Merge branch 'master' into lt/apply

* master: (40 commits)
  Clean up sha1 file writing
  Builtin git-cat-file
  builtin format-patch: squelch content-type for 7-bit ASCII
  CMIT_FMT_EMAIL: Q-encode Subject: and display-name part of From: fields.
  add more informative error messages to git-mktag
  remove the artificial restriction tagsize < 8kb
  git-rebase: use canonical A..B syntax to format-patch
  git-format-patch: now built-in.
  fmt-patch: Support --attach
  fmt-patch: understand old <his> notation
  Teach fmt-patch about --keep-subject
  Teach fmt-patch about --numbered
  fmt-patch: implement -o <dir>
  fmt-patch: output file names to stdout
  Teach fmt-patch to write individual files.
  Use RFC2822 dates from "git fmt-patch".
  git-fmt-patch: thinkofix to show [PATCH] properly.
  rename internal format-patch wip
  Minor tweak on subject line in --pretty=email
  Tentative built-in format-patch.
  ...

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 \
@@ -149,19 +149,16 @@ SIMPLE_PROGRAMS = \
 
 # ... and all the rest that could be moved out of bindir to gitexecdir
 PROGRAMS = \
-	git-apply$X git-cat-file$X \
-	git-checkout-index$X git-clone-pack$X git-commit-tree$X \
-	git-convert-objects$X git-diff-files$X \
-	git-diff-index$X git-diff-stages$X \
-	git-diff-tree$X git-fetch-pack$X git-fsck-objects$X \
+	git-checkout-index$X git-clone-pack$X \
+	git-convert-objects$X git-fetch-pack$X git-fsck-objects$X \
 	git-hash-object$X git-index-pack$X git-local-fetch$X \
-	git-ls-files$X git-ls-tree$X git-mailinfo$X git-merge-base$X \
+	git-mailinfo$X git-merge-base$X \
 	git-merge-index$X git-mktag$X git-mktree$X git-pack-objects$X git-patch-id$X \
-	git-peek-remote$X git-prune-packed$X git-read-tree$X \
+	git-peek-remote$X git-prune-packed$X \
 	git-receive-pack$X git-rev-parse$X \
-	git-send-pack$X git-show-branch$X git-shell$X \
+	git-send-pack$X git-shell$X \
 	git-show-index$X git-ssh-fetch$X \
-	git-ssh-upload$X git-tar-tree$X git-unpack-file$X \
+	git-ssh-upload$X git-unpack-file$X \
 	git-unpack-objects$X git-update-index$X git-update-server-info$X \
 	git-upload-pack$X git-verify-pack$X git-write-tree$X \
 	git-update-ref$X git-symbolic-ref$X \
@@ -170,8 +167,13 @@ 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-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$X git-cat-file$X
 
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
@@ -200,7 +202,7 @@ 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 \
@@ -211,7 +213,7 @@ LIB_OBJS = \
 	blob.o commit.o connect.o csum-file.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 \
@@ -219,8 +221,14 @@ 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-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-cat-file.o
 
 GITLIBS = $(LIB_FILE) $(XDIFF_LIB)
 LIBS = $(GITLIBS) -lz

builtin-add.c

@@ -0,0 +1,187 @@
+/*
+ * "git add" builtin command
+ *
+ * Copyright (C) 2006 Linus Torvalds
+ */
+#include <fnmatch.h>
+
+#include "cache.h"
+#include "builtin.h"
+#include "dir.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);
+	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;
+}

builtin-apply.c

@@ -11,6 +11,7 @@
 #include "quote.h"
 #include "blob.h"
 #include "delta.h"
+#include "builtin.h"
 
 //  --check turns on checking that the working tree matches the
 //    files that are being modified, but doesn't apply the patch
@@ -2168,7 +2169,7 @@ static int git_apply_config(const char *var, const char *value)
 }
 
 
-int main(int argc, char **argv)
+int cmd_apply(int argc, const char **argv, char **envp)
 {
 	int i;
 	int read_stdin = 1;

builtin-cat-file.c

@@ -7,6 +7,7 @@
 #include "exec_cmd.h"
 #include "tag.h"
 #include "tree.h"
+#include "builtin.h"
 
 static void flush_buffer(const char *buf, unsigned long size)
 {
@@ -93,7 +94,7 @@ static int pprint_tag(const unsigned char *sha1, const char *buf, unsigned long
 	return 0;
 }
 
-int main(int argc, char **argv)
+int cmd_cat_file(int argc, const char **argv, char **envp)
 {
 	unsigned char sha1[20];
 	char type[20];

builtin-commit-tree.c

@@ -6,6 +6,7 @@
 #include "cache.h"
 #include "commit.h"
 #include "tree.h"
+#include "builtin.h"
 
 #define BLOCKING (1ul << 14)
 
@@ -76,7 +77,7 @@ static int new_parent(int idx)
 	return 1;
 }
 
-int main(int argc, char **argv)
+int cmd_commit_tree(int argc, const char **argv, char **envp)
 {
 	int i;
 	int parents = 0;
@@ -98,7 +99,7 @@ int main(int argc, char **argv)
 
 	check_valid(tree_sha1, tree_type);
 	for (i = 2; i < argc; i += 2) {
-		char *a, *b;
+		const char *a, *b;
 		a = argv[i]; b = argv[i+1];
 		if (!b || strcmp(a, "-p"))
 			usage(commit_tree_usage);

builtin-diff-files.c

@@ -7,12 +7,13 @@
 #include "diff.h"
 #include "commit.h"
 #include "revision.h"
+#include "builtin.h"
 
 static const char diff_files_usage[] =
 "git-diff-files [-q] [-0/-1/2/3 |-c|--cc] [<common diff options>] [<path>...]"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_files(int argc, const char **argv, char **envp)
 {
 	struct rev_info rev;
 	int silent = 0;

builtin-diff-index.c

@@ -2,13 +2,14 @@
 #include "diff.h"
 #include "commit.h"
 #include "revision.h"
+#include "builtin.h"
 
 static const char diff_cache_usage[] =
 "git-diff-index [-m] [--cached] "
 "[<common diff options>] <tree-ish> [<path>...]"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_index(int argc, const char **argv, char **envp)
 {
 	struct rev_info rev;
 	int cached = 0;

builtin-diff-stages.c

@@ -4,6 +4,7 @@
 
 #include "cache.h"
 #include "diff.h"
+#include "builtin.h"
 
 static struct diff_options diff_options;
 
@@ -54,7 +55,7 @@ static void diff_stages(int stage1, int stage2, const char **pathspec)
 	}
 }
 
-int main(int ac, const char **av)
+int cmd_diff_stages(int ac, const char **av, char **envp)
 {
 	int stage1, stage2;
 	const char *prefix = setup_git_directory();

builtin-diff-tree.c

@@ -2,6 +2,7 @@
 #include "diff.h"
 #include "commit.h"
 #include "log-tree.h"
+#include "builtin.h"
 
 static struct rev_info log_tree_opt;
 
@@ -58,7 +59,7 @@ static const char diff_tree_usage[] =
 "  --root        include the initial commit as diff against /dev/null\n"
 COMMON_DIFF_OPTIONS_HELP;
 
-int main(int argc, const char **argv)
+int cmd_diff_tree(int argc, const char **argv, char **envp)
 {
 	int nr_sha1;
 	char line[1000];

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;

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;
+}
+

builtin-ls-files.c

@@ -5,23 +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';
 
@@ -38,309 +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
@@ -377,7 +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;
@@ -393,14 +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)
@@ -416,11 +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;
 
@@ -461,7 +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]);
 	}
 }
 
@@ -512,7 +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;
 
@@ -521,39 +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;
@@ -565,7 +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)
@@ -648,11 +322,13 @@ static const char ls_files_usage[] =
 	"[ --exclude-per-directory=<filename> ] [--full-name] [--abbrev] "
 	"[--] [<file>]*";
 
-int main(int argc, const char **argv)
+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);
@@ -697,7 +373,7 @@ int main(int argc, const char **argv)
 			continue;
 		}
 		if (!strcmp(arg, "-i") || !strcmp(arg, "--ignored")) {
-			show_ignored = 1;
+			dir.show_ignored = 1;
 			continue;
 		}
 		if (!strcmp(arg, "-s") || !strcmp(arg, "--stage")) {
@@ -709,11 +385,11 @@ int main(int argc, const char **argv)
 			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")) {
@@ -726,27 +402,27 @@ int main(int argc, const char **argv)
 		}
 		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")) {
@@ -788,7 +464,7 @@ int main(int argc, const char **argv)
 		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);
@@ -802,7 +478,7 @@ int main(int argc, const char **argv)
 	read_cache();
 	if (prefix)
 		prune_cache();
-	show_files();
+	show_files(&dir);
 
 	if (ps_matched) {
 		/* We need to make sure all pathspec matched otherwise

builtin-ls-tree.c

@@ -7,6 +7,7 @@
 #include "blob.h"
 #include "tree.h"
 #include "quote.h"
+#include "builtin.h"
 
 static int line_termination = '\n';
 #define LS_RECURSIVE 1
@@ -15,7 +16,7 @@ static int line_termination = '\n';
 #define LS_NAME_ONLY 8
 static int abbrev = 0;
 static int ls_options = 0;
-const char **pathspec;
+static const char **pathspec;
 static int chomp_prefix = 0;
 static const char *prefix;
 
@@ -84,7 +85,7 @@ static int show_tree(unsigned char *sha1, const char *base, int baselen,
 	return retval;
 }
 
-int main(int argc, const char **argv)
+int cmd_ls_tree(int argc, const char **argv, char **envp)
 {
 	unsigned char sha1[20];
 	struct tree *tree;

builtin-read-tree.c

@@ -11,6 +11,7 @@
 #include "tree.h"
 #include <sys/time.h>
 #include <signal.h>
+#include "builtin.h"
 
 static int reset = 0;
 static int merge = 0;
@@ -763,7 +764,7 @@ static const char read_tree_usage[] = "git-read-tree (<sha> | -m [--aggressive]
 
 static struct cache_file cache_file;
 
-int main(int argc, char **argv)
+int cmd_read_tree(int argc, const char **argv, char **envp)
 {
 	int i, newfd, stage = 0;
 	unsigned char sha1[20];

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);

builtin-rm.c

@@ -0,0 +1,150 @@
+/*
+ * "git rm" builtin command
+ *
+ * Copyright (C) Linus Torvalds 2006
+ */
+#include "cache.h"
+#include "builtin.h"
+#include "dir.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);
+	}
+
+	/*
+	 * 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;
+}

builtin-show-branch.c

@@ -3,13 +3,14 @@
 #include "cache.h"
 #include "commit.h"
 #include "refs.h"
+#include "builtin.h"
 
 static const char show_branch_usage[] =
 "git-show-branch [--dense] [--current] [--all] [--heads] [--tags] [--topo-order] [--more=count | --list | --independent | --merge-base ] [--topics] [<refs>...]";
 
 static int default_num = 0;
 static int default_alloc = 0;
-static char **default_arg = NULL;
+static const char **default_arg = NULL;
 
 #define UNINTERESTING	01
 
@@ -259,7 +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))
@@ -548,7 +549,7 @@ static int omit_in_dense(struct commit *commit, struct commit **rev, int n)
 	return 0;
 }
 
-int main(int ac, char **av)
+int cmd_show_branch(int ac, const char **av, char **envp)
 {
 	struct commit *rev[MAX_REVS], *commit;
 	struct commit_list *list = NULL, *seen = NULL;
@@ -581,7 +582,7 @@ int main(int ac, char **av)
 	}
 
 	while (1 < ac && av[1][0] == '-') {
-		char *arg = av[1];
+		const char *arg = av[1];
 		if (!strcmp(arg, "--")) {
 			ac--; av++;
 			break;

builtin-tar-tree.c

@@ -7,11 +7,14 @@
 #include "commit.h"
 #include "strbuf.h"
 #include "tar.h"
+#include "builtin.h"
+#include "pkt-line.h"
 
 #define RECORDSIZE	(512)
 #define BLOCKSIZE	(RECORDSIZE * 20)
 
-static const char tar_tree_usage[] = "git-tar-tree <key> [basedir]";
+static const char tar_tree_usage[] =
+"git-tar-tree [--remote=<repo>] <ent> [basedir]";
 
 static char block[BLOCKSIZE];
 static unsigned long offset;
@@ -301,7 +304,7 @@ static void traverse_tree(struct tree_desc *tree, struct strbuf *path)
 	}
 }
 
-int main(int argc, char **argv)
+static int generate_tar(int argc, const char **argv, char** envp)
 {
 	unsigned char sha1[20], tree_sha1[20];
 	struct commit *commit;
@@ -348,3 +351,58 @@ int main(int argc, char **argv)
 	free(current_path.buf);
 	return 0;
 }
+
+static const char *exec = "git-upload-tar";
+
+static int remote_tar(int argc, const char **argv)
+{
+	int fd[2], ret, len;
+	pid_t pid;
+	char buf[1024];
+	char *url;
+
+	if (argc < 3 || 4 < argc)
+		usage(tar_tree_usage);
+
+	/* --remote=<repo> */
+	url = strdup(argv[1]+9);
+	pid = git_connect(fd, url, exec);
+	if (pid < 0)
+		return 1;
+
+	packet_write(fd[1], "want %s\n", argv[2]);
+	if (argv[3])
+		packet_write(fd[1], "base %s\n", argv[3]);
+	packet_flush(fd[1]);
+
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (!len)
+		die("git-tar-tree: expected ACK/NAK, got EOF");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (strcmp(buf, "ACK")) {
+		if (5 < len && !strncmp(buf, "NACK ", 5))
+			die("git-tar-tree: NACK %s", buf + 5);
+		die("git-tar-tree: protocol error");
+	}
+	/* expect a flush */
+	len = packet_read_line(fd[0], buf, sizeof(buf));
+	if (len)
+		die("git-tar-tree: expected a flush");
+
+	/* Now, start reading from fd[0] and spit it out to stdout */
+	ret = copy_fd(fd[0], 1);
+	close(fd[0]);
+
+	ret |= finish_connect(pid);
+	return !!ret;
+}
+
+int cmd_tar_tree(int argc, const char **argv, char **envp)
+{
+	if (argc < 2)
+		usage(tar_tree_usage);
+	if (!strncmp("--remote=", argv[1], 9))
+		return remote_tar(argc, argv);
+	return generate_tar(argc, argv, envp);
+}

builtin-upload-tar.c

@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2006 Junio C Hamano
+ */
+#include "cache.h"
+#include "pkt-line.h"
+#include "exec_cmd.h"
+#include "builtin.h"
+
+static const char upload_tar_usage[] = "git-upload-tar <repo>";
+
+static int nak(const char *reason)
+{
+	packet_write(1, "NACK %s\n", reason);
+	packet_flush(1);
+	return 1;
+}
+
+int cmd_upload_tar(int argc, const char **argv, char **envp)
+{
+	int len;
+	const char *dir = argv[1];
+	char buf[8192];
+	unsigned char sha1[20];
+	char *base = NULL;
+	char hex[41];
+	int ac;
+	const char *av[4];
+
+	if (argc != 2)
+		usage(upload_tar_usage);
+	if (strlen(dir) < sizeof(buf)-1)
+		strcpy(buf, dir); /* enter-repo smudges its argument */
+	else
+		packet_write(1, "NACK insanely long repository name %s\n", dir);
+	if (!enter_repo(buf, 0)) {
+		packet_write(1, "NACK not a git archive %s\n", dir);
+		packet_flush(1);
+		return 1;
+	}
+
+	len = packet_read_line(0, buf, sizeof(buf));
+	if (len < 5 || strncmp("want ", buf, 5))
+		return nak("expected want");
+	if (buf[len-1] == '\n')
+		buf[--len] = 0;
+	if (get_sha1(buf + 5, sha1))
+		return nak("expected sha1");
+        strcpy(hex, sha1_to_hex(sha1));
+
+	len = packet_read_line(0, buf, sizeof(buf));
+	if (len) {
+		if (len < 5 || strncmp("base ", buf, 5))
+			return nak("expected (optional) base");
+		if (buf[len-1] == '\n')
+			buf[--len] = 0;
+		base = strdup(buf + 5);
+		len = packet_read_line(0, buf, sizeof(buf));
+	}
+	if (len)
+		return nak("expected flush");
+
+	packet_write(1, "ACK\n");
+	packet_flush(1);
+
+	ac = 0;
+	av[ac++] = "tar-tree";
+	av[ac++] = hex;
+	if (base)
+		av[ac++] = base;
+	av[ac++] = NULL;
+	execv_git_cmd(av);
+	/* should it return that is an error */
+	return 1;
+}

builtin.h

@@ -20,12 +20,28 @@ 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);
+extern int cmd_tar_tree(int argc, const char **argv, char **envp);
+extern int cmd_upload_tar(int argc, const char **argv, char **envp);
+extern int cmd_ls_files(int argc, const char **argv, char **envp);
+extern int cmd_ls_tree(int argc, const char **argv, char **envp);
+extern int cmd_read_tree(int argc, const char **argv, char **envp);
+extern int cmd_commit_tree(int argc, const char **argv, char **envp);
+extern int cmd_apply(int argc, const char **argv, char **envp);
+extern int cmd_show_branch(int argc, const char **argv, char **envp);
+extern int cmd_diff_files(int argc, const char **argv, char **envp);
+extern int cmd_diff_index(int argc, const char **argv, char **envp);
+extern int cmd_diff_stages(int argc, const char **argv, char **envp);
+extern int cmd_diff_tree(int argc, const char **argv, char **envp);
+extern int cmd_cat_file(int argc, const char **argv, char **envp);
 
 #endif

cache.h

@@ -142,6 +142,7 @@ 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 */
@@ -154,6 +155,7 @@ extern int ce_match_stat(struct cache_entry *ce, struct stat *st, int);
 extern int ce_modified(struct cache_entry *ce, struct stat *st, int);
 extern int ce_path_match(const struct cache_entry *ce, const char **pathspec);
 extern int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type);
+extern int read_pipe(int fd, char** return_buf, unsigned long* return_size);
 extern int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object);
 extern int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object);
 extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
@@ -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 *);

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);
 
+	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;
 		}
 
+		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--;

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.

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;
 }

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.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)
 {
@@ -1988,6 +1989,12 @@ void diff_flush(struct diff_options *options)
 		show_stats(diffstat);
 		free(diffstat);
 		diffstat = NULL;
+		if (options->summary)
+			for (i = 0; i < q->nr; i++)
+				diff_summary(q->queue[i]);
+		if (options->stat_sep)
+			fputs(options->stat_sep, stdout);
+		else
 			putchar(options->line_termination);
 	}
 	for (i = 0; i < q->nr; i++) {
@@ -2001,7 +2008,7 @@ void diff_flush(struct diff_options *options)
 	}
 
 	for (i = 0; i < q->nr; i++) {
-		if (options->summary)
+		if (diffstat && options->summary)
 			diff_summary(q->queue[i]);
 		diff_free_filepair(q->queue[i]);
 	}

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,

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;
+}

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

fetch-pack.c

@@ -262,23 +262,59 @@ 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;
+	struct ref **return_refs;
+	struct ref *newlist = NULL;
+	struct ref **newtail = &newlist;
+	struct ref *ref, *next;
+	struct ref *fastarray[32];
 
-	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;
+	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)
 {

git-add.sh

@@ -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

git-format-patch.sh

@@ -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

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"
 

git-rm.sh

@@ -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

git.c

@@ -47,12 +47,29 @@ 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 },
-		{ "check-ref-format", cmd_check_ref_format }
+		{ "tar-tree", cmd_tar_tree },
+		{ "upload-tar", cmd_upload_tar },
+		{ "check-ref-format", cmd_check_ref_format },
+		{ "ls-files", cmd_ls_files },
+		{ "ls-tree", cmd_ls_tree },
+		{ "tar-tree", cmd_tar_tree },
+		{ "read-tree", cmd_read_tree },
+		{ "commit-tree", cmd_commit_tree },
+		{ "apply", cmd_apply },
+		{ "show-branch", cmd_show_branch },
+		{ "diff-files", cmd_diff_files },
+		{ "diff-index", cmd_diff_index },
+		{ "diff-stages", cmd_diff_stages },
+		{ "diff-tree", cmd_diff_tree },
+		{ "cat-file", cmd_cat_file }
 	};
 	int i;
 

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..
 	 */
+
+	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));
+			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;
 }

mktag.c

@@ -45,42 +45,46 @@ static int verify_tag(char *buffer, unsigned long size)
 	unsigned char sha1[20];
 	const char *object, *type_line, *tag_line, *tagger_line;
 
-	if (size < 64 || size > MAXSIZE-1)
-		return -1;
+	if (size < 64)
+		return error("wanna fool me ? you obviously got the size wrong !\n");
+
 	buffer[size] = 0;
 
 	/* Verify object line */
 	object = buffer;
 	if (memcmp(object, "object ", 7))
-		return -1;
+		return error("char%d: does not start with \"object \"\n", 0);
+
 	if (get_sha1_hex(object + 7, sha1))
-		return -1;
+		return error("char%d: could not get SHA1 hash\n", 7);
 
 	/* Verify type line */
 	type_line = object + 48;
 	if (memcmp(type_line - 1, "\ntype ", 6))
-		return -1;
+		return error("char%d: could not find \"\\ntype \"\n", 47);
 
 	/* Verify tag-line */
 	tag_line = strchr(type_line, '\n');
 	if (!tag_line)
-		return -1;
+		return error("char%td: could not find next \"\\n\"\n", type_line - buffer);
 	tag_line++;
 	if (memcmp(tag_line, "tag ", 4) || tag_line[4] == '\n')
-		return -1;
+		return error("char%td: no \"tag \" found\n", tag_line - buffer);
 
 	/* Get the actual type */
 	typelen = tag_line - type_line - strlen("type \n");
 	if (typelen >= sizeof(type))
-		return -1;
+		return error("char%td: type too long\n", type_line+5 - buffer);
+
 	memcpy(type, type_line+5, typelen);
 	type[typelen] = 0;
 
 	/* Verify that the object matches */
 	if (get_sha1_hex(object + 7, sha1))
-		return -1;
+		return error("char%d: could not get SHA1 hash but this is really odd since i got it before !\n", 7);
+
 	if (verify_object(sha1, type))
-		return -1;
+		return error("char%d: could not verify object %s\n", 7, sha1);
 
 	/* Verify the tag-name: we don't allow control characters or spaces in it */
 	tag_line += 4;
@@ -90,14 +94,14 @@ static int verify_tag(char *buffer, unsigned long size)
 			break;
 		if (c > ' ')
 			continue;
-		return -1;
+		return error("char%td: could not verify tag name\n", tag_line - buffer);
 	}
 
 	/* Verify the tagger line */
 	tagger_line = tag_line;
 
 	if (memcmp(tagger_line, "tagger", 6) || (tagger_line[6] == '\n'))
-		return -1;
+		return error("char%td: could not find \"tagger\"\n", tagger_line - buffer);
 
 	/* The actual stuff afterwards we don't care about.. */
 	return 0;
@@ -105,8 +109,8 @@ static int verify_tag(char *buffer, unsigned long size)
 
 int main(int argc, char **argv)
 {
-	unsigned long size;
-	char buffer[MAXSIZE];
+	unsigned long size = 4096;
+	char *buffer = malloc(size);
 	unsigned char result_sha1[20];
 
 	if (argc != 1)
@@ -114,13 +118,9 @@ int main(int argc, char **argv)
 
 	setup_git_directory();
 
-	// Read the signature
-	size = 0;
-	for (;;) {
-		int ret = xread(0, buffer + size, MAXSIZE - size);
-		if (ret <= 0)
-			break;
-		size += ret;
+	if (read_pipe(0, &buffer, &size)) {
+		free(buffer);
+		die("could not read from stdin");
 	}
 
 	// Verify it for some basic sanity: it needs to start with "object <sha1>\ntype\ntagger "
@@ -129,6 +129,9 @@ int main(int argc, char **argv)
 
 	if (write_sha1_file(buffer, size, tag_type, result_sha1) < 0)
 		die("unable to write tag file");
+
+	free(buffer);
+
 	printf("%s\n", sha1_to_hex(result_sha1));
 	return 0;
 }

read-cache.c

@@ -331,6 +331,70 @@ int ce_path_match(const struct cache_entry *ce, const char **pathspec)
 	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;
+}
+
+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 +536,8 @@ 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)) {

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;

sha1_file.c

@@ -1399,6 +1399,25 @@ int move_temp_to_file(const char *tmpfile, char *filename)
 	return 0;
 }
 
+static int write_buffer(int fd, const void *buf, size_t len)
+{
+	while (len) {
+		ssize_t size;
+
+		size = write(fd, buf, len);
+		if (!size)
+			return error("file write: disk full");
+		if (size < 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
+			return error("file write error (%s)", strerror(errno));
+		}
+		len -= size;
+		buf += size;
+	}
+	return 0;
+}
+
 int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
 {
 	int size;
@@ -1465,8 +1484,8 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	deflateEnd(&stream);
 	size = stream.total_out;
 
-	if (write(fd, compressed, size) != size)
-		die("unable to write file");
+	if (write_buffer(fd, compressed, size) < 0)
+		die("unable to write sha1 file");
 	fchmod(fd, 0444);
 	close(fd);
 	free(compressed);
@@ -1474,22 +1493,21 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	return move_temp_to_file(tmpfile, filename);
 }
 
-int write_sha1_to_fd(int fd, const unsigned char *sha1)
+/*
+ * We need to unpack and recompress the object for writing
+ * it out to a different file.
+ */
+static void *repack_object(const unsigned char *sha1, unsigned long *objsize)
 {
-	ssize_t size;
-	unsigned long objsize;
-	int posn = 0;
-	void *map = map_sha1_file_internal(sha1, &objsize);
-	void *buf = map;
-	void *temp_obj = NULL;
+	size_t size;
 	z_stream stream;
-
-	if (!buf) {
 	unsigned char *unpacked;
 	unsigned long len;
 	char type[20];
 	char hdr[50];
 	int hdrlen;
+	void *buf;
+
 	// need to unpack and recompress it by itself
 	unpacked = read_packed_sha1(sha1, type, &len);
 
@@ -1499,7 +1517,7 @@ int write_sha1_to_fd(int fd, const unsigned char *sha1)
 	memset(&stream, 0, sizeof(stream));
 	deflateInit(&stream, Z_BEST_COMPRESSION);
 	size = deflateBound(&stream, len + hdrlen);
-		temp_obj = buf = xmalloc(size);
+	buf = xmalloc(size);
 
 	/* Compress it */
 	stream.next_out = buf;
@@ -1519,28 +1537,26 @@ int write_sha1_to_fd(int fd, const unsigned char *sha1)
 	deflateEnd(&stream);
 	free(unpacked);
 
-		objsize = stream.total_out;
+	*objsize = stream.total_out;
+	return buf;
 }
 
-	do {
-		size = write(fd, buf + posn, objsize - posn);
-		if (size <= 0) {
-			if (!size) {
-				fprintf(stderr, "write closed\n");
-			} else {
-				perror("write ");
-			}
-			return -1;
-		}
-		posn += size;
-	} while (posn < objsize);
+int write_sha1_to_fd(int fd, const unsigned char *sha1)
+{
+	int retval;
+	unsigned long objsize;
+	void *buf = map_sha1_file_internal(sha1, &objsize);
 
-	if (map)
-		munmap(map, objsize);
-	if (temp_obj)
-		free(temp_obj);
+	if (buf) {
+		retval = write_buffer(fd, buf, objsize);
+		munmap(buf, objsize);
+		return retval;
+	}
 
-	return 0;
+	buf = repack_object(sha1, &objsize);
+	retval = write_buffer(fd, buf, objsize);
+	free(buf);
+	return retval;
 }
 
 int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
@@ -1579,7 +1595,8 @@ int write_sha1_from_fd(const unsigned char *sha1, int fd, char *buffer,
 				SHA1_Update(&c, discard, sizeof(discard) -
 					    stream.avail_out);
 			} while (stream.avail_in && ret == Z_OK);
-			write(local, buffer, *bufposn - stream.avail_in);
+			if (write_buffer(local, buffer, *bufposn - stream.avail_in) < 0)
+				die("unable to write sha1 file");
 			memmove(buffer, buffer + *bufposn - stream.avail_in,
 				stream.avail_in);
 			*bufposn = stream.avail_in;
@@ -1645,16 +1662,24 @@ int has_sha1_file(const unsigned char *sha1)
 	return find_sha1_file(sha1, &st) ? 1 : 0;
 }
 
-int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+/*
+ * reads from fd as long as possible into a supplied buffer of size bytes.
+ * If neccessary the buffer's size is increased using realloc()
+ *
+ * returns 0 if anything went fine and -1 otherwise
+ *
+ * NOTE: both buf and size may change, but even when -1 is returned
+ * you still have to free() it yourself.
+ */
+int read_pipe(int fd, char** return_buf, unsigned long* return_size)
 {
-	unsigned long size = 4096;
-	char *buf = malloc(size);
-	int iret, ret;
+	char* buf = *return_buf;
+	unsigned long size = *return_size;
+	int iret;
 	unsigned long off = 0;
-	unsigned char hdr[50];
-	int hdrlen;
+
 	do {
-		iret = read(fd, buf + off, size - off);
+		iret = xread(fd, buf + off, size - off);
 		if (iret > 0) {
 			off += iret;
 			if (off == size) {
@@ -1663,16 +1688,34 @@ int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
 			}
 		}
 	} while (iret > 0);
-	if (iret < 0) {
+
+	*return_buf = buf;
+	*return_size = off;
+
+	if (iret < 0)
+		return -1;
+	return 0;
+}
+
+int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
+{
+	unsigned long size = 4096;
+	char *buf = malloc(size);
+	int ret;
+	unsigned char hdr[50];
+	int hdrlen;
+
+	if (read_pipe(fd, &buf, &size)) {
 		free(buf);
 		return -1;
 	}
+
 	if (!type)
 		type = blob_type;
 	if (write_object)
-		ret = write_sha1_file(buf, off, type, sha1);
+		ret = write_sha1_file(buf, size, type, sha1);
 	else {
-		write_sha1_file_prepare(buf, off, type, sha1, hdr, &hdrlen);
+		write_sha1_file_prepare(buf, size, type, sha1, hdr, &hdrlen);
 		ret = 0;
 	}
 	free(buf);

update-index.c

@@ -120,70 +120,6 @@ 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)
 {