path: root/builtin/cat-file.c
diff options
authorJeff King <>2013-07-11 20:45:59 (GMT)
committerJunio C Hamano <>2013-07-12 16:18:42 (GMT)
commitc334b87b30c1464a1ab563fe1fb8de5eaf0e5bac (patch)
tree95093a5c179984322a67de65f61e78eadc0ce6f7 /builtin/cat-file.c
parenta4ac1061783d25db4253309d2b58b9c2b89401d7 (diff)
cat-file: split --batch input lines on whitespace
If we get an input line to --batch or --batch-check that looks like "HEAD foo bar", we will currently feed the whole thing to get_sha1(). This means that to use --batch-check with `rev-list --objects`, one must pre-process the input, like: git rev-list --objects HEAD | cut -d' ' -f1 | git cat-file --batch-check Besides being more typing and slightly less efficient to invoke `cut`, the result loses information: we no longer know which path each object was found at. This patch teaches cat-file to split input lines at the first whitespace. Everything to the left of the whitespace is considered an object name, and everything to the right is made available as the %(reset) atom. So you can now do: git rev-list --objects HEAD | git cat-file --batch-check='%(objectsize) %(rest)' to collect object sizes at particular paths. Even if %(rest) is not used, we always do the whitespace split (which means you can simply eliminate the `cut` command from the first example above). This whitespace split is backwards compatible for any reasonable input. Object names cannot contain spaces, so any input with spaces would have resulted in a "missing" line. The only input hurt is if somebody really expected input of the form "HEAD is a fine-looking ref!" to fail; it will now parse HEAD, and make "is a fine-looking ref!" available as %(rest). Signed-off-by: Jeff King <> Signed-off-by: Junio C Hamano <>
Diffstat (limited to 'builtin/cat-file.c')
1 files changed, 19 insertions, 1 deletions
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 11fa8c0..0e64b41 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -119,6 +119,7 @@ struct expand_data {
enum object_type type;
unsigned long size;
unsigned long disk_size;
+ const char *rest;
* If mark_query is true, we do not expand anything, but rather
@@ -161,6 +162,9 @@ static void expand_atom(struct strbuf *sb, const char *atom, int len,
data->info.disk_sizep = &data->disk_size;
strbuf_addf(sb, "%lu", data->disk_size);
+ } else if (is_atom("rest", atom, len)) {
+ if (!data->mark_query && data->rest)
+ strbuf_addstr(sb, data->rest);
} else
die("unknown format element: %.*s", len, atom);
@@ -263,7 +267,21 @@ static int batch_objects(struct batch_options *opt)
data.mark_query = 0;
while (strbuf_getline(&buf, stdin, '\n') != EOF) {
- int error = batch_one_object(buf.buf, opt, &data);
+ char *p;
+ int error;
+ /*
+ * Split at first whitespace, tying off the beginning of the
+ * string and saving the remainder (or NULL) in
+ */
+ p = strpbrk(buf.buf, " \t");
+ if (p) {
+ while (*p && strchr(" \t", *p))
+ *p++ = '\0';
+ }
+ = p;
+ error = batch_one_object(buf.buf, opt, &data);
if (error)
return error;