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

[PATCH v7 1/4] sha1_file.c: support reading from a loose object of unknown type

From
Karthik Nayak <karthik.188@gmail.com>
Date
Apr 4, 2015, 05:42 UTC
Message-ID
<1428126162-18987-1-git-send-email-karthik.188@gmail.com>
In-Reply-To
<551F7984.5070902@gmail.com>

Update sha1_loose_object_info() to optionally allow it to read from a loose object file of unknown/bogus type; as the function usually returns the type of the object it read in the form of enum for known types, add an optional "typename" field to receive the name of the type in textual form and a flag to indicate the reading of a loose object file of unknown/bogus type.

Add parse_sha1_header_extended() which acts as a wrapper around parse_sha1_header() allowing more information to be obtained.

Add unpack_sha1_header_to_strbuf() to unpack sha1 headers of unknown/corrupt objects which have a unknown sha1 header size to a strbuf structure. This was written by Junio C Hamano but tested by me.

Helped-by: Junio C Hamano <gitster@pobox.com>
Helped-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
---
 cache.h     |   2 ++
 sha1_file.c | 111 ++++++++++++++++++++++++++++++++++++++++++++++++------------
 2 files changed, 91 insertions(+), 22 deletions(-)
diff --git a/cache.h b/cache.h
index c47323e..ea6faf0 100644
--- a/cache.h
+++ b/cache.h
@@ -881,6 +881,7 @@ extern int is_ntfs_dotgit(const char *name);
 
 /* object replacement */
 #define LOOKUP_REPLACE_OBJECT 1
+#define LOOKUP_LITERALLY 2
 extern void *read_sha1_file_extended(const unsigned char *sha1, enum object_type *type, unsigned long *size, unsigned flag);
 static inline void *read_sha1_file(const unsigned char *sha1, enum object_type *type, unsigned long *size)
 {
@@ -1349,6 +1350,7 @@ struct object_info {
 	unsigned long *sizep;
 	unsigned long *disk_sizep;
 	unsigned char *delta_base_sha1;
+	struct strbuf *typename;
 
 	/* Response */
 	enum {
diff --git a/sha1_file.c b/sha1_file.c
index 980ce6b..5a1b904 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1564,6 +1564,34 @@ int unpack_sha1_header(git_zstream *stream, unsigned char *map, unsigned long ma
 	return git_inflate(stream, 0);
 }
 
+static int unpack_sha1_header_to_strbuf(git_zstream *stream, unsigned char *map,
+					unsigned long mapsize,
+					struct strbuf *header)
+{
+	unsigned char buffer[32], *cp;
+	unsigned long bufsiz = sizeof(buffer);
+	int status;
+
+	status = unpack_sha1_header(stream, map, mapsize, buffer, bufsiz);
+
+	if (status) {
+		strbuf_add(header, buffer, stream->next_out - buffer);
+		return status;
+	}
+
+	do {
+		status = git_inflate(stream, 0);
+		strbuf_add(header, buffer, stream->next_out - buffer);
+		for (cp = buffer; cp < stream->next_out; cp++)
+			if (!*cp)
+				/* Found the NUL at the end of the header */
+				return 0;
+		stream->next_out = buffer;
+		stream->avail_out = bufsiz;
+	} while (status != Z_STREAM_END);
+	return -1;
+}
+
 static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
 {
 	int bytes = strlen(buffer) + 1;
@@ -1614,27 +1642,24 @@ static void *unpack_sha1_rest(git_zstream *stream, void *buffer, unsigned long s
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-int parse_sha1_header(const char *hdr, unsigned long *sizep)
+int parse_sha1_header_extended(const char *hdr, struct object_info *oi,
+			       unsigned int flags)
 {
-	char type[10];
-	int i;
+	struct strbuf typename = STRBUF_INIT;
 	unsigned long size;
+	int type;
 
 	/*
 	 * The type can be at most ten bytes (including the
 	 * terminating '\0' that we add), and is followed by
 	 * a space.
 	 */
-	i = 0;
 	for (;;) {
 		char c = *hdr++;
 		if (c == ' ')
 			break;
-		type[i++] = c;
-		if (i >= sizeof(type))
-			return -1;
+		strbuf_addch(&typename, c);
 	}
-	type[i] = 0;
 
 	/*
 	 * The length must follow immediately, and be in canonical
@@ -1652,12 +1677,39 @@ int parse_sha1_header(const char *hdr, unsigned long *sizep)
 			size = size * 10 + c;
 		}
 	}
-	*sizep = size;
 
+	type = type_from_string_gently(typename.buf, typename.len, 1);
+	if (oi->sizep)
+		*oi->sizep = size;
+	if (oi->typename)
+		strbuf_addbuf(oi->typename, &typename);
+	strbuf_release(&typename);
+
+	/*
+	 * Set type to 0 if its an unknown object and
+	 * we're obtaining the type using '--literally'
+	 * option.
+	 */
+	if ((flags & LOOKUP_LITERALLY) && (type == -1))
+		type = 0;
+	else if (type == -1)
+		die("invalid object type");
+	if (oi->typep)
+		*oi->typep = type;
 	/*
 	 * The length must be followed by a zero byte
 	 */
-	return *hdr ? -1 : type_from_string(type);
+	return *hdr ? -1 : type;
+}
+
+int parse_sha1_header(const char *hdr, unsigned long *sizep)
+{
+	struct object_info oi;
+
+	oi.sizep = sizep;
+	oi.typename = NULL;
+	oi.typep = NULL;
+	return parse_sha1_header_extended(hdr, &oi, LOOKUP_REPLACE_OBJECT);
 }
 
 static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
@@ -2522,13 +2574,15 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1,
 }
 
 static int sha1_loose_object_info(const unsigned char *sha1,
-				  struct object_info *oi)
+				  struct object_info *oi,
+				  int flags)
 {
-	int status;
-	unsigned long mapsize, size;
+	int status = 0;
+	unsigned long mapsize;
 	void *map;
 	git_zstream stream;
 	char hdr[32];
+	struct strbuf hdrbuf = STRBUF_INIT;
 
 	if (oi->delta_base_sha1)
 		hashclr(oi->delta_base_sha1);
@@ -2555,17 +2609,26 @@ static int sha1_loose_object_info(const unsigned char *sha1,
 		return -1;
 	if (oi->disk_sizep)
 		*oi->disk_sizep = mapsize;
-	if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
-		status = error("unable to unpack %s header",
-			       sha1_to_hex(sha1));
-	else if ((status = parse_sha1_header(hdr, &size)) < 0)
-		status = error("unable to parse %s header", sha1_to_hex(sha1));
-	else if (oi->sizep)
-		*oi->sizep = size;
+	if ((flags & LOOKUP_LITERALLY)) {
+		if (unpack_sha1_header_to_strbuf(&stream, map, mapsize, &hdrbuf) < 0)
+			status = error("unable to unpack %s header with --literally",
+				       sha1_to_hex(sha1));
+		else if ((status = parse_sha1_header_extended(hdrbuf.buf, oi, flags)) < 0)
+			status = error("unable to parse %s header with --literally",
+				       sha1_to_hex(sha1));
+	} else {
+		if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
+			status = error("unable to unpack %s header",
+				       sha1_to_hex(sha1));
+		else if ((status = parse_sha1_header_extended(hdr, oi, flags)) < 0)
+			status = error("unable to parse %s header", sha1_to_hex(sha1));
+	}
 	git_inflate_end(&stream);
 	munmap(map, mapsize);
-	if (oi->typep)
+	if (status && oi->typep)
 		*oi->typep = status;
+	if (hdrbuf.buf)
+		strbuf_release(&hdrbuf);
 	return 0;
 }
 
@@ -2586,13 +2649,15 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 			*(oi->disk_sizep) = 0;
 		if (oi->delta_base_sha1)
 			hashclr(oi->delta_base_sha1);
+		if (oi->typename)
+			strbuf_addstr(oi->typename, typename(co->type));
 		oi->whence = OI_CACHED;
 		return 0;
 	}
 
 	if (!find_pack_entry(real, &e)) {
 		/* Most likely it's a loose object. */
-		if (!sha1_loose_object_info(real, oi)) {
+		if (!sha1_loose_object_info(real, oi, flags)) {
 			oi->whence = OI_LOOSE;
 			return 0;
 		}
@@ -2616,6 +2681,8 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
 		oi->u.packed.is_delta = (rtype == OBJ_REF_DELTA ||
 					 rtype == OBJ_OFS_DELTA);
 	}
+	if (oi->typename)
+		strbuf_addstr(oi->typename, typename(*oi->typep));
 
 	return 0;
 }

-- 
2.4.0.rc1.249.g9f2ee54
Previous: karthik nayakNext: Junio C Hamano
Message 2 of 19 in “cat-file: teach cat-file a '--literally' option”
  1. 0/4 cat-file: teach cat-file a '--literally' optionkarthik nayak, Apr 4, 2015
  2. 1/4 sha1_file.c: support reading from a loose object of unknown typeKarthik Nayak, Apr 4, 2015
  3. Junio C HamanoApr 4, 2015
  4. karthik nayakApr 4, 2015
  5. Junio C HamanoApr 5, 2015
  6. karthik nayakApr 5, 2015
  7. Junio C HamanoApr 5, 2015
  8. karthik nayakApr 7, 2015
  9. 1/4 sha1_file.c: support reading from a loose object of unknown typeKarthik Nayak, Apr 5, 2015
  10. Eric SunshineApr 7, 2015
  11. 2/4 cat-file: teach cat-file a '--literally' optionKarthik Nayak, Apr 4, 2015
  12. Eric SunshineApr 7, 2015
  13. 3/4 cat-file: add documentation for '--literally' option.Karthik Nayak, Apr 4, 2015
  14. Eric SunshineApr 7, 2015
  15. 4/4 t1006: add tests for git cat-file --literallyKarthik Nayak, Apr 4, 2015
  16. Eric SunshineApr 7, 2015
  17. karthik nayakApr 8, 2015
  18. Eric SunshineApr 8, 2015
  19. Karthik NayakApr 9, 2015

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.