42 files changed, 2340 insertions, 1090 deletions

diff --git a/.gitignore b/.gitignore
index 199cc31..18a7295 100644
--- a/.gitignore
+++ b/.gitignore
@@ -124,6 +124,7 @@ git-write-tree
 git-core-*/?*
 test-date
 test-delta
+test-dump-cache-tree
 common-cmds.h
 *.tar.gz
 *.dsc
diff --git a/Documentation/git-read-tree.txt b/Documentation/git-read-tree.txt
index 844cfda..1f21d95 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 77e12cb..c85fa89 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 14873fa..355e0cc 100644
--- a/Makefile
+++ b/Makefile
@@ -113,14 +113,14 @@ SPARSE_FLAGS = -D__BIG_ENDIAN__ -D__powerpc__
 ### --- END CONFIGURATION SECTION ---
 
 SCRIPT_SH = \
-	git-add.sh git-bisect.sh git-branch.sh git-checkout.sh \
+	git-bisect.sh git-branch.sh git-checkout.sh \
 	git-cherry.sh git-clean.sh git-clone.sh git-commit.sh \
 	git-fetch.sh \
-	git-format-patch.sh git-ls-remote.sh \
+	git-ls-remote.sh \
 	git-merge-one-file.sh git-parse-remote.sh \
 	git-prune.sh git-pull.sh git-rebase.sh \
 	git-repack.sh git-request-pull.sh git-reset.sh \
-	git-resolve.sh git-revert.sh git-rm.sh git-sh-setup.sh \
+	git-resolve.sh git-revert.sh git-sh-setup.sh \
 	git-tag.sh git-verify-tag.sh \
 	git-applymbox.sh git-applypatch.sh git-am.sh \
 	git-merge.sh git-merge-stupid.sh git-merge-octopus.sh \
@@ -168,12 +168,13 @@ PROGRAMS = \
 
 BUILT_INS = git-log$X git-whatchanged$X git-show$X \
 	git-count-objects$X git-diff$X git-push$X \
-	git-grep$X git-rev-list$X git-check-ref-format$X \
-	git-init-db$X git-ls-files$X git-ls-tree$X \
+	git-grep$X git-add$X git-rm$X git-rev-list$X \
+	git-check-ref-format$X \
+	git-init-db$X git-tar-tree$X git-upload-tar$X git-format-patch$X \
+	git-ls-files$X git-ls-tree$X \
 	git-read-tree$X git-commit-tree$X \
 	git-apply$X git-show-branch$X git-diff-files$X \
-	git-diff-index$X git-diff-stages$X git-diff-tree$X \
-	git-tar-tree$X git-upload-tar$X
+	git-diff-index$X git-diff-stages$X git-diff-tree$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -202,7 +203,7 @@ LIB_H = \
 	blob.h cache.h commit.h csum-file.h delta.h \
 	diff.h object.h pack.h pkt-line.h quote.h refs.h \
 	run-command.h strbuf.h tag.h tree.h git-compat-util.h revision.h \
-	tree-walk.h log-tree.h
+	tree-walk.h log-tree.h dir.h
 
 DIFF_OBJS = \
 	diff.o diff-lib.o diffcore-break.o diffcore-order.o \
@@ -210,10 +211,10 @@ 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 \
+	quote.o read-cache.o refs.o run-command.o dir.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
@@ -221,12 +222,13 @@ LIB_OBJS = \
 
 BUILTIN_OBJS = \
 	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
-	builtin-grep.o builtin-rev-list.o builtin-check-ref-format.o \
-	builtin-init-db.o builtin-ls-files.o builtin-ls-tree.o \
+	builtin-grep.o builtin-add.o builtin-rev-list.o builtin-check-ref-format.o \
+	builtin-rm.o builtin-init-db.o \
+	builtin-tar-tree.o builtin-upload-tar.o \
+	builtin-ls-files.o builtin-ls-tree.o \
 	builtin-read-tree.o builtin-commit-tree.o \
 	builtin-apply.o builtin-show-branch.o builtin-diff-files.o \
-	builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o \
-	builtin-tar-tree.o builtin-upload-tar.o
+	builtin-diff-index.o builtin-diff-stages.o builtin-diff-tree.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz
@@ -618,6 +620,9 @@ test-date$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/builtin-add.c b/builtin-add.c
new file mode 100644
index 0000000..02fe38b
--- /dev/null
+++ b/builtin-add.c
@@ -0,0 +1,189 @@
+/*
+ * "git add" builtin command
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ */
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+#include "cache-tree.h"
+
+static const char builtin_add_usage[] =
+"git-add [-n] [-v] <filepattern>...";
+
+static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix)
+{
+	char *seen;
+	int i, specs;
+	struct dir_entry **src, **dst;
+
+	for (specs = 0; pathspec[specs];  specs++)
+		/* nothing */;
+	seen = xmalloc(specs);
+	memset(seen, 0, specs);
+
+	src = dst = dir->entries;
+	i = dir->nr;
+	while (--i >= 0) {
+		struct dir_entry *entry = *src++;
+		if (!match_pathspec(pathspec, entry->name, entry->len, prefix, seen)) {
+			free(entry);
+			continue;
+		}
+		*dst++ = entry;
+	}
+	dir->nr = dst - dir->entries;
+
+	for (i = 0; i < specs; i++) {
+		struct stat st;
+		const char *match;
+		if (seen[i])
+			continue;
+
+		/* Existing file? We must have ignored it */
+		match = pathspec[i];
+		if (!match[0] || !lstat(match, &st))
+			continue;
+		die("pathspec '%s' did not match any files", match);
+	}
+}
+
+static void fill_directory(struct dir_struct *dir, const char **pathspec)
+{
+	const char *path, *base;
+	int baselen;
+
+	/* Set up the default git porcelain excludes */
+	memset(dir, 0, sizeof(*dir));
+	dir->exclude_per_dir = ".gitignore";
+	path = git_path("info/exclude");
+	if (!access(path, R_OK))
+		add_excludes_from_file(dir, path);
+
+	/*
+	 * Calculate common prefix for the pathspec, and
+	 * use that to optimize the directory walk
+	 */
+	baselen = common_prefix(pathspec);
+	path = ".";
+	base = "";
+	if (baselen) {
+		char *common = xmalloc(baselen + 1);
+		common = xmalloc(baselen + 1);
+		memcpy(common, *pathspec, baselen);
+		common[baselen] = 0;
+		path = base = common;
+	}
+
+	/* Read the directory and prune it */
+	read_directory(dir, path, base, baselen);
+	if (pathspec)
+		prune_directory(dir, pathspec, baselen);
+}
+
+static int add_file_to_index(const char *path, int verbose)
+{
+	int size, namelen;
+	struct stat st;
+	struct cache_entry *ce;
+
+	if (lstat(path, &st))
+		die("%s: unable to stat (%s)", path, strerror(errno));
+
+	if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode))
+		die("%s: can only add regular files or symbolic links", path);
+
+	namelen = strlen(path);
+	size = cache_entry_size(namelen);
+	ce = xcalloc(1, size);
+	memcpy(ce->name, path, namelen);
+	ce->ce_flags = htons(namelen);
+	fill_stat_cache_info(ce, &st);
+
+	ce->ce_mode = create_ce_mode(st.st_mode);
+	if (!trust_executable_bit) {
+		/* If there is an existing entry, pick the mode bits
+		 * from it.
+		 */
+		int pos = cache_name_pos(path, namelen);
+		if (pos >= 0)
+			ce->ce_mode = active_cache[pos]->ce_mode;
+	}
+
+	if (index_path(ce->sha1, path, &st, 1))
+		die("unable to index file %s", path);
+	if (add_cache_entry(ce, ADD_CACHE_OK_TO_ADD))
+		die("unable to add %s to index",path);
+	if (verbose)
+		printf("add '%s'\n", path);
+	cache_tree_invalidate_path(active_cache_tree, path);
+	return 0;
+}
+
+static struct cache_file cache_file;
+
+int cmd_add(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	struct dir_struct dir;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new cachefile");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+
+		if (arg[0] != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		die(builtin_add_usage);
+	}
+	git_config(git_default_config);
+	pathspec = get_pathspec(prefix, argv + i);
+
+	fill_directory(&dir, pathspec);
+
+	if (show_only) {
+		const char *sep = "", *eof = "";
+		for (i = 0; i < dir.nr; i++) {
+			printf("%s%s", sep, dir.entries[i]->name);
+			sep = " ";
+			eof = "\n";
+		}
+		fputs(eof, stdout);
+		return 0;
+	}
+
+	for (i = 0; i < dir.nr; i++)
+		add_file_to_index(dir.entries[i]->name, verbose);
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}
diff --git a/builtin-apply.c b/builtin-apply.c
index 4056b9d..f16c753 100644
--- a/builtin-apply.c
+++ b/builtin-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"
@@ -1918,6 +1919,7 @@ 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);
 	}
 	if (!cached)
 		unlink(patch->old_name);
@@ -2019,8 +2021,9 @@ 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 de81b05..27451d5 100644
--- a/builtin-diff.c
+++ b/builtin-diff.c
@@ -233,7 +233,7 @@ 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-log.c b/builtin-log.c
index c4ceee0..c8feb0f 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)
@@ -74,3 +78,171 @@ 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 if (!strcmp(argv[i], "--attach"))
+			rev.mime_boundary = git_version_string;
+		else if (!strncmp(argv[i], "--attach=", 9))
+			rev.mime_boundary = argv[i] + 9;
+		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) {
+			if (rev.mime_boundary)
+				printf("\n--%s%s--\n\n\n",
+				       mime_boundary_leader,
+				       rev.mime_boundary);
+			else
+				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-ls-files.c b/builtin-ls-files.c
index 3a0c5f2..8dae9f7 100644
--- a/builtin-ls-files.c
+++ b/builtin-ls-files.c
@@ -5,24 +5,21 @@
  *
  * Copyright (C) Linus Torvalds, 2005
  */
-#include <dirent.h>
 #include <fnmatch.h>
 
 #include "cache.h"
 #include "quote.h"
+#include "dir.h"
 #include "builtin.h"
 
 static int abbrev = 0;
 static int show_deleted = 0;
 static int show_cached = 0;
 static int show_others = 0;
-static int show_ignored = 0;
 static int show_stage = 0;
 static int show_unmerged = 0;
 static int show_modified = 0;
 static int show_killed = 0;
-static int show_other_directories = 0;
-static int hide_empty_directories = 0;
 static int show_valid_bit = 0;
 static int line_terminator = '\n';
 
@@ -39,309 +36,6 @@ static const char *tag_other = "";
 static const char *tag_killed = "";
 static const char *tag_modified = "";
 
-static const char *exclude_per_dir = NULL;
-
-/* We maintain three exclude pattern lists:
- * EXC_CMDL lists patterns explicitly given on the command line.
- * EXC_DIRS lists patterns obtained from per-directory ignore files.
- * EXC_FILE lists patterns from fallback ignore files.
- */
-#define EXC_CMDL 0
-#define EXC_DIRS 1
-#define EXC_FILE 2
-static struct exclude_list {
-	int nr;
-	int alloc;
-	struct exclude {
-		const char *pattern;
-		const char *base;
-		int baselen;
-	} **excludes;
-} exclude_list[3];
-
-static void add_exclude(const char *string, const char *base,
-			int baselen, struct exclude_list *which)
-{
-	struct exclude *x = xmalloc(sizeof (*x));
-
-	x->pattern = string;
-	x->base = base;
-	x->baselen = baselen;
-	if (which->nr == which->alloc) {
-		which->alloc = alloc_nr(which->alloc);
-		which->excludes = realloc(which->excludes,
-					  which->alloc * sizeof(x));
-	}
-	which->excludes[which->nr++] = x;
-}
-
-static int add_excludes_from_file_1(const char *fname,
-				    const char *base,
-				    int baselen,
-				    struct exclude_list *which)
-{
-	int fd, i;
-	long size;
-	char *buf, *entry;
-
-	fd = open(fname, O_RDONLY);
-	if (fd < 0)
-		goto err;
-	size = lseek(fd, 0, SEEK_END);
-	if (size < 0)
-		goto err;
-	lseek(fd, 0, SEEK_SET);
-	if (size == 0) {
-		close(fd);
-		return 0;
-	}
-	buf = xmalloc(size+1);
-	if (read(fd, buf, size) != size)
-		goto err;
-	close(fd);
-
-	buf[size++] = '\n';
-	entry = buf;
-	for (i = 0; i < size; i++) {
-		if (buf[i] == '\n') {
-			if (entry != buf + i && entry[0] != '#') {
-				buf[i - (i && buf[i-1] == '\r')] = 0;
-				add_exclude(entry, base, baselen, which);
-			}
-			entry = buf + i + 1;
-		}
-	}
-	return 0;
-
- err:
-	if (0 <= fd)
-		close(fd);
-	return -1;
-}
-
-static void add_excludes_from_file(const char *fname)
-{
-	if (add_excludes_from_file_1(fname, "", 0,
-				     &exclude_list[EXC_FILE]) < 0)
-		die("cannot use %s as an exclude file", fname);
-}
-
-static int push_exclude_per_directory(const char *base, int baselen)
-{
-	char exclude_file[PATH_MAX];
-	struct exclude_list *el = &exclude_list[EXC_DIRS];
-	int current_nr = el->nr;
-
-	if (exclude_per_dir) {
-		memcpy(exclude_file, base, baselen);
-		strcpy(exclude_file + baselen, exclude_per_dir);
-		add_excludes_from_file_1(exclude_file, base, baselen, el);
-	}
-	return current_nr;
-}
-
-static void pop_exclude_per_directory(int stk)
-{
-	struct exclude_list *el = &exclude_list[EXC_DIRS];
-
-	while (stk < el->nr)
-		free(el->excludes[--el->nr]);
-}
-
-/* Scan the list and let the last match determines the fate.
- * Return 1 for exclude, 0 for include and -1 for undecided.
- */
-static int excluded_1(const char *pathname,
-		      int pathlen,
-		      struct exclude_list *el)
-{
-	int i;
-
-	if (el->nr) {
-		for (i = el->nr - 1; 0 <= i; i--) {
-			struct exclude *x = el->excludes[i];
-			const char *exclude = x->pattern;
-			int to_exclude = 1;
-
-			if (*exclude == '!') {
-				to_exclude = 0;
-				exclude++;
-			}
-
-			if (!strchr(exclude, '/')) {
-				/* match basename */
-				const char *basename = strrchr(pathname, '/');
-				basename = (basename) ? basename+1 : pathname;
-				if (fnmatch(exclude, basename, 0) == 0)
-					return to_exclude;
-			}
-			else {
-				/* match with FNM_PATHNAME:
-				 * exclude has base (baselen long) implicitly
-				 * in front of it.
-				 */
-				int baselen = x->baselen;
-				if (*exclude == '/')
-					exclude++;
-
-				if (pathlen < baselen ||
-				    (baselen && pathname[baselen-1] != '/') ||
-				    strncmp(pathname, x->base, baselen))
-				    continue;
-
-				if (fnmatch(exclude, pathname+baselen,
-					    FNM_PATHNAME) == 0)
-					return to_exclude;
-			}
-		}
-	}
-	return -1; /* undecided */
-}
-
-static int excluded(const char *pathname)
-{
-	int pathlen = strlen(pathname);
-	int st;
-
-	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
-		switch (excluded_1(pathname, pathlen, &exclude_list[st])) {
-		case 0:
-			return 0;
-		case 1:
-			return 1;
-		}
-	}
-	return 0;
-}
-
-struct nond_on_fs {
-	int len;
-	char name[FLEX_ARRAY]; /* more */
-};
-
-static struct nond_on_fs **dir;
-static int nr_dir;
-static int dir_alloc;
-
-static void add_name(const char *pathname, int len)
-{
-	struct nond_on_fs *ent;
-
-	if (cache_name_pos(pathname, len) >= 0)
-		return;
-
-	if (nr_dir == dir_alloc) {
-		dir_alloc = alloc_nr(dir_alloc);
-		dir = xrealloc(dir, dir_alloc*sizeof(ent));
-	}
-	ent = xmalloc(sizeof(*ent) + len + 1);
-	ent->len = len;
-	memcpy(ent->name, pathname, len);
-	ent->name[len] = 0;
-	dir[nr_dir++] = ent;
-}
-
-static int dir_exists(const char *dirname, int len)
-{
-	int pos = cache_name_pos(dirname, len);
-	if (pos >= 0)
-		return 1;
-	pos = -pos-1;
-	if (pos >= active_nr) /* can't */
-		return 0;
-	return !strncmp(active_cache[pos]->name, dirname, len);
-}
-
-/*
- * Read a directory tree. We currently ignore anything but
- * directories, regular files and symlinks. That's because git
- * doesn't handle them at all yet. Maybe that will change some
- * day.
- *
- * Also, we ignore the name ".git" (even if it is not a directory).
- * That likely will not change.
- */
-static int read_directory(const char *path, const char *base, int baselen)
-{
-	DIR *fdir = opendir(path);
-	int contents = 0;
-
-	if (fdir) {
-		int exclude_stk;
-		struct dirent *de;
-		char fullname[MAXPATHLEN + 1];
-		memcpy(fullname, base, baselen);
-
-		exclude_stk = push_exclude_per_directory(base, baselen);
-
-		while ((de = readdir(fdir)) != NULL) {
-			int len;
-
-			if ((de->d_name[0] == '.') &&
-			    (de->d_name[1] == 0 ||
-			     !strcmp(de->d_name + 1, ".") ||
-			     !strcmp(de->d_name + 1, "git")))
-				continue;
-			len = strlen(de->d_name);
-			memcpy(fullname + baselen, de->d_name, len+1);
-			if (excluded(fullname) != show_ignored) {
-				if (!show_ignored || DTYPE(de) != DT_DIR) {
-					continue;
-				}
-			}
-
-			switch (DTYPE(de)) {
-			struct stat st;
-			int subdir, rewind_base;
-			default:
-				continue;
-			case DT_UNKNOWN:
-				if (lstat(fullname, &st))
-					continue;
-				if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
-					break;
-				if (!S_ISDIR(st.st_mode))
-					continue;
-				/* fallthrough */
-			case DT_DIR:
-				memcpy(fullname + baselen + len, "/", 2);
-				len++;
-				rewind_base = nr_dir;
-				subdir = read_directory(fullname, fullname,
-				                        baselen + len);
-				if (show_other_directories &&
-				    (subdir || !hide_empty_directories) &&
-				    !dir_exists(fullname, baselen + len)) {
-					// Rewind the read subdirectory
-					while (nr_dir > rewind_base)
-						free(dir[--nr_dir]);
-					break;
-				}
-				contents += subdir;
-				continue;
-			case DT_REG:
-			case DT_LNK:
-				break;
-			}
-			add_name(fullname, baselen + len);
-			contents++;
-		}
-		closedir(fdir);
-
-		pop_exclude_per_directory(exclude_stk);
-	}
-
-	return contents;
-}
-
-static int cmp_name(const void *p1, const void *p2)
-{
-	const struct nond_on_fs *e1 = *(const struct nond_on_fs **)p1;
-	const struct nond_on_fs *e2 = *(const struct nond_on_fs **)p2;
-
-	return cache_name_compare(e1->name, e1->len,
-				  e2->name, e2->len);
-}
 
 /*
  * Match a pathspec against a filename. The first "len" characters
@@ -378,7 +72,7 @@ static int match(const char **spec, char *ps_matched,
 	return 0;
 }
 
-static void show_dir_entry(const char *tag, struct nond_on_fs *ent)
+static void show_dir_entry(const char *tag, struct dir_entry *ent)
 {
 	int len = prefix_len;
 	int offset = prefix_offset;
@@ -394,14 +88,14 @@ static void show_dir_entry(const char *tag, struct nond_on_fs *ent)
 	putchar(line_terminator);
 }
 
-static void show_other_files(void)
+static void show_other_files(struct dir_struct *dir)
 {
 	int i;
-	for (i = 0; i < nr_dir; i++) {
+	for (i = 0; i < dir->nr; i++) {
 		/* We should not have a matching entry, but we
 		 * may have an unmerged entry for this path.
 		 */
-		struct nond_on_fs *ent = dir[i];
+		struct dir_entry *ent = dir->entries[i];
 		int pos = cache_name_pos(ent->name, ent->len);
 		struct cache_entry *ce;
 		if (0 <= pos)
@@ -417,11 +111,11 @@ static void show_other_files(void)
 	}
 }
 
-static void show_killed_files(void)
+static void show_killed_files(struct dir_struct *dir)
 {
 	int i;
-	for (i = 0; i < nr_dir; i++) {
-		struct nond_on_fs *ent = dir[i];
+	for (i = 0; i < dir->nr; i++) {
+		struct dir_entry *ent = dir->entries[i];
 		char *cp, *sp;
 		int pos, len, killed = 0;
 
@@ -462,7 +156,7 @@ static void show_killed_files(void)
 			}
 		}
 		if (killed)
-			show_dir_entry(tag_killed, dir[i]);
+			show_dir_entry(tag_killed, dir->entries[i]);
 	}
 }
 
@@ -513,7 +207,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	}
 }
 
-static void show_files(void)
+static void show_files(struct dir_struct *dir)
 {
 	int i;
 
@@ -522,39 +216,18 @@ static void show_files(void)
 		const char *path = ".", *base = "";
 		int baselen = prefix_len;
 
-		if (baselen) {
+		if (baselen)
 			path = base = prefix;
-			if (exclude_per_dir) {
-				char *p, *pp = xmalloc(baselen+1);
-				memcpy(pp, prefix, baselen+1);
-				p = pp;
-				while (1) {
-					char save = *p;
-					*p = 0;
-					push_exclude_per_directory(pp, p-pp);
-					*p++ = save;
-					if (!save)
-						break;
-					p = strchr(p, '/');
-					if (p)
-						p++;
-					else
-						p = pp + baselen;
-				}
-				free(pp);
-			}
-		}
-		read_directory(path, base, baselen);
-		qsort(dir, nr_dir, sizeof(struct nond_on_fs *), cmp_name);
+		read_directory(dir, path, base, baselen);
 		if (show_others)
-			show_other_files();
+			show_other_files(dir);
 		if (show_killed)
-			show_killed_files();
+			show_killed_files(dir);
 	}
 	if (show_cached | show_stage) {
 		for (i = 0; i < active_nr; i++) {
 			struct cache_entry *ce = active_cache[i];
-			if (excluded(ce->name) != show_ignored)
+			if (excluded(dir, ce->name) != dir->show_ignored)
 				continue;
 			if (show_unmerged && !ce_stage(ce))
 				continue;
@@ -566,7 +239,7 @@ static void show_files(void)
 			struct cache_entry *ce = active_cache[i];
 			struct stat st;
 			int err;
-			if (excluded(ce->name) != show_ignored)
+			if (excluded(dir, ce->name) != dir->show_ignored)
 				continue;
 			err = lstat(ce->name, &st);
 			if (show_deleted && err)
@@ -653,7 +326,9 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 {
 	int i;
 	int exc_given = 0;
+	struct dir_struct dir;
 
+	memset(&dir, 0, sizeof(dir));
 	prefix = setup_git_directory();
 	if (prefix)
 		prefix_offset = strlen(prefix);
@@ -698,7 +373,7 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 			continue;
 		}
 		if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) {
-			show_ignored = 1;
+			dir.show_ignored = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) {
@@ -710,11 +385,11 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 			continue;
 		}
 		if (!strcmp(arg, "--directory")) {
-			show_other_directories = 1;
+			dir.show_other_directories = 1;
 			continue;
 		}
 		if (!strcmp(arg, "--no-empty-directory")) {
-			hide_empty_directories = 1;
+			dir.hide_empty_directories = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-u") || !strcmp(arg, "--unmerged")) {
@@ -727,27 +402,27 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 		}
 		if (!strcmp(arg, "-x") && i+1 < argc) {
 			exc_given = 1;
-			add_exclude(argv[++i], "", 0, &exclude_list[EXC_CMDL]);
+			add_exclude(argv[++i], "", 0, &dir.exclude_list[EXC_CMDL]);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude=", 10)) {
 			exc_given = 1;
-			add_exclude(arg+10, "", 0, &exclude_list[EXC_CMDL]);
+			add_exclude(arg+10, "", 0, &dir.exclude_list[EXC_CMDL]);
 			continue;
 		}
 		if (!strcmp(arg, "-X") && i+1 < argc) {
 			exc_given = 1;
-			add_excludes_from_file(argv[++i]);
+			add_excludes_from_file(&dir, argv[++i]);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude-from=", 15)) {
 			exc_given = 1;
-			add_excludes_from_file(arg+15);
+			add_excludes_from_file(&dir, arg+15);
 			continue;
 		}
 		if (!strncmp(arg, "--exclude-per-directory=", 24)) {
 			exc_given = 1;
-			exclude_per_dir = arg + 24;
+			dir.exclude_per_dir = arg + 24;
 			continue;
 		}
 		if (!strcmp(arg, "--full-name")) {
@@ -789,7 +464,7 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 		ps_matched = xcalloc(1, num);
 	}
 
-	if (show_ignored && !exc_given) {
+	if (dir.show_ignored && !exc_given) {
 		fprintf(stderr, "%s: --ignored needs some exclude pattern\n",
 			argv[0]);
 		exit(1);
@@ -803,7 +478,7 @@ int cmd_ls_files(int argc, const char **argv, char** envp)
 	read_cache();
 	if (prefix)
 		prune_cache();
-	show_files();
+	show_files(&dir);
 
 	if (ps_matched) {
 		/* We need to make sure all pathspec matched otherwise
diff --git a/builtin-read-tree.c b/builtin-read-tree.c
index ec40d01..629d151 100644
--- a/builtin-read-tree.c
+++ b/builtin-read-tree.c
@@ -9,6 +9,7 @@
 
 #include "object.h"
 #include "tree.h"
+#include "cache-tree.h"
 #include <sys/time.h>
 #include <signal.h>
 #include "builtin.h"
@@ -22,6 +23,7 @@ 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;
@@ -370,7 +372,8 @@ 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;
 	}
 
@@ -427,6 +430,12 @@ 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);
+}
+
 /*
  * We do not want to remove or overwrite a working tree file that
  * is not tracked.
@@ -457,10 +466,13 @@ static int merged_entry(struct cache_entry *merge, struct cache_entry *old)
 			*merge = *old;
 		} else {
 			verify_uptodate(old);
+			invalidate_ce_path(old);
 		}
 	}
-	else
+	else {
 		verify_absent(merge->name, "overwritten");
+		invalidate_ce_path(merge);
+	}
 
 	merge->ce_flags &= ~htons(CE_STAGEMASK);
 	add_cache_entry(merge, ADD_CACHE_OK_TO_ADD);
@@ -475,6 +487,7 @@ static int deleted_entry(struct cache_entry *ce, struct cache_entry *old)
 		verify_absent(ce->name, "removed");
 	ce->ce_mode = 0;
 	add_cache_entry(ce, ADD_CACHE_OK_TO_ADD);
+	invalidate_ce_path(ce);
 	return 1;
 }
 
@@ -710,6 +723,28 @@ static int twoway_merge(struct cache_entry **src)
 }
 
 /*
+ * Bind merge.
+ *
+ * Keep the index entries at stage0, collapse stage1 but make sure
+ * stage0 does not have anything there.
+ */
+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 && old)
+		die("Entry '%s' overlaps.  Cannot bind.", a->name);
+	if (!a)
+		return keep_entry(old);
+	else
+		return merged_entry(a, NULL);
+}
+
+/*
  * One-way merge.
  *
  * The rule is:
@@ -724,8 +759,10 @@ 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 deleted_entry(old, old);
+	}
 	if (old && same(old, a)) {
 		if (reset) {
 			struct stat st;
@@ -750,6 +787,7 @@ 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)
@@ -760,7 +798,40 @@ 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;
 
@@ -805,9 +876,24 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 			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;
@@ -828,7 +914,7 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 
 		/* "-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");
@@ -850,21 +936,39 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 	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;
 		}
 
@@ -875,6 +979,18 @@ int cmd_read_tree(int argc, const char **argv, char **envp)
 	}
 
 	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/builtin-rev-list.c b/builtin-rev-list.c
index 446802d..f11dbd6 100644
--- a/builtin-rev-list.c
+++ b/builtin-rev-list.c
@@ -85,7 +85,7 @@ 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, NULL);
 		printf("%s%c", pretty_header, hdr_termination);
 	}
 	fflush(stdout);
diff --git a/builtin-rm.c b/builtin-rm.c
new file mode 100644
index 0000000..e7793a2
--- /dev/null
+++ b/builtin-rm.c
@@ -0,0 +1,152 @@
+/*
+ * "git rm" builtin command
+ *
+ * Copyright (C) Linus Torvalds 2006
+ */
+#include "cache.h"
+#include "builtin.h"
+#include "dir.h"
+#include "cache-tree.h"
+
+static const char builtin_rm_usage[] =
+"git-rm [-n] [-v] [-f] <filepattern>...";
+
+static struct {
+	int nr, alloc;
+	const char **name;
+} list;
+
+static void add_list(const char *name)
+{
+	if (list.nr >= list.alloc) {
+		list.alloc = alloc_nr(list.alloc);
+		list.name = xrealloc(list.name, list.alloc * sizeof(const char *));
+	}
+	list.name[list.nr++] = name;
+}
+
+static int remove_file(const char *name)
+{
+	int ret;
+	char *slash;
+
+	ret = unlink(name);
+	if (!ret && (slash = strrchr(name, '/'))) {
+		char *n = strdup(name);
+		do {
+			n[slash - name] = 0;
+			name = n;
+		} while (!rmdir(name) && (slash = strrchr(name, '/')));
+	}
+	return ret;
+}
+
+static struct cache_file cache_file;
+
+int cmd_rm(int argc, const char **argv, char **envp)
+{
+	int i, newfd;
+	int verbose = 0, show_only = 0, force = 0;
+	const char *prefix = setup_git_directory();
+	const char **pathspec;
+	char *seen;
+
+	git_config(git_default_config);
+
+	newfd = hold_index_file_for_update(&cache_file, get_index_file());
+	if (newfd < 0)
+		die("unable to create new index file");
+
+	if (read_cache() < 0)
+		die("index file corrupt");
+
+	for (i = 1 ; i < argc ; i++) {
+		const char *arg = argv[i];
+
+		if (*arg != '-')
+			break;
+		if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		if (!strcmp(arg, "-n")) {
+			show_only = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-v")) {
+			verbose = 1;
+			continue;
+		}
+		if (!strcmp(arg, "-f")) {
+			force = 1;
+			continue;
+		}
+		die(builtin_rm_usage);
+	}
+	pathspec = get_pathspec(prefix, argv + i);
+
+	seen = NULL;
+	if (pathspec) {
+		for (i = 0; pathspec[i] ; i++)
+			/* nothing */;
+		seen = xmalloc(i);
+		memset(seen, 0, i);
+	}
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen))
+			continue;
+		add_list(ce->name);
+	}
+
+	if (pathspec) {
+		const char *match;
+		for (i = 0; (match = pathspec[i]) != NULL ; i++) {
+			if (*match && !seen[i])
+				die("pathspec '%s' did not match any files", match);
+		}
+	}
+
+	/*
+	 * First remove the names from the index: we won't commit
+	 * the index unless all of them succeed
+	 */
+	for (i = 0; i < list.nr; i++) {
+		const char *path = list.name[i];
+		printf("rm '%s'\n", path);
+
+		if (remove_file_from_cache(path))
+			die("git rm: unable to remove %s", path);
+		cache_tree_invalidate_path(active_cache_tree, path);
+	}
+
+	/*
+	 * Then, if we used "-f", remove the filenames from the
+	 * workspace. If we fail to remove the first one, we
+	 * abort the "git rm" (but once we've successfully removed
+	 * any file at all, we'll go ahead and commit to it all:
+	 * by then we've already committed ourself and can't fail
+	 * in the middle)
+	 */
+	if (force) {
+		int removed = 0;
+		for (i = 0; i < list.nr; i++) {
+			const char *path = list.name[i];
+			if (!remove_file(path)) {
+				removed = 1;
+				continue;
+			}
+			if (!removed)
+				die("git rm: %s: %s", path, strerror(errno));
+		}
+	}
+
+	if (active_cache_changed) {
+		if (write_cache(newfd, active_cache, active_nr) ||
+		    commit_index_file(&cache_file))
+			die("Unable to write new index file");
+	}
+
+	return 0;
+}
diff --git a/builtin-show-branch.c b/builtin-show-branch.c
index 3af24e7..2895140 100644
--- a/builtin-show-branch.c
+++ b/builtin-show-branch.c
@@ -260,7 +260,7 @@ 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, NULL);
 	else
 		strcpy(pretty, "(unavailable)");
 	if (!strncmp(pretty, "[PATCH] ", 8))
diff --git a/builtin.h b/builtin.h
index 2249c5f..714b975 100644
--- a/builtin.h
+++ b/builtin.h
@@ -20,10 +20,13 @@ 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);
+extern int cmd_rm(int argc, const char **argv, char **envp);
+extern int cmd_add(int argc, const char **argv, char **envp);
 extern int cmd_rev_list(int argc, const char **argv, char **envp);
 extern int cmd_check_ref_format(int argc, const char **argv, char **envp);
 extern int cmd_init_db(int argc, const char **argv, char **envp);
diff --git a/cache-tree.c b/cache-tree.c
new file mode 100644
index 0000000..d9f7e1e
--- /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 0000000..119407e
--- /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 afa8e4f..31755c8 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"
@@ -142,6 +143,7 @@ extern void verify_non_filename(const char *prefix, const char *name);
 /* Initialize and use the cache information */
 extern int read_cache(void);
 extern int write_cache(int newfd, struct cache_entry **cache, int entries);
+extern int verify_path(const char *path);
 extern int cache_name_pos(const char *name, int namelen);
 #define ADD_CACHE_OK_TO_ADD 1		/* Ok to add */
 #define ADD_CACHE_OK_TO_REPLACE 2	/* Ok to replace file/directory */
@@ -257,6 +259,7 @@ 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 cc3a745..9876af6 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 4a26070..94f470b 100644
--- a/commit.c
+++ b/commit.c
@@ -30,6 +30,7 @@ struct cmt_fmt_map {
 	{ "raw",	1,	CMIT_FMT_RAW },
 	{ "medium",	1,	CMIT_FMT_MEDIUM },
 	{ "short",	1,	CMIT_FMT_SHORT },
+	{ "email",	1,	CMIT_FMT_EMAIL },
 	{ "full",	5,	CMIT_FMT_FULL },
 	{ "fuller",	5,	CMIT_FMT_FULLER },
 	{ "oneline",	1,	CMIT_FMT_ONELINE },
@@ -421,6 +422,46 @@ static int get_one_line(const char *msg, unsigned long len)
 	return ret;
 }
 
+static int is_rfc2047_special(char ch)
+{
+	return ((ch & 0x80) || (ch == '=') || (ch == '?') || (ch == '_'));
+}
+
+static int add_rfc2047(char *buf, const char *line, int len)
+{
+	char *bp = buf;
+	int i, needquote;
+	static const char q_utf8[] = "=?utf-8?q?";
+
+	for (i = needquote = 0; !needquote && i < len; i++) {
+		unsigned ch = line[i];
+		if (ch & 0x80)
+			needquote++;
+		if ((i + 1 < len) &&
+		    (ch == '=' && line[i+1] == '?'))
+			needquote++;
+	}
+	if (!needquote)
+		return sprintf(buf, "%.*s", len, line);
+
+	memcpy(bp, q_utf8, sizeof(q_utf8)-1);
+	bp += sizeof(q_utf8)-1;
+	for (i = 0; i < len; i++) {
+		unsigned ch = line[i];
+		if (is_rfc2047_special(ch)) {
+			sprintf(bp, "=%02X", ch);
+			bp += 3;
+		}
+		else if (ch == ' ')
+			*bp++ = '_';
+		else
+			*bp++ = ch;
+	}
+	memcpy(bp, "?=", 2);
+	bp += 2;
+	return bp - buf;
+}
+
 static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf, const char *line)
 {
 	char *date;
@@ -438,13 +479,35 @@ 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);
 
-	ret = sprintf(buf, "%s: %.*s%.*s\n", what,
-		      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
-		      filler, namelen, line);
+	if (fmt == CMIT_FMT_EMAIL) {
+		char *name_tail = strchr(line, '<');
+		int display_name_length;
+		if (!name_tail)
+			return 0;
+		while (line < name_tail && isspace(name_tail[-1]))
+			name_tail--;
+		display_name_length = name_tail - line;
+		filler = "";
+		strcpy(buf, "From: ");
+		ret = strlen(buf);
+		ret += add_rfc2047(buf + ret, line, display_name_length);
+		memcpy(buf + ret, name_tail, namelen - display_name_length);
+		ret += namelen - display_name_length;
+		buf[ret++] = '\n';
+	}
+	else {
+		ret = sprintf(buf, "%s: %.*s%.*s\n", what,
+			      (fmt == CMIT_FMT_FULLER) ? 4 : 0,
+			      filler, namelen, line);
+	}
 	switch (fmt) {
 	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;
@@ -455,10 +518,12 @@ 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;
 }
 
@@ -467,7 +532,8 @@ 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:");
@@ -486,13 +552,30 @@ 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, const char *after_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;
+	int plain_non_ascii = 0;
+
+	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
+		indent = 0;
+
+	/* After-subject is used to pass in Content-Type: multipart
+	 * MIME header; in that case we do not have to do the
+	 * plaintext content type even if the commit message has
+	 * non 7-bit ASCII character.  Otherwise, check if we need
+	 * to say this is not a 7-bit ASCII.
+	 */
+	if (fmt == CMIT_FMT_EMAIL && !after_subject) {
+		int i;
+		for (i = 0; !plain_non_ascii && msg[i] && i < len; i++)
+			if (msg[i] & 0x80)
+				plain_non_ascii = 1;
+	}
 
 	for (;;) {
 		const char *line = msg;
@@ -516,7 +599,7 @@ 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;
 			}
@@ -554,20 +637,47 @@ 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;
 		}
 
-		memset(buf + offset, ' ', indent);
-		memcpy(buf + offset + indent, line, linelen);
-		offset += linelen + indent;
+		if (subject) {
+			int slen = strlen(subject);
+			memcpy(buf + offset, subject, slen);
+			offset += slen;
+			offset += add_rfc2047(buf + offset, line, linelen);
+		}
+		else {
+			memset(buf + offset, ' ', indent);
+			memcpy(buf + offset + indent, line, linelen);
+			offset += linelen + indent;
+		}
+		buf[offset++] = '\n';
 		if (fmt == CMIT_FMT_ONELINE)
 			break;
+		if (subject && plain_non_ascii) {
+			static const char header[] =
+				"Content-Type: text/plain; charset=UTF-8\n"
+				"Content-Transfer-Encoding: 8bit\n";
+			memcpy(buf + offset, header, sizeof(header)-1);
+			offset += sizeof(header)-1;
+		}
+		if (after_subject) {
+			int slen = strlen(after_subject);
+			if (slen > space - offset - 1)
+				slen = space - offset - 1;
+			memcpy(buf + offset, after_subject, slen);
+			offset += slen;
+			after_subject = NULL;
+		}
+		subject = NULL;
 	}
 	while (offset && isspace(buf[offset-1]))
 		offset--;
diff --git a/commit.h b/commit.h
index de142af..c9de167 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, const char *after_subject);
 
 /** Removes the first commit from a list sorted by date, and adds all
  * of its parents.
diff --git a/connect.c b/connect.c
index 6a8f8a6..54f7bf7 100644
--- a/connect.c
+++ b/connect.c
@@ -100,7 +100,7 @@ int path_match(const char *path, int nr, char **match)
 		if (pathlen > len && path[pathlen - len - 1] != '/')
 			continue;
 		*s = 0;
-		return 1;
+		return (i + 1);
 	}
 	return 0;
 }
diff --git a/date.c b/date.c
index 034d722..365dc3b 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/diff.c b/diff.c
index 3a2a175..a7bb9b9 100644
--- a/diff.c
+++ b/diff.c
@@ -299,6 +299,7 @@ static void diffstat_consume(void *priv, char *line, unsigned long len)
 
 static const char pluses[] = "++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++";
 static const char minuses[]= "----------------------------------------------------------------------";
+const char mime_boundary_leader[] = "------------";
 
 static void show_stats(struct diffstat_t* data)
 {
@@ -1988,7 +1989,10 @@ void diff_flush(struct diff_options *options)
 		show_stats(diffstat);
 		free(diffstat);
 		diffstat = NULL;
-		putchar(options->line_termination);
+		if (options->stat_sep)
+			fputs(options->stat_sep, stdout);
+		else
+			putchar(options->line_termination);
 	}
 	for (i = 0; i < q->nr; i++) {
 		struct diff_filepair *p = q->queue[i];
diff --git a/diff.h b/diff.h
index c672277..4fc597c 100644
--- a/diff.h
+++ b/diff.h
@@ -44,6 +44,7 @@ struct diff_options {
 	int rename_limit;
 	int setup;
 	int abbrev;
+	const char *stat_sep;
 
 	int nr_paths;
 	const char **paths;
@@ -52,6 +53,8 @@ struct diff_options {
 	add_remove_fn_t add_remove;
 };
 
+extern const char mime_boundary_leader[];
+
 extern void diff_tree_setup_paths(const char **paths, struct diff_options *);
 extern void diff_tree_release_paths(struct diff_options *);
 extern int diff_tree(struct tree_desc *t1, struct tree_desc *t2,
diff --git a/dir.c b/dir.c
new file mode 100644
index 0000000..d778ecd
--- /dev/null
+++ b/dir.c
@@ -0,0 +1,401 @@
+/*
+ * This handles recursive filename detection with exclude
+ * files, index knowledge etc..
+ *
+ * Copyright (C) Linus Torvalds, 2005-2006
+ *		 Junio Hamano, 2005-2006
+ */
+#include <dirent.h>
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "dir.h"
+
+int common_prefix(const char **pathspec)
+{
+	const char *path, *slash, *next;
+	int prefix;
+
+	if (!pathspec)
+		return 0;
+
+	path = *pathspec;
+	slash = strrchr(path, '/');
+	if (!slash)
+		return 0;
+
+	prefix = slash - path + 1;
+	while ((next = *++pathspec) != NULL) {
+		int len = strlen(next);
+		if (len >= prefix && !memcmp(path, next, len))
+			continue;
+		for (;;) {
+			if (!len)
+				return 0;
+			if (next[--len] != '/')
+				continue;
+			if (memcmp(path, next, len+1))
+				continue;
+			prefix = len + 1;
+			break;
+		}
+	}
+	return prefix;
+}
+
+static int match_one(const char *match, const char *name, int namelen)
+{
+	int matchlen;
+
+	/* If the match was just the prefix, we matched */
+	matchlen = strlen(match);
+	if (!matchlen)
+		return 1;
+
+	/*
+	 * If we don't match the matchstring exactly,
+	 * we need to match by fnmatch
+	 */
+	if (strncmp(match, name, matchlen))
+		return !fnmatch(match, name, 0);
+
+	/*
+	 * If we did match the string exactly, we still
+	 * need to make sure that it happened on a path
+	 * component boundary (ie either the last character
+	 * of the match was '/', or the next character of
+	 * the name was '/' or the terminating NUL.
+	 */
+	return	match[matchlen-1] == '/' ||
+		name[matchlen] == '/' ||
+		!name[matchlen];
+}
+
+int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen)
+{
+	int retval;
+	const char *match;
+
+	name += prefix;
+	namelen -= prefix;
+
+	for (retval = 0; (match = *pathspec++) != NULL; seen++) {
+		if (retval & *seen)
+			continue;
+		match += prefix;
+		if (match_one(match, name, namelen)) {
+			retval = 1;
+			*seen = 1;
+		}
+	}
+	return retval;
+}
+
+void add_exclude(const char *string, const char *base,
+		 int baselen, struct exclude_list *which)
+{
+	struct exclude *x = xmalloc(sizeof (*x));
+
+	x->pattern = string;
+	x->base = base;
+	x->baselen = baselen;
+	if (which->nr == which->alloc) {
+		which->alloc = alloc_nr(which->alloc);
+		which->excludes = realloc(which->excludes,
+					  which->alloc * sizeof(x));
+	}
+	which->excludes[which->nr++] = x;
+}
+
+static int add_excludes_from_file_1(const char *fname,
+				    const char *base,
+				    int baselen,
+				    struct exclude_list *which)
+{
+	int fd, i;
+	long size;
+	char *buf, *entry;
+
+	fd = open(fname, O_RDONLY);
+	if (fd < 0)
+		goto err;
+	size = lseek(fd, 0, SEEK_END);
+	if (size < 0)
+		goto err;
+	lseek(fd, 0, SEEK_SET);
+	if (size == 0) {
+		close(fd);
+		return 0;
+	}
+	buf = xmalloc(size+1);
+	if (read(fd, buf, size) != size)
+		goto err;
+	close(fd);
+
+	buf[size++] = '\n';
+	entry = buf;
+	for (i = 0; i < size; i++) {
+		if (buf[i] == '\n') {
+			if (entry != buf + i && entry[0] != '#') {
+				buf[i - (i && buf[i-1] == '\r')] = 0;
+				add_exclude(entry, base, baselen, which);
+			}
+			entry = buf + i + 1;
+		}
+	}
+	return 0;
+
+ err:
+	if (0 <= fd)
+		close(fd);
+	return -1;
+}
+
+void add_excludes_from_file(struct dir_struct *dir, const char *fname)
+{
+	if (add_excludes_from_file_1(fname, "", 0,
+				     &dir->exclude_list[EXC_FILE]) < 0)
+		die("cannot use %s as an exclude file", fname);
+}
+
+static int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
+{
+	char exclude_file[PATH_MAX];
+	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
+	int current_nr = el->nr;
+
+	if (dir->exclude_per_dir) {
+		memcpy(exclude_file, base, baselen);
+		strcpy(exclude_file + baselen, dir->exclude_per_dir);
+		add_excludes_from_file_1(exclude_file, base, baselen, el);
+	}
+	return current_nr;
+}
+
+static void pop_exclude_per_directory(struct dir_struct *dir, int stk)
+{
+	struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
+
+	while (stk < el->nr)
+		free(el->excludes[--el->nr]);
+}
+
+/* Scan the list and let the last match determines the fate.
+ * Return 1 for exclude, 0 for include and -1 for undecided.
+ */
+static int excluded_1(const char *pathname,
+		      int pathlen,
+		      struct exclude_list *el)
+{
+	int i;
+
+	if (el->nr) {
+		for (i = el->nr - 1; 0 <= i; i--) {
+			struct exclude *x = el->excludes[i];
+			const char *exclude = x->pattern;
+			int to_exclude = 1;
+
+			if (*exclude == '!') {
+				to_exclude = 0;
+				exclude++;
+			}
+
+			if (!strchr(exclude, '/')) {
+				/* match basename */
+				const char *basename = strrchr(pathname, '/');
+				basename = (basename) ? basename+1 : pathname;
+				if (fnmatch(exclude, basename, 0) == 0)
+					return to_exclude;
+			}
+			else {
+				/* match with FNM_PATHNAME:
+				 * exclude has base (baselen long) implicitly
+				 * in front of it.
+				 */
+				int baselen = x->baselen;
+				if (*exclude == '/')
+					exclude++;
+
+				if (pathlen < baselen ||
+				    (baselen && pathname[baselen-1] != '/') ||
+				    strncmp(pathname, x->base, baselen))
+				    continue;
+
+				if (fnmatch(exclude, pathname+baselen,
+					    FNM_PATHNAME) == 0)
+					return to_exclude;
+			}
+		}
+	}
+	return -1; /* undecided */
+}
+
+int excluded(struct dir_struct *dir, const char *pathname)
+{
+	int pathlen = strlen(pathname);
+	int st;
+
+	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
+		switch (excluded_1(pathname, pathlen, &dir->exclude_list[st])) {
+		case 0:
+			return 0;
+		case 1:
+			return 1;
+		}
+	}
+	return 0;
+}
+
+static void add_name(struct dir_struct *dir, const char *pathname, int len)
+{
+	struct dir_entry *ent;
+
+	if (cache_name_pos(pathname, len) >= 0)
+		return;
+
+	if (dir->nr == dir->alloc) {
+		int alloc = alloc_nr(dir->alloc);
+		dir->alloc = alloc;
+		dir->entries = xrealloc(dir->entries, alloc*sizeof(ent));
+	}
+	ent = xmalloc(sizeof(*ent) + len + 1);
+	ent->len = len;
+	memcpy(ent->name, pathname, len);
+	ent->name[len] = 0;
+	dir->entries[dir->nr++] = ent;
+}
+
+static int dir_exists(const char *dirname, int len)
+{
+	int pos = cache_name_pos(dirname, len);
+	if (pos >= 0)
+		return 1;
+	pos = -pos-1;
+	if (pos >= active_nr) /* can't */
+		return 0;
+	return !strncmp(active_cache[pos]->name, dirname, len);
+}
+
+/*
+ * Read a directory tree. We currently ignore anything but
+ * directories, regular files and symlinks. That's because git
+ * doesn't handle them at all yet. Maybe that will change some
+ * day.
+ *
+ * Also, we ignore the name ".git" (even if it is not a directory).
+ * That likely will not change.
+ */
+static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen)
+{
+	DIR *fdir = opendir(path);
+	int contents = 0;
+
+	if (fdir) {
+		int exclude_stk;
+		struct dirent *de;
+		char fullname[MAXPATHLEN + 1];
+		memcpy(fullname, base, baselen);
+
+		exclude_stk = push_exclude_per_directory(dir, base, baselen);
+
+		while ((de = readdir(fdir)) != NULL) {
+			int len;
+
+			if ((de->d_name[0] == '.') &&
+			    (de->d_name[1] == 0 ||
+			     !strcmp(de->d_name + 1, ".") ||
+			     !strcmp(de->d_name + 1, "git")))
+				continue;
+			len = strlen(de->d_name);
+			memcpy(fullname + baselen, de->d_name, len+1);
+			if (excluded(dir, fullname) != dir->show_ignored) {
+				if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
+					continue;
+				}
+			}
+
+			switch (DTYPE(de)) {
+			struct stat st;
+			int subdir, rewind_base;
+			default:
+				continue;
+			case DT_UNKNOWN:
+				if (lstat(fullname, &st))
+					continue;
+				if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
+					break;
+				if (!S_ISDIR(st.st_mode))
+					continue;
+				/* fallthrough */
+			case DT_DIR:
+				memcpy(fullname + baselen + len, "/", 2);
+				len++;
+				rewind_base = dir->nr;
+				subdir = read_directory_recursive(dir, fullname, fullname,
+				                        baselen + len);
+				if (dir->show_other_directories &&
+				    (subdir || !dir->hide_empty_directories) &&
+				    !dir_exists(fullname, baselen + len)) {
+					// Rewind the read subdirectory
+					while (dir->nr > rewind_base)
+						free(dir->entries[--dir->nr]);
+					break;
+				}
+				contents += subdir;
+				continue;
+			case DT_REG:
+			case DT_LNK:
+				break;
+			}
+			add_name(dir, fullname, baselen + len);
+			contents++;
+		}
+		closedir(fdir);
+
+		pop_exclude_per_directory(dir, exclude_stk);
+	}
+
+	return contents;
+}
+
+static int cmp_name(const void *p1, const void *p2)
+{
+	const struct dir_entry *e1 = *(const struct dir_entry **)p1;
+	const struct dir_entry *e2 = *(const struct dir_entry **)p2;
+
+	return cache_name_compare(e1->name, e1->len,
+				  e2->name, e2->len);
+}
+
+int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen)
+{
+	/*
+	 * Make sure to do the per-directory exclude for all the
+	 * directories leading up to our base.
+	 */
+	if (baselen) {
+		if (dir->exclude_per_dir) {
+			char *p, *pp = xmalloc(baselen+1);
+			memcpy(pp, base, baselen+1);
+			p = pp;
+			while (1) {
+				char save = *p;
+				*p = 0;
+				push_exclude_per_directory(dir, pp, p-pp);
+				*p++ = save;
+				if (!save)
+					break;
+				p = strchr(p, '/');
+				if (p)
+					p++;
+				else
+					p = pp + baselen;
+			}
+			free(pp);
+		}
+	}
+
+	read_directory_recursive(dir, path, base, baselen);
+	qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
+	return dir->nr;
+}
diff --git a/dir.h b/dir.h
new file mode 100644
index 0000000..56a1b7f
--- /dev/null
+++ b/dir.h
@@ -0,0 +1,51 @@
+#ifndef DIR_H
+#define DIR_H
+
+/*
+ * We maintain three exclude pattern lists:
+ * EXC_CMDL lists patterns explicitly given on the command line.
+ * EXC_DIRS lists patterns obtained from per-directory ignore files.
+ * EXC_FILE lists patterns from fallback ignore files.
+ */
+#define EXC_CMDL 0
+#define EXC_DIRS 1
+#define EXC_FILE 2
+
+
+struct dir_entry {
+	int len;
+	char name[FLEX_ARRAY]; /* more */
+};
+
+struct exclude_list {
+	int nr;
+	int alloc;
+	struct exclude {
+		const char *pattern;
+		const char *base;
+		int baselen;
+	} **excludes;
+};
+
+struct dir_struct {
+	int nr, alloc;
+	unsigned int show_ignored:1,
+		     show_other_directories:1,
+		     hide_empty_directories:1;
+	struct dir_entry **entries;
+
+	/* Exclude info */
+	const char *exclude_per_dir;
+	struct exclude_list exclude_list[3];
+};
+
+extern int common_prefix(const char **pathspec);
+extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen);
+
+extern int read_directory(struct dir_struct *, const char *path, const char *base, int baselen);
+extern int excluded(struct dir_struct *, const char *);
+extern void add_excludes_from_file(struct dir_struct *, const char *fname);
+extern void add_exclude(const char *string, const char *base,
+			int baselen, struct exclude_list *which);
+
+#endif
diff --git a/dump-cache-tree.c b/dump-cache-tree.c
new file mode 100644
index 0000000..1ccaf51
--- /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/fetch-pack.c b/fetch-pack.c
index a3bcad0..8daa93d 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -262,22 +262,58 @@ static void mark_recent_complete_commits(unsigned long cutoff)
 
 static void filter_refs(struct ref **refs, int nr_match, char **match)
 {
-	struct ref *prev, *current, *next;
-
-	for (prev = NULL, current = *refs; current; current = next) {
-		next = current->next;
-		if ((!memcmp(current->name, "refs/", 5) &&
-		     check_ref_format(current->name + 5)) ||
-		    (!fetch_all &&
-		     !path_match(current->name, nr_match, match))) {
-			if (prev == NULL)
-				*refs = next;
-			else
-				prev->next = next;
-			free(current);
-		} else
-			prev = current;
+	struct ref **return_refs;
+	struct ref *newlist = NULL;
+	struct ref **newtail = &newlist;
+	struct ref *ref, *next;
+	struct ref *fastarray[32];
+
+	if (nr_match && !fetch_all) {
+		if (ARRAY_SIZE(fastarray) < nr_match)
+			return_refs = xcalloc(nr_match, sizeof(struct ref *));
+		else {
+			return_refs = fastarray;
+			memset(return_refs, 0, sizeof(struct ref *) * nr_match);
+		}
+	}
+	else
+		return_refs = NULL;
+
+	for (ref = *refs; ref; ref = next) {
+		next = ref->next;
+		if (!memcmp(ref->name, "refs/", 5) &&
+		    check_ref_format(ref->name + 5))
+			; /* trash */
+		else if (fetch_all) {
+			*newtail = ref;
+			ref->next = NULL;
+			newtail = &ref->next;
+			continue;
+		}
+		else {
+			int order = path_match(ref->name, nr_match, match);
+			if (order) {
+				return_refs[order-1] = ref;
+				continue; /* we will link it later */
+			}
+		}
+		free(ref);
+	}
+
+	if (!fetch_all) {
+		int i;
+		for (i = 0; i < nr_match; i++) {
+			ref = return_refs[i];
+			if (ref) {
+				*newtail = ref;
+				ref->next = NULL;
+				newtail = &ref->next;
+			}
+		}
+		if (return_refs != fastarray)
+			free(return_refs);
 	}
+	*refs = newlist;
 }
 
 static int everything_local(struct ref **refs, int nr_match, char **match)
diff --git a/fsck-objects.c b/fsck-objects.c
index 59b2590..1922b6d 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-add.sh b/git-add.sh
deleted file mode 100755
index d6a4bc7..0000000
--- a/git-add.sh
+++ /dev/null
@@ -1,56 +0,0 @@
-#!/bin/sh
-
-USAGE='[-n] [-v] <file>...'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-show_only=
-verbose=
-while : ; do
-  case "$1" in
-    -n)
-	show_only=true
-	;;
-    -v)
-	verbose=--verbose
-	;;
-    --)
-	shift
-	break
-	;;
-    -*)
-	usage
-	;;
-    *)
-	break
-	;;
-  esac
-  shift
-done
-
-# Check misspelled pathspec
-case "$#" in
-0)	;;
-*)
-	git-ls-files --error-unmatch --others --cached -- "$@" >/dev/null || {
-		echo >&2 "Maybe you misspelled it?"
-		exit 1
-	}
-	;;
-esac
-
-if test -f "$GIT_DIR/info/exclude"
-then
-	git-ls-files -z \
-	--exclude-from="$GIT_DIR/info/exclude" \
-	--others --exclude-per-directory=.gitignore -- "$@"
-else
-	git-ls-files -z \
-	--others --exclude-per-directory=.gitignore -- "$@"
-fi |
-case "$show_only" in
-true)
-	xargs -0 echo ;;
-*)
-	git-update-index --add $verbose -z --stdin ;;
-esac
diff --git a/git-format-patch.sh b/git-format-patch.sh
deleted file mode 100755
index 8a16ead..0000000
--- a/git-format-patch.sh
+++ /dev/null
@@ -1,344 +0,0 @@
-#!/bin/sh
-#
-# Copyright (c) 2005 Junio C Hamano
-#
-
-USAGE='[-n | -k] [-o <dir> | --stdout] [--signoff] [--check] [--diff-options] [--attach] <his> [<mine>]'
-LONG_USAGE='Prepare each commit with its patch since <mine> head forked from
-<his> head, one file per patch formatted to resemble UNIX mailbox
-format, for e-mail submission or use with git-am.
-
-Each output file is numbered sequentially from 1, and uses the
-first line of the commit message (massaged for pathname safety)
-as the filename.
-
-When -o is specified, output files are created in <dir>; otherwise
-they are created in the current working directory.  This option
-is ignored if --stdout is specified.
-
-When -n is specified, instead of "[PATCH] Subject", the first
-line is formatted as "[PATCH N/M] Subject", unless you have only
-one patch.
-
-When --attach is specified, patches are attached, not inlined.'
-
-. git-sh-setup
-
-# Force diff to run in C locale.
-LANG=C LC_ALL=C
-export LANG LC_ALL
-
-diff_opts=
-LF='
-'
-
-outdir=./
-while case "$#" in 0) break;; esac
-do
-    case "$1" in
-    -c|--c|--ch|--che|--chec|--check)
-    check=t ;;
-    -a|--a|--au|--aut|--auth|--autho|--author|\
-    -d|--d|--da|--dat|--date|\
-    -m|--m|--mb|--mbo|--mbox) # now noop
-    ;;
-    --at|--att|--atta|--attac|--attach)
-    attach=t ;;
-    -k|--k|--ke|--kee|--keep|--keep-|--keep-s|--keep-su|--keep-sub|\
-    --keep-subj|--keep-subje|--keep-subjec|--keep-subject)
-    keep_subject=t ;;
-    -n|--n|--nu|--num|--numb|--numbe|--number|--numbere|--numbered)
-    numbered=t ;;
-    -s|--s|--si|--sig|--sign|--signo|--signof|--signoff)
-    signoff=t ;;
-    --st|--std|--stdo|--stdou|--stdout)
-    stdout=t ;;
-    -o=*|--o=*|--ou=*|--out=*|--outp=*|--outpu=*|--output=*|--output-=*|\
-    --output-d=*|--output-di=*|--output-dir=*|--output-dire=*|\
-    --output-direc=*|--output-direct=*|--output-directo=*|\
-    --output-director=*|--output-directory=*)
-    outdir=`expr "$1" : '-[^=]*=\(.*\)'` ;;
-    -o|--o|--ou|--out|--outp|--outpu|--output|--output-|--output-d|\
-    --output-di|--output-dir|--output-dire|--output-direc|--output-direct|\
-    --output-directo|--output-director|--output-directory)
-    case "$#" in 1) usage ;; esac; shift
-    outdir="$1" ;;
-    -h|--h|--he|--hel|--help)
-        usage
-	;;
-    -*' '* | -*"$LF"* | -*'	'*)
-	# Ignore diff option that has whitespace for now.
-	;;
-    -*)	diff_opts="$diff_opts$1 " ;;
-    *) break ;;
-    esac
-    shift
-done
-
-case "$keep_subject$numbered" in
-tt)
-	die '--keep-subject and --numbered are incompatible.' ;;
-esac
-
-tmp=.tmp-series$$
-trap 'rm -f $tmp-*' 0 1 2 3 15
-
-series=$tmp-series
-commsg=$tmp-commsg
-filelist=$tmp-files
-
-# Backward compatible argument parsing hack.
-#
-# Historically, we supported:
-# 1. "rev1"		is equivalent to "rev1..HEAD"
-# 2. "rev1..rev2"
-# 3. "rev1" "rev2	is equivalent to "rev1..rev2"
-#
-# We want to take a sequence of "rev1..rev2" in general.
-# Also, "rev1.." should mean "rev1..HEAD"; git-diff users are
-# familiar with that syntax.
-
-case "$#,$1$2" in
-1,?*..?*)
-	# single "rev1..rev2"
-	;;
-1,?*..)
-	# single "rev1.." should mean "rev1..HEAD"
-	set x "$1"HEAD
-	shift
-	;;
-1,*)
-	# single rev1
-	set x "$1..HEAD"
-	shift
-	;;
-2,?*..?*)
-	# not traditional "rev1" "rev2"
-	;;
-2,*)
-	set x "$1..$2"
-	shift
-	;;
-esac
-
-# Now we have what we want in $@
-for revpair
-do
-	case "$revpair" in
-	?*..?*)
-		rev1=`expr "z$revpair" : 'z\(.*\)\.\.'`
-		rev2=`expr "z$revpair" : 'z.*\.\.\(.*\)'`
-		;;
-	*)
-		rev1="$revpair^"
-		rev2="$revpair"
-		;;
-	esac
-	git-rev-parse --verify "$rev1^0" >/dev/null 2>&1 ||
-		die "Not a valid rev $rev1 ($revpair)"
-	git-rev-parse --verify "$rev2^0" >/dev/null 2>&1 ||
-		die "Not a valid rev $rev2 ($revpair)"
-	git-cherry -v "$rev1" "$rev2" |
-	while read sign rev comment
-	do
-		case "$sign" in
-		'-')
-			echo >&2 "Merged already: $comment"
-			;;
-		*)
-			echo $rev
-			;;
-		esac
-	done
-done >$series
-
-me=`git-var GIT_AUTHOR_IDENT | sed -e 's/>.*/>/'`
-headers=`git-repo-config --get format.headers`
-case "$attach" in
-"") ;;
-*)
-	mimemagic="050802040500080604070107"
-esac
-
-case "$outdir" in
-*/) ;;
-*) outdir="$outdir/" ;;
-esac
-test -d "$outdir" || mkdir -p "$outdir" || exit
-
-titleScript='
-	/./d
-	/^$/n
-	s/^\[PATCH[^]]*\] *//
-	s/[^-a-z.A-Z_0-9]/-/g
-        s/\.\.\.*/\./g
-	s/\.*$//
-	s/--*/-/g
-	s/^-//
-	s/-$//
-	s/$/./
-	p
-	q
-'
-
-process_one () {
-	perl -w -e '
-my ($keep_subject, $num, $signoff, $headers, $mimemagic, $commsg) = @ARGV;
-my ($signoff_pattern, $done_header, $done_subject, $done_separator, $signoff_seen,
-    $last_was_signoff);
-
-if ($signoff) {
-	$signoff = "Signed-off-by: " . `git-var GIT_COMMITTER_IDENT`;
-	$signoff =~ s/>.*/>/;
-	$signoff_pattern = quotemeta($signoff);
-}
-
-my @weekday_names = qw(Sun Mon Tue Wed Thu Fri Sat);
-my @month_names = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
-
-sub show_date {
-    my ($time, $tz) = @_;
-    my $minutes = abs($tz);
-    $minutes = int($minutes / 100) * 60 + ($minutes % 100);
-    if ($tz < 0) {
-        $minutes = -$minutes;
-    }
-    my $t = $time + $minutes * 60;
-    my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday) = gmtime($t);
-    return sprintf("%s, %d %s %d %02d:%02d:%02d %+05d",
-		   $weekday_names[$wday], $mday,
-		   $month_names[$mon], $year+1900,
-		   $hour, $min, $sec, $tz);
-}
-
-print "From nobody Mon Sep 17 00:00:00 2001\n";
-open FH, "git stripspace <$commsg |" or die "open $commsg pipe";
-while (<FH>) {
-    unless ($done_header) {
-	if (/^$/) {
-	    $done_header = 1;
-	}
-	elsif (/^author (.*>) (.*)$/) {
-	    my ($author_ident, $author_date) = ($1, $2);
-	    my ($utc, $off) = ($author_date =~ /^(\d+) ([-+]?\d+)$/);
-	    $author_date = show_date($utc, $off);
-
-	    print "From: $author_ident\n";
-	    print "Date: $author_date\n";
-	}
-	next;
-    }
-    unless ($done_subject) {
-	unless ($keep_subject) {
-	    s/^\[PATCH[^]]*\]\s*//;
-	    s/^/[PATCH$num] /;
-	}
-	if ($headers) {
-	    print "$headers\n";
-	}
-        print "Subject: $_";
-	if ($mimemagic) {
-	    print "MIME-Version: 1.0\n";
-	    print "Content-Type: multipart/mixed;\n";
-	    print " boundary=\"------------$mimemagic\"\n";
-	    print "\n";
-	    print "This is a multi-part message in MIME format.\n";
-	    print "--------------$mimemagic\n";
-	    print "Content-Type: text/plain; charset=UTF-8; format=fixed\n";
-	    print "Content-Transfer-Encoding: 8bit\n";
-	}
-	$done_subject = 1;
-	next;
-    }
-    unless ($done_separator) {
-        print "\n";
-        $done_separator = 1;
-        next if (/^$/);
-    }
-
-    $last_was_signoff = 0;
-    if (/Signed-off-by:/i) {
-        if ($signoff ne "" && /Signed-off-by:\s*$signoff_pattern$/i) {
-	    $signoff_seen = 1;
-	}
-    }
-    print $_;
-}
-if (!$signoff_seen && $signoff ne "") {
-    if (!$last_was_signoff) {
-        print "\n";
-    }
-    print "$signoff\n";
-}
-print "\n---\n\n";
-close FH or die "close $commsg pipe";
-' "$keep_subject" "$num" "$signoff" "$headers" "$mimemagic" $commsg
-
-	git-diff-tree -p --stat --summary $diff_opts "$commit"
-	echo
-	case "$mimemagic" in
-	'');;
-	*)
-		echo "--------------$mimemagic"
-		echo "Content-Type: text/x-patch;"
-		echo " name=\"$commit.diff\""
-		echo "Content-Transfer-Encoding: 8bit"
-		echo "Content-Disposition: inline;"
-		echo " filename=\"$commit.diff\""
-		echo
-	esac
-	git-diff-tree -p $diff_opts "$commit"
-	case "$mimemagic" in
-	'')
-		echo "-- "
-		echo "@@GIT_VERSION@@"
-		;;
-	*)
-		echo
-		echo "--------------$mimemagic--"
-		echo
-		;;
-	esac
-	echo
-}
-
-total=`wc -l <$series | tr -dc "[0-9]"`
-case "$total,$numbered" in
-1,*)
-	numfmt='' ;;
-*,t)
-	numfmt=`echo "$total" | wc -c`
-	numfmt=$(($numfmt-1))
-	numfmt=" %0${numfmt}d/$total"
-esac
-
-i=1
-while read commit
-do
-    git-cat-file commit "$commit" | git-stripspace >$commsg
-    title=`sed -ne "$titleScript" <$commsg`
-    case "$numbered" in
-    '') num= ;;
-    *)
-        num=`printf "$numfmt" $i` ;;
-    esac
-
-    file=`printf '%04d-%stxt' $i "$title"`
-    if test '' = "$stdout"
-    then
-	    echo "$file"
-	    process_one >"$outdir$file"
-	    if test t = "$check"
-	    then
-		# This is slightly modified from Andrew Morton's Perfect Patch.
-		# Lines you introduce should not have trailing whitespace.
-		# Also check for an indentation that has SP before a TAB.
-		grep -n '^+\([ 	]* 	.*\|.*[ 	]\)$' "$outdir$file"
-		:
-	    fi
-    else
-	    echo >&2 "$file"
-	    process_one
-    fi
-    i=`expr "$i" + 1`
-done <$series
diff --git a/git-rebase.sh b/git-rebase.sh
index 6ff6088..e6b57b8 100755
--- a/git-rebase.sh
+++ b/git-rebase.sh
@@ -152,6 +152,6 @@ then
 	exit 0
 fi
 
-git-format-patch -k --stdout --full-index "$upstream" ORIG_HEAD |
+git-format-patch -k --stdout --full-index "$upstream"..ORIG_HEAD |
 git am --binary -3 -k --resolvemsg="$RESOLVEMSG"
 
diff --git a/git-rm.sh b/git-rm.sh
deleted file mode 100755
index fda4541..0000000
--- a/git-rm.sh
+++ /dev/null
@@ -1,70 +0,0 @@
-#!/bin/sh
-
-USAGE='[-f] [-n] [-v] [--] <file>...'
-SUBDIRECTORY_OK='Yes'
-. git-sh-setup
-
-remove_files=
-show_only=
-verbose=
-while : ; do
-  case "$1" in
-    -f)
-	remove_files=true
-	;;
-    -n)
-	show_only=true
-	;;
-    -v)
-	verbose=--verbose
-	;;
-    --)
-	shift; break
-	;;
-    -*)
-	usage
-	;;
-    *)
-	break
-	;;
-  esac
-  shift
-done
-
-# This is typo-proofing. If some paths match and some do not, we want
-# to do nothing.
-case "$#" in
-0)	;;
-*)
-	git-ls-files --error-unmatch -- "$@" >/dev/null || {
-		echo >&2 "Maybe you misspelled it?"
-		exit 1
-	}
-	;;
-esac
-
-if test -f "$GIT_DIR/info/exclude"
-then
-	git-ls-files -z \
-	--exclude-from="$GIT_DIR/info/exclude" \
-	--exclude-per-directory=.gitignore -- "$@"
-else
-	git-ls-files -z \
-	--exclude-per-directory=.gitignore -- "$@"
-fi |
-case "$show_only,$remove_files" in
-true,*)
-	xargs -0 echo
-	;;
-*,true)
-	xargs -0 sh -c "
-		while [ \$# -gt 0 ]; do
-			file=\$1; shift
-			rm -- \"\$file\" && git-update-index --remove $verbose \"\$file\"
-		done
-	" inline
-	;;
-*)
-	git-update-index --force-remove $verbose -z --stdin
-	;;
-esac
diff --git a/git.c b/git.c
index 38e8461..5a884bb 100644
--- a/git.c
+++ b/git.c
@@ -47,9 +47,12 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "whatchanged", cmd_whatchanged },
 		{ "show", cmd_show },
 		{ "push", cmd_push },
+		{ "format-patch", cmd_format_patch },
 		{ "count-objects", cmd_count_objects },
 		{ "diff", cmd_diff },
 		{ "grep", cmd_grep },
+		{ "rm", cmd_rm },
+		{ "add", cmd_add },
 		{ "rev-list", cmd_rev_list },
 		{ "init-db", cmd_init_db },
 		{ "tar-tree", cmd_tar_tree },
diff --git a/http-fetch.c b/http-fetch.c
index 861644b..178f1ee 100644
--- a/http-fetch.c
+++ b/http-fetch.c
@@ -1269,10 +1269,10 @@ int main(int argc, char **argv)
 	if (pull(commit_id))
 		rc = 1;
 
-	curl_slist_free_all(no_pragma_header);
-
 	http_cleanup();
 
+	curl_slist_free_all(no_pragma_header);
+
 	if (corrupt_object_found) {
 		fprintf(stderr,
 "Some loose object were found to be corrupt, but they might be just\n"
diff --git a/log-tree.c b/log-tree.c
index b90ba67..7e23e42 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, *after_subject = NULL;
 
 	opt->loginfo = NULL;
 	if (!opt->verbose_header) {
@@ -49,19 +50,67 @@ 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) {
+		char *sha1 = sha1_to_hex(commit->object.sha1);
+		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 Mon Sep 17 00:00:00 2001\n", sha1);
+		if (opt->mime_boundary) {
+			static char subject_buffer[1024];
+			static char buffer[1024];
+			snprintf(subject_buffer, sizeof(subject_buffer) - 1,
+				 "MIME-Version: 1.0\n"
+				 "Content-Type: multipart/mixed;\n"
+				 " boundary=\"%s%s\"\n"
+				 "\n"
+				 "This is a multi-part message in MIME "
+				 "format.\n"
+				 "--%s%s\n"
+				 "Content-Type: text/plain; "
+				 "charset=UTF-8; format=fixed\n"
+				 "Content-Transfer-Encoding: 8bit\n\n",
+				 mime_boundary_leader, opt->mime_boundary,
+				 mime_boundary_leader, opt->mime_boundary);
+			after_subject = subject_buffer;
+
+			snprintf(buffer, sizeof(buffer) - 1,
+				 "--%s%s\n"
+				 "Content-Type: text/x-patch;\n"
+				 " name=\"%s.diff\"\n"
+				 "Content-Transfer-Encoding: 8bit\n"
+				 "Content-Disposition: inline;\n"
+				 " filename=\"%s.diff\"\n\n",
+				 mime_boundary_leader, opt->mime_boundary,
+				 sha1, sha1);
+			opt->diffopt.stat_sep = buffer;
+		}
+	} 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, after_subject);
 	printf("%s%s%s", this_header, extra, sep);
 }
 
@@ -166,15 +215,18 @@ 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/mailinfo.c b/mailinfo.c
index b276519..a133e6d 100644
--- a/mailinfo.c
+++ b/mailinfo.c
@@ -237,10 +237,17 @@ static int eatspace(char *line)
 #define SEEN_FROM 01
 #define SEEN_DATE 02
 #define SEEN_SUBJECT 04
+#define SEEN_BOGUS_UNIX_FROM 010
 
 /* First lines of body can have From:, Date:, and Subject: */
 static int handle_inbody_header(int *seen, char *line)
 {
+	if (!memcmp(">From", line, 5) && isspace(line[5])) {
+		if (!(*seen & SEEN_BOGUS_UNIX_FROM)) {
+			*seen |= SEEN_BOGUS_UNIX_FROM;
+			return 1;
+		}
+	}
 	if (!memcmp("From:", line, 5) && isspace(line[5])) {
 		if (!(*seen & SEEN_FROM) && handle_from(line+6)) {
 			*seen |= SEEN_FROM;
diff --git a/read-cache.c b/read-cache.c
index b95edcc..36bd4ea 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
@@ -332,6 +347,70 @@ int ce_path_match(const struct cache_entry *ce, const char **pathspec)
 }
 
 /*
+ * We fundamentally don't like some paths: we don't want
+ * dot or dot-dot anywhere, and for obvious reasons don't
+ * want to recurse into ".git" either.
+ *
+ * Also, we don't want double slashes or slashes at the
+ * end that can make pathnames ambiguous.
+ */
+static int verify_dotfile(const char *rest)
+{
+	/*
+	 * The first character was '.', but that
+	 * has already been discarded, we now test
+	 * the rest.
+	 */
+	switch (*rest) {
+	/* "." is not allowed */
+	case '\0': case '/':
+		return 0;
+
+	/*
+	 * ".git" followed by  NUL or slash is bad. This
+	 * shares the path end test with the ".." case.
+	 */
+	case 'g':
+		if (rest[1] != 'i')
+			break;
+		if (rest[2] != 't')
+			break;
+		rest += 2;
+	/* fallthrough */
+	case '.':
+		if (rest[1] == '\0' || rest[1] == '/')
+			return 0;
+	}
+	return 1;
+}
+
+int verify_path(const char *path)
+{
+	char c;
+
+	goto inside;
+	for (;;) {
+		if (!c)
+			return 1;
+		if (c == '/') {
+inside:
+			c = *path++;
+			switch (c) {
+			default:
+				continue;
+			case '/': case '\0':
+				break;
+			case '.':
+				if (verify_dotfile(path))
+					continue;
+			}
+			return 0;
+		}
+		c = *path++;
+	}
+}
+
+/*
  * Do we have another file that has the beginning components being a
  * proper superset of the name we're trying to add?
  */
@@ -472,6 +551,8 @@ int add_cache_entry(struct cache_entry *ce, int option)
 
 	if (!ok_to_add)
 		return -1;
+	if (!verify_path(ce->name))
+		return -1;
 
 	if (!skip_df_check &&
 	    check_file_directory_conflict(ce, pos, ok_to_replace)) {
@@ -630,6 +711,22 @@ 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;
@@ -678,6 +775,22 @@ 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:
@@ -712,6 +825,17 @@ 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;
@@ -808,5 +932,19 @@ 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/revision.h b/revision.h
index 48d7b4c..bdbdd23 100644
--- a/revision.h
+++ b/revision.h
@@ -58,6 +58,8 @@ struct rev_info {
 	unsigned int	abbrev;
 	enum cmit_fmt	commit_format;
 	struct log_info *loginfo;
+	int		nr, total;
+	const char	*mime_boundary;
 
 	/* special limits */
 	int max_count;
diff --git a/t/t0000-basic.sh b/t/t0000-basic.sh
index cf33989..2c9bbb5 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 7d6de82..956b6b3 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"
 
 /*
@@ -51,6 +52,7 @@ 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;
 	}
@@ -64,6 +66,12 @@ 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
@@ -120,70 +128,6 @@ static int add_file_to_cache(const char *path)
 	return 0;
 }
 
-/*
- * We fundamentally don't like some paths: we don't want
- * dot or dot-dot anywhere, and for obvious reasons don't
- * want to recurse into ".git" either.
- *
- * Also, we don't want double slashes or slashes at the
- * end that can make pathnames ambiguous.
- */
-static int verify_dotfile(const char *rest)
-{
-	/*
-	 * The first character was '.', but that
-	 * has already been discarded, we now test
-	 * the rest.
-	 */
-	switch (*rest) {
-	/* "." is not allowed */
-	case '\0': case '/':
-		return 0;
-
-	/*
-	 * ".git" followed by  NUL or slash is bad. This
-	 * shares the path end test with the ".." case.
-	 */
-	case 'g':
-		if (rest[1] != 'i')
-			break;
-		if (rest[2] != 't')
-			break;
-		rest += 2;
-	/* fallthrough */
-	case '.':
-		if (rest[1] == '\0' || rest[1] == '/')
-			return 0;
-	}
-	return 1;
-}
-
-static int verify_path(const char *path)
-{
-	char c;
-
-	goto inside;
-	for (;;) {
-		if (!c)
-			return 1;
-		if (c == '/') {
-inside:
-			c = *path++;
-			switch (c) {
-			default:
-				continue;
-			case '/': case '\0':
-				break;
-			case '.':
-				if (verify_dotfile(path))
-					continue;
-			}
-			return 0;
-		}
-		c = *path++;
-	}
-}
-
 static int add_cacheinfo(unsigned int mode, const unsigned char *sha1,
 			 const char *path, int stage)
 {
@@ -209,6 +153,7 @@ 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;
 }
 
@@ -233,6 +178,7 @@ 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;
@@ -254,6 +200,7 @@ 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))
@@ -332,6 +279,7 @@ 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 */
@@ -438,6 +386,7 @@ 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 dcad6e6..895e7a3 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;
 }