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>maint
René Scharfe
Junio C Hamano
parent
282616c72d
commit
4aff646d17
|
|
@ -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);
|
||||
|
|
|
|||
|
|
@ -33,6 +33,37 @@ check_zip() {
|
|||
test_expect_success UNZIP " validate file contents" "
|
||||
diff -r a ${dir_with_prefix}a
|
||||
"
|
||||
|
||||
dir=eol_$1
|
||||
dir_with_prefix=$dir/$2
|
||||
extracted=${dir_with_prefix}a
|
||||
original=a
|
||||
|
||||
test_expect_success UNZIP " extract ZIP archive with EOL conversion" '
|
||||
(mkdir $dir && cd $dir && "$GIT_UNZIP" -a ../$zipfile)
|
||||
'
|
||||
|
||||
test_expect_success UNZIP " validate that text files are converted" "
|
||||
test_cmp_bin $extracted/text.cr $extracted/text.crlf &&
|
||||
test_cmp_bin $extracted/text.cr $extracted/text.lf
|
||||
"
|
||||
|
||||
test_expect_success UNZIP " validate that binary files are unchanged" "
|
||||
test_cmp_bin $original/binary.cr $extracted/binary.cr &&
|
||||
test_cmp_bin $original/binary.crlf $extracted/binary.crlf &&
|
||||
test_cmp_bin $original/binary.lf $extracted/binary.lf
|
||||
"
|
||||
|
||||
test_expect_success UNZIP " validate that diff files are converted" "
|
||||
test_cmp_bin $extracted/diff.cr $extracted/diff.crlf &&
|
||||
test_cmp_bin $extracted/diff.cr $extracted/diff.lf
|
||||
"
|
||||
|
||||
test_expect_success UNZIP " validate that -diff files are unchanged" "
|
||||
test_cmp_bin $original/nodiff.cr $extracted/nodiff.cr &&
|
||||
test_cmp_bin $original/nodiff.crlf $extracted/nodiff.crlf &&
|
||||
test_cmp_bin $original/nodiff.lf $extracted/nodiff.lf
|
||||
"
|
||||
}
|
||||
|
||||
test_expect_success \
|
||||
|
|
@ -41,6 +72,18 @@ test_expect_success \
|
|||
echo simple textfile >a/a &&
|
||||
mkdir a/bin &&
|
||||
cp /bin/sh a/bin &&
|
||||
printf "text\r" >a/text.cr &&
|
||||
printf "text\r\n" >a/text.crlf &&
|
||||
printf "text\n" >a/text.lf &&
|
||||
printf "text\r" >a/nodiff.cr &&
|
||||
printf "text\r\n" >a/nodiff.crlf &&
|
||||
printf "text\n" >a/nodiff.lf &&
|
||||
printf "\0\r" >a/binary.cr &&
|
||||
printf "\0\r\n" >a/binary.crlf &&
|
||||
printf "\0\n" >a/binary.lf &&
|
||||
printf "\0\r" >a/diff.cr &&
|
||||
printf "\0\r\n" >a/diff.crlf &&
|
||||
printf "\0\n" >a/diff.lf &&
|
||||
printf "A\$Format:%s\$O" "$SUBSTFORMAT" >a/substfile1 &&
|
||||
printf "A not substituted O" >a/substfile2 &&
|
||||
(p=long_path_to_a_file && cd a &&
|
||||
|
|
@ -70,7 +113,9 @@ test_expect_success \
|
|||
git update-ref HEAD $(TZ=GMT GIT_COMMITTER_DATE="2005-05-27 22:00:00" \
|
||||
git commit-tree $treeid </dev/null)'
|
||||
|
||||
test_expect_success 'setup export-subst' '
|
||||
test_expect_success 'setup export-subst and diff attributes' '
|
||||
echo "a/nodiff.* -diff" >>.git/info/attributes &&
|
||||
echo "a/diff.* diff" >>.git/info/attributes &&
|
||||
echo "substfile?" export-subst >>.git/info/attributes &&
|
||||
git log --max-count=1 "--pretty=format:A${SUBSTFORMAT}O" HEAD \
|
||||
>a/substfile1
|
||||
|
|
|
|||
Loading…
Reference in New Issue