Merge branch 'fb/archive' into next

* fb/archive:
  git-archive: make compression level of ZIP archives configurable
  Add git-upload-archive
  git-archive: wire up ZIP format.
  git-archive: wire up TAR format.
  Add git-archive

.gitignore

@@ -8,6 +8,7 @@ git-apply
 git-applymbox
 git-applypatch
 git-archimport
+git-archive
 git-bisect
 git-branch
 git-cat-file
@@ -119,6 +120,7 @@ git-unpack-objects
 git-update-index
 git-update-ref
 git-update-server-info
+git-upload-archive
 git-upload-pack
 git-upload-tar
 git-var

Documentation/git-archive.txt

@@ -0,0 +1,100 @@
+git-archive(1)
+==============
+
+NAME
+----
+git-archive - Creates a archive of the files in the named tree
+
+
+SYNOPSIS
+--------
+'git-archive' --format=<fmt> [--list] [--prefix=<prefix>/] [<extra>]
+	      [--remote=<repo>] <tree-ish> [path...]
+
+DESCRIPTION
+-----------
+Creates an archive of the specified format containing the tree
+structure for the named tree.  If <prefix> is specified it is
+prepended to the filenames in the archive.
+
+'git-archive' behaves differently when given a tree ID versus when
+given a commit ID or tag ID.  In the first case the current time is
+used as modification time of each file in the archive.  In the latter
+case the commit time as recorded in the referenced commit object is
+used instead.  Additionally the commit ID is stored in a global
+extended pax header if the tar format is used; it can be extracted
+using 'git-get-tar-commit-id'. In ZIP files it is stored as a file
+comment.
+
+OPTIONS
+-------
+
+--format=<fmt>::
+	Format of the resulting archive: 'tar', 'zip'...
+
+--list::
+	Show all available formats.
+
+--prefix=<prefix>/::
+	Prepend <prefix>/ to each filename in the archive.
+
+<extra>::
+	This can be any options that the archiver backend understand.
+
+--remote=<repo>::
+	Instead of making a tar archive from local repository,
+	retrieve a tar archive from a remote repository.
+
+<tree-ish>::
+	The tree or commit to produce an archive for.
+
+path::
+	If one or more paths are specified, include only these in the
+	archive, otherwise include all files and subdirectories.
+
+CONFIGURATION
+-------------
+By default, file and directories modes are set to 0666 or 0777 in tar
+archives.  It is possible to change this by setting the "umask" variable
+in the repository configuration as follows :
+
+[tar]
+        umask = 002	;# group friendly
+
+The special umask value "user" indicates that the user's current umask
+will be used instead. The default value remains 0, which means world
+readable/writable files and directories.
+
+EXAMPLES
+--------
+git archive --format=tar --prefix=junk/ HEAD | (cd /var/tmp/ && tar xf -)::
+
+	Create a tar archive that contains the contents of the
+	latest commit on the current branch, and extracts it in
+	`/var/tmp/junk` directory.
+
+git archive --format=tar --prefix=git-1.4.0/ v1.4.0 | gzip >git-1.4.0.tar.gz::
+
+	Create a compressed tarball for v1.4.0 release.
+
+git archive --format=tar --prefix=git-1.4.0/ v1.4.0{caret}\{tree\} | gzip >git-1.4.0.tar.gz::
+
+	Create a compressed tarball for v1.4.0 release, but without a
+	global extended pax header.
+
+git archive --format=zip --prefix=git-docs/ HEAD:Documentation/ > git-1.4.0-docs.zip::
+
+	Put everything in the current head's Documentation/ directory
+	into 'git-1.4.0-docs.zip', with the prefix 'git-docs/'.
+
+Author
+------
+Written by Franck Bui-Huu and Rene Scharfe.
+
+Documentation
+--------------
+Documentation by David Greaves, Junio C Hamano and the git-list <git@vger.kernel.org>.
+
+GIT
+---
+Part of the gitlink:git[7] suite

Documentation/git-upload-archive.txt

@@ -0,0 +1,37 @@
+git-upload-archive(1)
+====================
+
+NAME
+----
+git-upload-archive - Send archive
+
+
+SYNOPSIS
+--------
+'git-upload-archive' <directory>
+
+DESCRIPTION
+-----------
+Invoked by 'git-archive --remote' and sends a generated archive to the
+other end over the git protocol.
+
+This command is usually not invoked directly by the end user.  The UI
+for the protocol is on the 'git-archive' side, and the program pair
+is meant to be used to get an archive from a remote repository.
+
+OPTIONS
+-------
+<directory>::
+	The repository to get a tar archive from.
+
+Author
+------
+Written by Franck Bui-Huu.
+
+Documentation
+--------------
+Documentation by Junio C Hamano and the git-list <git@vger.kernel.org>.
+
+GIT
+---
+Part of the gitlink:git[7] suite

Makefile

@@ -243,7 +243,7 @@ LIB_FILE=libgit.a
 XDIFF_LIB=xdiff/lib.a
 
 LIB_H = \
-	blob.h cache.h commit.h csum-file.h delta.h \
+	archive.h blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
 	tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h
@@ -268,6 +268,7 @@ LIB_OBJS = \
 BUILTIN_OBJS = \
 	builtin-add.o \
 	builtin-apply.o \
+	builtin-archive.o \
 	builtin-cat-file.o \
 	builtin-checkout-index.o \
 	builtin-check-ref-format.o \
@@ -305,6 +306,7 @@ BUILTIN_OBJS = \
 	builtin-unpack-objects.o \
 	builtin-update-index.o \
 	builtin-update-ref.o \
+	builtin-upload-archive.o \
 	builtin-upload-tar.o \
 	builtin-verify-pack.o \
 	builtin-write-tree.o \

archive.h

@@ -0,0 +1,47 @@
+#ifndef ARCHIVE_H
+#define ARCHIVE_H
+
+#define MAX_EXTRA_ARGS	32
+#define MAX_ARGS	(MAX_EXTRA_ARGS + 32)
+
+struct archiver_args {
+	const char *base;
+	struct tree *tree;
+	const unsigned char *commit_sha1;
+	time_t time;
+	const char **pathspec;
+	void *extra;
+};
+
+typedef int (*write_archive_fn_t)(struct archiver_args *);
+
+typedef void *(*parse_extra_args_fn_t)(int argc, const char **argv);
+
+struct archiver {
+	const char *name;
+	const char *remote;
+	struct archiver_args args;
+	write_archive_fn_t write_archive;
+	parse_extra_args_fn_t parse_extra;
+};
+
+extern struct archiver archivers[];
+
+extern int parse_archive_args(int argc,
+			      const char **argv,
+			      struct archiver *ar);
+
+extern void parse_treeish_arg(const char **treeish,
+			      struct archiver_args *ar_args,
+			      const char *prefix);
+
+extern void parse_pathspec_arg(const char **pathspec,
+			       struct archiver_args *args);
+/*
+ * Archive-format specific backends.
+ */
+extern int write_tar_archive(struct archiver_args *);
+extern int write_zip_archive(struct archiver_args *);
+extern void *parse_extra_zip_args(int argc, const char **argv);
+
+#endif	/* ARCHIVE_H */

builtin-archive.c

@@ -0,0 +1,236 @@
+/*
+ * Copyright (c) 2006 Franck Bui-Huu
+ * Copyright (c) 2006 Rene Scharfe
+ */
+#include <time.h>
+#include "cache.h"
+#include "builtin.h"
+#include "archive.h"
+#include "commit.h"
+#include "tree-walk.h"
+#include "exec_cmd.h"
+#include "pkt-line.h"
+
+static const char archive_usage[] = \
+"git-archive --format=<fmt> [--prefix=<prefix>/] [<extra>] <tree-ish> [path...]";
+
+struct archiver archivers[] = {
+	{
+		.name		= "tar",
+		.write_archive	= write_tar_archive,
+	},
+	{
+		.name		= "zip",
+		.write_archive	= write_zip_archive,
+		.parse_extra	= parse_extra_zip_args,
+	},
+};
+
+static int run_remote_archiver(struct archiver *ar, int argc,
+			       const char **argv)
+{
+	char *url, buf[1024];
+	int fd[2], i, len, rv;
+	pid_t pid;
+
+	sprintf(buf, "git-upload-archive");
+
+	url = xstrdup(ar->remote);
+	pid = git_connect(fd, url, buf);
+	if (pid < 0)
+		return pid;
+
+	for (i = 1; i < argc; i++) {
+		if (!strncmp(argv[i], "--remote=", 9))
+			continue;
+		packet_write(fd[1], "argument %s\n", argv[i]);
+	}
+	packet_flush(fd[1]);
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (!len)
+		die("git-archive: expected ACK/NAK, got EOF");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (strcmp(buf, "ACK")) {
+		if (len > 5 && !strncmp(buf, "NACK ", 5))
+			die("git-archive: NACK %s", buf + 5);
+		die("git-archive: protocol error");
+	}
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (len)
+		die("git-archive: expected a flush");
+
+	/* Now, start reading from fd[0] and spit it out to stdout */
+	rv = copy_fd(fd[0], 1);
+
+	close(fd[0]);
+	rv |= finish_connect(pid);
+
+	return !!rv;
+}
+
+static int init_archiver(const char *name, struct archiver *ar)
+{
+	int rv = -1, i;
+
+	for (i = 0; i < ARRAY_SIZE(archivers); i++) {
+		if (!strcmp(name, archivers[i].name)) {
+			memcpy(ar, &archivers[i], sizeof(struct archiver));
+			rv = 0;
+			break;
+		}
+	}
+	return rv;
+}
+
+void parse_pathspec_arg(const char **pathspec, struct archiver_args *ar_args)
+{
+	ar_args->pathspec = get_pathspec(ar_args->base, pathspec);
+}
+
+void parse_treeish_arg(const char **argv, struct archiver_args *ar_args,
+		       const char *prefix)
+{
+	const char *name = argv[0];
+	const unsigned char *commit_sha1;
+	time_t archive_time;
+	struct tree *tree;
+	struct commit *commit;
+	unsigned char sha1[20];
+
+	if (get_sha1(name, sha1))
+		die("Not a valid object name");
+
+	commit = lookup_commit_reference_gently(sha1, 1);
+	if (commit) {
+		commit_sha1 = commit->object.sha1;
+		archive_time = commit->date;
+	} else {
+		commit_sha1 = NULL;
+		archive_time = time(NULL);
+	}
+
+	tree = parse_tree_indirect(sha1);
+	if (tree == NULL)
+		die("not a tree object");
+
+	if (prefix) {
+		unsigned char tree_sha1[20];
+		unsigned int mode;
+		int err;
+
+		err = get_tree_entry(tree->object.sha1, prefix,
+				     tree_sha1, &mode);
+		if (err || !S_ISDIR(mode))
+			die("current working directory is untracked");
+
+		free(tree);
+		tree = parse_tree_indirect(tree_sha1);
+	}
+	ar_args->tree = tree;
+	ar_args->commit_sha1 = commit_sha1;
+	ar_args->time = archive_time;
+}
+
+static const char *default_parse_extra(struct archiver *ar,
+				       const char **argv)
+{
+	static char msg[64];
+
+	snprintf(msg, sizeof(msg) - 4, "'%s' format does not handle %s",
+		 ar->name, *argv);
+
+	return strcat(msg, "...");
+}
+
+int parse_archive_args(int argc, const char **argv, struct archiver *ar)
+{
+	const char *extra_argv[MAX_EXTRA_ARGS];
+	int extra_argc = 0;
+	const char *format = NULL; /* might want to default to "tar" */
+	const char *remote = NULL;
+	const char *base = "";
+	int list = 0;
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (!strcmp(arg, "--list") || !strcmp(arg, "-l")) {
+			list = 1;
+			continue;
+		}
+		if (!strncmp(arg, "--format=", 9)) {
+			format = arg + 9;
+			continue;
+		}
+		if (!strncmp(arg, "--prefix=", 9)) {
+			base = arg + 9;
+			continue;
+		}
+		if (!strncmp(arg, "--remote=", 9)) {
+			remote = arg + 9;
+			continue;
+		}
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (arg[0] == '-') {
+			if (extra_argc > MAX_EXTRA_ARGS - 1)
+				die("Too many extra options");
+			extra_argv[extra_argc++] = arg;
+			continue;
+		}
+		break;
+	}
+
+	if (list) {
+		if (!remote) {
+			for (i = 0; i < ARRAY_SIZE(archivers); i++)
+				printf("%s\n", archivers[i].name);
+			exit(0);
+		}
+		die("--list and --remote are mutually exclusive");
+	}
+
+	if (argc - i < 1)
+		usage(archive_usage);
+	if (!format)
+		die("You must specify an archive format");
+	if (init_archiver(format, ar) < 0)
+		die("Unknown archive format '%s'", format);
+
+	if (extra_argc && !remote) {
+		if (!ar->parse_extra) {
+			die("%s", default_parse_extra(ar, extra_argv));
+		}
+		ar->args.extra = ar->parse_extra(extra_argc, extra_argv);
+	}
+	ar->remote = remote;
+	ar->args.base = base;
+
+	return i;
+}
+
+int cmd_archive(int argc, const char **argv, const char *prefix)
+{
+	struct archiver ar;
+	int tree_idx;
+
+	tree_idx = parse_archive_args(argc, argv, &ar);
+
+	if (ar.remote)
+		return run_remote_archiver(&ar, argc, argv);
+
+	if (prefix == NULL)
+		prefix = setup_git_directory();
+
+	argv += tree_idx;
+	parse_treeish_arg(argv, &ar.args, prefix);
+	parse_pathspec_arg(argv + 1, &ar.args);
+
+	return ar.write_archive(&ar.args);
+}

builtin-tar-tree.c

@@ -9,6 +9,7 @@
 #include "tar.h"
 #include "builtin.h"
 #include "pkt-line.h"
+#include "archive.h"
 
 #define RECORDSIZE	(512)
 #define BLOCKSIZE	(RECORDSIZE * 20)
@@ -338,6 +339,72 @@ static int generate_tar(int argc, const char **argv, const char *prefix)
 	return 0;
 }
 
+static int write_tar_entry(const unsigned char *sha1,
+                           const char *base, int baselen,
+                           const char *filename, unsigned mode, int stage)
+{
+	static struct strbuf path;
+	int filenamelen = strlen(filename);
+	void *buffer;
+	char type[20];
+	unsigned long size;
+
+	if (!path.alloc) {
+		path.buf = xmalloc(PATH_MAX);
+		path.alloc = PATH_MAX;
+		path.len = path.eof = 0;
+	}
+	if (path.alloc < baselen + filenamelen) {
+		free(path.buf);
+		path.buf = xmalloc(baselen + filenamelen);
+		path.alloc = baselen + filenamelen;
+	}
+	memcpy(path.buf, base, baselen);
+	memcpy(path.buf + baselen, filename, filenamelen);
+	path.len = baselen + filenamelen;
+	if (S_ISDIR(mode)) {
+		strbuf_append_string(&path, "/");
+		buffer = NULL;
+		size = 0;
+	} else {
+		buffer = read_sha1_file(sha1, type, &size);
+		if (!buffer)
+			die("cannot read %s", sha1_to_hex(sha1));
+	}
+
+	write_entry(sha1, &path, mode, buffer, size);
+	free(buffer);
+
+	return READ_TREE_RECURSIVE;
+}
+
+int write_tar_archive(struct archiver_args *args)
+{
+	int plen = strlen(args->base);
+
+	git_config(git_tar_config);
+
+	archive_time = args->time;
+
+	if (args->commit_sha1)
+		write_global_extended_header(args->commit_sha1);
+
+	if (args->base && plen > 0 && args->base[plen - 1] == '/') {
+		char *base = strdup(args->base);
+		int baselen = strlen(base);
+
+		while (baselen > 0 && base[baselen - 1] == '/')
+			base[--baselen] = '\0';
+		write_tar_entry(args->tree->object.sha1, "", 0, base, 040777, 0);
+		free(base);
+	}
+	read_tree_recursive(args->tree, args->base, plen, 0,
+			    args->pathspec, write_tar_entry);
+	write_trailer();
+
+	return 0;
+}
+
 static const char *exec = "git-upload-tar";
 
 static int remote_tar(int argc, const char **argv)

builtin-upload-archive.c

@@ -0,0 +1,72 @@
+/*
+ * Copyright (c) 2006 Franck Bui-Huu
+ */
+#include <time.h>
+#include "cache.h"
+#include "builtin.h"
+#include "archive.h"
+#include "pkt-line.h"
+
+static const char upload_archive_usage[] =
+	"git-upload-archive <repo>";
+
+
+int cmd_upload_archive(int argc, const char **argv, const char *prefix)
+{
+	struct archiver ar;
+	const char *sent_argv[MAX_ARGS];
+	const char *arg_cmd = "argument ";
+	char *p, buf[4096];
+	int treeish_idx;
+	int sent_argc;
+	int len;
+
+	if (argc != 2)
+		usage(upload_archive_usage);
+
+	if (strlen(argv[1]) > sizeof(buf))
+		die("insanely long repository name");
+
+	strcpy(buf, argv[1]); /* enter-repo smudges its argument */
+
+	if (!enter_repo(buf, 0))
+		die("not a git archive");
+
+	/* put received options in sent_argv[] */
+	sent_argc = 1;
+	sent_argv[0] = "git-upload-archive";
+	for (p = buf;;) {
+		/* This will die if not enough free space in buf */
+		len = packet_read_line(0, p, (buf + sizeof buf) - p);
+		if (len == 0)
+			break;	/* got a flush */
+		if (sent_argc > MAX_ARGS - 2)
+			die("Too many options (>29)");
+
+		if (p[len-1] == '\n') {
+			p[--len] = 0;
+		}
+		if (len < strlen(arg_cmd) ||
+		    strncmp(arg_cmd, p, strlen(arg_cmd)))
+			die("'argument' token or flush expected");
+
+		len -= strlen(arg_cmd);
+		memmove(p, p + strlen(arg_cmd), len);
+		sent_argv[sent_argc++] = p;
+		p += len;
+		*p++ = 0;
+	}
+	sent_argv[sent_argc] = NULL;
+
+	/* parse all options sent by the client */
+	treeish_idx = parse_archive_args(sent_argc, sent_argv, &ar);
+
+	parse_treeish_arg(sent_argv + treeish_idx, &ar.args, prefix);
+	parse_pathspec_arg(sent_argv + treeish_idx + 1, &ar.args);
+
+	packet_write(1, "ACK\n");
+	packet_flush(1);
+
+	return ar.write_archive(&ar.args);
+}
+

builtin-zip-tree.c

@@ -8,6 +8,7 @@
 #include "tree.h"
 #include "quote.h"
 #include "builtin.h"
+#include "archive.h"
 
 static const char zip_tree_usage[] =
 "git-zip-tree [-0|...|-9] <tree-ish> [ <base> ]";
@@ -351,3 +352,43 @@ int cmd_zip_tree(int argc, const char **argv, const char *prefix)
 
 	return 0;
 }
+
+int write_zip_archive(struct archiver_args *args)
+{
+	int plen = strlen(args->base);
+
+	dos_time(&args->time, &zip_date, &zip_time);
+
+	zip_dir = xmalloc(ZIP_DIRECTORY_MIN_SIZE);
+	zip_dir_size = ZIP_DIRECTORY_MIN_SIZE;
+
+	if (args->base && plen > 0 && args->base[plen - 1] == '/') {
+		char *base = strdup(args->base);
+		int baselen = strlen(base);
+
+		while (baselen > 0 && base[baselen - 1] == '/')
+			base[--baselen] = '\0';
+		write_zip_entry(args->tree->object.sha1, "", 0, base, 040777, 0);
+		free(base);
+	}
+	read_tree_recursive(args->tree, args->base, plen, 0,
+			    args->pathspec, write_zip_entry);
+	write_zip_trailer(args->commit_sha1);
+
+	free(zip_dir);
+
+	return 0;
+}
+
+void *parse_extra_zip_args(int argc, const char **argv)
+{
+	for (; argc > 0; argc--, argv++) {
+		const char *arg = argv[0];
+
+		if (arg[0] == '-' && isdigit(arg[1]) && arg[2] == '\0')
+			zlib_compression_level = arg[1] - '0';
+		else
+			die("Unknown argument for zip format: %s", arg);
+	}
+	return NULL;
+}

builtin.h

@@ -15,6 +15,7 @@ extern int write_tree(unsigned char *sha1, int missing_ok, const char *prefix);
 
 extern int cmd_add(int argc, const char **argv, const char *prefix);
 extern int cmd_apply(int argc, const char **argv, const char *prefix);
+extern int cmd_archive(int argc, const char **argv, const char *prefix);
 extern int cmd_cat_file(int argc, const char **argv, const char *prefix);
 extern int cmd_checkout_index(int argc, const char **argv, const char *prefix);
 extern int cmd_check_ref_format(int argc, const char **argv, const char *prefix);
@@ -57,6 +58,7 @@ extern int cmd_zip_tree(int argc, const char **argv, const char *prefix);
 extern int cmd_unpack_objects(int argc, const char **argv, const char *prefix);
 extern int cmd_update_index(int argc, const char **argv, const char *prefix);
 extern int cmd_update_ref(int argc, const char **argv, const char *prefix);
+extern int cmd_upload_archive(int argc, const char **argv, const char *prefix);
 extern int cmd_upload_tar(int argc, const char **argv, const char *prefix);
 extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_whatchanged(int argc, const char **argv, const char *prefix);

daemon.c

@@ -325,7 +325,14 @@ static int upload_pack(void)
 	return -1;
 }
 
+static int upload_archive(void)
+{
+	execl_git_cmd("upload-archive", ".", NULL);
+	return -1;
+}
+
 static struct daemon_service daemon_service[] = {
+	{ "upload-archive", "uploadarch", upload_archive, 0, 1 },
 	{ "upload-pack", "uploadpack", upload_pack, 1, 1 },
 };
 

generate-cmdlist.sh

@@ -12,6 +12,7 @@ struct cmdname_help common_cmds[] = {"
 sort <<\EOF |
 add
 apply
+archive
 bisect
 branch
 checkout

git.c

@@ -220,6 +220,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 	} commands[] = {
 		{ "add", cmd_add, RUN_SETUP },
 		{ "apply", cmd_apply },
+		{ "archive", cmd_archive },
 		{ "cat-file", cmd_cat_file, RUN_SETUP },
 		{ "checkout-index", cmd_checkout_index, RUN_SETUP },
 		{ "check-ref-format", cmd_check_ref_format },
@@ -262,6 +263,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "unpack-objects", cmd_unpack_objects, RUN_SETUP },
 		{ "update-index", cmd_update_index, RUN_SETUP },
 		{ "update-ref", cmd_update_ref, RUN_SETUP },
+		{ "upload-archive", cmd_upload_archive },
 		{ "upload-tar", cmd_upload_tar },
 		{ "version", cmd_version },
 		{ "whatchanged", cmd_whatchanged, RUN_SETUP | USE_PAGER },