1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

string.c: wchar succ

Browse Source 
* string.c (enc_succ_char, enc_pred_char): consider wchar case.
  [ruby-core:56071] [Bug #8653]
* string.c (rb_str_succ): do not replace with invalid char.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@42078 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2013-07-20 03:14:09 +00:00
parent 241ad8877d
commit e6a6dd8e7e
3 changed files with 64 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
ChangeLog
View File

@ -1,4 +1,9 @@
Sat Jul 20 12:13:37 2013 Nobuyoshi Nakada <nobu@ruby-lang.org> Sat Jul 20 12:14:07 2013 Nobuyoshi Nakada <nobu@ruby-lang.org>
* string.c (enc_succ_char, enc_pred_char): consider wchar case.
[ruby-core:56071] [Bug #8653]
* string.c (rb_str_succ): do not replace with invalid char.
* encoding.c (rb_enc_code_to_mbclen): add new function which returns * encoding.c (rb_enc_code_to_mbclen): add new function which returns
mbclen from codepoint like as rb_enc_codelen() but 0 for invalid mbclen from codepoint like as rb_enc_codelen() but 0 for invalid

45
string.c
View File

@ -2870,6 +2870,24 @@ enc_succ_char(char *p, long len, rb_encoding *enc)
{ {
long i; long i;
int l; int l;
if (rb_enc_mbminlen(enc) > 1) {
/* wchar, trivial case */
int r = rb_enc_precise_mbclen(p, p + len, enc), c;
if (!MBCLEN_CHARFOUND_P(r)) {
return NEIGHBOR_NOT_CHAR;
}
c = rb_enc_mbc_to_codepoint(p, p + len, enc) + 1;
l = rb_enc_code_to_mbclen(c, enc);
if (!l) return NEIGHBOR_NOT_CHAR;
if (l != len) return NEIGHBOR_WRAPPED;
rb_enc_mbcput(c, p, enc);
r = rb_enc_precise_mbclen(p, p + len, enc);
if (!MBCLEN_CHARFOUND_P(r)) {
return NEIGHBOR_NOT_CHAR;
}
return NEIGHBOR_FOUND;
}
while (1) { while (1) {
for (i = len-1; 0 <= i && (unsigned char)p[i] == 0xff; i--) for (i = len-1; 0 <= i && (unsigned char)p[i] == 0xff; i--)
p[i] = '\0'; p[i] = '\0';
@ -2904,6 +2922,25 @@ enc_pred_char(char *p, long len, rb_encoding *enc)
{ {
long i; long i;
int l; int l;
if (rb_enc_mbminlen(enc) > 1) {
/* wchar, trivial case */
int r = rb_enc_precise_mbclen(p, p + len, enc), c;
if (!MBCLEN_CHARFOUND_P(r)) {
return NEIGHBOR_NOT_CHAR;
}
c = rb_enc_mbc_to_codepoint(p, p + len, enc);
if (!c) return NEIGHBOR_NOT_CHAR;
--c;
l = rb_enc_code_to_mbclen(c, enc);
if (!l) return NEIGHBOR_NOT_CHAR;
if (l != len) return NEIGHBOR_WRAPPED;
rb_enc_mbcput(c, p, enc);
r = rb_enc_precise_mbclen(p, p + len, enc);
if (!MBCLEN_CHARFOUND_P(r)) {
return NEIGHBOR_NOT_CHAR;
}
return NEIGHBOR_FOUND;
}
while (1) { while (1) {
for (i = len-1; 0 <= i && (unsigned char)p[i] == 0; i--) for (i = len-1; 0 <= i && (unsigned char)p[i] == 0; i--)
p[i] = '\xff'; p[i] = '\xff';
@ -3074,12 +3111,16 @@ rb_str_succ(VALUE orig)
s = e; s = e;
while ((s = rb_enc_prev_char(sbeg, s, e, enc)) != 0) { while ((s = rb_enc_prev_char(sbeg, s, e, enc)) != 0) {
enum neighbor_char neighbor; enum neighbor_char neighbor;
char tmp[ONIGENC_CODE_TO_MBC_MAXLEN];
l = rb_enc_precise_mbclen(s, e, enc); l = rb_enc_precise_mbclen(s, e, enc);
if (!ONIGENC_MBCLEN_CHARFOUND_P(l)) continue; if (!ONIGENC_MBCLEN_CHARFOUND_P(l)) continue;
l = ONIGENC_MBCLEN_CHARFOUND_LEN(l); l = ONIGENC_MBCLEN_CHARFOUND_LEN(l);
neighbor = enc_succ_char(s, l, enc); MEMCPY(tmp, s, char, l);
if (neighbor == NEIGHBOR_FOUND) neighbor = enc_succ_char(tmp, l, enc);
if (neighbor == NEIGHBOR_FOUND) {
MEMCPY(s, tmp, char, l);
return str; return str;
}
if (rb_enc_precise_mbclen(s, s+l, enc) != l) { if (rb_enc_precise_mbclen(s, s+l, enc) != l) {
/* wrapped to \0...\0. search next valid char. */ /* wrapped to \0...\0. search next valid char. */
enc_succ_char(s, l, enc); enc_succ_char(s, l, enc);

19
test/ruby/test_m17n_comb.rb
View File

@ -50,10 +50,12 @@ class TestM17NComb < Test::Unit::TestCase
# for transitivity test # for transitivity test
u("\xe0\xa0\xa1"), e("\xe0\xa0\xa1"), s("\xe0\xa0\xa1"), # [ruby-dev:32693] u("\xe0\xa0\xa1"), e("\xe0\xa0\xa1"), s("\xe0\xa0\xa1"), # [ruby-dev:32693]
e("\xa1\xa1"), a("\xa1\xa1"), s("\xa1\xa1"), # [ruby-dev:36484] e("\xa1\xa1"), a("\xa1\xa1"), s("\xa1\xa1"), # [ruby-dev:36484]
]
#"aa".force_encoding("utf-16be"), WSTRINGS = [
#"aaaa".force_encoding("utf-32be"), "aa".force_encoding("utf-16be"),
#"aaa".force_encoding("utf-32be"), "aaaa".force_encoding("utf-32be"),
"aaa".force_encoding("utf-32be"),
] ]
def combination(*args, &b) def combination(*args, &b)
@ -84,7 +86,7 @@ class TestM17NComb < Test::Unit::TestCase
r r
end end
def enccall(recv, meth, *args, &block) def assert_enccall(recv, meth, *args, &block)
desc = '' desc = ''
if String === recv if String === recv
desc << encdump(recv) desc << encdump(recv)
@ -113,6 +115,7 @@ class TestM17NComb < Test::Unit::TestCase
} }
result result
end end
alias enccall assert_enccall
def assert_str_enc_propagation(t, s1, s2) def assert_str_enc_propagation(t, s1, s2)
if !s1.ascii_only? if !s1.ascii_only?
@ -1327,6 +1330,14 @@ class TestM17NComb < Test::Unit::TestCase
s = t s = t
} }
} }
Encoding.list.each do |enc|
next if enc.dummy?
{"A"=>"B", "A1"=>"A2", "A9"=>"B0", "9"=>"10", "Z"=>"AA"}.each do |orig, expected|
s = orig.encode(enc)
assert_strenc(expected.encode(enc), enc, s.succ, proc {"#{orig.dump}.encode(#{enc}).succ"})
end
end
end end
def test_str_hash def test_str_hash