archive-zip: streaming for deflated files

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>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 74 insertions, 1 deletions

diff --git a/archive-zip.c b/archive-zip.c
index 1c6c39d42..f5af81f90 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 9db54b56b..55ed955ce 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 3b54c3862..94f2ebac5 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'