[PATCH v3 0/9] Large file support for git-archive

[PATCH v3 0/9] Large file support for git-archive

[Nguyễn Thái Ngọc Duy]

Compared to v2 [1], this series reworks the large file support patch
for tar and makes use of test_config.

[1] http://thread.gmane.org/gmane.comp.version-control.git/196803

Nguyễn Thái Ngọc Duy (4):
  archive-tar: turn write_tar_entry into blob-writing only
  archive-tar: unindent write_tar_entry by one level
  archive: delegate blob reading to backend
  archive-tar: stream large blobs to tar file

René Scharfe (5):
  streaming: void pointer instead of char pointer
  archive-zip: remove uncompressed_size
  archive-zip: factor out helpers for writing sizes and CRC
  archive-zip: streaming for stored files
  archive-zip: streaming for deflated files

 archive-tar.c       |  207 +++++++++++++++++++++++++++++++++++---------------
 archive-zip.c       |  200 +++++++++++++++++++++++++++++++++++++++++++------
 archive.c           |   28 +++----
 archive.h           |   10 ++-
 streaming.c         |    2 +-
 streaming.h         |    2 +-
 t/t1050-large.sh    |   12 +++
 t/t5000-tar-tree.sh |   19 +++++
 8 files changed, 375 insertions(+), 105 deletions(-)

-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 1/9] streaming: void pointer instead of char pointer

[Nguyễn Thái Ngọc Duy]

From: René Scharfe <rene.scharfe@lsrfire.ath.cx>

Allow any kind of buffer to be fed to read_istream() without an explicit
cast by making it's buf argument a void pointer.  It's about arbitrary
data, not only characters.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 streaming.c |    2 +-
 streaming.h |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/streaming.c b/streaming.c
index 7e7ee2b..3a3cd12 100644
--- a/streaming.c
+++ b/streaming.c
@@ -99,7 +99,7 @@ int close_istream(struct git_istream *st)
 	return r;
 }
 
-ssize_t read_istream(struct git_istream *st, char *buf, size_t sz)
+ssize_t read_istream(struct git_istream *st, void *buf, size_t sz)
 {
 	return st->vtbl->read(st, buf, sz);
 }
diff --git a/streaming.h b/streaming.h
index 3e82770..1d05c2a 100644
--- a/streaming.h
+++ b/streaming.h
@@ -10,7 +10,7 @@ struct git_istream;
 
 extern struct git_istream *open_istream(const unsigned char *, enum object_type *, unsigned long *, struct stream_filter *);
 extern int close_istream(struct git_istream *);
-extern ssize_t read_istream(struct git_istream *, char *, size_t);
+extern ssize_t read_istream(struct git_istream *, void *, size_t);
 
 extern int stream_blob_to_fd(int fd, const unsigned char *, struct stream_filter *, int can_seek);
 
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 2/9] archive-tar: turn write_tar_entry into blob-writing only

[Nguyễn Thái Ngọc Duy]

Before this patch write_tar_entry() can:

 - write global header
   by write_global_extended_header() calling write_tar_entry with
   with both sha1 and path == NULL

 - write extended header for symlinks, by write_tar_entry() calling
   itself with sha1 != NULL and path == NULL

 - write a normal blob. In this case both sha1 and path are valid.

After this patch, the first two call sites are modified to write the
header without calling write_tar_entry(). The function is now for
writing blobs only. This simplifies handling when write_tar_entry()
learns about large blobs.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-tar.c |   78 ++++++++++++++++++++++++++++++++++++++-------------------
 1 files changed, 52 insertions(+), 26 deletions(-)

diff --git a/archive-tar.c b/archive-tar.c
index 20af005..1727ab9 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -123,6 +123,43 @@ static size_t get_path_prefix(const char *path, size_t pathlen, size_t maxlen)
 	return i;
 }
 
+static void prepare_header(struct archiver_args *args,
+			   struct ustar_header *header,
+			   unsigned int mode, unsigned long size)
+{
+	sprintf(header->mode, "%07o", mode & 07777);
+	sprintf(header->size, "%011lo", S_ISREG(mode) ? size : 0);
+	sprintf(header->mtime, "%011lo", (unsigned long) args->time);
+
+	sprintf(header->uid, "%07o", 0);
+	sprintf(header->gid, "%07o", 0);
+	strlcpy(header->uname, "root", sizeof(header->uname));
+	strlcpy(header->gname, "root", sizeof(header->gname));
+	sprintf(header->devmajor, "%07o", 0);
+	sprintf(header->devminor, "%07o", 0);
+
+	memcpy(header->magic, "ustar", 6);
+	memcpy(header->version, "00", 2);
+
+	sprintf(header->chksum, "%07o", ustar_header_chksum(header));
+}
+
+static int write_extended_header(struct archiver_args *args,
+				 const unsigned char *sha1,
+				 const void *buffer, unsigned long size)
+{
+	struct ustar_header header;
+	unsigned int mode;
+	memset(&header, 0, sizeof(header));
+	*header.typeflag = TYPEFLAG_EXT_HEADER;
+	mode = 0100666;
+	sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1));
+	prepare_header(args, &header, mode, size);
+	write_blocked(&header, sizeof(header));
+	write_blocked(buffer, size);
+	return 0;
+}
+
 static int write_tar_entry(struct archiver_args *args,
 		const unsigned char *sha1, const char *path, size_t pathlen,
 		unsigned int mode, void *buffer, unsigned long size)
@@ -134,13 +171,9 @@ static int write_tar_entry(struct archiver_args *args,
 	memset(&header, 0, sizeof(header));
 
 	if (!sha1) {
-		*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
-		mode = 0100666;
-		strcpy(header.name, "pax_global_header");
+		die("BUG: sha1 == NULL is not supported");
 	} else if (!path) {
-		*header.typeflag = TYPEFLAG_EXT_HEADER;
-		mode = 0100666;
-		sprintf(header.name, "%s.paxheader", sha1_to_hex(sha1));
+		die("BUG: path == NULL is not supported");
 	} else {
 		if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
 			*header.typeflag = TYPEFLAG_DIR;
@@ -182,25 +215,11 @@ static int write_tar_entry(struct archiver_args *args,
 			memcpy(header.linkname, buffer, size);
 	}
 
-	sprintf(header.mode, "%07o", mode & 07777);
-	sprintf(header.size, "%011lo", S_ISREG(mode) ? size : 0);
-	sprintf(header.mtime, "%011lo", (unsigned long) args->time);
-
-	sprintf(header.uid, "%07o", 0);
-	sprintf(header.gid, "%07o", 0);
-	strlcpy(header.uname, "root", sizeof(header.uname));
-	strlcpy(header.gname, "root", sizeof(header.gname));
-	sprintf(header.devmajor, "%07o", 0);
-	sprintf(header.devminor, "%07o", 0);
-
-	memcpy(header.magic, "ustar", 6);
-	memcpy(header.version, "00", 2);
-
-	sprintf(header.chksum, "%07o", ustar_header_chksum(&header));
+	prepare_header(args, &header, mode, size);
 
 	if (ext_header.len > 0) {
-		err = write_tar_entry(args, sha1, NULL, 0, 0, ext_header.buf,
-				ext_header.len);
+		err = write_extended_header(args, sha1, ext_header.buf,
+					    ext_header.len);
 		if (err)
 			return err;
 	}
@@ -215,11 +234,18 @@ static int write_global_extended_header(struct archiver_args *args)
 {
 	const unsigned char *sha1 = args->commit_sha1;
 	struct strbuf ext_header = STRBUF_INIT;
-	int err;
+	struct ustar_header header;
+	unsigned int mode;
+	int err = 0;
 
 	strbuf_append_ext_header(&ext_header, "comment", sha1_to_hex(sha1), 40);
-	err = write_tar_entry(args, NULL, NULL, 0, 0, ext_header.buf,
-			ext_header.len);
+	memset(&header, 0, sizeof(header));
+	*header.typeflag = TYPEFLAG_GLOBAL_HEADER;
+	mode = 0100666;
+	strcpy(header.name, "pax_global_header");
+	prepare_header(args, &header, mode, ext_header.len);
+	write_blocked(&header, sizeof(header));
+	write_blocked(ext_header.buf, ext_header.len);
 	strbuf_release(&ext_header);
 	return err;
 }
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 3/9] archive-tar: unindent write_tar_entry by one level

[Nguyễn Thái Ngọc Duy]

It's used to be

if (!sha1) {
  ...
} else if (!path) {
  ...
} else {
  ...
}

Now that the first two blocks are no-op. We can remove the if/else
skeleton and put the else block back by one indent level.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-tar.c |   56 +++++++++++++++++++++++++-------------------------------
 1 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/archive-tar.c b/archive-tar.c
index 1727ab9..6c8a0bd 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -170,40 +170,34 @@ static int write_tar_entry(struct archiver_args *args,
 
 	memset(&header, 0, sizeof(header));
 
-	if (!sha1) {
-		die("BUG: sha1 == NULL is not supported");
-	} else if (!path) {
-		die("BUG: path == NULL is not supported");
+	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
+		*header.typeflag = TYPEFLAG_DIR;
+		mode = (mode | 0777) & ~tar_umask;
+	} else if (S_ISLNK(mode)) {
+		*header.typeflag = TYPEFLAG_LNK;
+		mode |= 0777;
+	} else if (S_ISREG(mode)) {
+		*header.typeflag = TYPEFLAG_REG;
+		mode = (mode | ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
 	} else {
-		if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
-			*header.typeflag = TYPEFLAG_DIR;
-			mode = (mode | 0777) & ~tar_umask;
-		} else if (S_ISLNK(mode)) {
-			*header.typeflag = TYPEFLAG_LNK;
-			mode |= 0777;
-		} else if (S_ISREG(mode)) {
-			*header.typeflag = TYPEFLAG_REG;
-			mode = (mode | ((mode & 0100) ? 0777 : 0666)) & ~tar_umask;
+		return error("unsupported file mode: 0%o (SHA1: %s)",
+			     mode, sha1_to_hex(sha1));
+	}
+	if (pathlen > sizeof(header.name)) {
+		size_t plen = get_path_prefix(path, pathlen,
+					      sizeof(header.prefix));
+		size_t rest = pathlen - plen - 1;
+		if (plen > 0 && rest <= sizeof(header.name)) {
+			memcpy(header.prefix, path, plen);
+				memcpy(header.name, path + plen + 1, rest);
 		} else {
-			return error("unsupported file mode: 0%o (SHA1: %s)",
-					mode, sha1_to_hex(sha1));
+			sprintf(header.name, "%s.data",
+				sha1_to_hex(sha1));
+			strbuf_append_ext_header(&ext_header, "path",
+						 path, pathlen);
 		}
-		if (pathlen > sizeof(header.name)) {
-			size_t plen = get_path_prefix(path, pathlen,
-					sizeof(header.prefix));
-			size_t rest = pathlen - plen - 1;
-			if (plen > 0 && rest <= sizeof(header.name)) {
-				memcpy(header.prefix, path, plen);
-				memcpy(header.name, path + plen + 1, rest);
-			} else {
-				sprintf(header.name, "%s.data",
-				        sha1_to_hex(sha1));
-				strbuf_append_ext_header(&ext_header, "path",
-						path, pathlen);
-			}
-		} else
-			memcpy(header.name, path, pathlen);
-	}
+	} else
+		memcpy(header.name, path, pathlen);
 
 	if (S_ISLNK(mode) && buffer) {
 		if (size > sizeof(header.linkname)) {
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 4/9] archive: delegate blob reading to backend

[Nguyễn Thái Ngọc Duy]

archive-tar.c and archive-zip.c now perform conversion check, with
help of sha1_file_to_archive() from archive.c

This gives backends more freedom in dealing with (streaming) large
blobs.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-tar.c |   25 +++++++++++++++++++++----
 archive-zip.c |   15 +++++++++++++--
 archive.c     |   28 +++++++++++-----------------
 archive.h     |   10 +++++++++-
 4 files changed, 54 insertions(+), 24 deletions(-)

diff --git a/archive-tar.c b/archive-tar.c
index 6c8a0bd..3be0cdf 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -161,11 +161,15 @@ static int write_extended_header(struct archiver_args *args,
 }
 
 static int write_tar_entry(struct archiver_args *args,
-		const unsigned char *sha1, const char *path, size_t pathlen,
-		unsigned int mode, void *buffer, unsigned long size)
+			   const unsigned char *sha1,
+			   const char *path, size_t pathlen,
+			   unsigned int mode)
 {
 	struct ustar_header header;
 	struct strbuf ext_header = STRBUF_INIT;
+	unsigned int old_mode = mode;
+	unsigned long size;
+	void *buffer;
 	int err = 0;
 
 	memset(&header, 0, sizeof(header));
@@ -199,7 +203,17 @@ static int write_tar_entry(struct archiver_args *args,
 	} else
 		memcpy(header.name, path, pathlen);
 
-	if (S_ISLNK(mode) && buffer) {
+	if (S_ISLNK(mode) || S_ISREG(mode)) {
+		enum object_type type;
+		buffer = sha1_file_to_archive(args, path, sha1, old_mode, &type, &size);
+		if (!buffer)
+			return error("cannot read %s", sha1_to_hex(sha1));
+	} else {
+		buffer = NULL;
+		size = 0;
+	}
+
+	if (S_ISLNK(mode)) {
 		if (size > sizeof(header.linkname)) {
 			sprintf(header.linkname, "see %s.paxheader",
 			        sha1_to_hex(sha1));
@@ -214,13 +228,16 @@ static int write_tar_entry(struct archiver_args *args,
 	if (ext_header.len > 0) {
 		err = write_extended_header(args, sha1, ext_header.buf,
 					    ext_header.len);
-		if (err)
+		if (err) {
+			free(buffer);
 			return err;
+		}
 	}
 	strbuf_release(&ext_header);
 	write_blocked(&header, sizeof(header));
 	if (S_ISREG(mode) && buffer && size > 0)
 		write_blocked(buffer, size);
+	free(buffer);
 	return err;
 }
 
diff --git a/archive-zip.c b/archive-zip.c
index 02d1f37..716cc42 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -121,8 +121,9 @@ static void *zlib_deflate(void *data, unsigned long size,
 }
 
 static int write_zip_entry(struct archiver_args *args,
-		const unsigned char *sha1, const char *path, size_t pathlen,
-		unsigned int mode, void *buffer, unsigned long size)
+			   const unsigned char *sha1,
+			   const char *path, size_t pathlen,
+			   unsigned int mode)
 {
 	struct zip_local_header header;
 	struct zip_dir_header dirent;
@@ -134,6 +135,8 @@ static int write_zip_entry(struct archiver_args *args,
 	int method;
 	unsigned char *out;
 	void *deflated = NULL;
+	void *buffer;
+	unsigned long size;
 
 	crc = crc32(0, NULL, 0);
 
@@ -148,7 +151,14 @@ static int write_zip_entry(struct archiver_args *args,
 		out = NULL;
 		uncompressed_size = 0;
 		compressed_size = 0;
+		buffer = NULL;
+		size = 0;
 	} else if (S_ISREG(mode) || S_ISLNK(mode)) {
+		enum object_type type;
+		buffer = sha1_file_to_archive(args, path, sha1, mode, &type, &size);
+		if (!buffer)
+			return error("cannot read %s", sha1_to_hex(sha1));
+
 		method = 0;
 		attr2 = S_ISLNK(mode) ? ((mode | 0777) << 16) :
 			(mode & 0111) ? ((mode) << 16) : 0;
@@ -229,6 +239,7 @@ static int write_zip_entry(struct archiver_args *args,
 	}
 
 	free(deflated);
+	free(buffer);
 
 	return 0;
 }
diff --git a/archive.c b/archive.c
index 1ee837d..cd083ea 100644
--- a/archive.c
+++ b/archive.c
@@ -59,12 +59,15 @@ static void format_subst(const struct commit *commit,
 	free(to_free);
 }
 
-static void *sha1_file_to_archive(const char *path, const unsigned char *sha1,
-		unsigned int mode, enum object_type *type,
-		unsigned long *sizep, const struct commit *commit)
+void *sha1_file_to_archive(const struct archiver_args *args,
+			   const char *path, const unsigned char *sha1,
+			   unsigned int mode, enum object_type *type,
+			   unsigned long *sizep)
 {
 	void *buffer;
+	const struct commit *commit = args->convert ? args->commit : NULL;
 
+	path += args->baselen;
 	buffer = read_sha1_file(sha1, type, sizep);
 	if (buffer && S_ISREG(mode)) {
 		struct strbuf buf = STRBUF_INIT;
@@ -109,12 +112,9 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 	write_archive_entry_fn_t write_entry = c->write_entry;
 	struct git_attr_check check[2];
 	const char *path_without_prefix;
-	int convert = 0;
 	int err;
-	enum object_type type;
-	unsigned long size;
-	void *buffer;
 
+	args->convert = 0;
 	strbuf_reset(&path);
 	strbuf_grow(&path, PATH_MAX);
 	strbuf_add(&path, args->base, args->baselen);
@@ -126,28 +126,22 @@ static int write_archive_entry(const unsigned char *sha1, const char *base,
 	if (!git_check_attr(path_without_prefix, ARRAY_SIZE(check), check)) {
 		if (ATTR_TRUE(check[0].value))
 			return 0;
-		convert = ATTR_TRUE(check[1].value);
+		args->convert = ATTR_TRUE(check[1].value);
 	}
 
 	if (S_ISDIR(mode) || S_ISGITLINK(mode)) {
 		strbuf_addch(&path, '/');
 		if (args->verbose)
 			fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
-		err = write_entry(args, sha1, path.buf, path.len, mode, NULL, 0);
+		err = write_entry(args, sha1, path.buf, path.len, mode);
 		if (err)
 			return err;
 		return (S_ISDIR(mode) ? READ_TREE_RECURSIVE : 0);
 	}
 
-	buffer = sha1_file_to_archive(path_without_prefix, sha1, mode,
-			&type, &size, convert ? args->commit : NULL);
-	if (!buffer)
-		return error("cannot read %s", sha1_to_hex(sha1));
 	if (args->verbose)
 		fprintf(stderr, "%.*s\n", (int)path.len, path.buf);
-	err = write_entry(args, sha1, path.buf, path.len, mode, buffer, size);
-	free(buffer);
-	return err;
+	return write_entry(args, sha1, path.buf, path.len, mode);
 }
 
 int write_archive_entries(struct archiver_args *args,
@@ -167,7 +161,7 @@ int write_archive_entries(struct archiver_args *args,
 		if (args->verbose)
 			fprintf(stderr, "%.*s\n", (int)len, args->base);
 		err = write_entry(args, args->tree->object.sha1, args->base,
-				len, 040777, NULL, 0);
+				  len, 040777);
 		if (err)
 			return err;
 	}
diff --git a/archive.h b/archive.h
index 2b0884f..895afcd 100644
--- a/archive.h
+++ b/archive.h
@@ -11,6 +11,7 @@ struct archiver_args {
 	const char **pathspec;
 	unsigned int verbose : 1;
 	unsigned int worktree_attributes : 1;
+	unsigned int convert : 1;
 	int compression_level;
 };
 
@@ -27,11 +28,18 @@ extern void register_archiver(struct archiver *);
 extern void init_tar_archiver(void);
 extern void init_zip_archiver(void);
 
-typedef int (*write_archive_entry_fn_t)(struct archiver_args *args, const unsigned char *sha1, const char *path, size_t pathlen, unsigned int mode, void *buffer, unsigned long size);
+typedef int (*write_archive_entry_fn_t)(struct archiver_args *args,
+					const unsigned char *sha1,
+					const char *path, size_t pathlen,
+					unsigned int mode);
 
 extern int write_archive_entries(struct archiver_args *args, write_archive_entry_fn_t write_entry);
 extern int write_archive(int argc, const char **argv, const char *prefix, int setup_prefix, const char *name_hint, int remote);
 
 const char *archive_format_from_filename(const char *filename);
+extern void *sha1_file_to_archive(const struct archiver_args *args,
+				  const char *path, const unsigned char *sha1,
+				  unsigned int mode, enum object_type *type,
+				  unsigned long *sizep);
 
 #endif	/* ARCHIVE_H */
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 5/9] archive-tar: stream large blobs to tar file

[Nguyễn Thái Ngọc Duy]

t5000 verifies output while t1050 makes sure the command always
respects core.bigfilethreshold

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-tar.c       |   56 ++++++++++++++++++++++++++++++++++++++++++++++----
 t/t1050-large.sh    |    4 +++
 t/t5000-tar-tree.sh |    6 +++++
 3 files changed, 61 insertions(+), 5 deletions(-)

diff --git a/archive-tar.c b/archive-tar.c
index 3be0cdf..93387ea 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -4,6 +4,7 @@
 #include "cache.h"
 #include "tar.h"
 #include "archive.h"
+#include "streaming.h"
 #include "run-command.h"
 
 #define RECORDSIZE	(512)
@@ -30,10 +31,9 @@ static void write_if_needed(void)
  * queues up writes, so that all our write(2) calls write exactly one
  * full block; pads writes to RECORDSIZE
  */
-static void write_blocked(const void *data, unsigned long size)
+static void do_write_blocked(const void *data, unsigned long size)
 {
 	const char *buf = data;
-	unsigned long tail;
 
 	if (offset) {
 		unsigned long chunk = BLOCKSIZE - offset;
@@ -54,6 +54,11 @@ static void write_blocked(const void *data, unsigned long size)
 		memcpy(block + offset, buf, size);
 		offset += size;
 	}
+}
+
+static void finish_record(void)
+{
+	unsigned long tail;
 	tail = offset % RECORDSIZE;
 	if (tail)  {
 		memset(block + offset, 0, RECORDSIZE - tail);
@@ -62,6 +67,12 @@ static void write_blocked(const void *data, unsigned long size)
 	write_if_needed();
 }
 
+static void write_blocked(const void *data, unsigned long size)
+{
+	do_write_blocked(data, size);
+	finish_record();
+}
+
 /*
  * The end of tar archives is marked by 2*512 nul bytes and after that
  * follows the rest of the block (if any).
@@ -78,6 +89,33 @@ static void write_trailer(void)
 }
 
 /*
+ * queues up writes, so that all our write(2) calls write exactly one
+ * full block; pads writes to RECORDSIZE
+ */
+static int stream_blocked(const unsigned char *sha1)
+{
+	struct git_istream *st;
+	enum object_type type;
+	unsigned long sz;
+	char buf[BLOCKSIZE];
+	ssize_t readlen;
+
+	st = open_istream(sha1, &type, &sz, NULL);
+	if (!st)
+		return error("cannot stream blob %s", sha1_to_hex(sha1));
+	for (;;) {
+		readlen = read_istream(st, buf, sizeof(buf));
+		if (readlen <= 0)
+			break;
+		do_write_blocked(buf, readlen);
+	}
+	close_istream(st);
+	if (!readlen)
+		finish_record();
+	return readlen;
+}
+
+/*
  * pax extended header records have the format "%u %s=%s\n".  %u contains
  * the size of the whole string (including the %u), the first %s is the
  * keyword, the second one is the value.  This function constructs such a
@@ -203,7 +241,11 @@ static int write_tar_entry(struct archiver_args *args,
 	} else
 		memcpy(header.name, path, pathlen);
 
-	if (S_ISLNK(mode) || S_ISREG(mode)) {
+	if (S_ISREG(mode) && !args->convert &&
+	    sha1_object_info(sha1, &size) == OBJ_BLOB &&
+	    size > big_file_threshold)
+		buffer = NULL;
+	else if (S_ISLNK(mode) || S_ISREG(mode)) {
 		enum object_type type;
 		buffer = sha1_file_to_archive(args, path, sha1, old_mode, &type, &size);
 		if (!buffer)
@@ -235,8 +277,12 @@ static int write_tar_entry(struct archiver_args *args,
 	}
 	strbuf_release(&ext_header);
 	write_blocked(&header, sizeof(header));
-	if (S_ISREG(mode) && buffer && size > 0)
-		write_blocked(buffer, size);
+	if (S_ISREG(mode) && size > 0) {
+		if (buffer)
+			write_blocked(buffer, size);
+		else
+			err = stream_blocked(sha1);
+	}
 	free(buffer);
 	return err;
 }
diff --git a/t/t1050-large.sh b/t/t1050-large.sh
index 4d127f1..fe47554 100755
--- a/t/t1050-large.sh
+++ b/t/t1050-large.sh
@@ -134,4 +134,8 @@ test_expect_success 'repack' '
 	git repack -ad
 '
 
+test_expect_success 'tar achiving' '
+	git archive --format=tar HEAD >/dev/null
+'
+
 test_done
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 527c9e7..d9b997f 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -84,6 +84,12 @@ test_expect_success \
     'git archive vs. git tar-tree' \
     'test_cmp b.tar b2.tar'
 
+test_expect_success 'git archive on large files' '
+    test_config core.bigfilethreshold 1 &&
+    git archive HEAD >b3.tar &&
+    test_cmp b.tar b3.tar
+'
+
 test_expect_success \
     'git archive in a bare repo' \
     '(cd bare.git && git archive HEAD) >b3.tar'
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 6/9] archive-zip: remove uncompressed_size

[Nguyễn Thái Ngọc Duy]

From: René Scharfe <rene.scharfe@lsrfire.ath.cx>

We only need size and compressed_size.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-zip.c |    8 +++-----
 1 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/archive-zip.c b/archive-zip.c
index 716cc42..400ba38 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -129,7 +129,6 @@ static int write_zip_entry(struct archiver_args *args,
 	struct zip_dir_header dirent;
 	unsigned long attr2;
 	unsigned long compressed_size;
-	unsigned long uncompressed_size;
 	unsigned long crc;
 	unsigned long direntsize;
 	int method;
@@ -149,7 +148,7 @@ static int write_zip_entry(struct archiver_args *args,
 		method = 0;
 		attr2 = 16;
 		out = NULL;
-		uncompressed_size = 0;
+		size = 0;
 		compressed_size = 0;
 		buffer = NULL;
 		size = 0;
@@ -166,7 +165,6 @@ static int write_zip_entry(struct archiver_args *args,
 			method = 8;
 		crc = crc32(crc, buffer, size);
 		out = buffer;
-		uncompressed_size = size;
 		compressed_size = size;
 	} else {
 		return error("unsupported file mode: 0%o (SHA1: %s)", mode,
@@ -204,7 +202,7 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(dirent.mdate, zip_date);
 	copy_le32(dirent.crc32, crc);
 	copy_le32(dirent.compressed_size, compressed_size);
-	copy_le32(dirent.size, uncompressed_size);
+	copy_le32(dirent.size, size);
 	copy_le16(dirent.filename_length, pathlen);
 	copy_le16(dirent.extra_length, 0);
 	copy_le16(dirent.comment_length, 0);
@@ -226,7 +224,7 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(header.mdate, zip_date);
 	copy_le32(header.crc32, crc);
 	copy_le32(header.compressed_size, compressed_size);
-	copy_le32(header.size, uncompressed_size);
+	copy_le32(header.size, size);
 	copy_le16(header.filename_length, pathlen);
 	copy_le16(header.extra_length, 0);
 	write_or_die(1, &header, ZIP_LOCAL_HEADER_SIZE);
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 7/9] archive-zip: factor out helpers for writing sizes and CRC

[Nguyễn Thái Ngọc Duy]

From: René Scharfe <rene.scharfe@lsrfire.ath.cx>

We're going to reuse them soon for streaming.  Also, update the ZIP
directory only at the very end, which will also make streaming easier.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-zip.c |   39 ++++++++++++++++++++++++++++-----------
 1 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/archive-zip.c b/archive-zip.c
index 400ba38..678569a 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -120,6 +120,26 @@ static void *zlib_deflate(void *data, unsigned long size,
 	return buffer;
 }
 
+static void set_zip_dir_data_desc(struct zip_dir_header *header,
+				  unsigned long size,
+				  unsigned long compressed_size,
+				  unsigned long crc)
+{
+	copy_le32(header->crc32, crc);
+	copy_le32(header->compressed_size, compressed_size);
+	copy_le32(header->size, size);
+}
+
+static void set_zip_header_data_desc(struct zip_local_header *header,
+				     unsigned long size,
+				     unsigned long compressed_size,
+				     unsigned long crc)
+{
+	copy_le32(header->crc32, crc);
+	copy_le32(header->compressed_size, compressed_size);
+	copy_le32(header->size, size);
+}
+
 static int write_zip_entry(struct archiver_args *args,
 			   const unsigned char *sha1,
 			   const char *path, size_t pathlen,
@@ -200,9 +220,7 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(dirent.compression_method, method);
 	copy_le16(dirent.mtime, zip_time);
 	copy_le16(dirent.mdate, zip_date);
-	copy_le32(dirent.crc32, crc);
-	copy_le32(dirent.compressed_size, compressed_size);
-	copy_le32(dirent.size, size);
+	set_zip_dir_data_desc(&dirent, size, compressed_size, crc);
 	copy_le16(dirent.filename_length, pathlen);
 	copy_le16(dirent.extra_length, 0);
 	copy_le16(dirent.comment_length, 0);
@@ -210,11 +228,6 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(dirent.attr1, 0);
 	copy_le32(dirent.attr2, attr2);
 	copy_le32(dirent.offset, zip_offset);
-	memcpy(zip_dir + zip_dir_offset, &dirent, ZIP_DIR_HEADER_SIZE);
-	zip_dir_offset += ZIP_DIR_HEADER_SIZE;
-	memcpy(zip_dir + zip_dir_offset, path, pathlen);
-	zip_dir_offset += pathlen;
-	zip_dir_entries++;
 
 	copy_le32(header.magic, 0x04034b50);
 	copy_le16(header.version, 10);
@@ -222,9 +235,7 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(header.compression_method, method);
 	copy_le16(header.mtime, zip_time);
 	copy_le16(header.mdate, zip_date);
-	copy_le32(header.crc32, crc);
-	copy_le32(header.compressed_size, compressed_size);
-	copy_le32(header.size, size);
+	set_zip_header_data_desc(&header, size, compressed_size, crc);
 	copy_le16(header.filename_length, pathlen);
 	copy_le16(header.extra_length, 0);
 	write_or_die(1, &header, ZIP_LOCAL_HEADER_SIZE);
@@ -239,6 +250,12 @@ static int write_zip_entry(struct archiver_args *args,
 	free(deflated);
 	free(buffer);
 
+	memcpy(zip_dir + zip_dir_offset, &dirent, ZIP_DIR_HEADER_SIZE);
+	zip_dir_offset += ZIP_DIR_HEADER_SIZE;
+	memcpy(zip_dir + zip_dir_offset, path, pathlen);
+	zip_dir_offset += pathlen;
+	zip_dir_entries++;
+
 	return 0;
 }
 
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 8/9] archive-zip: streaming for stored files

[Nguyễn Thái Ngọc Duy]

From: René Scharfe <rene.scharfe@lsrfire.ath.cx>

Write a data descriptor containing the CRC of the entry and its sizes
after streaming it out.  For simplicity, do that only if we're storing
files (option -0) for now.

t5000 verifies output. t1050 makes sure the command always respects
core.bigfilethreshold

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-zip.c       |   90 ++++++++++++++++++++++++++++++++++++++++++++-------
 t/t1050-large.sh    |    4 ++
 t/t5000-tar-tree.sh |    6 +++
 3 files changed, 88 insertions(+), 12 deletions(-)

diff --git a/archive-zip.c b/archive-zip.c
index 678569a..1c6c39d 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -3,6 +3,7 @@
  */
 #include "cache.h"
 #include "archive.h"
+#include "streaming.h"
 
 static int zip_date;
 static int zip_time;
@@ -15,6 +16,7 @@ static unsigned int zip_dir_offset;
 static unsigned int zip_dir_entries;
 
 #define ZIP_DIRECTORY_MIN_SIZE	(1024 * 1024)
+#define ZIP_STREAM (8)
 
 struct zip_local_header {
 	unsigned char magic[4];
@@ -31,6 +33,14 @@ struct zip_local_header {
 	unsigned char _end[1];
 };
 
+struct zip_data_desc {
+	unsigned char magic[4];
+	unsigned char crc32[4];
+	unsigned char compressed_size[4];
+	unsigned char size[4];
+	unsigned char _end[1];
+};
+
 struct zip_dir_header {
 	unsigned char magic[4];
 	unsigned char creator_version[2];
@@ -70,6 +80,7 @@ struct zip_dir_trailer {
  * we're interested in.
  */
 #define ZIP_LOCAL_HEADER_SIZE	offsetof(struct zip_local_header, _end)
+#define ZIP_DATA_DESC_SIZE	offsetof(struct zip_data_desc, _end)
 #define ZIP_DIR_HEADER_SIZE	offsetof(struct zip_dir_header, _end)
 #define ZIP_DIR_TRAILER_SIZE	offsetof(struct zip_dir_trailer, _end)
 
@@ -120,6 +131,19 @@ static void *zlib_deflate(void *data, unsigned long size,
 	return buffer;
 }
 
+static void write_zip_data_desc(unsigned long size,
+				unsigned long compressed_size,
+				unsigned long crc)
+{
+	struct zip_data_desc trailer;
+
+	copy_le32(trailer.magic, 0x08074b50);
+	copy_le32(trailer.crc32, crc);
+	copy_le32(trailer.compressed_size, compressed_size);
+	copy_le32(trailer.size, size);
+	write_or_die(1, &trailer, ZIP_DATA_DESC_SIZE);
+}
+
 static void set_zip_dir_data_desc(struct zip_dir_header *header,
 				  unsigned long size,
 				  unsigned long compressed_size,
@@ -140,6 +164,8 @@ static void set_zip_header_data_desc(struct zip_local_header *header,
 	copy_le32(header->size, size);
 }
 
+#define STREAM_BUFFER_SIZE (1024 * 16)
+
 static int write_zip_entry(struct archiver_args *args,
 			   const unsigned char *sha1,
 			   const char *path, size_t pathlen,
@@ -155,6 +181,8 @@ static int write_zip_entry(struct archiver_args *args,
 	unsigned char *out;
 	void *deflated = NULL;
 	void *buffer;
+	struct git_istream *stream = NULL;
+	unsigned long flags = 0;
 	unsigned long size;
 
 	crc = crc32(0, NULL, 0);
@@ -173,25 +201,38 @@ static int write_zip_entry(struct archiver_args *args,
 		buffer = NULL;
 		size = 0;
 	} else if (S_ISREG(mode) || S_ISLNK(mode)) {
-		enum object_type type;
-		buffer = sha1_file_to_archive(args, path, sha1, mode, &type, &size);
-		if (!buffer)
-			return error("cannot read %s", sha1_to_hex(sha1));
+		enum object_type type = sha1_object_info(sha1, &size);
 
 		method = 0;
 		attr2 = S_ISLNK(mode) ? ((mode | 0777) << 16) :
 			(mode & 0111) ? ((mode) << 16) : 0;
-		if (S_ISREG(mode) && args->compression_level != 0)
+		if (S_ISREG(mode) && args->compression_level != 0 && size > 0)
 			method = 8;
-		crc = crc32(crc, buffer, size);
-		out = buffer;
 		compressed_size = size;
+
+		if (S_ISREG(mode) && type == OBJ_BLOB && !args->convert &&
+		    size > big_file_threshold && method == 0) {
+			stream = open_istream(sha1, &type, &size, NULL);
+			if (!stream)
+				return error("cannot stream blob %s",
+					     sha1_to_hex(sha1));
+			flags |= ZIP_STREAM;
+			out = buffer = NULL;
+		} else {
+			buffer = sha1_file_to_archive(args, path, sha1, mode,
+						      &type, &size);
+			if (!buffer)
+				return error("cannot read %s",
+					     sha1_to_hex(sha1));
+			crc = crc32(crc, buffer, size);
+			out = buffer;
+		}
 	} else {
 		return error("unsupported file mode: 0%o (SHA1: %s)", mode,
 				sha1_to_hex(sha1));
 	}
 
-	if (method == 8) {
+	if (buffer && method == 8) {
 		deflated = zlib_deflate(buffer, size, args->compression_level,
 				&compressed_size);
 		if (deflated && compressed_size - 6 < size) {
@@ -216,7 +257,7 @@ static int write_zip_entry(struct archiver_args *args,
 	copy_le16(dirent.creator_version,
 		S_ISLNK(mode) || (S_ISREG(mode) && (mode & 0111)) ? 0x0317 : 0);
 	copy_le16(dirent.version, 10);
-	copy_le16(dirent.flags, 0);
+	copy_le16(dirent.flags, flags);
 	copy_le16(dirent.compression_method, method);
 	copy_le16(dirent.mtime, zip_time);
 	copy_le16(dirent.mdate, zip_date);
@@ -231,18 +272,43 @@ static int write_zip_entry(struct archiver_args *args,
 
 	copy_le32(header.magic, 0x04034b50);
 	copy_le16(header.version, 10);
-	copy_le16(header.flags, 0);
+	copy_le16(header.flags, flags);
 	copy_le16(header.compression_method, method);
 	copy_le16(header.mtime, zip_time);
 	copy_le16(header.mdate, zip_date);
-	set_zip_header_data_desc(&header, size, compressed_size, crc);
+	if (flags & ZIP_STREAM)
+		set_zip_header_data_desc(&header, 0, 0, 0);
+	else
+		set_zip_header_data_desc(&header, size, compressed_size, crc);
 	copy_le16(header.filename_length, pathlen);
 	copy_le16(header.extra_length, 0);
 	write_or_die(1, &header, ZIP_LOCAL_HEADER_SIZE);
 	zip_offset += ZIP_LOCAL_HEADER_SIZE;
 	write_or_die(1, path, pathlen);
 	zip_offset += pathlen;
-	if (compressed_size > 0) {
+	if (stream && method == 0) {
+		unsigned char buf[STREAM_BUFFER_SIZE];
+		ssize_t readlen;
+
+		for (;;) {
+			readlen = read_istream(stream, buf, sizeof(buf));
+			if (readlen <= 0)
+				break;
+			crc = crc32(crc, buf, readlen);
+			write_or_die(1, buf, readlen);
+		}
+		close_istream(stream);
+		if (readlen)
+			return readlen;
+
+		compressed_size = size;
+		zip_offset += compressed_size;
+
+		write_zip_data_desc(size, compressed_size, crc);
+		zip_offset += ZIP_DATA_DESC_SIZE;
+
+		set_zip_dir_data_desc(&dirent, size, compressed_size, crc);
+	} else if (compressed_size > 0) {
 		write_or_die(1, out, compressed_size);
 		zip_offset += compressed_size;
 	}
diff --git a/t/t1050-large.sh b/t/t1050-large.sh
index fe47554..9db54b5 100755
--- a/t/t1050-large.sh
+++ b/t/t1050-large.sh
@@ -138,4 +138,8 @@ test_expect_success 'tar achiving' '
 	git archive --format=tar HEAD >/dev/null
 '
 
+test_expect_success 'zip achiving, store only' '
+	git archive --format=zip -0 HEAD >/dev/null
+'
+
 test_done
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index d9b997f..3b54c38 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -244,6 +244,12 @@ test_expect_success UNZIP \
     'validate file contents with prefix' \
     'diff -r a e/prefix/a'
 
+test_expect_success UNZIP 'git archive -0 --format=zip on large files' '
+    test_config core.bigfilethreshold 1 &&
+    git archive -0 --format=zip HEAD >large.zip &&
+    (mkdir large && cd large && $UNZIP ../large.zip)
+'
+
 test_expect_success \
     'git archive --list outside of a git repo' \
     'GIT_DIR=some/non-existing/directory git archive --list'
-- 
1.7.3.1.256.g2539c.dirty

[PATCH v3 9/9] archive-zip: streaming for deflated files

[Nguyễn Thái Ngọc Duy]

From: René Scharfe <rene.scharfe@lsrfire.ath.cx>

After an entry has been streamed out, its CRC and sizes are written as
part of a data descriptor.

For simplicity, we make the buffer for the compressed chunks twice as
big as for the uncompressed ones, to be sure the result fit in even
if deflate makes them bigger.

t5000 verifies output. t1050 makes sure the command always respects
core.bigfilethreshold

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 archive-zip.c       |   64 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 t/t1050-large.sh    |    4 +++
 t/t5000-tar-tree.sh |    7 +++++
 3 files changed, 74 insertions(+), 1 deletions(-)

diff --git a/archive-zip.c b/archive-zip.c
index 1c6c39d..f5af81f 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -211,7 +211,7 @@ static int write_zip_entry(struct archiver_args *args,
 		compressed_size = size;
 
 		if (S_ISREG(mode) && type == OBJ_BLOB && !args->convert &&
-		    size > big_file_threshold && method == 0) {
+		    size > big_file_threshold) {
 			stream = open_istream(sha1, &type, &size, NULL);
 			if (!stream)
 				return error("cannot stream blob %s",
@@ -308,6 +308,68 @@ static int write_zip_entry(struct archiver_args *args,
 		zip_offset += ZIP_DATA_DESC_SIZE;
 
 		set_zip_dir_data_desc(&dirent, size, compressed_size, crc);
+	} else if (stream && method == 8) {
+		unsigned char buf[STREAM_BUFFER_SIZE];
+		ssize_t readlen;
+		git_zstream zstream;
+		int result;
+		size_t out_len;
+		unsigned char compressed[STREAM_BUFFER_SIZE * 2];
+
+		memset(&zstream, 0, sizeof(zstream));
+		git_deflate_init(&zstream, args->compression_level);
+
+		compressed_size = 0;
+		zstream.next_out = compressed;
+		zstream.avail_out = sizeof(compressed);
+
+		for (;;) {
+			readlen = read_istream(stream, buf, sizeof(buf));
+			if (readlen <= 0)
+				break;
+			crc = crc32(crc, buf, readlen);
+
+			zstream.next_in = buf;
+			zstream.avail_in = readlen;
+			result = git_deflate(&zstream, 0);
+			if (result != Z_OK)
+				die("deflate error (%d)", result);
+			out = compressed;
+			if (!compressed_size)
+				out += 2;
+			out_len = zstream.next_out - out;
+
+			if (out_len > 0) {
+				write_or_die(1, out, out_len);
+				compressed_size += out_len;
+				zstream.next_out = compressed;
+				zstream.avail_out = sizeof(compressed);
+			}
+
+		}
+		close_istream(stream);
+		if (readlen)
+			return readlen;
+
+		zstream.next_in = buf;
+		zstream.avail_in = 0;
+		result = git_deflate(&zstream, Z_FINISH);
+		if (result != Z_STREAM_END)
+			die("deflate error (%d)", result);
+
+		git_deflate_end(&zstream);
+		out = compressed;
+		if (!compressed_size)
+			out += 2;
+		out_len = zstream.next_out - out - 4;
+		write_or_die(1, out, out_len);
+		compressed_size += out_len;
+		zip_offset += compressed_size;
+
+		write_zip_data_desc(size, compressed_size, crc);
+		zip_offset += ZIP_DATA_DESC_SIZE;
+
+		set_zip_dir_data_desc(&dirent, size, compressed_size, crc);
 	} else if (compressed_size > 0) {
 		write_or_die(1, out, compressed_size);
 		zip_offset += compressed_size;
diff --git a/t/t1050-large.sh b/t/t1050-large.sh
index 9db54b5..55ed955 100755
--- a/t/t1050-large.sh
+++ b/t/t1050-large.sh
@@ -142,4 +142,8 @@ test_expect_success 'zip achiving, store only' '
 	git archive --format=zip -0 HEAD >/dev/null
 '
 
+test_expect_success 'zip achiving, deflate' '
+	git archive --format=zip HEAD >/dev/null
+'
+
 test_done
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 3b54c38..94f2eba 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -250,6 +250,13 @@ test_expect_success UNZIP 'git archive -0 --format=zip on large files' '
     (mkdir large && cd large && $UNZIP ../large.zip)
 '
 
+test_expect_success UNZIP 'git archive --format=zip on large files' '
+    test_config core.bigfilethreshold 1 &&
+    git archive --format=zip HEAD >large-compressed.zip &&
+    (mkdir large-compressed && cd large-compressed && $UNZIP ../large-compressed.zip) &&
+    test_cmp large-compressed/a/bin/sh large/a/bin/sh
+'
+
 test_expect_success \
     'git archive --list outside of a git repo' \
     'GIT_DIR=some/non-existing/directory git archive --list'
-- 
1.7.3.1.256.g2539c.dirty

[PATCH 10/9] t5000: rationalize unzip tests

[René Scharfe]

Factor out a function for checking the contents of ZIP archives.  It
extracts their contents and compares them to the original files.  This
removes some duplicate code.  Tests that just create archives can lose
their UNZIP prerequisite.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
---
 t/t5000-tar-tree.sh |   81 +++++++++++++++++++++++++--------------------------
 1 file changed, 40 insertions(+), 41 deletions(-)

diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 94f2eba..a5314f6 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -31,6 +31,26 @@ GUNZIP=${GUNZIP:-gzip -d}
 
 SUBSTFORMAT=%H%n
 
+check_zip() {
+	zipfile=$1.zip
+	listfile=$1.lst
+	dir=$1
+	dir_with_prefix=$dir/$2
+
+	test_expect_success UNZIP " extract ZIP archive" "
+		(mkdir $dir && cd $dir && $UNZIP ../$zipfile)
+	"
+
+	test_expect_success UNZIP " validate filenames" "
+		(cd ${dir_with_prefix}a && find .) | sort >$listfile &&
+		test_cmp a.lst $listfile
+	"
+
+	test_expect_success UNZIP " validate file contents" "
+		diff -r a ${dir_with_prefix}a
+	"
+}
+
 test_expect_success \
     'populate workdir' \
     'mkdir a b c &&
@@ -181,10 +201,19 @@ test_expect_success \
       test_cmp a/substfile2 g/prefix/a/substfile2
 '
 
+$UNZIP -v >/dev/null 2>&1
+if [ $? -eq 127 ]; then
+	say "Skipping ZIP tests, because unzip was not found"
+else
+	test_set_prereq UNZIP
+fi
+
 test_expect_success \
     'git archive --format=zip' \
     'git archive --format=zip HEAD >d.zip'
 
+check_zip d
+
 test_expect_success \
     'git archive --format=zip in a bare repo' \
     '(cd bare.git && git archive --format=zip HEAD) >d1.zip'
@@ -207,56 +236,26 @@ test_expect_success 'git archive with --output, override inferred format' '
 	test_cmp b.tar d4.zip
 '
 
-$UNZIP -v >/dev/null 2>&1
-if [ $? -eq 127 ]; then
-	say "Skipping ZIP tests, because unzip was not found"
-else
-	test_set_prereq UNZIP
-fi
-
-test_expect_success UNZIP \
-    'extract ZIP archive' \
-    '(mkdir d && cd d && $UNZIP ../d.zip)'
-
-test_expect_success UNZIP \
-    'validate filenames' \
-    '(cd d/a && find .) | sort >d.lst &&
-     test_cmp a.lst d.lst'
-
-test_expect_success UNZIP \
-    'validate file contents' \
-    'diff -r a d/a'
-
 test_expect_success \
     'git archive --format=zip with prefix' \
     'git archive --format=zip --prefix=prefix/ HEAD >e.zip'
 
-test_expect_success UNZIP \
-    'extract ZIP archive with prefix' \
-    '(mkdir e && cd e && $UNZIP ../e.zip)'
+check_zip e prefix/
 
-test_expect_success UNZIP \
-    'validate filenames with prefix' \
-    '(cd e/prefix/a && find .) | sort >e.lst &&
-     test_cmp a.lst e.lst'
-
-test_expect_success UNZIP \
-    'validate file contents with prefix' \
-    'diff -r a e/prefix/a'
-
-test_expect_success UNZIP 'git archive -0 --format=zip on large files' '
-    test_config core.bigfilethreshold 1 &&
-    git archive -0 --format=zip HEAD >large.zip &&
-    (mkdir large && cd large && $UNZIP ../large.zip)
+test_expect_success 'git archive -0 --format=zip on large files' '
+	test_config core.bigfilethreshold 1 &&
+	git archive -0 --format=zip HEAD >large.zip
 '
 
-test_expect_success UNZIP 'git archive --format=zip on large files' '
-    test_config core.bigfilethreshold 1 &&
-    git archive --format=zip HEAD >large-compressed.zip &&
-    (mkdir large-compressed && cd large-compressed && $UNZIP ../large-compressed.zip) &&
-    test_cmp large-compressed/a/bin/sh large/a/bin/sh
+check_zip large
+
+test_expect_success 'git archive --format=zip on large files' '
+	test_config core.bigfilethreshold 1 &&
+	git archive --format=zip HEAD >large-compressed.zip
 '
 
+check_zip large-compressed
+
 test_expect_success \
     'git archive --list outside of a git repo' \
     'GIT_DIR=some/non-existing/directory git archive --list'