git-fetch: follow tag only when tracking remote branch.

Unless --no-tags flag was given, git-fetch tried to always
follow remote tags that point at the commits we picked up.

It is not very useful to pick up tags from remote unless storing
the fetched branch head in a local tracking branch.  This is
especially true if the fetch is done to merge the remote branch
into our current branch as one-shot basis (i.e. "please pull"),
and is even harmful if the remote repository has many irrelevant
tags.

This proposed update disables the automated tag following unless
we are storing the a fetched branch head in a local tracking
branch.

Signed-off-by: Junio C Hamano <junkio@cox.net>

Documentation/git-add.txt

@@ -7,7 +7,7 @@ git-add - Add files to the index file.
 
 SYNOPSIS
 --------
-'git-add' [-n] [-v] <file>...
+'git-add' [-n] [-v] [--] <file>...
 
 DESCRIPTION
 -----------
@@ -26,6 +26,11 @@ OPTIONS
 -v::
         Be verbose.
 
+--::
+	This option can be used to separate command-line options from
+	the list of files, (useful when filenames might be mistaken
+	for command-line options).
+
 
 DISCUSSION
 ----------

Documentation/git-pack-objects.txt

@@ -8,7 +8,10 @@ git-pack-objects - Create a packed archive of objects.
 
 SYNOPSIS
 --------
-'git-pack-objects' [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list
+[verse]
+'git-pack-objects' [-q] [--no-reuse-delta] [--non-empty]
+	[--local] [--incremental] [--window=N] [--depth=N]
+	{--stdout | base-name} < object-list
 
 
 DESCRIPTION
@@ -32,6 +35,10 @@ Placing both in the pack/ subdirectory of $GIT_OBJECT_DIRECTORY (or
 any of the directories on $GIT_ALTERNATE_OBJECT_DIRECTORIES)
 enables git to read from such an archive.
 
+In a packed archive, an object is either stored as a compressed
+whole, or as a difference from some other object.  The latter is
+often called a delta.
+
 
 OPTIONS
 -------
@@ -74,6 +81,18 @@ base-name::
         Only create a packed archive if it would contain at
         least one object.
 
+-q::
+	This flag makes the command not to report its progress
+	on the standard error stream.
+
+--no-reuse-delta::
+	When creating a packed archive in a repository that
+	has existing packs, the command reuses existing deltas.
+	This sometimes results in a slightly suboptimal pack.
+	This flag tells the command not to reuse existing deltas
+	but compute them from scratch.
+
+
 Author
 ------
 Written by Linus Torvalds <torvalds@osdl.org>

Documentation/git-push.txt

@@ -43,6 +43,12 @@ to fast forward the remote ref that matches <dst>.  If
 the optional plus `+` is used, the remote ref is updated
 even if it does not result in a fast forward update.
 +
+Note: If no explicit refspec is found, (that is neither
+on the command line nor in any Push line of the
+corresponding remotes file---see below), then all the
+refs that exist both on the local side and on the remote
+side are updated.
++
 Some short-cut notations are also supported.
 +
 * `tag <tag>` means the same as `refs/tags/<tag>:refs/tags/<tag>`.

Documentation/git-repack.txt

@@ -9,7 +9,7 @@ objects into pack files.
 
 SYNOPSIS
 --------
-'git-repack' [-a] [-d] [-l] [-n]
+'git-repack' [-a] [-d] [-f] [-l] [-n] [-q]
 
 DESCRIPTION
 -----------
@@ -43,6 +43,14 @@ OPTIONS
         Pass the `--local` option to `git pack-objects`, see
         gitlink:git-pack-objects[1].
 
+-f::
+        Pass the `--no-reuse-delta` option to `git pack-objects`, see
+        gitlink:git-pack-objects[1].
+
+-q::
+        Pass the `-q` option to `git pack-objects`, see
+        gitlink:git-pack-objects[1].
+
 -n::
         Do not update the server information with
         `git update-server-info`.

cache.h

@@ -246,8 +246,8 @@ void datestamp(char *buf, int bufsize);
 unsigned long approxidate(const char *);
 
 extern int setup_ident(void);
-extern const char *git_author_info(void);
-extern const char *git_committer_info(void);
+extern const char *git_author_info(int);
+extern const char *git_committer_info(int);
 
 struct checkout {
 	const char *base_dir;

commit-tree.c

@@ -118,8 +118,8 @@ int main(int argc, char **argv)
 		add_buffer(&buffer, &size, "parent %s\n", sha1_to_hex(parent_sha1[i]));
 
 	/* Person/date information */
-	add_buffer(&buffer, &size, "author %s\n", git_author_info());
-	add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info());
+	add_buffer(&buffer, &size, "author %s\n", git_author_info(1));
+	add_buffer(&buffer, &size, "committer %s\n\n", git_committer_info(1));
 
 	/* And add the comment */
 	while (fgets(comment, sizeof(comment), stdin) != NULL)

git-add.sh

@@ -14,6 +14,10 @@ while : ; do
     -v)
 	verbose=--verbose
 	;;
+    --)
+	shift
+	break
+	;;
     -*)
 	usage
 	;;

git-am.sh

@@ -1,11 +1,13 @@
 #!/bin/sh
 #
-#
+# Copyright (c) 2005, 2006 Junio C Hamano
 
 USAGE='[--signoff] [--dotest=<dir>] [--utf8] [--binary] [--3way] <mbox>
   or, when resuming [--skip | --resolved]'
 . git-sh-setup
 
+git var GIT_COMMITTER_IDENT >/dev/null || exit
+
 stop_here () {
     echo "$1" >"$dotest/next"
     exit 1

git-applymbox.sh

@@ -21,6 +21,8 @@
 USAGE='[-u] [-k] [-q] [-m] (-c .dotest/<num> | mbox) [signoff]'
 . git-sh-setup
 
+git var GIT_COMMITTER_IDENT >/dev/null || exit
+
 keep_subject= query_apply= continue= utf8= resume=t
 while case "$#" in 0) break ;; esac
 do

git-fetch.sh

@@ -368,20 +368,25 @@ fetch_main "$reflist"
 # automated tag following
 case "$no_tags$tags" in
 '')
-	taglist=$(IFS=" " &&
-	git-ls-remote $upload_pack --tags "$remote" |
-	sed -ne 's|^\([0-9a-f]*\)[ 	]\(refs/tags/.*\)^{}$|\1 \2|p' |
-	while read sha1 name
-	do
-		test -f "$GIT_DIR/$name" && continue
-	  	git-check-ref-format "$name" || {
-			echo >&2 "warning: tag ${name} ignored"
-			continue
-		}
-		git-cat-file -t "$sha1" >/dev/null 2>&1 || continue
-		echo >&2 "Auto-following $name"
-		echo ".${name}:${name}"
-	done)
+	case "$reflist" in
+	*:refs/*)
+		# effective only when we are following remote branch
+		# using local tracking branch.
+		taglist=$(IFS=" " &&
+		git-ls-remote $upload_pack --tags "$remote" |
+		sed -ne 's|^\([0-9a-f]*\)[ 	]\(refs/tags/.*\)^{}$|\1 \2|p' |
+		while read sha1 name
+		do
+			test -f "$GIT_DIR/$name" && continue
+			git-check-ref-format "$name" || {
+				echo >&2 "warning: tag ${name} ignored"
+				continue
+			}
+			git-cat-file -t "$sha1" >/dev/null 2>&1 || continue
+			echo >&2 "Auto-following $name"
+			echo ".${name}:${name}"
+		done)
+	esac
 	case "$taglist" in
 	'') ;;
 	?*)

git-format-patch.sh

@@ -189,7 +189,7 @@ my @month_names = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
 sub show_date {
     my ($time, $tz) = @_;
     my $minutes = abs($tz);
-    $minutes = ($minutes / 100) * 60 + ($minutes % 100);
+    $minutes = int($minutes / 100) * 60 + ($minutes % 100);
     if ($tz < 0) {
         $minutes = -$minutes;
     }

git-merge.sh

@@ -142,6 +142,8 @@ case "$#,$common,$no_commit" in
 1,*,)
 	# We are not doing octopus, not fast forward, and have only
 	# one common.  See if it is really trivial.
+	git var GIT_COMMITTER_IDENT >/dev/null || exit
+
 	echo "Trying really trivial in-index merge..."
 	git-update-index --refresh 2>/dev/null
 	if git-read-tree --trivial -m -u $common $head "$1" &&
@@ -179,6 +181,9 @@ case "$#,$common,$no_commit" in
 	;;
 esac
 
+# We are going to make a new commit.
+git var GIT_COMMITTER_IDENT >/dev/null || exit
+
 case "$use_strategies" in
 '')
 	case "$#" in

git-repack.sh

@@ -3,17 +3,20 @@
 # Copyright (c) 2005 Linus Torvalds
 #
 
-USAGE='[-a] [-d] [-l] [-n]'
+USAGE='[-a] [-d] [-f] [-l] [-n] [-q]'
 . git-sh-setup
 	
-no_update_info= all_into_one= remove_redundant= local=
+no_update_info= all_into_one= remove_redundant=
+local= quiet= no_reuse_delta=
 while case "$#" in 0) break ;; esac
 do
 	case "$1" in
 	-n)	no_update_info=t ;;
 	-a)	all_into_one=t ;;
 	-d)	remove_redundant=t ;;
-	-l)	local=t ;;
+	-q)	quiet=-q ;;
+	-f)	no_reuse_delta=--no-reuse-delta ;;
+	-l)	local=--local ;;
 	*)	usage ;;
 	esac
 	shift
@@ -39,9 +42,7 @@ case ",$all_into_one," in
 	    find . -type f \( -name '*.pack' -o -name '*.idx' \) -print`
 	;;
 esac
-if [ "$local" ]; then
-	pack_objects="$pack_objects --local"
-fi
+pack_objects="$pack_objects $local $quiet $no_reuse_delta"
 name=$(git-rev-list --objects $rev_list $(git-rev-parse $rev_parse) 2>&1 |
 	git-pack-objects --non-empty $pack_objects .tmp-pack) ||
 	exit 1

git-resolve.sh

@@ -50,6 +50,9 @@ case "$common" in
 	;;
 esac
 
+# We are going to make a new commit.
+git var GIT_COMMITTER_IDENT >/dev/null || exit
+
 # Find an optimum merge base if there are more than one candidates.
 LF='
 '

ident.c

@@ -156,8 +156,18 @@ static int copy(char *buf, int size, int offset, const char *src)
 	return offset;
 }
 
+static const char au_env[] = "GIT_AUTHOR_NAME";
+static const char co_env[] = "GIT_COMMITTER_NAME";
+static const char *env_hint =
+"\n*** Environment problem:\n"
+"*** Your name cannot be determined from your system services (gecos).\n"
+"*** You would need to set %s and %s\n"
+"*** environment variables; otherwise you won't be able to perform\n"
+"*** certain operations because of \"empty ident\" errors.\n"
+"*** Alternatively, you can use user.name configuration variable.\n\n";
+
 static const char *get_ident(const char *name, const char *email,
-			     const char *date_str)
+			     const char *date_str, int error_on_no_name)
 {
 	static char buffer[1000];
 	char date[50];
@@ -168,9 +178,14 @@ static const char *get_ident(const char *name, const char *email,
 	if (!email)
 		email = git_default_email;
 
-	if (!*name || !*email)
-		die("empty ident %s <%s> not allowed",
-		    name, email);
+	if (!*name) {
+		if (name == git_default_name && env_hint) {
+			fprintf(stderr, env_hint, au_env, co_env);
+			env_hint = NULL; /* warn only once, for "git-var -l" */
+		}
+		if (error_on_no_name)
+			die("empty ident %s <%s> not allowed", name, email);
+	}
 
 	strcpy(date, git_default_date);
 	if (date_str)
@@ -187,16 +202,18 @@ static const char *get_ident(const char *name, const char *email,
 	return buffer;
 }
 
-const char *git_author_info(void)
+const char *git_author_info(int error_on_no_name)
 {
 	return get_ident(getenv("GIT_AUTHOR_NAME"),
 			 getenv("GIT_AUTHOR_EMAIL"),
-			 getenv("GIT_AUTHOR_DATE"));
+			 getenv("GIT_AUTHOR_DATE"),
+			 error_on_no_name);
 }
 
-const char *git_committer_info(void)
+const char *git_committer_info(int error_on_no_name)
 {
 	return get_ident(getenv("GIT_COMMITTER_NAME"),
 			 getenv("GIT_COMMITTER_EMAIL"),
-			 getenv("GIT_COMMITTER_DATE"));
+			 getenv("GIT_COMMITTER_DATE"),
+			 error_on_no_name);
 }

pack-objects.c

@@ -4,22 +4,47 @@
 #include "pack.h"
 #include "csum-file.h"
 #include <sys/time.h>
+#include <signal.h>
 
-static const char pack_usage[] = "git-pack-objects [-q] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
+static const char pack_usage[] = "git-pack-objects [-q] [--no-reuse-delta] [--non-empty] [--local] [--incremental] [--window=N] [--depth=N] {--stdout | base-name} < object-list";
 
 struct object_entry {
 	unsigned char sha1[20];
-	unsigned long size;
-	unsigned long offset;
-	unsigned int depth;
-	unsigned int hash;
+	unsigned long size;	/* uncompressed size */
+	unsigned long offset;	/* offset into the final pack file;
+				 * nonzero if already written.
+				 */
+	unsigned int depth;	/* delta depth */
+	unsigned int delta_limit;	/* base adjustment for in-pack delta */
+	unsigned int hash;	/* name hint hash */
 	enum object_type type;
-	unsigned long delta_size;
-	struct object_entry *delta;
+	enum object_type in_pack_type;	/* could be delta */
+	unsigned long delta_size;	/* delta data size (uncompressed) */
+	struct object_entry *delta;	/* delta base object */
+	struct packed_git *in_pack; 	/* already in pack */
+	unsigned int in_pack_offset;
+	struct object_entry *delta_child; /* delitified objects who bases me */
+	struct object_entry *delta_sibling; /* other deltified objects who
+					     * uses the same base as me
+					     */
 };
 
+/*
+ * Objects we are going to pack are colected in objects array (dynamically
+ * expanded).  nr_objects & nr_alloc controls this array.  They are stored
+ * in the order we see -- typically rev-list --objects order that gives us
+ * nice "minimum seek" order.
+ *
+ * sorted-by-sha ans sorted-by-type are arrays of pointers that point at
+ * elements in the objects array.  The former is used to build the pack
+ * index (lists object names in the ascending order to help offset lookup),
+ * and the latter is used to group similar things together by try_delta()
+ * heuristics.
+ */
+
 static unsigned char object_list_sha1[20];
 static int non_empty = 0;
+static int no_reuse_delta = 0;
 static int local = 0;
 static int incremental = 0;
 static struct object_entry **sorted_by_sha, **sorted_by_type;
@@ -28,6 +53,138 @@ static int nr_objects = 0, nr_alloc = 0;
 static const char *base_name;
 static unsigned char pack_file_sha1[20];
 static int progress = 1;
+static volatile int progress_update = 0;
+
+/*
+ * The object names in objects array are hashed with this hashtable,
+ * to help looking up the entry by object name.  Binary search from
+ * sorted_by_sha is also possible but this was easier to code and faster.
+ * This hashtable is built after all the objects are seen.
+ */
+static int *object_ix = NULL;
+static int object_ix_hashsz = 0;
+
+/*
+ * Pack index for existing packs give us easy access to the offsets into
+ * corresponding pack file where each object's data starts, but the entries
+ * do not store the size of the compressed representation (uncompressed
+ * size is easily available by examining the pack entry header).  We build
+ * a hashtable of existing packs (pack_revindex), and keep reverse index
+ * here -- pack index file is sorted by object name mapping to offset; this
+ * pack_revindex[].revindex array is an ordered list of offsets, so if you
+ * know the offset of an object, next offset is where its packed
+ * representation ends.
+ */
+struct pack_revindex {
+	struct packed_git *p;
+	unsigned long *revindex;
+} *pack_revindex = NULL;
+static int pack_revindex_hashsz = 0;
+
+/*
+ * stats
+ */
+static int written = 0;
+static int written_delta = 0;
+static int reused = 0;
+static int reused_delta = 0;
+
+static int pack_revindex_ix(struct packed_git *p)
+{
+	unsigned int ui = (unsigned int) p;
+	int i;
+
+	ui = ui ^ (ui >> 16); /* defeat structure alignment */
+	i = (int)(ui % pack_revindex_hashsz);
+	while (pack_revindex[i].p) {
+		if (pack_revindex[i].p == p)
+			return i;
+		if (++i == pack_revindex_hashsz)
+			i = 0;
+	}
+	return -1 - i;
+}
+
+static void prepare_pack_ix(void)
+{
+	int num;
+	struct packed_git *p;
+	for (num = 0, p = packed_git; p; p = p->next)
+		num++;
+	if (!num)
+		return;
+	pack_revindex_hashsz = num * 11;
+	pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
+	for (p = packed_git; p; p = p->next) {
+		num = pack_revindex_ix(p);
+		num = - 1 - num;
+		pack_revindex[num].p = p;
+	}
+	/* revindex elements are lazily initialized */
+}
+
+static int cmp_offset(const void *a_, const void *b_)
+{
+	unsigned long a = *(unsigned long *) a_;
+	unsigned long b = *(unsigned long *) b_;
+	if (a < b)
+		return -1;
+	else if (a == b)
+		return 0;
+	else
+		return 1;
+}
+
+/*
+ * Ordered list of offsets of objects in the pack.
+ */
+static void prepare_pack_revindex(struct pack_revindex *rix)
+{
+	struct packed_git *p = rix->p;
+	int num_ent = num_packed_objects(p);
+	int i;
+	void *index = p->index_base + 256;
+
+	rix->revindex = xmalloc(sizeof(unsigned long) * (num_ent + 1));
+	for (i = 0; i < num_ent; i++) {
+		long hl = *((long *)(index + 24 * i));
+		rix->revindex[i] = ntohl(hl);
+	}
+	/* This knows the pack format -- the 20-byte trailer
+	 * follows immediately after the last object data.
+	 */
+	rix->revindex[num_ent] = p->pack_size - 20;
+	qsort(rix->revindex, num_ent, sizeof(unsigned long), cmp_offset);
+}
+
+static unsigned long find_packed_object_size(struct packed_git *p,
+					     unsigned long ofs)
+{
+	int num;
+	int lo, hi;
+	struct pack_revindex *rix;
+	unsigned long *revindex;
+	num = pack_revindex_ix(p);
+	if (num < 0)
+		die("internal error: pack revindex uninitialized");
+	rix = &pack_revindex[num];
+	if (!rix->revindex)
+		prepare_pack_revindex(rix);
+	revindex = rix->revindex;
+	lo = 0;
+	hi = num_packed_objects(p) + 1;
+	do {
+		int mi = (lo + hi) / 2;
+		if (revindex[mi] == ofs) {
+			return revindex[mi+1] - ofs;
+		}
+		else if (ofs < revindex[mi])
+			hi = mi;
+		else
+			lo = mi + 1;
+	} while (lo < hi);
+	die("internal error: pack revindex corrupt");
+}
 
 static void *delta_against(void *buf, unsigned long size, struct object_entry *entry)
 {
@@ -78,35 +235,69 @@ static unsigned long write_object(struct sha1file *f, struct object_entry *entry
 {
 	unsigned long size;
 	char type[10];
-	void *buf = read_sha1_file(entry->sha1, type, &size);
+	void *buf;
 	unsigned char header[10];
 	unsigned hdrlen, datalen;
 	enum object_type obj_type;
+	int to_reuse = 0;
 
-	if (!buf)
-		die("unable to read %s", sha1_to_hex(entry->sha1));
-	if (size != entry->size)
-		die("object %s size inconsistency (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
-
-	/*
-	 * The object header is a byte of 'type' followed by zero or
-	 * more bytes of length.  For deltas, the 20 bytes of delta sha1
-	 * follows that.
-	 */
 	obj_type = entry->type;
-	if (entry->delta) {
-		buf = delta_against(buf, size, entry);
-		size = entry->delta_size;
-		obj_type = OBJ_DELTA;
+	if (! entry->in_pack)
+		to_reuse = 0;	/* can't reuse what we don't have */
+	else if (obj_type == OBJ_DELTA)
+		to_reuse = 1;	/* check_object() decided it for us */
+	else if (obj_type != entry->in_pack_type)
+		to_reuse = 0;	/* pack has delta which is unusable */
+	else if (entry->delta)
+		to_reuse = 0;	/* we want to pack afresh */
+	else
+		to_reuse = 1;	/* we have it in-pack undeltified,
+				 * and we do not need to deltify it.
+				 */
+
+	if (! to_reuse) {
+		buf = read_sha1_file(entry->sha1, type, &size);
+		if (!buf)
+			die("unable to read %s", sha1_to_hex(entry->sha1));
+		if (size != entry->size)
+			die("object %s size inconsistency (%lu vs %lu)",
+			    sha1_to_hex(entry->sha1), size, entry->size);
+		if (entry->delta) {
+			buf = delta_against(buf, size, entry);
+			size = entry->delta_size;
+			obj_type = OBJ_DELTA;
+		}
+		/*
+		 * The object header is a byte of 'type' followed by zero or
+		 * more bytes of length.  For deltas, the 20 bytes of delta
+		 * sha1 follows that.
+		 */
+		hdrlen = encode_header(obj_type, size, header);
+		sha1write(f, header, hdrlen);
+
+		if (entry->delta) {
+			sha1write(f, entry->delta, 20);
+			hdrlen += 20;
+		}
+		datalen = sha1write_compressed(f, buf, size);
+		free(buf);
 	}
-	hdrlen = encode_header(obj_type, size, header);
-	sha1write(f, header, hdrlen);
-	if (entry->delta) {
-		sha1write(f, entry->delta, 20);
-		hdrlen += 20;
+	else {
+		struct packed_git *p = entry->in_pack;
+		use_packed_git(p);
+
+		datalen = find_packed_object_size(p, entry->in_pack_offset);
+		buf = p->pack_base + entry->in_pack_offset;
+		sha1write(f, buf, datalen);
+		unuse_packed_git(p);
+		hdrlen = 0; /* not really */
+		if (obj_type == OBJ_DELTA)
+			reused_delta++;
+		reused++;
 	}
-	datalen = sha1write_compressed(f, buf, size);
-	free(buf);
+	if (obj_type == OBJ_DELTA)
+		written_delta++;
+	written++;
 	return hdrlen + datalen;
 }
 
@@ -132,24 +323,41 @@ static void write_pack_file(void)
 	int i;
 	struct sha1file *f;
 	unsigned long offset;
-	unsigned long mb;
 	struct pack_header hdr;
+	unsigned last_percent = 999;
+	int do_progress = 0;
 
 	if (!base_name)
 		f = sha1fd(1, "<stdout>");
-	else
-		f = sha1create("%s-%s.%s", base_name, sha1_to_hex(object_list_sha1), "pack");
+	else {
+		f = sha1create("%s-%s.%s", base_name,
+			       sha1_to_hex(object_list_sha1), "pack");
+		do_progress = progress;
+	}
+	if (do_progress)
+		fprintf(stderr, "Writing %d objects.\n", nr_objects);
+
 	hdr.hdr_signature = htonl(PACK_SIGNATURE);
 	hdr.hdr_version = htonl(PACK_VERSION);
 	hdr.hdr_entries = htonl(nr_objects);
 	sha1write(f, &hdr, sizeof(hdr));
 	offset = sizeof(hdr);
-	for (i = 0; i < nr_objects; i++)
+	for (i = 0; i < nr_objects; i++) {
 		offset = write_one(f, objects + i, offset);
+		if (do_progress) {
+			unsigned percent = written * 100 / nr_objects;
+			if (progress_update || percent != last_percent) {
+				fprintf(stderr, "%4u%% (%u/%u) done\r",
+					percent, written, nr_objects);
+				progress_update = 0;
+				last_percent = percent;
+			}
+		}
+	}
+	if (do_progress)
+		fputc('\n', stderr);
 
 	sha1close(f, pack_file_sha1, 1);
-	mb = offset >> 20;
-	offset &= 0xfffff;
 }
 
 static void write_index_file(void)
@@ -196,18 +404,20 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash)
 {
 	unsigned int idx = nr_objects;
 	struct object_entry *entry;
+	struct packed_git *p;
+	unsigned int found_offset = 0;
+	struct packed_git *found_pack = NULL;
 
-	if (incremental || local) {
-		struct packed_git *p;
-
-		for (p = packed_git; p; p = p->next) {
-			struct pack_entry e;
-
-			if (find_pack_entry_one(sha1, &e, p)) {
-				if (incremental)
-					return 0;
-				if (local && !p->pack_local)
-					return 0;
+	for (p = packed_git; p; p = p->next) {
+		struct pack_entry e;
+		if (find_pack_entry_one(sha1, &e, p)) {
+			if (incremental)
+				return 0;
+			if (local && !p->pack_local)
+				return 0;
+			if (!found_pack) {
+				found_offset = e.offset;
+				found_pack = e.p;
 			}
 		}
 	}
@@ -221,39 +431,143 @@ static int add_object_entry(unsigned char *sha1, unsigned int hash)
 	memset(entry, 0, sizeof(*entry));
 	memcpy(entry->sha1, sha1, 20);
 	entry->hash = hash;
+	if (found_pack) {
+		entry->in_pack = found_pack;
+		entry->in_pack_offset = found_offset;
+	}
 	nr_objects = idx+1;
 	return 1;
 }
 
+static int locate_object_entry_hash(unsigned char *sha1)
+{
+	int i;
+	unsigned int ui;
+	memcpy(&ui, sha1, sizeof(unsigned int));
+	i = ui % object_ix_hashsz;
+	while (0 < object_ix[i]) {
+		if (!memcmp(sha1, objects[object_ix[i]-1].sha1, 20))
+			return i;
+		if (++i == object_ix_hashsz)
+			i = 0;
+	}
+	return -1 - i;
+}
+
+static struct object_entry *locate_object_entry(unsigned char *sha1)
+{
+	int i = locate_object_entry_hash(sha1);
+	if (0 <= i)
+		return &objects[object_ix[i]-1];
+	return NULL;
+}
+
 static void check_object(struct object_entry *entry)
 {
 	char type[20];
 
-	if (!sha1_object_info(entry->sha1, type, &entry->size)) {
-		if (!strcmp(type, "commit")) {
-			entry->type = OBJ_COMMIT;
-		} else if (!strcmp(type, "tree")) {
-			entry->type = OBJ_TREE;
-		} else if (!strcmp(type, "blob")) {
-			entry->type = OBJ_BLOB;
-		} else if (!strcmp(type, "tag")) {
-			entry->type = OBJ_TAG;
-		} else
-			die("unable to pack object %s of type %s",
-			    sha1_to_hex(entry->sha1), type);
+	if (entry->in_pack) {
+		unsigned char base[20];
+		unsigned long size;
+		struct object_entry *base_entry;
+
+		/* We want in_pack_type even if we do not reuse delta.
+		 * There is no point not reusing non-delta representations.
+		 */
+		check_reuse_pack_delta(entry->in_pack,
+				       entry->in_pack_offset,
+				       base, &size,
+				       &entry->in_pack_type);
+
+		/* Check if it is delta, and the base is also an object
+		 * we are going to pack.  If so we will reuse the existing
+		 * delta.
+		 */
+		if (!no_reuse_delta &&
+		    entry->in_pack_type == OBJ_DELTA &&
+		    (base_entry = locate_object_entry(base))) {
+
+			/* Depth value does not matter - find_deltas()
+			 * will never consider reused delta as the
+			 * base object to deltify other objects
+			 * against, in order to avoid circular deltas.
+			 */
+
+			/* uncompressed size of the delta data */
+			entry->size = entry->delta_size = size;
+			entry->delta = base_entry;
+			entry->type = OBJ_DELTA;
+
+			entry->delta_sibling = base_entry->delta_child;
+			base_entry->delta_child = entry;
+
+			return;
+		}
+		/* Otherwise we would do the usual */
 	}
-	else
+
+	if (sha1_object_info(entry->sha1, type, &entry->size))
 		die("unable to get type of object %s",
 		    sha1_to_hex(entry->sha1));
+
+	if (!strcmp(type, "commit")) {
+		entry->type = OBJ_COMMIT;
+	} else if (!strcmp(type, "tree")) {
+		entry->type = OBJ_TREE;
+	} else if (!strcmp(type, "blob")) {
+		entry->type = OBJ_BLOB;
+	} else if (!strcmp(type, "tag")) {
+		entry->type = OBJ_TAG;
+	} else
+		die("unable to pack object %s of type %s",
+		    sha1_to_hex(entry->sha1), type);
+}
+
+static void hash_objects(void)
+{
+	int i;
+	struct object_entry *oe;
+
+	object_ix_hashsz = nr_objects * 2;
+	object_ix = xcalloc(sizeof(int), object_ix_hashsz);
+	for (i = 0, oe = objects; i < nr_objects; i++, oe++) {
+		int ix = locate_object_entry_hash(oe->sha1);
+		if (0 <= ix) {
+			error("the same object '%s' added twice",
+			      sha1_to_hex(oe->sha1));
+			continue;
+		}
+		ix = -1 - ix;
+		object_ix[ix] = i + 1;
+	}
+}
+
+static unsigned int check_delta_limit(struct object_entry *me, unsigned int n)
+{
+	struct object_entry *child = me->delta_child;
+	unsigned int m = n;
+	while (child) {
+		unsigned int c = check_delta_limit(child, n + 1);
+		if (m < c)
+			m = c;
+		child = child->delta_sibling;
+	}
+	return m;
 }
 
 static void get_object_details(void)
 {
 	int i;
-	struct object_entry *entry = objects;
+	struct object_entry *entry;
 
-	for (i = 0; i < nr_objects; i++)
-		check_object(entry++);
+	hash_objects();
+	prepare_pack_ix();
+	for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+		check_object(entry);
+	for (i = 0, entry = objects; i < nr_objects; i++, entry++)
+		if (!entry->delta && entry->delta_child)
+			entry->delta_limit =
+				check_delta_limit(entry, 1);
 }
 
 typedef int (*entry_sort_t)(const struct object_entry *, const struct object_entry *);
@@ -326,6 +640,16 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
 	if (cur_entry->type != old_entry->type)
 		return -1;
 
+	/* If the current object is at edge, take the depth the objects
+	 * that depend on the current object into account -- otherwise
+	 * they would become too deep.
+	 */
+	if (cur_entry->delta_child) {
+		if (max_depth <= cur_entry->delta_limit)
+			return 0;
+		max_depth -= cur_entry->delta_limit;
+	}
+
 	size = cur_entry->size;
 	if (size < 50)
 		return -1;
@@ -359,17 +683,25 @@ static int try_delta(struct unpacked *cur, struct unpacked *old, unsigned max_de
 	return 0;
 }
 
+static void progress_interval(int signum)
+{
+	signal(SIGALRM, progress_interval);
+	progress_update = 1;
+}
+
 static void find_deltas(struct object_entry **list, int window, int depth)
 {
 	int i, idx;
 	unsigned int array_size = window * sizeof(struct unpacked);
 	struct unpacked *array = xmalloc(array_size);
-	int eye_candy;
+	unsigned processed = 0;
+	unsigned last_percent = 999;
 
 	memset(array, 0, array_size);
 	i = nr_objects;
 	idx = 0;
-	eye_candy = i - (nr_objects / 20);
+	if (progress)
+		fprintf(stderr, "Deltifying %d objects.\n", nr_objects);
 
 	while (--i >= 0) {
 		struct object_entry *entry = list[i];
@@ -378,15 +710,29 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 		char type[10];
 		int j;
 
-		if (progress && i <= eye_candy) {
-			eye_candy -= nr_objects / 20;
-			fputc('.', stderr);
+		processed++;
+		if (progress) {
+			unsigned percent = processed * 100 / nr_objects;
+			if (percent != last_percent || progress_update) {
+				fprintf(stderr, "%4u%% (%u/%u) done\r",
+					percent, processed, nr_objects);
+				progress_update = 0;
+				last_percent = percent;
+			}
 		}
+
+		if (entry->delta)
+			/* This happens if we decided to reuse existing
+			 * delta from a pack.  "!no_reuse_delta &&" is implied.
+			 */
+			continue;
+
 		free(n->data);
 		n->entry = entry;
 		n->data = read_sha1_file(entry->sha1, type, &size);
 		if (size != entry->size)
 			die("object %s inconsistent object length (%lu vs %lu)", sha1_to_hex(entry->sha1), size, entry->size);
+
 		j = window;
 		while (--j > 0) {
 			unsigned int other_idx = idx + j;
@@ -404,6 +750,9 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 			idx = 0;
 	}
 
+	if (progress)
+		fputc('\n', stderr);
+
 	for (i = 0; i < window; ++i)
 		free(array[i].data);
 	free(array);
@@ -412,15 +761,9 @@ static void find_deltas(struct object_entry **list, int window, int depth)
 static void prepare_pack(int window, int depth)
 {
 	get_object_details();
-
-	if (progress)
-		fprintf(stderr, "Packing %d objects", nr_objects);
 	sorted_by_type = create_sorted_list(type_size_sort);
 	if (window && depth)
 		find_deltas(sorted_by_type, window+1, depth);
-	if (progress)
-		fputc('\n', stderr);
-	write_pack_file();
 }
 
 static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
@@ -443,8 +786,9 @@ static int reuse_cached_pack(unsigned char *sha1, int pack_to_stdout)
 		}
 	}
 
-	fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
-		sha1_to_hex(sha1));
+	if (progress)
+		fprintf(stderr, "Reusing %d objects pack %s\n", nr_objects,
+			sha1_to_hex(sha1));
 
 	if (pack_to_stdout) {
 		if (copy_fd(ifd, 1))
@@ -483,10 +827,6 @@ int main(int argc, char **argv)
 	int window = 10, depth = 10, pack_to_stdout = 0;
 	struct object_entry **list;
 	int i;
-	struct timeval prev_tv;
-	int eye_candy = 0;
-	int eye_candy_incr = 500;
-
 
 	setup_git_directory();
 
@@ -524,6 +864,10 @@ int main(int argc, char **argv)
 				progress = 0;
 				continue;
 			}
+			if (!strcmp("--no-reuse-delta", arg)) {
+				no_reuse_delta = 1;
+				continue;
+			}
 			if (!strcmp("--stdout", arg)) {
 				pack_to_stdout = 1;
 				continue;
@@ -539,30 +883,25 @@ int main(int argc, char **argv)
 		usage(pack_usage);
 
 	prepare_packed_git();
+
 	if (progress) {
+		struct itimerval v;
+		v.it_interval.tv_sec = 1;
+		v.it_interval.tv_usec = 0;
+		v.it_value = v.it_interval;
+		signal(SIGALRM, progress_interval);
+		setitimer(ITIMER_REAL, &v, NULL);
 		fprintf(stderr, "Generating pack...\n");
-		gettimeofday(&prev_tv, NULL);
 	}
+
 	while (fgets(line, sizeof(line), stdin) != NULL) {
 		unsigned int hash;
 		char *p;
 		unsigned char sha1[20];
 
-		if (progress && (eye_candy <= nr_objects)) {
+		if (progress_update) {
 			fprintf(stderr, "Counting objects...%d\r", nr_objects);
-			if (eye_candy && (50 <= eye_candy_incr)) {
-				struct timeval tv;
-				int time_diff;
-				gettimeofday(&tv, NULL);
-				time_diff = (tv.tv_sec - prev_tv.tv_sec);
-				time_diff <<= 10;
-				time_diff += (tv.tv_usec - prev_tv.tv_usec);
-				if ((1 << 9) < time_diff)
-					eye_candy_incr += 50;
-				else if (50 < eye_candy_incr)
-					eye_candy_incr -= 50;
-			}
-			eye_candy += eye_candy_incr;
+			progress_update = 0;
 		}
 		if (get_sha1_hex(line, sha1))
 			die("expected sha1, got garbage:\n %s", line);
@@ -594,10 +933,21 @@ int main(int argc, char **argv)
 		;
 	else {
 		prepare_pack(window, depth);
+		if (progress && pack_to_stdout) {
+			/* the other end usually displays progress itself */
+			struct itimerval v = {{0,},};
+			setitimer(ITIMER_REAL, &v, NULL);
+			signal(SIGALRM, SIG_IGN );
+			progress_update = 0;
+		}
+		write_pack_file();
 		if (!pack_to_stdout) {
 			write_index_file();
 			puts(sha1_to_hex(object_list_sha1));
 		}
 	}
+	if (progress)
+		fprintf(stderr, "Total %d, written %d (delta %d), reused %d (delta %d)\n",
+			nr_objects, written, written_delta, reused, reused_delta);
 	return 0;
 }

pack.h

@@ -29,5 +29,7 @@ struct pack_header {
 };
 
 extern int verify_pack(struct packed_git *, int);
-
+extern int check_reuse_pack_delta(struct packed_git *, unsigned long,
+				  unsigned char *, unsigned long *,
+				  enum object_type *);
 #endif

sha1_file.c

@@ -247,6 +247,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
 		for ( ; cp < ep && *cp != sep; cp++)
 			;
 		if (last != cp) {
+			struct stat st;
 			struct alternate_object_database *alt;
 			/* 43 = 40-byte + 2 '/' + terminating NUL */
 			int pfxlen = cp - last;
@@ -269,9 +270,19 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
 			}
 			else
 				memcpy(ent->base, last, pfxlen);
+
 			ent->name = ent->base + pfxlen + 1;
-			ent->base[pfxlen] = ent->base[pfxlen + 3] = '/';
-			ent->base[entlen-1] = 0;
+			ent->base[pfxlen + 3] = '/';
+			ent->base[pfxlen] = ent->base[entlen-1] = 0;
+
+			/* Detect cases where alternate disappeared */
+			if (stat(ent->base, &st) || !S_ISDIR(st.st_mode)) {
+				error("object directory %s does not exist; "
+				      "check .git/objects/info/alternates.",
+				      ent->base);
+				goto bad;
+			}
+			ent->base[pfxlen] = '/';
 
 			/* Prevent the common mistake of listing the same
 			 * thing twice, or object directory itself.
@@ -552,7 +563,9 @@ static void prepare_packed_git_one(char *objdir, int local)
 	len = strlen(path);
 	dir = opendir(path);
 	if (!dir) {
-		fprintf(stderr, "unable to open object pack directory: %s: %s\n", path, strerror(errno));
+		if (errno != ENOENT)
+			error("unable to open object pack directory: %s: %s\n",
+			      path, strerror(errno));
 		return;
 	}
 	path[len++] = '/';
@@ -828,6 +841,25 @@ static unsigned long unpack_object_header(struct packed_git *p, unsigned long of
 	return offset;
 }
 
+int check_reuse_pack_delta(struct packed_git *p, unsigned long offset,
+			   unsigned char *base, unsigned long *sizep,
+			   enum object_type *kindp)
+{
+	unsigned long ptr;
+	int status = -1;
+
+	use_packed_git(p);
+	ptr = offset;
+	ptr = unpack_object_header(p, ptr, kindp, sizep);
+	if (*kindp != OBJ_DELTA)
+		goto done;
+	memcpy(base, p->pack_base + ptr, 20);
+	status = 0;
+ done:
+	unuse_packed_git(p);
+	return status;
+}
+
 void packed_object_info_detail(struct pack_entry *e,
 			       char *type,
 			       unsigned long *size,

t/t3700-add.sh

@@ -0,0 +1,22 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Carl D. Worth
+#
+
+test_description='Test of git-add, including the -- option.'
+
+. ./test-lib.sh
+
+test_expect_success \
+    'Test of git-add' \
+    'touch foo && git-add foo'
+
+test_expect_success \
+    'Post-check that foo is in the index' \
+    'git-ls-files foo | grep foo'
+
+test_expect_success \
+    'Test that "git-add -- -q" works' \
+    'touch -- -q && git-add -- -q'
+
+test_done

var.c

@@ -12,7 +12,7 @@ static const char var_usage[] = "git-var [-l | <variable>]";
 
 struct git_var {
 	const char *name;
-	const char *(*read)(void);
+	const char *(*read)(int);
 };
 static struct git_var git_vars[] = {
 	{ "GIT_COMMITTER_IDENT", git_committer_info },
@@ -24,7 +24,7 @@ static void list_vars(void)
 {
 	struct git_var *ptr;
 	for(ptr = git_vars; ptr->read; ptr++) {
-		printf("%s=%s\n", ptr->name, ptr->read());
+		printf("%s=%s\n", ptr->name, ptr->read(0));
 	}
 }
 
@@ -35,7 +35,7 @@ static const char *read_var(const char *var)
 	val = NULL;
 	for(ptr = git_vars; ptr->read; ptr++) {
 		if (strcmp(var, ptr->name) == 0) {
-			val = ptr->read();
+			val = ptr->read(1);
 			break;
 		}
 	}