[PATCH 04/10] cat-file: teach --batch to stream blob objects

[Jeff King]

The regular "git cat-file -p" and "git cat-file blob" code
paths already learned to stream large blobs. Let's do the
same here.

Note that this means we look up the type and size before
making a decision of whether to load the object into memory
or stream (just like the "-p" code path does). That can lead
to extra work, but it should be dwarfed by the cost of
actually accessing the object itself. In my measurements,
there was a 1-2% slowdown when using "--batch" on a large
number of objects.

Signed-off-by: Jeff King <p...@peff.net>
---
 builtin/cat-file.c | 41 ++++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 13 deletions(-)

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 045cee7..70dd8c8 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -117,12 +117,36 @@ static int batch_one_object(const char *obj_name, int 
print_contents)
        return 0;
 }
 
+static void print_object_or_die(int fd, const unsigned char *sha1,
+                               enum object_type type, unsigned long size)
+{
+       if (type == OBJ_BLOB) {
+               if (stream_blob_to_fd(fd, sha1, NULL, 0) < 0)
+                       die("unable to stream %s to stdout", sha1_to_hex(sha1));
+       }
+       else {
+               enum object_type rtype;
+               unsigned long rsize;
+               void *contents;
+
+               contents = read_sha1_file(sha1, &rtype, &rsize);
+               if (!contents)
+                       die("object %s disappeared", sha1_to_hex(sha1));
+               if (rtype != type)
+                       die("object %s changed type!?", sha1_to_hex(sha1));
+               if (rsize != size)
+                       die("object %s change size!?", sha1_to_hex(sha1));
+
+               write_or_die(fd, contents, size);
+               free(contents);
+       }
+}
+
 static int batch_one_object(const char *obj_name, int print_contents)
 {
        unsigned char sha1[20];
        enum object_type type = 0;
        unsigned long size;
-       void *contents = NULL;
 
        if (!obj_name)
           return 1;
@@ -133,16 +157,10 @@ static int batch_one_object(const char *obj_name, int 
print_contents)
                return 0;
        }
 
-       if (print_contents == BATCH)
-               contents = read_sha1_file(sha1, &type, &size);
-       else
-               type = sha1_object_info(sha1, &size);
-
+       type = sha1_object_info(sha1, &size);
        if (type <= 0) {
                printf("%s missing\n", obj_name);
                fflush(stdout);
-               if (print_contents == BATCH)
-                       free(contents);
                return 0;
        }
 
@@ -150,12 +168,9 @@ static int batch_one_object(const char *obj_name, int 
print_contents)
        fflush(stdout);
 
        if (print_contents == BATCH) {
-               write_or_die(1, contents, size);
-               printf("\n");
-               fflush(stdout);
-               free(contents);
+               print_object_or_die(1, sha1, type, size);
+               write_or_die(1, "\n", 1);
        }
-
        return 0;
 }
 
-- 
1.8.3.rc3.24.gec82cb9

--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html