fast-export: add a --show-original-ids option to show original names

Knowing the original names (hashes) of commits can sometimes enable
post-filtering that would otherwise be difficult or impossible.  In
particular, the desire to rewrite commit messages which refer to other
prior commits (on top of whatever other filtering is being done) is
very difficult without knowing the original names of each commit.

In addition, knowing the original names (hashes) of blobs can allow
filtering by blob-id without requiring re-hashing the content of the
blob, and is thus useful as a small optimization.

Once we add original ids for both commits and blobs, we may as well
add them for tags too for completeness.  Perhaps someone will have a
use for them.

This commit teaches a new --show-original-ids option to fast-export
which will make it add a 'original-oid <hash>' line to blob, commits,
and tags.  It also teaches fast-import to parse (and ignore) such
lines.

Signed-off-by: Elijah Newren <newren@gmail.com>
Acked-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 15 insertions, 5 deletions

diff --git a/builtin/fast-export.c b/builtin/fast-export.c
index 78fc67b03aa..36c2575de52 100644
--- a/builtin/fast-export.c
+++ b/builtin/fast-export.c
@@ -38,6 +38,7 @@ static int use_done_feature;
 static int no_data;
 static int full_tree;
 static int reference_excluded_commits;
+static int show_original_ids;
 static struct string_list extra_refs = STRING_LIST_INIT_NODUP;
 static struct string_list tag_refs = STRING_LIST_INIT_NODUP;
 static struct refspec refspecs = REFSPEC_INIT_FETCH;
@@ -271,7 +272,10 @@ static void export_blob(const struct object_id *oid)
 
 	mark_next_object(object);
 
-	printf("blob\nmark :%"PRIu32"\ndata %lu\n", last_idnum, size);
+	printf("blob\nmark :%"PRIu32"\n", last_idnum);
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(oid));
+	printf("data %lu\n", size);
 	if (size && fwrite(buf, size, 1, stdout) != 1)
 		die_errno("could not write blob '%s'", oid_to_hex(oid));
 	printf("\n");
@@ -635,8 +639,10 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 		reencoded = reencode_string(message, "UTF-8", encoding);
 	if (!commit->parents)
 		printf("reset %s\n", refname);
-	printf("commit %s\nmark :%"PRIu32"\n%.*s\n%.*s\ndata %u\n%s",
-	       refname, last_idnum,
+	printf("commit %s\nmark :%"PRIu32"\n", refname, last_idnum);
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(&commit->object.oid));
+	printf("%.*s\n%.*s\ndata %u\n%s",
 	       (int)(author_end - author), author,
 	       (int)(committer_end - committer), committer,
 	       (unsigned)(reencoded
@@ -814,8 +820,10 @@ static void handle_tag(const char *name, struct tag *tag)
 
 	if (starts_with(name, "refs/tags/"))
 		name += 10;
-	printf("tag %s\nfrom :%d\n%.*s%sdata %d\n%.*s\n",
-	       name, tagged_mark,
+	printf("tag %s\nfrom :%d\n", name, tagged_mark);
+	if (show_original_ids)
+		printf("original-oid %s\n", oid_to_hex(&tag->object.oid));
+	printf("%.*s%sdata %d\n%.*s\n",
 	       (int)(tagger_end - tagger), tagger,
 	       tagger == tagger_end ? "" : "\n",
 	       (int)message_size, (int)message_size, message ? message : "");
@@ -1096,6 +1104,8 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
 		OPT_BOOL(0, "anonymize", &anonymize, N_("anonymize output")),
 		OPT_BOOL(0, "reference-excluded-parents",
 			 &reference_excluded_commits, N_("Reference parents which are not in fast-export stream by object id")),
+		OPT_BOOL(0, "show-original-ids", &show_original_ids,
+			    N_("Show original object ids of blobs/commits")),
 
 		OPT_END()
 	};