summaryrefslogtreecommitdiff
path: root/archive-zip.c
diff options
context:
space:
mode:
authorRené Scharfe <l.s.r@web.de>2015-03-05 19:06:02 (GMT)
committerJunio C Hamano <gitster@pobox.com>2015-03-05 23:27:48 (GMT)
commit4aff646d17e81084000100da586bef8f9d6a17a5 (patch)
tree622066ccb07b949730584e1833554b54aadeb87e /archive-zip.c
parent282616c72d1d08a77ca4fe1186cb708c38408d87 (diff)
downloadgit-4aff646d17e81084000100da586bef8f9d6a17a5.zip
git-4aff646d17e81084000100da586bef8f9d6a17a5.tar.gz
git-4aff646d17e81084000100da586bef8f9d6a17a5.tar.bz2
archive-zip: mark text files in archives
Set the text flag for ZIP archive entries that look like text files so that unzip -a can be used to perform end-of-line conversions. Info-ZIP zip does the same. Detect binary files the same way as git diff and git grep do, namely by checking for the attribute "diff" and its negation "-diff", and if none is found by falling back to checking for the presence of NUL bytes in the first few bytes of the file contents. 7-Zip, Windows' built-in ZIP functionality and Info-ZIP unzip without the switch -a are not affected by the change and still extract text files without doing any end-of-line conversions. NB: The actual end-of-line style used in the archive entries doesn't matter to unzip -a, as it converts any CR, CRLF and LF to the line end characters appropriate for the platform it is running on. Suggested-by: Ulrike Fischer <luatex@nililand.de> Signed-off-by: Rene Scharfe <l.s.r@web.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'archive-zip.c')
-rw-r--r--archive-zip.c25
1 files changed, 24 insertions, 1 deletions
diff --git a/archive-zip.c b/archive-zip.c
index 4bde019..0f9e87f 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -5,6 +5,8 @@
#include "archive.h"
#include "streaming.h"
#include "utf8.h"
+#include "userdiff.h"
+#include "xdiff-interface.h"
static int zip_date;
static int zip_time;
@@ -189,6 +191,16 @@ static int has_only_ascii(const char *s)
}
}
+static int entry_is_binary(const char *path, const void *buffer, size_t size)
+{
+ struct userdiff_driver *driver = userdiff_find_by_path(path);
+ if (!driver)
+ driver = userdiff_find_by_name("default");
+ if (driver->binary != -1)
+ return driver->binary;
+ return buffer_is_binary(buffer, size);
+}
+
#define STREAM_BUFFER_SIZE (1024 * 16)
static int write_zip_entry(struct archiver_args *args,
@@ -210,6 +222,8 @@ static int write_zip_entry(struct archiver_args *args,
struct git_istream *stream = NULL;
unsigned long flags = 0;
unsigned long size;
+ int is_binary = -1;
+ const char *path_without_prefix = path + args->baselen;
crc = crc32(0, NULL, 0);
@@ -256,6 +270,8 @@ static int write_zip_entry(struct archiver_args *args,
return error("cannot read %s",
sha1_to_hex(sha1));
crc = crc32(crc, buffer, size);
+ is_binary = entry_is_binary(path_without_prefix,
+ buffer, size);
out = buffer;
}
compressed_size = (method == 0) ? size : 0;
@@ -300,7 +316,6 @@ static int write_zip_entry(struct archiver_args *args,
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);
@@ -328,6 +343,9 @@ static int write_zip_entry(struct archiver_args *args,
if (readlen <= 0)
break;
crc = crc32(crc, buf, readlen);
+ if (is_binary == -1)
+ is_binary = entry_is_binary(path_without_prefix,
+ buf, readlen);
write_or_die(1, buf, readlen);
}
close_istream(stream);
@@ -361,6 +379,9 @@ static int write_zip_entry(struct archiver_args *args,
if (readlen <= 0)
break;
crc = crc32(crc, buf, readlen);
+ if (is_binary == -1)
+ is_binary = entry_is_binary(path_without_prefix,
+ buf, readlen);
zstream.next_in = buf;
zstream.avail_in = readlen;
@@ -405,6 +426,8 @@ static int write_zip_entry(struct archiver_args *args,
free(deflated);
free(buffer);
+ copy_le16(dirent.attr1, !is_binary);
+
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);