diff options
author | nobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2018-03-15 11:08:04 +0000 |
---|---|---|
committer | nobu <nobu@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2018-03-15 11:08:04 +0000 |
commit | 2258a97fe2b21da9ec294ccedd00b3bbbc85cb07 () | |
tree | 0121480b97ec68b369acc9c7f41261929aa22c4d | |
parent | d13a2d498cb2758cd71523e1099f9591c30c2b86 (diff) |
string.c: split with block
* string.c (rb_str_split_m): yield each split substrings if the block is given, instead of returing the array. [Feature #4780] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62763 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | NEWS | 4 | ||||
-rw-r--r-- | string.c | 82 | ||||
-rw-r--r-- | test/ruby/test_string.rb | 40 |
3 files changed, 95 insertions, 31 deletions
@@ -93,6 +93,10 @@ with all sufficient information, see the ChangeLog file or Redmine * added Random.bytes. [Feature #4938] === Stdlib updates (outstanding ones only) * ERB @@ -7602,6 +7602,35 @@ static const char isspacetable[256] = { #define ascii_isspace(c) isspacetable[(unsigned char)(c)] /* * call-seq: * str.split(pattern=nil, [limit]) -> an_array @@ -7660,20 +7689,27 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) VALUE spat; VALUE limit; enum {awk, string, regexp} split_type; - long beg, end, i = 0; int lim = 0; VALUE result, tmp; if (rb_scan_args(argc, argv, "02", &spat, &limit) == 2) { lim = NUM2INT(limit); if (lim <= 0) limit = Qnil; else if (lim == 1) { if (RSTRING_LEN(str) == 0) - return rb_ary_new2(0); - return rb_ary_new3(1, rb_str_dup(str)); } i = 1; } enc = STR_ENC_GET(str); split_type = regexp; @@ -7712,7 +7748,9 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) } } - result = rb_ary_new(); beg = 0; if (split_type == awk) { char *ptr = RSTRING_PTR(str); @@ -7736,7 +7774,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) } } else if (ascii_isspace(c)) { - rb_ary_push(result, rb_str_subseq(str, beg, end-beg)); skip = 1; beg = ptr - bptr; if (!NIL_P(limit)) ++i; @@ -7763,7 +7801,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) } } else if (rb_isspace(c)) { - rb_ary_push(result, rb_str_subseq(str, beg, end-beg)); skip = 1; beg = ptr - bptr; if (!NIL_P(limit)) ++i; @@ -7792,8 +7830,7 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) ptr = t; continue; } - rb_ary_push(result, rb_str_subseq(str, substr_start - str_start, - (ptr+end) - substr_start)); ptr += end + slen; substr_start = ptr; if (!NIL_P(limit) && lim <= ++i) break; @@ -7812,14 +7849,11 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) regs = RMATCH_REGS(rb_backref_get()); if (start == end && BEG(0) == END(0)) { if (!ptr) { - rb_ary_push(result, str_new_empty(str)); break; } else if (last_null == 1) { - rb_ary_push(result, rb_str_subseq(str, beg, - rb_enc_fast_mbclen(ptr+beg, - ptr+len, - enc))); beg = start; } else { @@ -7832,37 +7866,23 @@ rb_str_split_m(int argc, VALUE *argv, VALUE str) } } else { - rb_ary_push(result, rb_str_subseq(str, beg, end-beg)); beg = start = END(0); } last_null = 0; for (idx=1; idx < regs->num_regs; idx++) { if (BEG(idx) == -1) continue; - if (BEG(idx) == END(idx)) - tmp = str_new_empty(str); - else - tmp = rb_str_subseq(str, BEG(idx), END(idx)-BEG(idx)); - rb_ary_push(result, tmp); } if (!NIL_P(limit) && lim <= ++i) break; } } if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) { - if (RSTRING_LEN(str) == beg) - tmp = str_new_empty(str); - else - tmp = rb_str_subseq(str, beg, RSTRING_LEN(str)-beg); - rb_ary_push(result, tmp); - } - if (NIL_P(limit) && lim == 0) { - long len; - while ((len = RARRAY_LEN(result)) > 0 && - (tmp = RARRAY_AREF(result, len-1), RSTRING_LEN(tmp) == 0)) - rb_ary_pop(result); } - return result; } VALUE @@ -1699,7 +1699,46 @@ CODE assert_equal([S("a"), S(""), S("b"), S("c"), S("")], S("a||b|c|").split(S('|'), -1)) assert_equal([], "".split(//, 1)) ensure $; = fs end @@ -1762,6 +1801,7 @@ CODE s.split("b", 1).map(&:upcase!) assert_equal("abc", s) end def test_squeeze assert_equal(S("abc"), S("aaabbbbccc").squeeze) assert_equal(S("aa bb cc"), S("aa bb cc").squeeze(S(" "))) |