kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

re.c: fix for wide character encodings

Browse source 
* re.c (rb_memsearch): should match only char boundaries in wide
  character encodings.  [ruby-core:70220] [Bug #11413]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@51470 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2015-08-03 01:08:36 +00:00
parent e60d35e302
commit 2c8986d23b
4 changed files with 47 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
ChangeLog
View file

@ -1,3 +1,8 @@
Mon Aug 3 10:08:33 2015 Nobuyoshi Nakada <nobu@ruby-lang.org>
* re.c (rb_memsearch): should match only char boundaries in wide
character encodings. [ruby-core:70220] [Bug #11413]
Sun Aug 2 07:01:17 2015 Eric Wong <e@80x24.org>
* ext/openssl/lib/openssl/buffering.rb (gets):

44
re.c
View file

@ -221,6 +221,32 @@ rb_memsearch_qs_utf8(const unsigned char *xs, long m, const unsigned char *ys, l
return -1;
}
static inline long
rb_memsearch_wchar(const unsigned char *xs, long m, const unsigned char *ys, long n)
{
const unsigned char *x = xs, x0 = *xs, *y = ys;
enum {char_size = 2};
for (n -= m; n > 0; n -= char_size, y += char_size) {
if (x0 == *y && memcmp(x+1, y+1, m-1) == 0)
return y - ys;
}
return -1;
}
static inline long
rb_memsearch_qchar(const unsigned char *xs, long m, const unsigned char *ys, long n)
{
const unsigned char *x = xs, x0 = *xs, *y = ys;
enum {char_size = 4};
for (n -= m; n > 0; n -= char_size, y += char_size) {
if (x0 == *y && memcmp(x+1, y+1, m-1) == 0)
return y - ys;
}
return -1;
}
long
rb_memsearch(const void *x0, long m, const void *y0, long n, rb_encoding *enc)
{
@ -241,15 +267,21 @@ rb_memsearch(const void *x0, long m, const void *y0, long n, rb_encoding *enc)
else
return -1;
}
else if (m <= SIZEOF_VALUE) {
return rb_memsearch_ss(x0, m, y0, n);
else if (LIKELY(rb_enc_mbminlen(enc) == 1)) {
if (m <= SIZEOF_VALUE) {
return rb_memsearch_ss(x0, m, y0, n);
}
else if (enc == rb_utf8_encoding()){
return rb_memsearch_qs_utf8(x0, m, y0, n);
}
}
else if (enc == rb_utf8_encoding()){
return rb_memsearch_qs_utf8(x0, m, y0, n);
else if (LIKELY(rb_enc_mbminlen(enc) == 2)) {
return rb_memsearch_wchar(x0, m, y0, n);
}
else {
return rb_memsearch_qs(x0, m, y0, n);
else if (LIKELY(rb_enc_mbminlen(enc) == 4)) {
return rb_memsearch_qchar(x0, m, y0, n);
}
return rb_memsearch_qs(x0, m, y0, n);
}
#define REG_LITERAL FL_USER5

7
string.c
View file

@ -6544,15 +6544,10 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str)
}
enc = STR_ENC_GET(str);
if (NIL_P(spat)) {
if (!NIL_P(rb_fs)) {
spat = rb_fs;
goto fs_set;
}
if (NIL_P(spat) && NIL_P(spat = rb_fs)) {
split_type = awk;
}
else {
fs_set:
spat = get_pat_quoted(spat, 0);
if (BUILTIN_TYPE(spat) == T_STRING) {
rb_encoding *enc2 = STR_ENC_GET(spat);

3
test/ruby/test_m17n.rb
View file

@ -1236,6 +1236,9 @@ class TestM17N < Test::Unit::TestCase
each_encoding("abc,def", ",", "abc", "def") do |str, sep, *expected|
assert_equal(expected, str.split(sep, -1))
end
each_encoding("abc\0def", "\0", "abc", "def") do |str, sep, *expected|
assert_equal(expected, str.split(sep, -1))
end
end
def test_nonascii_method_name