aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGeoffrey Irving <irving@naml.us>2009-07-27 22:20:22 -0400
committerJunio C Hamano <gitster@pobox.com>2009-07-31 07:48:09 -0700
commit79559f27be7e2963213d840a857dee92c579843f (patch)
treee528f5e534c2f0898b291ac12821627f5c73353e
parent86b5efb2864ca50d86437f94ec4c26042cba193e (diff)
downloadgit-79559f27be7e2963213d840a857dee92c579843f.tar.gz
git-79559f27be7e2963213d840a857dee92c579843f.tar.xz
git fast-export: add --no-data option
When using git fast-export and git fast-import to rewrite the history of a repository with large binary files, almost all of the time is spent dealing with blobs. This is extremely inefficient if all we want to do is rewrite the commits and tree structure. --no-data skips the output of blobs and writes SHA-1s instead of marks, which provides a massive speedup. Signed-off-by: Geoffrey Irving <irving@naml.us> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--Documentation/git-fast-export.txt8
-rw-r--r--builtin-fast-export.c9
2 files changed, 16 insertions, 1 deletions
diff --git a/Documentation/git-fast-export.txt b/Documentation/git-fast-export.txt
index af2328d40..75b06f33e 100644
--- a/Documentation/git-fast-export.txt
+++ b/Documentation/git-fast-export.txt
@@ -82,6 +82,14 @@ marks the same across runs.
allow that. So fake a tagger to be able to fast-import the
output.
+--no-data::
+ Skip output of blob objects and instead refer to blobs via
+ their original SHA-1 hash. This is useful when rewriting the
+ directory structure or history of a repository without
+ touching the contents of individual files. Note that the
+ resulting stream can only be used by a repository which
+ already contains the necessary objects.
+
[git-rev-list-args...]::
A list of arguments, acceptable to 'git-rev-parse' and
'git-rev-list', that specifies the specific objects and references
diff --git a/builtin-fast-export.c b/builtin-fast-export.c
index c48c18d0c..b0a4029c9 100644
--- a/builtin-fast-export.c
+++ b/builtin-fast-export.c
@@ -26,6 +26,7 @@ static int progress;
static enum { ABORT, VERBATIM, WARN, STRIP } signed_tag_mode = ABORT;
static enum { ERROR, DROP, REWRITE } tag_of_filtered_mode = ABORT;
static int fake_missing_tagger;
+static int no_data;
static int parse_opt_signed_tag_mode(const struct option *opt,
const char *arg, int unset)
@@ -116,6 +117,9 @@ static void handle_object(const unsigned char *sha1)
char *buf;
struct object *object;
+ if (no_data)
+ return;
+
if (is_null_sha1(sha1))
return;
@@ -173,7 +177,7 @@ static void show_filemodify(struct diff_queue_struct *q,
* Links refer to objects in another repositories;
* output the SHA-1 verbatim.
*/
- if (S_ISGITLINK(spec->mode))
+ if (no_data || S_ISGITLINK(spec->mode))
printf("M %06o %s %s\n", spec->mode,
sha1_to_hex(spec->sha1), spec->path);
else {
@@ -580,6 +584,9 @@ int cmd_fast_export(int argc, const char **argv, const char *prefix)
"Import marks from this file"),
OPT_BOOLEAN(0, "fake-missing-tagger", &fake_missing_tagger,
"Fake a tagger when tags lack one"),
+ { OPTION_NEGBIT, 0, "data", &no_data, NULL,
+ "Skip output of blob data",
+ PARSE_OPT_NOARG | PARSE_OPT_NEGHELP, NULL, 1 },
OPT_END()
};