[PATCH v6 0/4] cat-file: add a '--literally' option

[PATCH v6 0/4] cat-file: add a '--literally' option

[karthik nayak]

The changes made in this version are :

*  unpack_sha1_header_to_strbuf() now checks for Z_STREAM_END and also
the return is not changed to status (as per Junios suggestion) as this 
breaks the check done in sha1_loose_object_info() as the return is 
sometimes Z_BUF_ERROR (-5).

* In sha1_loose_object_info() if the status is set, then change the type 
to status. Also check for this in cat-file.c

* Add documentation and tests for the same.

Thanks for your suggestions.

[PATCH v6 1/4] sha1_file.c: support reading from a loose object of unknown type

[Karthik Nayak]

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 4d02efc..949ef4c 100644
--- a/cache.h
+++ b/cache.h
@@ -830,6 +830,7 @@ 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)
 {
@@ -1296,6 +1297,7 @@ 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 69a60ec..8b58b94 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)
@@ -2524,13 +2576,15 @@ 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);
@@ -2557,17 +2611,26 @@ 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;
 }
 
@@ -2588,13 +2651,15 @@ 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;
 		}
@@ -2618,6 +2683,8 @@ 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(rtype));
 
 	return 0;
 }
-- 
2.3.1.172.g04a1281

[PATCH v6 2/4] cat-file: teach cat-file a '--literally' option

[Karthik Nayak]

Currently 'git cat-file' throws an error while trying to
print the type or size of a broken/corrupt object which is
created using 'git hash-object --literally'. This is
because these objects are usually of unknown types.

Teach git cat-file a '--literally' option where it prints
the type or size of a broken/corrupt object without throwing
an error.

Modify '-t' and '-s' options to call sha1_object_info_extended()
directly to support the '--literally' option.

Helped-by: Junio C Hamano <gitster@pobox.com>
Helped-by: Eric Sunshine <sunshine@sunshineco
Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
---
 builtin/cat-file.c | 38 +++++++++++++++++++++++++++++---------
 1 file changed, 29 insertions(+), 9 deletions(-)

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index df99df4..91ceae0 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -9,13 +9,20 @@
 #include "userdiff.h"
 #include "streaming.h"
 
-static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
+static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
+			int literally)
 {
 	unsigned char sha1[20];
 	enum object_type type;
 	char *buf;
 	unsigned long size;
 	struct object_context obj_context;
+	struct object_info oi = {NULL};
+	struct strbuf sb = STRBUF_INIT;
+	unsigned flags = LOOKUP_REPLACE_OBJECT;
+
+	if (literally)
+		flags |= LOOKUP_LITERALLY;
 
 	if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
 		die("Not a valid object name %s", obj_name);
@@ -23,16 +30,24 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 	buf = NULL;
 	switch (opt) {
 	case 't':
-		type = sha1_object_info(sha1, NULL);
-		if (type > 0) {
-			printf("%s\n", typename(type));
+		oi.typep = &type;
+		oi.typename = &sb;
+		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
+			die("git cat-file: could not get object info");
+		if (type >= 0 && sb.len) {
+			printf("%s\n", sb.buf);
+			strbuf_release(&sb);
 			return 0;
 		}
 		break;
 
 	case 's':
-		type = sha1_object_info(sha1, &size);
-		if (type > 0) {
+		oi.typep = &type;
+		oi.typename = &sb;
+		oi.sizep = &size;
+		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
+			die("git cat-file: could not get object info");
+		if (type >= 0 && sb.len) {
 			printf("%lu\n", size);
 			return 0;
 		}
@@ -323,7 +338,7 @@ static int batch_objects(struct batch_options *opt)
 }
 
 static const char * const cat_file_usage[] = {
-	N_("git cat-file (-t | -s | -e | -p | <type> | --textconv) <object>"),
+	N_("git cat-file (-t [--literally]|-s [--literally]|-e|-p|<type>|--textconv) <object>"),
 	N_("git cat-file (--batch | --batch-check) < <list-of-objects>"),
 	NULL
 };
@@ -359,6 +374,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	int opt = 0;
 	const char *exp_type = NULL, *obj_name = NULL;
 	struct batch_options batch = {0};
+	int literally = 0;
 
 	const struct option options[] = {
 		OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
@@ -369,6 +385,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 		OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
 		OPT_SET_INT(0, "textconv", &opt,
 			    N_("for blob objects, run textconv on object's content"), 'c'),
+		OPT_BOOL( 0, "literally", &literally,
+			  N_("get information about corrupt objects for debugging Git")),
 		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
 			N_("show info and content of objects fed from the standard input"),
 			PARSE_OPT_OPTARG, batch_option_callback },
@@ -380,7 +398,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 
 	git_config(git_cat_file_config, NULL);
 
-	if (argc != 3 && argc != 2)
+	if (argc < 2 || argc > 4)
 		usage_with_options(cat_file_usage, options);
 
 	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
@@ -405,5 +423,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
 	if (batch.enabled)
 		return batch_objects(&batch);
 
-	return cat_one_file(opt, exp_type, obj_name);
+	if (literally && opt != 't' && opt != 's')
+		die("git cat-file --literally: use with -s or -t");
+	return cat_one_file(opt, exp_type, obj_name, literally);
 }
-- 
2.3.1.172.g04a1281

[PATCH v6 3/4] cat-file: add documentation for '--literally' option.

[Karthik Nayak]

Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
---
 Documentation/git-cat-file.txt | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index f6a16f4..8bac7bd 100644
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -9,7 +9,7 @@ git-cat-file - Provide content or type and size information for repository objec
 SYNOPSIS
 --------
 [verse]
-'git cat-file' (-t | -s | -e | -p | <type> | --textconv ) <object>
+'git cat-file' (-t [--literally]| -s [--literally]| -e | -p | <type> | --textconv ) <object>
 'git cat-file' (--batch | --batch-check) < <list-of-objects>
 
 DESCRIPTION
@@ -69,6 +69,10 @@ OPTIONS
 	not be combined with any other options or arguments.  See the
 	section `BATCH OUTPUT` below for details.
 
+--literally::
+	Print information of broken/corrupt objects of unknown type without
+	throwing an error. To be used combined with '-s' or '-t' option.
+
 OUTPUT
 ------
 If '-t' is specified, one of the <type>.
-- 
2.3.1.172.g04a1281

[PATCH v6 4/4] t1006: add tests for git cat-file --literally

[Karthik Nayak]

Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
---
 t/t1006-cat-file.sh | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index a72e700..3015062 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -47,6 +47,18 @@ $content"
 	test_cmp expect actual
     '
 
+    test_expect_success "Type of $type is correct using --literally" '
+	echo $type >expect &&
+	git cat-file -t --literally $sha1 >actual &&
+	test_cmp expect actual
+    '
+
+    test_expect_success "Size of $type is correct using --literally" '
+	echo $size >expect &&
+	git cat-file -s --literally $sha1 >actual &&
+	test_cmp expect actual
+    '
+
     test -z "$content" ||
     test_expect_success "Content of $type is correct" '
 	maybe_remove_timestamp "$content" $no_ts >expect &&
@@ -296,4 +308,19 @@ test_expect_success '%(deltabase) reports packed delta bases' '
 	}
 '
 
+bogus_type="bogus"
+bogus_sha1=$(git hash-object -t $bogus_type --literally -w --stdin </dev/null)
+
+test_expect_success "Type of broken object is correct" '
+	echo $bogus_type >expect &&
+	git cat-file -t --literally $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success "Size of broken object is correct" '
+	echo "0" >expect &&
+	git cat-file -s --literally $bogus_sha1 >actual &&
+	test_cmp expect actual
+'
+
 test_done
-- 
2.3.1.172.g04a1281

Re: [PATCH v6 2/4] cat-file: teach cat-file a '--literally' option

[Junio C Hamano]

Karthik Nayak <karthik.188@gmail.com> writes:

> Currently 'git cat-file' throws an error while trying to
> print the type or size of a broken/corrupt object which is
> created using 'git hash-object --literally'. This is
> because these objects are usually of unknown types.
>
> Teach git cat-file a '--literally' option where it prints
> the type or size of a broken/corrupt object without throwing
> an error.
>
> Modify '-t' and '-s' options to call sha1_object_info_extended()
> directly to support the '--literally' option.
>
> Helped-by: Junio C Hamano <gitster@pobox.com>
> Helped-by: Eric Sunshine <sunshine@sunshineco

s/$/.com/ perhaps?

> Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
> ---
>  builtin/cat-file.c | 38 +++++++++++++++++++++++++++++---------
>  1 file changed, 29 insertions(+), 9 deletions(-)
>
> diff --git a/builtin/cat-file.c b/builtin/cat-file.c
> index df99df4..91ceae0 100644
> --- a/builtin/cat-file.c
> +++ b/builtin/cat-file.c
> @@ -9,13 +9,20 @@
>  #include "userdiff.h"
>  #include "streaming.h"
>  
> -static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
> +static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
> +			int literally)
>  {
>  	unsigned char sha1[20];
>  	enum object_type type;
>  	char *buf;
>  	unsigned long size;
>  	struct object_context obj_context;
> +	struct object_info oi = {NULL};
> +	struct strbuf sb = STRBUF_INIT;
> +	unsigned flags = LOOKUP_REPLACE_OBJECT;
> +
> +	if (literally)
> +		flags |= LOOKUP_LITERALLY;
>  
>  	if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
>  		die("Not a valid object name %s", obj_name);
> @@ -23,16 +30,24 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
>  	buf = NULL;
>  	switch (opt) {
>  	case 't':
> -		type = sha1_object_info(sha1, NULL);
> -		if (type > 0) {
> -			printf("%s\n", typename(type));
> +		oi.typep = &type;
> +		oi.typename = &sb;
> +		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
> +			die("git cat-file: could not get object info");
> +		if (type >= 0 && sb.len) {
> +			printf("%s\n", sb.buf);
> +			strbuf_release(&sb);
>  			return 0;
>  		}
>  		break;
>  
>  	case 's':
> -		type = sha1_object_info(sha1, &size);
> -		if (type > 0) {
> +		oi.typep = &type;
> +		oi.typename = &sb;
> +		oi.sizep = &size;
> +		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
> +			die("git cat-file: could not get object info");
> +		if (type >= 0 && sb.len) {
>  			printf("%lu\n", size);
>  			return 0;
>  		}
> @@ -323,7 +338,7 @@ static int batch_objects(struct batch_options *opt)
>  }
>  
>  static const char * const cat_file_usage[] = {
> -	N_("git cat-file (-t | -s | -e | -p | <type> | --textconv) <object>"),
> +	N_("git cat-file (-t [--literally]|-s [--literally]|-e|-p|<type>|--textconv) <object>"),
>  	N_("git cat-file (--batch | --batch-check) < <list-of-objects>"),
>  	NULL
>  };
> @@ -359,6 +374,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>  	int opt = 0;
>  	const char *exp_type = NULL, *obj_name = NULL;
>  	struct batch_options batch = {0};
> +	int literally = 0;
>  
>  	const struct option options[] = {
>  		OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
> @@ -369,6 +385,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>  		OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
>  		OPT_SET_INT(0, "textconv", &opt,
>  			    N_("for blob objects, run textconv on object's content"), 'c'),
> +		OPT_BOOL( 0, "literally", &literally,
> +			  N_("get information about corrupt objects for debugging Git")),
>  		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
>  			N_("show info and content of objects fed from the standard input"),
>  			PARSE_OPT_OPTARG, batch_option_callback },
> @@ -380,7 +398,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>  
>  	git_config(git_cat_file_config, NULL);
>  
> -	if (argc != 3 && argc != 2)
> +	if (argc < 2 || argc > 4)
>  		usage_with_options(cat_file_usage, options);
>  
>  	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
> @@ -405,5 +423,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>  	if (batch.enabled)
>  		return batch_objects(&batch);
>  
> -	return cat_one_file(opt, exp_type, obj_name);
> +	if (literally && opt != 't' && opt != 's')
> +		die("git cat-file --literally: use with -s or -t");
> +	return cat_one_file(opt, exp_type, obj_name, literally);
>  }

Re: [PATCH v6 1/4] sha1_file.c: support reading from a loose object of unknown type

[Junio C Hamano]

Karthik Nayak <karthik.188@gmail.com> writes:

> +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);

I briefly wondered if this can return Z_BUF_ERROR, but it is OK
because we do not call inflate with Z_FINISH in unpack_sha1_header()
for obvious reasons ;-)

> +	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;
> +}

OK.

> @@ -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

Is this still a valid comment?

>  	 * 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

Re: [PATCH v6 0/4] cat-file: add a '--literally' option

[Junio C Hamano]

When merged to 'pu', this seems to break at least 5309 and 5300
tests (there might be others, but I didn't check).

Re: [PATCH v6 2/4] cat-file: teach cat-file a '--literally' option

[karthik nayak]

On 04/03/2015 12:38 AM, Junio C Hamano wrote:
> Karthik Nayak <karthik.188@gmail.com> writes:
>
>> Currently 'git cat-file' throws an error while trying to
>> print the type or size of a broken/corrupt object which is
>> created using 'git hash-object --literally'. This is
>> because these objects are usually of unknown types.
>>
>> Teach git cat-file a '--literally' option where it prints
>> the type or size of a broken/corrupt object without throwing
>> an error.
>>
>> Modify '-t' and '-s' options to call sha1_object_info_extended()
>> directly to support the '--literally' option.
>>
>> Helped-by: Junio C Hamano <gitster@pobox.com>
>> Helped-by: Eric Sunshine <sunshine@sunshineco
>
> s/$/.com/ perhaps?
Definitely!
>
>> Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
>> ---
>>   builtin/cat-file.c | 38 +++++++++++++++++++++++++++++---------
>>   1 file changed, 29 insertions(+), 9 deletions(-)
>>
>> diff --git a/builtin/cat-file.c b/builtin/cat-file.c
>> index df99df4..91ceae0 100644
>> --- a/builtin/cat-file.c
>> +++ b/builtin/cat-file.c
>> @@ -9,13 +9,20 @@
>>   #include "userdiff.h"
>>   #include "streaming.h"
>>
>> -static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
>> +static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
>> +			int literally)
>>   {
>>   	unsigned char sha1[20];
>>   	enum object_type type;
>>   	char *buf;
>>   	unsigned long size;
>>   	struct object_context obj_context;
>> +	struct object_info oi = {NULL};
>> +	struct strbuf sb = STRBUF_INIT;
>> +	unsigned flags = LOOKUP_REPLACE_OBJECT;
>> +
>> +	if (literally)
>> +		flags |= LOOKUP_LITERALLY;
>>
>>   	if (get_sha1_with_context(obj_name, 0, sha1, &obj_context))
>>   		die("Not a valid object name %s", obj_name);
>> @@ -23,16 +30,24 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
>>   	buf = NULL;
>>   	switch (opt) {
>>   	case 't':
>> -		type = sha1_object_info(sha1, NULL);
>> -		if (type > 0) {
>> -			printf("%s\n", typename(type));
>> +		oi.typep = &type;
>> +		oi.typename = &sb;
>> +		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
>> +			die("git cat-file: could not get object info");
>> +		if (type >= 0 && sb.len) {
>> +			printf("%s\n", sb.buf);
>> +			strbuf_release(&sb);
>>   			return 0;
>>   		}
>>   		break;
>>
>>   	case 's':
>> -		type = sha1_object_info(sha1, &size);
>> -		if (type > 0) {
>> +		oi.typep = &type;
>> +		oi.typename = &sb;
>> +		oi.sizep = &size;
>> +		if (sha1_object_info_extended(sha1, &oi, flags) < 0)
>> +			die("git cat-file: could not get object info");
>> +		if (type >= 0 && sb.len) {
>>   			printf("%lu\n", size);
>>   			return 0;
>>   		}
>> @@ -323,7 +338,7 @@ static int batch_objects(struct batch_options *opt)
>>   }
>>
>>   static const char * const cat_file_usage[] = {
>> -	N_("git cat-file (-t | -s | -e | -p | <type> | --textconv) <object>"),
>> +	N_("git cat-file (-t [--literally]|-s [--literally]|-e|-p|<type>|--textconv) <object>"),
>>   	N_("git cat-file (--batch | --batch-check) < <list-of-objects>"),
>>   	NULL
>>   };
>> @@ -359,6 +374,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>>   	int opt = 0;
>>   	const char *exp_type = NULL, *obj_name = NULL;
>>   	struct batch_options batch = {0};
>> +	int literally = 0;
>>
>>   	const struct option options[] = {
>>   		OPT_GROUP(N_("<type> can be one of: blob, tree, commit, tag")),
>> @@ -369,6 +385,8 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>>   		OPT_SET_INT('p', NULL, &opt, N_("pretty-print object's content"), 'p'),
>>   		OPT_SET_INT(0, "textconv", &opt,
>>   			    N_("for blob objects, run textconv on object's content"), 'c'),
>> +		OPT_BOOL( 0, "literally", &literally,
>> +			  N_("get information about corrupt objects for debugging Git")),
>>   		{ OPTION_CALLBACK, 0, "batch", &batch, "format",
>>   			N_("show info and content of objects fed from the standard input"),
>>   			PARSE_OPT_OPTARG, batch_option_callback },
>> @@ -380,7 +398,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>>
>>   	git_config(git_cat_file_config, NULL);
>>
>> -	if (argc != 3 && argc != 2)
>> +	if (argc < 2 || argc > 4)
>>   		usage_with_options(cat_file_usage, options);
>>
>>   	argc = parse_options(argc, argv, prefix, options, cat_file_usage, 0);
>> @@ -405,5 +423,7 @@ int cmd_cat_file(int argc, const char **argv, const char *prefix)
>>   	if (batch.enabled)
>>   		return batch_objects(&batch);
>>
>> -	return cat_one_file(opt, exp_type, obj_name);
>> +	if (literally && opt != 't' && opt != 's')
>> +		die("git cat-file --literally: use with -s or -t");
>> +	return cat_one_file(opt, exp_type, obj_name, literally);
>>   }

Re: [PATCH v6 0/4] cat-file: add a '--literally' option

[karthik nayak]

On 04/03/2015 02:05 AM, Junio C Hamano wrote:
> When merged to 'pu', this seems to break at least 5309 and 5300
> tests (there might be others, but I didn't check).
>

There was a problem with packed object types. I have it fixed, will send 
a re-roll.