd_config(int argc, const char **argv, const char *prefix) argv[2]); else file = argv[2]; - setenv(CONFIG_ENVIRONMENT, file, 1); + config_exclusive_filename = file; argc--; argv++; } diff --git a/cache.h b/cache.h index 64ef86e129..bab0115b6f 100644 --- a/cache.h +++ b/cache.h @@ -298,7 +298,6 @@ static inline enum object_type object_type(unsigned int mode) #define GRAFT_ENVIRONMENT "GIT_GRAFT_FILE" #define TEMPLATE_DIR_ENVIRONMENT "GIT_TEMPLATE_DIR" #define CONFIG_ENVIRONMENT "GIT_CONFIG" -#define CONFIG_LOCAL_ENVIRONMENT "GIT_CONFIG_LOCAL" #define EXEC_PATH_ENVIRONMENT "GIT_EXEC_PATH" #define GITATTRIBUTES_FILE ".gitattributes" #define INFOATTRIBUTES_FILE "info/attributes" @@ -743,6 +742,7 @@ extern int check_repository_format_version(const char *var, const char *value, v extern int git_config_system(void); extern int git_config_global(void); extern int config_error_nonbool(const char *); +extern const char *config_exclusive_filename; #define MAX_GITNAME (1000) extern char git_default_email[MAX_GITNAME]; diff --git a/config.c b/config.c index 58749bf416..2862cc45cb 100644 --- a/config.c +++ b/config.c @@ -16,6 +16,8 @@ static int config_linenr; static int config_file_eof; static int zlib_compression_seen; +const char *config_exclusive_filename = NULL; + static int get_next_char(void) { int c; @@ -611,31 +613,28 @@ int git_config(config_fn_t fn, void *data) { int ret = 0; char *repo_config = NULL; - const char *home = NULL, *filename; + const char *home = NULL; /* $GIT_CONFIG makes git read _only_ the given config file, * $GIT_CONFIG_LOCAL will make it process it in addition to the * global config file, the same way it would the per-repository * config file otherwise. */ - filename = getenv(CONFIG_ENVIRONMENT); - if (!filename) { - if (git_config_system() && !access(git_etc_gitconfig(), R_OK)) - ret += git_config_from_file(fn, git_etc_gitconfig(), - data); - home = getenv("HOME"); - filename = getenv(CONFIG_LOCAL_ENVIRONMENT); - if (!filename) - filename = repo_config = xstrdup(git_path("config")); - } + if (config_exclusive_filename) + return git_config_from_file(fn, config_exclusive_filename, data); + if (git_config_system() && !access(git_etc_gitconfig(), R_OK)) + ret += git_config_from_file(fn, git_etc_gitconfig(), + data); + home = getenv("HOME"); if (git_config_global() && home) { char *user_config = xstrdup(mkpath("%s/.gitconfig", home)); if (!access(user_config, R_OK)) - ret = git_config_from_file(fn, user_config, data); + ret += git_config_from_file(fn, user_config, data); free(user_config); } - ret += git_config_from_file(fn, filename, data); + repo_config = xstrdup(git_path("config")); + ret += git_config_from_file(fn, repo_config, data); free(repo_config); return ret; } @@ -873,13 +872,10 @@ int git_config_set_multivar(const char* key, const char* value, struct lock_file *lock = NULL; const char* last_dot = strrchr(key, '.'); - config_filename = getenv(CONFIG_ENVIRONMENT); - if (!config_filename) { - config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT); - if (!config_filename) - config_filename = git_path("config"); - } - config_filename = xstrdup(config_filename); + if (config_exclusive_filename) + config_filename = xstrdup(config_exclusive_filename); + else + config_filename = xstrdup(git_path("config")); /* * Since "key" actually contains the section name and the real @@ -1136,13 +1132,10 @@ int git_config_rename_section(const char *old_name, const char *new_name) int out_fd; char buf[1024]; - config_filename = getenv(CONFIG_ENVIRONMENT); - if (!config_filename) { - config_filename = getenv(CONFIG_LOCAL_ENVIRONMENT); - if (!config_filename) - config_filename = git_path("config"); - } - config_filename = xstrdup(config_filename); + if (config_exclusive_filename) + config_filename = xstrdup(config_exclusive_filename); + else + config_filename = xstrdup(git_path("config")); out_fd = hold_lock_file_for_update(lock, config_filename, 0); if (out_fd < 0) { ret = error("could not lock config file %s", config_filename); From 4f3dcc2753ef6c244622334cef94a72682fcd850 Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Tue, 1 Jul 2008 11:47:04 +0200 Subject: [PATCH 172/295] Fix 'git show' on signed tag of signed tag of commit The cmd_show loop resolves tags by showing them, then pointing the object to the 'tagged' member. However, this object is not fully initialized; it only contains the SHA1. (This resulted in a segfault if there were two levels of tags.) We apply parse_object to get a full object. Noticed by Kalle Olavi Niemitalo on IRC. Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- builtin-log.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/builtin-log.c b/builtin-log.c index 9817d6fbeb..9979e37f38 100644 --- a/builtin-log.c +++ b/builtin-log.c @@ -360,7 +360,7 @@ int cmd_show(int argc, const char **argv, const char *prefix) t->tag, diff_get_color_opt(&rev.diffopt, DIFF_RESET)); ret = show_object(o->sha1, 1, &rev); - objects[i].item = (struct object *)t->tagged; + objects[i].item = parse_object(t->tagged->sha1); i--; break; } From 7ad0f27b925463c5ca6908573ed24ede11a9981f Mon Sep 17 00:00:00 2001 From: Junio C Hamano Date: Tue, 1 Jul 2008 17:09:21 -0700 Subject: [PATCH 173/295] Start draft release notes for 1.5.6.2 Signed-off-by: Junio C Hamano --- Documentation/RelNotes-1.5.6.2.txt | 31 ++++++++++++++++++++++++++++++ RelNotes | 2 +- 2 files changed, 32 insertions(+), 1 deletion(-) create mode 100644 Documentation/RelNotes-1.5.6.2.txt diff --git a/Documentation/RelNotes-1.5.6.2.txt b/Documentation/RelNotes-1.5.6.2.txt new file mode 100644 index 0000000000..02d5910d5c --- /dev/null +++ b/Documentation/RelNotes-1.5.6.2.txt @@ -0,0 +1,31 @@ +GIT v1.5.6.2 Release Notes +========================== + +Futureproof +----------- + + * "git-shell" accepts requests without a dash between "git" and + subcommand name (e.g. "git upload-pack") which the newer client will + start to make sometime in the future. + +Fixes since v1.5.6.1 +-------------------- + +* Optimization for a large import via "git-svn" introduced in v1.5.6 had a + serious memory and temporary file leak, which made it unusable for + moderately large import. + +* "git-svn" mangled remote nickname used in the configuration file + unnecessarily. + +* "git diff --check" did not report the result via its exit status + reliably. + +* "git show" segfaulted when an annotated tag that points at another + annotated tag was given to it. + +-- +exec >/var/tmp/1 +echo O=$(git describe maint) +O=v1.5.6.1-13-g4f3dcc2 +git shortlog --no-merges $O..maint diff --git a/RelNotes b/RelNotes index ebc4b20148..0072160018 120000 --- a/RelNotes +++ b/RelNotes @@ -1 +1 @@ -Documentation/RelNotes-1.5.6.1.txt \ No newline at end of file +Documentation/RelNotes-1.5.6.2.txt \ No newline at end of file From 6998e4db52c6d98670a2cd1e59a7708dc18e2c52 Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 17:01:21 -0500 Subject: [PATCH 174/295] Documentation: fix links to tutorials and other new manual pages With the conversion of HTML documentation to man pages tutorial.html -> gittutorial (7) tutorial-2.html -> gittutorial-2 (7) cvs-migration.html -> gitcvs-migration (7) diffcore.html -> gitdiffcore (7) repository-layout.html -> gitrepository-layout (5) hooks.html -> githooks (5) glossary.html -> gitglossary (7) core-tutorial.html -> gitcore-tutorial (7) and the automatic update of references to these pages, a little debris was left behind. We clear it away. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/diff-options.txt | 2 +- Documentation/git-add.txt | 2 +- Documentation/git-commit.txt | 4 ++-- Documentation/git-update-server-info.txt | 2 +- Documentation/git.txt | 20 ++++++++++---------- Documentation/gitcore-tutorial.txt | 9 ++++----- Documentation/gitcvs-migration.txt | 12 ++++++------ Documentation/gitrepository-layout.txt | 2 +- Documentation/gittutorial-2.txt | 12 +++++------- Documentation/gittutorial.txt | 8 ++++---- Documentation/user-manual.txt | 7 +++---- 11 files changed, 38 insertions(+), 42 deletions(-) diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt index 572154834b..cba90fd27c 100644 --- a/Documentation/diff-options.txt +++ b/Documentation/diff-options.txt @@ -241,4 +241,4 @@ endif::git-format-patch[] Do not show any source or destination prefix. For more detailed explanation on these common options, see also -linkgit:gitdiffcore[7][diffcore documentation]. +linkgit:gitdiffcore[7]. diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index b8e3fa6759..2b0ccb3c93 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -107,7 +107,7 @@ Configuration The optional configuration variable 'core.excludesfile' indicates a path to a file containing patterns of file names to exclude from git-add, similar to $GIT_DIR/info/exclude. Patterns in the exclude file are used in addition to -those in info/exclude. See linkgit:gitrepository-layout[5][repository layout]. +those in info/exclude. See linkgit:gitrepository-layout[5]. EXAMPLES diff --git a/Documentation/git-commit.txt b/Documentation/git-commit.txt index d0fe192fb3..656d4db593 100644 --- a/Documentation/git-commit.txt +++ b/Documentation/git-commit.txt @@ -97,7 +97,7 @@ OPTIONS -n:: --no-verify:: This option bypasses the pre-commit and commit-msg hooks. - See also linkgit:githooks[5][hooks]. + See also linkgit:githooks[5]. --allow-empty:: Usually recording a commit that has the exact same tree as its @@ -316,7 +316,7 @@ order). HOOKS ----- This command can run `commit-msg`, `prepare-commit-msg`, `pre-commit`, -and `post-commit` hooks. See linkgit:githooks[5][hooks] for more +and `post-commit` hooks. See linkgit:githooks[5] for more information. diff --git a/Documentation/git-update-server-info.txt b/Documentation/git-update-server-info.txt index d21be41d06..0102410821 100644 --- a/Documentation/git-update-server-info.txt +++ b/Documentation/git-update-server-info.txt @@ -31,7 +31,7 @@ OUTPUT ------ Currently the command updates the following files. Please see -linkgit:gitrepository-layout[5][repository-layout] for description of +linkgit:gitrepository-layout[5] for description of what they are for: * objects/info/packs diff --git a/Documentation/git.txt b/Documentation/git.txt index 85468a154d..1978e1bc2e 100644 --- a/Documentation/git.txt +++ b/Documentation/git.txt @@ -20,11 +20,11 @@ Git is a fast, scalable, distributed revision control system with an unusually rich command set that provides both high-level operations and full access to internals. -See this linkgit:gittutorial[7][tutorial] to get started, then see +See linkgit:gittutorial[7] to get started, then see link:everyday.html[Everyday Git] for a useful minimum set of commands, and "man git-commandname" for documentation of each command. CVS users may -also want to read linkgit:gitcvs-migration[7][CVS migration]. See -link:user-manual.html[Git User's Manual] for a more in-depth +also want to read linkgit:gitcvs-migration[7]. See +the link:user-manual.html[Git User's Manual] for a more in-depth introduction. The COMMAND is either a name of a Git command (see below) or an alias @@ -182,13 +182,14 @@ See the references above to get started using git. The following is probably more detail than necessary for a first-time user. The link:user-manual.html#git-concepts[git concepts chapter of the -user-manual] and the linkgit:gitcore-tutorial[7][Core tutorial] both provide +user-manual] and linkgit:gitcore-tutorial[7] both provide introductions to the underlying git architecture. See also the link:howto-index.html[howto] documents for some useful examples. -The internals are documented link:technical/api-index.html[here]. +The internals are documented in the +link:technical/api-index.html[GIT API documentation]. GIT COMMANDS ------------ @@ -372,10 +373,9 @@ For a more complete list of ways to spell object names, see File/Directory Structure ------------------------ -Please see the linkgit:gitrepository-layout[5][repository layout] -document. +Please see the linkgit:gitrepository-layout[5] document. -Read linkgit:githooks[5][hooks] for more details about each hook. +Read linkgit:githooks[5] for more details about each hook. Higher level SCMs may provide and manage additional information in the `$GIT_DIR`. @@ -383,7 +383,7 @@ Higher level SCMs may provide and manage additional information in the Terminology ----------- -Please see the linkgit:gitglossary[7][glossary] document. +Please see linkgit:gitglossary[7]. Environment Variables @@ -527,7 +527,7 @@ Discussion[[Discussion]] More detail on the following is available from the link:user-manual.html#git-concepts[git concepts chapter of the -user-manual] and the linkgit:gitcore-tutorial[7][Core tutorial]. +user-manual] and linkgit:gitcore-tutorial[7]. A git project normally consists of a working directory with a ".git" subdirectory at the top level. The .git directory contains, among other diff --git a/Documentation/gitcore-tutorial.txt b/Documentation/gitcore-tutorial.txt index cb4ec40440..6bb32a8258 100644 --- a/Documentation/gitcore-tutorial.txt +++ b/Documentation/gitcore-tutorial.txt @@ -16,8 +16,8 @@ This tutorial explains how to use the "core" git programs to set up and work with a git repository. If you just need to use git as a revision control system you may prefer -to start with linkgit:gittutorial[7][a tutorial introduction to git] or -link:user-manual.html[the git user manual]. +to start with "A Tutorial Introduction to GIT" (linkgit:gittutorial[7]) or +link:user-manual.html[the GIT User Manual]. However, an understanding of these low-level tools can be helpful if you want to understand git's internals. @@ -108,8 +108,7 @@ references in these `refs` subdirectories when you actually start populating your tree. [NOTE] -An advanced user may want to take a look at the -linkgit:gitrepository-layout[5][repository layout] document +An advanced user may want to take a look at linkgit:gitrepository-layout[5] after finishing this tutorial. You have now created your first git repository. Of course, since it's @@ -1589,7 +1588,7 @@ suggested in the previous section may be new to you. You do not have to worry. git supports "shared public repository" style of cooperation you are probably more familiar with as well. -See linkgit:gitcvs-migration[7][git for CVS users] for the details. +See linkgit:gitcvs-migration[7] for the details. Bundling your work together --------------------------- diff --git a/Documentation/gitcvs-migration.txt b/Documentation/gitcvs-migration.txt index 1db3f52945..d65265835d 100644 --- a/Documentation/gitcvs-migration.txt +++ b/Documentation/gitcvs-migration.txt @@ -18,9 +18,9 @@ important than any other. However, you can emulate the CVS model by designating a single shared repository which people can synchronize with; this document explains how to do that. -Some basic familiarity with git is required. This -linkgit:gittutorial[7][tutorial introduction to git] and the -linkgit:gitglossary[7][git glossary] should be sufficient. +Some basic familiarity with git is required. Having gone through +linkgit:gittutorial[7] and +linkgit:gitglossary[7] should be sufficient. Developing against a shared repository -------------------------------------- @@ -81,8 +81,8 @@ Setting Up a Shared Repository ------------------------------ We assume you have already created a git repository for your project, -possibly created from scratch or from a tarball (see the -linkgit:gittutorial[7][tutorial]), or imported from an already existing CVS +possibly created from scratch or from a tarball (see +linkgit:gittutorial[7]), or imported from an already existing CVS repository (see the next section). Assume your existing repo is at /home/alice/myproject. Create a new "bare" @@ -148,7 +148,7 @@ Advanced Shared Repository Management Git allows you to specify scripts called "hooks" to be run at certain points. You can use these, for example, to send all commits to the shared -repository to a mailing list. See linkgit:githooks[5][Hooks used by git]. +repository to a mailing list. See linkgit:githooks[5]. You can enforce finer grained permissions using update hooks. See link:howto/update-hook-example.txt[Controlling access to branches using diff --git a/Documentation/gitrepository-layout.txt b/Documentation/gitrepository-layout.txt index 03c52ff526..b75508aa50 100644 --- a/Documentation/gitrepository-layout.txt +++ b/Documentation/gitrepository-layout.txt @@ -135,7 +135,7 @@ hooks:: commands. A handful of sample hooks are installed when `git init` is run, but all of them are disabled by default. To enable, they need to be made executable. - Read linkgit:githooks[5][hooks] for more details about + Read linkgit:githooks[5] for more details about each hook. index:: diff --git a/Documentation/gittutorial-2.txt b/Documentation/gittutorial-2.txt index 31e8a23a4f..2c5467057a 100644 --- a/Documentation/gittutorial-2.txt +++ b/Documentation/gittutorial-2.txt @@ -12,8 +12,7 @@ git * DESCRIPTION ----------- -You should work through linkgit:gittutorial[7][A tutorial introduction to -git] before reading this tutorial. +You should work through linkgit:gittutorial[7] before reading this tutorial. The goal of this tutorial is to introduce two fundamental pieces of git's architecture--the object database and the index file--and to @@ -390,7 +389,7 @@ in the index file is identical to the one in the working directory. In addition to being the staging area for new commits, the index file is also populated from the object database when checking out a branch, and is used to hold the trees involved in a merge operation. -See the linkgit:gitcore-tutorial[7][core tutorial] and the relevant man +See linkgit:gitcore-tutorial[7] and the relevant man pages for details. What next? @@ -399,20 +398,19 @@ What next? At this point you should know everything necessary to read the man pages for any of the git commands; one good place to start would be with the commands mentioned in link:everyday.html[Everyday git]. You -should be able to find any unknown jargon in the -linkgit:gitglossary[7][Glossary]. +should be able to find any unknown jargon in linkgit:gitglossary[7]. The link:user-manual.html[Git User's Manual] provides a more comprehensive introduction to git. -The linkgit:gitcvs-migration[7][CVS migration] document explains how to +linkgit:gitcvs-migration[7] explains how to import a CVS repository into git, and shows how to use git in a CVS-like way. For some interesting examples of git use, see the link:howto-index.html[howtos]. -For git developers, the linkgit:gitcore-tutorial[7][Core tutorial] goes +For git developers, linkgit:gitcore-tutorial[7] goes into detail on the lower-level git mechanisms involved in, for example, creating a new commit. diff --git a/Documentation/gittutorial.txt b/Documentation/gittutorial.txt index d465aab64e..3d16e3d449 100644 --- a/Documentation/gittutorial.txt +++ b/Documentation/gittutorial.txt @@ -392,7 +392,7 @@ see linkgit:git-pull[1] for details. Git can also be used in a CVS-like mode, with a central repository that various users push changes to; see linkgit:git-push[1] and -linkgit:gitcvs-migration[7][git for CVS users]. +linkgit:gitcvs-migration[7]. Exploring history ----------------- @@ -571,9 +571,9 @@ is based: used to create commits, check out working directories, and hold the various trees involved in a merge. -linkgit:gittutorial-2[7][Part two of this tutorial] explains the object +Part two of this tutorial explains the object database, the index file, and a few other odds and ends that you'll -need to make the most of git. +need to make the most of git. You can find it at linkgit:gittutorial-2[7]. If you don't want to continue with that right away, a few other digressions that may be interesting at this point are: @@ -592,7 +592,7 @@ digressions that may be interesting at this point are: * link:everyday.html[Everyday GIT with 20 Commands Or So] - * linkgit:gitcvs-migration[7][git for CVS users]. + * linkgit:gitcvs-migration[7]: Git for CVS users. SEE ALSO -------- diff --git a/Documentation/user-manual.txt b/Documentation/user-manual.txt index 64a820bf60..ca4363ffc0 100644 --- a/Documentation/user-manual.txt +++ b/Documentation/user-manual.txt @@ -1879,8 +1879,7 @@ $ chmod a+x hooks/post-update ------------------------------------------------- (For an explanation of the last two lines, see -linkgit:git-update-server-info[1], and the documentation -linkgit:githooks[5][Hooks used by git].) +linkgit:git-update-server-info[1] and linkgit:githooks[5].) Advertise the URL of proj.git. Anybody else should then be able to clone or pull from that URL, for example with a command line like: @@ -1992,7 +1991,7 @@ the right to push to the same repository. In that case, the correct solution is to retry the push after first updating your work by either a pull or a fetch followed by a rebase; see the <> and -linkgit:gitcvs-migration[7][git for CVS users] for more. +linkgit:gitcvs-migration[7] for more. [[setting-up-a-shared-repository]] Setting up a shared repository @@ -2001,7 +2000,7 @@ Setting up a shared repository Another way to collaborate is by using a model similar to that commonly used in CVS, where several developers with special rights all push to and pull from a single shared repository. See -linkgit:gitcvs-migration[7][git for CVS users] for instructions on how to +linkgit:gitcvs-migration[7] for instructions on how to set this up. However, while there is nothing wrong with git's support for shared From 3f2d1ee89f6f1978a84ce184084738af4a462db9 Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 17:05:15 -0500 Subject: [PATCH 175/295] whitespace fix in Documentation/git-repack.txt Change leading spaces to tabs to match the rest of the file. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/git-repack.txt | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt index 04d6f1fbc4..9011d06e7d 100644 --- a/Documentation/git-repack.txt +++ b/Documentation/git-repack.txt @@ -55,15 +55,15 @@ OPTIONS Also runs linkgit:git-prune-packed[1]. -l:: - Pass the `--local` option to `git pack-objects`, see + Pass the `--local` option to `git pack-objects`, see linkgit:git-pack-objects[1]. -f:: - Pass the `--no-reuse-delta` option to `git pack-objects`, see + Pass the `--no-reuse-delta` option to `git pack-objects`, see linkgit:git-pack-objects[1]. -q:: - Pass the `-q` option to `git pack-objects`, see + Pass the `-q` option to `git pack-objects`, see linkgit:git-pack-objects[1]. -n:: From 3861cd5582d4ae4b41a3bf4c464e780d1725ad4e Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 17:10:25 -0500 Subject: [PATCH 176/295] Documentation: complicate example of "man git-command" The manual page for the command invoked as "git clone" is named git-clone(1), and similarly for the rest of the git commands. Make sure our first example of this in tutorials makes it clear that it is the first two words of a command line that make up the command's name (that is: for example, the effect of "git svn dcommit" is described in git-svn(1)). Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/gittutorial.txt | 4 ++-- Documentation/user-manual.txt | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/gittutorial.txt b/Documentation/gittutorial.txt index 3d16e3d449..b833167242 100644 --- a/Documentation/gittutorial.txt +++ b/Documentation/gittutorial.txt @@ -20,10 +20,10 @@ for example, to test the latest version, you may prefer to start with the first two chapters of link:user-manual.html[The Git User's Manual]. First, note that you can get documentation for a command such as "git -diff" with: +log --graph" with: ------------------------------------------------ -$ man git-diff +$ man git-log ------------------------------------------------ It is a good idea to introduce yourself to git with your name and diff --git a/Documentation/user-manual.txt b/Documentation/user-manual.txt index ca4363ffc0..36ab372204 100644 --- a/Documentation/user-manual.txt +++ b/Documentation/user-manual.txt @@ -18,7 +18,7 @@ People needing to do actual development will also want to read Further chapters cover more specialized topics. Comprehensive reference documentation is available through the man -pages. For a command such as "git clone", just use +pages. For a command such as "git clone ", just use ------------------------------------------------ $ man git-clone From 963a653fa635c6b07ed399b2fafca2a4d7866a21 Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 17:15:57 -0500 Subject: [PATCH 177/295] git-daemon(1): don't assume git-daemon is in /usr/bin In the example inetd.conf lines in git-daemon(1), it was assumed that `git-daemon` resides in the user's /usr/bin. With this patch, we only assume `git` is in /usr/bin. The stronger assumption fails in the default installation nowadays. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/git-daemon.txt | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Documentation/git-daemon.txt b/Documentation/git-daemon.txt index 344f24ea59..b71eb94d54 100644 --- a/Documentation/git-daemon.txt +++ b/Documentation/git-daemon.txt @@ -206,8 +206,8 @@ git-daemon as inetd server:: /etc/inetd all on one line: + ------------------------------------------------ - git stream tcp nowait nobody /usr/bin/git-daemon - git-daemon --inetd --verbose --export-all + git stream tcp nowait nobody /usr/bin/git + git daemon --inetd --verbose --export-all /pub/foo /pub/bar ------------------------------------------------ @@ -219,8 +219,8 @@ git-daemon as inetd server for virtual hosts:: `/etc/inetd` all on one line: + ------------------------------------------------ - git stream tcp nowait nobody /usr/bin/git-daemon - git-daemon --inetd --verbose --export-all + git stream tcp nowait nobody /usr/bin/git + git daemon --inetd --verbose --export-all --interpolated-path=/pub/%H%D /pub/www.example.org/software /pub/www.example.com/software @@ -241,7 +241,7 @@ git-daemon as regular daemon for virtual hosts:: their IP addresses, start the daemon like this: + ------------------------------------------------ - git-daemon --verbose --export-all + git daemon --verbose --export-all --interpolated-path=/pub/%IP/%D /pub/192.168.1.200/software /pub/10.10.220.23/software From 46e56e81b3bc91af7071809fbda8dcdec22c4cb1 Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 17:17:07 -0500 Subject: [PATCH 178/295] Documentation: prepare to be consistent about "git-" versus "git " With the dashed forms of git commands not in $(bindir), we have to change many instances of "git-command" to "git command". Also, for consistency it is at times appropriate to make the opposite change. In some cases, the change is not so simple as changing one character. This patch gets rid of some of those cases by rewrapping lines. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/git-mailinfo.txt | 4 ++-- Documentation/git-tag.txt | 4 ++-- Documentation/gitrepository-layout.txt | 8 ++++---- Documentation/gittutorial.txt | 4 ++-- 4 files changed, 10 insertions(+), 10 deletions(-) diff --git a/Documentation/git-mailinfo.txt b/Documentation/git-mailinfo.txt index 183dc1dd75..6a73b7371a 100644 --- a/Documentation/git-mailinfo.txt +++ b/Documentation/git-mailinfo.txt @@ -29,8 +29,8 @@ OPTIONS among which (1) remove 'Re:' or 're:', (2) leading whitespaces, (3) '[' up to ']', typically '[PATCH]', and then prepends "[PATCH] ". This flag forbids this - munging, and is most useful when used to read back 'git - format-patch -k' output. + munging, and is most useful when used to read back + 'git format-patch -k' output. -u:: The commit log message, author name and author email are diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt index 8f40f4bf0d..0c41711115 100644 --- a/Documentation/git-tag.txt +++ b/Documentation/git-tag.txt @@ -122,8 +122,8 @@ others have already seen the old one. So just use "git tag -f" again, as if you hadn't already published the old one. However, Git does *not* (and it should not) change tags behind -users back. So if somebody already got the old tag, doing a "git -pull" on your tree shouldn't just make them overwrite the old +users back. So if somebody already got the old tag, doing a +"git pull" on your tree shouldn't just make them overwrite the old one. If somebody got a release tag from you, you cannot just change diff --git a/Documentation/gitrepository-layout.txt b/Documentation/gitrepository-layout.txt index b75508aa50..2afc5a3e88 100644 --- a/Documentation/gitrepository-layout.txt +++ b/Documentation/gitrepository-layout.txt @@ -167,14 +167,14 @@ info/grafts:: info/exclude:: This file, by convention among Porcelains, stores the exclude pattern list. `.gitignore` is the per-directory - ignore file. `git status`, `git add`, `git rm` and `git - clean` look at it but the core git commands do not look + ignore file. `git status`, `git add`, `git rm` and + `git clean` look at it but the core git commands do not look at it. See also: linkgit:gitignore[5]. remotes:: Stores shorthands to be used to give URL and default - refnames to interact with remote repository to `git - fetch`, `git pull` and `git push` commands. + refnames to interact with remote repository to + `git fetch`, `git pull` and `git push` commands. logs:: Records of changes made to refs are stored in this diff --git a/Documentation/gittutorial.txt b/Documentation/gittutorial.txt index b833167242..144bacd3de 100644 --- a/Documentation/gittutorial.txt +++ b/Documentation/gittutorial.txt @@ -19,8 +19,8 @@ If you are instead primarily interested in using git to fetch a project, for example, to test the latest version, you may prefer to start with the first two chapters of link:user-manual.html[The Git User's Manual]. -First, note that you can get documentation for a command such as "git -log --graph" with: +First, note that you can get documentation for a command such as +"git log --graph" with: ------------------------------------------------ $ man git-log From b1889c36d85514e5e70462294c561a02c2edfe2b Mon Sep 17 00:00:00 2001 From: Jonathan Nieder Date: Mon, 30 Jun 2008 01:09:04 -0500 Subject: [PATCH 179/295] Documentation: be consistent about "git-" versus "git " Since the git-* commands are not installed in $(bindir), using "git-command " in examples in the documentation is not a good idea. On the other hand, it is nice to be able to refer to each command using one hyphenated word. (There is no escaping it, anyway: man page names cannot have spaces in them.) This patch retains the dash in naming an operation, command, program, process, or action. Complete command lines that can be entered at a shell (i.e., without options omitted) are made to use the dashless form. The changes consist only of replacing some spaces with hyphens and vice versa. After a "s/ /-/g", the unpatched and patched versions are identical. Signed-off-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- Documentation/git-add.txt | 2 +- Documentation/git-am.txt | 4 +- Documentation/git-annotate.txt | 2 +- Documentation/git-apply.txt | 2 +- Documentation/git-archimport.txt | 2 +- Documentation/git-archive.txt | 2 +- Documentation/git-bisect.txt | 2 +- Documentation/git-blame.txt | 2 +- Documentation/git-branch.txt | 8 +- Documentation/git-bundle.txt | 14 ++-- Documentation/git-cat-file.txt | 4 +- Documentation/git-check-attr.txt | 2 +- Documentation/git-check-ref-format.txt | 4 +- Documentation/git-checkout-index.txt | 20 ++--- Documentation/git-checkout.txt | 8 +- Documentation/git-cherry-pick.txt | 2 +- Documentation/git-cherry.txt | 2 +- Documentation/git-clean.txt | 2 +- Documentation/git-clone.txt | 2 +- Documentation/git-commit-tree.txt | 2 +- Documentation/git-commit.txt | 4 +- Documentation/git-config.txt | 26 +++--- Documentation/git-count-objects.txt | 4 +- Documentation/git-cvsexportcommit.txt | 8 +- Documentation/git-cvsimport.txt | 4 +- Documentation/git-cvsserver.txt | 2 +- Documentation/git-daemon.txt | 2 +- Documentation/git-describe.txt | 10 +-- Documentation/git-diff-files.txt | 2 +- Documentation/git-diff-index.txt | 12 +-- Documentation/git-diff-tree.txt | 8 +- Documentation/git-diff.txt | 18 ++-- Documentation/git-fast-export.txt | 2 +- Documentation/git-fast-import.txt | 8 +- Documentation/git-fetch-pack.txt | 2 +- Documentation/git-fetch.txt | 4 +- Documentation/git-filter-branch.txt | 4 +- Documentation/git-fmt-merge-msg.txt | 4 +- Documentation/git-for-each-ref.txt | 8 +- Documentation/git-format-patch.txt | 2 +- Documentation/git-fsck-objects.txt | 2 +- Documentation/git-fsck.txt | 4 +- Documentation/git-gc.txt | 6 +- Documentation/git-get-tar-commit-id.txt | 2 +- Documentation/git-grep.txt | 2 +- Documentation/git-hash-object.txt | 2 +- Documentation/git-http-fetch.txt | 2 +- Documentation/git-http-push.txt | 2 +- Documentation/git-imap-send.txt | 4 +- Documentation/git-index-pack.txt | 4 +- Documentation/git-init-db.txt | 2 +- Documentation/git-init.txt | 6 +- Documentation/git-instaweb.txt | 4 +- Documentation/git-log.txt | 2 +- Documentation/git-lost-found.txt | 2 +- Documentation/git-ls-files.txt | 2 +- Documentation/git-ls-remote.txt | 2 +- Documentation/git-ls-tree.txt | 2 +- Documentation/git-mailinfo.txt | 4 +- Documentation/git-mailsplit.txt | 2 +- Documentation/git-merge-base.txt | 4 +- Documentation/git-merge-file.txt | 4 +- Documentation/git-merge-index.txt | 6 +- Documentation/git-merge-tree.txt | 2 +- Documentation/git-merge.txt | 10 +-- Documentation/git-mergetool.txt | 16 ++-- Documentation/git-mktag.txt | 2 +- Documentation/git-mktree.txt | 2 +- Documentation/git-mv.txt | 6 +- Documentation/git-name-rev.txt | 2 +- Documentation/git-pack-objects.txt | 2 +- Documentation/git-pack-redundant.txt | 6 +- Documentation/git-pack-refs.txt | 4 +- Documentation/git-patch-id.txt | 2 +- Documentation/git-peek-remote.txt | 2 +- Documentation/git-prune-packed.txt | 2 +- Documentation/git-prune.txt | 4 +- Documentation/git-pull.txt | 2 +- Documentation/git-push.txt | 2 +- Documentation/git-quiltimport.txt | 2 +- Documentation/git-read-tree.txt | 32 +++---- Documentation/git-rebase.txt | 20 ++--- Documentation/git-receive-pack.txt | 10 +-- Documentation/git-relink.txt | 2 +- Documentation/git-remote.txt | 12 +-- Documentation/git-repack.txt | 10 +-- Documentation/git-repo-config.txt | 2 +- Documentation/git-request-pull.txt | 2 +- Documentation/git-rerere.txt | 4 +- Documentation/git-rev-list.txt | 10 +-- Documentation/git-rev-parse.txt | 6 +- Documentation/git-revert.txt | 2 +- Documentation/git-rm.txt | 8 +- Documentation/git-send-email.txt | 2 +- Documentation/git-send-pack.txt | 2 +- Documentation/git-shortlog.txt | 6 +- Documentation/git-show-branch.txt | 4 +- Documentation/git-show-index.txt | 2 +- Documentation/git-show-ref.txt | 6 +- Documentation/git-show.txt | 2 +- Documentation/git-stash.txt | 12 +-- Documentation/git-status.txt | 6 +- Documentation/git-stripspace.txt | 2 +- Documentation/git-submodule.txt | 10 +-- Documentation/git-svn.txt | 34 ++++---- Documentation/git-symbolic-ref.txt | 2 +- Documentation/git-tag.txt | 14 ++-- Documentation/git-tar-tree.txt | 2 +- Documentation/git-unpack-file.txt | 2 +- Documentation/git-unpack-objects.txt | 2 +- Documentation/git-update-index.txt | 12 +-- Documentation/git-update-ref.txt | 10 +-- Documentation/git-update-server-info.txt | 2 +- Documentation/git-upload-archive.txt | 2 +- Documentation/git-upload-pack.txt | 2 +- Documentation/git-var.txt | 4 +- Documentation/git-verify-pack.txt | 2 +- Documentation/git-verify-tag.txt | 2 +- Documentation/git-web--browse.txt | 6 +- Documentation/git-whatchanged.txt | 6 +- Documentation/git-write-tree.txt | 2 +- Documentation/gitattributes.txt | 14 ++-- Documentation/gitcore-tutorial.txt | 102 +++++++++++------------ Documentation/gitcvs-migration.txt | 8 +- Documentation/gitdiffcore.txt | 2 +- Documentation/githooks.txt | 10 +-- Documentation/gitignore.txt | 4 +- Documentation/gitrepository-layout.txt | 18 ++-- Documentation/gittutorial-2.txt | 18 ++-- Documentation/gittutorial.txt | 30 +++---- Documentation/user-manual.txt | 76 ++++++++--------- 131 files changed, 462 insertions(+), 462 deletions(-) diff --git a/Documentation/git-add.txt b/Documentation/git-add.txt index 2b0ccb3c93..011a743652 100644 --- a/Documentation/git-add.txt +++ b/Documentation/git-add.txt @@ -8,7 +8,7 @@ git-add - Add file contents to the index SYNOPSIS -------- [verse] -'git-add' [-n] [-v] [--force | -f] [--interactive | -i] [--patch | -p] +'git add' [-n] [-v] [--force | -f] [--interactive | -i] [--patch | -p] [--update | -u] [--refresh] [--ignore-errors] [--] ... diff --git a/Documentation/git-am.txt b/Documentation/git-am.txt index 46544a0769..1296b91172 100644 --- a/Documentation/git-am.txt +++ b/Documentation/git-am.txt @@ -9,11 +9,11 @@ git-am - Apply a series of patches from a mailbox SYNOPSIS -------- [verse] -'git-am' [--signoff] [--keep] [--utf8 | --no-utf8] +'git am' [--signoff] [--keep] [--utf8 | --no-utf8] [--3way] [--interactive] [--binary] [--whitespace=