From: Junio C Hamano <junkio@cox.net>
Date: Wed, 10 May 2006 02:32:08 +0000 (-0700)
Subject: Merge branch 'master' into next
X-Git-Tag: v1.4.1-rc1~117
X-Git-Url: https://git.lorimer.id.au/gitweb.git/diff_plain/7278a29a277750e9e3cccce3cfb751d6171b1a43?hp=f7a3276bab880222e3117f8b8cbef40920dfe884

Merge branch 'master' into next

* master:
checkout: use --aggressive when running a 3-way merge (-m).
revert/cherry-pick: use aggressive merge.
read-cache.c: use xcalloc() not calloc()
apply: fix infinite loop with multiple patches with --index
---

diff --git a/.gitignore b/.gitignore
index b5959d6311..7906909b30 100644
--- a/.gitignore
+++ b/.gitignore
@@ -123,6 +123,7 @@ git-write-tree
 git-core-*/?*
 test-date
 test-delta
+test-dump-cache-tree
 common-cmds.h
 *.tar.gz
 *.dsc
diff --git a/Documentation/git-cvsexportcommit.txt b/Documentation/git-cvsexportcommit.txt
index d30435a9e4..56bd3e517d 100644
--- a/Documentation/git-cvsexportcommit.txt
+++ b/Documentation/git-cvsexportcommit.txt
@@ -8,7 +8,7 @@ git-cvsexportcommit - Export a commit to a CVS checkout
 
 SYNOPSIS
 --------
-'git-cvsexportcommmit' [-h] [-v] [-c] [-p] [PARENTCOMMIT] COMMITID
+'git-cvsexportcommmit' [-h] [-v] [-c] [-p] [-f] [-m msgprefix] [PARENTCOMMIT] COMMITID
 
 
 DESCRIPTION
@@ -39,6 +39,13 @@ OPTIONS
 	Be pedantic (paranoid) when applying patches. Invokes patch with 
 	--fuzz=0
 
+-f::
+	Force the merge even if the files are not up to date.
+
+-m::
+	Prepend the commit message with the provided prefix. 
+	Useful for patch series and the like.
+
 -v::
 	Verbose.
 
diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
index d55456ae93..74102b7944 100644
--- a/Documentation/git-grep.txt
+++ b/Documentation/git-grep.txt
@@ -8,43 +8,82 @@ git-grep - Print lines matching a pattern
 
 SYNOPSIS
 --------
-'git-grep' [<option>...] [-e] <pattern> [--] [<path>...]
+[verse]
+'git-grep' [--cached]
+	   [-a | --text] [-I] [-i | --ignore-case] [-w | --word-regexp]
+	   [-v | --invert-match]
+	   [-E | --extended-regexp] [-G | --basic-regexp] [-F | --fixed-strings]
+	   [-n] [-l | --files-with-matches] [-L | --files-without-match]
+	   [-c | --count]
+	   [-A <post-context>] [-B <pre-context>] [-C <context>]
+	   [-f <file>] [-e <pattern>]
+	   [<tree>...]
+	   [--] [<path>...]
 
 DESCRIPTION
 -----------
-Searches list of files `git-ls-files` produces for lines
-containing a match to the given pattern.
+Look for specified patterns in the working tree files, blobs
+registered in the index file, or given tree objects.
 
 
 OPTIONS
 -------
-`--`::
-	Signals the end of options; the rest of the parameters
-	are <path> limiters.
+--cached::
+	Instead of searching in the working tree files, check
+	the blobs registerd in the index file.
+
+-a | --text::
+	Process binary files as if they were text.
+
+-i | --ignore-case::
+	Ignore case differences between the patterns and the
+	files.
+
+-w | --word-regexp::
+	Match the pattern only at word boundary (either begin at the
+	beginning of a line, or preceded by a non-word character; end at
+	the end of a line or followed by a non-word character).
+
+-v | --invert-match::
+	Select non-matching lines.
+
+-E | --extended-regexp | -G | --basic-regexp::
+	Use POSIX extended/basic regexp for patterns.  Default
+	is to use basic regexp.
 
-<option>...::
-	Either an option to pass to `grep` or `git-ls-files`.
-+
-The following are the specific `git-ls-files` options
-that may be given: `-o`, `--cached`, `--deleted`, `--others`,
-`--killed`, `--ignored`, `--modified`, `--exclude=\*`,
-`--exclude-from=\*`, and `--exclude-per-directory=\*`.
-+
-All other options will be passed to `grep`.
+-n::
+	Prefix the line number to matching lines.
 
-<pattern>::
-	The pattern to look for.  The first non option is taken
-	as the pattern; if your pattern begins with a dash, use
-	`-e <pattern>`.
+-l | --files-with-matches | -L | --files-without-match::
+	Instead of showing every matched line, show only the
+	names of files that contain (or do not contain) matches.
 
-<path>...::
-	Optional paths to limit the set of files to be searched;
-	passed to `git-ls-files`.
+-c | --count::
+	Instead of showing every matched line, show the number of
+	lines that match.
+
+-[ABC] <context>::
+	Show `context` trailing (`A` -- after), or leading (`B`
+	-- before), or both (`C` -- context) lines, and place a
+	line containing `--` between continguous groups of
+	matches.
+
+-f <file>::
+	Read patterns from <file>, one per line.
+
+`<tree>...`::
+	Search blobs in the trees for specified patterns.
+
+`--`::
+	Signals the end of options; the rest of the parameters
+	are <path> limiters.
 
 
 Author
 ------
-Written by Linus Torvalds <torvalds@osdl.org>
+Originally written by Linus Torvalds <torvalds@osdl.org>, later
+revamped by Junio C Hamano.
+
 
 Documentation
 --------------
diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt
index 844cfda8d2..1f21d95684 100644
--- a/Documentation/git-read-tree.txt
+++ b/Documentation/git-read-tree.txt
@@ -8,7 +8,7 @@ git-read-tree - Reads tree information into the index
 
 SYNOPSIS
 --------
-'git-read-tree' (<tree-ish> | [[-m [--aggressive]| --reset] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]])
+'git-read-tree' (<tree-ish> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <tree-ish1> [<tree-ish2> [<tree-ish3>]])
 
 
 DESCRIPTION
@@ -63,6 +63,15 @@ OPTIONS
 * when both sides adds a path identically.  The resolution
   is to add that path.
 
+--prefix=<prefix>/::
+	Keep the current index contents, and read the contents
+	of named tree-ish under directory at `<prefix>`.  The
+	original index file cannot have anything at the path
+	`<prefix>` itself, and have nothing in `<prefix>/`
+	directory.  Note that the `<prefix>/` value must end
+	with a slash.
+
+
 <tree-ish#>::
 	The id of the tree object(s) to be read/merged.
 
diff --git a/Documentation/git-write-tree.txt b/Documentation/git-write-tree.txt
index 77e12cb949..c85fa89c30 100644
--- a/Documentation/git-write-tree.txt
+++ b/Documentation/git-write-tree.txt
@@ -8,7 +8,7 @@ git-write-tree - Creates a tree object from the current index
 
 SYNOPSIS
 --------
-'git-write-tree' [--missing-ok]
+'git-write-tree' [--missing-ok] [--prefix=<prefix>/]
 
 DESCRIPTION
 -----------
@@ -30,6 +30,12 @@ OPTIONS
 	directory exist in the object database.  This option disables this
 	check.
 
+--prefix=<prefix>/::
+	Writes a tree object that represents a subdirectory
+	`<prefix>`.  This can be used to write the tree object
+	for a subproject that is in the named subdirectory.
+
+
 Author
 ------
 Written by Linus Torvalds <torvalds@osdl.org>
diff --git a/Makefile b/Makefile
index 37fbe789d3..070c478bf2 100644
--- a/Makefile
+++ b/Makefile
@@ -205,7 +205,7 @@ DIFF_OBJS = \
 	diffcore-delta.o log-tree.o
 
 LIB_OBJS = \
-	blob.o commit.o connect.o csum-file.o base85.o \
+	blob.o commit.o connect.o csum-file.o cache-tree.o base85.o \
 	date.o diff-delta.o entry.o exec_cmd.o ident.o index.o \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o \
 	quote.o read-cache.o refs.o run-command.o \
@@ -215,7 +215,8 @@ LIB_OBJS = \
 	$(DIFF_OBJS)
 
 BUILTIN_OBJS = \
-	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o
+	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
+	builtin-grep.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
@@ -609,6 +610,9 @@ test-date$X: test-date.c date.o ctype.o
 test-delta$X: test-delta.c diff-delta.o patch-delta.o
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $^
 
+test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS)
+	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+
 check:
 	for i in *.c; do sparse $(ALL_CFLAGS) $(SPARSE_FLAGS) $$i || exit; done
 
diff --git a/apply.c b/apply.c
index 7c8146a7f3..ea6fb4c880 100644
--- a/apply.c
+++ b/apply.c
@@ -8,6 +8,7 @@
  */
 #include <fnmatch.h>
 #include "cache.h"
+#include "cache-tree.h"
 #include "quote.h"
 #include "blob.h"
 #include "delta.h"
@@ -1893,6 +1894,7 @@ static void remove_file(struct patch *patch)
 	if (write_index) {
 		if (remove_file_from_cache(patch->old_name) < 0)
 			die("unable to remove %s from index", patch->old_name);
+		cache_tree_invalidate_path(active_cache_tree, patch->old_name);
 	}
 	unlink(patch->old_name);
 }
@@ -1989,8 +1991,9 @@ static void create_file(struct patch *patch)
 
 	if (!mode)
 		mode = S_IFREG | 0644;
-	create_one_file(path, mode, buf, size);	
+	create_one_file(path, mode, buf, size);
 	add_index_file(path, mode, buf, size);
+	cache_tree_invalidate_path(active_cache_tree, path);
 }
 
 static void write_out_one_result(struct patch *patch)
diff --git a/builtin-diff.c b/builtin-diff.c
index d3ac581f29..71742aa10b 100644
--- a/builtin-diff.c
+++ b/builtin-diff.c
@@ -231,7 +231,7 @@ static int builtin_diff_combined(struct rev_info *revs,
 	return 0;
 }
 
-static void add_head(struct rev_info *revs)
+void add_head(struct rev_info *revs)
 {
 	unsigned char sha1[20];
 	struct object *obj;
diff --git a/builtin-grep.c b/builtin-grep.c
new file mode 100644
index 0000000000..fead356629
--- /dev/null
+++ b/builtin-grep.c
@@ -0,0 +1,757 @@
+/*
+ * Builtin "git grep"
+ *
+ * Copyright (c) 2006 Junio C Hamano
+ */
+#include "cache.h"
+#include "blob.h"
+#include "tree.h"
+#include "commit.h"
+#include "tag.h"
+#include "tree-walk.h"
+#include "builtin.h"
+#include <regex.h>
+#include <fnmatch.h>
+
+/*
+ * git grep pathspecs are somewhat different from diff-tree pathspecs;
+ * pathname wildcards are allowed.
+ */
+static int pathspec_matches(const char **paths, const char *name)
+{
+	int namelen, i;
+	if (!paths || !*paths)
+		return 1;
+	namelen = strlen(name);
+	for (i = 0; paths[i]; i++) {
+		const char *match = paths[i];
+		int matchlen = strlen(match);
+		const char *cp, *meta;
+
+		if ((matchlen <= namelen) &&
+		    !strncmp(name, match, matchlen) &&
+		    (match[matchlen-1] == '/' ||
+		     name[matchlen] == '\0' || name[matchlen] == '/'))
+			return 1;
+		if (!fnmatch(match, name, 0))
+			return 1;
+		if (name[namelen-1] != '/')
+			continue;
+
+		/* We are being asked if the directory ("name") is worth
+		 * descending into.
+		 *
+		 * Find the longest leading directory name that does
+		 * not have metacharacter in the pathspec; the name
+		 * we are looking at must overlap with that directory.
+		 */
+		for (cp = match, meta = NULL; cp - match < matchlen; cp++) {
+			char ch = *cp;
+			if (ch == '*' || ch == '[' || ch == '?') {
+				meta = cp;
+				break;
+			}
+		}
+		if (!meta)
+			meta = cp; /* fully literal */
+
+		if (namelen <= meta - match) {
+			/* Looking at "Documentation/" and
+			 * the pattern says "Documentation/howto/", or
+			 * "Documentation/diff*.txt".  The name we
+			 * have should match prefix.
+			 */
+			if (!memcmp(match, name, namelen))
+				return 1;
+			continue;
+		}
+
+		if (meta - match < namelen) {
+			/* Looking at "Documentation/howto/" and
+			 * the pattern says "Documentation/h*";
+			 * match up to "Do.../h"; this avoids descending
+			 * into "Documentation/technical/".
+			 */
+			if (!memcmp(match, name, meta - match))
+				return 1;
+			continue;
+		}
+	}
+	return 0;
+}
+
+struct grep_pat {
+	struct grep_pat *next;
+	const char *origin;
+	int no;
+	const char *pattern;
+	regex_t regexp;
+};
+
+struct grep_opt {
+	struct grep_pat *pattern_list;
+	struct grep_pat **pattern_tail;
+	regex_t regexp;
+	unsigned linenum:1;
+	unsigned invert:1;
+	unsigned name_only:1;
+	unsigned unmatch_name_only:1;
+	unsigned count:1;
+	unsigned word_regexp:1;
+	unsigned fixed:1;
+#define GREP_BINARY_DEFAULT	0
+#define GREP_BINARY_NOMATCH	1
+#define GREP_BINARY_TEXT	2
+	unsigned binary:2;
+	int regflags;
+	unsigned pre_context;
+	unsigned post_context;
+};
+
+static void add_pattern(struct grep_opt *opt, const char *pat,
+			const char *origin, int no)
+{
+	struct grep_pat *p = xcalloc(1, sizeof(*p));
+	p->pattern = pat;
+	p->origin = origin;
+	p->no = no;
+	*opt->pattern_tail = p;
+	opt->pattern_tail = &p->next;
+	p->next = NULL;
+}
+
+static void compile_patterns(struct grep_opt *opt)
+{
+	struct grep_pat *p;
+	for (p = opt->pattern_list; p; p = p->next) {
+		int err = regcomp(&p->regexp, p->pattern, opt->regflags);
+		if (err) {
+			char errbuf[1024];
+			char where[1024];
+			if (p->no)
+				sprintf(where, "In '%s' at %d, ",
+					p->origin, p->no);
+			else if (p->origin)
+				sprintf(where, "%s, ", p->origin);
+			else
+				where[0] = 0;
+			regerror(err, &p->regexp, errbuf, 1024);
+			regfree(&p->regexp);
+			die("%s'%s': %s", where, p->pattern, errbuf);
+		}
+	}
+}
+
+static char *end_of_line(char *cp, unsigned long *left)
+{
+	unsigned long l = *left;
+	while (l && *cp != '\n') {
+		l--;
+		cp++;
+	}
+	*left = l;
+	return cp;
+}
+
+static int word_char(char ch)
+{
+	return isalnum(ch) || ch == '_';
+}
+
+static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
+		      const char *name, unsigned lno, char sign)
+{
+	printf("%s%c", name, sign);
+	if (opt->linenum)
+		printf("%d%c", lno, sign);
+	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;
+	if (memchr(ptr, 0, size))
+		return 1;
+	return 0;
+}
+
+static int fixmatch(const char *pattern, char *line, regmatch_t *match)
+{
+	char *hit = strstr(line, pattern);
+	if (!hit) {
+		match->rm_so = match->rm_eo = -1;
+		return REG_NOMATCH;
+	}
+	else {
+		match->rm_so = hit - line;
+		match->rm_eo = match->rm_so + strlen(pattern);
+		return 0;
+	}
+}
+
+static int grep_buffer(struct grep_opt *opt, const char *name,
+		       char *buf, unsigned long size)
+{
+	char *bol = buf;
+	unsigned long left = size;
+	unsigned lno = 1;
+	struct pre_context_line {
+		char *bol;
+		char *eol;
+	} *prev = NULL, *pcl;
+	unsigned last_hit = 0;
+	unsigned last_shown = 0;
+	int binary_match_only = 0;
+	const char *hunk_mark = "";
+	unsigned count = 0;
+
+	if (buffer_is_binary(buf, size)) {
+		switch (opt->binary) {
+		case GREP_BINARY_DEFAULT:
+			binary_match_only = 1;
+			break;
+		case GREP_BINARY_NOMATCH:
+			return 0; /* Assume unmatch */
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (opt->pre_context)
+		prev = xcalloc(opt->pre_context, sizeof(*prev));
+	if (opt->pre_context || opt->post_context)
+		hunk_mark = "--\n";
+
+	while (left) {
+		regmatch_t pmatch[10];
+		char *eol, ch;
+		int hit = 0;
+		struct grep_pat *p;
+
+		eol = end_of_line(bol, &left);
+		ch = *eol;
+		*eol = 0;
+
+		for (p = opt->pattern_list; p; p = p->next) {
+			if (!opt->fixed) {
+				regex_t *exp = &p->regexp;
+				hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
+					       pmatch, 0);
+			}
+			else {
+				hit = !fixmatch(p->pattern, bol, pmatch);
+			}
+
+			if (hit && opt->word_regexp) {
+				/* Match beginning must be either
+				 * beginning of the line, or at word
+				 * boundary (i.e. the last char must
+				 * not be alnum or underscore).
+				 */
+				if ((pmatch[0].rm_so < 0) ||
+				    (eol - bol) <= pmatch[0].rm_so ||
+				    (pmatch[0].rm_eo < 0) ||
+				    (eol - bol) < pmatch[0].rm_eo)
+					die("regexp returned nonsense");
+				if (pmatch[0].rm_so != 0 &&
+				    word_char(bol[pmatch[0].rm_so-1]))
+					hit = 0;
+				if (pmatch[0].rm_eo != (eol-bol) &&
+				    word_char(bol[pmatch[0].rm_eo]))
+					hit = 0;
+			}
+			if (hit)
+				break;
+		}
+		/* "grep -v -e foo -e bla" should list lines
+		 * that do not have either, so inversion should
+		 * be done outside.
+		 */
+		if (opt->invert)
+			hit = !hit;
+		if (opt->unmatch_name_only) {
+			if (hit)
+				return 0;
+			goto next_line;
+		}
+		if (hit) {
+			count++;
+			if (binary_match_only) {
+				printf("Binary file %s matches\n", name);
+				return 1;
+			}
+			if (opt->name_only) {
+				printf("%s\n", name);
+				return 1;
+			}
+			/* Hit at this line.  If we haven't shown the
+			 * pre-context lines, we would need to show them.
+			 * When asked to do "count", this still show
+			 * the context which is nonsense, but the user
+			 * deserves to get that ;-).
+			 */
+			if (opt->pre_context) {
+				unsigned from;
+				if (opt->pre_context < lno)
+					from = lno - opt->pre_context;
+				else
+					from = 1;
+				if (from <= last_shown)
+					from = last_shown + 1;
+				if (last_shown && from != last_shown + 1)
+					printf(hunk_mark);
+				while (from < lno) {
+					pcl = &prev[lno-from-1];
+					show_line(opt, pcl->bol, pcl->eol,
+						  name, from, '-');
+					from++;
+				}
+				last_shown = lno-1;
+			}
+			if (last_shown && lno != last_shown + 1)
+				printf(hunk_mark);
+			if (!opt->count)
+				show_line(opt, bol, eol, name, lno, ':');
+			last_shown = last_hit = lno;
+		}
+		else if (last_hit &&
+			 lno <= last_hit + opt->post_context) {
+			/* If the last hit is within the post context,
+			 * we need to show this line.
+			 */
+			if (last_shown && lno != last_shown + 1)
+				printf(hunk_mark);
+			show_line(opt, bol, eol, name, lno, '-');
+			last_shown = lno;
+		}
+		if (opt->pre_context) {
+			memmove(prev+1, prev,
+				(opt->pre_context-1) * sizeof(*prev));
+			prev->bol = bol;
+			prev->eol = eol;
+		}
+
+	next_line:
+		*eol = ch;
+		bol = eol + 1;
+		if (!left)
+			break;
+		left--;
+		lno++;
+	}
+
+	if (opt->unmatch_name_only) {
+		/* We did not see any hit, so we want to show this */
+		printf("%s\n", name);
+		return 1;
+	}
+
+	/* NEEDSWORK:
+	 * The real "grep -c foo *.c" gives many "bar.c:0" lines,
+	 * which feels mostly useless but sometimes useful.  Maybe
+	 * make it another option?  For now suppress them.
+	 */
+	if (opt->count && count)
+		printf("%s:%u\n", name, count);
+	return !!last_hit;
+}
+
+static int grep_sha1(struct grep_opt *opt, const unsigned char *sha1, const char *name)
+{
+	unsigned long size;
+	char *data;
+	char type[20];
+	int hit;
+	data = read_sha1_file(sha1, type, &size);
+	if (!data) {
+		error("'%s': unable to read %s", name, sha1_to_hex(sha1));
+		return 0;
+	}
+	hit = grep_buffer(opt, name, data, size);
+	free(data);
+	return hit;
+}
+
+static int grep_file(struct grep_opt *opt, const char *filename)
+{
+	struct stat st;
+	int i;
+	char *data;
+	if (lstat(filename, &st) < 0) {
+	err_ret:
+		if (errno != ENOENT)
+			error("'%s': %s", filename, strerror(errno));
+		return 0;
+	}
+	if (!st.st_size)
+		return 0; /* empty file -- no grep hit */
+	if (!S_ISREG(st.st_mode))
+		return 0;
+	i = open(filename, O_RDONLY);
+	if (i < 0)
+		goto err_ret;
+	data = xmalloc(st.st_size + 1);
+	if (st.st_size != xread(i, data, st.st_size)) {
+		error("'%s': short read %s", filename, strerror(errno));
+		close(i);
+		free(data);
+		return 0;
+	}
+	close(i);
+	i = grep_buffer(opt, filename, data, st.st_size);
+	free(data);
+	return i;
+}
+
+static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
+{
+	int hit = 0;
+	int nr;
+	read_cache();
+
+	for (nr = 0; nr < active_nr; nr++) {
+		struct cache_entry *ce = active_cache[nr];
+		if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
+			continue;
+		if (!pathspec_matches(paths, ce->name))
+			continue;
+		if (cached)
+			hit |= grep_sha1(opt, ce->sha1, ce->name);
+		else
+			hit |= grep_file(opt, ce->name);
+	}
+	return hit;
+}
+
+static int grep_tree(struct grep_opt *opt, const char **paths,
+		     struct tree_desc *tree,
+		     const char *tree_name, const char *base)
+{
+	unsigned mode;
+	int len;
+	int hit = 0;
+	const char *path;
+	const unsigned char *sha1;
+	char *down;
+	char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
+
+	if (tree_name[0]) {
+		int offset = sprintf(path_buf, "%s:", tree_name);
+		down = path_buf + offset;
+		strcat(down, base);
+	}
+	else {
+		down = path_buf;
+		strcpy(down, base);
+	}
+	len = strlen(path_buf);
+
+	while (tree->size) {
+		int pathlen;
+		sha1 = tree_entry_extract(tree, &path, &mode);
+		pathlen = strlen(path);
+		strcpy(path_buf + len, path);
+
+		if (S_ISDIR(mode))
+			/* Match "abc/" against pathspec to
+			 * decide if we want to descend into "abc"
+			 * directory.
+			 */
+			strcpy(path_buf + len + pathlen, "/");
+
+		if (!pathspec_matches(paths, down))
+			;
+		else if (S_ISREG(mode))
+			hit |= grep_sha1(opt, sha1, path_buf);
+		else if (S_ISDIR(mode)) {
+			char type[20];
+			struct tree_desc sub;
+			void *data;
+			data = read_sha1_file(sha1, type, &sub.size);
+			if (!data)
+				die("unable to read tree (%s)",
+				    sha1_to_hex(sha1));
+			sub.buf = data;
+			hit |= grep_tree(opt, paths, &sub, tree_name, down);
+			free(data);
+		}
+		update_tree_entry(tree);
+	}
+	return hit;
+}
+
+static int grep_object(struct grep_opt *opt, const char **paths,
+		       struct object *obj, const char *name)
+{
+	if (!strcmp(obj->type, blob_type))
+		return grep_sha1(opt, obj->sha1, name);
+	if (!strcmp(obj->type, commit_type) ||
+	    !strcmp(obj->type, tree_type)) {
+		struct tree_desc tree;
+		void *data;
+		int hit;
+		data = read_object_with_reference(obj->sha1, tree_type,
+						  &tree.size, NULL);
+		if (!data)
+			die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
+		tree.buf = data;
+		hit = grep_tree(opt, paths, &tree, name, "");
+		free(data);
+		return hit;
+	}
+	die("unable to grep from object of type %s", obj->type);
+}
+
+static const char builtin_grep_usage[] =
+"git-grep <option>* <rev>* [-e] <pattern> [<path>...]";
+
+int cmd_grep(int argc, const char **argv, char **envp)
+{
+	int hit = 0;
+	int cached = 0;
+	int seen_dashdash = 0;
+	struct grep_opt opt;
+	struct object_list *list, **tail, *object_list = NULL;
+	const char *prefix = setup_git_directory();
+	const char **paths = NULL;
+	int i;
+
+	memset(&opt, 0, sizeof(opt));
+	opt.pattern_tail = &opt.pattern_list;
+	opt.regflags = REG_NEWLINE;
+
+	/*
+	 * If there is no -- then the paths must exist in the working
+	 * tree.  If there is no explicit pattern specified with -e or
+	 * -f, we take the first unrecognized non option to be the
+	 * pattern, but then what follows it must be zero or more
+	 * valid refs up to the -- (if exists), and then existing
+	 * paths.  If there is an explicit pattern, then the first
+	 * unrecocnized non option is the beginning of the refs list
+	 * that continues up to the -- (if exists), and then paths.
+	 */
+
+	tail = &object_list;
+	while (1 < argc) {
+		const char *arg = argv[1];
+		argc--; argv++;
+		if (!strcmp("--cached", arg)) {
+			cached = 1;
+			continue;
+		}
+		if (!strcmp("-a", arg) ||
+		    !strcmp("--text", arg)) {
+			opt.binary = GREP_BINARY_TEXT;
+			continue;
+		}
+		if (!strcmp("-i", arg) ||
+		    !strcmp("--ignore-case", arg)) {
+			opt.regflags |= REG_ICASE;
+			continue;
+		}
+		if (!strcmp("-I", arg)) {
+			opt.binary = GREP_BINARY_NOMATCH;
+			continue;
+		}
+		if (!strcmp("-v", arg) ||
+		    !strcmp("--invert-match", arg)) {
+			opt.invert = 1;
+			continue;
+		}
+		if (!strcmp("-E", arg) ||
+		    !strcmp("--extended-regexp", arg)) {
+			opt.regflags |= REG_EXTENDED;
+			continue;
+		}
+		if (!strcmp("-F", arg) ||
+		    !strcmp("--fixed-strings", arg)) {
+			opt.fixed = 1;
+			continue;
+		}
+		if (!strcmp("-G", arg) ||
+		    !strcmp("--basic-regexp", arg)) {
+			opt.regflags &= ~REG_EXTENDED;
+			continue;
+		}
+		if (!strcmp("-n", arg)) {
+			opt.linenum = 1;
+			continue;
+		}
+		if (!strcmp("-H", arg)) {
+			/* We always show the pathname, so this
+			 * is a noop.
+			 */
+			continue;
+		}
+		if (!strcmp("-l", arg) ||
+		    !strcmp("--files-with-matches", arg)) {
+			opt.name_only = 1;
+			continue;
+		}
+		if (!strcmp("-L", arg) ||
+		    !strcmp("--files-without-match", arg)) {
+			opt.unmatch_name_only = 1;
+			continue;
+		}
+		if (!strcmp("-c", arg) ||
+		    !strcmp("--count", arg)) {
+			opt.count = 1;
+			continue;
+		}
+		if (!strcmp("-w", arg) ||
+		    !strcmp("--word-regexp", arg)) {
+			opt.word_regexp = 1;
+			continue;
+		}
+		if (!strncmp("-A", arg, 2) ||
+		    !strncmp("-B", arg, 2) ||
+		    !strncmp("-C", arg, 2) ||
+		    (arg[0] == '-' && '1' <= arg[1] && arg[1] <= '9')) {
+			unsigned num;
+			const char *scan;
+			switch (arg[1]) {
+			case 'A': case 'B': case 'C':
+				if (!arg[2]) {
+					if (argc <= 1)
+						usage(builtin_grep_usage);
+					scan = *++argv;
+					argc--;
+				}
+				else
+					scan = arg + 2;
+				break;
+			default:
+				scan = arg + 1;
+				break;
+			}
+			if (sscanf(scan, "%u", &num) != 1)
+				usage(builtin_grep_usage);
+			switch (arg[1]) {
+			case 'A':
+				opt.post_context = num;
+				break;
+			default:
+			case 'C':
+				opt.post_context = num;
+			case 'B':
+				opt.pre_context = num;
+				break;
+			}
+			continue;
+		}
+		if (!strcmp("-f", arg)) {
+			FILE *patterns;
+			int lno = 0;
+			char buf[1024];
+			if (argc <= 1)
+				usage(builtin_grep_usage);
+			patterns = fopen(argv[1], "r");
+			if (!patterns)
+				die("'%s': %s", argv[1], strerror(errno));
+			while (fgets(buf, sizeof(buf), patterns)) {
+				int len = strlen(buf);
+				if (buf[len-1] == '\n')
+					buf[len-1] = 0;
+				/* ignore empty line like grep does */
+				if (!buf[0])
+					continue;
+				add_pattern(&opt, strdup(buf), argv[1], ++lno);
+			}
+			fclose(patterns);
+			argv++;
+			argc--;
+			continue;
+		}
+		if (!strcmp("-e", arg)) {
+			if (1 < argc) {
+				add_pattern(&opt, argv[1], "-e option", 0);
+				argv++;
+				argc--;
+				continue;
+			}
+			usage(builtin_grep_usage);
+		}
+		if (!strcmp("--", arg))
+			break;
+		if (*arg == '-')
+			usage(builtin_grep_usage);
+
+		/* First unrecognized non-option token */
+		if (!opt.pattern_list) {
+			add_pattern(&opt, arg, "command line", 0);
+			break;
+		}
+		else {
+			/* We are looking at the first path or rev;
+			 * it is found at argv[1] after leaving the
+			 * loop.
+			 */
+			argc++; argv--;
+			break;
+		}
+	}
+
+	if (!opt.pattern_list)
+		die("no pattern given.");
+	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
+		die("cannot mix --fixed-strings and regexp");
+	if (!opt.fixed)
+		compile_patterns(&opt);
+
+	/* Check revs and then paths */
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+		unsigned char sha1[20];
+		/* Is it a rev? */
+		if (!get_sha1(arg, sha1)) {
+			struct object *object = parse_object(sha1);
+			struct object_list *elem;
+			if (!object)
+				die("bad object %s", arg);
+			elem = object_list_insert(object, tail);
+			elem->name = arg;
+			tail = &elem->next;
+			continue;
+		}
+		if (!strcmp(arg, "--")) {
+			i++;
+			seen_dashdash = 1;
+		}
+		break;
+	}
+
+	/* The rest are paths */
+	if (!seen_dashdash) {
+		int j;
+		for (j = i; j < argc; j++)
+			verify_filename(prefix, argv[j]);
+	}
+
+	if (i < argc)
+		paths = get_pathspec(prefix, argv + i);
+	else if (prefix) {
+		paths = xcalloc(2, sizeof(const char *));
+		paths[0] = prefix;
+		paths[1] = NULL;
+	}
+
+	if (!object_list)
+		return !grep_cache(&opt, paths, cached);
+
+	if (cached)
+		die("both --cached and trees are given.");
+
+	for (list = object_list; list; list = list->next) {
+		struct object *real_obj;
+		real_obj = deref_tag(list->item, NULL, 0);
+		if (grep_object(&opt, paths, real_obj, list->name))
+			hit = 1;
+	}
+	return !hit;
+}
diff --git a/builtin-log.c b/builtin-log.c
index 69f2911cb4..d5bbc1cc06 100644
--- a/builtin-log.c
+++ b/builtin-log.c
@@ -9,6 +9,10 @@
 #include "diff.h"
 #include "revision.h"
 #include "log-tree.h"
+#include "builtin.h"
+
+/* this is in builtin-diff.c */
+void add_head(struct rev_info *revs);
 
 static int cmd_log_wc(int argc, const char **argv, char **envp,
 		      struct rev_info *rev)
@@ -67,3 +71,160 @@ int cmd_log(int argc, const char **argv, char **envp)
 	rev.diffopt.recursive = 1;
 	return cmd_log_wc(argc, argv, envp, &rev);
 }
+
+static int istitlechar(char c)
+{
+	return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
+		(c >= '0' && c <= '9') || c == '.' || c == '_';
+}
+
+static FILE *realstdout = NULL;
+static char *output_directory = NULL;
+
+static void reopen_stdout(struct commit *commit, int nr, int keep_subject)
+{
+	char filename[1024];
+	char *sol;
+	int len = 0;
+
+	if (output_directory) {
+		strncpy(filename, output_directory, 1010);
+		len = strlen(filename);
+		if (filename[len - 1] != '/')
+			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 && !strncmp(sol, "[PATCH", 6)) {
+			char *eos = strchr(sol + 6, ']');
+			if (eos) {
+				while (isspace(*eos))
+					eos++;
+				sol = eos;
+			}
+		}
+
+		for (j = 0; len < 1024 - 6 && 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--;
+	}
+	strcpy(filename + len, ".txt");
+	fprintf(realstdout, "%s\n", filename);
+	freopen(filename, "w", stdout);
+}
+
+int cmd_format_patch(int argc, const char **argv, char **envp)
+{
+	struct commit *commit;
+	struct commit **list = NULL;
+	struct rev_info rev;
+	int nr = 0, total, i, j;
+	int use_stdout = 0;
+	int numbered = 0;
+	int keep_subject = 0;
+
+	init_revisions(&rev);
+	rev.commit_format = CMIT_FMT_EMAIL;
+	rev.verbose_header = 1;
+	rev.diff = 1;
+	rev.diffopt.with_raw = 0;
+	rev.diffopt.with_stat = 1;
+	rev.combine_merges = 0;
+	rev.ignore_merges = 1;
+	rev.diffopt.output_format = DIFF_FORMAT_PATCH;
+
+	/*
+	 * Parse the arguments before setup_revisions(), or something
+	 * like "git fmt-patch -o a123 HEAD^.." may fail; a123 is
+	 * possibly a valid SHA1.
+	 */
+	for (i = 1, j = 1; i < argc; i++) {
+		if (!strcmp(argv[i], "--stdout"))
+			use_stdout = 1;
+		else if (!strcmp(argv[i], "-n") ||
+				!strcmp(argv[i], "--numbered"))
+			numbered = 1;
+		else if (!strcmp(argv[i], "-k") ||
+				!strcmp(argv[i], "--keep-subject")) {
+			keep_subject = 1;
+			rev.total = -1;
+		} else if (!strcmp(argv[i], "-o")) {
+			if (argc < 3)
+				die ("Which directory?");
+			if (mkdir(argv[i + 1], 0777) < 0 && errno != EEXIST)
+				die("Could not create directory %s",
+						argv[i + 1]);
+			output_directory = strdup(argv[i + 1]);
+			i++;
+		} else
+			argv[j++] = argv[i];
+	}
+	argc = j;
+
+	if (numbered && keep_subject < 0)
+		die ("-n and -k are mutually exclusive.");
+
+	argc = setup_revisions(argc, argv, &rev, "HEAD");
+	if (argc > 1)
+		die ("unrecognized argument: %s", argv[1]);
+
+	if (rev.pending_objects && rev.pending_objects->next == NULL) {
+		rev.pending_objects->item->flags |= UNINTERESTING;
+		add_head(&rev);
+	}
+
+	if (!use_stdout)
+		realstdout = fdopen(dup(1), "w");
+
+	prepare_revision_walk(&rev);
+	while ((commit = get_revision(&rev)) != NULL) {
+		/* ignore merges */
+		if (commit->parents && commit->parents->next)
+			continue;
+		nr++;
+		list = realloc(list, nr * sizeof(list[0]));
+		list[nr - 1] = commit;
+	}
+	total = nr;
+	if (numbered)
+		rev.total = total;
+	while (0 <= --nr) {
+		int shown;
+		commit = list[nr];
+		rev.nr = total - nr;
+		if (!use_stdout)
+			reopen_stdout(commit, rev.nr, keep_subject);
+		shown = log_tree_commit(&rev, commit);
+		free(commit->buffer);
+		commit->buffer = NULL;
+		if (shown)
+			printf("-- \n%s\n\n", git_version_string);
+		if (!use_stdout)
+			fclose(stdout);
+	}
+	if (output_directory)
+		free(output_directory);
+	free(list);
+	return 0;
+}
+
diff --git a/builtin.h b/builtin.h
index bb63f0729a..97e2464468 100644
--- a/builtin.h
+++ b/builtin.h
@@ -20,8 +20,10 @@ extern int cmd_whatchanged(int argc, const char **argv, char **envp);
 extern int cmd_show(int argc, const char **argv, char **envp);
 extern int cmd_log(int argc, const char **argv, char **envp);
 extern int cmd_diff(int argc, const char **argv, char **envp);
+extern int cmd_format_patch(int argc, const char **argv, char **envp);
 extern int cmd_count_objects(int argc, const char **argv, char **envp);
 
 extern int cmd_push(int argc, const char **argv, char **envp);
+extern int cmd_grep(int argc, const char **argv, char **envp);
 
 #endif
diff --git a/cache-tree.c b/cache-tree.c
new file mode 100644
index 0000000000..d9f7e1e3dd
--- /dev/null
+++ b/cache-tree.c
@@ -0,0 +1,557 @@
+#include "cache.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+#define DEBUG 0
+
+struct cache_tree *cache_tree(void)
+{
+	struct cache_tree *it = xcalloc(1, sizeof(struct cache_tree));
+	it->entry_count = -1;
+	return it;
+}
+
+void cache_tree_free(struct cache_tree **it_p)
+{
+	int i;
+	struct cache_tree *it = *it_p;
+
+	if (!it)
+		return;
+	for (i = 0; i < it->subtree_nr; i++)
+		if (it->down[i])
+			cache_tree_free(&it->down[i]->cache_tree);
+	free(it->down);
+	free(it);
+	*it_p = NULL;
+}
+
+static int subtree_name_cmp(const char *one, int onelen,
+			    const char *two, int twolen)
+{
+	if (onelen < twolen)
+		return -1;
+	if (twolen < onelen)
+		return 1;
+	return memcmp(one, two, onelen);
+}
+
+static int subtree_pos(struct cache_tree *it, const char *path, int pathlen)
+{
+	struct cache_tree_sub **down = it->down;
+	int lo, hi;
+	lo = 0;
+	hi = it->subtree_nr;
+	while (lo < hi) {
+		int mi = (lo + hi) / 2;
+		struct cache_tree_sub *mdl = down[mi];
+		int cmp = subtree_name_cmp(path, pathlen,
+					   mdl->name, mdl->namelen);
+		if (!cmp)
+			return mi;
+		if (cmp < 0)
+			hi = mi;
+		else
+			lo = mi + 1;
+	}
+	return -lo-1;
+}
+
+static struct cache_tree_sub *find_subtree(struct cache_tree *it,
+					   const char *path,
+					   int pathlen,
+					   int create)
+{
+	struct cache_tree_sub *down;
+	int pos = subtree_pos(it, path, pathlen);
+	if (0 <= pos)
+		return it->down[pos];
+	if (!create)
+		return NULL;
+
+	pos = -pos-1;
+	if (it->subtree_alloc <= it->subtree_nr) {
+		it->subtree_alloc = alloc_nr(it->subtree_alloc);
+		it->down = xrealloc(it->down, it->subtree_alloc *
+				    sizeof(*it->down));
+	}
+	it->subtree_nr++;
+
+	down = xmalloc(sizeof(*down) + pathlen + 1);
+	down->cache_tree = NULL;
+	down->namelen = pathlen;
+	memcpy(down->name, path, pathlen);
+	down->name[pathlen] = 0;
+
+	if (pos < it->subtree_nr)
+		memmove(it->down + pos + 1,
+			it->down + pos,
+			sizeof(down) * (it->subtree_nr - pos - 1));
+	it->down[pos] = down;
+	return down;
+}
+
+struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path)
+{
+	int pathlen = strlen(path);
+	return find_subtree(it, path, pathlen, 1);
+}
+
+void cache_tree_invalidate_path(struct cache_tree *it, const char *path)
+{
+	/* a/b/c
+	 * ==> invalidate self
+	 * ==> find "a", have it invalidate "b/c"
+	 * a
+	 * ==> invalidate self
+	 * ==> if "a" exists as a subtree, remove it.
+	 */
+	const char *slash;
+	int namelen;
+	struct cache_tree_sub *down;
+
+#if DEBUG
+	fprintf(stderr, "cache-tree invalidate <%s>\n", path);
+#endif
+
+	if (!it)
+		return;
+	slash = strchr(path, '/');
+	it->entry_count = -1;
+	if (!slash) {
+		int pos;
+		namelen = strlen(path);
+		pos = subtree_pos(it, path, namelen);
+		if (0 <= pos) {
+			cache_tree_free(&it->down[pos]->cache_tree);
+			free(it->down[pos]);
+			/* 0 1 2 3 4 5
+			 *       ^     ^subtree_nr = 6
+			 *       pos
+			 * move 4 and 5 up one place (2 entries)
+			 * 2 = 6 - 3 - 1 = subtree_nr - pos - 1
+			 */
+			memmove(it->down+pos, it->down+pos+1,
+				sizeof(struct cache_tree_sub *) *
+				(it->subtree_nr - pos - 1));
+			it->subtree_nr--;
+		}
+		return;
+	}
+	namelen = slash - path;
+	down = find_subtree(it, path, namelen, 0);
+	if (down)
+		cache_tree_invalidate_path(down->cache_tree, slash + 1);
+}
+
+static int verify_cache(struct cache_entry **cache,
+			int entries)
+{
+	int i, funny;
+
+	/* Verify that the tree is merged */
+	funny = 0;
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		if (ce_stage(ce)) {
+			if (10 < ++funny) {
+				fprintf(stderr, "...\n");
+				break;
+			}
+			fprintf(stderr, "%s: unmerged (%s)\n",
+				ce->name, sha1_to_hex(ce->sha1));
+		}
+	}
+	if (funny)
+		return -1;
+
+	/* Also verify that the cache does not have path and path/file
+	 * at the same time.  At this point we know the cache has only
+	 * stage 0 entries.
+	 */
+	funny = 0;
+	for (i = 0; i < entries - 1; i++) {
+		/* path/file always comes after path because of the way
+		 * the cache is sorted.  Also path can appear only once,
+		 * which means conflicting one would immediately follow.
+		 */
+		const char *this_name = cache[i]->name;
+		const char *next_name = cache[i+1]->name;
+		int this_len = strlen(this_name);
+		if (this_len < strlen(next_name) &&
+		    strncmp(this_name, next_name, this_len) == 0 &&
+		    next_name[this_len] == '/') {
+			if (10 < ++funny) {
+				fprintf(stderr, "...\n");
+				break;
+			}
+			fprintf(stderr, "You have both %s and %s\n",
+				this_name, next_name);
+		}
+	}
+	if (funny)
+		return -1;
+	return 0;
+}
+
+static void discard_unused_subtrees(struct cache_tree *it)
+{
+	struct cache_tree_sub **down = it->down;
+	int nr = it->subtree_nr;
+	int dst, src;
+	for (dst = src = 0; src < nr; src++) {
+		struct cache_tree_sub *s = down[src];
+		if (s->used)
+			down[dst++] = s;
+		else {
+			cache_tree_free(&s->cache_tree);
+			free(s);
+			it->subtree_nr--;
+		}
+	}
+}
+
+int cache_tree_fully_valid(struct cache_tree *it)
+{
+	int i;
+	if (!it)
+		return 0;
+	if (it->entry_count < 0 || !has_sha1_file(it->sha1))
+		return 0;
+	for (i = 0; i < it->subtree_nr; i++) {
+		if (!cache_tree_fully_valid(it->down[i]->cache_tree))
+			return 0;
+	}
+	return 1;
+}
+
+static int update_one(struct cache_tree *it,
+		      struct cache_entry **cache,
+		      int entries,
+		      const char *base,
+		      int baselen,
+		      int missing_ok,
+		      int dryrun)
+{
+	unsigned long size, offset;
+	char *buffer;
+	int i;
+
+	if (0 <= it->entry_count && has_sha1_file(it->sha1))
+		return it->entry_count;
+
+	/*
+	 * We first scan for subtrees and update them; we start by
+	 * marking existing subtrees -- the ones that are unmarked
+	 * should not be in the result.
+	 */
+	for (i = 0; i < it->subtree_nr; i++)
+		it->down[i]->used = 0;
+
+	/*
+	 * Find the subtrees and update them.
+	 */
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		struct cache_tree_sub *sub;
+		const char *path, *slash;
+		int pathlen, sublen, subcnt;
+
+		path = ce->name;
+		pathlen = ce_namelen(ce);
+		if (pathlen <= baselen || memcmp(base, path, baselen))
+			break; /* at the end of this level */
+
+		slash = strchr(path + baselen, '/');
+		if (!slash)
+			continue;
+		/*
+		 * a/bbb/c (base = a/, slash = /c)
+		 * ==>
+		 * path+baselen = bbb/c, sublen = 3
+		 */
+		sublen = slash - (path + baselen);
+		sub = find_subtree(it, path + baselen, sublen, 1);
+		if (!sub->cache_tree)
+			sub->cache_tree = cache_tree();
+		subcnt = update_one(sub->cache_tree,
+				    cache + i, entries - i,
+				    path,
+				    baselen + sublen + 1,
+				    missing_ok,
+				    dryrun);
+		i += subcnt - 1;
+		sub->used = 1;
+	}
+
+	discard_unused_subtrees(it);
+
+	/*
+	 * Then write out the tree object for this level.
+	 */
+	size = 8192;
+	buffer = xmalloc(size);
+	offset = 0;
+
+	for (i = 0; i < entries; i++) {
+		struct cache_entry *ce = cache[i];
+		struct cache_tree_sub *sub;
+		const char *path, *slash;
+		int pathlen, entlen;
+		const unsigned char *sha1;
+		unsigned mode;
+
+		path = ce->name;
+		pathlen = ce_namelen(ce);
+		if (pathlen <= baselen || memcmp(base, path, baselen))
+			break; /* at the end of this level */
+
+		slash = strchr(path + baselen, '/');
+		if (slash) {
+			entlen = slash - (path + baselen);
+			sub = find_subtree(it, path + baselen, entlen, 0);
+			if (!sub)
+				die("cache-tree.c: '%.*s' in '%s' not found",
+				    entlen, path + baselen, path);
+			i += sub->cache_tree->entry_count - 1;
+			sha1 = sub->cache_tree->sha1;
+			mode = S_IFDIR;
+		}
+		else {
+			sha1 = ce->sha1;
+			mode = ntohl(ce->ce_mode);
+			entlen = pathlen - baselen;
+		}
+		if (!missing_ok && !has_sha1_file(sha1))
+			return error("invalid object %s", sha1_to_hex(sha1));
+
+		if (!ce->ce_mode)
+			continue; /* entry being removed */
+
+		if (size < offset + entlen + 100) {
+			size = alloc_nr(offset + entlen + 100);
+			buffer = xrealloc(buffer, size);
+		}
+		offset += sprintf(buffer + offset,
+				  "%o %.*s", mode, entlen, path + baselen);
+		buffer[offset++] = 0;
+		memcpy(buffer + offset, sha1, 20);
+		offset += 20;
+
+#if DEBUG
+		fprintf(stderr, "cache-tree update-one %o %.*s\n",
+			mode, entlen, path + baselen);
+#endif
+	}
+
+	if (dryrun) {
+		unsigned char hdr[200];
+		int hdrlen;
+		write_sha1_file_prepare(buffer, offset, tree_type, it->sha1,
+					hdr, &hdrlen);
+	}
+	else
+		write_sha1_file(buffer, offset, tree_type, it->sha1);
+	free(buffer);
+	it->entry_count = i;
+#if DEBUG
+	fprintf(stderr, "cache-tree update-one (%d ent, %d subtree) %s\n",
+		it->entry_count, it->subtree_nr,
+		sha1_to_hex(it->sha1));
+#endif
+	return i;
+}
+
+int cache_tree_update(struct cache_tree *it,
+		      struct cache_entry **cache,
+		      int entries,
+		      int missing_ok,
+		      int dryrun)
+{
+	int i;
+	i = verify_cache(cache, entries);
+	if (i)
+		return i;
+	i = update_one(it, cache, entries, "", 0, missing_ok, dryrun);
+	if (i < 0)
+		return i;
+	return 0;
+}
+
+static void *write_one(struct cache_tree *it,
+		       char *path,
+		       int pathlen,
+		       char *buffer,
+		       unsigned long *size,
+		       unsigned long *offset)
+{
+	int i;
+
+	/* One "cache-tree" entry consists of the following:
+	 * path (NUL terminated)
+	 * entry_count, subtree_nr ("%d %d\n")
+	 * tree-sha1 (missing if invalid)
+	 * subtree_nr "cache-tree" entries for subtrees.
+	 */
+	if (*size < *offset + pathlen + 100) {
+		*size = alloc_nr(*offset + pathlen + 100);
+		buffer = xrealloc(buffer, *size);
+	}
+	*offset += sprintf(buffer + *offset, "%.*s%c%d %d\n",
+			   pathlen, path, 0,
+			   it->entry_count, it->subtree_nr);
+
+#if DEBUG
+	if (0 <= it->entry_count)
+		fprintf(stderr, "cache-tree <%.*s> (%d ent, %d subtree) %s\n",
+			pathlen, path, it->entry_count, it->subtree_nr,
+			sha1_to_hex(it->sha1));
+	else
+		fprintf(stderr, "cache-tree <%.*s> (%d subtree) invalid\n",
+			pathlen, path, it->subtree_nr);
+#endif
+
+	if (0 <= it->entry_count) {
+		memcpy(buffer + *offset, it->sha1, 20);
+		*offset += 20;
+	}
+	for (i = 0; i < it->subtree_nr; i++) {
+		struct cache_tree_sub *down = it->down[i];
+		if (i) {
+			struct cache_tree_sub *prev = it->down[i-1];
+			if (subtree_name_cmp(down->name, down->namelen,
+					     prev->name, prev->namelen) <= 0)
+				die("fatal - unsorted cache subtree");
+		}
+		buffer = write_one(down->cache_tree, down->name, down->namelen,
+				   buffer, size, offset);
+	}
+	return buffer;
+}
+
+void *cache_tree_write(struct cache_tree *root, unsigned long *size_p)
+{
+	char path[PATH_MAX];
+	unsigned long size = 8192;
+	char *buffer = xmalloc(size);
+
+	*size_p = 0;
+	path[0] = 0;
+	return write_one(root, path, 0, buffer, &size, size_p);
+}
+
+static struct cache_tree *read_one(const char **buffer, unsigned long *size_p)
+{
+	const char *buf = *buffer;
+	unsigned long size = *size_p;
+	const char *cp;
+	char *ep;
+	struct cache_tree *it;
+	int i, subtree_nr;
+
+	it = NULL;
+	/* skip name, but make sure name exists */
+	while (size && *buf) {
+		size--;
+		buf++;
+	}
+	if (!size)
+		goto free_return;
+	buf++; size--;
+	it = cache_tree();
+
+	cp = buf;
+	it->entry_count = strtol(cp, &ep, 10);
+	if (cp == ep)
+		goto free_return;
+	cp = ep;
+	subtree_nr = strtol(cp, &ep, 10);
+	if (cp == ep)
+		goto free_return;
+	while (size && *buf && *buf != '\n') {
+		size--;
+		buf++;
+	}
+	if (!size)
+		goto free_return;
+	buf++; size--;
+	if (0 <= it->entry_count) {
+		if (size < 20)
+			goto free_return;
+		memcpy(it->sha1, buf, 20);
+		buf += 20;
+		size -= 20;
+	}
+
+#if DEBUG
+	if (0 <= it->entry_count)
+		fprintf(stderr, "cache-tree <%s> (%d ent, %d subtree) %s\n",
+			*buffer, it->entry_count, subtree_nr,
+			sha1_to_hex(it->sha1));
+	else
+		fprintf(stderr, "cache-tree <%s> (%d subtrees) invalid\n",
+			*buffer, subtree_nr);
+#endif
+
+	/*
+	 * Just a heuristic -- we do not add directories that often but
+	 * we do not want to have to extend it immediately when we do,
+	 * hence +2.
+	 */
+	it->subtree_alloc = subtree_nr + 2;
+	it->down = xcalloc(it->subtree_alloc, sizeof(struct cache_tree_sub *));
+	for (i = 0; i < subtree_nr; i++) {
+		/* read each subtree */
+		struct cache_tree *sub;
+		struct cache_tree_sub *subtree;
+		const char *name = buf;
+
+		sub = read_one(&buf, &size);
+		if (!sub)
+			goto free_return;
+		subtree = cache_tree_sub(it, name);
+		subtree->cache_tree = sub;
+	}
+	if (subtree_nr != it->subtree_nr)
+		die("cache-tree: internal error");
+	*buffer = buf;
+	*size_p = size;
+	return it;
+
+ free_return:
+	cache_tree_free(&it);
+	return NULL;
+}
+
+struct cache_tree *cache_tree_read(const char *buffer, unsigned long size)
+{
+	if (buffer[0])
+		return NULL; /* not the whole tree */
+	return read_one(&buffer, &size);
+}
+
+struct cache_tree *cache_tree_find(struct cache_tree *it, const char *path)
+{
+	while (*path) {
+		const char *slash;
+		struct cache_tree_sub *sub;
+
+		slash = strchr(path, '/');
+		if (!slash)
+			slash = path + strlen(path);
+		/* between path and slash is the name of the
+		 * subtree to look for.
+		 */
+		sub = find_subtree(it, path, slash - path, 0);
+		if (!sub)
+			return NULL;
+		it = sub->cache_tree;
+		if (slash)
+			while (*slash && *slash == '/')
+				slash++;
+		if (!slash || !*slash)
+			return it; /* prefix ended with slashes */
+		path = slash;
+	}
+	return it;
+}
diff --git a/cache-tree.h b/cache-tree.h
new file mode 100644
index 0000000000..119407e3a1
--- /dev/null
+++ b/cache-tree.h
@@ -0,0 +1,33 @@
+#ifndef CACHE_TREE_H
+#define CACHE_TREE_H
+
+struct cache_tree;
+struct cache_tree_sub {
+	struct cache_tree *cache_tree;
+	int namelen;
+	int used;
+	char name[FLEX_ARRAY];
+};
+
+struct cache_tree {
+	int entry_count; /* negative means "invalid" */
+	unsigned char sha1[20];
+	int subtree_nr;
+	int subtree_alloc;
+	struct cache_tree_sub **down;
+};
+
+struct cache_tree *cache_tree(void);
+void cache_tree_free(struct cache_tree **);
+void cache_tree_invalidate_path(struct cache_tree *, const char *);
+struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
+
+void *cache_tree_write(struct cache_tree *root, unsigned long *size_p);
+struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
+
+int cache_tree_fully_valid(struct cache_tree *);
+int cache_tree_update(struct cache_tree *, struct cache_entry **, int, int, int);
+
+struct cache_tree *cache_tree_find(struct cache_tree *, const char *);
+
+#endif
diff --git a/cache.h b/cache.h
index 4b7a439253..b1300cd989 100644
--- a/cache.h
+++ b/cache.h
@@ -114,6 +114,7 @@ static inline unsigned int create_ce_mode(unsigned int mode)
 
 extern struct cache_entry **active_cache;
 extern unsigned int active_nr, active_alloc, active_cache_changed;
+extern struct cache_tree *active_cache_tree;
 
 #define GIT_DIR_ENVIRONMENT "GIT_DIR"
 #define DEFAULT_GIT_DIR_ENVIRONMENT ".git"
@@ -251,6 +252,7 @@ extern void *read_object_with_reference(const unsigned char *sha1,
 					unsigned char *sha1_ret);
 
 const char *show_date(unsigned long time, int timezone);
+const char *show_rfc2822_date(unsigned long time, int timezone);
 int parse_date(const char *date, char *buf, int bufsize);
 void datestamp(char *buf, int bufsize);
 unsigned long approxidate(const char *);
diff --git a/checkout-index.c b/checkout-index.c
index cc3a745c14..9876af6fd6 100644
--- a/checkout-index.c
+++ b/checkout-index.c
@@ -39,6 +39,7 @@
 #include "cache.h"
 #include "strbuf.h"
 #include "quote.h"
+#include "cache-tree.h"
 
 #define CHECKOUT_ALL 4
 static const char *prefix;
diff --git a/commit.c b/commit.c
index 2717dd81c3..93b3903ea7 100644
--- a/commit.c
+++ b/commit.c
@@ -36,6 +36,8 @@ enum cmit_fmt get_commit_format(const char *arg)
 		return CMIT_FMT_FULL;
 	if (!strcmp(arg, "=fuller"))
 		return CMIT_FMT_FULLER;
+	if (!strcmp(arg, "=email"))
+		return CMIT_FMT_EMAIL;
 	if (!strcmp(arg, "=oneline"))
 		return CMIT_FMT_ONELINE;
 	die("invalid --pretty format");
@@ -428,6 +430,10 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c
 	time = strtoul(date, &date, 10);
 	tz = strtol(date, NULL, 10);
 
+	if (fmt == CMIT_FMT_EMAIL) {
+		what = "From";
+		filler = "";
+	}
 	ret = sprintf(buf, "%s: %.*s%.*s\n", what,
 		      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
 		      filler, namelen, line);
@@ -435,6 +441,10 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c
 	case CMIT_FMT_MEDIUM:
 		ret += sprintf(buf + ret, "Date:   %s\n", show_date(time, tz));
 		break;
+	case CMIT_FMT_EMAIL:
+		ret += sprintf(buf + ret, "Date: %s\n",
+			       show_rfc2822_date(time, tz));
+		break;
 	case CMIT_FMT_FULLER:
 		ret += sprintf(buf + ret, "%sDate: %s\n", what, show_date(time, tz));
 		break;
@@ -445,10 +455,12 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const c
 	return ret;
 }
 
-static int is_empty_line(const char *line, int len)
+static int is_empty_line(const char *line, int *len_p)
 {
+	int len = *len_p;
 	while (len && isspace(line[len-1]))
 		len--;
+	*len_p = len;
 	return !len;
 }
 
@@ -457,7 +469,8 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com
 	struct commit_list *parent = commit->parents;
 	int offset;
 
-	if ((fmt == CMIT_FMT_ONELINE) || !parent || !parent->next)
+	if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) ||
+	    !parent || !parent->next)
 		return 0;
 
 	offset = sprintf(buf, "Merge:");
@@ -476,14 +489,17 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com
 	return offset;
 }
 
-unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev)
+unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject)
 {
 	int hdr = 1, body = 0;
 	unsigned long offset = 0;
-	int indent = (fmt == CMIT_FMT_ONELINE) ? 0 : 4;
+	int indent = 4;
 	int parents_shown = 0;
 	const char *msg = commit->buffer;
 
+	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
+		indent = 0;
+
 	for (;;) {
 		const char *line = msg;
 		int linelen = get_one_line(msg, len);
@@ -506,7 +522,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 		if (hdr) {
 			if (linelen == 1) {
 				hdr = 0;
-				if (fmt != CMIT_FMT_ONELINE)
+				if ((fmt != CMIT_FMT_ONELINE) && !subject)
 					buf[offset++] = '\n';
 				continue;
 			}
@@ -544,20 +560,29 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 			continue;
 		}
 
-		if (is_empty_line(line, linelen)) {
+		if (is_empty_line(line, &linelen)) {
 			if (!body)
 				continue;
+			if (subject)
+				continue;
 			if (fmt == CMIT_FMT_SHORT)
 				break;
 		} else {
 			body = 1;
 		}
 
+		if (subject) {
+			int slen = strlen(subject);
+			memcpy(buf + offset, subject, slen);
+			offset += slen;
+		}
 		memset(buf + offset, ' ', indent);
 		memcpy(buf + offset + indent, line, linelen);
 		offset += linelen + indent;
+		buf[offset++] = '\n';
 		if (fmt == CMIT_FMT_ONELINE)
 			break;
+		subject = NULL;
 	}
 	while (offset && isspace(buf[offset-1]))
 		offset--;
diff --git a/commit.h b/commit.h
index de142afe73..8d7514cd00 100644
--- a/commit.h
+++ b/commit.h
@@ -45,12 +45,13 @@ enum cmit_fmt {
 	CMIT_FMT_FULL,
 	CMIT_FMT_FULLER,
 	CMIT_FMT_ONELINE,
+	CMIT_FMT_EMAIL,
 
 	CMIT_FMT_UNSPECIFIED,
 };
 
 extern enum cmit_fmt get_commit_format(const char *arg);
-extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev);
+extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char *buf, unsigned long space, int abbrev, const char *subject);
 
 /** Removes the first commit from a list sorted by date, and adds all
  * of its parents.
diff --git a/contrib/remotes2config.sh b/contrib/remotes2config.sh
new file mode 100644
index 0000000000..25901e2b3b
--- /dev/null
+++ b/contrib/remotes2config.sh
@@ -0,0 +1,35 @@
+#!/bin/sh
+
+# Use this tool to rewrite your .git/remotes/ files into the config.
+
+. git-sh-setup
+
+if [ -d "$GIT_DIR"/remotes ]; then
+	echo "Rewriting $GIT_DIR/remotes" >&2
+	error=0
+	# rewrite into config
+	{
+		cd "$GIT_DIR"/remotes
+		ls | while read f; do
+			name=$(echo -n "$f" | tr -c "A-Za-z0-9" ".")
+			sed -n \
+			-e "s/^URL: \(.*\)$/remote.$name.url \1 ./p" \
+			-e "s/^Pull: \(.*\)$/remote.$name.fetch \1 ^$ /p" \
+			-e "s/^Push: \(.*\)$/remote.$name.push \1 ^$ /p" \
+			< "$f"
+		done
+		echo done
+	} | while read key value regex; do
+		case $key in
+		done)
+			if [ $error = 0 ]; then
+				mv "$GIT_DIR"/remotes "$GIT_DIR"/remotes.old
+			fi ;;
+		*)
+			echo "git-repo-config $key "$value" $regex"
+			git-repo-config $key "$value" $regex || error=1 ;;
+		esac
+	done
+fi
+
+
diff --git a/date.c b/date.c
index 034d7228bf..365dc3b14e 100644
--- a/date.c
+++ b/date.c
@@ -42,18 +42,24 @@ static const char *weekday_names[] = {
  * thing, which means that tz -0100 is passed in as the integer -100,
  * even though it means "sixty minutes off"
  */
-const char *show_date(unsigned long time, int tz)
+static struct tm *time_to_tm(unsigned long time, int tz)
 {
-	struct tm *tm;
 	time_t t;
-	static char timebuf[200];
 	int minutes;
 
 	minutes = tz < 0 ? -tz : tz;
 	minutes = (minutes / 100)*60 + (minutes % 100);
 	minutes = tz < 0 ? -minutes : minutes;
 	t = time + minutes * 60;
-	tm = gmtime(&t);
+	return gmtime(&t);
+}
+
+const char *show_date(unsigned long time, int tz)
+{
+	struct tm *tm;
+	static char timebuf[200];
+
+	tm = time_to_tm(time, tz);
 	if (!tm)
 		return NULL;
 	sprintf(timebuf, "%.3s %.3s %d %02d:%02d:%02d %d %+05d",
@@ -65,6 +71,21 @@ const char *show_date(unsigned long time, int tz)
 	return timebuf;
 }
 
+const char *show_rfc2822_date(unsigned long time, int tz)
+{
+	struct tm *tm;
+	static char timebuf[200];
+
+	tm = time_to_tm(time, tz);
+	if (!tm)
+		return NULL;
+	sprintf(timebuf, "%.3s, %d %.3s %d %02d:%02d:%02d %+05d",
+		weekday_names[tm->tm_wday], tm->tm_mday,
+		month_names[tm->tm_mon], tm->tm_year + 1900,
+		tm->tm_hour, tm->tm_min, tm->tm_sec, tz);
+	return timebuf;
+}
+
 /*
  * Check these. And note how it doesn't do the summer-time conversion.
  *
diff --git a/dump-cache-tree.c b/dump-cache-tree.c
new file mode 100644
index 0000000000..1ccaf51773
--- /dev/null
+++ b/dump-cache-tree.c
@@ -0,0 +1,64 @@
+#include "cache.h"
+#include "tree.h"
+#include "cache-tree.h"
+
+
+static void dump_one(struct cache_tree *it, const char *pfx, const char *x)
+{
+	if (it->entry_count < 0)
+		printf("%-40s %s%s (%d subtrees)\n",
+		       "invalid", x, pfx, it->subtree_nr);
+	else
+		printf("%s %s%s (%d entries, %d subtrees)\n",
+		       sha1_to_hex(it->sha1), x, pfx,
+		       it->entry_count, it->subtree_nr);
+}
+
+static int dump_cache_tree(struct cache_tree *it,
+			   struct cache_tree *ref,
+			   const char *pfx)
+{
+	int i;
+	int errs = 0;
+
+	if (!it || !ref)
+		/* missing in either */
+		return 0;
+
+	if (it->entry_count < 0) {
+		dump_one(it, pfx, "");
+		dump_one(ref, pfx, "#(ref) ");
+		if (it->subtree_nr != ref->subtree_nr)
+			errs = 1;
+	}
+	else {
+		dump_one(it, pfx, "");
+		if (memcmp(it->sha1, ref->sha1, 20) ||
+		    ref->entry_count != it->entry_count ||
+		    ref->subtree_nr != it->subtree_nr) {
+			dump_one(ref, pfx, "#(ref) ");
+			errs = 1;
+		}
+	}
+
+	for (i = 0; i < it->subtree_nr; i++) {
+		char path[PATH_MAX];
+		struct cache_tree_sub *down = it->down[i];
+		struct cache_tree_sub *rdwn;
+
+		rdwn = cache_tree_sub(ref, down->name);
+		sprintf(path, "%s%.*s/", pfx, down->namelen, down->name);
+		if (dump_cache_tree(down->cache_tree, rdwn->cache_tree, path))
+			errs = 1;
+	}
+	return errs;
+}
+
+int main(int ac, char **av)
+{
+	struct cache_tree *another = cache_tree();
+	if (read_cache() < 0)
+		die("unable to read index file");
+	cache_tree_update(another, active_cache, active_nr, 0, 1);
+	return dump_cache_tree(active_cache_tree, another, "");
+}
diff --git a/fsck-objects.c b/fsck-objects.c
index 59b25904cb..1922b6d84c 100644
--- a/fsck-objects.c
+++ b/fsck-objects.c
@@ -8,6 +8,7 @@
 #include "tag.h"
 #include "refs.h"
 #include "pack.h"
+#include "cache-tree.h"
 
 #define REACHABLE 0x0001
 
@@ -438,6 +439,28 @@ static int fsck_head_link(void)
 	return 0;
 }
 
+static int fsck_cache_tree(struct cache_tree *it)
+{
+	int i;
+	int err = 0;
+
+	if (0 <= it->entry_count) {
+		struct object *obj = parse_object(it->sha1);
+		if (!obj) {
+			error("%s: invalid sha1 pointer in cache-tree",
+			      sha1_to_hex(it->sha1));
+			return 1;
+		}
+		mark_reachable(obj, REACHABLE);
+		obj->used = 1;
+		if (obj->type != tree_type)
+			err |= objerror(obj, "non-tree in cache-tree");
+	}
+	for (i = 0; i < it->subtree_nr; i++)
+		err |= fsck_cache_tree(it->down[i]->cache_tree);
+	return err;
+}
+
 int main(int argc, char **argv)
 {
 	int i, heads;
@@ -547,6 +570,8 @@ int main(int argc, char **argv)
 			obj->used = 1;
 			mark_reachable(obj, REACHABLE);
 		}
+		if (active_cache_tree)
+			fsck_cache_tree(active_cache_tree);
 	}
 
 	check_connectivity();
diff --git a/git-cvsexportcommit.perl b/git-cvsexportcommit.perl
index 7b3a3d323b..f994443c6f 100755
--- a/git-cvsexportcommit.perl
+++ b/git-cvsexportcommit.perl
@@ -10,9 +10,9 @@
     die "GIT_DIR is not defined or is unreadable";
 }
 
-our ($opt_h, $opt_p, $opt_v, $opt_c );
+our ($opt_h, $opt_p, $opt_v, $opt_c, $opt_f, $opt_m );
 
-getopts('hpvc');
+getopts('hpvcfm:');
 
 $opt_h && usage();
 
@@ -77,12 +77,16 @@
 $opt_v && print "Applying to CVS commit $commit from parent $parent\n";
 
 # grab the commit message
-`git-cat-file commit $commit | sed -e '1,/^\$/d' > .msg`;
+open(MSG, ">.msg") or die "Cannot open .msg for writing";
+print MSG $opt_m;
+close MSG;
+
+`git-cat-file commit $commit | sed -e '1,/^\$/d' >> .msg`;
 $? && die "Error extracting the commit message";
 
 my (@afiles, @dfiles, @mfiles);
 my @files = safe_pipe_capture('git-diff-tree', '-r', $parent, $commit);
-print @files;
+#print @files;
 $? && die "Error in git-diff-tree";
 foreach my $f (@files) {
     chomp $f;
@@ -109,7 +113,7 @@
     if (@status > 1) { warn 'Strange! cvs status returned more than one line?'};
     unless ($status[0] =~ m/Status: Unknown$/) {
  	$dirty = 1;
-	warn "File $f is already known in your CVS checkout!\n";
+	warn "File $f is already known in your CVS checkout -- perhaps it has been added by another user. Or this may indicate that it exists on a different branch. If this is the case, use -f to force the merge.\n";
     }
 }
 foreach my $f (@mfiles, @dfiles) {
@@ -122,7 +126,11 @@
     }
 }
 if ($dirty) {
-    die "Exiting: your CVS tree is not clean for this merge.";
+    if ($opt_f) {	warn "The tree is not clean -- forced merge\n";
+	$dirty = 0;
+    } else {
+	die "Exiting: your CVS tree is not clean for this merge.";
+    }
 }
 
 ###
@@ -215,7 +223,7 @@
 }
 sub usage {
 	print STDERR <<END;
-Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [ parent ] commit
+Usage: GIT_DIR=/path/to/.git ${\basename $0} [-h] [-p] [-v] [-c] [-f] [-m msgprefix] [ parent ] commit
 END
 	exit(1);
 }
diff --git a/git-cvsserver.perl b/git-cvsserver.perl
index ffd9c66f94..5ccca4f99f 100755
--- a/git-cvsserver.perl
+++ b/git-cvsserver.perl
@@ -214,8 +214,7 @@ sub req_Globaloption
 {
     my ( $cmd, $data ) = @_;
     $log->debug("req_Globaloption : $data");
-
-    # TODO : is this data useful ???
+    $state->{globaloptions}{$data} = 1;
 }
 
 # Valid-responses request-list \n
@@ -267,12 +266,32 @@ sub req_Directory
 
     $state->{localdir} = $data;
     $state->{repository} = $repository;
-    $state->{directory} = $repository;
-    $state->{directory} =~ s/^$state->{CVSROOT}\///;
-    $state->{module} = $1 if ($state->{directory} =~ s/^(.*?)(\/|$)//);
+    $state->{path} = $repository;
+    $state->{path} =~ s/^$state->{CVSROOT}\///;
+    $state->{module} = $1 if ($state->{path} =~ s/^(.*?)(\/|$)//);
+    $state->{path} .= "/" if ( $state->{path} =~ /\S/ );
+
+    $state->{directory} = $state->{localdir};
+    $state->{directory} = "" if ( $state->{directory} eq "." );
     $state->{directory} .= "/" if ( $state->{directory} =~ /\S/ );
 
-    $log->debug("req_Directory : localdir=$data repository=$repository directory=$state->{directory} module=$state->{module}");
+    if ( not defined($state->{prependdir}) and $state->{localdir} eq "." and $state->{path} =~ /\S/ )
+    {
+        $log->info("Setting prepend to '$state->{path}'");
+        $state->{prependdir} = $state->{path};
+        foreach my $entry ( keys %{$state->{entries}} )
+        {
+            $state->{entries}{$state->{prependdir} . $entry} = $state->{entries}{$entry};
+            delete $state->{entries}{$entry};
+        }
+    }
+
+    if ( defined ( $state->{prependdir} ) )
+    {
+        $log->debug("Prepending '$state->{prependdir}' to state|directory");
+        $state->{directory} = $state->{prependdir} . $state->{directory}
+    }
+    $log->debug("req_Directory : localdir=$data repository=$repository path=$state->{path} directory=$state->{directory} module=$state->{module}");
 }
 
 # Entry entry-line \n
@@ -290,7 +309,7 @@ sub req_Entry
 {
     my ( $cmd, $data ) = @_;
 
-    $log->debug("req_Entry : $data");
+    #$log->debug("req_Entry : $data");
 
     my @data = split(/\//, $data);
 
@@ -300,6 +319,22 @@ sub req_Entry
         options     => $data[4],
         tag_or_date => $data[5],
     };
+
+    $log->info("Received entry line '$data' => '" . $state->{directory} . $data[1] . "'");
+}
+
+# Questionable filename \n
+#     Response expected: no. Additional data: no. Tell the server to check
+#     whether filename should be ignored, and if not, next time the server
+#     sends responses, send (in a M response) `?' followed by the directory and
+#     filename. filename must not contain `/'; it needs to be a file in the
+#     directory named by the most recent Directory request.
+sub req_Questionable
+{
+    my ( $cmd, $data ) = @_;
+
+    $log->debug("req_Questionable : $data");
+    $state->{entries}{$state->{directory}.$data}{questionable} = 1;
 }
 
 # add \n
@@ -332,8 +367,7 @@ sub req_add
             next;
         }
 
-
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         print "E cvs add: scheduling file `$filename' for addition\n";
 
@@ -414,7 +448,7 @@ sub req_remove
         }
 
 
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         print "E cvs remove: scheduling `$filename' for removal\n";
 
@@ -502,22 +536,6 @@ sub req_Unchanged
     #$log->debug("req_Unchanged : $data");
 }
 
-# Questionable filename \n
-#     Response expected: no. Additional data: no.
-#     Tell the server to check whether filename should be ignored,
-#     and if not, next time the server sends responses, send (in
-#     a M response) `?' followed by the directory and filename.
-#     filename must not contain `/'; it needs to be a file in the
-#     directory named by the most recent Directory request.
-sub req_Questionable
-{
-    my ( $cmd, $data ) = @_;
-
-    $state->{entries}{$state->{directory}.$data}{questionable} = 1;
-
-    #$log->debug("req_Questionable : $data");
-}
-
 # Argument text \n
 #     Response expected: no. Save argument for use in a subsequent command.
 #     Arguments accumulate until an argument-using command is given, at which
@@ -757,8 +775,7 @@ sub req_update
 
     $updater->update();
 
-    # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     #$log->debug("update state : " . Dumper($state));
 
@@ -767,6 +784,8 @@ sub req_update
     {
         $filename = filecleanup($filename);
 
+        $log->debug("Processing file $filename");
+
         # if we have a -C we should pretend we never saw modified stuff
         if ( exists ( $state->{opt}{C} ) )
         {
@@ -821,13 +840,16 @@ sub req_update
 
         if ( $meta->{filehash} eq "deleted" )
         {
-            my ( $filepart, $dirpart ) = filenamesplit($filename);
+            my ( $filepart, $dirpart ) = filenamesplit($filename,1);
 
             $log->info("Removing '$filename' from working copy (no longer in the repo)");
 
             print "E cvs update: `$filename' is no longer in the repository\n";
-            print "Removed $dirpart\n";
-            print "$filepart\n";
+            # Don't want to actually _DO_ the update if -n specified
+            unless ( $state->{globaloptions}{-n} ) {
+		print "Removed $dirpart\n";
+		print "$filepart\n";
+	    }
         }
         elsif ( not defined ( $state->{entries}{$filename}{modified_hash} )
 		or $state->{entries}{$filename}{modified_hash} eq $oldmeta->{filehash} )
@@ -840,34 +862,42 @@ sub req_update
             print "MT newline\n";
             print "MT -updated\n";
 
-            my ( $filepart, $dirpart ) = filenamesplit($filename);
-            $dirpart =~ s/^$state->{directory}//;
-
-            if ( defined ( $wrev ) )
-            {
-                # instruct client we're sending a file to put in this path as a replacement
-                print "Update-existing $dirpart\n";
-                $log->debug("Updating existing file 'Update-existing $dirpart'");
-            } else {
-                # instruct client we're sending a file to put in this path as a new file
-                print "Created $dirpart\n";
-                $log->debug("Creating new file 'Created $dirpart'");
-            }
-            print $state->{CVSROOT} . "/$state->{module}/$filename\n";
-
-            # this is an "entries" line
-            $log->debug("/$filepart/1.$meta->{revision}///");
-            print "/$filepart/1.$meta->{revision}///\n";
-
-            # permissions
-            $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
-            print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
-
-            # transmit file
-            transmitfile($meta->{filehash});
+            my ( $filepart, $dirpart ) = filenamesplit($filename,1);
+
+	    # Don't want to actually _DO_ the update if -n specified
+	    unless ( $state->{globaloptions}{-n} )
+	    {
+		if ( defined ( $wrev ) )
+		{
+		    # instruct client we're sending a file to put in this path as a replacement
+		    print "Update-existing $dirpart\n";
+		    $log->debug("Updating existing file 'Update-existing $dirpart'");
+		} else {
+		    # instruct client we're sending a file to put in this path as a new file
+		    print "Clear-static-directory $dirpart\n";
+		    print $state->{CVSROOT} . "/$state->{module}/$dirpart\n";
+		    print "Clear-sticky $dirpart\n";
+		    print $state->{CVSROOT} . "/$state->{module}/$dirpart\n";
+
+		    $log->debug("Creating new file 'Created $dirpart'");
+		    print "Created $dirpart\n";
+		}
+		print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+
+		# this is an "entries" line
+		$log->debug("/$filepart/1.$meta->{revision}///");
+		print "/$filepart/1.$meta->{revision}///\n";
+
+		# permissions
+		$log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
+		print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
+
+		# transmit file
+		transmitfile($meta->{filehash});
+	    }
         } else {
             $log->info("Updating '$filename'");
-            my ( $filepart, $dirpart ) = filenamesplit($meta->{name});
+            my ( $filepart, $dirpart ) = filenamesplit($meta->{name},1);
 
             my $dir = tempdir( DIR => $TEMP_DIR, CLEANUP => 1 ) . "/";
 
@@ -892,19 +922,29 @@ sub req_update
                 $log->info("Merged successfully");
                 print "M M $filename\n";
                 $log->debug("Update-existing $dirpart");
-                print "Update-existing $dirpart\n";
-                $log->debug($state->{CVSROOT} . "/$state->{module}/$filename");
-                print $state->{CVSROOT} . "/$state->{module}/$filename\n";
-                $log->debug("/$filepart/1.$meta->{revision}///");
-                print "/$filepart/1.$meta->{revision}///\n";
+
+                # Don't want to actually _DO_ the update if -n specified
+                unless ( $state->{globaloptions}{-n} )
+                {
+                    print "Update-existing $dirpart\n";
+                    $log->debug($state->{CVSROOT} . "/$state->{module}/$filename");
+                    print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+                    $log->debug("/$filepart/1.$meta->{revision}///");
+                    print "/$filepart/1.$meta->{revision}///\n";
+                }
             }
             elsif ( $return == 1 )
             {
                 $log->info("Merged with conflicts");
                 print "M C $filename\n";
-                print "Update-existing $dirpart\n";
-                print $state->{CVSROOT} . "/$state->{module}/$filename\n";
-                print "/$filepart/1.$meta->{revision}/+//\n";
+
+                # Don't want to actually _DO_ the update if -n specified
+                unless ( $state->{globaloptions}{-n} )
+                {
+                    print "Update-existing $dirpart\n";
+                    print $state->{CVSROOT} . "/$state->{module}/$filename\n";
+                    print "/$filepart/1.$meta->{revision}/+//\n";
+                }
             }
             else
             {
@@ -912,17 +952,21 @@ sub req_update
                 next;
             }
 
-            # permissions
-            $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
-            print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
-
-            # transmit file, format is single integer on a line by itself (file
-            # size) followed by the file contents
-            # TODO : we should copy files in blocks
-            my $data = `cat $file_local`;
-            $log->debug("File size : " . length($data));
-            print length($data) . "\n";
-            print $data;
+            # Don't want to actually _DO_ the update if -n specified
+            unless ( $state->{globaloptions}{-n} )
+            {
+                # permissions
+                $log->debug("SEND : u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}");
+                print "u=$meta->{mode},g=$meta->{mode},o=$meta->{mode}\n";
+
+                # transmit file, format is single integer on a line by itself (file
+                # size) followed by the file contents
+                # TODO : we should copy files in blocks
+                my $data = `cat $file_local`;
+                $log->debug("File size : " . length($data));
+                print length($data) . "\n";
+                print $data;
+            }
 
             chdir "/";
         }
@@ -950,6 +994,7 @@ sub req_ci
 
     if ( -e $state->{CVSROOT} . "/index" )
     {
+        $log->warn("file 'index' already exists in the git repository");
         print "error 1 Index already exists in git repo\n";
         exit;
     }
@@ -957,6 +1002,7 @@ sub req_ci
     my $lockfile = "$state->{CVSROOT}/refs/heads/$state->{module}.lock";
     unless ( sysopen(LOCKFILE,$lockfile,O_EXCL|O_CREAT|O_WRONLY) )
     {
+        $log->warn("lockfile '$lockfile' already exists, please try again");
         print "error 1 Lock file '$lockfile' already exists, please try again\n";
         exit;
     }
@@ -988,6 +1034,7 @@ sub req_ci
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
     {
+        my $committedfile = $filename;
         $filename = filecleanup($filename);
 
         next unless ( exists $state->{entries}{$filename}{modified_filename} or not $state->{entries}{$filename}{unchanged} );
@@ -1022,7 +1069,7 @@ sub req_ci
             exit;
         }
 
-        push @committedfiles, $filename;
+        push @committedfiles, $committedfile;
         $log->info("Committing $filename");
 
         system("mkdir","-p",$dirpart) unless ( -d $dirpart );
@@ -1105,7 +1152,7 @@ sub req_ci
 
         my $meta = $updater->getmeta($filename);
 
-        my ( $filepart, $dirpart ) = filenamesplit($filename);
+        my ( $filepart, $dirpart ) = filenamesplit($filename, 1);
 
         $log->debug("Checked-in $dirpart : $filename");
 
@@ -1141,7 +1188,7 @@ sub req_status
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1242,7 +1289,7 @@ sub req_diff
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1384,7 +1431,7 @@ sub req_log
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing status on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # foreach file specified on the commandline ...
     foreach my $filename ( @{$state->{args}} )
@@ -1460,7 +1507,7 @@ sub req_annotate
     $updater->update();
 
     # if no files were specified, we need to work out what files we should be providing annotate on ...
-    argsfromdir($updater) if ( scalar ( @{$state->{args}} ) == 0 );
+    argsfromdir($updater);
 
     # we'll need a temporary checkout dir
     my $tmpdir = tempdir ( DIR => $TEMP_DIR );
@@ -1655,13 +1702,36 @@ sub argsfromdir
 {
     my $updater = shift;
 
-    $state->{args} = [];
+    $state->{args} = [] if ( scalar(@{$state->{args}}) == 1 and $state->{args}[0] eq "." );
+
+    return if ( scalar ( @{$state->{args}} ) > 1 );
 
-    foreach my $file ( @{$updater->gethead} )
+    if ( scalar(@{$state->{args}}) == 1 )
     {
-        next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
-        next unless ( $file->{name} =~ s/^$state->{directory}// );
-        push @{$state->{args}}, $file->{name};
+        my $arg = $state->{args}[0];
+        $arg .= $state->{prependdir} if ( defined ( $state->{prependdir} ) );
+
+        $log->info("Only one arg specified, checking for directory expansion on '$arg'");
+
+        foreach my $file ( @{$updater->gethead} )
+        {
+            next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
+            next unless ( $file->{name} =~ /^$arg\// or $file->{name} eq $arg  );
+            push @{$state->{args}}, $file->{name};
+        }
+
+        shift @{$state->{args}} if ( scalar(@{$state->{args}}) > 1 );
+    } else {
+        $log->info("Only one arg specified, populating file list automatically");
+
+        $state->{args} = [];
+
+        foreach my $file ( @{$updater->gethead} )
+        {
+            next if ( $file->{filehash} eq "deleted" and not defined ( $state->{entries}{$file->{name}} ) );
+            next unless ( $file->{name} =~ s/^$state->{prependdir}// );
+            push @{$state->{args}}, $file->{name};
+        }
     }
 }
 
@@ -1736,11 +1806,17 @@ sub transmitfile
 sub filenamesplit
 {
     my $filename = shift;
+    my $fixforlocaldir = shift;
 
     my ( $filepart, $dirpart ) = ( $filename, "." );
     ( $filepart, $dirpart ) = ( $2, $1 ) if ( $filename =~ /(.*)\/(.*)/ );
     $dirpart .= "/";
 
+    if ( $fixforlocaldir )
+    {
+        $dirpart =~ s/^$state->{prependdir}//;
+    }
+
     return ( $filepart, $dirpart );
 }
 
@@ -1756,8 +1832,7 @@ sub filecleanup
     }
 
     $filename =~ s/^\.\///g;
-    $filename = $state->{directory} . $filename;
-
+    $filename = $state->{prependdir} . $filename;
     return $filename;
 }
 
diff --git a/git-parse-remote.sh b/git-parse-remote.sh
index c9b899e3d7..187f0883c9 100755
--- a/git-parse-remote.sh
+++ b/git-parse-remote.sh
@@ -10,7 +10,10 @@ get_data_source () {
 		# Not so fast.	This could be the partial URL shorthand...
 		token=$(expr "z$1" : 'z\([^/]*\)/')
 		remainder=$(expr "z$1" : 'z[^/]*/\(.*\)')
-		if test -f "$GIT_DIR/branches/$token"
+		if test "$(git-repo-config --get "remote.$token.url")"
+		then
+			echo config-partial
+		elif test -f "$GIT_DIR/branches/$token"
 		then
 			echo branches-partial
 		else
@@ -18,7 +21,10 @@ get_data_source () {
 		fi
 		;;
 	*)
-		if test -f "$GIT_DIR/remotes/$1"
+		if test "$(git-repo-config --get "remote.$1.url")"
+		then
+			echo config
+		elif test -f "$GIT_DIR/remotes/$1"
 		then
 			echo remotes
 		elif test -f "$GIT_DIR/branches/$1"
@@ -35,6 +41,15 @@ get_remote_url () {
 	case "$data_source" in
 	'')
 		echo "$1" ;;
+	config-partial)
+		token=$(expr "z$1" : 'z\([^/]*\)/')
+		remainder=$(expr "z$1" : 'z[^/]*/\(.*\)')
+		url=$(git-repo-config --get "remote.$token.url")
+		echo "$url/$remainder"
+		;;
+	config)
+		git-repo-config --get "remote.$1.url"
+		;;
 	remotes)
 		sed -ne '/^URL: */{
 			s///p
@@ -56,8 +71,10 @@ get_remote_url () {
 get_remote_default_refs_for_push () {
 	data_source=$(get_data_source "$1")
 	case "$data_source" in
-	'' | branches | branches-partial)
+	'' | config-partial | branches | branches-partial)
 		;; # no default push mapping, just send matching refs.
+	config)
+		git-repo-config --get-all "remote.$1.push" ;;
 	remotes)
 		sed -ne '/^Push: */{
 			s///p
@@ -111,8 +128,11 @@ canon_refs_list_for_fetch () {
 get_remote_default_refs_for_fetch () {
 	data_source=$(get_data_source "$1")
 	case "$data_source" in
-	'' | branches-partial)
+	'' | config-partial | branches-partial)
 		echo "HEAD:" ;;
+	config)
+		canon_refs_list_for_fetch \
+			$(git-repo-config --get-all "remote.$1.fetch") ;;
 	branches)
 		remote_branch=$(sed -ne '/#/s/.*#//p' "$GIT_DIR/branches/$1")
 		case "$remote_branch" in '') remote_branch=master ;; esac
diff --git a/git.c b/git.c
index 49ba5189d9..84803a62e6 100644
--- a/git.c
+++ b/git.c
@@ -47,8 +47,10 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "whatchanged", cmd_whatchanged },
 		{ "show", cmd_show },
 		{ "push", cmd_push },
+		{ "fmt-patch", cmd_format_patch },
 		{ "count-objects", cmd_count_objects },
 		{ "diff", cmd_diff },
+		{ "grep", cmd_grep },
 	};
 	int i;
 
diff --git a/log-tree.c b/log-tree.c
index b90ba6762a..526d578e98 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -20,6 +20,7 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep)
 	int abbrev_commit = opt->abbrev_commit ? opt->abbrev : 40;
 	const char *extra;
 	int len;
+	char* subject = NULL;
 
 	opt->loginfo = NULL;
 	if (!opt->verbose_header) {
@@ -49,19 +50,38 @@ void show_log(struct rev_info *opt, struct log_info *log, const char *sep)
 	/*
 	 * Print header line of header..
 	 */
-	printf("%s%s",
-		opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ",
-		diff_unique_abbrev(commit->object.sha1, abbrev_commit));
-	if (opt->parents)
-		show_parents(commit, abbrev_commit);
-	if (parent)
-		printf(" (from %s)", diff_unique_abbrev(parent->object.sha1, abbrev_commit));
-	putchar(opt->commit_format == CMIT_FMT_ONELINE ? ' ' : '\n');
+
+	if (opt->commit_format == CMIT_FMT_EMAIL) {
+		if (opt->total > 0) {
+			static char buffer[64];
+			snprintf(buffer, sizeof(buffer),
+					"Subject: [PATCH %d/%d] ",
+					opt->nr, opt->total);
+			subject = buffer;
+		} else if (opt->total == 0)
+			subject = "Subject: [PATCH] ";
+		else
+			subject = "Subject: ";
+
+		printf("From %s  Thu Apr 7 15:13:13 2005\n",
+		       sha1_to_hex(commit->object.sha1));
+	} else {
+		printf("%s%s",
+		       opt->commit_format == CMIT_FMT_ONELINE ? "" : "commit ",
+		       diff_unique_abbrev(commit->object.sha1, abbrev_commit));
+		if (opt->parents)
+			show_parents(commit, abbrev_commit);
+		if (parent) 
+			printf(" (from %s)",
+			       diff_unique_abbrev(parent->object.sha1,
+						  abbrev_commit));
+		putchar(opt->commit_format == CMIT_FMT_ONELINE ? ' ' : '\n');
+	}
 
 	/*
 	 * And then the pretty-printed message itself
 	 */
-	len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, sizeof(this_header), abbrev);
+	len = pretty_print_commit(opt->commit_format, commit, ~0u, this_header, sizeof(this_header), abbrev, subject);
 	printf("%s%s%s", this_header, extra, sep);
 }
 
@@ -166,15 +186,18 @@ static int log_tree_diff(struct rev_info *opt, struct commit *commit, struct log
 int log_tree_commit(struct rev_info *opt, struct commit *commit)
 {
 	struct log_info log;
+	int shown;
 
 	log.commit = commit;
 	log.parent = NULL;
 	opt->loginfo = &log;
 
-	if (!log_tree_diff(opt, commit, &log) && opt->loginfo && opt->always_show_header) {
+	shown = log_tree_diff(opt, commit, &log);
+	if (!shown && opt->loginfo && opt->always_show_header) {
 		log.parent = NULL;
 		show_log(opt, opt->loginfo, "");
+		shown = 1;
 	}
 	opt->loginfo = NULL;
-	return 0;
+	return shown;
 }
diff --git a/read-cache.c b/read-cache.c
index a917ab0cfe..ed0da38e07 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -4,11 +4,26 @@
  * Copyright (C) Linus Torvalds, 2005
  */
 #include "cache.h"
+#include "cache-tree.h"
+
+/* Index extensions.
+ *
+ * The first letter should be 'A'..'Z' for extensions that are not
+ * necessary for a correct operation (i.e. optimization data).
+ * When new extensions are added that _needs_ to be understood in
+ * order to correctly interpret the index file, pick character that
+ * is outside the range, to cause the reader to abort.
+ */
+
+#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
+#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
 
 struct cache_entry **active_cache = NULL;
 static time_t index_file_timestamp;
 unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;
 
+struct cache_tree *active_cache_tree = NULL;
+
 /*
  * This only updates the "non-critical" parts of the directory
  * cache, ie the parts that aren't tracked by GIT, and only used
@@ -513,6 +528,22 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size)
 	return 0;
 }
 
+static int read_index_extension(const char *ext, void *data, unsigned long sz)
+{
+	switch (CACHE_EXT(ext)) {
+	case CACHE_EXT_TREE:
+		active_cache_tree = cache_tree_read(data, sz);
+		break;
+	default:
+		if (*ext < 'A' || 'Z' < *ext)
+			return error("index uses %.4s extension, which we do not understand",
+				     ext);
+		fprintf(stderr, "ignoring %.4s extension\n", ext);
+		break;
+	}
+	return 0;
+}
+
 int read_cache(void)
 {
 	int fd, i;
@@ -561,6 +592,22 @@ int read_cache(void)
 		active_cache[i] = ce;
 	}
 	index_file_timestamp = st.st_mtime;
+	while (offset <= size - 20 - 8) {
+		/* After an array of active_nr index entries,
+		 * there can be arbitrary number of extended
+		 * sections, each of which is prefixed with
+		 * extension name (4-byte) and section length
+		 * in 4-byte network byte order.
+		 */
+		unsigned long extsize;
+		memcpy(&extsize, map + offset + 4, 4);
+		extsize = ntohl(extsize);
+		if (read_index_extension(map + offset,
+					 map + offset + 8, extsize) < 0)
+			goto unmap;
+		offset += 8;
+		offset += extsize;
+	}
 	return active_nr;
 
 unmap:
@@ -595,6 +642,17 @@ static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len)
  	return 0;
 }
 
+static int write_index_ext_header(SHA_CTX *context, int fd,
+				  unsigned long ext, unsigned long sz)
+{
+	ext = htonl(ext);
+	sz = htonl(sz);
+	if ((ce_write(context, fd, &ext, 4) < 0) ||
+	    (ce_write(context, fd, &sz, 4) < 0))
+		return -1;
+	return 0;
+}
+
 static int ce_flush(SHA_CTX *context, int fd)
 {
 	unsigned int left = write_buffer_len;
@@ -691,5 +749,19 @@ int write_cache(int newfd, struct cache_entry **cache, int entries)
 		if (ce_write(&c, newfd, ce, ce_size(ce)) < 0)
 			return -1;
 	}
+
+	/* Write extension data here */
+	if (active_cache_tree) {
+		unsigned long sz;
+		void *data = cache_tree_write(active_cache_tree, &sz);
+		if (data &&
+		    !write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sz) &&
+		    !ce_write(&c, newfd, data, sz))
+			;
+		else {
+			free(data);
+			return -1;
+		}
+	}
 	return ce_flush(&c, newfd);
 }
diff --git a/read-tree.c b/read-tree.c
index e926e4c880..c25385d79f 100644
--- a/read-tree.c
+++ b/read-tree.c
@@ -9,6 +9,7 @@
 
 #include "object.h"
 #include "tree.h"
+#include "cache-tree.h"
 #include <sys/time.h>
 #include <signal.h>
 
@@ -20,6 +21,7 @@ static int trivial_merges_only = 0;
 static int aggressive = 0;
 static int verbose_update = 0;
 static volatile int progress_update = 0;
+static const char *prefix = NULL;
 
 static int head_idx = -1;
 static int merge_size = 0;
@@ -368,7 +370,8 @@ static int unpack_trees(merge_fn_t fn)
 			posns[i] = ((struct tree *) posn->item)->entries;
 			posn = posn->next;
 		}
-		if (unpack_trees_rec(posns, len, "", fn, &indpos))
+		if (unpack_trees_rec(posns, len, prefix ? prefix : "",
+				     fn, &indpos))
 			return -1;
 	}
 
@@ -421,6 +424,12 @@ static void verify_uptodate(struct cache_entry *ce)
 	die("Entry '%s' not uptodate. Cannot merge.", ce->name);
 }
 
+static void invalidate_ce_path(struct cache_entry *ce)
+{
+	if (ce)
+		cache_tree_invalidate_path(active_cache_tree, ce->name);
+}
+
 static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 {
 	merge->ce_flags |= htons(CE_UPDATE);
@@ -436,8 +445,11 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 			*merge = *old;
 		} else {
 			verify_uptodate(old);
+			invalidate_ce_path(old);
 		}
 	}
+	else
+		invalidate_ce_path(merge);
 	merge->ce_flags &= ~htons(CE_STAGEMASK);
 	add_cache_entry(merge, ADD_CACHE_OK_TO_ADD);
 	return 1;
@@ -449,6 +461,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old)
 		verify_uptodate(old);
 	ce->ce_mode = 0;
 	add_cache_entry(ce, ADD_CACHE_OK_TO_ADD);
+	invalidate_ce_path(ce);
 	return 1;
 }
 
@@ -668,6 +681,28 @@ static int twoway_merge(struct cache_entry **src)
 		return deleted_entry(oldtree, current);
 }
 
+/*
+ * Bind merge.
+ *
+ * Keep the index entries at stage0, collapse stage1 but make sure
+ * stage0 does not have anything in prefix.
+ */
+static int bind_merge(struct cache_entry **src)
+{
+	struct cache_entry *old = src[0];
+	struct cache_entry *a = src[1];
+
+	if (merge_size != 1)
+		return error("Cannot do a bind merge of %d trees\n",
+			     merge_size);
+	if (!a)
+		return merged_entry(old, NULL);
+	if (old)
+		die("Entry '%s' overlaps.  Cannot bind.", a->name);
+
+	return merged_entry(a, NULL);
+}
+
 /*
  * One-way merge.
  *
@@ -683,8 +718,10 @@ static int oneway_merge(struct cache_entry **src)
 		return error("Cannot do a oneway merge of %d trees",
 			     merge_size);
 
-	if (!a)
+	if (!a) {
+		invalidate_ce_path(old);
 		return 0;
+	}
 	if (old && same(old, a)) {
 		return keep_entry(old);
 	}
@@ -703,6 +740,7 @@ static int read_cache_unmerged(void)
 		struct cache_entry *ce = active_cache[i];
 		if (ce_stage(ce)) {
 			deleted++;
+			invalidate_ce_path(ce);
 			continue;
 		}
 		if (deleted)
@@ -713,7 +751,40 @@ static int read_cache_unmerged(void)
 	return deleted;
 }
 
-static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive] [-u | -i] <sha1> [<sha2> [<sha3>]])";
+static void prime_cache_tree_rec(struct cache_tree *it, struct tree *tree)
+{
+	struct tree_entry_list *ent;
+	int cnt;
+	
+	memcpy(it->sha1, tree->object.sha1, 20);
+	for (cnt = 0, ent = tree->entries; ent; ent = ent->next) {
+		if (!ent->directory)
+			cnt++;
+		else {
+			struct cache_tree_sub *sub;
+			struct tree *subtree = (struct tree *)ent->item.tree;
+			if (!subtree->object.parsed)
+				parse_tree(subtree);
+			sub = cache_tree_sub(it, ent->name);
+			sub->cache_tree = cache_tree();
+			prime_cache_tree_rec(sub->cache_tree, subtree);
+			cnt += sub->cache_tree->entry_count;
+		}
+	}
+	it->entry_count = cnt;
+}
+
+static void prime_cache_tree(void)
+{
+	struct tree *tree = (struct tree *)trees->item;
+	if (!tree)
+		return;
+	active_cache_tree = cache_tree();
+	prime_cache_tree_rec(active_cache_tree, tree);
+
+}
+
+static const char read_tree_usage[] = "git-read-tree (<sha> | [[-m [--aggressive] | --reset | --prefix=<prefix>] [-u | -i]] <sha1> [<sha2> [<sha3>]])";
 
 static struct cache_file cache_file;
 
@@ -758,9 +829,24 @@ int main(int argc, char **argv)
 			continue;
 		}
 
+		/* "--prefix=<subdirectory>/" means keep the current index
+		 *  entries and put the entries from the tree under the
+		 * given subdirectory.
+		 */
+		if (!strncmp(arg, "--prefix=", 9)) {
+			if (stage || merge || prefix)
+				usage(read_tree_usage);
+			prefix = arg + 9;
+			merge = 1;
+			stage = 1;
+			if (read_cache_unmerged())
+				die("you need to resolve your current index first");
+			continue;
+		}
+
 		/* This differs from "-m" in that we'll silently ignore unmerged entries */
 		if (!strcmp(arg, "--reset")) {
-			if (stage || merge)
+			if (stage || merge || prefix)
 				usage(read_tree_usage);
 			reset = 1;
 			merge = 1;
@@ -781,7 +867,7 @@ int main(int argc, char **argv)
 
 		/* "-m" stands for "merge", meaning we start in stage 1 */
 		if (!strcmp(arg, "-m")) {
-			if (stage || merge)
+			if (stage || merge || prefix)
 				usage(read_tree_usage);
 			if (read_cache_unmerged())
 				die("you need to resolve your current index first");
@@ -803,21 +889,39 @@ int main(int argc, char **argv)
 	if ((update||index_only) && !merge)
 		usage(read_tree_usage);
 
+	if (prefix) {
+		int pfxlen = strlen(prefix);
+		int pos;
+		if (prefix[pfxlen-1] != '/')
+			die("prefix must end with /");
+		if (stage != 2)
+			die("binding merge takes only one tree");
+		pos = cache_name_pos(prefix, pfxlen);
+		if (0 <= pos)
+			die("corrupt index file");
+		pos = -pos-1;
+		if (pos < active_nr &&
+		    !strncmp(active_cache[pos]->name, prefix, pfxlen))
+			die("subdirectory '%s' already exists.", prefix);
+		pos = cache_name_pos(prefix, pfxlen-1);
+		if (0 <= pos)
+			die("file '%.*s' already exists.", pfxlen-1, prefix);
+	}
+
 	if (merge) {
 		if (stage < 2)
 			die("just how do you expect me to merge %d trees?", stage-1);
 		switch (stage - 1) {
 		case 1:
-			fn = oneway_merge;
+			fn = prefix ? bind_merge : oneway_merge;
 			break;
 		case 2:
 			fn = twoway_merge;
 			break;
 		case 3:
-			fn = threeway_merge;
-			break;
 		default:
 			fn = threeway_merge;
+			cache_tree_free(&active_cache_tree);
 			break;
 		}
 
@@ -828,6 +932,18 @@ int main(int argc, char **argv)
 	}
 
 	unpack_trees(fn);
+
+	/*
+	 * When reading only one tree (either the most basic form,
+	 * "-m ent" or "--reset ent" form), we can obtain a fully
+	 * valid cache-tree because the index must match exactly
+	 * what came from the tree.
+	 */
+	if (trees && trees->item && (!merge || (stage == 2))) {
+		cache_tree_free(&active_cache_tree);
+		prime_cache_tree();
+	}
+
 	if (write_cache(newfd, active_cache, active_nr) ||
 	    commit_index_file(&cache_file))
 		die("unable to write new index file");
diff --git a/rev-list.c b/rev-list.c
index 8b0ec388fa..235ae4c7e1 100644
--- a/rev-list.c
+++ b/rev-list.c
@@ -84,7 +84,7 @@ static void show_commit(struct commit *commit)
 		static char pretty_header[16384];
 		pretty_print_commit(revs.commit_format, commit, ~0,
 				    pretty_header, sizeof(pretty_header),
-				    revs.abbrev);
+				    revs.abbrev, NULL);
 		printf("%s%c", pretty_header, hdr_termination);
 	}
 	fflush(stdout);
diff --git a/revision.h b/revision.h
index 48d7b4ca94..62759f7bc0 100644
--- a/revision.h
+++ b/revision.h
@@ -58,6 +58,7 @@ struct rev_info {
 	unsigned int	abbrev;
 	enum cmit_fmt	commit_format;
 	struct log_info *loginfo;
+	int		nr, total;
 
 	/* special limits */
 	int max_count;
diff --git a/show-branch.c b/show-branch.c
index 268c57b180..bbe26c2e7a 100644
--- a/show-branch.c
+++ b/show-branch.c
@@ -259,7 +259,7 @@ static void show_one_commit(struct commit *commit, int no_name)
 	struct commit_name *name = commit->object.util;
 	if (commit->object.parsed)
 		pretty_print_commit(CMIT_FMT_ONELINE, commit, ~0,
-				    pretty, sizeof(pretty), 0);
+				    pretty, sizeof(pretty), 0, NULL);
 	else
 		strcpy(pretty, "(unavailable)");
 	if (!strncmp(pretty, "[PATCH] ", 8))
diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh
index cf33989b56..2c9bbb59b0 100755
--- a/t/t0000-basic.sh
+++ b/t/t0000-basic.sh
@@ -195,6 +195,20 @@ test_expect_success \
     'git-ls-tree -r output for a known tree.' \
     'diff current expected'
 
+test_expect_success \
+    'writing partial tree out with git-write-tree --prefix.' \
+    'ptree=$(git-write-tree --prefix=path3)'
+test_expect_success \
+    'validate object ID for a known tree.' \
+    'test "$ptree" = 21ae8269cacbe57ae09138dcc3a2887f904d02b3'
+
+test_expect_success \
+    'writing partial tree out with git-write-tree --prefix.' \
+    'ptree=$(git-write-tree --prefix=path3/subp3)'
+test_expect_success \
+    'validate object ID for a known tree.' \
+    'test "$ptree" = 3c5e5399f3a333eddecce7a9b9465b63f65f51e2'
+
 ################################################################
 rm .git/index
 test_expect_success \
diff --git a/update-index.c b/update-index.c
index 3d7e02db2c..f6b09a4800 100644
--- a/update-index.c
+++ b/update-index.c
@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "strbuf.h"
 #include "quote.h"
+#include "cache-tree.h"
 #include "tree-walk.h"
 
 /*
@@ -71,6 +72,7 @@ static int mark_valid(const char *path)
 			active_cache[pos]->ce_flags &= ~htons(CE_VALID);
 			break;
 		}
+		cache_tree_invalidate_path(active_cache_tree, path);
 		active_cache_changed = 1;
 		return 0;
 	}
@@ -84,6 +86,12 @@ static int add_file_to_cache(const char *path)
 	struct stat st;
 
 	status = lstat(path, &st);
+
+	/* We probably want to do this in remove_file_from_cache() and
+	 * add_cache_entry() instead...
+	 */
+	cache_tree_invalidate_path(active_cache_tree, path);
+
 	if (status < 0 || S_ISDIR(st.st_mode)) {
 		/* When we used to have "path" and now we want to add
 		 * "path/file", we need a way to remove "path" before
@@ -326,6 +334,7 @@ static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 		return error("%s: cannot add to the index - missing --add option?",
 			     path);
 	report("add '%s'", path);
+	cache_tree_invalidate_path(active_cache_tree, path);
 	return 0;
 }
 
@@ -350,6 +359,7 @@ static void chmod_path(int flip, const char *path)
 	default:
 		goto fail;
 	}
+	cache_tree_invalidate_path(active_cache_tree, path);
 	active_cache_changed = 1;
 	report("chmod %cx '%s'", flip, path);
 	return;
@@ -371,6 +381,7 @@ static void update_one(const char *path, const char *prefix, int prefix_length)
 			die("Unable to mark file %s", path);
 		goto free_return;
 	}
+	cache_tree_invalidate_path(active_cache_tree, path);
 
 	if (force_remove) {
 		if (remove_file_from_cache(p))
@@ -449,6 +460,7 @@ static void read_index_info(int line_termination)
 				free(path_name);
 			continue;
 		}
+		cache_tree_invalidate_path(active_cache_tree, path_name);
 
 		if (!mode) {
 			/* mode == 0 means there is no such path -- remove */
@@ -555,6 +567,7 @@ static int unresolve_one(const char *path)
 		goto free_return;
 	}
 
+	cache_tree_invalidate_path(active_cache_tree, path);
 	remove_file_from_cache(path);
 	if (add_cache_entry(ce_2, ADD_CACHE_OK_TO_ADD)) {
 		error("%s: cannot add our version to the index.", path);
diff --git a/write-tree.c b/write-tree.c
index dcad6e6670..895e7a359d 100644
--- a/write-tree.c
+++ b/write-tree.c
@@ -5,154 +5,68 @@
  */
 #include "cache.h"
 #include "tree.h"
+#include "cache-tree.h"
 
 static int missing_ok = 0;
+static char *prefix = NULL;
 
-static int check_valid_sha1(unsigned char *sha1)
-{
-	int ret;
-
-	/* If we were anal, we'd check that the sha1 of the contents actually matches */
-	ret = has_sha1_file(sha1);
-	if (ret == 0)
-		perror(sha1_file_name(sha1));
-	return ret ? 0 : -1;
-}
-
-static int write_tree(struct cache_entry **cachep, int maxentries, const char *base, int baselen, unsigned char *returnsha1)
-{
-	unsigned char subdir_sha1[20];
-	unsigned long size, offset;
-	char *buffer;
-	int nr;
-
-	/* Guess at some random initial size */
-	size = 8192;
-	buffer = xmalloc(size);
-	offset = 0;
-
-	nr = 0;
-	while (nr < maxentries) {
-		struct cache_entry *ce = cachep[nr];
-		const char *pathname = ce->name, *filename, *dirname;
-		int pathlen = ce_namelen(ce), entrylen;
-		unsigned char *sha1;
-		unsigned int mode;
-
-		/* Did we hit the end of the directory? Return how many we wrote */
-		if (baselen >= pathlen || memcmp(base, pathname, baselen))
-			break;
-
-		sha1 = ce->sha1;
-		mode = ntohl(ce->ce_mode);
-
-		/* Do we have _further_ subdirectories? */
-		filename = pathname + baselen;
-		dirname = strchr(filename, '/');
-		if (dirname) {
-			int subdir_written;
-
-			subdir_written = write_tree(cachep + nr, maxentries - nr, pathname, dirname-pathname+1, subdir_sha1);
-			nr += subdir_written;
-
-			/* Now we need to write out the directory entry into this tree.. */
-			mode = S_IFDIR;
-			pathlen = dirname - pathname;
-
-			/* ..but the directory entry doesn't count towards the total count */
-			nr--;
-			sha1 = subdir_sha1;
-		}
+static const char write_tree_usage[] =
+"git-write-tree [--missing-ok] [--prefix=<prefix>/]";
 
-		if (!missing_ok && check_valid_sha1(sha1) < 0)
-			exit(1);
-
-		entrylen = pathlen - baselen;
-		if (offset + entrylen + 100 > size) {
-			size = alloc_nr(offset + entrylen + 100);
-			buffer = xrealloc(buffer, size);
-		}
-		offset += sprintf(buffer + offset, "%o %.*s", mode, entrylen, filename);
-		buffer[offset++] = 0;
-		memcpy(buffer + offset, sha1, 20);
-		offset += 20;
-		nr++;
-	}
-
-	write_sha1_file(buffer, offset, tree_type, returnsha1);
-	free(buffer);
-	return nr;
-}
-
-static const char write_tree_usage[] = "git-write-tree [--missing-ok]";
+static struct cache_file cache_file;
 
 int main(int argc, char **argv)
 {
-	int i, funny;
-	int entries;
-	unsigned char sha1[20];
-	
+	int entries, was_valid, newfd;
+
 	setup_git_directory();
 
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
 	entries = read_cache();
-	if (argc == 2) {
-		if (!strcmp(argv[1], "--missing-ok"))
+
+	while (1 < argc) {
+		char *arg = argv[1];
+		if (!strcmp(arg, "--missing-ok"))
 			missing_ok = 1;
+		else if (!strncmp(arg, "--prefix=", 9))
+			prefix = arg + 9;
 		else
 			die(write_tree_usage);
+		argc--; argv++;
 	}
-	
+
 	if (argc > 2)
 		die("too many options");
 
 	if (entries < 0)
 		die("git-write-tree: error reading cache");
 
-	/* Verify that the tree is merged */
-	funny = 0;
-	for (i = 0; i < entries; i++) {
-		struct cache_entry *ce = active_cache[i];
-		if (ce_stage(ce)) {
-			if (10 < ++funny) {
-				fprintf(stderr, "...\n");
-				break;
-			}
-			fprintf(stderr, "%s: unmerged (%s)\n", ce->name, sha1_to_hex(ce->sha1));
+	if (!active_cache_tree)
+		active_cache_tree = cache_tree();
+
+	was_valid = cache_tree_fully_valid(active_cache_tree);
+	if (!was_valid) {
+		if (cache_tree_update(active_cache_tree,
+				      active_cache, active_nr,
+				      missing_ok, 0) < 0)
+			die("git-write-tree: error building trees");
+		if (0 <= newfd) {
+			if (!write_cache(newfd, active_cache, active_nr))
+				commit_index_file(&cache_file);
 		}
-	}
-	if (funny)
-		die("git-write-tree: not able to write tree");
-
-	/* Also verify that the cache does not have path and path/file
-	 * at the same time.  At this point we know the cache has only
-	 * stage 0 entries.
-	 */
-	funny = 0;
-	for (i = 0; i < entries - 1; i++) {
-		/* path/file always comes after path because of the way
-		 * the cache is sorted.  Also path can appear only once,
-		 * which means conflicting one would immediately follow.
+		/* Not being able to write is fine -- we are only interested
+		 * in updating the cache-tree part, and if the next caller
+		 * ends up using the old index with unupdated cache-tree part
+		 * it misses the work we did here, but that is just a
+		 * performance penalty and not a big deal.
 		 */
-		const char *this_name = active_cache[i]->name;
-		const char *next_name = active_cache[i+1]->name;
-		int this_len = strlen(this_name);
-		if (this_len < strlen(next_name) &&
-		    strncmp(this_name, next_name, this_len) == 0 &&
-		    next_name[this_len] == '/') {
-			if (10 < ++funny) {
-				fprintf(stderr, "...\n");
-				break;
-			}
-			fprintf(stderr, "You have both %s and %s\n",
-				this_name, next_name);
-		}
 	}
-	if (funny)
-		die("git-write-tree: not able to write tree");
-
-	/* Ok, write it out */
-	if (write_tree(active_cache, entries, "", 0, sha1) != entries)
-		die("git-write-tree: internal error");
-	printf("%s\n", sha1_to_hex(sha1));
+	if (prefix) {
+		struct cache_tree *subtree =
+			cache_tree_find(active_cache_tree, prefix);
+		printf("%s\n", sha1_to_hex(subtree->sha1));
+	}
+	else
+		printf("%s\n", sha1_to_hex(active_cache_tree->sha1));
 	return 0;
 }