Re: [RFC] pack-objects: compression level for non-blobs

From

Jeff King <peff@peff.net>

Date

Dec 29, 2012, 09:05 UTC

Message-ID

<20121229090558.GA31291@sigill.intra.peff.net>

In-Reply-To

<20121229052747.GA14928@sigill.intra.peff.net>

On Sat, Dec 29, 2012 at 12:27:47AM -0500, Jeff King wrote:

> > I think I tried the partial decompression for commit header and it did
> > not help much (or I misremember it, not so sure).
> 
> I'll see if I can dig up the reference, as it was something I was going
> to look at next.

diff --git a/commit.c b/commit.c
index e8eb0ae..efd6c06 100644
--- a/commit.c
+++ b/commit.c
@@ -8,6 +8,7 @@
 #include "notes.h"
 #include "gpg-interface.h"
 #include "mergesort.h"
+#include "streaming.h"
 
 static struct commit_extra_header *read_commit_extra_header_lines(const char *buf, size_t len, const char **);
 
@@ -306,6 +307,39 @@ int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long s
 	return 0;
 }
 
+static void *read_commit_header(const unsigned char *sha1,
+				enum object_type *type,
+				unsigned long *size)
+{
+	static const int chunk_size = 256;
+	struct strbuf buf = STRBUF_INIT;
+	struct git_istream *st;
+
+	st = open_istream(sha1, type, size, NULL);
+	if (!st)
+		return NULL;
+	while (1) {
+		size_t start = buf.len;
+		ssize_t readlen;
+
+		strbuf_grow(&buf, chunk_size);
+		readlen = read_istream(st, buf.buf + start, chunk_size);
+		buf.buf[start + readlen + 1] = '\0';
+		buf.len += readlen;
+
+		if (readlen < 0) {
+			close_istream(st);
+			strbuf_release(&buf);
+			return NULL;
+		}
+		if (!readlen || strstr(buf.buf + start, "\n\n"))
+			break;
+	}
+
+	close_istream(st);
+	return strbuf_detach(&buf, size);
+}
+
 int parse_commit(struct commit *item)
 {
 	enum object_type type;
@@ -317,7 +351,11 @@ int parse_commit(struct commit *item)
 		return -1;
 	if (item->object.parsed)
 		return 0;
-	buffer = read_sha1_file(item->object.sha1, &type, &size);
+
+	if (!save_commit_buffer)
+		buffer = read_commit_header(item->object.sha1, &type, &size);
+	else
+		buffer = read_sha1_file(item->object.sha1, &type, &size);
 	if (!buffer)
 		return error("Could not read %s",
 			     sha1_to_hex(item->object.sha1));