git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v3 2/6] varint-in-pack: refactor varint encoding/decoding

From
Junio C Hamano <gitster@pobox.com>
Date
Dec 2, 2011, 00:40 UTC
Message-ID
<1322786449-25753-3-git-send-email-gitster@pobox.com>
In-Reply-To
<1322786449-25753-1-git-send-email-gitster@pobox.com>

Refactor encode/decode_in_pack_varint() functions from OFS_DELTA codepaths to read and write variable-length integers in the pack stream.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 builtin/pack-objects.c |   28 +++++++++++++---------------
 pack-write.c           |   27 +++++++++++++++++++++++++++
 pack.h                 |    2 ++
 sha1_file.c            |   18 ++++++------------
 4 files changed, 48 insertions(+), 27 deletions(-)
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index dde913e..72206a9 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -210,7 +210,7 @@ static unsigned long write_object(struct sha1file *f,
 {
 	unsigned long size, limit, datalen;
 	void *buf;
-	unsigned char header[10], dheader[10];
+	unsigned char header[10];
 	unsigned hdrlen;
 	enum object_type type;
 	int usable_delta, to_reuse;
@@ -304,17 +304,16 @@ static unsigned long write_object(struct sha1file *f,
 			 * base from this object's position in the pack.
 			 */
 			off_t ofs = entry->idx.offset - entry->delta->idx.offset;
-			unsigned pos = sizeof(dheader) - 1;
-			dheader[pos] = ofs & 127;
-			while (ofs >>= 7)
-				dheader[--pos] = 128 | (--ofs & 127);
-			if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+			unsigned char dheader[10];
+			unsigned pos = encode_in_pack_varint(ofs, dheader);
+
+			if (limit && hdrlen + pos + datalen + 20 >= limit) {
 				free(buf);
 				return 0;
 			}
 			sha1write(f, header, hdrlen);
-			sha1write(f, dheader + pos, sizeof(dheader) - pos);
-			hdrlen += sizeof(dheader) - pos;
+			sha1write(f, dheader, pos);
+			hdrlen += pos;
 		} else if (type == OBJ_REF_DELTA) {
 			/*
 			 * Deltas with a base reference contain
@@ -369,17 +368,16 @@ static unsigned long write_object(struct sha1file *f,
 
 		if (type == OBJ_OFS_DELTA) {
 			off_t ofs = entry->idx.offset - entry->delta->idx.offset;
-			unsigned pos = sizeof(dheader) - 1;
-			dheader[pos] = ofs & 127;
-			while (ofs >>= 7)
-				dheader[--pos] = 128 | (--ofs & 127);
-			if (limit && hdrlen + sizeof(dheader) - pos + datalen + 20 >= limit) {
+			unsigned char dheader[10];
+			unsigned pos = encode_in_pack_varint(ofs, dheader);
+
+			if (limit && hdrlen + pos + datalen + 20 >= limit) {
 				unuse_pack(&w_curs);
 				return 0;
 			}
 			sha1write(f, header, hdrlen);
-			sha1write(f, dheader + pos, sizeof(dheader) - pos);
-			hdrlen += sizeof(dheader) - pos;
+			sha1write(f, dheader, pos);
+			hdrlen += pos;
 			reused_delta++;
 		} else if (type == OBJ_REF_DELTA) {
 			if (limit && hdrlen + 20 + datalen + 20 >= limit) {
diff --git a/pack-write.c b/pack-write.c
index cadc3e1..5702cec 100644
--- a/pack-write.c
+++ b/pack-write.c
@@ -302,6 +302,33 @@ char *index_pack_lockfile(int ip_out)
 	return NULL;
 }
 
+uintmax_t decode_in_pack_varint(const unsigned char **bufp)
+{
+	const unsigned char *buf = *bufp;
+	unsigned char c = *buf++;
+	uintmax_t val = c & 127;
+	while (c & 128) {
+		val += 1;
+		if (!val || MSB(val, 7))
+			return 0; /* overflow */
+		c = *buf++;
+		val = (val << 7) + (c & 127);
+	}
+	*bufp = buf;
+	return val;
+}
+
+int encode_in_pack_varint(uintmax_t value, unsigned char *buf)
+{
+	unsigned char varint[16];
+	unsigned pos = sizeof(varint) - 1;
+	varint[pos] = value & 127;
+	while (value >>= 7)
+		varint[--pos] = 128 | (--value & 127);
+	memcpy(buf, varint + pos, sizeof(varint) - pos);
+	return sizeof(varint) - pos;
+}
+
 /*
  * The per-object header is a pretty dense thing, which is
  *  - first byte: low four bits are "size", then three bits of "type",
diff --git a/pack.h b/pack.h
index cfb0f69..d7dc6ca 100644
--- a/pack.h
+++ b/pack.h
@@ -79,6 +79,8 @@ extern off_t write_pack_header(struct sha1file *f, uint32_t);
 extern void fixup_pack_header_footer(int, unsigned char *, const char *, uint32_t, unsigned char *, off_t);
 extern char *index_pack_lockfile(int fd);
 extern int encode_in_pack_object_header(enum object_type, uintmax_t, unsigned char *);
+extern int encode_in_pack_varint(uintmax_t, unsigned char *);
+extern uintmax_t decode_in_pack_varint(const unsigned char **);
 
 #define PH_ERROR_EOF		(-1)
 #define PH_ERROR_PACK_SIGNATURE	(-2)
diff --git a/sha1_file.c b/sha1_file.c
index c96e366..f066c2b 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1484,20 +1484,14 @@ static off_t get_delta_base(struct packed_git *p,
 	 * is stupid, as then a REF_DELTA would be smaller to store.
 	 */
 	if (type == OBJ_OFS_DELTA) {
-		unsigned used = 0;
-		unsigned char c = base_info[used++];
-		base_offset = c & 127;
-		while (c & 128) {
-			base_offset += 1;
-			if (!base_offset || MSB(base_offset, 7))
-				return 0;  /* overflow */
-			c = base_info[used++];
-			base_offset = (base_offset << 7) + (c & 127);
-		}
-		base_offset = delta_obj_offset - base_offset;
+		const unsigned char *buf = base_info;
+		uintmax_t ofs = decode_in_pack_varint(&buf);
+		if (!ofs && buf == base_info)
+			return 0; /* overflow */
+		base_offset = delta_obj_offset - ofs;
 		if (base_offset <= 0 || base_offset >= delta_obj_offset)
 			return 0;  /* out of bound */
-		*curpos += used;
+		*curpos += buf - base_info;
 	} else if (type == OBJ_REF_DELTA) {
 		/* The base entry _must_ be in the same pack */
 		base_offset = find_pack_entry_one(base_info, p);

-- 
1.7.8.rc4.177.g4d64
Previous: Junio C HamanoNext: Junio C Hamano
Message 11 of 15 in “Bulk Check-in”
  1. 0/5 Bulk Check-inJunio C Hamano, Dec 1, 2011
  2. 1/5 write_pack_header(): a helper functionJunio C Hamano, Dec 1, 2011
  3. 2/5 create_tmp_packfile(): a helper functionJunio C Hamano, Dec 1, 2011
  4. 3/5 finish_tmp_packfile(): a helper functionJunio C Hamano, Dec 1, 2011
  5. 4/5 csum-file: introduce sha1file_checkpointJunio C Hamano, Dec 1, 2011
  6. 5/5 bulk-checkin: replace fast-import based implementationJunio C Hamano, Dec 1, 2011
  7. Nguyen Thai Ngoc DuyDec 1, 2011
  8. Junio C HamanoDec 1, 2011
  9. 0/6 Bulk check-inJunio C Hamano, Dec 2, 2011
  10. 1/6 bulk-checkin: replace fast-import based implementationJunio C Hamano, Dec 2, 2011
  11. 2/6 varint-in-pack: refactor varint encoding/decodingJunio C Hamano, Dec 2, 2011
  12. 3/6 new representation types in the packstreamJunio C Hamano, Dec 2, 2011
  13. 4/6 bulk-checkin: allow the same data to be multiply hashedJunio C Hamano, Dec 2, 2011
  14. 5/6 bulk-checkin: support chunked-object encodingJunio C Hamano, Dec 2, 2011
  15. 6/6 chunked-object: fallback checkout codepathsJunio C Hamano, Dec 2, 2011

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.