Merge branch 'jc/bm' into next

* jc/bm: Allow branch.*.merge to talk about remote tracking branches. commit-tree: encourage UTF-8 commit messages. Switch git_mmap to use pread. Rename gitfakemmap to git_mmap. gitweb: Paginate commit/author/committer search output Makefile: add quick-install-doc for installing pre-built manpages Conflicts: Makefile
2026-03-14 02:43:25 +01:00 · 2006-12-24 02:19:25 -08:00
parent 389ed09e67 80c797764a
commit 50dae10065
10 changed files with 460 additions and 72 deletions
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -32,6 +32,7 @@ man7dir=$(mandir)/man7
 # DESTDIR=

 INSTALL?=install
+DOC_REF = origin/man

 -include ../config.mak.autogen

@@ -112,3 +113,6 @@ $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt

 install-webdoc : html
 	sh ./install-webdoc.sh $(WEBDOC_DEST)
+
+quick-install:
+	sh ./install-doc-quick.sh $(DOC_REF) $(mandir)
--- a/Documentation/install-doc-quick.sh
+++ b/Documentation/install-doc-quick.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+# This requires a branch named in $head
+# (usually 'man' or 'html', provided by the git.git repository)
+set -e
+head="$1"
+mandir="$2"
+SUBDIRECTORY_OK=t
+USAGE='<refname> <target directory>'
+. git-sh-setup
+export GIT_DIR
+
+test -z "$mandir" && usage
+if ! git-rev-parse --verify "$head^0" >/dev/null; then
+	echo >&2 "head: $head does not exist in the current repository"
+	usage
+fi
+
+GIT_INDEX_FILE=`pwd`/.quick-doc.index
+export GIT_INDEX_FILE
+rm -f "$GIT_INDEX_FILE"
+git-read-tree $head
+git-checkout-index -a -f --prefix="$mandir"/
+
+if test -n "$GZ"; then
+	cd "$mandir"
+	for i in `git-ls-tree -r --name-only $head`
+	do
+		gzip < $i > $i.gz && rm $i
+	done
+fi
+rm -f "$GIT_INDEX_FILE"
--- a/7
+++ b/7
@@ -230,7 +230,8 @@ LIB_H = \
 	archive.h blob.h cache.h commit.h csum-file.h delta.h grep.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h list-objects.h sideband.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
+	tree-walk.h log-tree.h dir.h path-list.h unpack-trees.h builtin.h \
+	utf8.h

 DIFF_OBJS = \
 	diff.o diff-lib.o diffcore-break.o diffcore-order.o \
@@ -249,7 +250,7 @@ LIB_OBJS = \
 	revision.o pager.o tree-walk.o xdiff-interface.o \
 	write_or_die.o trace.o list-objects.o grep.o \
 	alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \
-	color.o wt-status.o archive-zip.o archive-tar.o shallow.o
+	color.o wt-status.o archive-zip.o archive-tar.o shallow.o utf8.o

 BUILTIN_OBJS = \
 	builtin-add.o \
@@ -826,6 +827,8 @@ install: all
 install-doc:
 	$(MAKE) -C Documentation install

+quick-install-doc:
+	$(MAKE) -C Documentation quick-install



--- a/builtin-commit-tree.c
+++ b/builtin-commit-tree.c
@@ -7,6 +7,7 @@
 #include "commit.h"
 #include "tree.h"
 #include "builtin.h"
+#include "utf8.h"

 #define BLOCKING (1ul << 14)

@@ -32,7 +33,7 @@ static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...)
 	len = vsnprintf(one_line, sizeof(one_line), fmt, args);
 	va_end(args);
 	size = *sizep;
-	newsize = size + len;
+	newsize = size + len + 1;
 	alloc = (size + 32767) & ~32767;
 	buf = *bufp;
 	if (newsize > alloc) {
@@ -40,7 +41,7 @@ static void add_buffer(char **bufp, unsigned int *sizep, const char *fmt, ...)
 		buf = xrealloc(buf, alloc);
 		*bufp = buf;
 	}
-	*sizep = newsize;
+	*sizep = newsize - 1;
 	memcpy(buf + size, one_line, len);
 }

@@ -77,6 +78,11 @@ static int new_parent(int idx)
 	return 1;
 }

+static const char commit_utf8_warn[] =
+"Warning: commit message does not conform to UTF-8.\n"
+"You may want to amend it after fixing the message, or set the config\n"
+"variable i18n.commitencoding to the encoding your project uses.\n";
+
 int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -130,6 +136,11 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 	while (fgets(comment, sizeof(comment), stdin) != NULL)
 		add_buffer(&buffer, &size, "%s", comment);

+	/* And check the encoding */
+	buffer[size] = '\0';
+	if (!strcmp(git_commit_encoding, "utf-8") && !is_utf8(buffer))
+		fprintf(stderr, commit_utf8_warn);
+
 	if (!write_sha1_file(buffer, size, commit_type, commit_sha1)) {
 		printf("%s\n", sha1_to_hex(commit_sha1));
 		return 0;
--- a/compat/mmap.c
+++ b/compat/mmap.c
@@ -1,17 +1,11 @@
 #include "../git-compat-util.h"

-void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_t offset)
+void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset)
 {
-	int n = 0;
-	off_t current_offset = lseek(fd, 0, SEEK_CUR);
+	size_t n = 0;

 	if (start != NULL || !(flags & MAP_PRIVATE))
-		die("Invalid usage of gitfakemmap.");
-
-	if (lseek(fd, offset, SEEK_SET) < 0) {
-		errno = EINVAL;
-		return MAP_FAILED;
-	}
+		die("Invalid usage of mmap when built with NO_MMAP");

 	start = xmalloc(length);
 	if (start == NULL) {
@@ -20,14 +14,16 @@ void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_
 	}

 	while (n < length) {
-		int count = read(fd, start+n, length-n);
+		ssize_t count = pread(fd, (char *)start + n, length - n, offset + n);

 		if (count == 0) {
-			memset(start+n, 0, length-n);
+			memset((char *)start+n, 0, length-n);
 			break;
 		}

 		if (count < 0) {
+			if (errno == EAGAIN || errno == EINTR)
+				continue;
 			free(start);
 			errno = EACCES;
 			return MAP_FAILED;
@@ -36,15 +32,10 @@ void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_
 		n += count;
 	}

-	if (current_offset != lseek(fd, current_offset, SEEK_SET)) {
-		errno = EINVAL;
-		return MAP_FAILED;
-	}
-
 	return start;
 }

-int gitfakemunmap(void *start, size_t length)
+int git_munmap(void *start, size_t length)
 {
 	free(start);
 	return 0;
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -87,10 +87,10 @@ extern void set_warn_routine(void (*routine)(const char *warn, va_list params));
 #define MAP_FAILED ((void*)-1)
 #endif

-#define mmap gitfakemmap
-#define munmap gitfakemunmap
-extern void *gitfakemmap(void *start, size_t length, int prot , int flags, int fd, off_t offset);
-extern int gitfakemunmap(void *start, size_t length);
+#define mmap git_mmap
+#define munmap git_munmap
+extern void *git_mmap(void *start, size_t length, int prot, int flags, int fd, off_t offset);
+extern int git_munmap(void *start, size_t length);

 #else /* NO_MMAP */

--- a/git-parse-remote.sh
+++ b/git-parse-remote.sh
@@ -146,8 +146,12 @@ canon_refs_list_for_fetch () {
 		else
 			for merge_branch in $merge_branches
 			do
-			    [ "$remote" = "$merge_branch" ] &&
-			    dot_prefix= && break
+			    if	test "$remote" = "$merge_branch" ||
+				test "$local" = "$merge_branch"
+			    then
+				    dot_prefix=
+				    break
+			    fi
 			done
 		fi
 		case "$remote" in
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -2852,6 +2852,58 @@ sub git_heads_body {
 	print "</table>\n";
 }

+sub git_search_grep_body {
+	my ($greplist, $from, $to, $extra) = @_;
+	$from = 0 unless defined $from;
+	$to = $#{$greplist} if (!defined $to || $#{$greplist} < $to);
+
+	print "<table class=\"grep\" cellspacing=\"0\">\n";
+	my $alternate = 1;
+	for (my $i = $from; $i <= $to; $i++) {
+		my $commit = $greplist->[$i];
+		my %co = parse_commit($commit);
+		if (!%co) {
+			next;
+		}
+		if ($alternate) {
+			print "<tr class=\"dark\">\n";
+		} else {
+			print "<tr class=\"light\">\n";
+		}
+		$alternate ^= 1;
+		print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
+		      "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" .
+		      "<td>" .
+		      $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"},
+			       esc_html(chop_str($co{'title'}, 50)) . "<br/>");
+		my $comment = $co{'comment'};
+		foreach my $line (@$comment) {
+			if ($line =~ m/^(.*)($searchtext)(.*)$/i) {
+				my $lead = esc_html($1) || "";
+				$lead = chop_str($lead, 30, 10);
+				my $match = esc_html($2) || "";
+				my $trail = esc_html($3) || "";
+				$trail = chop_str($trail, 30, 10);
+				my $text = "$lead<span class=\"match\">$match</span>$trail";
+				print chop_str($text, 80, 5) . "<br/>\n";
+			}
+		}
+		print "</td>\n" .
+		      "<td class=\"link\">" .
+		      $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") .
+		      " | " .
+		      $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree");
+		print "</td>\n" .
+		      "</tr>\n";
+	}
+	if (defined $extra) {
+		print "<tr>\n" .
+		      "<td colspan=\"3\">$extra</td>\n" .
+		      "</tr>\n";
+	}
+	print "</table>\n";
+}
+
 ## ======================================================================
 ## ======================================================================
 ## actions
@@ -4174,6 +4226,9 @@ sub git_search {
 	if (!%co) {
 		die_error(undef, "Unknown commit object");
 	}
+	if (!defined $page) {
+		$page = 0;
+	}

 	$searchtype ||= 'commit';
 	if ($searchtype eq 'pickaxe') {
@@ -4186,11 +4241,7 @@ sub git_search {
 	}

 	git_header_html();
-	git_print_page_nav('','', $hash,$co{'tree'},$hash);
-	git_print_header_div('commit', esc_html($co{'title'}), $hash);

-	print "<table cellspacing=\"0\">\n";
-	my $alternate = 1;
 	if ($searchtype eq 'commit' or $searchtype eq 'author' or $searchtype eq 'committer') {
 		my $greptype;
 		if ($searchtype eq 'commit') {
@@ -4200,52 +4251,58 @@ sub git_search {
 		} elsif ($searchtype eq 'committer') {
 			$greptype = "--committer=";
 		}
-		$/ = "\0";
 		open my $fd, "-|", git_cmd(), "rev-list",
-			"--header", "--parents", ($greptype . $searchtext),
-			 $hash, "--"
+			("--max-count=" . (100 * ($page+1))),
+			($greptype . $searchtext),
+			$hash, "--"
 			or next;
-		while (my $commit_text = <$fd>) {
-			my @commit_lines = split "\n", $commit_text;
-			my %co = parse_commit(undef, \@commit_lines);
-			if (!%co) {
-				next;
-			}
-			if ($alternate) {
-				print "<tr class=\"dark\">\n";
-			} else {
-				print "<tr class=\"light\">\n";
-			}
-			$alternate ^= 1;
-			print "<td title=\"$co{'age_string_age'}\"><i>$co{'age_string_date'}</i></td>\n" .
-			      "<td><i>" . esc_html(chop_str($co{'author_name'}, 15, 5)) . "</i></td>\n" .
-			      "<td>" .
-			      $cgi->a({-href => href(action=>"commit", hash=>$co{'id'}), -class => "list subject"},
-			               esc_html(chop_str($co{'title'}, 50)) . "<br/>");
-			my $comment = $co{'comment'};
-			foreach my $line (@$comment) {
-				if ($line =~ m/^(.*)($searchtext)(.*)$/i) {
-					my $lead = esc_html($1) || "";
-					$lead = chop_str($lead, 30, 10);
-					my $match = esc_html($2) || "";
-					my $trail = esc_html($3) || "";
-					$trail = chop_str($trail, 30, 10);
-					my $text = "$lead<span class=\"match\">$match</span>$trail";
-					print chop_str($text, 80, 5) . "<br/>\n";
-				}
-			}
-			print "</td>\n" .
-			      "<td class=\"link\">" .
-			      $cgi->a({-href => href(action=>"commit", hash=>$co{'id'})}, "commit") .
-			      " | " .
-			      $cgi->a({-href => href(action=>"tree", hash=>$co{'tree'}, hash_base=>$co{'id'})}, "tree");
-			print "</td>\n" .
-			      "</tr>\n";
-		}
+		my @revlist = map { chomp; $_ } <$fd>;
 		close $fd;
+
+		my $paging_nav = '';
+		if ($page > 0) {
+			$paging_nav .=
+				$cgi->a({-href => href(action=>"search", hash=>$hash,
+						       searchtext=>$searchtext, searchtype=>$searchtype)},
+					"first");
+			$paging_nav .= " &sdot; " .
+				$cgi->a({-href => href(action=>"search", hash=>$hash,
+						       searchtext=>$searchtext, searchtype=>$searchtype,
+						       page=>$page-1),
+					 -accesskey => "p", -title => "Alt-p"}, "prev");
+		} else {
+			$paging_nav .= "first";
+			$paging_nav .= " &sdot; prev";
+		}
+		if ($#revlist >= (100 * ($page+1)-1)) {
+			$paging_nav .= " &sdot; " .
+				$cgi->a({-href => href(action=>"search", hash=>$hash,
+						       searchtext=>$searchtext, searchtype=>$searchtype,
+						       page=>$page+1),
+					 -accesskey => "n", -title => "Alt-n"}, "next");
+		} else {
+			$paging_nav .= " &sdot; next";
+		}
+		my $next_link = '';
+		if ($#revlist >= (100 * ($page+1)-1)) {
+			$next_link =
+				$cgi->a({-href => href(action=>"search", hash=>$hash,
+						       searchtext=>$searchtext, searchtype=>$searchtype,
+						       page=>$page+1),
+					 -accesskey => "n", -title => "Alt-n"}, "next");
+		}
+
+		git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav);
+		git_print_header_div('commit', esc_html($co{'title'}), $hash);
+		git_search_grep_body(\@revlist, ($page * 100), $#revlist, $next_link);
 	}

 	if ($searchtype eq 'pickaxe') {
+		git_print_page_nav('','', $hash,$co{'tree'},$hash);
+		git_print_header_div('commit', esc_html($co{'title'}), $hash);
+
+		print "<table cellspacing=\"0\">\n";
+		my $alternate = 1;
 		$/ = "\n";
 		my $git_command = git_cmd_str();
 		open my $fd, "-|", "$git_command rev-list $hash | " .
@@ -4300,8 +4357,9 @@ sub git_search {
 			}
 		}
 		close $fd;
+
+		print "</table>\n";
 	}
-	print "</table>\n";
 	git_footer_html();
 }

--- a/utf8.c
+++ b/utf8.c
@@ -0,0 +1,278 @@
+#include "git-compat-util.h"
+#include "utf8.h"
+
+/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
+
+struct interval {
+  int first;
+  int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(wchar_t ucs, const struct interval *table, int max) {
+	int min = 0;
+	int mid;
+
+	if (ucs < table[0].first || ucs > table[max].last)
+		return 0;
+	while (max >= min) {
+		mid = (min + max) / 2;
+		if (ucs > table[mid].last)
+			min = mid + 1;
+		else if (ucs < table[mid].first)
+			max = mid - 1;
+		else
+			return 1;
+	}
+
+	return 0;
+}
+
+/* The following two functions define the column width of an ISO 10646
+ * character as follows:
+ *
+ *    - The null character (U+0000) has a column width of 0.
+ *
+ *    - Other C0/C1 control characters and DEL will lead to a return
+ *      value of -1.
+ *
+ *    - Non-spacing and enclosing combining characters (general
+ *      category code Mn or Me in the Unicode database) have a
+ *      column width of 0.
+ *
+ *    - SOFT HYPHEN (U+00AD) has a column width of 1.
+ *
+ *    - Other format characters (general category code Cf in the Unicode
+ *      database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
+ *
+ *    - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
+ *      have a column width of 0.
+ *
+ *    - Spacing characters in the East Asian Wide (W) or East Asian
+ *      Full-width (F) category as defined in Unicode Technical
+ *      Report #11 have a column width of 2.
+ *
+ *    - All remaining characters (including all printable
+ *      ISO 8859-1 and WGL4 characters, Unicode control characters,
+ *      etc.) have a column width of 1.
+ *
+ * This implementation assumes that wchar_t characters are encoded
+ * in ISO 10646.
+ */
+
+static int wcwidth(wchar_t ch)
+{
+	/*
+	 * Sorted list of non-overlapping intervals of non-spacing characters,
+	 * generated by
+	 *   "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c".
+	 */
+	static const struct interval combining[] = {
+		{ 0x0300, 0x0357 }, { 0x035D, 0x036F }, { 0x0483, 0x0486 },
+		{ 0x0488, 0x0489 }, { 0x0591, 0x05A1 }, { 0x05A3, 0x05B9 },
+		{ 0x05BB, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
+		{ 0x05C4, 0x05C4 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 },
+		{ 0x064B, 0x0658 }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 },
+		{ 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F },
+		{ 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 },
+		{ 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 },
+		{ 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 },
+		{ 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 },
+		{ 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 },
+		{ 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 },
+		{ 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 },
+		{ 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 },
+		{ 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 },
+		{ 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 },
+		{ 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 },
+		{ 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 },
+		{ 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 },
+		{ 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 },
+		{ 0x0CCC, 0x0CCD }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
+		{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+		{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
+		{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
+		{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
+		{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
+		{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
+		{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
+		{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
+		{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x1712, 0x1714 },
+		{ 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 },
+		{ 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 },
+		{ 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D },
+		{ 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 },
+		{ 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x200B, 0x200F },
+		{ 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F },
+		{ 0x20D0, 0x20EA }, { 0x302A, 0x302F }, { 0x3099, 0x309A },
+		{ 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 },
+		{ 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x1D167, 0x1D169 },
+		{ 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B },
+		{ 0x1D1AA, 0x1D1AD }, { 0xE0001, 0xE0001 },
+		{ 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF }
+	};
+
+	/* test for 8-bit control characters */
+	if (ch == 0)
+		return 0;
+	if (ch < 32 || (ch >= 0x7f && ch < 0xa0))
+		return -1;
+
+	/* binary search in table of non-spacing characters */
+	if (bisearch(ch, combining, sizeof(combining)
+				/ sizeof(struct interval) - 1))
+		return 0;
+
+	/*
+	 * If we arrive here, ch is neither a combining nor a C0/C1
+	 * control character.
+	 */
+
+	return 1 +
+		(ch >= 0x1100 &&
+                    /* Hangul Jamo init. consonants */
+		 (ch <= 0x115f ||
+		  ch == 0x2329 || ch == 0x232a ||
+                  /* CJK ... Yi */
+		  (ch >= 0x2e80 && ch <= 0xa4cf &&
+		   ch != 0x303f) ||
+		  /* Hangul Syllables */
+		  (ch >= 0xac00 && ch <= 0xd7a3) ||
+		  /* CJK Compatibility Ideographs */
+		  (ch >= 0xf900 && ch <= 0xfaff) ||
+		  /* CJK Compatibility Forms */
+		  (ch >= 0xfe30 && ch <= 0xfe6f) ||
+		  /* Fullwidth Forms */
+		  (ch >= 0xff00 && ch <= 0xff60) ||
+		  (ch >= 0xffe0 && ch <= 0xffe6) ||
+		  (ch >= 0x20000 && ch <= 0x2fffd) ||
+		  (ch >= 0x30000 && ch <= 0x3fffd)));
+}
+
+/*
+ * This function returns the number of columns occupied by the character
+ * pointed to by the variable start. The pointer is updated to point at
+ * the next character. If it was not valid UTF-8, the pointer is set to NULL.
+ */
+int utf8_width(const char **start)
+{
+	unsigned char *s = (unsigned char *)*start;
+	wchar_t ch;
+
+	if (*s < 0x80) {
+		/* 0xxxxxxx */
+		ch = *s;
+		*start += 1;
+	} else if ((s[0] & 0xe0) == 0xc0) {
+		/* 110XXXXx 10xxxxxx */
+		if ((s[1] & 0xc0) != 0x80 ||
+				/* overlong? */
+				(s[0] & 0xfe) == 0xc0)
+			goto invalid;
+		ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
+		*start += 2;
+	} else if ((s[0] & 0xf0) == 0xe0) {
+		/* 1110XXXX 10Xxxxxx 10xxxxxx */
+		if ((s[1] & 0xc0) != 0x80 ||
+				(s[2] & 0xc0) != 0x80 ||
+				/* overlong? */
+				(s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) ||
+				/* surrogate? */
+				(s[0] == 0xed && (s[1] & 0xe0) == 0xa0) ||
+				/* U+FFFE or U+FFFF? */
+				(s[0] == 0xef && s[1] == 0xbf &&
+				 (s[2] & 0xfe) == 0xbe))
+			goto invalid;
+		ch = ((s[0] & 0x0f) << 12) |
+			((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
+		*start += 3;
+	} else if ((s[0] & 0xf8) == 0xf0) {
+		/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
+		if ((s[1] & 0xc0) != 0x80 ||
+				(s[2] & 0xc0) != 0x80 ||
+				(s[3] & 0xc0) != 0x80 ||
+				/* overlong? */
+				(s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||
+				/* > U+10FFFF? */
+				(s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4)
+			goto invalid;
+		ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) |
+			((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
+		*start += 4;
+	} else {
+invalid:
+		*start = NULL;
+		return 0;
+	}
+
+	return wcwidth(ch);
+}
+
+int is_utf8(const char *text)
+{
+	while (*text) {
+		if (*text == '\n' || *text == '\t' || *text == '\r') {
+			text++;
+			continue;
+		}
+		utf8_width(&text);
+		if (!text)
+			return 0;
+	}
+	return 1;
+}
+
+static void print_spaces(int count)
+{
+	static const char s[] = "                    ";
+	while (count >= sizeof(s)) {
+		fwrite(s, sizeof(s) - 1, 1, stdout);
+		count -= sizeof(s) - 1;
+	}
+	fwrite(s, count, 1, stdout);
+}
+
+/*
+ * Wrap the text, if necessary. The variable indent is the indent for the
+ * first line, indent2 is the indent for all other lines.
+ */
+void print_wrapped_text(const char *text, int indent, int indent2, int width)
+{
+	int w = indent, assume_utf8 = is_utf8(text);
+	const char *bol = text, *space = NULL;
+
+	for (;;) {
+		char c = *text;
+		if (!c || isspace(c)) {
+			if (w < width || !space) {
+				const char *start = bol;
+				if (space)
+					start = space;
+				else
+					print_spaces(indent);
+				fwrite(start, text - start, 1, stdout);
+				if (!c) {
+					putchar('\n');
+					return;
+				} else if (c == '\t')
+					w |= 0x07;
+				space = text;
+				w++;
+				text++;
+			}
+			else {
+				putchar('\n');
+				text = bol = space + 1;
+				space = NULL;
+				w = indent = indent2;
+			}
+			continue;
+		}
+		if (assume_utf8)
+			w += utf8_width(&text);
+		else {
+			w++;
+			text++;
+		}
+	}
+}
--- a/utf8.h
+++ b/utf8.h
@@ -0,0 +1,8 @@
+#ifndef GIT_UTF8_H
+#define GIT_UTF8_H
+
+int utf8_width(const char **start);
+int is_utf8(const char *text);
+void print_wrapped_text(const char *text, int indent, int indent2, int len);
+
+#endif