builtin-fast-export: Add importing and exporting of revision marks

This adds the --import-marks and --export-marks to fast-export. These import
and export the marks used to for all revisions exported in a similar fashion
to what fast-import does. The format is the same as fast-import, so you can
create a bidirectional importer / exporter by using the same marks file on
both sides.

Signed-off-by: Pieter de Bie <pdebie@ai.rug.nl>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 137 insertions, 6 deletions

diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt
index 332346cc5..277a547a0 100644
--- a/Documentation/git-fast-export.txt
+++ b/Documentation/git-fast-export.txt
@@ -36,6 +36,26 @@ when encountering a signed tag.  With 'strip', the tags will be made
 unsigned, with 'verbatim', they will be silently exported
 and with 'warn', they will be exported, but you will see a warning.
 
+--export-marks=<file>::
+	Dumps the internal marks table to <file> when complete.
+	Marks are written one per line as `:markid SHA-1`. Only marks
+	for revisions are dumped; marks for blobs are ignored.
+	Backends can use this file to validate imports after they
+	have been completed, or to save the marks table across
+	incremental runs.  As <file> is only opened and truncated
+	at completion, the same path can also be safely given to
+	\--import-marks.
+
+--import-marks=<file>::
+	Before processing any input, load the marks specified in
+	<file>.  The input file must exist, must be readable, and
+	must use the same format as produced by \--export-marks.
++
+Any commits that have already been marked will not be exported again.
+If the backend uses a similar \--import-marks file, this allows for
+incremental bidirectional exporting of the repository by keeping the
+marks the same across runs.
+
 
 EXAMPLES
 --------
diff --git a/builtin-fast-export.c b/builtin-fast-export.c
index d0a462ff8..45786ef1b 100644
--- a/builtin-fast-export.c
+++ b/builtin-fast-export.c
@@ -56,10 +56,24 @@ static int has_unshown_parent(struct commit *commit)
 }
 
 /* Since intptr_t is C99, we do not use it here */
-static void mark_object(struct object *object)
+static inline uint32_t *mark_to_ptr(uint32_t mark)
 {
-	last_idnum++;
-	add_decoration(&idnums, object, ((uint32_t *)NULL) + last_idnum);
+	return ((uint32_t *)NULL) + mark;
+}
+
+static inline uint32_t ptr_to_mark(void * mark)
+{
+	return (uint32_t *)mark - (uint32_t *)NULL;
+}
+
+static inline void mark_object(struct object *object, uint32_t mark)
+{
+	add_decoration(&idnums, object, mark_to_ptr(mark));
+}
+
+static inline void mark_next_object(struct object *object)
+{
+	mark_object(object, ++last_idnum);
 }
 
 static int get_object_mark(struct object *object)
@@ -67,7 +81,7 @@ 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;
+	return ptr_to_mark(decoration);
 }
 
 static void show_progress(void)
@@ -100,7 +114,7 @@ static void handle_object(const unsigned char *sha1)
 	if (!buf)
 		die ("Could not read blob %s", sha1_to_hex(sha1));
 
-	mark_object(object);
+	mark_next_object(object);
 
 	printf("blob\nmark :%d\ndata %lu\n", last_idnum, size);
 	if (size && fwrite(buf, size, 1, stdout) != 1)
@@ -185,7 +199,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev)
 	for (i = 0; i < diff_queued_diff.nr; i++)
 		handle_object(diff_queued_diff.queue[i]->two->sha1);
 
-	mark_object(&commit->object);
+	mark_next_object(&commit->object);
 	if (!is_encoding_utf8(encoding))
 		reencoded = reencode_string(message, "UTF-8", encoding);
 	if (!commit->parents)
@@ -354,18 +368,85 @@ static void handle_tags_and_duplicates(struct path_list *extra_refs)
 	}
 }
 
+static void export_marks(char *file)
+{
+	unsigned int i;
+	uint32_t mark;
+	struct object_decoration *deco = idnums.hash;
+	FILE *f;
+
+	f = fopen(file, "w");
+	if (!f)
+		error("Unable to open marks file %s for writing", file);
+
+	for (i = 0; i < idnums.size; ++i) {
+		deco++;
+		if (deco && deco->base && deco->base->type == 1) {
+			mark = ptr_to_mark(deco->decoration);
+			fprintf(f, ":%u %s\n", mark, sha1_to_hex(deco->base->sha1));
+		}
+	}
+
+	if (ferror(f) || fclose(f))
+		error("Unable to write marks file %s.", file);
+}
+
+static void import_marks(char * input_file)
+{
+	char line[512];
+	FILE *f = fopen(input_file, "r");
+	if (!f)
+		die("cannot read %s: %s", input_file, strerror(errno));
+
+	while (fgets(line, sizeof(line), f)) {
+		uint32_t mark;
+		char *line_end, *mark_end;
+		unsigned char sha1[20];
+		struct object *object;
+
+		line_end = strchr(line, '\n');
+		if (line[0] != ':' || !line_end)
+			die("corrupt mark line: %s", line);
+		*line_end = 0;
+
+		mark = strtoumax(line + 1, &mark_end, 10);
+		if (!mark || mark_end == line + 1
+			|| *mark_end != ' ' || get_sha1(mark_end + 1, sha1))
+			die("corrupt mark line: %s", line);
+
+		object = parse_object(sha1);
+		if (!object)
+			die ("Could not read blob %s", sha1_to_hex(sha1));
+
+		if (object->flags & SHOWN)
+			error("Object %s already has a mark", sha1);
+
+		mark_object(object, mark);
+		if (last_idnum < mark)
+			last_idnum = mark;
+
+		object->flags |= SHOWN;
+	}
+	fclose(f);
+}
+
 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;
+	char *export_filename = NULL, *import_filename = NULL;
 	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_STRING(0, "export-marks", &export_filename, "FILE",
+			     "Dump marks to this file"),
+		OPT_STRING(0, "import-marks", &import_filename, "FILE",
+			     "Import marks from this file"),
 		OPT_END()
 	};
 
@@ -378,6 +459,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 	if (argc > 1)
 		usage_with_options (fast_export_usage, options);
 
+	if (import_filename)
+		import_marks(import_filename);
+
 	get_tags_and_duplicates(&revs.pending, &extra_refs);
 
 	if (prepare_revision_walk(&revs))
@@ -400,5 +484,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 
 	handle_tags_and_duplicates(&extra_refs);
 
+	if (export_filename)
+		export_marks(export_filename);
+
 	return 0;
 }
diff --git a/t/t9301-fast-export.sh b/t/t9301-fast-export.sh
index f09bfb111..60b5ee397 100755
--- a/t/t9301-fast-export.sh
+++ b/t/t9301-fast-export.sh
@@ -78,6 +78,30 @@ test_expect_success 'iso-8859-1' '
 		 git cat-file commit i18n | grep "Áéí óú")
 
 '
+test_expect_success 'import/export-marks' '
+
+	git checkout -b marks master &&
+	git fast-export --export-marks=tmp-marks HEAD &&
+	test -s tmp-marks &&
+	cp tmp-marks ~ &&
+	test $(wc -l < tmp-marks) -eq 3 &&
+	test $(
+		git fast-export --import-marks=tmp-marks\
+		--export-marks=tmp-marks HEAD |
+		grep ^commit |
+		wc -l) \
+	-eq 0 &&
+	echo change > file &&
+	git commit -m "last commit" file &&
+	test $(
+		git fast-export --import-marks=tmp-marks \
+		--export-marks=tmp-marks HEAD |
+		grep ^commit\  |
+		wc -l) \
+	-eq 1 &&
+	test $(wc -l < tmp-marks) -eq 4
+
+'
 
 cat > signed-tag-import << EOF
 tag sign-your-name