René Scharfe <rene.scharfe@xxxxxxxxxxxxxx> writes:
> But now for the patch, which is a bit confusing as well. I'm curious to
> hear about results for more platforms, extractors and character classes.
> Based on that we can see if we need to generate the extra fields instead
> of relying on the new flag.
Thanks for keeping the ball rolling.
> Subject: [PATCH] archive-zip: support UTF-8 paths
>
> Set general purpose flag 11 if we encounter a path that contains
> non-ASCII characters. We assume that all paths are given as UTF-8; no
> conversion is done.
>
> The flag seems to be ignored by unzip unless we also mark the archive
> entry as coming from a Unix system. This is done by setting the field
> creator_version ("version made by" in the standard[1]) to 0x03NN.
>
> The NN part represents the version of the standard supported by us, and
> this patch sets it to 3f (for version 6.3) for Unix paths. We keep
> creator_version set to 0 (FAT filesystem, standard version 0) in the
> non-special cases, as before.
>
> But when we declare a file to have a Unix path, then we have to set the
> file mode as well, or unzip will extract the files with the permission
> set 0000, i.e. inaccessible by all.
>
> [1] http://www.pkware.com/documents/casestudies/APPNOTE.TXT
>
> Signed-off-by: Rene Scharfe <rene.scharfe@xxxxxxxxxxxxxx>
> ---
> archive-zip.c | 27 +++++++++++++++++++++------
> 1 file changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/archive-zip.c b/archive-zip.c
> index f5af81f..928da1d 100644
> --- a/archive-zip.c
> +++ b/archive-zip.c
> @@ -4,6 +4,8 @@
> #include "cache.h"
> #include "archive.h"
> #include "streaming.h"
> +#include "commit.h"
> +#include "utf8.h"
>
> static int zip_date;
> static int zip_time;
> @@ -16,7 +18,8 @@ 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];
> @@ -173,7 +176,8 @@ static int write_zip_entry(struct archiver_args *args,
> {
> struct zip_local_header header;
> struct zip_dir_header dirent;
> - unsigned long attr2;
> + unsigned int creator_version = 0;
> + unsigned long attr2 = 0;
> unsigned long compressed_size;
> unsigned long crc;
> unsigned long direntsize;
> @@ -187,6 +191,13 @@ static int write_zip_entry(struct archiver_args *args,
>
> crc = crc32(0, NULL, 0);
>
> + if (has_non_ascii(path)) {
Do we want to treat \033 as "ascii" in this codepath? The function
primarily is used by the log formatter to see if we need 8-bit CTE
when writing out in the e-mail format.
> + 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);
> @@ -204,10 +215,15 @@ static int write_zip_entry(struct archiver_args *args,
> 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 && size > 0)
> method = 8;
> + if (S_ISLNK(mode) || (mode & 0111) || (flags & ZIP_UTF8)) {
> + creator_version = 0x033f;
> + attr2 = mode;
> + if (S_ISLNK(mode))
> + attr2 |= 0777;
> + attr2 <<= 16;
> + }
> compressed_size = size;
>
> if (S_ISREG(mode) && type == OBJ_BLOB && !args->convert &&
> @@ -254,8 +270,7 @@ static int write_zip_entry(struct archiver_args *args,
> }
>
> copy_le32(dirent.magic, 0x02014b50);
> - copy_le16(dirent.creator_version,
> - S_ISLNK(mode) || (S_ISREG(mode) && (mode & 0111)) ? 0x0317 : 0);
> + copy_le16(dirent.creator_version, creator_version);
> copy_le16(dirent.version, 10);
> copy_le16(dirent.flags, flags);
> copy_le16(dirent.compression_method, method);
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html