From: Nobuyoshi Nakada Date: 2008-12-09T02:27:34+09:00 Subject: [ruby-core:20431] Re: [Feature #836] Patches for StringScanner, adding #size, #captures and #values_at Hi, At Mon, 8 Dec 2008 11:20:55 +0900, Stefan Rusterholz wrote in [ruby-core:20412]: > The methods are named to be consistent with MatchData. > My C-fu isn't very strong, so a review of the patch would be appreciated. > I attached the revised code and a diff file. If other formats are wished, please tell. > If I need to submit something else with that patch, please tell. * Variable declaration is disallowed after executing statements. * call-seq: for captures was `size'. Index: ext/strscan/strscan.c =================================================================== --- ext/strscan/strscan.c (revision 20570) +++ ext/strscan/strscan.c (working copy) @@ -964,4 +964,90 @@ strscan_aref(VALUE self, VALUE idx) /* + * call-seq: size + * + * Return the amount of subgroups in the most recent match. + * The full match counts as a subgroup. + * + * s = StringScanner.new("Fri Dec 12 1975 14:39") + * s.scan(/(\w+) (\w+) (\d+) /) # -> "Fri Dec 12 " + * s.size # -> 4 + */ +static VALUE +strscan_size(VALUE self) +{ + struct strscanner *p; + + GET_SCANNER(self, p); + if (! MATCHED_P(p)) return Qnil; + return INT2FIX(p->regs.num_regs); +} + +/* + * call-seq: captures + * + * Returns the subgroups in the most recent match (not including the full match). + * If nothing was priorly matched, it returns nil. + * + * s = StringScanner.new("Fri Dec 12 1975 14:39") + * s.scan(/(\w+) (\w+) (\d+) /) # -> "Fri Dec 12 " + * s.captures # -> ["Fri", "Dec", "12"] + * s.scan(/(\w+) (\w+) (\d+) /) # -> nil + * s.captures # -> nil + */ +static VALUE +strscan_captures(VALUE self) +{ + struct strscanner *p; + int i, num_regs; + VALUE new_ary; + + GET_SCANNER(self, p); + if (! MATCHED_P(p)) return Qnil; + + num_regs = p->regs.num_regs; + new_ary = rb_ary_new2(num_regs); + + for (i = 1; i < num_regs; i++) { + VALUE str = extract_range(p, p->prev + p->regs.beg[i], + p->prev + p->regs.end[i]); + rb_ary_push(new_ary, str); + } + + return new_ary; +} + +/* + * call-seq: + * scanner.values_at( i1, i2, ... iN ) -> an_array + * + * Returns the subgroups in the most recent match at the given indices. + * If nothing was priorly matched, it returns nil. + * + * s = StringScanner.new("Fri Dec 12 1975 14:39") + * s.scan(/(\w+) (\w+) (\d+) /) # -> "Fri Dec 12 " + * s.values_at 0, -1, 5, 2 # -> ["Fri Dec 12 ", "12", nil, "Dec"] + * s.scan(/(\w+) (\w+) (\d+) /) # -> nil + * s.captures # -> nil + */ + +static VALUE +strscan_values_at(int argc, VALUE *argv, VALUE self) +{ + struct strscanner *p; + long i; + VALUE new_ary; + + GET_SCANNER(self, p); + if (! MATCHED_P(p)) return Qnil; + + new_ary = rb_ary_new2(argc); + for (i = 0; ipre-match (in the regular expression sense) of the last scan. * @@ -1312,4 +1398,7 @@ Init_strscan(void) rb_define_method(StringScanner, "pre_match", strscan_pre_match, 0); rb_define_method(StringScanner, "post_match", strscan_post_match, 0); + rb_define_method(StringScanner, "size", strscan_size, 0); + rb_define_method(StringScanner, "captures", strscan_captures, 0); + rb_define_method(StringScanner, "values_at", strscan_values_at, -1); rb_define_method(StringScanner, "rest", strscan_rest, 0); -- Nobu Nakada