mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
* string.c (rb_str_subseq): retrieve substring based on byte offset.
* string.c (rb_str_rindex_m): was confusing character offset and byte offset. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@13295 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
matz
parent
01c24a2f78
commit
51b4cc11d1
4 changed files with 40 additions and 20 deletions
|
|
@ -1,3 +1,10 @@
|
|||
Tue Aug 28 15:42:09 2007 Yukihiro Matsumoto <matz@ruby-lang.org>
|
||||
|
||||
* string.c (rb_str_subseq): retrieve substring based on byte offset.
|
||||
|
||||
* string.c (rb_str_rindex_m): was confusing character offset and
|
||||
byte offset.
|
||||
|
||||
Tue Aug 28 14:23:31 2007 Nobuyoshi Nakada <nobu@ruby-lang.org>
|
||||
|
||||
* string.c (rb_str_splice_0): should check to modify. [ruby-dev:31665]
|
||||
|
|
|
|||
|
|
@ -500,6 +500,7 @@ VALUE rb_str_plus(VALUE, VALUE);
|
|||
VALUE rb_str_times(VALUE, VALUE);
|
||||
int rb_str_sublen(VALUE, int);
|
||||
VALUE rb_str_substr(VALUE, long, long);
|
||||
VALUE rb_str_subseq(VALUE, long, long);
|
||||
void rb_str_modify(VALUE);
|
||||
VALUE rb_str_freeze(VALUE);
|
||||
void rb_str_set_len(VALUE, long);
|
||||
|
|
|
|||
10
re.c
10
re.c
|
|
@ -1114,7 +1114,7 @@ rb_reg_nth_match(int nth, VALUE match)
|
|||
if (start == -1) return Qnil;
|
||||
end = RMATCH(match)->END(nth);
|
||||
len = end - start;
|
||||
str = rb_str_substr(RMATCH(match)->str, start, len);
|
||||
str = rb_str_subseq(RMATCH(match)->str, start, len);
|
||||
OBJ_INFECT(str, match);
|
||||
return str;
|
||||
}
|
||||
|
|
@ -1144,7 +1144,7 @@ rb_reg_match_pre(VALUE match)
|
|||
|
||||
if (NIL_P(match)) return Qnil;
|
||||
if (RMATCH(match)->BEG(0) == -1) return Qnil;
|
||||
str = rb_str_substr(RMATCH(match)->str, 0, RMATCH(match)->BEG(0));
|
||||
str = rb_str_subseq(RMATCH(match)->str, 0, RMATCH(match)->BEG(0));
|
||||
if (OBJ_TAINTED(match)) OBJ_TAINT(str);
|
||||
return str;
|
||||
}
|
||||
|
|
@ -1171,7 +1171,7 @@ rb_reg_match_post(VALUE match)
|
|||
if (RMATCH(match)->BEG(0) == -1) return Qnil;
|
||||
str = RMATCH(match)->str;
|
||||
pos = RMATCH(match)->END(0);
|
||||
str = rb_str_substr(str, pos, RSTRING_LEN(str) - pos);
|
||||
str = rb_str_subseq(str, pos, RSTRING_LEN(str) - pos);
|
||||
if (OBJ_TAINTED(match)) OBJ_TAINT(str);
|
||||
return str;
|
||||
}
|
||||
|
|
@ -1228,7 +1228,7 @@ match_array(VALUE match, int start)
|
|||
rb_ary_push(ary, Qnil);
|
||||
}
|
||||
else {
|
||||
VALUE str = rb_str_substr(target, regs->beg[i], regs->end[i]-regs->beg[i]);
|
||||
VALUE str = rb_str_subseq(target, regs->beg[i], regs->end[i]-regs->beg[i]);
|
||||
if (taint) OBJ_TAINT(str);
|
||||
rb_ary_push(ary, str);
|
||||
}
|
||||
|
|
@ -1423,7 +1423,7 @@ match_select(int argc, VALUE *argv, VALUE match)
|
|||
int taint = OBJ_TAINTED(match);
|
||||
|
||||
for (i=0; i<regs->num_regs; i++) {
|
||||
VALUE str = rb_str_substr(target, regs->beg[i], regs->end[i]-regs->beg[i]);
|
||||
VALUE str = rb_str_subseq(target, regs->beg[i], regs->end[i]-regs->beg[i]);
|
||||
if (taint) OBJ_TAINT(str);
|
||||
if (RTEST(rb_yield(str))) {
|
||||
rb_ary_push(result, str);
|
||||
|
|
|
|||
42
string.c
42
string.c
|
|
@ -400,10 +400,10 @@ rb_str_init(int argc, VALUE *argv, VALUE str)
|
|||
return str;
|
||||
}
|
||||
|
||||
static int
|
||||
static long
|
||||
str_strlen(VALUE str, rb_encoding *enc)
|
||||
{
|
||||
int len;
|
||||
long len;
|
||||
|
||||
if (!enc) enc = rb_enc_get(str);
|
||||
len = rb_enc_strlen(RSTRING_PTR(str), RSTRING_END(str), enc);
|
||||
|
|
@ -696,14 +696,14 @@ str_offset(const char *p, const char *e, int nth, rb_encoding *enc)
|
|||
return pp - p;
|
||||
}
|
||||
|
||||
static int
|
||||
str_sublen(VALUE str, int pos, rb_encoding *enc)
|
||||
static long
|
||||
str_sublen(VALUE str, long pos, rb_encoding *enc)
|
||||
{
|
||||
if (rb_enc_mbmaxlen(enc) == 1 || pos < 0) return pos;
|
||||
else {
|
||||
char *p = RSTRING_PTR(str);
|
||||
char *e = p + pos;
|
||||
int i;
|
||||
long i;
|
||||
|
||||
i = 0;
|
||||
while (p < e) {
|
||||
|
|
@ -720,6 +720,17 @@ rb_str_sublen(VALUE str, int len)
|
|||
return str_sublen(str, len, rb_enc_get(str));
|
||||
}
|
||||
|
||||
VALUE
|
||||
rb_str_subseq(VALUE str, long beg, long len)
|
||||
{
|
||||
VALUE str2 = rb_str_new5(str, RSTRING_PTR(str)+beg, len);
|
||||
|
||||
rb_enc_copy(str2, str);
|
||||
OBJ_INFECT(str2, str);
|
||||
|
||||
return str2;
|
||||
}
|
||||
|
||||
VALUE
|
||||
rb_str_substr(VALUE str, long beg, long len)
|
||||
{
|
||||
|
|
@ -1439,12 +1450,13 @@ rb_str_rindex_m(int argc, VALUE *argv, VALUE str)
|
|||
{
|
||||
VALUE sub;
|
||||
VALUE vpos;
|
||||
long pos;
|
||||
rb_encoding *enc = rb_enc_get(str);
|
||||
long pos, len = str_strlen(str, enc);
|
||||
|
||||
if (rb_scan_args(argc, argv, "11", &sub, &vpos) == 2) {
|
||||
pos = NUM2LONG(vpos);
|
||||
if (pos < 0) {
|
||||
pos += RSTRING_LEN(str);
|
||||
pos += len;
|
||||
if (pos < 0) {
|
||||
if (TYPE(sub) == T_REGEXP) {
|
||||
rb_backref_set(Qnil);
|
||||
|
|
@ -1452,17 +1464,15 @@ rb_str_rindex_m(int argc, VALUE *argv, VALUE str)
|
|||
return Qnil;
|
||||
}
|
||||
}
|
||||
if (pos > RSTRING_LEN(str)) pos = RSTRING_LEN(str);
|
||||
if (pos > len) pos = len;
|
||||
}
|
||||
else {
|
||||
pos = RSTRING_LEN(str);
|
||||
pos = len;
|
||||
}
|
||||
|
||||
switch (TYPE(sub)) {
|
||||
case T_REGEXP:
|
||||
/* enc = rb_get_check(str, sub); */
|
||||
pos++; /* xxx adjust for Oniguruma 5.x */
|
||||
pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos, rb_enc_get(str));
|
||||
if (RREGEXP(sub)->len) {
|
||||
pos = rb_reg_adjust_startpos(sub, str, pos, 1);
|
||||
pos = rb_reg_search(sub, str, pos, 1);
|
||||
|
|
@ -1483,6 +1493,7 @@ rb_str_rindex_m(int argc, VALUE *argv, VALUE str)
|
|||
}
|
||||
/* fall through */
|
||||
case T_STRING:
|
||||
pos = str_sublen(str, pos, enc);
|
||||
pos = rb_str_rindex(str, sub, pos);
|
||||
if (pos >= 0) return LONG2NUM(pos);
|
||||
break;
|
||||
|
|
@ -2076,6 +2087,7 @@ rb_str_slice_bang(int argc, VALUE *argv, VALUE str)
|
|||
for (i=0; i<argc; i++) {
|
||||
buf[i] = argv[i];
|
||||
}
|
||||
rb_str_modify(str);
|
||||
buf[i] = rb_str_new(0,0);
|
||||
result = rb_str_aref_m(argc, buf, str);
|
||||
if (!NIL_P(result)) {
|
||||
|
|
@ -3786,7 +3798,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str)
|
|||
break;
|
||||
}
|
||||
else if (last_null == 1) {
|
||||
rb_ary_push(result, rb_str_substr(str, beg,
|
||||
rb_ary_push(result, rb_str_subseq(str, beg,
|
||||
rb_enc_mbclen(RSTRING_PTR(str)+beg,enc)));
|
||||
beg = start;
|
||||
}
|
||||
|
|
@ -3797,7 +3809,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str)
|
|||
}
|
||||
}
|
||||
else {
|
||||
rb_ary_push(result, rb_str_substr(str, beg, end-beg));
|
||||
rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
|
||||
beg = start = END(0);
|
||||
}
|
||||
last_null = 0;
|
||||
|
|
@ -3807,7 +3819,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str)
|
|||
if (BEG(idx) == END(idx))
|
||||
tmp = rb_str_new5(str, 0, 0);
|
||||
else
|
||||
tmp = rb_str_substr(str, BEG(idx), END(idx)-BEG(idx));
|
||||
tmp = rb_str_subseq(str, BEG(idx), END(idx)-BEG(idx));
|
||||
rb_ary_push(result, tmp);
|
||||
}
|
||||
if (!NIL_P(limit) && lim <= ++i) break;
|
||||
|
|
@ -3817,7 +3829,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str)
|
|||
if (RSTRING_LEN(str) == beg)
|
||||
tmp = rb_str_new5(str, 0, 0);
|
||||
else
|
||||
tmp = rb_str_substr(str, beg, RSTRING_LEN(str)-beg);
|
||||
tmp = rb_str_subseq(str, beg, RSTRING_LEN(str)-beg);
|
||||
rb_ary_push(result, tmp);
|
||||
}
|
||||
if (NIL_P(limit) && lim == 0) {
|
||||
|
|
|
|||
Loading…
Reference in a new issue