From: Junio C Hamano <gitster@pobox.com>
Date: Wed, 6 Jun 2007 09:29:41 +0000 (-0700)
Subject: Merge branch 'mm/tag'
X-Git-Tag: v1.5.3-rc0~152
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/6abd0fb396a0c575dafd4e1021d37d178740396c?hp=980ea5c5bb1dfbbf93b919942c703b9158c35968

Merge branch 'mm/tag'

* mm/tag:
Teach git-tag about showing tag annotations.
---

diff --git a/.gitignore b/.gitignore
index 15aed70631..27e5aeb8a0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -40,6 +40,7 @@ git-fast-import
 git-fetch
 git-fetch--tool
 git-fetch-pack
+git-filter-branch
 git-findtags
 git-fmt-merge-msg
 git-for-each-ref
@@ -151,6 +152,7 @@ test-delta
 test-dump-cache-tree
 test-genrandom
 test-match-trees
+test-sha1
 common-cmds.h
 *.tar.gz
 *.dsc
diff --git a/Documentation/git-format-patch.txt b/Documentation/git-format-patch.txt
index a33d157b97..363edb0fcf 100644
--- a/Documentation/git-format-patch.txt
+++ b/Documentation/git-format-patch.txt
@@ -11,7 +11,8 @@ SYNOPSIS
 [verse]
 'git-format-patch' [-n | -k] [-o <dir> | --stdout] [--thread]
                    [--attach[=<boundary>] | --inline[=<boundary>]]
-                   [-s | --signoff] [<common diff options>] [--start-number <n>]
+                   [-s | --signoff] [<common diff options>]
+                   [--start-number <n>] [--numbered-files]
                    [--in-reply-to=Message-Id] [--suffix=.<sfx>]
                    [--ignore-if-in-upstream]
                    [--subject-prefix=Subject-Prefix]
@@ -30,9 +31,11 @@ gitlink:git-rev-parse[1].
 The output of this command is convenient for e-mail submission or
 for use with gitlink:git-am[1].
 
-Each output file is numbered sequentially from 1, and uses the
+By default, each output file is numbered sequentially from 1, and uses the
 first line of the commit message (massaged for pathname safety) as
-the filename. The names of the output files are printed to standard
+the filename. With the --numbered-files option, the output file names
+will only be numbers, without the first line of the commit appended.
+The names of the output files are printed to standard
 output, unless the --stdout option is specified.
 
 If -o is specified, output files are created in <dir>.  Otherwise
@@ -60,6 +63,11 @@ include::diff-options.txt[]
 --start-number <n>::
 	Start numbering the patches at <n> instead of 1.
 
+--numbered-files::
+	Output file names will be a simple number sequence
+	without the default first line of the commit appended.
+	Mutually exclusive with the --stdout option.
+
 -k|--keep-subject::
 	Do not strip/add '[PATCH]' from the first line of the
 	commit log message.
diff --git a/Documentation/git-fsck.txt b/Documentation/git-fsck.txt
index 8c68cf0372..ed6413a3c7 100644
--- a/Documentation/git-fsck.txt
+++ b/Documentation/git-fsck.txt
@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git-fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
-		 [--full] [--strict] [<object>*]
+		 [--full] [--strict] [--verbose] [<object>*]
 
 DESCRIPTION
 -----------
@@ -61,6 +61,9 @@ index file and all SHA1 references in .git/refs/* as heads.
 	objects that triggers this check, but it is recommended
 	to check new projects with this flag.
 
+--verbose::
+	Be chatty.
+
 It tests SHA1 and general object sanity, and it does full tracking of
 the resulting reachability and everything else. It prints out any
 corruption it finds (missing or bad objects), and if you use the
diff --git a/Makefile b/Makefile
index a11ff60549..cd3026db8d 100644
--- a/Makefile
+++ b/Makefile
@@ -1051,8 +1051,9 @@ dist-doc:
 
 clean:
 	rm -f *.o mozilla-sha1/*.o arm/*.o ppc/*.o compat/*.o xdiff/*.o \
-		test-chmtime$X test-genrandom$X $(LIB_FILE) $(XDIFF_LIB)
+		$(LIB_FILE) $(XDIFF_LIB)
 	rm -f $(ALL_PROGRAMS) $(BUILT_INS) git$X
+	rm -f $(TEST_PROGRAMS)
 	rm -f *.spec *.pyc *.pyo */*.pyc */*.pyo common-cmds.h TAGS tags
 	rm -rf autom4te.cache
 	rm -f configure config.log config.mak.autogen config.mak.append config.status config.cache
diff --git a/builtin-branch.c b/builtin-branch.c
index a5b6bbef6e..67f46c1ae2 100644
--- a/builtin-branch.c
+++ b/builtin-branch.c
@@ -317,8 +317,6 @@ static void print_ref_list(int kinds, int detached, int verbose, int abbrev)
 static char *config_repo;
 static char *config_remote;
 static const char *start_ref;
-static int start_len;
-static int base_len;
 
 static int get_remote_branch_name(const char *value)
 {
@@ -334,26 +332,41 @@ static int get_remote_branch_name(const char *value)
 
 	end = value + strlen(value);
 
-	/* Try an exact match first.  */
+	/*
+	 * Try an exact match first.  I.e. handle the case where the
+	 * value is "$anything:refs/foo/bar/baz" and start_ref is exactly
+	 * "refs/foo/bar/baz". Then the name at the remote is $anything.
+	 */
 	if (!strcmp(colon + 1, start_ref)) {
-		/* Truncate the value before the colon.  */
+		/* Truncate the value before the colon. */
 		nfasprintf(&config_repo, "%.*s", colon - value, value);
 		return 1;
 	}
 
-	/* Try with a wildcard match now.  */
-	if (end - value > 2 && end[-2] == '/' && end[-1] == '*' &&
-	    colon - value > 2 && colon[-2] == '/' && colon[-1] == '*' &&
-	    (end - 2) - (colon + 1) == base_len &&
-	    !strncmp(colon + 1, start_ref, base_len)) {
-		/* Replace the star with the remote branch name.  */
-		nfasprintf(&config_repo, "%.*s%s",
-			   (colon - 2) - value, value,
-			   start_ref + base_len);
-		return 1;
-	}
+	/*
+	 * Is this a wildcard match?
+	 */
+	if ((end - 2 <= value) || end[-2] != '/' || end[-1] != '*' ||
+	    (colon - 2 <= value) || colon[-2] != '/' || colon[-1] != '*')
+		return 0;
 
-	return 0;
+	/*
+	 * Value is "refs/foo/bar/<asterisk>:refs/baz/boa/<asterisk>"
+	 * and start_ref begins with "refs/baz/boa/"; the name at the
+	 * remote is refs/foo/bar/ with the remaining part of the
+	 * start_ref.  The length of the prefix on the RHS is (end -
+	 * colon - 2), including the slash immediately before the
+	 * asterisk.
+	 */
+	if ((strlen(start_ref) < end - colon - 2) ||
+	    memcmp(start_ref, colon + 1, end - colon - 2))
+		return 0; /* does not match prefix */
+
+	/* Replace the asterisk with the remote branch name.  */
+	nfasprintf(&config_repo, "%.*s%s",
+		   (colon - 1) - value, value,
+		   start_ref + (end - colon - 2));
+	return 1;
 }
 
 static int get_remote_config(const char *key, const char *value)
@@ -363,10 +376,12 @@ static int get_remote_config(const char *key, const char *value)
 		return 0;
 
 	var = strrchr(key, '.');
-	if (var == key + 6)
+	if (var == key + 6 || strcmp(var, ".fetch"))
 		return 0;
-
-	if (!strcmp(var, ".fetch") && get_remote_branch_name(value))
+	/*
+	 * Ok, we are looking at key == "remote.$foo.fetch";
+	 */
+	if (get_remote_branch_name(value))
 		nfasprintf(&config_remote, "%.*s", var - (key + 7), key + 7);
 
 	return 0;
@@ -392,14 +407,14 @@ static void set_branch_merge(const char *name, const char *config_remote,
 
 static void set_branch_defaults(const char *name, const char *real_ref)
 {
-	const char *slash = strrchr(real_ref, '/');
-
-	if (!slash)
-		return;
-
+	/*
+	 * name is the name of new branch under refs/heads;
+	 * real_ref is typically refs/remotes/$foo/$bar, where
+	 * $foo is the remote name (there typically are no slashes)
+	 * and $bar is the branch name we map from the remote
+	 * (it could have slashes).
+	 */
 	start_ref = real_ref;
-	start_len = strlen(real_ref);
-	base_len = slash - real_ref;
 	git_config(get_remote_config);
 	if (!config_repo && !config_remote &&
 	    !prefixcmp(real_ref, "refs/heads/")) {
diff --git a/builtin-fsck.c b/builtin-fsck.c
index 9959818ced..bacae5dfa6 100644
--- a/builtin-fsck.c
+++ b/builtin-fsck.c
@@ -20,6 +20,7 @@ static int check_strict;
 static int keep_cache_objects;
 static unsigned char head_sha1[20];
 static int errors_found;
+static int verbose;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 
@@ -149,6 +150,9 @@ static void check_unreachable_object(struct object *obj)
 
 static void check_object(struct object *obj)
 {
+	if (verbose)
+		fprintf(stderr, "Checking %s\n", sha1_to_hex(obj->sha1));
+
 	if (obj->flags & REACHABLE)
 		check_reachable_object(obj);
 	else
@@ -161,6 +165,9 @@ static void check_connectivity(void)
 
 	/* Look up all the requirements, warn about missing objects.. */
 	max = get_max_object_index();
+	if (verbose)
+		fprintf(stderr, "Checking connectivity (%d objects)\n", max);
+
 	for (i = 0; i < max; i++) {
 		struct object *obj = get_indexed_object(i);
 
@@ -229,6 +236,10 @@ static int fsck_tree(struct tree *item)
 	const char *o_name;
 	const unsigned char *o_sha1;
 
+	if (verbose)
+		fprintf(stderr, "Checking tree %s\n",
+				sha1_to_hex(item->object.sha1));
+
 	init_tree_desc(&desc, item->buffer, item->size);
 
 	o_mode = 0;
@@ -317,6 +328,10 @@ static int fsck_commit(struct commit *commit)
 	char *buffer = commit->buffer;
 	unsigned char tree_sha1[20], sha1[20];
 
+	if (verbose)
+		fprintf(stderr, "Checking commit %s\n",
+			sha1_to_hex(commit->object.sha1));
+
 	if (memcmp(buffer, "tree ", 5))
 		return objerror(&commit->object, "invalid format - expected 'tree' line");
 	if (get_sha1_hex(buffer+5, tree_sha1) || buffer[45] != '\n')
@@ -345,6 +360,10 @@ static int fsck_tag(struct tag *tag)
 {
 	struct object *tagged = tag->tagged;
 
+	if (verbose)
+		fprintf(stderr, "Checking tag %s\n",
+			sha1_to_hex(tag->object.sha1));
+
 	if (!tagged) {
 		return objerror(&tag->object, "could not load tagged object");
 	}
@@ -446,6 +465,9 @@ static void fsck_dir(int i, char *path)
 	if (!dir)
 		return;
 
+	if (verbose)
+		fprintf(stderr, "Checking directory %s\n", path);
+
 	while ((de = readdir(dir)) != NULL) {
 		char name[100];
 		unsigned char sha1[20];
@@ -480,6 +502,10 @@ static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
 {
 	struct object *obj;
 
+	if (verbose)
+		fprintf(stderr, "Checking reflog %s->%s\n",
+			sha1_to_hex(osha1), sha1_to_hex(nsha1));
+
 	if (!is_null_sha1(osha1)) {
 		obj = lookup_object(osha1);
 		if (obj) {
@@ -549,6 +575,10 @@ static void get_default_heads(void)
 static void fsck_object_dir(const char *path)
 {
 	int i;
+
+	if (verbose)
+		fprintf(stderr, "Checking object directory\n");
+
 	for (i = 0; i < 256; i++) {
 		static char dir[4096];
 		sprintf(dir, "%s/%02x", path, i);
@@ -564,6 +594,9 @@ static int fsck_head_link(void)
 	int null_is_error = 0;
 	const char *head_points_at = resolve_ref("HEAD", sha1, 0, &flag);
 
+	if (verbose)
+		fprintf(stderr, "Checking HEAD link\n");
+
 	if (!head_points_at)
 		return error("Invalid HEAD");
 	if (!strcmp(head_points_at, "HEAD"))
@@ -586,6 +619,9 @@ static int fsck_cache_tree(struct cache_tree *it)
 	int i;
 	int err = 0;
 
+	if (verbose)
+		fprintf(stderr, "Checking cache tree\n");
+
 	if (0 <= it->entry_count) {
 		struct object *obj = parse_object(it->sha1);
 		if (!obj) {
@@ -605,7 +641,7 @@ static int fsck_cache_tree(struct cache_tree *it)
 
 static const char fsck_usage[] =
 "git-fsck [--tags] [--root] [[--unreachable] [--cache] [--full] "
-"[--strict] <head-sha1>*]";
+"[--strict] [--verbose] <head-sha1>*]";
 
 int cmd_fsck(int argc, char **argv, const char *prefix)
 {
@@ -645,6 +681,10 @@ int cmd_fsck(int argc, char **argv, const char *prefix)
 			check_strict = 1;
 			continue;
 		}
+		if (!strcmp(arg, "--verbose")) {
+			verbose = 1;
+			continue;
+		}
 		if (*arg == '-')
 			usage(fsck_usage);
 	}
diff --git a/builtin-log.c b/builtin-log.c
index 37447123f9..212cdfc769 100644
--- a/builtin-log.c
+++ b/builtin-log.c
@@ -298,7 +298,8 @@ static int git_format_config(const char *var, const char *value)
 static FILE *realstdout = NULL;
 static const char *output_directory = NULL;
 
-static int reopen_stdout(struct commit *commit, int nr, int keep_subject)
+static int reopen_stdout(struct commit *commit, int nr, int keep_subject,
+			 int numbered_files)
 {
 	char filename[PATH_MAX];
 	char *sol;
@@ -315,53 +316,61 @@ static int reopen_stdout(struct commit *commit, int nr, int keep_subject)
 			filename[len++] = '/';
 	}
 
-	sprintf(filename + len, "%04d", nr);
-	len = strlen(filename);
-
-	sol = strstr(commit->buffer, "\n\n");
-	if (sol) {
-		int j, space = 1;
-
-		sol += 2;
-		/* strip [PATCH] or [PATCH blabla] */
-		if (!keep_subject && !prefixcmp(sol, "[PATCH")) {
-			char *eos = strchr(sol + 6, ']');
-			if (eos) {
-				while (isspace(*eos))
-					eos++;
-				sol = eos;
-			}
-		}
+	if (numbered_files) {
+		sprintf(filename + len, "%d", nr);
+		len = strlen(filename);
 
-		for (j = 0;
-		     j < FORMAT_PATCH_NAME_MAX - suffix_len - 5 &&
-			     len < sizeof(filename) - suffix_len &&
-			     sol[j] && sol[j] != '\n';
-		     j++) {
-			if (istitlechar(sol[j])) {
-				if (space) {
-					filename[len++] = '-';
-					space = 0;
+	} else {
+		sprintf(filename + len, "%04d", nr);
+		len = strlen(filename);
+
+		sol = strstr(commit->buffer, "\n\n");
+		if (sol) {
+			int j, space = 1;
+
+			sol += 2;
+			/* strip [PATCH] or [PATCH blabla] */
+			if (!keep_subject && !prefixcmp(sol, "[PATCH")) {
+				char *eos = strchr(sol + 6, ']');
+				if (eos) {
+					while (isspace(*eos))
+						eos++;
+					sol = eos;
 				}
-				filename[len++] = sol[j];
-				if (sol[j] == '.')
-					while (sol[j + 1] == '.')
-						j++;
-			} else
-				space = 1;
+			}
+
+			for (j = 0;
+			     j < FORMAT_PATCH_NAME_MAX - suffix_len - 5 &&
+				     len < sizeof(filename) - suffix_len &&
+				     sol[j] && sol[j] != '\n';
+			     j++) {
+				if (istitlechar(sol[j])) {
+					if (space) {
+						filename[len++] = '-';
+						space = 0;
+					}
+					filename[len++] = sol[j];
+					if (sol[j] == '.')
+						while (sol[j + 1] == '.')
+							j++;
+				} else
+					space = 1;
+			}
+			while (filename[len - 1] == '.'
+			       || filename[len - 1] == '-')
+				len--;
+			filename[len] = 0;
 		}
-		while (filename[len - 1] == '.' || filename[len - 1] == '-')
-			len--;
-		filename[len] = 0;
+		if (len + suffix_len >= sizeof(filename))
+			return error("Patch pathname too long");
+		strcpy(filename + len, fmt_patch_suffix);
 	}
-	if (len + suffix_len >= sizeof(filename))
-		return error("Patch pathname too long");
-	strcpy(filename + len, fmt_patch_suffix);
+
 	fprintf(realstdout, "%s\n", filename);
 	if (freopen(filename, "w", stdout) == NULL)
 		return error("Cannot open patch file %s",filename);
-	return 0;
 
+	return 0;
 }
 
 static void get_patch_ids(struct rev_info *rev, struct patch_ids *ids, const char *prefix)
@@ -431,6 +440,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 	int numbered = 0;
 	int start_number = -1;
 	int keep_subject = 0;
+	int numbered_files = 0;		/* _just_ numbers */
 	int subject_prefix = 0;
 	int ignore_if_in_upstream = 0;
 	int thread = 0;
@@ -465,6 +475,8 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 			numbered = 1;
 		else if (!prefixcmp(argv[i], "--start-number="))
 			start_number = strtol(argv[i] + 15, NULL, 10);
+		else if (!strcmp(argv[i], "--numbered-files"))
+			numbered_files = 1;
 		else if (!strcmp(argv[i], "--start-number")) {
 			i++;
 			if (i == argc)
@@ -540,6 +552,8 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 		die ("-n and -k are mutually exclusive.");
 	if (keep_subject && subject_prefix)
 		die ("--subject-prefix and -k are mutually exclusive.");
+	if (numbered_files && use_stdout)
+		die ("--numbered-files and --stdout are mutually exclusive.");
 
 	argc = setup_revisions(argc, argv, &rev, "HEAD");
 	if (argc > 1)
@@ -614,7 +628,8 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 			rev.message_id = message_id;
 		}
 		if (!use_stdout)
-			if (reopen_stdout(commit, rev.nr, keep_subject))
+			if (reopen_stdout(commit, rev.nr, keep_subject,
+					  numbered_files))
 				die("Failed to create output files");
 		shown = log_tree_commit(&rev, commit);
 		free(commit->buffer);
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index ccb25f6a9c..8b9740c277 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -23,10 +23,9 @@ git-pack-objects [{ -q | --progress | --all-progress }] [--max-pack-size=N] \n\
 	[--stdout | base-name] [<ref-list | <object-list]";
 
 struct object_entry {
-	unsigned char sha1[20];
-	uint32_t crc32;		/* crc of raw pack data for this object */
-	off_t offset;		/* offset into the final pack file */
+	struct pack_idx_entry idx;
 	unsigned long size;	/* uncompressed size */
+
 	unsigned int hash;	/* name hint hash */
 	unsigned int depth;	/* delta depth */
 	struct packed_git *in_pack; 	/* already in pack */
@@ -66,7 +65,6 @@ static int allow_ofs_delta;
 static const char *pack_tmp_name, *idx_tmp_name;
 static char tmpname[PATH_MAX];
 static const char *base_name;
-static unsigned char pack_file_sha1[20];
 static int progress = 1;
 static int window = 10;
 static uint32_t pack_size_limit;
@@ -246,11 +244,11 @@ static void *delta_against(void *buf, unsigned long size, struct object_entry *e
 {
 	unsigned long othersize, delta_size;
 	enum object_type type;
-	void *otherbuf = read_sha1_file(entry->delta->sha1, &type, &othersize);
+	void *otherbuf = read_sha1_file(entry->delta->idx.sha1, &type, &othersize);
 	void *delta_buf;
 
 	if (!otherbuf)
-		die("unable to read %s", sha1_to_hex(entry->delta->sha1));
+		die("unable to read %s", sha1_to_hex(entry->delta->idx.sha1));
         delta_buf = diff_delta(otherbuf, othersize,
 			       buf, size, &delta_size, 0);
         if (!delta_buf || delta_size != entry->delta_size)
@@ -379,11 +377,11 @@ static unsigned long write_object(struct sha1file *f,
 				/* yes if unlimited packfile */
 				!pack_size_limit ? 1 :
 				/* no if base written to previous pack */
-				entry->delta->offset == (off_t)-1 ? 0 :
+				entry->delta->idx.offset == (off_t)-1 ? 0 :
 				/* otherwise double-check written to this
 				 * pack,  like we do below
 				 */
-				entry->delta->offset ? 1 : 0;
+				entry->delta->idx.offset ? 1 : 0;
 
 	if (!pack_to_stdout)
 		crc32_begin(f);
@@ -411,22 +409,22 @@ static unsigned long write_object(struct sha1file *f,
 		unsigned long maxsize;
 		void *out;
 		if (!usable_delta) {
-			buf = read_sha1_file(entry->sha1, &obj_type, &size);
+			buf = read_sha1_file(entry->idx.sha1, &obj_type, &size);
 			if (!buf)
-				die("unable to read %s", sha1_to_hex(entry->sha1));
+				die("unable to read %s", sha1_to_hex(entry->idx.sha1));
 		} else if (entry->delta_data) {
 			size = entry->delta_size;
 			buf = entry->delta_data;
 			entry->delta_data = NULL;
-			obj_type = (allow_ofs_delta && entry->delta->offset) ?
+			obj_type = (allow_ofs_delta && entry->delta->idx.offset) ?
 				OBJ_OFS_DELTA : OBJ_REF_DELTA;
 		} else {
-			buf = read_sha1_file(entry->sha1, &type, &size);
+			buf = read_sha1_file(entry->idx.sha1, &type, &size);
 			if (!buf)
-				die("unable to read %s", sha1_to_hex(entry->sha1));
+				die("unable to read %s", sha1_to_hex(entry->idx.sha1));
 			buf = delta_against(buf, size, entry);
 			size = entry->delta_size;
-			obj_type = (allow_ofs_delta && entry->delta->offset) ?
+			obj_type = (allow_ofs_delta && entry->delta->idx.offset) ?
 				OBJ_OFS_DELTA : OBJ_REF_DELTA;
 		}
 		/* compress the data to store and put compressed length in datalen */
@@ -456,7 +454,7 @@ static unsigned long write_object(struct sha1file *f,
 			 * encoding of the relative offset for the delta
 			 * base from this object's position in the pack.
 			 */
-			off_t ofs = entry->offset - entry->delta->offset;
+			off_t ofs = entry->idx.offset - entry->delta->idx.offset;
 			unsigned pos = sizeof(dheader) - 1;
 			dheader[pos] = ofs & 127;
 			while (ofs >>= 7)
@@ -480,7 +478,7 @@ static unsigned long write_object(struct sha1file *f,
 				return 0;
 			}
 			sha1write(f, header, hdrlen);
-			sha1write(f, entry->delta->sha1, 20);
+			sha1write(f, entry->delta->idx.sha1, 20);
 			hdrlen += 20;
 		} else {
 			if (limit && hdrlen + datalen + 20 >= limit) {
@@ -501,7 +499,7 @@ static unsigned long write_object(struct sha1file *f,
 		off_t offset;
 
 		if (entry->delta) {
-			obj_type = (allow_ofs_delta && entry->delta->offset) ?
+			obj_type = (allow_ofs_delta && entry->delta->idx.offset) ?
 				OBJ_OFS_DELTA : OBJ_REF_DELTA;
 			reused_delta++;
 		}
@@ -511,11 +509,11 @@ static unsigned long write_object(struct sha1file *f,
 		datalen = revidx[1].offset - offset;
 		if (!pack_to_stdout && p->index_version > 1 &&
 		    check_pack_crc(p, &w_curs, offset, datalen, revidx->nr))
-			die("bad packed object CRC for %s", sha1_to_hex(entry->sha1));
+			die("bad packed object CRC for %s", sha1_to_hex(entry->idx.sha1));
 		offset += entry->in_pack_header_size;
 		datalen -= entry->in_pack_header_size;
 		if (obj_type == OBJ_OFS_DELTA) {
-			off_t ofs = entry->offset - entry->delta->offset;
+			off_t ofs = entry->idx.offset - entry->delta->idx.offset;
 			unsigned pos = sizeof(dheader) - 1;
 			dheader[pos] = ofs & 127;
 			while (ofs >>= 7)
@@ -529,7 +527,7 @@ static unsigned long write_object(struct sha1file *f,
 			if (limit && hdrlen + 20 + datalen + 20 >= limit)
 				return 0;
 			sha1write(f, header, hdrlen);
-			sha1write(f, entry->delta->sha1, 20);
+			sha1write(f, entry->delta->idx.sha1, 20);
 			hdrlen += 20;
 		} else {
 			if (limit && hdrlen + datalen + 20 >= limit)
@@ -539,7 +537,7 @@ static unsigned long write_object(struct sha1file *f,
 
 		if (!pack_to_stdout && p->index_version == 1 &&
 		    check_pack_inflate(p, &w_curs, offset, datalen, entry->size))
-			die("corrupt packed object for %s", sha1_to_hex(entry->sha1));
+			die("corrupt packed object for %s", sha1_to_hex(entry->idx.sha1));
 		copy_pack_data(f, p, &w_curs, offset, datalen);
 		unuse_pack(&w_curs);
 		reused++;
@@ -548,7 +546,7 @@ static unsigned long write_object(struct sha1file *f,
 		written_delta++;
 	written++;
 	if (!pack_to_stdout)
-		entry->crc32 = crc32_end(f);
+		entry->idx.crc32 = crc32_end(f);
 	return hdrlen + datalen;
 }
 
@@ -559,7 +557,7 @@ static off_t write_one(struct sha1file *f,
 	unsigned long size;
 
 	/* offset is non zero if object is written already. */
-	if (e->offset || e->preferred_base)
+	if (e->idx.offset || e->preferred_base)
 		return offset;
 
 	/* if we are deltified, write out base object first. */
@@ -569,10 +567,10 @@ static off_t write_one(struct sha1file *f,
 			return 0;
 	}
 
-	e->offset = offset;
+	e->idx.offset = offset;
 	size = write_object(f, e, offset);
 	if (!size) {
-		e->offset = 0;
+		e->idx.offset = 0;
 		return 0;
 	}
 	written_list[nr_written++] = e;
@@ -589,8 +587,7 @@ static int open_object_dir_tmp(const char *path)
     return mkstemp(tmpname);
 }
 
-/* forward declarations for write_pack_file */
-static void write_index_file(off_t last_obj_offset, unsigned char *sha1);
+/* forward declaration for write_pack_file */
 static int adjust_perm(const char *path, mode_t mode);
 
 static void write_pack_file(void)
@@ -607,6 +604,8 @@ static void write_pack_file(void)
 	written_list = xmalloc(nr_objects * sizeof(struct object_entry *));
 
 	do {
+		unsigned char sha1[20];
+
 		if (pack_to_stdout) {
 			f = sha1fd(1, "<stdout>");
 		} else {
@@ -638,23 +637,23 @@ static void write_pack_file(void)
 		 * If so, rewrite it like in fast-import
 		 */
 		if (pack_to_stdout || nr_written == nr_remaining) {
-			sha1close(f, pack_file_sha1, 1);
+			sha1close(f, sha1, 1);
 		} else {
-			sha1close(f, pack_file_sha1, 0);
-			fixup_pack_header_footer(f->fd, pack_file_sha1, pack_tmp_name, nr_written);
+			sha1close(f, sha1, 0);
+			fixup_pack_header_footer(f->fd, sha1, pack_tmp_name, nr_written);
 			close(f->fd);
 		}
 
 		if (!pack_to_stdout) {
-			unsigned char object_list_sha1[20];
 			mode_t mode = umask(0);
 
 			umask(mode);
 			mode = 0444 & ~mode;
 
-			write_index_file(last_obj_offset, object_list_sha1);
+			idx_tmp_name = write_idx_file(NULL,
+				(struct pack_idx_entry **) written_list, nr_written, sha1);
 			snprintf(tmpname, sizeof(tmpname), "%s-%s.pack",
-				 base_name, sha1_to_hex(object_list_sha1));
+				 base_name, sha1_to_hex(sha1));
 			if (adjust_perm(pack_tmp_name, mode))
 				die("unable to make temporary pack file readable: %s",
 				    strerror(errno));
@@ -662,19 +661,19 @@ static void write_pack_file(void)
 				die("unable to rename temporary pack file: %s",
 				    strerror(errno));
 			snprintf(tmpname, sizeof(tmpname), "%s-%s.idx",
-				 base_name, sha1_to_hex(object_list_sha1));
+				 base_name, sha1_to_hex(sha1));
 			if (adjust_perm(idx_tmp_name, mode))
 				die("unable to make temporary index file readable: %s",
 				    strerror(errno));
 			if (rename(idx_tmp_name, tmpname))
 				die("unable to rename temporary index file: %s",
 				    strerror(errno));
-			puts(sha1_to_hex(object_list_sha1));
+			puts(sha1_to_hex(sha1));
 		}
 
 		/* mark written objects as written to previous pack */
 		for (j = 0; j < nr_written; j++) {
-			written_list[j]->offset = (off_t)-1;
+			written_list[j]->idx.offset = (off_t)-1;
 		}
 		nr_remaining -= nr_written;
 	} while (nr_remaining && i < nr_objects);
@@ -692,129 +691,12 @@ static void write_pack_file(void)
 	 */
 	for (j = 0; i < nr_objects; i++) {
 		struct object_entry *e = objects + i;
-		j += !e->offset && !e->preferred_base;
+		j += !e->idx.offset && !e->preferred_base;
 	}
 	if (j)
 		die("wrote %u objects as expected but %u unwritten", written, j);
 }
 
-static int sha1_sort(const void *_a, const void *_b)
-{
-	const struct object_entry *a = *(struct object_entry **)_a;
-	const struct object_entry *b = *(struct object_entry **)_b;
-	return hashcmp(a->sha1, b->sha1);
-}
-
-static uint32_t index_default_version = 1;
-static uint32_t index_off32_limit = 0x7fffffff;
-
-static void write_index_file(off_t last_obj_offset, unsigned char *sha1)
-{
-	struct sha1file *f;
-	struct object_entry **sorted_by_sha, **list, **last;
-	uint32_t array[256];
-	uint32_t i, index_version;
-	SHA_CTX ctx;
-
-	int fd = open_object_dir_tmp("tmp_idx_XXXXXX");
-	if (fd < 0)
-		die("unable to create %s: %s\n", tmpname, strerror(errno));
-	idx_tmp_name = xstrdup(tmpname);
-	f = sha1fd(fd, idx_tmp_name);
-
-	if (nr_written) {
-		sorted_by_sha = written_list;
-		qsort(sorted_by_sha, nr_written, sizeof(*sorted_by_sha), sha1_sort);
-		list = sorted_by_sha;
-		last = sorted_by_sha + nr_written;
-	} else
-		sorted_by_sha = list = last = NULL;
-
-	/* if last object's offset is >= 2^31 we should use index V2 */
-	index_version = (last_obj_offset >> 31) ? 2 : index_default_version;
-
-	/* index versions 2 and above need a header */
-	if (index_version >= 2) {
-		struct pack_idx_header hdr;
-		hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
-		hdr.idx_version = htonl(index_version);
-		sha1write(f, &hdr, sizeof(hdr));
-	}
-
-	/*
-	 * Write the first-level table (the list is sorted,
-	 * but we use a 256-entry lookup to be able to avoid
-	 * having to do eight extra binary search iterations).
-	 */
-	for (i = 0; i < 256; i++) {
-		struct object_entry **next = list;
-		while (next < last) {
-			struct object_entry *entry = *next;
-			if (entry->sha1[0] != i)
-				break;
-			next++;
-		}
-		array[i] = htonl(next - sorted_by_sha);
-		list = next;
-	}
-	sha1write(f, array, 256 * 4);
-
-	/* Compute the SHA1 hash of sorted object names. */
-	SHA1_Init(&ctx);
-
-	/* Write the actual SHA1 entries. */
-	list = sorted_by_sha;
-	for (i = 0; i < nr_written; i++) {
-		struct object_entry *entry = *list++;
-		if (index_version < 2) {
-			uint32_t offset = htonl(entry->offset);
-			sha1write(f, &offset, 4);
-		}
-		sha1write(f, entry->sha1, 20);
-		SHA1_Update(&ctx, entry->sha1, 20);
-	}
-
-	if (index_version >= 2) {
-		unsigned int nr_large_offset = 0;
-
-		/* write the crc32 table */
-		list = sorted_by_sha;
-		for (i = 0; i < nr_written; i++) {
-			struct object_entry *entry = *list++;
-			uint32_t crc32_val = htonl(entry->crc32);
-			sha1write(f, &crc32_val, 4);
-		}
-
-		/* write the 32-bit offset table */
-		list = sorted_by_sha;
-		for (i = 0; i < nr_written; i++) {
-			struct object_entry *entry = *list++;
-			uint32_t offset = (entry->offset <= index_off32_limit) ?
-				entry->offset : (0x80000000 | nr_large_offset++);
-			offset = htonl(offset);
-			sha1write(f, &offset, 4);
-		}
-
-		/* write the large offset table */
-		list = sorted_by_sha;
-		while (nr_large_offset) {
-			struct object_entry *entry = *list++;
-			uint64_t offset = entry->offset;
-			if (offset > index_off32_limit) {
-				uint32_t split[2];
-				split[0]        = htonl(offset >> 32);
-				split[1] = htonl(offset & 0xffffffff);
-				sha1write(f, split, 8);
-				nr_large_offset--;
-			}
-		}
-	}
-
-	sha1write(f, pack_file_sha1, 20);
-	sha1close(f, NULL, 1);
-	SHA1_Final(sha1, &ctx);
-}
-
 static int locate_object_entry_hash(const unsigned char *sha1)
 {
 	int i;
@@ -822,7 +704,7 @@ static int locate_object_entry_hash(const unsigned char *sha1)
 	memcpy(&ui, sha1, sizeof(unsigned int));
 	i = ui % object_ix_hashsz;
 	while (0 < object_ix[i]) {
-		if (!hashcmp(sha1, objects[object_ix[i] - 1].sha1))
+		if (!hashcmp(sha1, objects[object_ix[i] - 1].idx.sha1))
 			return i;
 		if (++i == object_ix_hashsz)
 			i = 0;
@@ -854,7 +736,7 @@ static void rehash_objects(void)
 	object_ix = xrealloc(object_ix, sizeof(int) * object_ix_hashsz);
 	memset(object_ix, 0, sizeof(int) * object_ix_hashsz);
 	for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
-		int ix = locate_object_entry_hash(oe->sha1);
+		int ix = locate_object_entry_hash(oe->idx.sha1);
 		if (0 <= ix)
 			continue;
 		ix = -1 - ix;
@@ -948,7 +830,7 @@ static int add_object_entry(const unsigned char *sha1, enum object_type type,
 
 	entry = objects + nr_objects++;
 	memset(entry, 0, sizeof(*entry));
-	hashcpy(entry->sha1, sha1);
+	hashcpy(entry->idx.sha1, sha1);
 	entry->hash = hash;
 	if (type)
 		entry->type = type;
@@ -1268,13 +1150,13 @@ static void check_object(struct object_entry *entry)
 				ofs += 1;
 				if (!ofs || MSB(ofs, 7))
 					die("delta base offset overflow in pack for %s",
-					    sha1_to_hex(entry->sha1));
+					    sha1_to_hex(entry->idx.sha1));
 				c = buf[used_0++];
 				ofs = (ofs << 7) + (c & 127);
 			}
 			if (ofs >= entry->in_pack_offset)
 				die("delta base offset out of bound for %s",
-				    sha1_to_hex(entry->sha1));
+				    sha1_to_hex(entry->idx.sha1));
 			ofs = entry->in_pack_offset - ofs;
 			if (!no_reuse_delta && !entry->preferred_base)
 				base_ref = find_packed_object_name(p, ofs);
@@ -1321,10 +1203,10 @@ static void check_object(struct object_entry *entry)
 		unuse_pack(&w_curs);
 	}
 
-	entry->type = sha1_object_info(entry->sha1, &entry->size);
+	entry->type = sha1_object_info(entry->idx.sha1, &entry->size);
 	if (entry->type < 0)
 		die("unable to get type of object %s",
-		    sha1_to_hex(entry->sha1));
+		    sha1_to_hex(entry->idx.sha1));
 }
 
 static int pack_offset_sort(const void *_a, const void *_b)
@@ -1334,7 +1216,7 @@ static int pack_offset_sort(const void *_a, const void *_b)
 
 	/* avoid filesystem trashing with loose objects */
 	if (!a->in_pack && !b->in_pack)
-		return hashcmp(a->sha1, b->sha1);
+		return hashcmp(a->idx.sha1, b->idx.sha1);
 
 	if (a->in_pack < b->in_pack)
 		return -1;
@@ -1463,16 +1345,16 @@ static int try_delta(struct unpacked *trg, struct unpacked *src,
 
 	/* Load data if not already done */
 	if (!trg->data) {
-		trg->data = read_sha1_file(trg_entry->sha1, &type, &sz);
+		trg->data = read_sha1_file(trg_entry->idx.sha1, &type, &sz);
 		if (sz != trg_size)
 			die("object %s inconsistent object length (%lu vs %lu)",
-			    sha1_to_hex(trg_entry->sha1), sz, trg_size);
+			    sha1_to_hex(trg_entry->idx.sha1), sz, trg_size);
 	}
 	if (!src->data) {
-		src->data = read_sha1_file(src_entry->sha1, &type, &sz);
+		src->data = read_sha1_file(src_entry->idx.sha1, &type, &sz);
 		if (sz != src_size)
 			die("object %s inconsistent object length (%lu vs %lu)",
-			    sha1_to_hex(src_entry->sha1), sz, src_size);
+			    sha1_to_hex(src_entry->idx.sha1), sz, src_size);
 	}
 	if (!src->index) {
 		src->index = create_delta_index(src->data, src_size);
@@ -1869,12 +1751,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		}
 		if (!prefixcmp(arg, "--index-version=")) {
 			char *c;
-			index_default_version = strtoul(arg + 16, &c, 10);
-			if (index_default_version > 2)
+			pack_idx_default_version = strtoul(arg + 16, &c, 10);
+			if (pack_idx_default_version > 2)
 				die("bad %s", arg);
 			if (*c == ',')
-				index_off32_limit = strtoul(c+1, &c, 0);
-			if (*c || index_off32_limit & 0x80000000)
+				pack_idx_off32_limit = strtoul(c+1, &c, 0);
+			if (*c || pack_idx_off32_limit & 0x80000000)
 				die("bad %s", arg);
 			continue;
 		}
diff --git a/diff.c b/diff.c
index 508bc51ed5..c57ac33414 100644
--- a/diff.c
+++ b/diff.c
@@ -1107,10 +1107,8 @@ static void setup_diff_attr_check(struct git_attr_check *check)
 	check->attr = attr_diff;
 }
 
-#define FIRST_FEW_BYTES 8000
 static int file_is_binary(struct diff_filespec *one)
 {
-	unsigned long sz;
 	struct git_attr_check attr_diff_check;
 
 	setup_diff_attr_check(&attr_diff_check);
@@ -1127,10 +1125,7 @@ static int file_is_binary(struct diff_filespec *one)
 			return 0;
 		diff_populate_filespec(one, 0);
 	}
-	sz = one->size;
-	if (FIRST_FEW_BYTES < sz)
-		sz = FIRST_FEW_BYTES;
-	return !!memchr(one->data, 0, sz);
+	return buffer_is_binary(one->data, one->size);
 }
 
 static void builtin_diff(const char *name_a,
diff --git a/git-mergetool.sh b/git-mergetool.sh
index e62351bcba..bb21b037d6 100755
--- a/git-mergetool.sh
+++ b/git-mergetool.sh
@@ -5,7 +5,7 @@
 # Copyright (c) 2006 Theodore Y. Ts'o
 #
 # This file is licensed under the GPL v2, or a later version
-# at the discretion of Junio C Hammano.
+# at the discretion of Junio C Hamano.
 #
 
 USAGE='[--tool=tool] [file to merge] ...'
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index c3921cb0ba..e92596c295 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -94,6 +94,13 @@ BEGIN
 # (relative to the current git repository)
 our $mimetypes_file = undef;
 
+# assume this charset if line contains non-UTF-8 characters;
+# it should be valid encoding (see Encoding::Supported(3pm) for list),
+# for which encoding all byte sequences are valid, for example
+# 'iso-8859-1' aka 'latin1' (it is decoded without checking, so it
+# could be even 'utf-8' for the old behavior)
+our $fallback_encoding = 'latin1';
+
 # You define site-wide feature defaults here; override them with
 # $GITWEB_CONFIG as necessary.
 our %feature = (
@@ -602,6 +609,20 @@ sub validate_refname {
 	return $input;
 }
 
+# decode sequences of octets in utf8 into Perl's internal form,
+# which is utf-8 with utf8 flag set if needed.  gitweb writes out
+# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning
+sub to_utf8 {
+	my $str = shift;
+	my $res;
+	eval { $res = decode_utf8($str, Encode::FB_CROAK); };
+	if (defined $res) {
+		return $res;
+	} else {
+		return decode($fallback_encoding, $str, Encode::FB_DEFAULT);
+	}
+}
+
 # quote unsafe chars, but keep the slash, even when it's not
 # correct, but quoted slashes look too horrible in bookmarks
 sub esc_param {
@@ -626,7 +647,7 @@ ($;%)
 	my $str = shift;
 	my %opts = @_;
 
-	$str = decode_utf8($str);
+	$str = to_utf8($str);
 	$str = $cgi->escapeHTML($str);
 	if ($opts{'-nbsp'}) {
 		$str =~ s/ /&nbsp;/g;
@@ -640,7 +661,7 @@ sub esc_path {
 	my $str = shift;
 	my %opts = @_;
 
-	$str = decode_utf8($str);
+	$str = to_utf8($str);
 	$str = $cgi->escapeHTML($str);
 	if ($opts{'-nbsp'}) {
 		$str =~ s/ /&nbsp;/g;
@@ -925,7 +946,7 @@ sub format_subject_html {
 
 	if (length($short) < length($long)) {
 		return $cgi->a({-href => $href, -class => "list subject",
-		                -title => decode_utf8($long)},
+		                -title => to_utf8($long)},
 		       esc_html($short) . $extra);
 	} else {
 		return $cgi->a({-href => $href, -class => "list subject"},
@@ -1239,7 +1260,7 @@ sub git_get_projects_list {
 			if (check_export_ok("$projectroot/$path")) {
 				my $pr = {
 					path => $path,
-					owner => decode_utf8($owner),
+					owner => to_utf8($owner),
 				};
 				push @list, $pr;
 				(my $forks_path = $path) =~ s/\.git$//;
@@ -1269,7 +1290,7 @@ sub git_get_project_owner {
 			$pr = unescape($pr);
 			$ow = unescape($ow);
 			if ($pr eq $project) {
-				$owner = decode_utf8($ow);
+				$owner = to_utf8($ow);
 				last;
 			}
 		}
@@ -1759,7 +1780,7 @@ sub get_file_owner {
 	}
 	my $owner = $gcos;
 	$owner =~ s/[,;].*$//;
-	return decode_utf8($owner);
+	return to_utf8($owner);
 }
 
 ## ......................................................................
@@ -1842,7 +1863,7 @@ sub git_header_html {
 
 	my $title = "$site_name";
 	if (defined $project) {
-		$title .= " - " . decode_utf8($project);
+		$title .= " - " . to_utf8($project);
 		if (defined $action) {
 			$title .= "/$action";
 			if (defined $file_name) {
@@ -2116,7 +2137,7 @@ sub git_print_page_path {
 
 	print "<div class=\"page_path\">";
 	print $cgi->a({-href => href(action=>"tree", hash_base=>$hb),
-	              -title => 'tree root'}, decode_utf8("[$project]"));
+	              -title => 'tree root'}, to_utf8("[$project]"));
 	print " / ";
 	if (defined $name) {
 		my @dirname = split '/', $name;
@@ -2936,7 +2957,7 @@ sub git_project_list_body {
 		($pr->{'age'}, $pr->{'age_string'}) = @aa;
 		if (!defined $pr->{'descr'}) {
 			my $descr = git_get_project_description($pr->{'path'}) || "";
-			$pr->{'descr_long'} = decode_utf8($descr);
+			$pr->{'descr_long'} = to_utf8($descr);
 			$pr->{'descr'} = chop_str($descr, 25, 5);
 		}
 		if (!defined $pr->{'owner'}) {
@@ -3981,7 +4002,7 @@ sub git_snapshot {
 	my $git = git_cmd_str();
 	my $name = $project;
 	$name =~ s/\047/\047\\\047\047/g;
-	my $filename = decode_utf8(basename($project));
+	my $filename = to_utf8(basename($project));
 	my $cmd;
 	if ($suffix eq 'zip') {
 		$filename .= "-$hash.$suffix";
diff --git a/grep.c b/grep.c
index fcc6762302..f67d6716ea 100644
--- a/grep.c
+++ b/grep.c
@@ -1,5 +1,6 @@
 #include "cache.h"
 #include "grep.h"
+#include "xdiff-interface.h"
 
 void append_grep_pattern(struct grep_opt *opt, const char *pat,
 			 const char *origin, int no, enum grep_pat_token t)
@@ -232,17 +233,6 @@ static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
 	printf("%.*s\n", (int)(eol-bol), bol);
 }
 
-/*
- * NEEDSWORK: share code with diff.c
- */
-#define FIRST_FEW_BYTES 8000
-static int buffer_is_binary(const char *ptr, unsigned long size)
-{
-	if (FIRST_FEW_BYTES < size)
-		size = FIRST_FEW_BYTES;
-	return !!memchr(ptr, 0, size);
-}
-
 static int fixmatch(const char *pattern, char *line, regmatch_t *match)
 {
 	char *hit = strstr(line, pattern);
diff --git a/ident.c b/ident.c
index 69a04b827d..3d49608e6f 100644
--- a/ident.c
+++ b/ident.c
@@ -195,10 +195,10 @@ const char *fmt_ident(const char *name, const char *email,
 	setup_ident();
 	if (!name)
 		name = git_default_name;
-	if (!email)
-		email = getenv("EMAIL");
 	if (!email)
 		email = git_default_email;
+	if (!email)
+		email = getenv("EMAIL");
 
 	if (!*name) {
 		struct passwd *pw;
diff --git a/index-pack.c b/index-pack.c
index 58c4a9c41d..82c8da3683 100644
--- a/index-pack.c
+++ b/index-pack.c
@@ -13,13 +13,11 @@ static const char index_pack_usage[] =
 
 struct object_entry
 {
-	off_t offset;
+	struct pack_idx_entry idx;
 	unsigned long size;
 	unsigned int hdr_size;
-	uint32_t crc32;
 	enum object_type type;
 	enum object_type real_type;
-	unsigned char sha1[20];
 };
 
 union delta_base {
@@ -197,7 +195,7 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
 	unsigned shift;
 	void *data;
 
-	obj->offset = consumed_bytes;
+	obj->idx.offset = consumed_bytes;
 	input_crc32 = crc32(0, Z_NULL, 0);
 
 	p = fill(1);
@@ -229,15 +227,15 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
 		while (c & 128) {
 			base_offset += 1;
 			if (!base_offset || MSB(base_offset, 7))
-				bad_object(obj->offset, "offset value overflow for delta base object");
+				bad_object(obj->idx.offset, "offset value overflow for delta base object");
 			p = fill(1);
 			c = *p;
 			use(1);
 			base_offset = (base_offset << 7) + (c & 127);
 		}
-		delta_base->offset = obj->offset - base_offset;
-		if (delta_base->offset >= obj->offset)
-			bad_object(obj->offset, "delta base offset is out of bound");
+		delta_base->offset = obj->idx.offset - base_offset;
+		if (delta_base->offset >= obj->idx.offset)
+			bad_object(obj->idx.offset, "delta base offset is out of bound");
 		break;
 	case OBJ_COMMIT:
 	case OBJ_TREE:
@@ -245,19 +243,19 @@ static void *unpack_raw_entry(struct object_entry *obj, union delta_base *delta_
 	case OBJ_TAG:
 		break;
 	default:
-		bad_object(obj->offset, "unknown object type %d", obj->type);
+		bad_object(obj->idx.offset, "unknown object type %d", obj->type);
 	}
-	obj->hdr_size = consumed_bytes - obj->offset;
+	obj->hdr_size = consumed_bytes - obj->idx.offset;
 
-	data = unpack_entry_data(obj->offset, obj->size);
-	obj->crc32 = input_crc32;
+	data = unpack_entry_data(obj->idx.offset, obj->size);
+	obj->idx.crc32 = input_crc32;
 	return data;
 }
 
 static void *get_data_from_pack(struct object_entry *obj)
 {
-	unsigned long from = obj[0].offset + obj[0].hdr_size;
-	unsigned long len = obj[1].offset - from;
+	unsigned long from = obj[0].idx.offset + obj[0].hdr_size;
+	unsigned long len = obj[1].idx.offset - from;
 	unsigned long rdy = 0;
 	unsigned char *src, *data;
 	z_stream stream;
@@ -360,11 +358,11 @@ static void resolve_delta(struct object_entry *delta_obj, void *base_data,
 			     &result_size);
 	free(delta_data);
 	if (!result)
-		bad_object(delta_obj->offset, "failed to apply delta");
-	sha1_object(result, result_size, type, delta_obj->sha1);
+		bad_object(delta_obj->idx.offset, "failed to apply delta");
+	sha1_object(result, result_size, type, delta_obj->idx.sha1);
 	nr_resolved_deltas++;
 
-	hashcpy(delta_base.sha1, delta_obj->sha1);
+	hashcpy(delta_base.sha1, delta_obj->idx.sha1);
 	if (!find_delta_children(&delta_base, &first, &last)) {
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
@@ -374,7 +372,7 @@ static void resolve_delta(struct object_entry *delta_obj, void *base_data,
 	}
 
 	memset(&delta_base, 0, sizeof(delta_base));
-	delta_base.offset = delta_obj->offset;
+	delta_base.offset = delta_obj->idx.offset;
 	if (!find_delta_children(&delta_base, &first, &last)) {
 		for (j = first; j <= last; j++) {
 			struct object_entry *child = objects + deltas[j].obj_no;
@@ -418,12 +416,12 @@ static void parse_pack_objects(unsigned char *sha1)
 			delta->obj_no = i;
 			delta++;
 		} else
-			sha1_object(data, obj->size, obj->type, obj->sha1);
+			sha1_object(data, obj->size, obj->type, obj->idx.sha1);
 		free(data);
 		if (verbose)
 			display_progress(&progress, i+1);
 	}
-	objects[i].offset = consumed_bytes;
+	objects[i].idx.offset = consumed_bytes;
 	if (verbose)
 		stop_progress(&progress);
 
@@ -465,10 +463,10 @@ static void parse_pack_objects(unsigned char *sha1)
 
 		if (obj->type == OBJ_REF_DELTA || obj->type == OBJ_OFS_DELTA)
 			continue;
-		hashcpy(base.sha1, obj->sha1);
+		hashcpy(base.sha1, obj->idx.sha1);
 		ref = !find_delta_children(&base, &ref_first, &ref_last);
 		memset(&base, 0, sizeof(base));
-		base.offset = obj->offset;
+		base.offset = obj->idx.offset;
 		ofs = !find_delta_children(&base, &ofs_first, &ofs_last);
 		if (!ref && !ofs)
 			continue;
@@ -535,11 +533,11 @@ static void append_obj_to_pack(const unsigned char *sha1, void *buf,
 	}
 	header[n++] = c;
 	write_or_die(output_fd, header, n);
-	obj[0].crc32 = crc32(0, Z_NULL, 0);
-	obj[0].crc32 = crc32(obj[0].crc32, header, n);
-	obj[1].offset = obj[0].offset + n;
-	obj[1].offset += write_compressed(output_fd, buf, size, &obj[0].crc32);
-	hashcpy(obj->sha1, sha1);
+	obj[0].idx.crc32 = crc32(0, Z_NULL, 0);
+	obj[0].idx.crc32 = crc32(obj[0].idx.crc32, header, n);
+	obj[1].idx.offset = obj[0].idx.offset + n;
+	obj[1].idx.offset += write_compressed(output_fd, buf, size, &obj[0].idx.crc32);
+	hashcpy(obj->idx.sha1, sha1);
 }
 
 static int delta_pos_compare(const void *_a, const void *_b)
@@ -602,145 +600,6 @@ static void fix_unresolved_deltas(int nr_unresolved)
 	free(sorted_by_pos);
 }
 
-static uint32_t index_default_version = 1;
-static uint32_t index_off32_limit = 0x7fffffff;
-
-static int sha1_compare(const void *_a, const void *_b)
-{
-	struct object_entry *a = *(struct object_entry **)_a;
-	struct object_entry *b = *(struct object_entry **)_b;
-	return hashcmp(a->sha1, b->sha1);
-}
-
-/*
- * On entry *sha1 contains the pack content SHA1 hash, on exit it is
- * the SHA1 hash of sorted object names.
- */
-static const char *write_index_file(const char *index_name, unsigned char *sha1)
-{
-	struct sha1file *f;
-	struct object_entry **sorted_by_sha, **list, **last;
-	uint32_t array[256];
-	int i, fd;
-	SHA_CTX ctx;
-	uint32_t index_version;
-
-	if (nr_objects) {
-		sorted_by_sha =
-			xcalloc(nr_objects, sizeof(struct object_entry *));
-		list = sorted_by_sha;
-		last = sorted_by_sha + nr_objects;
-		for (i = 0; i < nr_objects; ++i)
-			sorted_by_sha[i] = &objects[i];
-		qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
-		      sha1_compare);
-	}
-	else
-		sorted_by_sha = list = last = NULL;
-
-	if (!index_name) {
-		static char tmpfile[PATH_MAX];
-		snprintf(tmpfile, sizeof(tmpfile),
-			 "%s/tmp_idx_XXXXXX", get_object_directory());
-		fd = mkstemp(tmpfile);
-		index_name = xstrdup(tmpfile);
-	} else {
-		unlink(index_name);
-		fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
-	}
-	if (fd < 0)
-		die("unable to create %s: %s", index_name, strerror(errno));
-	f = sha1fd(fd, index_name);
-
-	/* if last object's offset is >= 2^31 we should use index V2 */
-	index_version = (objects[nr_objects-1].offset >> 31) ? 2 : index_default_version;
-
-	/* index versions 2 and above need a header */
-	if (index_version >= 2) {
-		struct pack_idx_header hdr;
-		hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
-		hdr.idx_version = htonl(index_version);
-		sha1write(f, &hdr, sizeof(hdr));
-	}
-
-	/*
-	 * Write the first-level table (the list is sorted,
-	 * but we use a 256-entry lookup to be able to avoid
-	 * having to do eight extra binary search iterations).
-	 */
-	for (i = 0; i < 256; i++) {
-		struct object_entry **next = list;
-		while (next < last) {
-			struct object_entry *obj = *next;
-			if (obj->sha1[0] != i)
-				break;
-			next++;
-		}
-		array[i] = htonl(next - sorted_by_sha);
-		list = next;
-	}
-	sha1write(f, array, 256 * 4);
-
-	/* compute the SHA1 hash of sorted object names. */
-	SHA1_Init(&ctx);
-
-	/*
-	 * Write the actual SHA1 entries..
-	 */
-	list = sorted_by_sha;
-	for (i = 0; i < nr_objects; i++) {
-		struct object_entry *obj = *list++;
-		if (index_version < 2) {
-			uint32_t offset = htonl(obj->offset);
-			sha1write(f, &offset, 4);
-		}
-		sha1write(f, obj->sha1, 20);
-		SHA1_Update(&ctx, obj->sha1, 20);
-	}
-
-	if (index_version >= 2) {
-		unsigned int nr_large_offset = 0;
-
-		/* write the crc32 table */
-		list = sorted_by_sha;
-		for (i = 0; i < nr_objects; i++) {
-			struct object_entry *obj = *list++;
-			uint32_t crc32_val = htonl(obj->crc32);
-			sha1write(f, &crc32_val, 4);
-		}
-
-		/* write the 32-bit offset table */
-		list = sorted_by_sha;
-		for (i = 0; i < nr_objects; i++) {
-			struct object_entry *obj = *list++;
-			uint32_t offset = (obj->offset <= index_off32_limit) ?
-				obj->offset : (0x80000000 | nr_large_offset++);
-			offset = htonl(offset);
-			sha1write(f, &offset, 4);
-		}
-
-		/* write the large offset table */
-		list = sorted_by_sha;
-		while (nr_large_offset) {
-			struct object_entry *obj = *list++;
-			uint64_t offset = obj->offset;
-			if (offset > index_off32_limit) {
-				uint32_t split[2];
-				split[0]	= htonl(offset >> 32);
-				split[1] = htonl(offset & 0xffffffff);
-				sha1write(f, split, 8);
-				nr_large_offset--;
-			}
-		}
-	}
-
-	sha1write(f, sha1, 20);
-	sha1close(f, NULL, 1);
-	free(sorted_by_sha);
-	SHA1_Final(sha1, &ctx);
-	return index_name;
-}
-
 static void final(const char *final_pack_name, const char *curr_pack_name,
 		  const char *final_index_name, const char *curr_index_name,
 		  const char *keep_name, const char *keep_msg,
@@ -830,6 +689,7 @@ int main(int argc, char **argv)
 	const char *curr_index, *index_name = NULL;
 	const char *keep_name = NULL, *keep_msg = NULL;
 	char *index_name_buf = NULL, *keep_name_buf = NULL;
+	struct pack_idx_entry **idx_objects;
 	unsigned char sha1[20];
 
 	for (i = 1; i < argc; i++) {
@@ -865,12 +725,12 @@ int main(int argc, char **argv)
 				index_name = argv[++i];
 			} else if (!prefixcmp(arg, "--index-version=")) {
 				char *c;
-				index_default_version = strtoul(arg + 16, &c, 10);
-				if (index_default_version > 2)
+				pack_idx_default_version = strtoul(arg + 16, &c, 10);
+				if (pack_idx_default_version > 2)
 					die("bad %s", arg);
 				if (*c == ',')
-					index_off32_limit = strtoul(c+1, &c, 0);
-				if (*c || index_off32_limit & 0x80000000)
+					pack_idx_off32_limit = strtoul(c+1, &c, 0);
+				if (*c || pack_idx_off32_limit & 0x80000000)
 					die("bad %s", arg);
 			} else
 				usage(index_pack_usage);
@@ -940,7 +800,13 @@ int main(int argc, char **argv)
 			    nr_deltas - nr_resolved_deltas);
 	}
 	free(deltas);
-	curr_index = write_index_file(index_name, sha1);
+
+	idx_objects = xmalloc((nr_objects) * sizeof(struct pack_idx_entry *));
+	for (i = 0; i < nr_objects; i++)
+		idx_objects[i] = &objects[i].idx;
+	curr_index = write_idx_file(index_name, idx_objects, nr_objects, sha1);
+	free(idx_objects);
+
 	final(pack_name, curr_pack,
 		index_name, curr_index,
 		keep_name, keep_msg,
diff --git a/merge-recursive.c b/merge-recursive.c
index 8f72b2c079..4a82b741ae 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -680,6 +680,12 @@ static int ll_xdl_merge(const struct ll_merge_driver *drv_unused,
 {
 	xpparam_t xpp;
 
+	if (buffer_is_binary(orig->ptr, orig->size) ||
+			buffer_is_binary(src1->ptr, src1->size) ||
+			buffer_is_binary(src2->ptr, src2->size))
+		return error("Cannot merge binary files: %s vs. %s\n",
+			name1, name2);
+
 	memset(&xpp, 0, sizeof(xpp));
 	return xdl_merge(orig,
 			 src1, name1,
diff --git a/pack-write.c b/pack-write.c
index ae2e481e55..1cf5f7c9f0 100644
--- a/pack-write.c
+++ b/pack-write.c
@@ -1,5 +1,147 @@
 #include "cache.h"
 #include "pack.h"
+#include "csum-file.h"
+
+uint32_t pack_idx_default_version = 1;
+uint32_t pack_idx_off32_limit = 0x7fffffff;
+
+static int sha1_compare(const void *_a, const void *_b)
+{
+	struct pack_idx_entry *a = *(struct pack_idx_entry **)_a;
+	struct pack_idx_entry *b = *(struct pack_idx_entry **)_b;
+	return hashcmp(a->sha1, b->sha1);
+}
+
+/*
+ * On entry *sha1 contains the pack content SHA1 hash, on exit it is
+ * the SHA1 hash of sorted object names. The objects array passed in
+ * will be sorted by SHA1 on exit.
+ */
+const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1)
+{
+	struct sha1file *f;
+	struct pack_idx_entry **sorted_by_sha, **list, **last;
+	off_t last_obj_offset = 0;
+	uint32_t array[256];
+	int i, fd;
+	SHA_CTX ctx;
+	uint32_t index_version;
+
+	if (nr_objects) {
+		sorted_by_sha = objects;
+		list = sorted_by_sha;
+		last = sorted_by_sha + nr_objects;
+		for (i = 0; i < nr_objects; ++i) {
+			if (objects[i]->offset > last_obj_offset)
+				last_obj_offset = objects[i]->offset;
+		}
+		qsort(sorted_by_sha, nr_objects, sizeof(sorted_by_sha[0]),
+		      sha1_compare);
+	}
+	else
+		sorted_by_sha = list = last = NULL;
+
+	if (!index_name) {
+		static char tmpfile[PATH_MAX];
+		snprintf(tmpfile, sizeof(tmpfile),
+			 "%s/tmp_idx_XXXXXX", get_object_directory());
+		fd = mkstemp(tmpfile);
+		index_name = xstrdup(tmpfile);
+	} else {
+		unlink(index_name);
+		fd = open(index_name, O_CREAT|O_EXCL|O_WRONLY, 0600);
+	}
+	if (fd < 0)
+		die("unable to create %s: %s", index_name, strerror(errno));
+	f = sha1fd(fd, index_name);
+
+	/* if last object's offset is >= 2^31 we should use index V2 */
+	index_version = (last_obj_offset >> 31) ? 2 : pack_idx_default_version;
+
+	/* index versions 2 and above need a header */
+	if (index_version >= 2) {
+		struct pack_idx_header hdr;
+		hdr.idx_signature = htonl(PACK_IDX_SIGNATURE);
+		hdr.idx_version = htonl(index_version);
+		sha1write(f, &hdr, sizeof(hdr));
+	}
+
+	/*
+	 * Write the first-level table (the list is sorted,
+	 * but we use a 256-entry lookup to be able to avoid
+	 * having to do eight extra binary search iterations).
+	 */
+	for (i = 0; i < 256; i++) {
+		struct pack_idx_entry **next = list;
+		while (next < last) {
+			struct pack_idx_entry *obj = *next;
+			if (obj->sha1[0] != i)
+				break;
+			next++;
+		}
+		array[i] = htonl(next - sorted_by_sha);
+		list = next;
+	}
+	sha1write(f, array, 256 * 4);
+
+	/* compute the SHA1 hash of sorted object names. */
+	SHA1_Init(&ctx);
+
+	/*
+	 * Write the actual SHA1 entries..
+	 */
+	list = sorted_by_sha;
+	for (i = 0; i < nr_objects; i++) {
+		struct pack_idx_entry *obj = *list++;
+		if (index_version < 2) {
+			uint32_t offset = htonl(obj->offset);
+			sha1write(f, &offset, 4);
+		}
+		sha1write(f, obj->sha1, 20);
+		SHA1_Update(&ctx, obj->sha1, 20);
+	}
+
+	if (index_version >= 2) {
+		unsigned int nr_large_offset = 0;
+
+		/* write the crc32 table */
+		list = sorted_by_sha;
+		for (i = 0; i < nr_objects; i++) {
+			struct pack_idx_entry *obj = *list++;
+			uint32_t crc32_val = htonl(obj->crc32);
+			sha1write(f, &crc32_val, 4);
+		}
+
+		/* write the 32-bit offset table */
+		list = sorted_by_sha;
+		for (i = 0; i < nr_objects; i++) {
+			struct pack_idx_entry *obj = *list++;
+			uint32_t offset = (obj->offset <= pack_idx_off32_limit) ?
+				obj->offset : (0x80000000 | nr_large_offset++);
+			offset = htonl(offset);
+			sha1write(f, &offset, 4);
+		}
+
+		/* write the large offset table */
+		list = sorted_by_sha;
+		while (nr_large_offset) {
+			struct pack_idx_entry *obj = *list++;
+			uint64_t offset = obj->offset;
+			if (offset > pack_idx_off32_limit) {
+				uint32_t split[2];
+				split[0] = htonl(offset >> 32);
+				split[1] = htonl(offset & 0xffffffff);
+				sha1write(f, split, 8);
+				nr_large_offset--;
+			}
+		}
+	}
+
+	sha1write(f, sha1, 20);
+	sha1close(f, NULL, 1);
+	SHA1_Final(sha1, &ctx);
+	return index_name;
+}
 
 void fixup_pack_header_footer(int pack_fd,
 			 unsigned char *pack_file_sha1,
diff --git a/pack.h b/pack.h
index d667fb8d5a..f357c9f428 100644
--- a/pack.h
+++ b/pack.h
@@ -34,6 +34,10 @@ struct pack_header {
  */
 #define PACK_IDX_SIGNATURE 0xff744f63	/* "\377tOc" */
 
+/* These may be overridden by command-line parameters */
+extern uint32_t pack_idx_default_version;
+extern uint32_t pack_idx_off32_limit;
+
 /*
  * Packed object index header
  */
@@ -42,6 +46,16 @@ struct pack_idx_header {
 	uint32_t idx_version;
 };
 
+/*
+ * Common part of object structure used for write_idx_file
+ */
+struct pack_idx_entry {
+	unsigned char sha1[20];
+	uint32_t crc32;
+	off_t offset;
+};
+
+extern const char *write_idx_file(const char *index_name, struct pack_idx_entry **objects, int nr_objects, unsigned char *sha1);
 
 extern int verify_pack(struct packed_git *, int);
 extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t);
diff --git a/t/t3200-branch.sh b/t/t3200-branch.sh
index 828d553a4b..6f6d8844e8 100755
--- a/t/t3200-branch.sh
+++ b/t/t3200-branch.sh
@@ -136,8 +136,8 @@ test_expect_success 'test tracking setup (non-wildcard, not matching)' \
      git-config remote.local.fetch refs/heads/s:refs/remotes/local/s &&
      (git-show-ref -q refs/remotes/local/master || git-fetch local) &&
      git-branch --track my5 local/master &&
-     ! test $(git-config branch.my5.remote) = local &&
-     ! test $(git-config branch.my5.merge) = refs/heads/master'
+     ! test "$(git-config branch.my5.remote)" = local &&
+     ! test "$(git-config branch.my5.merge)" = refs/heads/master'
 
 test_expect_success 'test tracking setup via config' \
     'git-config branch.autosetupmerge true &&
@@ -155,14 +155,22 @@ test_expect_success 'test overriding tracking setup via --no-track' \
      (git-show-ref -q refs/remotes/local/master || git-fetch local) &&
      git-branch --no-track my2 local/master &&
      git-config branch.autosetupmerge false &&
-     ! test $(git-config branch.my2.remote) = local &&
-     ! test $(git-config branch.my2.merge) = refs/heads/master'
+     ! test "$(git-config branch.my2.remote)" = local &&
+     ! test "$(git-config branch.my2.merge)" = refs/heads/master'
 
 test_expect_success 'test local tracking setup' \
     'git branch --track my6 s &&
      test $(git-config branch.my6.remote) = . &&
      test $(git-config branch.my6.merge) = refs/heads/s'
 
+test_expect_success 'test tracking setup via --track but deeper' \
+    'git-config remote.local.url . &&
+     git-config remote.local.fetch refs/heads/*:refs/remotes/local/* &&
+     (git-show-ref -q refs/remotes/local/o/o || git-fetch local) &&
+     git-branch --track my7 local/o/o &&
+     test "$(git-config branch.my7.remote)" = local &&
+     test "$(git-config branch.my7.merge)" = refs/heads/o/o'
+
 # Keep this test last, as it changes the current branch
 cat >expect <<EOF
 0000000000000000000000000000000000000000 $HEAD $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> 1117150200 +0000	branch: Created from master
diff --git a/t/t6024-recursive-merge.sh b/t/t6024-recursive-merge.sh
index a398556137..058db9cc52 100755
--- a/t/t6024-recursive-merge.sh
+++ b/t/t6024-recursive-merge.sh
@@ -81,4 +81,18 @@ EOF
 
 test_expect_success "virtual trees were processed" "git diff expect out"
 
+git reset --hard
+test_expect_success 'refuse to merge binary files' '
+	printf "\0" > binary-file &&
+	git add binary-file &&
+	git commit -m binary &&
+	git checkout G &&
+	printf "\0\0" > binary-file &&
+	git add binary-file &&
+	git commit -m binary2 &&
+	! git merge F > merge.out 2> merge.err &&
+	grep "Cannot merge binary files: HEAD:binary-file vs. F:binary-file" \
+		merge.err
+'
+
 test_done
diff --git a/t/t9500-gitweb-standalone-no-errors.sh b/t/t9500-gitweb-standalone-no-errors.sh
index b92ab63312..44ae503b99 100755
--- a/t/t9500-gitweb-standalone-no-errors.sh
+++ b/t/t9500-gitweb-standalone-no-errors.sh
@@ -487,4 +487,32 @@ test_expect_success \
 	'gitweb_run "p=.git;a=atom"'
 test_debug 'cat gitweb.log'
 
+# ----------------------------------------------------------------------
+# encoding/decoding
+
+test_expect_success \
+	'encode(commit): utf8' \
+	'. ../t3901-utf8.txt &&
+	 echo "UTF-8" >> file &&
+	 git add file &&
+	 git commit -F ../t3900/1-UTF-8.txt &&
+	 gitweb_run "p=.git;a=commit"'
+test_debug 'cat gitweb.log'
+
+test_expect_success \
+	'encode(commit): iso-8859-1' \
+	'. ../t3901-8859-1.txt &&
+	 echo "ISO-8859-1" >> file &&
+	 git add file &&
+	 git config i18n.commitencoding ISO-8859-1 &&
+	 git commit -F ../t3900/ISO-8859-1.txt &&
+	 git config --unset i18n.commitencoding &&
+	 gitweb_run "p=.git;a=commit"'
+test_debug 'cat gitweb.log'
+
+test_expect_success \
+	'encode(log): utf-8 and iso-8859-1' \
+	'gitweb_run "p=.git;a=log"'
+test_debug 'cat gitweb.log'
+
 test_done
diff --git a/xdiff-interface.c b/xdiff-interface.c
index 10816e95a0..963bb89b08 100644
--- a/xdiff-interface.c
+++ b/xdiff-interface.c
@@ -122,4 +122,12 @@ int read_mmfile(mmfile_t *ptr, const char *filename)
 	return 0;
 }
 
+#define FIRST_FEW_BYTES 8000
+int buffer_is_binary(const char *ptr, unsigned long size)
+{
+	if (FIRST_FEW_BYTES < size)
+		size = FIRST_FEW_BYTES;
+	return !!memchr(ptr, 0, size);
+}
+
 
diff --git a/xdiff-interface.h b/xdiff-interface.h
index 1918808081..536f4e4d97 100644
--- a/xdiff-interface.h
+++ b/xdiff-interface.h
@@ -18,5 +18,6 @@ int parse_hunk_header(char *line, int len,
 		      int *ob, int *on,
 		      int *nb, int *nn);
 int read_mmfile(mmfile_t *ptr, const char *filename);
+int buffer_is_binary(const char *ptr, unsigned long size);
 
 #endif