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

[PATCH v2 2/4] sha1_file: move delta base cache code up

From
JTJonathan Tan <jonathantanmy@google.com>
Date
Jun 13, 2017, 21:05 UTC
Message-ID
<36b7984ee85d22800b974a04952c50eef043fa67.1497387714.git.jonathantanmy@google.com>
In-Reply-To
<cover.1497387713.git.jonathantanmy@google.com>

In a subsequent patch, packed_object_info() will be modified to use the delta base cache, so move the relevant code to before packed_object_info().

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 sha1_file.c | 226 +++++++++++++++++++++++++++++++-----------------------------
 1 file changed, 116 insertions(+), 110 deletions(-)
diff --git a/sha1_file.c b/sha1_file.c
index a52b27541..a158907d1 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -2239,116 +2239,6 @@ static enum object_type packed_to_object_type(struct packed_git *p,
 	goto out;
 }
 
-int packed_object_info(struct packed_git *p, off_t obj_offset,
-		       struct object_info *oi)
-{
-	struct pack_window *w_curs = NULL;
-	unsigned long size;
-	off_t curpos = obj_offset;
-	enum object_type type;
-
-	/*
-	 * We always get the representation type, but only convert it to
-	 * a "real" type later if the caller is interested.
-	 */
-	type = unpack_object_header(p, &w_curs, &curpos, &size);
-
-	if (oi->sizep) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			off_t tmp_pos = curpos;
-			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
-							   type, obj_offset);
-			if (!base_offset) {
-				type = OBJ_BAD;
-				goto out;
-			}
-			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
-			if (*oi->sizep == 0) {
-				type = OBJ_BAD;
-				goto out;
-			}
-		} else {
-			*oi->sizep = size;
-		}
-	}
-
-	if (oi->disk_sizep) {
-		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
-		*oi->disk_sizep = revidx[1].offset - obj_offset;
-	}
-
-	if (oi->typep || oi->typename) {
-		enum object_type ptot;
-		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
-					     curpos);
-		if (oi->typep)
-			*oi->typep = ptot;
-		if (oi->typename) {
-			const char *tn = typename(ptot);
-			if (tn)
-				strbuf_addstr(oi->typename, tn);
-		}
-		if (ptot < 0) {
-			type = OBJ_BAD;
-			goto out;
-		}
-	}
-
-	if (oi->delta_base_sha1) {
-		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
-			const unsigned char *base;
-
-			base = get_delta_base_sha1(p, &w_curs, curpos,
-						   type, obj_offset);
-			if (!base) {
-				type = OBJ_BAD;
-				goto out;
-			}
-
-			hashcpy(oi->delta_base_sha1, base);
-		} else
-			hashclr(oi->delta_base_sha1);
-	}
-
-out:
-	unuse_pack(&w_curs);
-	return type;
-}
-
-static void *unpack_compressed_entry(struct packed_git *p,
-				    struct pack_window **w_curs,
-				    off_t curpos,
-				    unsigned long size)
-{
-	int st;
-	git_zstream stream;
-	unsigned char *buffer, *in;
-
-	buffer = xmallocz_gently(size);
-	if (!buffer)
-		return NULL;
-	memset(&stream, 0, sizeof(stream));
-	stream.next_out = buffer;
-	stream.avail_out = size + 1;
-
-	git_inflate_init(&stream);
-	do {
-		in = use_pack(p, w_curs, curpos, &stream.avail_in);
-		stream.next_in = in;
-		st = git_inflate(&stream, Z_FINISH);
-		if (!stream.avail_out)
-			break; /* the payload is larger than it should be */
-		curpos += stream.next_in - in;
-	} while (st == Z_OK || st == Z_BUF_ERROR);
-	git_inflate_end(&stream);
-	if ((st != Z_STREAM_END) || stream.total_out != size) {
-		free(buffer);
-		return NULL;
-	}
-
-	return buffer;
-}
-
 static struct hashmap delta_base_cache;
 static size_t delta_base_cached;
 
@@ -2486,6 +2376,122 @@ static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
 	hashmap_add(&delta_base_cache, ent);
 }
 
+int packed_object_info(struct packed_git *p, off_t obj_offset,
+		       struct object_info *oi)
+{
+	struct pack_window *w_curs = NULL;
+	unsigned long size;
+	off_t curpos = obj_offset;
+	enum object_type type;
+
+	/*
+	 * We always get the representation type, but only convert it to
+	 * a "real" type later if the caller is interested.
+	 */
+	type = unpack_object_header(p, &w_curs, &curpos, &size);
+
+	if (oi->sizep) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			off_t tmp_pos = curpos;
+			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
+							   type, obj_offset);
+			if (!base_offset) {
+				type = OBJ_BAD;
+				goto out;
+			}
+			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
+			if (*oi->sizep == 0) {
+				type = OBJ_BAD;
+				goto out;
+			}
+		} else {
+			*oi->sizep = size;
+		}
+	}
+
+	if (oi->disk_sizep) {
+		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
+		*oi->disk_sizep = revidx[1].offset - obj_offset;
+	}
+
+	if (oi->typep || oi->typename) {
+		enum object_type ptot;
+		ptot = packed_to_object_type(p, obj_offset, type, &w_curs,
+					     curpos);
+		if (oi->typep)
+			*oi->typep = ptot;
+		if (oi->typename) {
+			const char *tn = typename(ptot);
+			if (tn)
+				strbuf_addstr(oi->typename, tn);
+		}
+		if (ptot < 0) {
+			type = OBJ_BAD;
+			goto out;
+		}
+	}
+
+	if (oi->delta_base_sha1) {
+		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
+			const unsigned char *base;
+
+			base = get_delta_base_sha1(p, &w_curs, curpos,
+						   type, obj_offset);
+			if (!base) {
+				type = OBJ_BAD;
+				goto out;
+			}
+
+			hashcpy(oi->delta_base_sha1, base);
+		} else
+			hashclr(oi->delta_base_sha1);
+	}
+
+	oi->whence = OI_PACKED;
+	oi->u.packed.offset = obj_offset;
+	oi->u.packed.pack = p;
+	oi->u.packed.is_delta = (type == OBJ_REF_DELTA ||
+				 type == OBJ_OFS_DELTA);
+
+out:
+	unuse_pack(&w_curs);
+	return type;
+}
+
+static void *unpack_compressed_entry(struct packed_git *p,
+				    struct pack_window **w_curs,
+				    off_t curpos,
+				    unsigned long size)
+{
+	int st;
+	git_zstream stream;
+	unsigned char *buffer, *in;
+
+	buffer = xmallocz_gently(size);
+	if (!buffer)
+		return NULL;
+	memset(&stream, 0, sizeof(stream));
+	stream.next_out = buffer;
+	stream.avail_out = size + 1;
+
+	git_inflate_init(&stream);
+	do {
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
+		stream.next_in = in;
+		st = git_inflate(&stream, Z_FINISH);
+		if (!stream.avail_out)
+			break; /* the payload is larger than it should be */
+		curpos += stream.next_in - in;
+	} while (st == Z_OK || st == Z_BUF_ERROR);
+	git_inflate_end(&stream);
+	if ((st != Z_STREAM_END) || stream.total_out != size) {
+		free(buffer);
+		return NULL;
+	}
+
+	return buffer;
+}
+
 static void *read_object(const unsigned char *sha1, enum object_type *type,
 			 unsigned long *size);
 
-- 
2.13.1.518.g3df882009-goog
Previous: Jonathan TanNext: Junio C Hamano
Message 12 of 65 in “Improvements to sha1_file”
  1. 0/4 Improvements to sha1_fileJonathan Tan, Jun 9, 2017
  2. 1/4 sha1_file: teach packed_object_info about typenameJonathan Tan, Jun 9, 2017
  3. Junio C HamanoJun 12, 2017
  4. 2/4 sha1_file: extract type and size from object_infoJonathan Tan, Jun 9, 2017
  5. Jeff KingJun 10, 2017
  6. Jonathan TanJun 12, 2017
  7. Jeff KingJun 12, 2017
  8. 4/4 sha1_file, fsck: add missing blob supportJonathan Tan, Jun 9, 2017
  9. 3/4 sha1_file: consolidate storage-agnostic object fnsJonathan Tan, Jun 9, 2017
  10. 0/4 Improvements to sha1_fileJonathan Tan, Jun 13, 2017
  11. 1/4 sha1_file: teach packed_object_info about typenameJonathan Tan, Jun 13, 2017
  12. 2/4 sha1_file: move delta base cache code upJonathan Tan, Jun 13, 2017
  13. Junio C HamanoJun 15, 2017
  14. 3/4 sha1_file: consolidate storage-agnostic object fnsJonathan Tan, Jun 13, 2017
  15. Junio C HamanoJun 15, 2017
  16. Jonathan TanJun 15, 2017
  17. Jeff KingJun 17, 2017
  18. Junio C HamanoJun 19, 2017
  19. 4/4 sha1_file, fsck: add missing blob supportJonathan Tan, Jun 13, 2017
  20. Junio C HamanoJun 15, 2017
  21. Jonathan TanJun 15, 2017
  22. Junio C HamanoJun 15, 2017
  23. 0/8 Improvements to sha1_fileJonathan Tan, Jun 20, 2017
  24. 1/8 sha1_file: teach packed_object_info about typenameJonathan Tan, Jun 20, 2017
  25. 2/8 sha1_file: rename LOOKUP_UNKNOWN_OBJECTJonathan Tan, Jun 20, 2017
  26. Junio C HamanoJun 21, 2017
  27. Jonathan TanJun 21, 2017
  28. 3/8 sha1_file: rename LOOKUP_REPLACE_OBJECTJonathan Tan, Jun 20, 2017
  29. Junio C HamanoJun 21, 2017
  30. 4/8 sha1_file: move delta base cache code upJonathan Tan, Jun 20, 2017
  31. 5/8 sha1_file: refactor read_objectJonathan Tan, Jun 20, 2017
  32. Junio C HamanoJun 21, 2017
  33. 6/8 sha1_file: improve sha1_object_info_extendedJonathan Tan, Jun 20, 2017
  34. Jeff KingJun 24, 2017
  35. Jonathan TanJun 26, 2017
  36. Junio C HamanoJun 26, 2017
  37. Jonathan TanJun 26, 2017
  38. Junio C HamanoJun 26, 2017
  39. 8/8 sha1_file: refactor has_sha1_file_with_flagsJonathan Tan, Jun 20, 2017
  40. 7/8 sha1_file: do not access pack if unneededJonathan Tan, Jun 20, 2017
  41. Junio C HamanoJun 21, 2017
  42. Jeff KingJun 24, 2017
  43. Junio C HamanoJun 24, 2017
  44. Jeff KingJun 24, 2017
  45. Jonathan TanJun 26, 2017
  46. Junio C HamanoJun 21, 2017
  47. Jeff KingJun 24, 2017
  48. 0/8 Improvements to sha1_fileJonathan Tan, Jun 22, 2017
  49. 1/8 sha1_file: teach packed_object_info about typenameJonathan Tan, Jun 22, 2017
  50. 2/8 sha1_file: rename LOOKUP_UNKNOWN_OBJECTJonathan Tan, Jun 22, 2017
  51. 3/8 sha1_file: rename LOOKUP_REPLACE_OBJECTJonathan Tan, Jun 22, 2017
  52. 8/8 sha1_file: refactor has_sha1_file_with_flagsJonathan Tan, Jun 22, 2017
  53. Christian CouderJul 18, 2017
  54. Jonathan TanJul 18, 2017
  55. Johannes SchindelinJul 19, 2017
  56. sha1_file: use access(), not lstat(), if possibleJonathan Tan, Jul 19, 2017
  57. Junio C HamanoJul 20, 2017
  58. Johannes SchindelinJul 22, 2017
  59. Junio C HamanoJul 22, 2017
  60. Johannes SchindelinJul 25, 2017
  61. 6/8 sha1_file: improve sha1_object_info_extendedJonathan Tan, Jun 22, 2017
  62. 5/8 sha1_file: refactor read_objectJonathan Tan, Jun 22, 2017
  63. 4/8 sha1_file: move delta base cache code upJonathan Tan, Jun 22, 2017
  64. 7/8 sha1_file: do not access pack if unneededJonathan Tan, Jun 22, 2017
  65. Junio C HamanoJun 22, 2017

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.