diff options
author | Joe Tsai <joetsai@digital-static.net> | 2017-11-02 13:53:16 -0700 |
---|---|---|
committer | Joe Tsai <thebrokentoaster@gmail.com> | 2017-11-06 21:35:59 +0000 |
commit | 4fcc835971ad63cf913ebe074ef6191e35a44ab9 (patch) | |
tree | 21b132a256d3f8652416b9eb9d4a4fe5a25473d5 /src/archive/zip/reader_test.go | |
parent | 0c554957483aaf1f62c6251dbe62ab5fce3e219c (diff) | |
download | go-4fcc835971ad63cf913ebe074ef6191e35a44ab9.tar.gz go-4fcc835971ad63cf913ebe074ef6191e35a44ab9.zip |
archive/zip: add FileHeader.NonUTF8 field
The NonUTF8 field provides users with a way to explictly tell the
ZIP writer to avoid setting the UTF-8 flag.
This is necessary because many readers:
1) (Still) do not support UTF-8
2) And use the local system encoding instead
Thus, even though character encodings other than CP-437 and UTF-8
are not officially supported by the ZIP specification, pragmatically
the world has permitted use of them.
When a non-standard encoding is used, it is the user's responsibility
to ensure that the target system is expecting the encoding used
(e.g., producing a ZIP file you know is used on a Chinese version of Windows).
We adjust the detectUTF8 function to account for Shift-JIS and EUC-KR
not being identical to ASCII for two characters.
We don't need an API for users to explicitly specify that they are encoding
with UTF-8 since all single byte characters are compatible with all other
common encodings (Windows-1256, Windows-1252, Windows-1251, Windows-1250,
IEC-8859, EUC-KR, KOI8-R, Latin-1, Shift-JIS, GB-2312, GBK) except for
the non-printable characters and the backslash character (all of which
are invalid characters in a path name anyways).
Fixes #10741
Change-Id: I9004542d1d522c9137973f1b6e2b623fa54dfd66
Reviewed-on: https://go-review.googlesource.com/75592
Run-TryBot: Joe Tsai <thebrokentoaster@gmail.com>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Diffstat (limited to 'src/archive/zip/reader_test.go')
-rw-r--r-- | src/archive/zip/reader_test.go | 65 |
1 files changed, 64 insertions, 1 deletions
diff --git a/src/archive/zip/reader_test.go b/src/archive/zip/reader_test.go index d2d051b223..5fa2c80afa 100644 --- a/src/archive/zip/reader_test.go +++ b/src/archive/zip/reader_test.go @@ -29,7 +29,8 @@ type ZipTest struct { type ZipTestFile struct { Name string Mode os.FileMode - ModTime time.Time // optional, modified time in format "mm-dd-yy hh:mm:ss" + NonUTF8 bool + ModTime time.Time // Information describing expected zip file content. // First, reading the entire content should produce the error ContentErr. @@ -320,6 +321,68 @@ var tests = []ZipTest{ }, }, { + Name: "utf8-7zip.zip", + File: []ZipTestFile{ + { + Name: "世界", + Content: []byte{}, + Mode: 0666, + ModTime: time.Date(2017, 11, 6, 13, 9, 27, 867862500, timeZone(-8*time.Hour)), + }, + }, + }, + { + Name: "utf8-infozip.zip", + File: []ZipTestFile{ + { + Name: "世界", + Content: []byte{}, + Mode: 0644, + // Name is valid UTF-8, but format does not have UTF-8 flag set. + // We don't do UTF-8 detection for multi-byte runes due to + // false-positives with other encodings (e.g., Shift-JIS). + // Format says encoding is not UTF-8, so we trust it. + NonUTF8: true, + ModTime: time.Date(2017, 11, 6, 13, 9, 27, 0, timeZone(-8*time.Hour)), + }, + }, + }, + { + Name: "utf8-osx.zip", + File: []ZipTestFile{ + { + Name: "世界", + Content: []byte{}, + Mode: 0644, + // Name is valid UTF-8, but format does not have UTF-8 set. + NonUTF8: true, + ModTime: time.Date(2017, 11, 6, 13, 9, 27, 0, timeZone(-8*time.Hour)), + }, + }, + }, + { + Name: "utf8-winrar.zip", + File: []ZipTestFile{ + { + Name: "世界", + Content: []byte{}, + Mode: 0666, + ModTime: time.Date(2017, 11, 6, 13, 9, 27, 867862500, timeZone(-8*time.Hour)), + }, + }, + }, + { + Name: "utf8-winzip.zip", + File: []ZipTestFile{ + { + Name: "世界", + Content: []byte{}, + Mode: 0666, + ModTime: time.Date(2017, 11, 6, 13, 9, 27, 867000000, timeZone(-8*time.Hour)), + }, + }, + }, + { Name: "time-7zip.zip", File: []ZipTestFile{ { |