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>
René Scharfe committed
Mar 5, 2015 at 20:06 UTC
4aff646d17e81084000100da586bef8f9d6a17a5
2 files changed
+70
-2
archive-zip.c
+24
-1
@@ -5,6 +5,8 @@
5
#include "archive.h"
6
#include "streaming.h"
7
#include "utf8.h"
8
+#include "userdiff.h"
9
+#include "xdiff-interface.h"
10
11
static int zip_date;
12
static int zip_time;
@@ -189,6 +191,16 @@ static int has_only_ascii(const char *s)
191
}
192
}
193
194
+static int entry_is_binary(const char *path, const void *buffer, size_t size)
195
+{
196
+ struct userdiff_driver *driver = userdiff_find_by_path(path);
197
+ if (!driver)
198
+ driver = userdiff_find_by_name("default");
199
+ if (driver->binary != -1)
200
+ return driver->binary;
201
+ return buffer_is_binary(buffer, size);
202
+}
203
+
204
#define STREAM_BUFFER_SIZE (1024 * 16)
205
206
static int write_zip_entry(struct archiver_args *args,
@@ -210,6 +222,8 @@ static int write_zip_entry(struct archiver_args *args,
222
struct git_istream *stream = NULL;
223
unsigned long flags = 0;
224
unsigned long size;
225
+ int is_binary = -1;
226
+ const char *path_without_prefix = path + args->baselen;
227
228
crc = crc32(0, NULL, 0);
229
@@ -256,6 +270,8 @@ static int write_zip_entry(struct archiver_args *args,
270
return error("cannot read %s",
271
sha1_to_hex(sha1));
272
crc = crc32(crc, buffer, size);
273
+ is_binary = entry_is_binary(path_without_prefix,
274
+ buffer, size);
275
out = buffer;
276
}
277
compressed_size = (method == 0) ? size : 0;
@@ -300,7 +316,6 @@ static int write_zip_entry(struct archiver_args *args,
316
copy_le16(dirent.extra_length, ZIP_EXTRA_MTIME_SIZE);
317
copy_le16(dirent.comment_length, 0);
318
copy_le16(dirent.disk, 0);
303
- copy_le16(dirent.attr1, 0);
319
copy_le32(dirent.attr2, attr2);
320
copy_le32(dirent.offset, zip_offset);
321
@@ -328,6 +343,9 @@ static int write_zip_entry(struct archiver_args *args,
343
if (readlen <= 0)
344
break;
345
crc = crc32(crc, buf, readlen);
346
+ if (is_binary == -1)
347
+ is_binary = entry_is_binary(path_without_prefix,
348
+ buf, readlen);
349
write_or_die(1, buf, readlen);
350
}
351
close_istream(stream);
@@ -361,6 +379,9 @@ static int write_zip_entry(struct archiver_args *args,
379
if (readlen <= 0)
380
break;
381
crc = crc32(crc, buf, readlen);
382
+ if (is_binary == -1)
383
+ is_binary = entry_is_binary(path_without_prefix,
384
+ buf, readlen);
385
386
zstream.next_in = buf;
387
zstream.avail_in = readlen;
@@ -405,6 +426,8 @@ static int write_zip_entry(struct archiver_args *args,
426
free(deflated);
427
free(buffer);
428
429
+ copy_le16(dirent.attr1, !is_binary);
430
+
431
memcpy(zip_dir + zip_dir_offset, &dirent, ZIP_DIR_HEADER_SIZE);
432
zip_dir_offset += ZIP_DIR_HEADER_SIZE;
433
memcpy(zip_dir + zip_dir_offset, path, pathlen);
t/t5003-archive-zip.sh
+46
-1
@@ -33,6 +33,37 @@ check_zip() {
33
test_expect_success UNZIP " validate file contents" "
34
diff -r a ${dir_with_prefix}a
35
"
36
+
37
+ dir=eol_$1
38
+ dir_with_prefix=$dir/$2
39
+ extracted=${dir_with_prefix}a
40
+ original=a
41
+
42
+ test_expect_success UNZIP " extract ZIP archive with EOL conversion" '
43
+ (mkdir $dir && cd $dir && "$GIT_UNZIP" -a ../$zipfile)
44
+ '
45
+
46
+ test_expect_success UNZIP " validate that text files are converted" "
47
+ test_cmp_bin $extracted/text.cr $extracted/text.crlf &&
48
+ test_cmp_bin $extracted/text.cr $extracted/text.lf
49
+ "
50
+
51
+ test_expect_success UNZIP " validate that binary files are unchanged" "
52
+ test_cmp_bin $original/binary.cr $extracted/binary.cr &&
53
+ test_cmp_bin $original/binary.crlf $extracted/binary.crlf &&
54
+ test_cmp_bin $original/binary.lf $extracted/binary.lf
55
+ "
56
+
57
+ test_expect_success UNZIP " validate that diff files are converted" "
58
+ test_cmp_bin $extracted/diff.cr $extracted/diff.crlf &&
59
+ test_cmp_bin $extracted/diff.cr $extracted/diff.lf
60
+ "
61
+
62
+ test_expect_success UNZIP " validate that -diff files are unchanged" "
63
+ test_cmp_bin $original/nodiff.cr $extracted/nodiff.cr &&
64
+ test_cmp_bin $original/nodiff.crlf $extracted/nodiff.crlf &&
65
+ test_cmp_bin $original/nodiff.lf $extracted/nodiff.lf
66
+ "
67
}
68
69
test_expect_success \
@@ -41,6 +72,18 @@ test_expect_success \
72
echo simple textfile >a/a &&
73
mkdir a/bin &&
74
cp /bin/sh a/bin &&
75
+ printf "text\r" >a/text.cr &&
76
+ printf "text\r\n" >a/text.crlf &&
77
+ printf "text\n" >a/text.lf &&
78
+ printf "text\r" >a/nodiff.cr &&
79
+ printf "text\r\n" >a/nodiff.crlf &&
80
+ printf "text\n" >a/nodiff.lf &&
81
+ printf "\0\r" >a/binary.cr &&
82
+ printf "\0\r\n" >a/binary.crlf &&
83
+ printf "\0\n" >a/binary.lf &&
84
+ printf "\0\r" >a/diff.cr &&
85
+ printf "\0\r\n" >a/diff.crlf &&
86
+ printf "\0\n" >a/diff.lf &&
87
printf "A\$Format:%s\$O" "$SUBSTFORMAT" >a/substfile1 &&
88
printf "A not substituted O" >a/substfile2 &&
89
(p=long_path_to_a_file && cd a &&
@@ -70,7 +113,9 @@ test_expect_success \
113
git update-ref HEAD $(TZ=GMT GIT_COMMITTER_DATE="2005-05-27 22:00:00" \
114
git commit-tree $treeid </dev/null)'
115
73
-test_expect_success 'setup export-subst' '
116
+test_expect_success 'setup export-subst and diff attributes' '
117
+ echo "a/nodiff.* -diff" >>.git/info/attributes &&
118
+ echo "a/diff.* diff" >>.git/info/attributes &&
119
echo "substfile?" export-subst >>.git/info/attributes &&
120
git log --max-count=1 "--pretty=format:A${SUBSTFORMAT}O" HEAD \
121
>a/substfile1