Merge branch 'js/fast-export'

* js/fast-export:
  Add 'git fast-export', the sister of 'git fast-import'

7 files changed, 616 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
index c8c13f5503..916fabc6c5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -35,6 +35,7 @@ git-diff-files
 git-diff-index
 git-diff-tree
 git-describe
+git-fast-export
 git-fast-import
 git-fetch
 git-fetch--tool
diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt
new file mode 100644
index 0000000000..073ff7f123
--- /dev/null
+++ b/Documentation/git-fast-export.txt
@@ -0,0 +1,83 @@
+git-fast-export(1)
+==================
+
+NAME
+----
+git-fast-export - Git data exporter
+
+
+SYNOPSIS
+--------
+'git-fast-export [options]' | 'git-fast-import'
+
+DESCRIPTION
+-----------
+This program dumps the given revisions in a form suitable to be piped
+into gitlink:git-fast-import[1].
+
+You can use it as a human readable bundle replacement (see
+gitlink:git-bundle[1]), or as a kind of an interactive
+gitlink:git-filter-branch[1].
+
+
+OPTIONS
+-------
+--progress=<n>::
+	Insert 'progress' statements every <n> objects, to be shown by
+	gitlink:git-fast-import[1] during import.
+
+--signed-tags=(ignore|warn|strip|abort)::
+	Specify how to handle signed tags.  Since any transformation
+	after the export can change the tag names (which can also happen
+	when excluding revisions) the signatures will not match.
++
+When asking to 'abort' (which is the default), this program will die
+when encountering a signed tag.  With 'strip', the tags will be made
+unsigned, with 'ignore', they will be silently ignored (i.e. not exported)
+and with 'warn', they will be exported, but you will see a warning.
+
+
+EXAMPLES
+--------
+
+-------------------------------------------------------------------
+$ git fast-export --all | (cd /empty/repository && git fast-import)
+-------------------------------------------------------------------
+
+This will export the whole repository and import it into the existing
+empty repository.  Except for reencoding commits that are not in
+UTF-8, it would be a one-to-one mirror.
+
+-----------------------------------------------------
+$ git fast-export master~5..master |
+	sed "s|refs/heads/master|refs/heads/other|" |
+	git fast-import
+-----------------------------------------------------
+
+This makes a new branch called 'other' from 'master~5..master'
+(i.e. if 'master' has linear history, it will take the last 5 commits).
+
+Note that this assumes that none of the blobs and commit messages
+referenced by that revision range contains the string
+'refs/heads/master'.
+
+
+Limitations
+-----------
+
+Since gitlink:git-fast-import[1] cannot tag trees, you will not be
+able to export the linux-2.6.git repository completely, as it contains
+a tag referencing a tree instead of a commit.
+
+
+Author
+------
+Written by Johannes E. Schindelin <johannes.schindelin@gmx.de>.
+
+Documentation
+--------------
+Documentation by Johannes E. Schindelin <johannes.schindelin@gmx.de>.
+
+GIT
+---
+Part of the gitlink:git[7] suite
diff --git a/Makefile b/Makefile
index d5d2c7c0c0..feb52c6860 100644
--- a/Makefile
+++ b/Makefile
@@ -334,6 +334,7 @@ BUILTIN_OBJS = \
 	builtin-diff-files.o \
 	builtin-diff-index.o \
 	builtin-diff-tree.o \
+	builtin-fast-export.o \
 	builtin-fetch.o \
 	builtin-fetch-pack.o \
 	builtin-fetch--tool.o \
diff --git a/builtin-fast-export.c b/builtin-fast-export.c
new file mode 100755
index 0000000000..72be45db46
--- /dev/null
+++ b/builtin-fast-export.c
@@ -0,0 +1,406 @@
+/*
+ * "git fast-export" builtin command
+ *
+ * Copyright (C) 2007 Johannes E. Schindelin
+ */
+#include "builtin.h"
+#include "cache.h"
+#include "commit.h"
+#include "object.h"
+#include "tag.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "log-tree.h"
+#include "revision.h"
+#include "decorate.h"
+#include "path-list.h"
+#include "utf8.h"
+#include "parse-options.h"
+
+static const char *fast_export_usage[] = {
+	"git-fast-export [rev-list-opts]",
+	NULL
+};
+
+static int progress;
+static enum { IGNORE, WARN, STRIP, ABORT } signed_tag_mode = ABORT;
+
+static int parse_opt_signed_tag_mode(const struct option *opt,
+				     const char *arg, int unset)
+{
+	if (unset || !strcmp(arg, "abort"))
+		signed_tag_mode = ABORT;
+	else if (!strcmp(arg, "ignore"))
+		signed_tag_mode = IGNORE;
+	else if (!strcmp(arg, "warn"))
+		signed_tag_mode = WARN;
+	else if (!strcmp(arg, "strip"))
+		signed_tag_mode = STRIP;
+	else
+		return error("Unknown signed-tag mode: %s", arg);
+	return 0;
+}
+
+static struct decoration idnums;
+static uint32_t last_idnum;
+
+static int has_unshown_parent(struct commit *commit)
+{
+	struct commit_list *parent;
+
+	for (parent = commit->parents; parent; parent = parent->next)
+		if (!(parent->item->object.flags & SHOWN) &&
+		    !(parent->item->object.flags & UNINTERESTING))
+			return 1;
+	return 0;
+}
+
+/* Since intptr_t is C99, we do not use it here */
+static void mark_object(struct object *object)
+{
+	last_idnum++;
+	add_decoration(&idnums, object, ((uint32_t *)NULL) + last_idnum);
+}
+
+static int get_object_mark(struct object *object)
+{
+	void *decoration = lookup_decoration(&idnums, object);
+	if (!decoration)
+		return 0;
+	return (uint32_t *)decoration - (uint32_t *)NULL;
+}
+
+static void show_progress(void)
+{
+	static int counter = 0;
+	if (!progress)
+		return;
+	if ((++counter % progress) == 0)
+		printf("progress %d objects\n", counter);
+}
+
+static void handle_object(const unsigned char *sha1)
+{
+	unsigned long size;
+	enum object_type type;
+	char *buf;
+	struct object *object;
+
+	if (is_null_sha1(sha1))
+		return;
+
+	object = parse_object(sha1);
+	if (!object)
+		die ("Could not read blob %s", sha1_to_hex(sha1));
+
+	if (object->flags & SHOWN)
+		return;
+
+	buf = read_sha1_file(sha1, &type, &size);
+	if (!buf)
+		die ("Could not read blob %s", sha1_to_hex(sha1));
+
+	mark_object(object);
+
+	printf("blob\nmark :%d\ndata %lu\n", last_idnum, size);
+	if (fwrite(buf, size, 1, stdout) != 1)
+		die ("Could not write blob %s", sha1_to_hex(sha1));
+	printf("\n");
+
+	show_progress();
+
+	object->flags |= SHOWN;
+	free(buf);
+}
+
+static void show_filemodify(struct diff_queue_struct *q,
+			    struct diff_options *options, void *data)
+{
+	int i;
+	for (i = 0; i < q->nr; i++) {
+		struct diff_filespec *spec = q->queue[i]->two;
+		if (is_null_sha1(spec->sha1))
+			printf("D %s\n", spec->path);
+		else {
+			struct object *object = lookup_object(spec->sha1);
+			printf("M 0%06o :%d %s\n", spec->mode,
+			       get_object_mark(object), spec->path);
+		}
+	}
+}
+
+static const char *find_encoding(const char *begin, const char *end)
+{
+	const char *needle = "\nencoding ";
+	char *bol, *eol;
+
+	bol = memmem(begin, end ? end - begin : strlen(begin),
+		     needle, strlen(needle));
+	if (!bol)
+		return git_commit_encoding;
+	bol += strlen(needle);
+	eol = strchrnul(bol, '\n');
+	*eol = '\0';
+	return bol;
+}
+
+static void handle_commit(struct commit *commit, struct rev_info *rev)
+{
+	int saved_output_format = rev->diffopt.output_format;
+	const char *author, *author_end, *committer, *committer_end;
+	const char *encoding, *message;
+	char *reencoded = NULL;
+	struct commit_list *p;
+	int i;
+
+	rev->diffopt.output_format = DIFF_FORMAT_CALLBACK;
+
+	parse_commit(commit);
+	author = strstr(commit->buffer, "\nauthor ");
+	if (!author)
+		die ("Could not find author in commit %s",
+		     sha1_to_hex(commit->object.sha1));
+	author++;
+	author_end = strchrnul(author, '\n');
+	committer = strstr(author_end, "\ncommitter ");
+	if (!committer)
+		die ("Could not find committer in commit %s",
+		     sha1_to_hex(commit->object.sha1));
+	committer++;
+	committer_end = strchrnul(committer, '\n');
+	message = strstr(committer_end, "\n\n");
+	encoding = find_encoding(committer_end, message);
+	if (message)
+		message += 2;
+
+	if (commit->parents) {
+		parse_commit(commit->parents->item);
+		diff_tree_sha1(commit->parents->item->tree->object.sha1,
+			       commit->tree->object.sha1, "", &rev->diffopt);
+	}
+	else
+		diff_root_tree_sha1(commit->tree->object.sha1,
+				    "", &rev->diffopt);
+
+	for (i = 0; i < diff_queued_diff.nr; i++)
+		handle_object(diff_queued_diff.queue[i]->two->sha1);
+
+	mark_object(&commit->object);
+	if (!is_encoding_utf8(encoding))
+		reencoded = reencode_string(message, "UTF-8", encoding);
+	printf("commit %s\nmark :%d\n%.*s\n%.*s\ndata %u\n%s",
+	       (const char *)commit->util, last_idnum,
+	       (int)(author_end - author), author,
+	       (int)(committer_end - committer), committer,
+	       (unsigned)(reencoded
+			  ? strlen(reencoded) : message
+			  ? strlen(message) : 0),
+	       reencoded ? reencoded : message ? message : "");
+	if (reencoded)
+		free(reencoded);
+
+	for (i = 0, p = commit->parents; p; p = p->next) {
+		int mark = get_object_mark(&p->item->object);
+		if (!mark)
+			continue;
+		if (i == 0)
+			printf("from :%d\n", mark);
+		else if (i == 1)
+			printf("merge :%d", mark);
+		else
+			printf(" :%d", mark);
+		i++;
+	}
+	if (i > 1)
+		printf("\n");
+
+	log_tree_diff_flush(rev);
+	rev->diffopt.output_format = saved_output_format;
+
+	printf("\n");
+
+	show_progress();
+}
+
+static void handle_tail(struct object_array *commits, struct rev_info *revs)
+{
+	struct commit *commit;
+	while (commits->nr) {
+		commit = (struct commit *)commits->objects[commits->nr - 1].item;
+		if (has_unshown_parent(commit))
+			return;
+		handle_commit(commit, revs);
+		commits->nr--;
+	}
+}
+
+static void handle_tag(const char *name, struct tag *tag)
+{
+	unsigned long size;
+	enum object_type type;
+	char *buf;
+	const char *tagger, *tagger_end, *message;
+	size_t message_size = 0;
+
+	buf = read_sha1_file(tag->object.sha1, &type, &size);
+	if (!buf)
+		die ("Could not read tag %s", sha1_to_hex(tag->object.sha1));
+	message = memmem(buf, size, "\n\n", 2);
+	if (message) {
+		message += 2;
+		message_size = strlen(message);
+	}
+	tagger = memmem(buf, message ? message - buf : size, "\ntagger ", 8);
+	if (!tagger)
+		die ("No tagger for tag %s", sha1_to_hex(tag->object.sha1));
+	tagger++;
+	tagger_end = strchrnul(tagger, '\n');
+
+	/* handle signed tags */
+	if (message) {
+		const char *signature = strstr(message,
+					       "\n-----BEGIN PGP SIGNATURE-----\n");
+		if (signature)
+			switch(signed_tag_mode) {
+			case ABORT:
+				die ("Encountered signed tag %s; use "
+				     "--signed-tag=<mode> to handle it.",
+				     sha1_to_hex(tag->object.sha1));
+			case WARN:
+				warning ("Exporting signed tag %s",
+					 sha1_to_hex(tag->object.sha1));
+				/* fallthru */
+			case IGNORE:
+				break;
+			case STRIP:
+				message_size = signature + 1 - message;
+				break;
+			}
+	}
+
+	if (!prefixcmp(name, "refs/tags/"))
+		name += 10;
+	printf("tag %s\nfrom :%d\n%.*s\ndata %d\n%.*s\n",
+	       name, get_object_mark(tag->tagged),
+	       (int)(tagger_end - tagger), tagger,
+	       (int)message_size, (int)message_size, message ? message : "");
+}
+
+static void get_tags_and_duplicates(struct object_array *pending,
+				    struct path_list *extra_refs)
+{
+	struct tag *tag;
+	int i;
+
+	for (i = 0; i < pending->nr; i++) {
+		struct object_array_entry *e = pending->objects + i;
+		unsigned char sha1[20];
+		struct commit *commit = commit;
+		char *full_name;
+
+		if (dwim_ref(e->name, strlen(e->name), sha1, &full_name) != 1)
+			continue;
+
+		switch (e->item->type) {
+		case OBJ_COMMIT:
+			commit = (struct commit *)e->item;
+			break;
+		case OBJ_TAG:
+			tag = (struct tag *)e->item;
+			while (tag && tag->object.type == OBJ_TAG) {
+				path_list_insert(full_name, extra_refs)->util = tag;
+				tag = (struct tag *)tag->tagged;
+			}
+			if (!tag)
+				die ("Tag %s points nowhere?", e->name);
+			switch(tag->object.type) {
+			case OBJ_COMMIT:
+				commit = (struct commit *)tag;
+				break;
+			case OBJ_BLOB:
+				handle_object(tag->object.sha1);
+				continue;
+			}
+			break;
+		default:
+			die ("Unexpected object of type %s",
+			     typename(e->item->type));
+		}
+		if (commit->util)
+			/* more than one name for the same object */
+			path_list_insert(full_name, extra_refs)->util = commit;
+		else
+			commit->util = full_name;
+	}
+}
+
+static void handle_tags_and_duplicates(struct path_list *extra_refs)
+{
+	struct commit *commit;
+	int i;
+
+	for (i = extra_refs->nr - 1; i >= 0; i--) {
+		const char *name = extra_refs->items[i].path;
+		struct object *object = extra_refs->items[i].util;
+		switch (object->type) {
+		case OBJ_TAG:
+			handle_tag(name, (struct tag *)object);
+			break;
+		case OBJ_COMMIT:
+			/* create refs pointing to already seen commits */
+			commit = (struct commit *)object;
+			printf("reset %s\nfrom :%d\n\n", name,
+			       get_object_mark(&commit->object));
+			show_progress();
+			break;
+		}
+	}
+}
+
+int cmd_fast_export(int argc, const char **argv, const char *prefix)
+{
+	struct rev_info revs;
+	struct object_array commits = { 0, 0, NULL };
+	struct path_list extra_refs = { NULL, 0, 0, 0 };
+	struct commit *commit;
+	struct option options[] = {
+		OPT_INTEGER(0, "progress", &progress,
+			    "show progress after <n> objects"),
+		OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, "mode",
+			     "select handling of signed tags",
+			     parse_opt_signed_tag_mode),
+		OPT_END()
+	};
+
+	/* we handle encodings */
+	git_config(git_default_config);
+
+	init_revisions(&revs, prefix);
+	argc = setup_revisions(argc, argv, &revs, NULL);
+	argc = parse_options(argc, argv, options, fast_export_usage, 0);
+	if (argc > 1)
+		usage_with_options (fast_export_usage, options);
+
+	get_tags_and_duplicates(&revs.pending, &extra_refs);
+
+	prepare_revision_walk(&revs);
+	revs.diffopt.format_callback = show_filemodify;
+	DIFF_OPT_SET(&revs.diffopt, RECURSIVE);
+	while ((commit = get_revision(&revs))) {
+		if (has_unshown_parent(commit)) {
+			struct commit_list *parent = commit->parents;
+			add_object_array(&commit->object, NULL, &commits);
+			for (; parent; parent = parent->next)
+				if (!parent->item->util)
+					parent->item->util = commit->util;
+		}
+		else {
+			handle_commit(commit, &revs);
+			handle_tail(&commits, &revs);
+		}
+	}
+
+	handle_tags_and_duplicates(&extra_refs);
+
+	return 0;
+}
diff --git a/builtin.h b/builtin.h
index 98ada7b7f7..3c1bf38d83 100644
--- a/builtin.h
+++ b/builtin.h
@@ -32,6 +32,7 @@ extern int cmd_diff_files(int argc, const char **argv, const char *prefix);
 extern int cmd_diff_index(int argc, const char **argv, const char *prefix);
 extern int cmd_diff(int argc, const char **argv, const char *prefix);
 extern int cmd_diff_tree(int argc, const char **argv, const char *prefix);
+extern int cmd_fast_export(int argc, const char **argv, const char *prefix);
 extern int cmd_fetch(int argc, const char **argv, const char *prefix);
 extern int cmd_fetch_pack(int argc, const char **argv, const char *prefix);
 extern int cmd_fetch__tool(int argc, const char **argv, const char *prefix);
diff --git a/git.c b/git.c
index 01bbbc7325..f510fe3706 100644
--- a/git.c
+++ b/git.c
@@ -302,6 +302,7 @@ static void handle_internal_command(int argc, const char **argv)
 		{ "diff-files", cmd_diff_files },
 		{ "diff-index", cmd_diff_index, RUN_SETUP },
 		{ "diff-tree", cmd_diff_tree, RUN_SETUP },
+		{ "fast-export", cmd_fast_export, RUN_SETUP },
 		{ "fetch", cmd_fetch, RUN_SETUP },
 		{ "fetch-pack", cmd_fetch_pack, RUN_SETUP },
 		{ "fetch--tool", cmd_fetch__tool, RUN_SETUP },
diff --git a/t/t9301-fast-export.sh b/t/t9301-fast-export.sh
new file mode 100755
index 0000000000..e9c9fe65d0
--- /dev/null
+++ b/t/t9301-fast-export.sh
@@ -0,0 +1,123 @@
+#!/bin/sh
+#
+# Copyright (c) 2007 Johannes E. Schindelin
+#
+
+test_description='git-fast-export'
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+
+	echo Wohlauf > file &&
+	git add file &&
+	test_tick &&
+	git commit -m initial &&
+	echo die Luft > file &&
+	echo geht frisch > file2 &&
+	git add file file2 &&
+	test_tick &&
+	git commit -m second &&
+	echo und > file2 &&
+	test_tick &&
+	git commit -m third file2 &&
+	test_tick &&
+	git tag rein &&
+	git checkout -b wer HEAD^ &&
+	echo lange > file2
+	test_tick &&
+	git commit -m sitzt file2 &&
+	test_tick &&
+	git tag -a -m valentin muss &&
+	git merge -s ours master
+
+'
+
+test_expect_success 'fast-export | fast-import' '
+
+	MASTER=$(git rev-parse --verify master) &&
+	REIN=$(git rev-parse --verify rein) &&
+	WER=$(git rev-parse --verify wer) &&
+	MUSS=$(git rev-parse --verify muss) &&
+	mkdir new &&
+	git --git-dir=new/.git init &&
+	git fast-export --all |
+	(cd new &&
+	 git fast-import &&
+	 test $MASTER = $(git rev-parse --verify refs/heads/master) &&
+	 test $REIN = $(git rev-parse --verify refs/tags/rein) &&
+	 test $WER = $(git rev-parse --verify refs/heads/wer) &&
+	 test $MUSS = $(git rev-parse --verify refs/tags/muss))
+
+'
+
+test_expect_success 'fast-export master~2..master' '
+
+	git fast-export master~2..master |
+		sed "s/master/partial/" |
+		(cd new &&
+		 git fast-import &&
+		 test $MASTER != $(git rev-parse --verify refs/heads/partial) &&
+		 git diff master..partial &&
+		 git diff master^..partial^ &&
+		 ! git rev-parse partial~2)
+
+'
+
+test_expect_success 'iso-8859-1' '
+
+	git config i18n.commitencoding ISO-8859-1 &&
+	# use author and committer name in ISO-8859-1 to match it.
+	. ../t3901-8859-1.txt &&
+	test_tick &&
+	echo rosten >file &&
+	git commit -s -m den file &&
+	git fast-export wer^..wer |
+		sed "s/wer/i18n/" |
+		(cd new &&
+		 git fast-import &&
+		 git cat-file commit i18n | grep "Áéí óú")
+
+'
+
+cat > signed-tag-import << EOF
+tag sign-your-name
+from $(git rev-parse HEAD)
+tagger C O Mitter <committer@example.com> 1112911993 -0700
+data 210
+A message for a sign
+-----BEGIN PGP SIGNATURE-----
+Version: GnuPG v1.4.5 (GNU/Linux)
+
+fakedsignaturefakedsignaturefakedsignaturefakedsignaturfakedsign
+aturefakedsignaturefake=
+=/59v
+-----END PGP SIGNATURE-----
+EOF
+
+test_expect_success 'set up faked signed tag' '
+
+	cat signed-tag-import | git fast-import
+
+'
+
+test_expect_success 'signed-tags=abort' '
+
+	! git fast-export --signed-tags=abort sign-your-name
+
+'
+
+test_expect_success 'signed-tags=ignore' '
+
+	git fast-export --signed-tags=ignore sign-your-name > output &&
+	grep PGP output
+
+'
+
+test_expect_success 'signed-tags=strip' '
+
+	git fast-export --signed-tags=strip sign-your-name > output &&
+	! grep PGP output
+
+'
+
+test_done