aboutsummaryrefslogtreecommitdiffstats
path: root/builtin/unpack-objects.c
diff options
context:
space:
mode:
Diffstat (limited to 'builtin/unpack-objects.c')
-rw-r--r--builtin/unpack-objects.c106
1 files changed, 94 insertions, 12 deletions
diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 56d05e2725..43789b8ef2 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -97,15 +97,27 @@ static void use(int bytes)
display_throughput(progress, consumed_bytes);
}
+/*
+ * Decompress zstream from the standard input into a newly
+ * allocated buffer of specified size and return the buffer.
+ * The caller is responsible to free the returned buffer.
+ *
+ * But for dry_run mode, "get_data()" is only used to check the
+ * integrity of data, and the returned buffer is not used at all.
+ * Therefore, in dry_run mode, "get_data()" will release the small
+ * allocated buffer which is reused to hold temporary zstream output
+ * and return NULL instead of returning garbage data.
+ */
static void *get_data(unsigned long size)
{
git_zstream stream;
- void *buf = xmallocz(size);
+ unsigned long bufsize = dry_run && size > 8192 ? 8192 : size;
+ void *buf = xmallocz(bufsize);
memset(&stream, 0, sizeof(stream));
stream.next_out = buf;
- stream.avail_out = size;
+ stream.avail_out = bufsize;
stream.next_in = fill(1);
stream.avail_in = len;
git_inflate_init(&stream);
@@ -125,8 +137,17 @@ static void *get_data(unsigned long size)
}
stream.next_in = fill(1);
stream.avail_in = len;
+ if (dry_run) {
+ /* reuse the buffer in dry_run mode */
+ stream.next_out = buf;
+ stream.avail_out = bufsize > size - stream.total_out ?
+ size - stream.total_out :
+ bufsize;
+ }
}
git_inflate_end(&stream);
+ if (dry_run)
+ FREE_AND_NULL(buf);
return buf;
}
@@ -326,10 +347,70 @@ static void unpack_non_delta_entry(enum object_type type, unsigned long size,
{
void *buf = get_data(size);
- if (!dry_run && buf)
+ if (buf)
write_object(nr, type, buf, size);
- else
- free(buf);
+}
+
+struct input_zstream_data {
+ git_zstream *zstream;
+ unsigned char buf[8192];
+ int status;
+};
+
+static const void *feed_input_zstream(struct input_stream *in_stream,
+ unsigned long *readlen)
+{
+ struct input_zstream_data *data = in_stream->data;
+ git_zstream *zstream = data->zstream;
+ void *in = fill(1);
+
+ if (in_stream->is_finished) {
+ *readlen = 0;
+ return NULL;
+ }
+
+ zstream->next_out = data->buf;
+ zstream->avail_out = sizeof(data->buf);
+ zstream->next_in = in;
+ zstream->avail_in = len;
+
+ data->status = git_inflate(zstream, 0);
+
+ in_stream->is_finished = data->status != Z_OK;
+ use(len - zstream->avail_in);
+ *readlen = sizeof(data->buf) - zstream->avail_out;
+
+ return data->buf;
+}
+
+static void stream_blob(unsigned long size, unsigned nr)
+{
+ git_zstream zstream = { 0 };
+ struct input_zstream_data data = { 0 };
+ struct input_stream in_stream = {
+ .read = feed_input_zstream,
+ .data = &data,
+ };
+ struct obj_info *info = &obj_list[nr];
+
+ data.zstream = &zstream;
+ git_inflate_init(&zstream);
+
+ if (stream_loose_object(&in_stream, size, &info->oid))
+ die(_("failed to write object in stream"));
+
+ if (data.status != Z_STREAM_END)
+ die(_("inflate returned (%d)"), data.status);
+ git_inflate_end(&zstream);
+
+ if (strict) {
+ struct blob *blob = lookup_blob(the_repository, &info->oid);
+
+ if (!blob)
+ die(_("invalid blob object from stream"));
+ blob->object.flags |= FLAG_WRITTEN;
+ }
+ info->obj = NULL;
}
static int resolve_against_held(unsigned nr, const struct object_id *base,
@@ -359,10 +440,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
oidread(&base_oid, fill(the_hash_algo->rawsz));
use(the_hash_algo->rawsz);
delta_data = get_data(delta_size);
- if (dry_run || !delta_data) {
- free(delta_data);
+ if (!delta_data)
return;
- }
if (has_object_file(&base_oid))
; /* Ok we have this one */
else if (resolve_against_held(nr, &base_oid,
@@ -398,10 +477,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
die("offset value out of bound for delta base object");
delta_data = get_data(delta_size);
- if (dry_run || !delta_data) {
- free(delta_data);
+ if (!delta_data)
return;
- }
lo = 0;
hi = nr;
while (lo < hi) {
@@ -468,9 +545,14 @@ static void unpack_one(unsigned nr)
}
switch (type) {
+ case OBJ_BLOB:
+ if (!dry_run && size > big_file_threshold) {
+ stream_blob(size, nr);
+ return;
+ }
+ /* fallthrough */
case OBJ_COMMIT:
case OBJ_TREE:
- case OBJ_BLOB:
case OBJ_TAG:
unpack_non_delta_entry(type, size, nr);
return;