Skip to content

Use the external encoding for character boundaries in GzipReader #163

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mame wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Use the external encoding for character boundaries in GzipReader #163

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 9 additions & 6 deletions ext/zlib/zlib.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2484,6 +2484,9 @@ struct gzfile {

#define GZFILE_READ_SIZE 2048

/* the encoding of the data before conversion */
#define GZFILE_RAW_ENC(gz) ((gz)->enc2 ? (gz)->enc2 : (gz)->enc)

enum { read_raw_arg_len, read_raw_arg_buf, read_raw_arg__count};
struct read_raw_arg {
VALUE io;
Expand Down Expand Up @@ -3084,7 +3087,7 @@ gzfile_getc(struct gzfile *gz)
VALUE buf, dst = 0;
int len;

len = rb_enc_mbmaxlen(gz->enc);
len = rb_enc_mbmaxlen(GZFILE_RAW_ENC(gz));
while (!ZSTREAM_IS_FINISHED(&gz->z) && ZSTREAM_BUF_FILLED(&gz->z) < len) {
gzfile_read_more(gz, Qnil);
}
Expand Down Expand Up @@ -3113,7 +3116,7 @@ gzfile_getc(struct gzfile *gz)
}
else {
buf = gz->z.buf;
len = rb_enc_mbclen(RSTRING_PTR(buf), RSTRING_END(buf), gz->enc);
len = rb_enc_mbclen(RSTRING_PTR(buf), RSTRING_END(buf), GZFILE_RAW_ENC(gz));
dst = gzfile_read(gz, len, Qnil);
if (NIL_P(dst)) return dst;
return gzfile_newstr(gz, dst);
Expand Down Expand Up @@ -4347,10 +4350,11 @@ gzreader_charboundary(struct gzfile *gz, rb_len_t n)
{
char *s = RSTRING_PTR(gz->z.buf);
char *e = s + ZSTREAM_BUF_FILLED(&gz->z);
char *p = rb_enc_left_char_head(s, s + n - 1, e, gz->enc);
rb_encoding *enc = GZFILE_RAW_ENC(gz);
char *p = rb_enc_left_char_head(s, s + n - 1, e, enc);
rb_len_t l = p - s;
if (l < n) {
int n_bytes = rb_enc_precise_mbclen(p, e, gz->enc);
int n_bytes = rb_enc_precise_mbclen(p, e, enc);
if (MBCLEN_NEEDMORE_P(n_bytes)) {
if ((l = gzfile_fill(gz, n + MBCLEN_NEEDMORE_LEN(n_bytes), Qnil)) > 0) {
return l;
Expand All @@ -4373,8 +4377,7 @@ gzreader_gets(int argc, VALUE *argv, VALUE obj)
char *p, *res;
rb_len_t rslen, n, limit = -1;
int rspara;
rb_encoding *enc = gz->enc;
int maxlen = rb_enc_mbmaxlen(enc);
int maxlen = rb_enc_mbmaxlen(GZFILE_RAW_ENC(gz));

if (argc == 0) {
rs = rb_rs;
Expand Down
7 changes: 7 additions & 0 deletions test/zlib/test_zlib.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1279,6 +1279,13 @@
}
end

def test_getc_with_encoding_conversion
gz = Zlib.gzip("\x82\xa0\x82\xa2".b)
Zlib::GzipReader.wrap(StringIO.new(gz), external_encoding: "Shift_JIS", internal_encoding: "UTF-8") do |f|
assert_equal(["\u3042", "\u3044"], f.each_char.to_a)

Check failure on line 1285 in test/zlib/test_zlib.rb

View workflow job for this annotation

GitHub Actions / build (truffleruby-head / ubuntu-latest)

Failure 

<["あ", "い"]> expected but was
<["\x82", "\xA0", "\x82", "\xA2"]>.

Check failure on line 1285 in test/zlib/test_zlib.rb

View workflow job for this annotation

GitHub Actions / build (truffleruby-head / macos-latest)

Failure 

<["あ", "い"]> expected but was
<["\x82", "\xA0", "\x82", "\xA2"]>.
end
end

def test_gets2
Tempfile.create("test_zlib_gzip_reader_gets2") {|t|
t.close
Expand Down
Loading