1 files changed, 238 insertions, 43 deletions

diff --git a/archive-zip.c b/archive-zip.c
index cf285044e3..4bde019bce 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -3,6 +3,8 @@
  */
 #include "cache.h"
 #include "archive.h"
+#include "streaming.h"
+#include "utf8.h"
 
 static int zip_date;
 static int zip_time;
@@ -15,6 +17,8 @@ static unsigned int zip_dir_offset;
 static unsigned int zip_dir_entries;
 
 #define ZIP_DIRECTORY_MIN_SIZE	(1024 * 1024)
+#define ZIP_STREAM	(1 <<  3)
+#define ZIP_UTF8	(1 << 11)
 
 struct zip_local_header {
 	unsigned char magic[4];
@@ -31,6 +35,14 @@ 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];
@@ -64,14 +76,26 @@ struct zip_dir_trailer {
 	unsigned char _end[1];
 };
 
+struct zip_extra_mtime {
+	unsigned char magic[2];
+	unsigned char extra_size[2];
+	unsigned char flags[1];
+	unsigned char mtime[4];
+	unsigned char _end[1];
+};
+
 /*
  * On ARM, padding is added at the end of the struct, so a simple
  * sizeof(struct ...) reports two bytes more than the payload size
  * 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)
+#define ZIP_EXTRA_MTIME_SIZE	offsetof(struct zip_extra_mtime, _end)
+#define ZIP_EXTRA_MTIME_PAYLOAD_SIZE \
+	(ZIP_EXTRA_MTIME_SIZE - offsetof(struct zip_extra_mtime, flags))
 
 static void copy_le16(unsigned char *dest, unsigned int n)
 {
@@ -87,17 +111,18 @@ static void copy_le32(unsigned char *dest, unsigned int n)
 	dest[3] = 0xff & (n >> 030);
 }
 
-static void *zlib_deflate(void *data, unsigned long size,
-		int compression_level, unsigned long *compressed_size)
+static void *zlib_deflate_raw(void *data, unsigned long size,
+			      int compression_level,
+			      unsigned long *compressed_size)
 {
-	z_stream stream;
+	git_zstream stream;
 	unsigned long maxsize;
 	void *buffer;
 	int result;
 
 	memset(&stream, 0, sizeof(stream));
-	deflateInit(&stream, compression_level);
-	maxsize = deflateBound(&stream, size);
+	git_deflate_init_raw(&stream, compression_level);
+	maxsize = git_deflate_bound(&stream, size);
 	buffer = xmalloc(maxsize);
 
 	stream.next_in = data;
@@ -106,7 +131,7 @@ static void *zlib_deflate(void *data, unsigned long size,
 	stream.avail_out = maxsize;
 
 	do {
-		result = deflate(&stream, Z_FINISH);
+		result = git_deflate(&stream, Z_FINISH);
 	} while (result == Z_OK);
 
 	if (result != Z_STREAM_END) {
@@ -114,29 +139,87 @@ static void *zlib_deflate(void *data, unsigned long size,
 		return NULL;
 	}
 
-	deflateEnd(&stream);
+	git_deflate_end(&stream);
 	*compressed_size = stream.total_out;
 
 	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,
+				  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 has_only_ascii(const char *s)
+{
+	for (;;) {
+		int c = *s++;
+		if (c == '\0')
+			return 1;
+		if (!isascii(c))
+			return 0;
+	}
+}
+
+#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,
-		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;
+	struct zip_extra_mtime extra;
 	unsigned long attr2;
 	unsigned long compressed_size;
-	unsigned long uncompressed_size;
 	unsigned long crc;
 	unsigned long direntsize;
 	int method;
 	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);
 
+	if (!has_only_ascii(path)) {
+		if (is_utf8(path))
+			flags |= ZIP_UTF8;
+		else
+			warning("Path is not valid UTF-8: %s", path);
+	}
+
 	if (pathlen > 0xffff) {
 		return error("path too long (%d chars, SHA1: %s): %s",
 				(int)pathlen, sha1_to_hex(sha1), path);
@@ -146,39 +229,59 @@ 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;
 	} else if (S_ISREG(mode) || S_ISLNK(mode)) {
+		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;
-		uncompressed_size = size;
-		compressed_size = size;
+
+		if (S_ISREG(mode) && type == OBJ_BLOB && !args->convert &&
+		    size > big_file_threshold) {
+			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;
+		}
+		compressed_size = (method == 0) ? size : 0;
 	} else {
 		return error("unsupported file mode: 0%o (SHA1: %s)", mode,
 				sha1_to_hex(sha1));
 	}
 
-	if (method == 8) {
-		deflated = zlib_deflate(buffer, size, args->compression_level,
-				&compressed_size);
-		if (deflated && compressed_size - 6 < size) {
-			/* ZLIB --> raw compressed data (see RFC 1950) */
-			/* CMF and FLG ... */
-			out = (unsigned char *)deflated + 2;
-			compressed_size -= 6;	/* ... and ADLER32 */
-		} else {
+	if (buffer && method == 8) {
+		out = deflated = zlib_deflate_raw(buffer, size,
+						  args->compression_level,
+						  &compressed_size);
+		if (!out || compressed_size >= size) {
+			out = buffer;
 			method = 0;
 			compressed_size = size;
 		}
 	}
 
+	copy_le16(extra.magic, 0x5455);
+	copy_le16(extra.extra_size, ZIP_EXTRA_MTIME_PAYLOAD_SIZE);
+	extra.flags[0] = 1;	/* just mtime */
+	copy_le32(extra.mtime, args->time);
+
 	/* make sure we have enough free space in the dictionary */
-	direntsize = ZIP_DIR_HEADER_SIZE + pathlen;
+	direntsize = ZIP_DIR_HEADER_SIZE + pathlen + ZIP_EXTRA_MTIME_SIZE;
 	while (zip_dir_size < zip_dir_offset + direntsize) {
 		zip_dir_size += ZIP_DIRECTORY_MIN_SIZE;
 		zip_dir = xrealloc(zip_dir, zip_dir_size);
@@ -188,47 +291,127 @@ 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);
-	copy_le32(dirent.crc32, crc);
-	copy_le32(dirent.compressed_size, compressed_size);
-	copy_le32(dirent.size, uncompressed_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.extra_length, ZIP_EXTRA_MTIME_SIZE);
 	copy_le16(dirent.comment_length, 0);
 	copy_le16(dirent.disk, 0);
 	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);
-	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);
-	copy_le32(header.crc32, crc);
-	copy_le32(header.compressed_size, compressed_size);
-	copy_le32(header.size, uncompressed_size);
+	set_zip_header_data_desc(&header, size, compressed_size, crc);
 	copy_le16(header.filename_length, pathlen);
-	copy_le16(header.extra_length, 0);
+	copy_le16(header.extra_length, ZIP_EXTRA_MTIME_SIZE);
 	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) {
+	write_or_die(1, &extra, ZIP_EXTRA_MTIME_SIZE);
+	zip_offset += ZIP_EXTRA_MTIME_SIZE;
+	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 (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_raw(&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_len = zstream.next_out - compressed;
+
+			if (out_len > 0) {
+				write_or_die(1, compressed, 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_len = zstream.next_out - compressed;
+		write_or_die(1, compressed, 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;
 	}
 
 	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;
+	memcpy(zip_dir + zip_dir_offset, &extra, ZIP_EXTRA_MTIME_SIZE);
+	zip_dir_offset += ZIP_EXTRA_MTIME_SIZE;
+	zip_dir_entries++;
 
 	return 0;
 }
@@ -261,7 +444,8 @@ static void dos_time(time_t *time, int *dos_date, int *dos_time)
 	*dos_time = t->tm_sec / 2 + t->tm_min * 32 + t->tm_hour * 2048;
 }
 
-int write_zip_archive(struct archiver_args *args)
+static int write_zip_archive(const struct archiver *ar,
+			     struct archiver_args *args)
 {
 	int err;
 
@@ -278,3 +462,14 @@ int write_zip_archive(struct archiver_args *args)
 
 	return err;
 }
+
+static struct archiver zip_archiver = {
+	"zip",
+	write_zip_archive,
+	ARCHIVER_WANT_COMPRESSION_LEVELS|ARCHIVER_REMOTE
+};
+
+void init_zip_archiver(void)
+{
+	register_archiver(&zip_archiver);
+}