[PATCH 1/2] archive-zip: support UTF-8 paths

From

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

Date

Sep 18, 2012, 19:46 UTC

Message-ID

<5058CFB0.6040506@lsrfire.ath.cx>

In-Reply-To

<5058CE49.3070108@lsrfire.ath.cx>

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
---
Changes from previous version: Stop using has_non_ascii(), which does
slightly too much for our purposes, and split off creator version
change into a separate patch.

 archive-zip.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/archive-zip.c b/archive-zip.c
index f5af81f..0f763e8 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -4,6 +4,7 @@
 #include "cache.h"
 #include "archive.h"
 #include "streaming.h"
+#include "utf8.h"
 
 static int zip_date;
 static int zip_time;
@@ -16,7 +17,8 @@ static unsigned int zip_dir_offset;
 static unsigned int zip_dir_entries;
 
 #define ZIP_DIRECTORY_MIN_SIZE	(1024 * 1024)
-#define ZIP_STREAM (8)
+#define ZIP_STREAM	(1 <<  3)
+#define ZIP_UTF8	(1 << 11)
 
 struct zip_local_header {
 	unsigned char magic[4];
@@ -164,6 +166,17 @@ static void set_zip_header_data_desc(struct zip_local_header *header,
 	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,
@@ -187,6 +200,13 @@ static int write_zip_entry(struct archiver_args *args,
 
 	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);

-- 
1.7.12