X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=sha1_file.c;h=219a10f403e0c3aa2f8d60ecde5807cf51d1a659;hb=ed287ab7fa71528e8de288988d1662eebae64002;hp=43ff4023808cc8b5a5f54c75ff77e80776a581aa;hpb=8276c0070f8f8959ab4b6ec458fa0740e9abda9e;p=git.git

diff --git a/sha1_file.c b/sha1_file.c
index 43ff40238..219a10f40 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -349,6 +349,7 @@ static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
 static void read_info_alternates(const char * relative_base, int depth)
 {
 	char *map;
+	size_t mapsz;
 	struct stat st;
 	char path[PATH_MAX];
 	int fd;
@@ -361,12 +362,13 @@ static void read_info_alternates(const char * relative_base, int depth)
 		close(fd);
 		return;
 	}
-	map = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+	mapsz = xsize_t(st.st_size);
+	map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
 
-	link_alt_odb_entries(map, map + st.st_size, '\n', relative_base, depth);
+	link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth);
 
-	munmap(map, st.st_size);
+	munmap(map, mapsz);
 }
 
 void prepare_alt_odb(void)
@@ -407,7 +409,6 @@ static unsigned int peak_pack_open_windows;
 static unsigned int pack_open_windows;
 static size_t peak_pack_mapped;
 static size_t pack_mapped;
-static size_t page_size;
 struct packed_git *packed_git;
 
 void pack_report()
@@ -416,7 +417,7 @@ void pack_report()
 		"pack_report: getpagesize()            = %10" SZ_FMT "\n"
 		"pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
 		"pack_report: core.packedGitLimit      = %10" SZ_FMT "\n",
-		page_size,
+		(size_t) getpagesize(),
 		packed_git_window_size,
 		packed_git_limit);
 	fprintf(stderr,
@@ -431,13 +432,14 @@ void pack_report()
 		pack_mapped, peak_pack_mapped);
 }
 
-static int check_packed_git_idx(const char *path, unsigned long *idx_size_,
-				void **idx_map_)
+static int check_packed_git_idx(const char *path,
+	unsigned long *idx_size_,
+	void **idx_map_)
 {
 	void *idx_map;
 	uint32_t *index;
-	unsigned long idx_size;
-	int nr, i;
+	size_t idx_size;
+	uint32_t nr, i;
 	int fd = open(path, O_RDONLY);
 	struct stat st;
 	if (fd < 0)
@@ -446,7 +448,11 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_,
 		close(fd);
 		return -1;
 	}
-	idx_size = st.st_size;
+	idx_size = xsize_t(st.st_size);
+	if (idx_size < 4 * 256 + 20 + 20) {
+		close(fd);
+		return error("index file %s is too small", path);
+	}
 	idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
 
@@ -454,25 +460,25 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_,
 	*idx_map_ = idx_map;
 	*idx_size_ = idx_size;
 
-	/* check index map */
-	if (idx_size < 4*256 + 20 + 20)
-		return error("index file %s is too small", path);
-
 	/* a future index format would start with this, as older git
 	 * binaries would fail the non-monotonic index check below.
 	 * give a nicer warning to the user if we can.
 	 */
-	if (index[0] == htonl(PACK_IDX_SIGNATURE))
+	if (index[0] == htonl(PACK_IDX_SIGNATURE)) {
+		munmap(idx_map, idx_size);
 		return error("index file %s is a newer version"
 			" and is not supported by this binary"
 			" (try upgrading GIT to a newer version)",
 			path);
+	}
 
 	nr = 0;
 	for (i = 0; i < 256; i++) {
-		unsigned int n = ntohl(index[i]);
-		if (n < nr)
+		uint32_t n = ntohl(index[i]);
+		if (n < nr) {
+			munmap(idx_map, idx_size);
 			return error("non-monotonic index %s", path);
+		}
 		nr = n;
 	}
 
@@ -483,8 +489,10 @@ static int check_packed_git_idx(const char *path, unsigned long *idx_size_,
 	 *  - 20-byte SHA1 of the packfile
 	 *  - 20-byte SHA1 file checksum
 	 */
-	if (idx_size != 4*256 + nr * 24 + 20 + 20)
+	if (idx_size != 4*256 + nr * 24 + 20 + 20) {
+		munmap(idx_map, idx_size);
 		return error("wrong index file size in %s", path);
+	}
 
 	return 0;
 }
@@ -552,7 +560,11 @@ void unuse_pack(struct pack_window **w_cursor)
 	}
 }
 
-static void open_packed_git(struct packed_git *p)
+/*
+ * Do not call this directly as this leaks p->pack_fd on error return;
+ * call open_packed_git() instead.
+ */
+static int open_packed_git_1(struct packed_git *p)
 {
 	struct stat st;
 	struct pack_header hdr;
@@ -562,52 +574,64 @@ static void open_packed_git(struct packed_git *p)
 
 	p->pack_fd = open(p->pack_name, O_RDONLY);
 	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
-		die("packfile %s cannot be opened", p->pack_name);
+		return -1;
 
 	/* If we created the struct before we had the pack we lack size. */
 	if (!p->pack_size) {
 		if (!S_ISREG(st.st_mode))
-			die("packfile %s not a regular file", p->pack_name);
+			return error("packfile %s not a regular file", p->pack_name);
 		p->pack_size = st.st_size;
 	} else if (p->pack_size != st.st_size)
-		die("packfile %s size changed", p->pack_name);
+		return error("packfile %s size changed", p->pack_name);
 
 	/* We leave these file descriptors open with sliding mmap;
 	 * there is no point keeping them open across exec(), though.
 	 */
 	fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
 	if (fd_flag < 0)
-		die("cannot determine file descriptor flags");
+		return error("cannot determine file descriptor flags");
 	fd_flag |= FD_CLOEXEC;
 	if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
-		die("cannot set FD_CLOEXEC");
+		return error("cannot set FD_CLOEXEC");
 
 	/* Verify we recognize this pack file format. */
 	if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
-		die("file %s is far too short to be a packfile", p->pack_name);
+		return error("file %s is far too short to be a packfile", p->pack_name);
 	if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
-		die("file %s is not a GIT packfile", p->pack_name);
+		return error("file %s is not a GIT packfile", p->pack_name);
 	if (!pack_version_ok(hdr.hdr_version))
-		die("packfile %s is version %u and not supported"
+		return error("packfile %s is version %u and not supported"
 			" (try upgrading GIT to a newer version)",
 			p->pack_name, ntohl(hdr.hdr_version));
 
 	/* Verify the pack matches its index. */
 	if (num_packed_objects(p) != ntohl(hdr.hdr_entries))
-		die("packfile %s claims to have %u objects"
+		return error("packfile %s claims to have %u objects"
 			" while index size indicates %u objects",
 			p->pack_name, ntohl(hdr.hdr_entries),
 			num_packed_objects(p));
 	if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
-		die("end of packfile %s is unavailable", p->pack_name);
+		return error("end of packfile %s is unavailable", p->pack_name);
 	if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1))
-		die("packfile %s signature is unavailable", p->pack_name);
+		return error("packfile %s signature is unavailable", p->pack_name);
 	idx_sha1 = ((unsigned char *)p->index_base) + p->index_size - 40;
 	if (hashcmp(sha1, idx_sha1))
-		die("packfile %s does not match index", p->pack_name);
+		return error("packfile %s does not match index", p->pack_name);
+	return 0;
 }
 
-static int in_window(struct pack_window *win, unsigned long offset)
+static int open_packed_git(struct packed_git *p)
+{
+	if (!open_packed_git_1(p))
+		return 0;
+	if (p->pack_fd != -1) {
+		close(p->pack_fd);
+		p->pack_fd = -1;
+	}
+	return -1;
+}
+
+static int in_window(struct pack_window *win, off_t offset)
 {
 	/* We must promise at least 20 bytes (one hash) after the
 	 * offset is available from this window, otherwise the offset
@@ -622,13 +646,13 @@ static int in_window(struct pack_window *win, unsigned long offset)
 
 unsigned char* use_pack(struct packed_git *p,
 		struct pack_window **w_cursor,
-		unsigned long offset,
+		off_t offset,
 		unsigned int *left)
 {
 	struct pack_window *win = *w_cursor;
 
-	if (p->pack_fd == -1)
-		open_packed_git(p);
+	if (p->pack_fd == -1 && open_packed_git(p))
+		die("packfile %s cannot be accessed", p->pack_name);
 
 	/* Since packfiles end in a hash of their content and its
 	 * pointless to ask for an offset into the middle of that
@@ -646,13 +670,14 @@ unsigned char* use_pack(struct packed_git *p,
 				break;
 		}
 		if (!win) {
-			if (!page_size)
-				page_size = getpagesize();
+			size_t window_align = packed_git_window_size / 2;
+			off_t len;
 			win = xcalloc(1, sizeof(*win));
-			win->offset = (offset / page_size) * page_size;
-			win->len = p->pack_size - win->offset;
-			if (win->len > packed_git_window_size)
-				win->len = packed_git_window_size;
+			win->offset = (offset / window_align) * window_align;
+			len = p->pack_size - win->offset;
+			if (len > packed_git_window_size)
+				len = packed_git_window_size;
+			win->len = (size_t)len;
 			pack_mapped += win->len;
 			while (packed_git_limit < pack_mapped
 				&& unuse_one_window(p))
@@ -681,7 +706,7 @@ unsigned char* use_pack(struct packed_git *p,
 	}
 	offset -= win->offset;
 	if (left)
-		*left = win->len - offset;
+		*left = win->len - xsize_t(offset);
 	return win->base + offset;
 }
 
@@ -779,7 +804,7 @@ static void prepare_packed_git_one(char *objdir, int local)
 		if (!has_extension(de->d_name, ".idx"))
 			continue;
 
-		/* we have .idx.  Is it a file we can map? */
+		/* Don't reopen a pack we already have. */
 		strcpy(path + len, de->d_name);
 		for (p = packed_git; p; p = p->next) {
 			if (!memcmp(path, p->pack_name, len + namelen - 4))
@@ -787,11 +812,13 @@ static void prepare_packed_git_one(char *objdir, int local)
 		}
 		if (p)
 			continue;
+		/* See if it really is a valid .idx file with corresponding
+		 * .pack file that we can map.
+		 */
 		p = add_packed_git(path, len + namelen, local);
 		if (!p)
 			continue;
-		p->next = packed_git;
-		packed_git = p;
+		install_packed_git(p);
 	}
 	closedir(dir);
 }
@@ -855,9 +882,9 @@ void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
 		 */
 		sha1_file_open_flag = 0;
 	}
-	map = xmmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+	*size = xsize_t(st.st_size);
+	map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
-	*size = st.st_size;
 	return map;
 }
 
@@ -936,7 +963,7 @@ static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned lon
 
 	/* And generate the fake traditional header */
 	stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
-					 type_names[type], size);
+					 typename(type), size);
 	return 0;
 }
 
@@ -967,26 +994,27 @@ static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size
  * too permissive for what we want to check. So do an anal
  * object header parse by hand.
  */
-static int parse_sha1_header(char *hdr, char *type, unsigned long *sizep)
+static int parse_sha1_header(const char *hdr, unsigned long *sizep)
 {
+	char type[10];
 	int i;
 	unsigned long size;
 
 	/*
 	 * The type can be at most ten bytes (including the 
 	 * terminating '\0' that we add), and is followed by
-	 * a space. 
+	 * a space.
 	 */
-	i = 10;
+	i = 0;
 	for (;;) {
 		char c = *hdr++;
 		if (c == ' ')
 			break;
-		if (!--i)
+		type[i++] = c;
+		if (i >= sizeof(type))
 			return -1;
-		*type++ = c;
 	}
-	*type = 0;
+	type[i] = 0;
 
 	/*
 	 * The length must follow immediately, and be in canonical
@@ -1009,31 +1037,30 @@ static int parse_sha1_header(char *hdr, char *type, unsigned long *sizep)
 	/*
 	 * The length must be followed by a zero byte
 	 */
-	return *hdr ? -1 : 0;
+	return *hdr ? -1 : type_from_string(type);
 }
 
-void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size)
+void * unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size)
 {
 	int ret;
 	z_stream stream;
 	char hdr[8192];
 
 	ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
-	if (ret < Z_OK || parse_sha1_header(hdr, type, size) < 0)
+	if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0)
 		return NULL;
 
 	return unpack_sha1_rest(&stream, hdr, *size);
 }
 
-static unsigned long get_delta_base(struct packed_git *p,
+static off_t get_delta_base(struct packed_git *p,
 				    struct pack_window **w_curs,
-				    unsigned long offset,
-				    enum object_type kind,
-				    unsigned long delta_obj_offset,
-				    unsigned long *base_obj_offset)
+				    off_t *curpos,
+				    enum object_type type,
+				    off_t delta_obj_offset)
 {
-	unsigned char *base_info = use_pack(p, w_curs, offset, NULL);
-	unsigned long base_offset;
+	unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
+	off_t base_offset;
 
 	/* use_pack() assured us we have [base_info, base_info + 20)
 	 * as a range that we can look at without walking off the
@@ -1041,7 +1068,7 @@ static unsigned long get_delta_base(struct packed_git *p,
 	 * that is assured.  An OFS_DELTA longer than the hash size
 	 * is stupid, as then a REF_DELTA would be smaller to store.
 	 */
-	if (kind == OBJ_OFS_DELTA) {
+	if (type == OBJ_OFS_DELTA) {
 		unsigned used = 0;
 		unsigned char c = base_info[used++];
 		base_offset = c & 127;
@@ -1055,49 +1082,43 @@ static unsigned long get_delta_base(struct packed_git *p,
 		base_offset = delta_obj_offset - base_offset;
 		if (base_offset >= delta_obj_offset)
 			die("delta base offset out of bound");
-		offset += used;
-	} else if (kind == OBJ_REF_DELTA) {
+		*curpos += used;
+	} else if (type == OBJ_REF_DELTA) {
 		/* The base entry _must_ be in the same pack */
 		base_offset = find_pack_entry_one(base_info, p);
 		if (!base_offset)
 			die("failed to find delta-pack base object %s",
 				sha1_to_hex(base_info));
-		offset += 20;
+		*curpos += 20;
 	} else
 		die("I am totally screwed");
-	*base_obj_offset = base_offset;
-	return offset;
+	return base_offset;
 }
 
 /* forward declaration for a mutually recursive function */
-static int packed_object_info(struct packed_git *p, unsigned long offset,
-			      char *type, unsigned long *sizep);
+static int packed_object_info(struct packed_git *p, off_t offset,
+			      unsigned long *sizep);
 
 static int packed_delta_info(struct packed_git *p,
 			     struct pack_window **w_curs,
-			     unsigned long offset,
-			     enum object_type kind,
-			     unsigned long obj_offset,
-			     char *type,
+			     off_t curpos,
+			     enum object_type type,
+			     off_t obj_offset,
 			     unsigned long *sizep)
 {
-	unsigned long base_offset;
+	off_t base_offset;
 
-	offset = get_delta_base(p, w_curs, offset, kind,
-		obj_offset, &base_offset);
+	base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
+	type = packed_object_info(p, base_offset, NULL);
 
 	/* We choose to only get the type of the base object and
 	 * ignore potentially corrupt pack file that expects the delta
 	 * based on a base with a wrong size.  This saves tons of
 	 * inflate() calls.
 	 */
-	if (packed_object_info(p, base_offset, type, NULL))
-		die("cannot get info for delta-pack base");
-
 	if (sizep) {
 		const unsigned char *data;
 		unsigned char delta_head[20], *in;
-		unsigned long result_size;
 		z_stream stream;
 		int st;
 
@@ -1107,10 +1128,10 @@ static int packed_delta_info(struct packed_git *p,
 
 		inflateInit(&stream);
 		do {
-			in = use_pack(p, w_curs, offset, &stream.avail_in);
+			in = use_pack(p, w_curs, curpos, &stream.avail_in);
 			stream.next_in = in;
 			st = inflate(&stream, Z_FINISH);
-			offset += stream.next_in - in;
+			curpos += stream.next_in - in;
 		} while ((st == Z_OK || st == Z_BUF_ERROR)
 			&& stream.total_out < sizeof(delta_head));
 		inflateEnd(&stream);
@@ -1127,122 +1148,120 @@ static int packed_delta_info(struct packed_git *p,
 		get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
 
 		/* Read the result size */
-		result_size = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
-		*sizep = result_size;
+		*sizep = get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
 	}
-	return 0;
+
+	return type;
 }
 
-static unsigned long unpack_object_header(struct packed_git *p,
-		struct pack_window **w_curs,
-		unsigned long offset,
-		enum object_type *type,
-		unsigned long *sizep)
+static int unpack_object_header(struct packed_git *p,
+				struct pack_window **w_curs,
+				off_t *curpos,
+				unsigned long *sizep)
 {
 	unsigned char *base;
 	unsigned int left;
 	unsigned long used;
+	enum object_type type;
 
 	/* use_pack() assures us we have [base, base + 20) available
 	 * as a range that we can look at at.  (Its actually the hash
-	 * size that is assurred.)  With our object header encoding
+	 * size that is assured.)  With our object header encoding
 	 * the maximum deflated object size is 2^137, which is just
 	 * insane, so we know won't exceed what we have been given.
 	 */
-	base = use_pack(p, w_curs, offset, &left);
-	used = unpack_object_header_gently(base, left, type, sizep);
+	base = use_pack(p, w_curs, *curpos, &left);
+	used = unpack_object_header_gently(base, left, &type, sizep);
 	if (!used)
 		die("object offset outside of pack file");
+	*curpos += used;
 
-	return offset + used;
+	return type;
 }
 
-void packed_object_info_detail(struct packed_git *p,
-			       unsigned long offset,
-			       char *type,
-			       unsigned long *size,
-			       unsigned long *store_size,
-			       unsigned int *delta_chain_length,
-			       unsigned char *base_sha1)
+const char *packed_object_info_detail(struct packed_git *p,
+				      off_t obj_offset,
+				      unsigned long *size,
+				      unsigned long *store_size,
+				      unsigned int *delta_chain_length,
+				      unsigned char *base_sha1)
 {
 	struct pack_window *w_curs = NULL;
-	unsigned long obj_offset, val;
+	off_t curpos;
+	unsigned long dummy;
 	unsigned char *next_sha1;
-	enum object_type kind;
+	enum object_type type;
 
 	*delta_chain_length = 0;
-	obj_offset = offset;
-	offset = unpack_object_header(p, &w_curs, offset, &kind, size);
+	curpos = obj_offset;
+	type = unpack_object_header(p, &w_curs, &curpos, size);
 
 	for (;;) {
-		switch (kind) {
+		switch (type) {
 		default:
 			die("pack %s contains unknown object type %d",
-			    p->pack_name, kind);
+			    p->pack_name, type);
 		case OBJ_COMMIT:
 		case OBJ_TREE:
 		case OBJ_BLOB:
 		case OBJ_TAG:
-			strcpy(type, type_names[kind]);
 			*store_size = 0; /* notyet */
 			unuse_pack(&w_curs);
-			return;
+			return typename(type);
 		case OBJ_OFS_DELTA:
-			get_delta_base(p, &w_curs, offset, kind,
-				obj_offset, &offset);
+			obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
 			if (*delta_chain_length == 0) {
-				/* TODO: find base_sha1 as pointed by offset */
+				/* TODO: find base_sha1 as pointed by curpos */
+				hashclr(base_sha1);
 			}
 			break;
 		case OBJ_REF_DELTA:
-			next_sha1 = use_pack(p, &w_curs, offset, NULL);
+			next_sha1 = use_pack(p, &w_curs, curpos, NULL);
 			if (*delta_chain_length == 0)
 				hashcpy(base_sha1, next_sha1);
-			offset = find_pack_entry_one(next_sha1, p);
+			obj_offset = find_pack_entry_one(next_sha1, p);
 			break;
 		}
-		obj_offset = offset;
-		offset = unpack_object_header(p, &w_curs, offset, &kind, &val);
 		(*delta_chain_length)++;
+		curpos = obj_offset;
+		type = unpack_object_header(p, &w_curs, &curpos, &dummy);
 	}
 }
 
-static int packed_object_info(struct packed_git *p, unsigned long offset,
-			      char *type, unsigned long *sizep)
+static int packed_object_info(struct packed_git *p, off_t obj_offset,
+			      unsigned long *sizep)
 {
 	struct pack_window *w_curs = NULL;
-	unsigned long size, obj_offset = offset;
-	enum object_type kind;
-	int r;
+	unsigned long size;
+	off_t curpos = obj_offset;
+	enum object_type type;
 
-	offset = unpack_object_header(p, &w_curs, offset, &kind, &size);
+	type = unpack_object_header(p, &w_curs, &curpos, &size);
 
-	switch (kind) {
+	switch (type) {
 	case OBJ_OFS_DELTA:
 	case OBJ_REF_DELTA:
-		r = packed_delta_info(p, &w_curs, offset, kind,
-			obj_offset, type, sizep);
-		unuse_pack(&w_curs);
-		return r;
+		type = packed_delta_info(p, &w_curs, curpos,
+					 type, obj_offset, sizep);
+		break;
 	case OBJ_COMMIT:
 	case OBJ_TREE:
 	case OBJ_BLOB:
 	case OBJ_TAG:
-		strcpy(type, type_names[kind]);
-		unuse_pack(&w_curs);
+		if (sizep)
+			*sizep = size;
 		break;
 	default:
 		die("pack %s contains unknown object type %d",
-		    p->pack_name, kind);
+		    p->pack_name, type);
 	}
-	if (sizep)
-		*sizep = size;
-	return 0;
+	unuse_pack(&w_curs);
+	return type;
 }
 
 static void *unpack_compressed_entry(struct packed_git *p,
 				    struct pack_window **w_curs,
-				    unsigned long offset,
+				    off_t curpos,
 				    unsigned long size)
 {
 	int st;
@@ -1257,10 +1276,10 @@ static void *unpack_compressed_entry(struct packed_git *p,
 
 	inflateInit(&stream);
 	do {
-		in = use_pack(p, w_curs, offset, &stream.avail_in);
+		in = use_pack(p, w_curs, curpos, &stream.avail_in);
 		stream.next_in = in;
 		st = inflate(&stream, Z_FINISH);
-		offset += stream.next_in - in;
+		curpos += stream.next_in - in;
 	} while (st == Z_OK || st == Z_BUF_ERROR);
 	inflateEnd(&stream);
 	if ((st != Z_STREAM_END) || stream.total_out != size) {
@@ -1273,82 +1292,78 @@ static void *unpack_compressed_entry(struct packed_git *p,
 
 static void *unpack_delta_entry(struct packed_git *p,
 				struct pack_window **w_curs,
-				unsigned long offset,
+				off_t curpos,
 				unsigned long delta_size,
-				enum object_type kind,
-				unsigned long obj_offset,
-				char *type,
+				off_t obj_offset,
+				enum object_type *type,
 				unsigned long *sizep)
 {
 	void *delta_data, *result, *base;
-	unsigned long result_size, base_size, base_offset;
+	unsigned long base_size;
+	off_t base_offset;
 
-	offset = get_delta_base(p, w_curs, offset, kind,
-		obj_offset, &base_offset);
+	base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset);
 	base = unpack_entry(p, base_offset, type, &base_size);
 	if (!base)
-		die("failed to read delta base object at %lu from %s",
-		    base_offset, p->pack_name);
+		die("failed to read delta base object"
+		    " at %"PRIuMAX" from %s",
+		    (uintmax_t)base_offset, p->pack_name);
 
-	delta_data = unpack_compressed_entry(p, w_curs, offset, delta_size);
+	delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size);
 	result = patch_delta(base, base_size,
 			     delta_data, delta_size,
-			     &result_size);
+			     sizep);
 	if (!result)
 		die("failed to apply delta");
 	free(delta_data);
 	free(base);
-	*sizep = result_size;
 	return result;
 }
 
-void *unpack_entry(struct packed_git *p, unsigned long offset,
-			  char *type, unsigned long *sizep)
+void *unpack_entry(struct packed_git *p, off_t obj_offset,
+		   enum object_type *type, unsigned long *sizep)
 {
 	struct pack_window *w_curs = NULL;
-	unsigned long size, obj_offset = offset;
-	enum object_type kind;
-	void *retval;
+	off_t curpos = obj_offset;
+	void *data;
 
-	offset = unpack_object_header(p, &w_curs, offset, &kind, &size);
-	switch (kind) {
+	*type = unpack_object_header(p, &w_curs, &curpos, sizep);
+	switch (*type) {
 	case OBJ_OFS_DELTA:
 	case OBJ_REF_DELTA:
-		retval = unpack_delta_entry(p, &w_curs, offset, size,
-			kind, obj_offset, type, sizep);
+		data = unpack_delta_entry(p, &w_curs, curpos, *sizep,
+					  obj_offset, type, sizep);
 		break;
 	case OBJ_COMMIT:
 	case OBJ_TREE:
 	case OBJ_BLOB:
 	case OBJ_TAG:
-		strcpy(type, type_names[kind]);
-		*sizep = size;
-		retval = unpack_compressed_entry(p, &w_curs, offset, size);
+		data = unpack_compressed_entry(p, &w_curs, curpos, *sizep);
 		break;
 	default:
-		die("unknown object type %i in %s", kind, p->pack_name);
+		die("unknown object type %i in %s", *type, p->pack_name);
 	}
 	unuse_pack(&w_curs);
-	return retval;
+	return data;
 }
 
-int num_packed_objects(const struct packed_git *p)
+uint32_t num_packed_objects(const struct packed_git *p)
 {
 	/* See check_packed_git_idx() */
-	return (p->index_size - 20 - 20 - 4*256) / 24;
+	return (uint32_t)((p->index_size - 20 - 20 - 4*256) / 24);
 }
 
-int nth_packed_object_sha1(const struct packed_git *p, int n,
+int nth_packed_object_sha1(const struct packed_git *p, uint32_t n,
 			   unsigned char* sha1)
 {
 	void *index = p->index_base + 256;
-	if (n < 0 || num_packed_objects(p) <= n)
+	if (num_packed_objects(p) <= n)
 		return -1;
 	hashcpy(sha1, (unsigned char *) index + (24 * n) + 4);
 	return 0;
 }
 
-unsigned long find_pack_entry_one(const unsigned char *sha1,
+off_t find_pack_entry_one(const unsigned char *sha1,
 				  struct packed_git *p)
 {
 	uint32_t *level1_ofs = p->index_base;
@@ -1390,7 +1405,7 @@ static int matches_pack_name(struct packed_git *p, const char *ig)
 static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, const char **ignore_packed)
 {
 	struct packed_git *p;
-	unsigned long offset;
+	off_t offset;
 
 	prepare_packed_git();
 
@@ -1405,6 +1420,18 @@ static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e, cons
 		}
 		offset = find_pack_entry_one(sha1, p);
 		if (offset) {
+			/*
+			 * We are about to tell the caller where they can
+			 * locate the requested object.  We better make
+			 * sure the packfile is still here and can be
+			 * accessed before supplying that answer, as
+			 * it may have been deleted since the index
+			 * was loaded!
+			 */
+			if (p->pack_fd == -1 && open_packed_git(p)) {
+				error("packfile %s cannot be accessed", p->pack_name);
+				continue;
+			}
 			e->offset = offset;
 			e->p = p;
 			hashcpy(e->sha1, sha1);
@@ -1424,16 +1451,16 @@ struct packed_git *find_sha1_pack(const unsigned char *sha1,
 			return p;
 	}
 	return NULL;
-	
+
 }
 
-static int sha1_loose_object_info(const unsigned char *sha1, char *type, unsigned long *sizep)
+static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep)
 {
 	int status;
 	unsigned long mapsize, size;
 	void *map;
 	z_stream stream;
-	char hdr[128];
+	char hdr[32];
 
 	map = map_sha1_file(sha1, &mapsize);
 	if (!map)
@@ -1441,31 +1468,29 @@ static int sha1_loose_object_info(const unsigned char *sha1, char *type, unsigne
 	if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
 		status = error("unable to unpack %s header",
 			       sha1_to_hex(sha1));
-	if (parse_sha1_header(hdr, type, &size) < 0)
+	else if ((status = parse_sha1_header(hdr, &size)) < 0)
 		status = error("unable to parse %s header", sha1_to_hex(sha1));
-	else {
-		status = 0;
-		if (sizep)
-			*sizep = size;
-	}
+	else if (sizep)
+		*sizep = size;
 	inflateEnd(&stream);
 	munmap(map, mapsize);
 	return status;
 }
 
-int sha1_object_info(const unsigned char *sha1, char *type, unsigned long *sizep)
+int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
 {
 	struct pack_entry e;
 
 	if (!find_pack_entry(sha1, &e, NULL)) {
 		reprepare_packed_git();
 		if (!find_pack_entry(sha1, &e, NULL))
-			return sha1_loose_object_info(sha1, type, sizep);
+			return sha1_loose_object_info(sha1, sizep);
 	}
-	return packed_object_info(e.p, e.offset, type, sizep);
+	return packed_object_info(e.p, e.offset, sizep);
 }
 
-static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned long *size)
+static void *read_packed_sha1(const unsigned char *sha1,
+			      enum object_type *type, unsigned long *size)
 {
 	struct pack_entry e;
 
@@ -1475,10 +1500,71 @@ static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned lo
 		return unpack_entry(e.p, e.offset, type, size);
 }
 
-void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size)
+/*
+ * This is meant to hold a *small* number of objects that you would
+ * want read_sha1_file() to be able to return, but yet you do not want
+ * to write them into the object store (e.g. a browse-only
+ * application).
+ */
+static struct cached_object {
+	unsigned char sha1[20];
+	enum object_type type;
+	void *buf;
+	unsigned long size;
+} *cached_objects;
+static int cached_object_nr, cached_object_alloc;
+
+static struct cached_object *find_cached_object(const unsigned char *sha1)
+{
+	int i;
+	struct cached_object *co = cached_objects;
+
+	for (i = 0; i < cached_object_nr; i++, co++) {
+		if (!hashcmp(co->sha1, sha1))
+			return co;
+	}
+	return NULL;
+}
+
+int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
+		      unsigned char *sha1)
+{
+	struct cached_object *co;
+
+	hash_sha1_file(buf, len, typename(type), sha1);
+	if (has_sha1_file(sha1) || find_cached_object(sha1))
+		return 0;
+	if (cached_object_alloc <= cached_object_nr) {
+		cached_object_alloc = alloc_nr(cached_object_alloc);
+		cached_objects = xrealloc(cached_objects,
+					  sizeof(*cached_objects) *
+					  cached_object_alloc);
+	}
+	co = &cached_objects[cached_object_nr++];
+	co->size = len;
+	co->type = type;
+	co->buf = xmalloc(len);
+	memcpy(co->buf, buf, len);
+	hashcpy(co->sha1, sha1);
+	return 0;
+}
+
+void *read_sha1_file(const unsigned char *sha1, enum object_type *type,
+		     unsigned long *size)
 {
 	unsigned long mapsize;
 	void *map, *buf;
+	struct cached_object *co;
+
+	co = find_cached_object(sha1);
+	if (co) {
+		buf = xmalloc(co->size + 1);
+		memcpy(buf, co->buf, co->size);
+		((char*)buf)[co->size] = 0;
+		*type = co->type;
+		*size = co->size;
+		return buf;
+	}
 
 	buf = read_packed_sha1(sha1, type, size);
 	if (buf)
@@ -1494,33 +1580,34 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size
 }
 
 void *read_object_with_reference(const unsigned char *sha1,
-				 const char *required_type,
+				 const char *required_type_name,
 				 unsigned long *size,
 				 unsigned char *actual_sha1_return)
 {
-	char type[20];
+	enum object_type type, required_type;
 	void *buffer;
 	unsigned long isize;
 	unsigned char actual_sha1[20];
 
+	required_type = type_from_string(required_type_name);
 	hashcpy(actual_sha1, sha1);
 	while (1) {
 		int ref_length = -1;
 		const char *ref_type = NULL;
 
-		buffer = read_sha1_file(actual_sha1, type, &isize);
+		buffer = read_sha1_file(actual_sha1, &type, &isize);
 		if (!buffer)
 			return NULL;
-		if (!strcmp(type, required_type)) {
+		if (type == required_type) {
 			*size = isize;
 			if (actual_sha1_return)
 				hashcpy(actual_sha1_return, actual_sha1);
 			return buffer;
 		}
 		/* Handle references */
-		else if (!strcmp(type, commit_type))
+		else if (type == OBJ_COMMIT)
 			ref_type = "tree ";
-		else if (!strcmp(type, tag_type))
+		else if (type == OBJ_TAG)
 			ref_type = "object ";
 		else {
 			free(buffer);
@@ -1541,12 +1628,12 @@ void *read_object_with_reference(const unsigned char *sha1,
 
 static void write_sha1_file_prepare(void *buf, unsigned long len,
                                     const char *type, unsigned char *sha1,
-                                    unsigned char *hdr, int *hdrlen)
+                                    char *hdr, int *hdrlen)
 {
 	SHA_CTX c;
 
 	/* Generate the header */
-	*hdrlen = sprintf((char *)hdr, "%s %lu", type, len)+1;
+	*hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
 
 	/* Sha1.. */
 	SHA1_Init(&c);
@@ -1653,33 +1740,24 @@ static int write_binary_header(unsigned char *hdr, enum object_type type, unsign
 
 static void setup_object_header(z_stream *stream, const char *type, unsigned long len)
 {
-	int obj_type, hdr;
+	int obj_type, hdrlen;
 
 	if (use_legacy_headers) {
 		while (deflate(stream, 0) == Z_OK)
 			/* nothing */;
 		return;
 	}
-	if (!strcmp(type, blob_type))
-		obj_type = OBJ_BLOB;
-	else if (!strcmp(type, tree_type))
-		obj_type = OBJ_TREE;
-	else if (!strcmp(type, commit_type))
-		obj_type = OBJ_COMMIT;
-	else if (!strcmp(type, tag_type))
-		obj_type = OBJ_TAG;
-	else
-		die("trying to generate bogus object of type '%s'", type);
-	hdr = write_binary_header(stream->next_out, obj_type, len);
-	stream->total_out = hdr;
-	stream->next_out += hdr;
-	stream->avail_out -= hdr;
+	obj_type = type_from_string(type);
+	hdrlen = write_binary_header(stream->next_out, obj_type, len);
+	stream->total_out = hdrlen;
+	stream->next_out += hdrlen;
+	stream->avail_out -= hdrlen;
 }
 
 int hash_sha1_file(void *buf, unsigned long len, const char *type,
                    unsigned char *sha1)
 {
-	unsigned char hdr[50];
+	char hdr[32];
 	int hdrlen;
 	write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
 	return 0;
@@ -1693,7 +1771,7 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	unsigned char sha1[20];
 	char *filename;
 	static char tmpfile[PATH_MAX];
-	unsigned char hdr[50];
+	char hdr[32];
 	int fd, hdrlen;
 
 	/* Normally if we have it in the pack then we do not bother writing
@@ -1740,7 +1818,7 @@ int write_sha1_file(void *buf, unsigned long len, const char *type, unsigned cha
 	stream.avail_out = size;
 
 	/* First header.. */
-	stream.next_in = hdr;
+	stream.next_in = (unsigned char *)hdr;
 	stream.avail_in = hdrlen;
 	setup_object_header(&stream, type, len);
 
@@ -1771,17 +1849,17 @@ static void *repack_object(const unsigned char *sha1, unsigned long *objsize)
 	z_stream stream;
 	unsigned char *unpacked;
 	unsigned long len;
-	char type[20];
-	char hdr[50];
+	enum object_type type;
+	char hdr[32];
 	int hdrlen;
 	void *buf;
 
 	/* need to unpack and recompress it by itself */
-	unpacked = read_packed_sha1(sha1, type, &len);
+	unpacked = read_packed_sha1(sha1, &type, &len);
 	if (!unpacked)
 		error("cannot read sha1_file for %s", sha1_to_hex(sha1));
 
-	hdrlen = sprintf(hdr, "%s %lu", type, len) + 1;
+	hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
 
 	/* Set it up */
 	memset(&stream, 0, sizeof(stream));
@@ -1991,23 +2069,43 @@ int index_pipe(unsigned char *sha1, int fd, const char *type, int write_object)
 	return ret;
 }
 
-int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object, const char *type)
+int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
+	     enum object_type type, const char *path)
 {
-	unsigned long size = st->st_size;
-	void *buf;
-	int ret;
+	size_t size = xsize_t(st->st_size);
+	void *buf = NULL;
+	int ret, re_allocated = 0;
 
-	buf = "";
 	if (size)
 		buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
 	close(fd);
 
 	if (!type)
-		type = blob_type;
+		type = OBJ_BLOB;
+
+	/*
+	 * Convert blobs to git internal format
+	 */
+	if ((type == OBJ_BLOB) && S_ISREG(st->st_mode)) {
+		unsigned long nsize = size;
+		char *nbuf = buf;
+		if (convert_to_git(path, &nbuf, &nsize)) {
+			if (size)
+				munmap(buf, size);
+			size = nsize;
+			buf = nbuf;
+			re_allocated = 1;
+		}
+	}
+
 	if (write_object)
-		ret = write_sha1_file(buf, size, type, sha1);
+		ret = write_sha1_file(buf, size, typename(type), sha1);
 	else
-		ret = hash_sha1_file(buf, size, type, sha1);
+		ret = hash_sha1_file(buf, size, typename(type), sha1);
+	if (re_allocated) {
+		free(buf);
+		return ret;
+	}
 	if (size)
 		munmap(buf, size);
 	return ret;
@@ -2017,6 +2115,7 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 {
 	int fd;
 	char *target;
+	size_t len;
 
 	switch (st->st_mode & S_IFMT) {
 	case S_IFREG:
@@ -2024,21 +2123,22 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 		if (fd < 0)
 			return error("open(\"%s\"): %s", path,
 				     strerror(errno));
-		if (index_fd(sha1, fd, st, write_object, NULL) < 0)
+		if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path) < 0)
 			return error("%s: failed to insert into database",
 				     path);
 		break;
 	case S_IFLNK:
-		target = xmalloc(st->st_size+1);
-		if (readlink(path, target, st->st_size+1) != st->st_size) {
+		len = xsize_t(st->st_size);
+		target = xmalloc(len + 1);
+		if (readlink(path, target, len + 1) != st->st_size) {
 			char *errstr = strerror(errno);
 			free(target);
 			return error("readlink(\"%s\"): %s", path,
 			             errstr);
 		}
 		if (!write_object)
-			hash_sha1_file(target, st->st_size, blob_type, sha1);
-		else if (write_sha1_file(target, st->st_size, blob_type, sha1))
+			hash_sha1_file(target, len, blob_type, sha1);
+		else if (write_sha1_file(target, len, blob_type, sha1))
 			return error("%s: failed to insert into database",
 				     path);
 		free(target);
@@ -2048,3 +2148,24 @@ int index_path(unsigned char *sha1, const char *path, struct stat *st, int write
 	}
 	return 0;
 }
+
+int read_pack_header(int fd, struct pack_header *header)
+{
+	char *c = (char*)header;
+	ssize_t remaining = sizeof(struct pack_header);
+	do {
+		ssize_t r = xread(fd, c, remaining);
+		if (r <= 0)
+			/* "eof before pack header was fully read" */
+			return PH_ERROR_EOF;
+		remaining -= r;
+		c += r;
+	} while (remaining > 0);
+	if (header->hdr_signature != htonl(PACK_SIGNATURE))
+		/* "protocol error (pack signature mismatch detected)" */
+		return PH_ERROR_PACK_SIGNATURE;
+	if (!pack_version_ok(header->hdr_version))
+		/* "protocol error (pack version unsupported)" */
+		return PH_ERROR_PROTOCOL;
+	return 0;
+}