re2 0.6.0 → 0.6.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -2
- data/Rakefile +4 -0
- data/ext/re2/re2.cc +1168 -1161
- data/spec/re2/regexp_spec.rb +4 -0
- metadata +12 -11
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 44eacddc1b64782c61eff633b15f40db1ba3b9d9
|
4
|
+
data.tar.gz: 377ae25429bb8804c03a951d0150097d11cb808e
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 1f09c136bb17bfabfe739882cc61c7f0bf50dfba140aec66db0a6e2962de0d25e844804812137b5c3e798a61bb2b8002d83fc4d7766bc7fc52ce159535634b4e
|
7
|
+
data.tar.gz: f9742540b13859de929a299ac28a646d305e4a72bcffdd0588dad268f53cb0135f440a1f914cd7504a3b01eb5bf9c569c54c83cfaa4ba0b7f131326ef01a0212
|
data/README.md
CHANGED
@@ -1,9 +1,12 @@
|
|
1
|
-
re2 [![Build Status](https://
|
1
|
+
re2 [![Build Status](https://travis-ci.org/mudge/re2.svg?branch=master)](http://travis-ci.org/mudge/re2)
|
2
2
|
===
|
3
3
|
|
4
4
|
A Ruby binding to [re2][], an "efficient, principled regular expression
|
5
5
|
library".
|
6
6
|
|
7
|
+
**Current version:** 0.6.1
|
8
|
+
**Supported Ruby versions:** 1.8.7, 1.9.2, 1.9.3, 2.0.0, 2.1.0, Rubinius 2.2
|
9
|
+
|
7
10
|
Installation
|
8
11
|
------------
|
9
12
|
|
@@ -158,7 +161,7 @@ All feedback should go to the mailing list: <mailto:ruby.re2@librelist.com>
|
|
158
161
|
[ruby-dev]: http://packages.debian.org/ruby-dev
|
159
162
|
[build-essential]: http://packages.debian.org/build-essential
|
160
163
|
[Regexp]: http://ruby-doc.org/core/classes/Regexp.html
|
161
|
-
[MatchData]: http://ruby-doc.org/core/classes/MatchData.html
|
164
|
+
[MatchData]: http://ruby-doc.org/core/classes/MatchData.html
|
162
165
|
[Homebrew]: http://mxcl.github.com/homebrew
|
163
166
|
[libre2-dev]: http://packages.debian.org/search?keywords=libre2-dev
|
164
167
|
[official syntax page]: http://code.google.com/p/re2/wiki/Syntax
|
data/Rakefile
CHANGED
@@ -9,6 +9,10 @@ Rake::TestTask.new do |t|
|
|
9
9
|
t.verbose = true
|
10
10
|
end
|
11
11
|
|
12
|
+
task :valgrind do
|
13
|
+
system "valgrind --tool=memcheck --leak-check=full --show-reachable=no --num-callers=15 --track-fds=yes --workaround-gcc296-bugs=yes --max-stackframe=7304328 --dsymutil=yes --track-origins=yes --log-file=report.txt ruby spec/leak.rb"
|
14
|
+
end
|
15
|
+
|
12
16
|
task :test => :compile
|
13
17
|
task :spec => :test
|
14
18
|
task :default => :test
|
data/ext/re2/re2.cc
CHANGED
@@ -17,1304 +17,1311 @@ using std::nothrow;
|
|
17
17
|
using std::map;
|
18
18
|
using std::vector;
|
19
19
|
|
20
|
-
|
21
|
-
#
|
22
|
-
|
23
|
-
|
24
|
-
(
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
(
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
#
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
20
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
21
|
+
#include <ruby/encoding.h>
|
22
|
+
#define ENCODED_STR_NEW(str, length, encoding) \
|
23
|
+
({ \
|
24
|
+
VALUE _string = rb_str_new(str, length); \
|
25
|
+
int _enc = rb_enc_find_index(encoding); \
|
26
|
+
rb_enc_associate_index(_string, _enc); \
|
27
|
+
_string; \
|
28
|
+
})
|
29
|
+
#define ENCODED_STR_NEW2(str, length, str2) \
|
30
|
+
({ \
|
31
|
+
VALUE _string = rb_str_new(str, length); \
|
32
|
+
int _enc = rb_enc_get_index(str2); \
|
33
|
+
rb_enc_associate_index(_string, _enc); \
|
34
|
+
_string; \
|
35
|
+
})
|
36
|
+
#else
|
37
|
+
#define ENCODED_STR_NEW(str, length, encoding) \
|
38
|
+
rb_str_new((const char *)str, (long)length)
|
39
|
+
#define ENCODED_STR_NEW2(str, length, str2) \
|
40
|
+
rb_str_new((const char *)str, (long)length)
|
41
|
+
#endif
|
42
|
+
|
43
|
+
#define BOOL2RUBY(v) (v ? Qtrue : Qfalse)
|
44
|
+
#define UNUSED(x) ((void)x)
|
45
|
+
|
46
|
+
#ifndef RSTRING_LEN
|
47
|
+
#define RSTRING_LEN(x) (RSTRING(x)->len)
|
48
|
+
#endif
|
49
|
+
|
50
|
+
#ifndef RSTRING_PTR
|
51
|
+
#define RSTRING_PTR(x) (RSTRING(x)->ptr)
|
52
|
+
#endif
|
53
|
+
|
54
|
+
#ifdef HAVE_ENDPOS_ARGUMENT
|
55
|
+
#define match(pattern, text, startpos, endpos, anchor, match, nmatch) \
|
56
|
+
(pattern->Match(text, startpos, endpos, anchor, match, nmatch))
|
57
|
+
#else
|
58
|
+
#define match(pattern, text, startpos, endpos, anchor, match, nmatch) \
|
59
|
+
(pattern->Match(text, startpos, anchor, match, nmatch))
|
60
|
+
#endif
|
61
|
+
|
62
|
+
typedef struct {
|
63
|
+
RE2 *pattern;
|
64
|
+
} re2_pattern;
|
65
|
+
|
66
|
+
typedef struct {
|
67
|
+
re2::StringPiece *matches;
|
68
|
+
int number_of_matches;
|
69
|
+
VALUE regexp, text;
|
70
|
+
} re2_matchdata;
|
71
|
+
|
72
|
+
typedef struct {
|
73
|
+
re2::StringPiece *input;
|
74
|
+
int number_of_capturing_groups;
|
75
|
+
VALUE regexp, text;
|
76
|
+
} re2_scanner;
|
77
|
+
|
78
|
+
VALUE re2_mRE2, re2_cRegexp, re2_cMatchData, re2_cScanner;
|
79
|
+
|
80
|
+
/* Symbols used in RE2 options. */
|
81
|
+
static ID id_utf8, id_posix_syntax, id_longest_match, id_log_errors,
|
82
|
+
id_max_mem, id_literal, id_never_nl, id_case_sensitive,
|
83
|
+
id_perl_classes, id_word_boundary, id_one_line;
|
84
|
+
|
85
|
+
void re2_matchdata_mark(re2_matchdata* self) {
|
86
|
+
rb_gc_mark(self->regexp);
|
87
|
+
rb_gc_mark(self->text);
|
88
|
+
}
|
43
89
|
|
44
|
-
|
45
|
-
|
90
|
+
void re2_matchdata_free(re2_matchdata* self) {
|
91
|
+
if (self->matches) {
|
92
|
+
delete[] self->matches;
|
93
|
+
}
|
94
|
+
free(self);
|
95
|
+
}
|
46
96
|
|
47
|
-
|
48
|
-
|
49
|
-
|
97
|
+
void re2_scanner_mark(re2_scanner* self) {
|
98
|
+
rb_gc_mark(self->regexp);
|
99
|
+
rb_gc_mark(self->text);
|
100
|
+
}
|
50
101
|
|
51
|
-
|
52
|
-
|
53
|
-
|
102
|
+
void re2_scanner_free(re2_scanner* self) {
|
103
|
+
if (self->input) {
|
104
|
+
delete self->input;
|
105
|
+
}
|
106
|
+
free(self);
|
107
|
+
}
|
54
108
|
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
#endif
|
109
|
+
void re2_regexp_free(re2_pattern* self) {
|
110
|
+
if (self->pattern) {
|
111
|
+
delete self->pattern;
|
112
|
+
}
|
113
|
+
free(self);
|
114
|
+
}
|
62
115
|
|
63
|
-
|
64
|
-
|
65
|
-
|
116
|
+
static VALUE re2_matchdata_allocate(VALUE klass) {
|
117
|
+
re2_matchdata *m;
|
118
|
+
return Data_Make_Struct(klass, re2_matchdata, re2_matchdata_mark,
|
119
|
+
re2_matchdata_free, m);
|
120
|
+
}
|
66
121
|
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
122
|
+
static VALUE re2_scanner_allocate(VALUE klass) {
|
123
|
+
re2_scanner *c;
|
124
|
+
return Data_Make_Struct(klass, re2_scanner, re2_scanner_mark,
|
125
|
+
re2_scanner_free, c);
|
126
|
+
}
|
127
|
+
|
128
|
+
/*
|
129
|
+
* Returns a frozen copy of the string passed into +match+.
|
130
|
+
*
|
131
|
+
* @return [String] a frozen copy of the passed string.
|
132
|
+
* @example
|
133
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
134
|
+
* m.string #=> "bob 123"
|
135
|
+
*/
|
136
|
+
static VALUE re2_matchdata_string(VALUE self) {
|
137
|
+
re2_matchdata *m;
|
138
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
72
139
|
|
73
|
-
|
74
|
-
|
75
|
-
int number_of_capturing_groups;
|
76
|
-
VALUE regexp, text;
|
77
|
-
} re2_scanner;
|
140
|
+
return m->text;
|
141
|
+
}
|
78
142
|
|
79
|
-
|
143
|
+
/*
|
144
|
+
* Returns the string passed into the scanner.
|
145
|
+
*
|
146
|
+
* @return [String] the original string.
|
147
|
+
* @example
|
148
|
+
* c = RE2::Regexp.new('(\d+)').scan("foo")
|
149
|
+
* c.string #=> "foo"
|
150
|
+
*/
|
151
|
+
static VALUE re2_scanner_string(VALUE self) {
|
152
|
+
re2_scanner *c;
|
153
|
+
Data_Get_Struct(self, re2_scanner, c);
|
80
154
|
|
81
|
-
|
82
|
-
|
83
|
-
id_max_mem, id_literal, id_never_nl, id_case_sensitive,
|
84
|
-
id_perl_classes, id_word_boundary, id_one_line;
|
155
|
+
return c->text;
|
156
|
+
}
|
85
157
|
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
158
|
+
/*
|
159
|
+
* Rewind the scanner to the start of the string.
|
160
|
+
*
|
161
|
+
* @example
|
162
|
+
* s = RE2::Regexp.new('(\d+)').scan("1 2 3")
|
163
|
+
* e = s.to_enum
|
164
|
+
* e.scan #=> ["1"]
|
165
|
+
* e.scan #=> ["2"]
|
166
|
+
* s.rewind
|
167
|
+
* e.scan #=> ["1"]
|
168
|
+
*/
|
169
|
+
static VALUE re2_scanner_rewind(VALUE self) {
|
170
|
+
re2_scanner *c;
|
171
|
+
Data_Get_Struct(self, re2_scanner, c);
|
90
172
|
|
91
|
-
|
92
|
-
if (self->matches) {
|
93
|
-
delete[] self->matches;
|
94
|
-
}
|
95
|
-
free(self);
|
96
|
-
}
|
173
|
+
c->input = new(nothrow) re2::StringPiece(StringValuePtr(c->text));
|
97
174
|
|
98
|
-
|
99
|
-
|
100
|
-
rb_gc_mark(self->text);
|
101
|
-
}
|
175
|
+
return self;
|
176
|
+
}
|
102
177
|
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
178
|
+
/*
|
179
|
+
* Scan the given text incrementally for matches, returning an array of
|
180
|
+
* matches on each subsequent call. Returns nil if no matches are found.
|
181
|
+
*
|
182
|
+
* @return [Array<String>] the matches.
|
183
|
+
* @example
|
184
|
+
* s = RE2::Regexp.new('(\w+)').scan("Foo bar baz")
|
185
|
+
* s.scan #=> ["Foo"]
|
186
|
+
* s.scan #=> ["bar"]
|
187
|
+
*/
|
188
|
+
static VALUE re2_scanner_scan(VALUE self) {
|
189
|
+
int i;
|
190
|
+
re2_pattern *p;
|
191
|
+
re2_scanner *c;
|
192
|
+
VALUE result;
|
193
|
+
|
194
|
+
Data_Get_Struct(self, re2_scanner, c);
|
195
|
+
Data_Get_Struct(c->regexp, re2_pattern, p);
|
196
|
+
|
197
|
+
vector<RE2::Arg> argv(c->number_of_capturing_groups);
|
198
|
+
vector<RE2::Arg*> args(c->number_of_capturing_groups);
|
199
|
+
vector<string> matches(c->number_of_capturing_groups);
|
200
|
+
|
201
|
+
for (i = 0; i < c->number_of_capturing_groups; i++) {
|
202
|
+
matches[i] = "";
|
203
|
+
argv[i] = &matches[i];
|
204
|
+
args[i] = &argv[i];
|
108
205
|
}
|
109
206
|
|
110
|
-
|
111
|
-
|
112
|
-
|
207
|
+
if (RE2::FindAndConsumeN(c->input, *p->pattern, &args[0],
|
208
|
+
c->number_of_capturing_groups)) {
|
209
|
+
result = rb_ary_new2(c->number_of_capturing_groups);
|
210
|
+
for (i = 0; i < c->number_of_capturing_groups; i++) {
|
211
|
+
if (matches[i].empty()) {
|
212
|
+
rb_ary_push(result, Qnil);
|
213
|
+
} else {
|
214
|
+
rb_ary_push(result, ENCODED_STR_NEW(matches[i].data(),
|
215
|
+
matches[i].size(),
|
216
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1"));
|
217
|
+
}
|
113
218
|
}
|
114
|
-
|
219
|
+
} else {
|
220
|
+
result = Qnil;
|
115
221
|
}
|
116
222
|
|
117
|
-
|
118
|
-
|
119
|
-
return Data_Make_Struct(klass, re2_matchdata, re2_matchdata_mark,
|
120
|
-
re2_matchdata_free, m);
|
121
|
-
}
|
223
|
+
return result;
|
224
|
+
}
|
122
225
|
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
226
|
+
/*
|
227
|
+
* Returns the number of elements in the match array (including nils).
|
228
|
+
*
|
229
|
+
* @return [Fixnum] the number of elements
|
230
|
+
* @example
|
231
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
232
|
+
* m.size #=> 2
|
233
|
+
* m.length #=> 2
|
234
|
+
*/
|
235
|
+
static VALUE re2_matchdata_size(VALUE self) {
|
236
|
+
re2_matchdata *m;
|
237
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
128
238
|
|
129
|
-
|
130
|
-
|
131
|
-
*
|
132
|
-
* @return [String] a frozen copy of the passed string.
|
133
|
-
* @example
|
134
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
135
|
-
* m.string #=> "bob 123"
|
136
|
-
*/
|
137
|
-
static VALUE re2_matchdata_string(VALUE self) {
|
138
|
-
re2_matchdata *m;
|
139
|
-
Data_Get_Struct(self, re2_matchdata, m);
|
140
|
-
|
141
|
-
return m->text;
|
142
|
-
}
|
239
|
+
return INT2FIX(m->number_of_matches);
|
240
|
+
}
|
143
241
|
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
|
157
|
-
}
|
242
|
+
/*
|
243
|
+
* Returns the {RE2::Regexp} used in the match.
|
244
|
+
*
|
245
|
+
* @return [RE2::Regexp] the regexp used in the match
|
246
|
+
* @example
|
247
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
248
|
+
* m.regexp #=> #<RE2::Regexp /(\d+)/>
|
249
|
+
*/
|
250
|
+
static VALUE re2_matchdata_regexp(VALUE self) {
|
251
|
+
re2_matchdata *m;
|
252
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
253
|
+
return m->regexp;
|
254
|
+
}
|
158
255
|
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
static VALUE re2_scanner_rewind(VALUE self) {
|
171
|
-
re2_scanner *c;
|
172
|
-
Data_Get_Struct(self, re2_scanner, c);
|
173
|
-
|
174
|
-
c->input = new(nothrow) re2::StringPiece(StringValuePtr(c->text));
|
175
|
-
|
176
|
-
return self;
|
177
|
-
}
|
256
|
+
/*
|
257
|
+
* Returns the {RE2::Regexp} used in the scanner.
|
258
|
+
*
|
259
|
+
* @return [RE2::Regexp] the regexp used in the scanner
|
260
|
+
* @example
|
261
|
+
* c = RE2::Regexp.new('(\d+)').scan("bob 123")
|
262
|
+
* c.regexp #=> #<RE2::Regexp /(\d+)/>
|
263
|
+
*/
|
264
|
+
static VALUE re2_scanner_regexp(VALUE self) {
|
265
|
+
re2_scanner *c;
|
266
|
+
Data_Get_Struct(self, re2_scanner, c);
|
178
267
|
|
179
|
-
|
180
|
-
|
181
|
-
* matches on each subsequent call. Returns nil if no matches are found.
|
182
|
-
*
|
183
|
-
* @return [Array<String>] the matches.
|
184
|
-
* @example
|
185
|
-
* s = RE2::Regexp.new('(\w+)').scan("Foo bar baz")
|
186
|
-
* s.scan #=> ["Foo"]
|
187
|
-
* s.scan #=> ["bar"]
|
188
|
-
*/
|
189
|
-
static VALUE re2_scanner_scan(VALUE self) {
|
190
|
-
int i;
|
191
|
-
re2_pattern *p;
|
192
|
-
re2_scanner *c;
|
193
|
-
VALUE result;
|
194
|
-
|
195
|
-
Data_Get_Struct(self, re2_scanner, c);
|
196
|
-
Data_Get_Struct(c->regexp, re2_pattern, p);
|
197
|
-
|
198
|
-
vector<RE2::Arg> argv(c->number_of_capturing_groups);
|
199
|
-
vector<RE2::Arg*> args(c->number_of_capturing_groups);
|
200
|
-
vector<string> matches(c->number_of_capturing_groups);
|
268
|
+
return c->regexp;
|
269
|
+
}
|
201
270
|
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
}
|
271
|
+
static VALUE re2_regexp_allocate(VALUE klass) {
|
272
|
+
re2_pattern *p;
|
273
|
+
return Data_Make_Struct(klass, re2_pattern, 0, re2_regexp_free, p);
|
274
|
+
}
|
207
275
|
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
276
|
+
/*
|
277
|
+
* Returns the array of matches.
|
278
|
+
*
|
279
|
+
* @return [Array<String, nil>] the array of matches
|
280
|
+
* @example
|
281
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
282
|
+
* m.to_a #=> ["123", "123"]
|
283
|
+
*/
|
284
|
+
static VALUE re2_matchdata_to_a(VALUE self) {
|
285
|
+
int i;
|
286
|
+
re2_matchdata *m;
|
287
|
+
re2_pattern *p;
|
288
|
+
re2::StringPiece *match;
|
289
|
+
VALUE array;
|
290
|
+
|
291
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
292
|
+
Data_Get_Struct(m->regexp, re2_pattern, p);
|
293
|
+
|
294
|
+
array = rb_ary_new2(m->number_of_matches);
|
295
|
+
for (i = 0; i < m->number_of_matches; i++) {
|
296
|
+
match = &m->matches[i];
|
297
|
+
|
298
|
+
if (match->empty()) {
|
299
|
+
rb_ary_push(array, Qnil);
|
220
300
|
} else {
|
221
|
-
|
301
|
+
rb_ary_push(array, ENCODED_STR_NEW(match->data(), match->size(),
|
302
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1"));
|
222
303
|
}
|
223
|
-
|
224
|
-
return result;
|
225
304
|
}
|
226
305
|
|
227
|
-
|
228
|
-
|
229
|
-
*
|
230
|
-
* @return [Fixnum] the number of elements
|
231
|
-
* @example
|
232
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
233
|
-
* m.size #=> 2
|
234
|
-
* m.length #=> 2
|
235
|
-
*/
|
236
|
-
static VALUE re2_matchdata_size(VALUE self) {
|
237
|
-
re2_matchdata *m;
|
238
|
-
Data_Get_Struct(self, re2_matchdata, m);
|
239
|
-
|
240
|
-
return INT2FIX(m->number_of_matches);
|
241
|
-
}
|
306
|
+
return array;
|
307
|
+
}
|
242
308
|
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
* @example
|
248
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
249
|
-
* m.regexp #=> #<RE2::Regexp /(\d+)/>
|
250
|
-
*/
|
251
|
-
static VALUE re2_matchdata_regexp(VALUE self) {
|
252
|
-
re2_matchdata *m;
|
253
|
-
Data_Get_Struct(self, re2_matchdata, m);
|
254
|
-
return m->regexp;
|
255
|
-
}
|
309
|
+
static VALUE re2_matchdata_nth_match(int nth, VALUE self) {
|
310
|
+
re2_matchdata *m;
|
311
|
+
re2_pattern *p;
|
312
|
+
re2::StringPiece *match;
|
256
313
|
|
257
|
-
|
258
|
-
|
259
|
-
*
|
260
|
-
* @return [RE2::Regexp] the regexp used in the scanner
|
261
|
-
* @example
|
262
|
-
* c = RE2::Regexp.new('(\d+)').scan("bob 123")
|
263
|
-
* c.regexp #=> #<RE2::Regexp /(\d+)/>
|
264
|
-
*/
|
265
|
-
static VALUE re2_scanner_regexp(VALUE self) {
|
266
|
-
re2_scanner *c;
|
267
|
-
Data_Get_Struct(self, re2_scanner, c);
|
268
|
-
|
269
|
-
return c->regexp;
|
270
|
-
}
|
314
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
315
|
+
Data_Get_Struct(m->regexp, re2_pattern, p);
|
271
316
|
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
317
|
+
if (nth < 0 || nth >= m->number_of_matches) {
|
318
|
+
return Qnil;
|
319
|
+
} else {
|
320
|
+
match = &m->matches[nth];
|
276
321
|
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
|
282
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
283
|
-
* m.to_a #=> ["123", "123"]
|
284
|
-
*/
|
285
|
-
static VALUE re2_matchdata_to_a(VALUE self) {
|
286
|
-
int i;
|
287
|
-
re2_matchdata *m;
|
288
|
-
re2_pattern *p;
|
289
|
-
re2::StringPiece match;
|
290
|
-
VALUE array;
|
291
|
-
|
292
|
-
Data_Get_Struct(self, re2_matchdata, m);
|
293
|
-
Data_Get_Struct(m->regexp, re2_pattern, p);
|
294
|
-
|
295
|
-
array = rb_ary_new2(m->number_of_matches);
|
296
|
-
for (i = 0; i < m->number_of_matches; i++) {
|
297
|
-
if (m->matches[i].empty()) {
|
298
|
-
rb_ary_push(array, Qnil);
|
299
|
-
} else {
|
300
|
-
match = m->matches[i];
|
301
|
-
rb_ary_push(array, ENCODED_STR_NEW(match.data(), match.size(),
|
302
|
-
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1"));
|
303
|
-
}
|
322
|
+
if (match->empty()) {
|
323
|
+
return Qnil;
|
324
|
+
} else {
|
325
|
+
return ENCODED_STR_NEW(match->data(), match->size(),
|
326
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
304
327
|
}
|
305
|
-
|
306
|
-
return array;
|
307
328
|
}
|
329
|
+
}
|
308
330
|
|
309
|
-
|
310
|
-
|
311
|
-
|
312
|
-
|
331
|
+
static VALUE re2_matchdata_named_match(const char* name, VALUE self) {
|
332
|
+
int idx;
|
333
|
+
re2_matchdata *m;
|
334
|
+
re2_pattern *p;
|
335
|
+
map<string, int> groups;
|
336
|
+
string name_as_string(name);
|
313
337
|
|
314
|
-
|
315
|
-
|
338
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
339
|
+
Data_Get_Struct(m->regexp, re2_pattern, p);
|
316
340
|
|
317
|
-
|
318
|
-
return Qnil;
|
319
|
-
} else {
|
320
|
-
match = m->matches[nth];
|
341
|
+
groups = p->pattern->NamedCapturingGroups();
|
321
342
|
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
|
326
|
-
|
327
|
-
}
|
328
|
-
}
|
343
|
+
if (groups.count(name_as_string) == 1) {
|
344
|
+
idx = groups[name_as_string];
|
345
|
+
return re2_matchdata_nth_match(idx, self);
|
346
|
+
} else {
|
347
|
+
return Qnil;
|
329
348
|
}
|
349
|
+
}
|
330
350
|
|
331
|
-
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
|
351
|
+
/*
|
352
|
+
* Retrieve zero, one or more matches by index or name.
|
353
|
+
*
|
354
|
+
* @return [Array<String, nil>, String, Boolean]
|
355
|
+
*
|
356
|
+
* @overload [](index)
|
357
|
+
* Access a particular match by index.
|
358
|
+
*
|
359
|
+
* @param [Fixnum] index the index of the match to fetch
|
360
|
+
* @return [String, nil] the specified match
|
361
|
+
* @example
|
362
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
363
|
+
* m[0] #=> "123"
|
364
|
+
*
|
365
|
+
* @overload [](start, length)
|
366
|
+
* Access a range of matches by starting index and length.
|
367
|
+
*
|
368
|
+
* @param [Fixnum] start the index from which to start
|
369
|
+
* @param [Fixnum] length the number of elements to fetch
|
370
|
+
* @return [Array<String, nil>] the specified matches
|
371
|
+
* @example
|
372
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
373
|
+
* m[0, 1] #=> ["123"]
|
374
|
+
*
|
375
|
+
* @overload [](range)
|
376
|
+
* Access a range of matches by index.
|
377
|
+
*
|
378
|
+
* @param [Range] range the range of match indexes to fetch
|
379
|
+
* @return [Array<String, nil>] the specified matches
|
380
|
+
* @example
|
381
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
382
|
+
* m[0..1] #=> "[123", "123"]
|
383
|
+
*
|
384
|
+
* @overload [](name)
|
385
|
+
* Access a particular match by name.
|
386
|
+
*
|
387
|
+
* @param [String, Symbol] name the name of the match to fetch
|
388
|
+
* @return [String, nil] the specific match
|
389
|
+
* @example
|
390
|
+
* m = RE2::Regexp.new('(?P<number>\d+)').match("bob 123")
|
391
|
+
* m["number"] #=> "123"
|
392
|
+
* m[:number] #=> "123"
|
393
|
+
*/
|
394
|
+
static VALUE re2_matchdata_aref(int argc, VALUE *argv, VALUE self) {
|
395
|
+
VALUE idx, rest;
|
396
|
+
rb_scan_args(argc, argv, "11", &idx, &rest);
|
397
|
+
|
398
|
+
if (TYPE(idx) == T_STRING) {
|
399
|
+
return re2_matchdata_named_match(StringValuePtr(idx), self);
|
400
|
+
} else if (SYMBOL_P(idx)) {
|
401
|
+
return re2_matchdata_named_match(rb_id2name(SYM2ID(idx)), self);
|
402
|
+
} else if (!NIL_P(rest) || !FIXNUM_P(idx) || FIX2INT(idx) < 0) {
|
403
|
+
return rb_ary_aref(argc, argv, re2_matchdata_to_a(self));
|
404
|
+
} else {
|
405
|
+
return re2_matchdata_nth_match(FIX2INT(idx), self);
|
406
|
+
}
|
407
|
+
}
|
337
408
|
|
338
|
-
|
339
|
-
|
409
|
+
/*
|
410
|
+
* Returns the entire matched string.
|
411
|
+
*
|
412
|
+
* @return [String] the entire matched string
|
413
|
+
*/
|
414
|
+
static VALUE re2_matchdata_to_s(VALUE self) {
|
415
|
+
return re2_matchdata_nth_match(0, self);
|
416
|
+
}
|
340
417
|
|
341
|
-
|
418
|
+
/*
|
419
|
+
* Returns a printable version of the match.
|
420
|
+
*
|
421
|
+
* @return [String] a printable version of the match
|
422
|
+
* @example
|
423
|
+
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
424
|
+
* m.inspect #=> "#<RE2::MatchData \"123\" 1:\"123\">"
|
425
|
+
*/
|
426
|
+
static VALUE re2_matchdata_inspect(VALUE self) {
|
427
|
+
int i;
|
428
|
+
re2_matchdata *m;
|
429
|
+
re2_pattern *p;
|
430
|
+
VALUE match, result;
|
431
|
+
ostringstream output;
|
342
432
|
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
|
347
|
-
|
433
|
+
Data_Get_Struct(self, re2_matchdata, m);
|
434
|
+
Data_Get_Struct(m->regexp, re2_pattern, p);
|
435
|
+
|
436
|
+
output << "#<RE2::MatchData";
|
437
|
+
|
438
|
+
for (i = 0; i < m->number_of_matches; i++) {
|
439
|
+
output << " ";
|
440
|
+
|
441
|
+
if (i > 0) {
|
442
|
+
output << i << ":";
|
348
443
|
}
|
349
|
-
}
|
350
444
|
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
|
355
|
-
*
|
356
|
-
* @overload [](index)
|
357
|
-
* Access a particular match by index.
|
358
|
-
*
|
359
|
-
* @param [Fixnum] index the index of the match to fetch
|
360
|
-
* @return [String, nil] the specified match
|
361
|
-
* @example
|
362
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
363
|
-
* m[0] #=> "123"
|
364
|
-
*
|
365
|
-
* @overload [](start, length)
|
366
|
-
* Access a range of matches by starting index and length.
|
367
|
-
*
|
368
|
-
* @param [Fixnum] start the index from which to start
|
369
|
-
* @param [Fixnum] length the number of elements to fetch
|
370
|
-
* @return [Array<String, nil>] the specified matches
|
371
|
-
* @example
|
372
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
373
|
-
* m[0, 1] #=> ["123"]
|
374
|
-
*
|
375
|
-
* @overload [](range)
|
376
|
-
* Access a range of matches by index.
|
377
|
-
*
|
378
|
-
* @param [Range] range the range of match indexes to fetch
|
379
|
-
* @return [Array<String, nil>] the specified matches
|
380
|
-
* @example
|
381
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
382
|
-
* m[0..1] #=> "[123", "123"]
|
383
|
-
*
|
384
|
-
* @overload [](name)
|
385
|
-
* Access a particular match by name.
|
386
|
-
*
|
387
|
-
* @param [String, Symbol] name the name of the match to fetch
|
388
|
-
* @return [String, nil] the specific match
|
389
|
-
* @example
|
390
|
-
* m = RE2::Regexp.new('(?P<number>\d+)').match("bob 123")
|
391
|
-
* m["number"] #=> "123"
|
392
|
-
* m[:number] #=> "123"
|
393
|
-
*/
|
394
|
-
static VALUE re2_matchdata_aref(int argc, VALUE *argv, VALUE self) {
|
395
|
-
VALUE idx, rest;
|
396
|
-
rb_scan_args(argc, argv, "11", &idx, &rest);
|
397
|
-
|
398
|
-
if (TYPE(idx) == T_STRING) {
|
399
|
-
return re2_matchdata_named_match(StringValuePtr(idx), self);
|
400
|
-
} else if (TYPE(idx) == T_SYMBOL) {
|
401
|
-
return re2_matchdata_named_match(rb_id2name(SYM2ID(idx)), self);
|
402
|
-
} else if (!NIL_P(rest) || !FIXNUM_P(idx) || FIX2INT(idx) < 0) {
|
403
|
-
return rb_ary_aref(argc, argv, re2_matchdata_to_a(self));
|
445
|
+
match = re2_matchdata_nth_match(i, self);
|
446
|
+
|
447
|
+
if (match == Qnil) {
|
448
|
+
output << "nil";
|
404
449
|
} else {
|
405
|
-
|
450
|
+
output << "\"" << StringValuePtr(match) << "\"";
|
406
451
|
}
|
407
452
|
}
|
408
453
|
|
409
|
-
|
410
|
-
* Returns the entire matched string.
|
411
|
-
*
|
412
|
-
* @return [String] the entire matched string
|
413
|
-
*/
|
414
|
-
static VALUE re2_matchdata_to_s(VALUE self) {
|
415
|
-
return re2_matchdata_nth_match(0, self);
|
416
|
-
}
|
454
|
+
output << ">";
|
417
455
|
|
418
|
-
|
419
|
-
|
420
|
-
*
|
421
|
-
* @return [String] a printable version of the match
|
422
|
-
* @example
|
423
|
-
* m = RE2::Regexp.new('(\d+)').match("bob 123")
|
424
|
-
* m.inspect #=> "#<RE2::MatchData \"123\" 1:\"123\">"
|
425
|
-
*/
|
426
|
-
static VALUE re2_matchdata_inspect(VALUE self) {
|
427
|
-
int i;
|
428
|
-
re2_matchdata *m;
|
429
|
-
re2_pattern *p;
|
430
|
-
VALUE match, result;
|
431
|
-
ostringstream output;
|
432
|
-
|
433
|
-
Data_Get_Struct(self, re2_matchdata, m);
|
434
|
-
Data_Get_Struct(m->regexp, re2_pattern, p);
|
435
|
-
|
436
|
-
output << "#<RE2::MatchData";
|
437
|
-
|
438
|
-
for (i = 0; i < m->number_of_matches; i++) {
|
439
|
-
output << " ";
|
440
|
-
|
441
|
-
if (i > 0) {
|
442
|
-
output << i << ":";
|
443
|
-
}
|
456
|
+
result = ENCODED_STR_NEW(output.str().data(), output.str().length(),
|
457
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
444
458
|
|
445
|
-
|
459
|
+
return result;
|
460
|
+
}
|
446
461
|
|
447
|
-
|
448
|
-
|
449
|
-
|
450
|
-
|
451
|
-
|
462
|
+
/*
|
463
|
+
* Returns a new RE2 object with a compiled version of
|
464
|
+
* +pattern+ stored inside. Equivalent to +RE2.new+.
|
465
|
+
*
|
466
|
+
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern and options
|
467
|
+
* @param [String] pattern the pattern to compile
|
468
|
+
* @param [Hash] options the options to compile a regexp with
|
469
|
+
* @see RE2::Regexp.new
|
470
|
+
*
|
471
|
+
*/
|
472
|
+
static VALUE re2_re2(int argc, VALUE *argv, VALUE self) {
|
473
|
+
UNUSED(self);
|
474
|
+
return rb_class_new_instance(argc, argv, re2_cRegexp);
|
475
|
+
}
|
476
|
+
|
477
|
+
/*
|
478
|
+
* Returns a new {RE2::Regexp} object with a compiled version of
|
479
|
+
* +pattern+ stored inside.
|
480
|
+
*
|
481
|
+
* @return [RE2::Regexp]
|
482
|
+
*
|
483
|
+
* @overload initialize(pattern)
|
484
|
+
* Returns a new {RE2::Regexp} object with a compiled version of
|
485
|
+
* +pattern+ stored inside with the default options.
|
486
|
+
*
|
487
|
+
* @param [String] pattern the pattern to compile
|
488
|
+
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern
|
489
|
+
* @raise [NoMemoryError] if memory could not be allocated for the compiled
|
490
|
+
* pattern
|
491
|
+
*
|
492
|
+
* @overload initialize(pattern, options)
|
493
|
+
* Returns a new {RE2::Regexp} object with a compiled version of
|
494
|
+
* +pattern+ stored inside with the specified options.
|
495
|
+
*
|
496
|
+
* @param [String] pattern the pattern to compile
|
497
|
+
* @param [Hash] options the options with which to compile the pattern
|
498
|
+
* @option options [Boolean] :utf8 (true) text and pattern are UTF-8; otherwise Latin-1
|
499
|
+
* @option options [Boolean] :posix_syntax (false) restrict regexps to POSIX egrep syntax
|
500
|
+
* @option options [Boolean] :longest_match (false) search for longest match, not first match
|
501
|
+
* @option options [Boolean] :log_errors (true) log syntax and execution errors to ERROR
|
502
|
+
* @option options [Fixnum] :max_mem approx. max memory footprint of RE2
|
503
|
+
* @option options [Boolean] :literal (false) interpret string as literal, not regexp
|
504
|
+
* @option options [Boolean] :never_nl (false) never match \n, even if it is in regexp
|
505
|
+
* @option options [Boolean] :case_sensitive (true) match is case-sensitive (regexp can override with (?i) unless in posix_syntax mode)
|
506
|
+
* @option options [Boolean] :perl_classes (false) allow Perl's \d \s \w \D \S \W when in posix_syntax mode
|
507
|
+
* @option options [Boolean] :word_boundary (false) allow \b \B (word boundary and not) when in posix_syntax mode
|
508
|
+
* @option options [Boolean] :one_line (false) ^ and $ only match beginning and end of text when in posix_syntax mode
|
509
|
+
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern and options
|
510
|
+
* @raise [NoMemoryError] if memory could not be allocated for the compiled pattern
|
511
|
+
*/
|
512
|
+
static VALUE re2_regexp_initialize(int argc, VALUE *argv, VALUE self) {
|
513
|
+
VALUE pattern, options, utf8, posix_syntax, longest_match, log_errors,
|
514
|
+
max_mem, literal, never_nl, case_sensitive, perl_classes,
|
515
|
+
word_boundary, one_line;
|
516
|
+
re2_pattern *p;
|
517
|
+
|
518
|
+
rb_scan_args(argc, argv, "11", &pattern, &options);
|
519
|
+
Data_Get_Struct(self, re2_pattern, p);
|
520
|
+
|
521
|
+
if (RTEST(options)) {
|
522
|
+
if (TYPE(options) != T_HASH) {
|
523
|
+
rb_raise(rb_eArgError, "options should be a hash");
|
452
524
|
}
|
453
525
|
|
454
|
-
|
526
|
+
RE2::Options re2_options;
|
455
527
|
|
456
|
-
|
457
|
-
|
528
|
+
utf8 = rb_hash_aref(options, ID2SYM(id_utf8));
|
529
|
+
if (!NIL_P(utf8)) {
|
530
|
+
re2_options.set_utf8(RTEST(utf8));
|
531
|
+
}
|
458
532
|
|
459
|
-
|
460
|
-
|
533
|
+
posix_syntax = rb_hash_aref(options, ID2SYM(id_posix_syntax));
|
534
|
+
if (!NIL_P(posix_syntax)) {
|
535
|
+
re2_options.set_posix_syntax(RTEST(posix_syntax));
|
536
|
+
}
|
461
537
|
|
462
|
-
|
463
|
-
|
464
|
-
|
465
|
-
|
466
|
-
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern and options
|
467
|
-
* @param [String] pattern the pattern to compile
|
468
|
-
* @param [Hash] options the options to compile a regexp with
|
469
|
-
* @see RE2::Regexp.new
|
470
|
-
*
|
471
|
-
*/
|
472
|
-
static VALUE re2_re2(int argc, VALUE *argv, VALUE self) {
|
473
|
-
UNUSED(self);
|
474
|
-
return rb_class_new_instance(argc, argv, re2_cRegexp);
|
475
|
-
}
|
538
|
+
longest_match = rb_hash_aref(options, ID2SYM(id_longest_match));
|
539
|
+
if (!NIL_P(longest_match)) {
|
540
|
+
re2_options.set_longest_match(RTEST(longest_match));
|
541
|
+
}
|
476
542
|
|
477
|
-
|
478
|
-
|
479
|
-
|
480
|
-
|
481
|
-
* @return [RE2::Regexp]
|
482
|
-
*
|
483
|
-
* @overload initialize(pattern)
|
484
|
-
* Returns a new {RE2::Regexp} object with a compiled version of
|
485
|
-
* +pattern+ stored inside with the default options.
|
486
|
-
*
|
487
|
-
* @param [String] pattern the pattern to compile
|
488
|
-
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern
|
489
|
-
* @raise [NoMemoryError] if memory could not be allocated for the compiled
|
490
|
-
* pattern
|
491
|
-
*
|
492
|
-
* @overload initialize(pattern, options)
|
493
|
-
* Returns a new {RE2::Regexp} object with a compiled version of
|
494
|
-
* +pattern+ stored inside with the specified options.
|
495
|
-
*
|
496
|
-
* @param [String] pattern the pattern to compile
|
497
|
-
* @param [Hash] options the options with which to compile the pattern
|
498
|
-
* @option options [Boolean] :utf8 (true) text and pattern are UTF-8; otherwise Latin-1
|
499
|
-
* @option options [Boolean] :posix_syntax (false) restrict regexps to POSIX egrep syntax
|
500
|
-
* @option options [Boolean] :longest_match (false) search for longest match, not first match
|
501
|
-
* @option options [Boolean] :log_errors (true) log syntax and execution errors to ERROR
|
502
|
-
* @option options [Fixnum] :max_mem approx. max memory footprint of RE2
|
503
|
-
* @option options [Boolean] :literal (false) interpret string as literal, not regexp
|
504
|
-
* @option options [Boolean] :never_nl (false) never match \n, even if it is in regexp
|
505
|
-
* @option options [Boolean] :case_sensitive (true) match is case-sensitive (regexp can override with (?i) unless in posix_syntax mode)
|
506
|
-
* @option options [Boolean] :perl_classes (false) allow Perl's \d \s \w \D \S \W when in posix_syntax mode
|
507
|
-
* @option options [Boolean] :word_boundary (false) allow \b \B (word boundary and not) when in posix_syntax mode
|
508
|
-
* @option options [Boolean] :one_line (false) ^ and $ only match beginning and end of text when in posix_syntax mode
|
509
|
-
* @return [RE2::Regexp] an RE2::Regexp with the specified pattern and options
|
510
|
-
* @raise [NoMemoryError] if memory could not be allocated for the compiled pattern
|
511
|
-
*/
|
512
|
-
static VALUE re2_regexp_initialize(int argc, VALUE *argv, VALUE self) {
|
513
|
-
VALUE pattern, options, utf8, posix_syntax, longest_match, log_errors,
|
514
|
-
max_mem, literal, never_nl, case_sensitive, perl_classes,
|
515
|
-
word_boundary, one_line;
|
516
|
-
re2_pattern *p;
|
517
|
-
|
518
|
-
rb_scan_args(argc, argv, "11", &pattern, &options);
|
519
|
-
Data_Get_Struct(self, re2_pattern, p);
|
520
|
-
|
521
|
-
if (RTEST(options)) {
|
522
|
-
if (TYPE(options) != T_HASH) {
|
523
|
-
rb_raise(rb_eArgError, "options should be a hash");
|
524
|
-
}
|
543
|
+
log_errors = rb_hash_aref(options, ID2SYM(id_log_errors));
|
544
|
+
if (!NIL_P(log_errors)) {
|
545
|
+
re2_options.set_log_errors(RTEST(log_errors));
|
546
|
+
}
|
525
547
|
|
526
|
-
|
548
|
+
max_mem = rb_hash_aref(options, ID2SYM(id_max_mem));
|
549
|
+
if (!NIL_P(max_mem)) {
|
550
|
+
re2_options.set_max_mem(NUM2INT(max_mem));
|
551
|
+
}
|
527
552
|
|
528
|
-
|
529
|
-
|
530
|
-
|
531
|
-
|
553
|
+
literal = rb_hash_aref(options, ID2SYM(id_literal));
|
554
|
+
if (!NIL_P(literal)) {
|
555
|
+
re2_options.set_literal(RTEST(literal));
|
556
|
+
}
|
532
557
|
|
533
|
-
|
534
|
-
|
535
|
-
|
536
|
-
|
558
|
+
never_nl = rb_hash_aref(options, ID2SYM(id_never_nl));
|
559
|
+
if (!NIL_P(never_nl)) {
|
560
|
+
re2_options.set_never_nl(RTEST(never_nl));
|
561
|
+
}
|
537
562
|
|
538
|
-
|
539
|
-
|
540
|
-
|
541
|
-
|
563
|
+
case_sensitive = rb_hash_aref(options, ID2SYM(id_case_sensitive));
|
564
|
+
if (!NIL_P(case_sensitive)) {
|
565
|
+
re2_options.set_case_sensitive(RTEST(case_sensitive));
|
566
|
+
}
|
542
567
|
|
543
|
-
|
544
|
-
|
545
|
-
|
546
|
-
|
568
|
+
perl_classes = rb_hash_aref(options, ID2SYM(id_perl_classes));
|
569
|
+
if (!NIL_P(perl_classes)) {
|
570
|
+
re2_options.set_perl_classes(RTEST(perl_classes));
|
571
|
+
}
|
547
572
|
|
548
|
-
|
549
|
-
|
550
|
-
|
551
|
-
|
573
|
+
word_boundary = rb_hash_aref(options, ID2SYM(id_word_boundary));
|
574
|
+
if (!NIL_P(word_boundary)) {
|
575
|
+
re2_options.set_word_boundary(RTEST(word_boundary));
|
576
|
+
}
|
552
577
|
|
553
|
-
|
554
|
-
|
555
|
-
|
556
|
-
|
578
|
+
one_line = rb_hash_aref(options, ID2SYM(id_one_line));
|
579
|
+
if (!NIL_P(one_line)) {
|
580
|
+
re2_options.set_one_line(RTEST(one_line));
|
581
|
+
}
|
557
582
|
|
558
|
-
|
559
|
-
|
560
|
-
|
561
|
-
|
583
|
+
p->pattern = new(nothrow) RE2(StringValuePtr(pattern), re2_options);
|
584
|
+
} else {
|
585
|
+
p->pattern = new(nothrow) RE2(StringValuePtr(pattern));
|
586
|
+
}
|
562
587
|
|
563
|
-
|
564
|
-
|
565
|
-
|
566
|
-
}
|
588
|
+
if (p->pattern == 0) {
|
589
|
+
rb_raise(rb_eNoMemError, "not enough memory to allocate RE2 object");
|
590
|
+
}
|
567
591
|
|
568
|
-
|
569
|
-
|
570
|
-
re2_options.set_perl_classes(RTEST(perl_classes));
|
571
|
-
}
|
592
|
+
return self;
|
593
|
+
}
|
572
594
|
|
573
|
-
|
574
|
-
|
575
|
-
|
576
|
-
|
595
|
+
/*
|
596
|
+
* Returns a printable version of the regular expression +re2+.
|
597
|
+
*
|
598
|
+
* @return [String] a printable version of the regular expression
|
599
|
+
* @example
|
600
|
+
* re2 = RE2::Regexp.new("woo?")
|
601
|
+
* re2.inspect #=> "#<RE2::Regexp /woo?/>"
|
602
|
+
*/
|
603
|
+
static VALUE re2_regexp_inspect(VALUE self) {
|
604
|
+
re2_pattern *p;
|
605
|
+
VALUE result;
|
606
|
+
ostringstream output;
|
577
607
|
|
578
|
-
|
579
|
-
if (!NIL_P(one_line)) {
|
580
|
-
re2_options.set_one_line(RTEST(one_line));
|
581
|
-
}
|
608
|
+
Data_Get_Struct(self, re2_pattern, p);
|
582
609
|
|
583
|
-
|
584
|
-
} else {
|
585
|
-
p->pattern = new(nothrow) RE2(StringValuePtr(pattern));
|
586
|
-
}
|
610
|
+
output << "#<RE2::Regexp /" << p->pattern->pattern() << "/>";
|
587
611
|
|
588
|
-
|
589
|
-
|
590
|
-
}
|
612
|
+
result = ENCODED_STR_NEW(output.str().data(), output.str().length(),
|
613
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
591
614
|
|
592
|
-
|
593
|
-
|
615
|
+
return result;
|
616
|
+
}
|
617
|
+
|
618
|
+
/*
|
619
|
+
* Returns a string version of the regular expression +re2+.
|
620
|
+
*
|
621
|
+
* @return [String] a string version of the regular expression
|
622
|
+
* @example
|
623
|
+
* re2 = RE2::Regexp.new("woo?")
|
624
|
+
* re2.to_s #=> "woo?"
|
625
|
+
*/
|
626
|
+
static VALUE re2_regexp_to_s(VALUE self) {
|
627
|
+
re2_pattern *p;
|
628
|
+
Data_Get_Struct(self, re2_pattern, p);
|
629
|
+
return ENCODED_STR_NEW(p->pattern->pattern().data(),
|
630
|
+
p->pattern->pattern().size(),
|
631
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
632
|
+
}
|
594
633
|
|
595
|
-
|
596
|
-
|
597
|
-
|
598
|
-
|
599
|
-
|
600
|
-
|
601
|
-
|
602
|
-
|
603
|
-
|
604
|
-
|
605
|
-
|
606
|
-
|
634
|
+
/*
|
635
|
+
* Returns whether or not the regular expression +re2+
|
636
|
+
* was compiled successfully or not.
|
637
|
+
*
|
638
|
+
* @return [Boolean] whether or not compilation was successful
|
639
|
+
* @example
|
640
|
+
* re2 = RE2::Regexp.new("woo?")
|
641
|
+
* re2.ok? #=> true
|
642
|
+
*/
|
643
|
+
static VALUE re2_regexp_ok(VALUE self) {
|
644
|
+
re2_pattern *p;
|
645
|
+
Data_Get_Struct(self, re2_pattern, p);
|
646
|
+
return BOOL2RUBY(p->pattern->ok());
|
647
|
+
}
|
607
648
|
|
608
|
-
|
649
|
+
/*
|
650
|
+
* Returns whether or not the regular expression +re2+
|
651
|
+
* was compiled with the utf8 option set to true.
|
652
|
+
*
|
653
|
+
* @return [Boolean] the utf8 option
|
654
|
+
* @example
|
655
|
+
* re2 = RE2::Regexp.new("woo?", :utf8 => true)
|
656
|
+
* re2.utf8? #=> true
|
657
|
+
*/
|
658
|
+
static VALUE re2_regexp_utf8(VALUE self) {
|
659
|
+
re2_pattern *p;
|
660
|
+
Data_Get_Struct(self, re2_pattern, p);
|
661
|
+
return BOOL2RUBY(p->pattern->options().utf8());
|
662
|
+
}
|
609
663
|
|
610
|
-
|
664
|
+
/*
|
665
|
+
* Returns whether or not the regular expression +re2+
|
666
|
+
* was compiled with the posix_syntax option set to true.
|
667
|
+
*
|
668
|
+
* @return [Boolean] the posix_syntax option
|
669
|
+
* @example
|
670
|
+
* re2 = RE2::Regexp.new("woo?", :posix_syntax => true)
|
671
|
+
* re2.posix_syntax? #=> true
|
672
|
+
*/
|
673
|
+
static VALUE re2_regexp_posix_syntax(VALUE self) {
|
674
|
+
re2_pattern *p;
|
675
|
+
Data_Get_Struct(self, re2_pattern, p);
|
676
|
+
return BOOL2RUBY(p->pattern->options().posix_syntax());
|
677
|
+
}
|
611
678
|
|
612
|
-
|
613
|
-
|
679
|
+
/*
|
680
|
+
* Returns whether or not the regular expression +re2+
|
681
|
+
* was compiled with the longest_match option set to true.
|
682
|
+
*
|
683
|
+
* @return [Boolean] the longest_match option
|
684
|
+
* @example
|
685
|
+
* re2 = RE2::Regexp.new("woo?", :longest_match => true)
|
686
|
+
* re2.longest_match? #=> true
|
687
|
+
*/
|
688
|
+
static VALUE re2_regexp_longest_match(VALUE self) {
|
689
|
+
re2_pattern *p;
|
690
|
+
Data_Get_Struct(self, re2_pattern, p);
|
691
|
+
return BOOL2RUBY(p->pattern->options().longest_match());
|
692
|
+
}
|
614
693
|
|
615
|
-
|
616
|
-
|
694
|
+
/*
|
695
|
+
* Returns whether or not the regular expression +re2+
|
696
|
+
* was compiled with the log_errors option set to true.
|
697
|
+
*
|
698
|
+
* @return [Boolean] the log_errors option
|
699
|
+
* @example
|
700
|
+
* re2 = RE2::Regexp.new("woo?", :log_errors => true)
|
701
|
+
* re2.log_errors? #=> true
|
702
|
+
*/
|
703
|
+
static VALUE re2_regexp_log_errors(VALUE self) {
|
704
|
+
re2_pattern *p;
|
705
|
+
Data_Get_Struct(self, re2_pattern, p);
|
706
|
+
return BOOL2RUBY(p->pattern->options().log_errors());
|
707
|
+
}
|
617
708
|
|
618
|
-
|
619
|
-
|
620
|
-
|
621
|
-
|
622
|
-
|
623
|
-
|
624
|
-
|
625
|
-
|
626
|
-
|
627
|
-
|
628
|
-
|
629
|
-
|
630
|
-
|
631
|
-
|
632
|
-
}
|
709
|
+
/*
|
710
|
+
* Returns the max_mem setting for the regular expression
|
711
|
+
* +re2+.
|
712
|
+
*
|
713
|
+
* @return [Fixnum] the max_mem option
|
714
|
+
* @example
|
715
|
+
* re2 = RE2::Regexp.new("woo?", :max_mem => 1024)
|
716
|
+
* re2.max_mem #=> 1024
|
717
|
+
*/
|
718
|
+
static VALUE re2_regexp_max_mem(VALUE self) {
|
719
|
+
re2_pattern *p;
|
720
|
+
Data_Get_Struct(self, re2_pattern, p);
|
721
|
+
return INT2FIX(p->pattern->options().max_mem());
|
722
|
+
}
|
633
723
|
|
634
|
-
|
635
|
-
|
636
|
-
|
637
|
-
|
638
|
-
|
639
|
-
|
640
|
-
|
641
|
-
|
642
|
-
|
643
|
-
|
644
|
-
|
645
|
-
|
646
|
-
|
647
|
-
|
724
|
+
/*
|
725
|
+
* Returns whether or not the regular expression +re2+
|
726
|
+
* was compiled with the literal option set to true.
|
727
|
+
*
|
728
|
+
* @return [Boolean] the literal option
|
729
|
+
* @example
|
730
|
+
* re2 = RE2::Regexp.new("woo?", :literal => true)
|
731
|
+
* re2.literal? #=> true
|
732
|
+
*/
|
733
|
+
static VALUE re2_regexp_literal(VALUE self) {
|
734
|
+
re2_pattern *p;
|
735
|
+
Data_Get_Struct(self, re2_pattern, p);
|
736
|
+
return BOOL2RUBY(p->pattern->options().literal());
|
737
|
+
}
|
648
738
|
|
649
|
-
|
650
|
-
|
651
|
-
|
652
|
-
|
653
|
-
|
654
|
-
|
655
|
-
|
656
|
-
|
657
|
-
|
658
|
-
|
659
|
-
|
660
|
-
|
661
|
-
|
662
|
-
|
739
|
+
/*
|
740
|
+
* Returns whether or not the regular expression +re2+
|
741
|
+
* was compiled with the never_nl option set to true.
|
742
|
+
*
|
743
|
+
* @return [Boolean] the never_nl option
|
744
|
+
* @example
|
745
|
+
* re2 = RE2::Regexp.new("woo?", :never_nl => true)
|
746
|
+
* re2.never_nl? #=> true
|
747
|
+
*/
|
748
|
+
static VALUE re2_regexp_never_nl(VALUE self) {
|
749
|
+
re2_pattern *p;
|
750
|
+
Data_Get_Struct(self, re2_pattern, p);
|
751
|
+
return BOOL2RUBY(p->pattern->options().never_nl());
|
752
|
+
}
|
663
753
|
|
664
|
-
|
665
|
-
|
666
|
-
|
667
|
-
|
668
|
-
|
669
|
-
|
670
|
-
|
671
|
-
|
672
|
-
|
673
|
-
|
674
|
-
|
675
|
-
|
676
|
-
|
677
|
-
|
754
|
+
/*
|
755
|
+
* Returns whether or not the regular expression +re2+
|
756
|
+
* was compiled with the case_sensitive option set to true.
|
757
|
+
*
|
758
|
+
* @return [Boolean] the case_sensitive option
|
759
|
+
* @example
|
760
|
+
* re2 = RE2::Regexp.new("woo?", :case_sensitive => true)
|
761
|
+
* re2.case_sensitive? #=> true
|
762
|
+
*/
|
763
|
+
static VALUE re2_regexp_case_sensitive(VALUE self) {
|
764
|
+
re2_pattern *p;
|
765
|
+
Data_Get_Struct(self, re2_pattern, p);
|
766
|
+
return BOOL2RUBY(p->pattern->options().case_sensitive());
|
767
|
+
}
|
678
768
|
|
679
|
-
|
680
|
-
|
681
|
-
|
682
|
-
|
683
|
-
|
684
|
-
|
685
|
-
|
686
|
-
|
687
|
-
|
688
|
-
|
689
|
-
|
690
|
-
|
691
|
-
|
692
|
-
}
|
769
|
+
/*
|
770
|
+
* Returns whether or not the regular expression +re2+
|
771
|
+
* was compiled with the case_sensitive option set to false.
|
772
|
+
*
|
773
|
+
* @return [Boolean] the inverse of the case_sensitive option
|
774
|
+
* @example
|
775
|
+
* re2 = RE2::Regexp.new("woo?", :case_sensitive => true)
|
776
|
+
* re2.case_insensitive? #=> false
|
777
|
+
* re2.casefold? #=> false
|
778
|
+
*/
|
779
|
+
static VALUE re2_regexp_case_insensitive(VALUE self) {
|
780
|
+
return BOOL2RUBY(re2_regexp_case_sensitive(self) != Qtrue);
|
781
|
+
}
|
693
782
|
|
694
|
-
|
695
|
-
|
696
|
-
|
697
|
-
|
698
|
-
|
699
|
-
|
700
|
-
|
701
|
-
|
702
|
-
|
703
|
-
|
704
|
-
|
705
|
-
|
706
|
-
|
707
|
-
|
783
|
+
/*
|
784
|
+
* Returns whether or not the regular expression +re2+
|
785
|
+
* was compiled with the perl_classes option set to true.
|
786
|
+
*
|
787
|
+
* @return [Boolean] the perl_classes option
|
788
|
+
* @example
|
789
|
+
* re2 = RE2::Regexp.new("woo?", :perl_classes => true)
|
790
|
+
* re2.perl_classes? #=> true
|
791
|
+
*/
|
792
|
+
static VALUE re2_regexp_perl_classes(VALUE self) {
|
793
|
+
re2_pattern *p;
|
794
|
+
Data_Get_Struct(self, re2_pattern, p);
|
795
|
+
return BOOL2RUBY(p->pattern->options().perl_classes());
|
796
|
+
}
|
708
797
|
|
709
|
-
|
710
|
-
|
711
|
-
|
712
|
-
|
713
|
-
|
714
|
-
|
715
|
-
|
716
|
-
|
717
|
-
|
718
|
-
|
719
|
-
|
720
|
-
|
721
|
-
|
722
|
-
|
798
|
+
/*
|
799
|
+
* Returns whether or not the regular expression +re2+
|
800
|
+
* was compiled with the word_boundary option set to true.
|
801
|
+
*
|
802
|
+
* @return [Boolean] the word_boundary option
|
803
|
+
* @example
|
804
|
+
* re2 = RE2::Regexp.new("woo?", :word_boundary => true)
|
805
|
+
* re2.word_boundary? #=> true
|
806
|
+
*/
|
807
|
+
static VALUE re2_regexp_word_boundary(VALUE self) {
|
808
|
+
re2_pattern *p;
|
809
|
+
Data_Get_Struct(self, re2_pattern, p);
|
810
|
+
return BOOL2RUBY(p->pattern->options().word_boundary());
|
811
|
+
}
|
723
812
|
|
724
|
-
|
725
|
-
|
726
|
-
|
727
|
-
|
728
|
-
|
729
|
-
|
730
|
-
|
731
|
-
|
732
|
-
|
733
|
-
|
734
|
-
|
735
|
-
|
736
|
-
|
737
|
-
|
813
|
+
/*
|
814
|
+
* Returns whether or not the regular expression +re2+
|
815
|
+
* was compiled with the one_line option set to true.
|
816
|
+
*
|
817
|
+
* @return [Boolean] the one_line option
|
818
|
+
* @example
|
819
|
+
* re2 = RE2::Regexp.new("woo?", :one_line => true)
|
820
|
+
* re2.one_line? #=> true
|
821
|
+
*/
|
822
|
+
static VALUE re2_regexp_one_line(VALUE self) {
|
823
|
+
re2_pattern *p;
|
824
|
+
Data_Get_Struct(self, re2_pattern, p);
|
825
|
+
return BOOL2RUBY(p->pattern->options().one_line());
|
826
|
+
}
|
738
827
|
|
739
|
-
|
740
|
-
|
741
|
-
|
742
|
-
|
743
|
-
|
744
|
-
|
745
|
-
|
746
|
-
|
747
|
-
|
748
|
-
|
749
|
-
|
750
|
-
|
751
|
-
return
|
828
|
+
/*
|
829
|
+
* If the RE2 could not be created properly, returns an
|
830
|
+
* error string otherwise returns nil.
|
831
|
+
*
|
832
|
+
* @return [String, nil] the error string or nil
|
833
|
+
*/
|
834
|
+
static VALUE re2_regexp_error(VALUE self) {
|
835
|
+
re2_pattern *p;
|
836
|
+
Data_Get_Struct(self, re2_pattern, p);
|
837
|
+
if (p->pattern->ok()) {
|
838
|
+
return Qnil;
|
839
|
+
} else {
|
840
|
+
return rb_str_new(p->pattern->error().data(), p->pattern->error().size());
|
752
841
|
}
|
842
|
+
}
|
753
843
|
|
754
|
-
|
755
|
-
|
756
|
-
|
757
|
-
|
758
|
-
|
759
|
-
|
760
|
-
|
761
|
-
|
762
|
-
|
763
|
-
|
764
|
-
|
765
|
-
|
766
|
-
return
|
844
|
+
/*
|
845
|
+
* If the RE2 could not be created properly, returns
|
846
|
+
* the offending portion of the regexp otherwise returns nil.
|
847
|
+
*
|
848
|
+
* @return [String, nil] the offending portion of the regexp or nil
|
849
|
+
*/
|
850
|
+
static VALUE re2_regexp_error_arg(VALUE self) {
|
851
|
+
re2_pattern *p;
|
852
|
+
Data_Get_Struct(self, re2_pattern, p);
|
853
|
+
if (p->pattern->ok()) {
|
854
|
+
return Qnil;
|
855
|
+
} else {
|
856
|
+
return ENCODED_STR_NEW(p->pattern->error_arg().data(),
|
857
|
+
p->pattern->error_arg().size(),
|
858
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
767
859
|
}
|
860
|
+
}
|
768
861
|
|
769
|
-
|
770
|
-
|
771
|
-
|
772
|
-
|
773
|
-
|
774
|
-
|
775
|
-
|
776
|
-
|
777
|
-
|
778
|
-
|
779
|
-
|
780
|
-
|
781
|
-
}
|
862
|
+
/*
|
863
|
+
* Returns the program size, a very approximate measure
|
864
|
+
* of a regexp's "cost". Larger numbers are more expensive
|
865
|
+
* than smaller numbers.
|
866
|
+
*
|
867
|
+
* @return [Fixnum] the regexp "cost"
|
868
|
+
*/
|
869
|
+
static VALUE re2_regexp_program_size(VALUE self) {
|
870
|
+
re2_pattern *p;
|
871
|
+
Data_Get_Struct(self, re2_pattern, p);
|
872
|
+
return INT2FIX(p->pattern->ProgramSize());
|
873
|
+
}
|
782
874
|
|
783
|
-
|
784
|
-
|
785
|
-
|
786
|
-
|
787
|
-
|
788
|
-
|
789
|
-
|
790
|
-
|
791
|
-
|
792
|
-
static VALUE re2_regexp_perl_classes(VALUE self) {
|
793
|
-
re2_pattern *p;
|
794
|
-
Data_Get_Struct(self, re2_pattern, p);
|
795
|
-
return BOOL2RUBY(p->pattern->options().perl_classes());
|
796
|
-
}
|
875
|
+
/*
|
876
|
+
* Returns a hash of the options currently set for
|
877
|
+
* +re2+.
|
878
|
+
*
|
879
|
+
* @return [Hash] the options
|
880
|
+
*/
|
881
|
+
static VALUE re2_regexp_options(VALUE self) {
|
882
|
+
VALUE options;
|
883
|
+
re2_pattern *p;
|
797
884
|
|
798
|
-
|
799
|
-
|
800
|
-
* was compiled with the word_boundary option set to true.
|
801
|
-
*
|
802
|
-
* @return [Boolean] the word_boundary option
|
803
|
-
* @example
|
804
|
-
* re2 = RE2::Regexp.new("woo?", :word_boundary => true)
|
805
|
-
* re2.word_boundary? #=> true
|
806
|
-
*/
|
807
|
-
static VALUE re2_regexp_word_boundary(VALUE self) {
|
808
|
-
re2_pattern *p;
|
809
|
-
Data_Get_Struct(self, re2_pattern, p);
|
810
|
-
return BOOL2RUBY(p->pattern->options().word_boundary());
|
811
|
-
}
|
885
|
+
Data_Get_Struct(self, re2_pattern, p);
|
886
|
+
options = rb_hash_new();
|
812
887
|
|
813
|
-
|
814
|
-
|
815
|
-
* was compiled with the one_line option set to true.
|
816
|
-
*
|
817
|
-
* @return [Boolean] the one_line option
|
818
|
-
* @example
|
819
|
-
* re2 = RE2::Regexp.new("woo?", :one_line => true)
|
820
|
-
* re2.one_line? #=> true
|
821
|
-
*/
|
822
|
-
static VALUE re2_regexp_one_line(VALUE self) {
|
823
|
-
re2_pattern *p;
|
824
|
-
Data_Get_Struct(self, re2_pattern, p);
|
825
|
-
return BOOL2RUBY(p->pattern->options().one_line());
|
826
|
-
}
|
888
|
+
rb_hash_aset(options, ID2SYM(id_utf8),
|
889
|
+
BOOL2RUBY(p->pattern->options().utf8()));
|
827
890
|
|
828
|
-
|
829
|
-
|
830
|
-
* error string otherwise returns nil.
|
831
|
-
*
|
832
|
-
* @return [String, nil] the error string or nil
|
833
|
-
*/
|
834
|
-
static VALUE re2_regexp_error(VALUE self) {
|
835
|
-
re2_pattern *p;
|
836
|
-
Data_Get_Struct(self, re2_pattern, p);
|
837
|
-
if (p->pattern->ok()) {
|
838
|
-
return Qnil;
|
839
|
-
} else {
|
840
|
-
return rb_str_new(p->pattern->error().data(), p->pattern->error().size());
|
841
|
-
}
|
842
|
-
}
|
891
|
+
rb_hash_aset(options, ID2SYM(id_posix_syntax),
|
892
|
+
BOOL2RUBY(p->pattern->options().posix_syntax()));
|
843
893
|
|
844
|
-
|
845
|
-
|
846
|
-
* the offending portion of the regexp otherwise returns nil.
|
847
|
-
*
|
848
|
-
* @return [String, nil] the offending portion of the regexp or nil
|
849
|
-
*/
|
850
|
-
static VALUE re2_regexp_error_arg(VALUE self) {
|
851
|
-
re2_pattern *p;
|
852
|
-
Data_Get_Struct(self, re2_pattern, p);
|
853
|
-
if (p->pattern->ok()) {
|
854
|
-
return Qnil;
|
855
|
-
} else {
|
856
|
-
return ENCODED_STR_NEW(p->pattern->error_arg().data(),
|
857
|
-
p->pattern->error_arg().size(),
|
858
|
-
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
859
|
-
}
|
860
|
-
}
|
894
|
+
rb_hash_aset(options, ID2SYM(id_longest_match),
|
895
|
+
BOOL2RUBY(p->pattern->options().longest_match()));
|
861
896
|
|
862
|
-
|
863
|
-
|
864
|
-
|
865
|
-
|
866
|
-
|
867
|
-
* @return [Fixnum] the regexp "cost"
|
868
|
-
*/
|
869
|
-
static VALUE re2_regexp_program_size(VALUE self) {
|
870
|
-
re2_pattern *p;
|
871
|
-
Data_Get_Struct(self, re2_pattern, p);
|
872
|
-
return INT2FIX(p->pattern->ProgramSize());
|
873
|
-
}
|
897
|
+
rb_hash_aset(options, ID2SYM(id_log_errors),
|
898
|
+
BOOL2RUBY(p->pattern->options().log_errors()));
|
899
|
+
|
900
|
+
rb_hash_aset(options, ID2SYM(id_max_mem),
|
901
|
+
INT2FIX(p->pattern->options().max_mem()));
|
874
902
|
|
875
|
-
|
876
|
-
|
877
|
-
* +re2+.
|
878
|
-
*
|
879
|
-
* @return [Hash] the options
|
880
|
-
*/
|
881
|
-
static VALUE re2_regexp_options(VALUE self) {
|
882
|
-
VALUE options;
|
883
|
-
re2_pattern *p;
|
903
|
+
rb_hash_aset(options, ID2SYM(id_literal),
|
904
|
+
BOOL2RUBY(p->pattern->options().literal()));
|
884
905
|
|
885
|
-
|
886
|
-
|
906
|
+
rb_hash_aset(options, ID2SYM(id_never_nl),
|
907
|
+
BOOL2RUBY(p->pattern->options().never_nl()));
|
887
908
|
|
888
|
-
|
889
|
-
|
909
|
+
rb_hash_aset(options, ID2SYM(id_case_sensitive),
|
910
|
+
BOOL2RUBY(p->pattern->options().case_sensitive()));
|
890
911
|
|
891
|
-
|
892
|
-
|
912
|
+
rb_hash_aset(options, ID2SYM(id_perl_classes),
|
913
|
+
BOOL2RUBY(p->pattern->options().perl_classes()));
|
893
914
|
|
894
|
-
|
895
|
-
|
915
|
+
rb_hash_aset(options, ID2SYM(id_word_boundary),
|
916
|
+
BOOL2RUBY(p->pattern->options().word_boundary()));
|
896
917
|
|
897
|
-
|
898
|
-
|
918
|
+
rb_hash_aset(options, ID2SYM(id_one_line),
|
919
|
+
BOOL2RUBY(p->pattern->options().one_line()));
|
899
920
|
|
900
|
-
|
901
|
-
|
921
|
+
/* This is a read-only hash after all... */
|
922
|
+
rb_obj_freeze(options);
|
923
|
+
|
924
|
+
return options;
|
925
|
+
}
|
902
926
|
|
903
|
-
|
904
|
-
|
927
|
+
/*
|
928
|
+
* Returns the number of capturing subpatterns, or -1 if the regexp
|
929
|
+
* wasn't valid on construction. The overall match ($0) does not
|
930
|
+
* count: if the regexp is "(a)(b)", returns 2.
|
931
|
+
*
|
932
|
+
* @return [Fixnum] the number of capturing subpatterns
|
933
|
+
*/
|
934
|
+
static VALUE re2_regexp_number_of_capturing_groups(VALUE self) {
|
935
|
+
re2_pattern *p;
|
905
936
|
|
906
|
-
|
907
|
-
|
937
|
+
Data_Get_Struct(self, re2_pattern, p);
|
938
|
+
return INT2FIX(p->pattern->NumberOfCapturingGroups());
|
939
|
+
}
|
908
940
|
|
909
|
-
|
910
|
-
|
941
|
+
/*
|
942
|
+
* Returns a hash of names to capturing indices of groups.
|
943
|
+
*
|
944
|
+
* @return [Hash] a hash of names to capturing indices
|
945
|
+
*/
|
946
|
+
static VALUE re2_regexp_named_capturing_groups(VALUE self) {
|
947
|
+
VALUE capturing_groups;
|
948
|
+
re2_pattern *p;
|
949
|
+
map<string, int> groups;
|
950
|
+
map<string, int>::iterator iterator;
|
951
|
+
|
952
|
+
Data_Get_Struct(self, re2_pattern, p);
|
953
|
+
groups = p->pattern->NamedCapturingGroups();
|
954
|
+
capturing_groups = rb_hash_new();
|
955
|
+
|
956
|
+
for (iterator = groups.begin(); iterator != groups.end(); iterator++) {
|
957
|
+
rb_hash_aset(capturing_groups,
|
958
|
+
ENCODED_STR_NEW(iterator->first.data(), iterator->first.size(),
|
959
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1"),
|
960
|
+
INT2FIX(iterator->second));
|
961
|
+
}
|
911
962
|
|
912
|
-
|
913
|
-
|
963
|
+
return capturing_groups;
|
964
|
+
}
|
914
965
|
|
915
|
-
|
916
|
-
|
966
|
+
/*
|
967
|
+
* Match the pattern against the given +text+ and return either
|
968
|
+
* a boolean (if no submatches are required) or a {RE2::MatchData}
|
969
|
+
* instance.
|
970
|
+
*
|
971
|
+
* @return [Boolean, RE2::MatchData]
|
972
|
+
*
|
973
|
+
* @overload match(text)
|
974
|
+
* Returns an {RE2::MatchData} containing the matching
|
975
|
+
* pattern and all subpatterns resulting from looking for
|
976
|
+
* the regexp in +text+.
|
977
|
+
*
|
978
|
+
* @param [String] text the text to search
|
979
|
+
* @return [RE2::MatchData] the matches
|
980
|
+
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
981
|
+
* @example
|
982
|
+
* r = RE2::Regexp.new('w(o)(o)')
|
983
|
+
* r.match('woo') #=> #<RE2::MatchData "woo" 1:"o" 2:"o">
|
984
|
+
*
|
985
|
+
* @overload match(text, 0)
|
986
|
+
* Returns either true or false indicating whether a
|
987
|
+
* successful match was made.
|
988
|
+
*
|
989
|
+
* @param [String] text the text to search
|
990
|
+
* @return [Boolean] whether the match was successful
|
991
|
+
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
992
|
+
* @example
|
993
|
+
* r = RE2::Regexp.new('w(o)(o)')
|
994
|
+
* r.match('woo', 0) #=> true
|
995
|
+
* r.match('bob', 0) #=> false
|
996
|
+
*
|
997
|
+
* @overload match(text, number_of_matches)
|
998
|
+
* See +match(text)+ but with a specific number of
|
999
|
+
* matches returned (padded with nils if necessary).
|
1000
|
+
*
|
1001
|
+
* @param [String] text the text to search
|
1002
|
+
* @param [Fixnum] number_of_matches the number of matches to return
|
1003
|
+
* @return [RE2::MatchData] the matches
|
1004
|
+
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
1005
|
+
* @example
|
1006
|
+
* r = RE2::Regexp.new('w(o)(o)')
|
1007
|
+
* r.match('woo', 1) #=> #<RE2::MatchData "woo" 1:"o">
|
1008
|
+
* r.match('woo', 3) #=> #<RE2::MatchData "woo" 1:"o" 2:"o" 3:nil>
|
1009
|
+
*/
|
1010
|
+
static VALUE re2_regexp_match(int argc, VALUE *argv, VALUE self) {
|
1011
|
+
int n;
|
1012
|
+
bool matched;
|
1013
|
+
re2_pattern *p;
|
1014
|
+
re2_matchdata *m;
|
1015
|
+
VALUE text, number_of_matches, matchdata;
|
917
1016
|
|
918
|
-
|
919
|
-
BOOL2RUBY(p->pattern->options().one_line()));
|
1017
|
+
rb_scan_args(argc, argv, "11", &text, &number_of_matches);
|
920
1018
|
|
921
|
-
|
922
|
-
|
1019
|
+
/* Ensure text is a string. */
|
1020
|
+
text = StringValue(text);
|
923
1021
|
|
924
|
-
|
925
|
-
}
|
1022
|
+
Data_Get_Struct(self, re2_pattern, p);
|
926
1023
|
|
927
|
-
|
928
|
-
|
929
|
-
|
930
|
-
|
931
|
-
*
|
932
|
-
* @return [Fixnum] the number of capturing subpatterns
|
933
|
-
*/
|
934
|
-
static VALUE re2_regexp_number_of_capturing_groups(VALUE self) {
|
935
|
-
re2_pattern *p;
|
936
|
-
|
937
|
-
Data_Get_Struct(self, re2_pattern, p);
|
938
|
-
return INT2FIX(p->pattern->NumberOfCapturingGroups());
|
1024
|
+
if (RTEST(number_of_matches)) {
|
1025
|
+
n = NUM2INT(number_of_matches);
|
1026
|
+
} else {
|
1027
|
+
n = p->pattern->NumberOfCapturingGroups();
|
939
1028
|
}
|
940
1029
|
|
941
|
-
|
942
|
-
|
943
|
-
|
944
|
-
|
945
|
-
|
946
|
-
|
947
|
-
|
948
|
-
|
949
|
-
|
950
|
-
|
951
|
-
|
952
|
-
|
953
|
-
|
954
|
-
|
955
|
-
|
956
|
-
|
957
|
-
|
958
|
-
|
959
|
-
|
960
|
-
INT2FIX(iterator->second));
|
1030
|
+
if (n == 0) {
|
1031
|
+
matched = match(p->pattern, StringValuePtr(text), 0,
|
1032
|
+
static_cast<int>(RSTRING_LEN(text)), RE2::UNANCHORED, 0, 0);
|
1033
|
+
return BOOL2RUBY(matched);
|
1034
|
+
} else {
|
1035
|
+
|
1036
|
+
/* Because match returns the whole match as well. */
|
1037
|
+
n += 1;
|
1038
|
+
|
1039
|
+
matchdata = rb_class_new_instance(0, 0, re2_cMatchData);
|
1040
|
+
Data_Get_Struct(matchdata, re2_matchdata, m);
|
1041
|
+
m->matches = new(nothrow) re2::StringPiece[n];
|
1042
|
+
m->regexp = self;
|
1043
|
+
m->text = rb_str_dup(text);
|
1044
|
+
rb_str_freeze(m->text);
|
1045
|
+
|
1046
|
+
if (m->matches == 0) {
|
1047
|
+
rb_raise(rb_eNoMemError,
|
1048
|
+
"not enough memory to allocate StringPieces for matches");
|
961
1049
|
}
|
962
1050
|
|
963
|
-
|
964
|
-
|
1051
|
+
m->number_of_matches = n;
|
1052
|
+
|
1053
|
+
matched = match(p->pattern, StringValuePtr(text), 0,
|
1054
|
+
static_cast<int>(RSTRING_LEN(text)),
|
1055
|
+
RE2::UNANCHORED, m->matches, n);
|
965
1056
|
|
966
|
-
|
967
|
-
|
968
|
-
* a boolean (if no submatches are required) or a {RE2::MatchData}
|
969
|
-
* instance.
|
970
|
-
*
|
971
|
-
* @return [Boolean, RE2::MatchData]
|
972
|
-
*
|
973
|
-
* @overload match(text)
|
974
|
-
* Returns an {RE2::MatchData} containing the matching
|
975
|
-
* pattern and all subpatterns resulting from looking for
|
976
|
-
* the regexp in +text+.
|
977
|
-
*
|
978
|
-
* @param [String] text the text to search
|
979
|
-
* @return [RE2::MatchData] the matches
|
980
|
-
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
981
|
-
* @example
|
982
|
-
* r = RE2::Regexp.new('w(o)(o)')
|
983
|
-
* r.match('woo') #=> #<RE2::MatchData "woo" 1:"o" 2:"o">
|
984
|
-
*
|
985
|
-
* @overload match(text, 0)
|
986
|
-
* Returns either true or false indicating whether a
|
987
|
-
* successful match was made.
|
988
|
-
*
|
989
|
-
* @param [String] text the text to search
|
990
|
-
* @return [Boolean] whether the match was successful
|
991
|
-
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
992
|
-
* @example
|
993
|
-
* r = RE2::Regexp.new('w(o)(o)')
|
994
|
-
* r.match('woo', 0) #=> true
|
995
|
-
* r.match('bob', 0) #=> false
|
996
|
-
*
|
997
|
-
* @overload match(text, number_of_matches)
|
998
|
-
* See +match(text)+ but with a specific number of
|
999
|
-
* matches returned (padded with nils if necessary).
|
1000
|
-
*
|
1001
|
-
* @param [String] text the text to search
|
1002
|
-
* @param [Fixnum] number_of_matches the number of matches to return
|
1003
|
-
* @return [RE2::MatchData] the matches
|
1004
|
-
* @raise [NoMemoryError] if there was not enough memory to allocate the matches
|
1005
|
-
* @example
|
1006
|
-
* r = RE2::Regexp.new('w(o)(o)')
|
1007
|
-
* r.match('woo', 1) #=> #<RE2::MatchData "woo" 1:"o">
|
1008
|
-
* r.match('woo', 3) #=> #<RE2::MatchData "woo" 1:"o" 2:"o" 3:nil>
|
1009
|
-
*/
|
1010
|
-
static VALUE re2_regexp_match(int argc, VALUE *argv, VALUE self) {
|
1011
|
-
int n;
|
1012
|
-
bool matched;
|
1013
|
-
re2_pattern *p;
|
1014
|
-
re2_matchdata *m;
|
1015
|
-
VALUE text, number_of_matches, matchdata;
|
1016
|
-
|
1017
|
-
rb_scan_args(argc, argv, "11", &text, &number_of_matches);
|
1018
|
-
|
1019
|
-
Data_Get_Struct(self, re2_pattern, p);
|
1020
|
-
|
1021
|
-
if (RTEST(number_of_matches)) {
|
1022
|
-
n = NUM2INT(number_of_matches);
|
1057
|
+
if (matched) {
|
1058
|
+
return matchdata;
|
1023
1059
|
} else {
|
1024
|
-
|
1060
|
+
return Qnil;
|
1025
1061
|
}
|
1062
|
+
}
|
1063
|
+
}
|
1026
1064
|
|
1027
|
-
|
1028
|
-
|
1029
|
-
|
1030
|
-
|
1031
|
-
|
1065
|
+
/*
|
1066
|
+
* Returns true or false to indicate a successful match.
|
1067
|
+
* Equivalent to +re2.match(text, 0)+.
|
1068
|
+
*
|
1069
|
+
* @return [Boolean] whether the match was successful
|
1070
|
+
*/
|
1071
|
+
static VALUE re2_regexp_match_query(VALUE self, VALUE text) {
|
1072
|
+
VALUE argv[2];
|
1073
|
+
argv[0] = text;
|
1074
|
+
argv[1] = INT2FIX(0);
|
1032
1075
|
|
1033
|
-
|
1034
|
-
|
1076
|
+
return re2_regexp_match(2, argv, self);
|
1077
|
+
}
|
1035
1078
|
|
1036
|
-
|
1037
|
-
|
1038
|
-
|
1039
|
-
|
1040
|
-
|
1041
|
-
|
1079
|
+
/*
|
1080
|
+
* Returns a {RE2::Scanner} for scanning the given text incrementally.
|
1081
|
+
*
|
1082
|
+
* @example
|
1083
|
+
* c = RE2::Regexp.new('(\w+)').scan("Foo bar baz")
|
1084
|
+
*/
|
1085
|
+
static VALUE re2_regexp_scan(VALUE self, VALUE text) {
|
1086
|
+
re2_pattern *p;
|
1087
|
+
re2_scanner *c;
|
1088
|
+
VALUE scanner;
|
1042
1089
|
|
1043
|
-
|
1044
|
-
|
1045
|
-
|
1046
|
-
}
|
1090
|
+
Data_Get_Struct(self, re2_pattern, p);
|
1091
|
+
scanner = rb_class_new_instance(0, 0, re2_cScanner);
|
1092
|
+
Data_Get_Struct(scanner, re2_scanner, c);
|
1047
1093
|
|
1048
|
-
|
1094
|
+
c->input = new(nothrow) re2::StringPiece(StringValuePtr(text));
|
1095
|
+
c->regexp = self;
|
1096
|
+
c->text = text;
|
1097
|
+
c->number_of_capturing_groups = p->pattern->NumberOfCapturingGroups();
|
1049
1098
|
|
1050
|
-
|
1051
|
-
|
1052
|
-
RE2::UNANCHORED, m->matches, n);
|
1099
|
+
return scanner;
|
1100
|
+
}
|
1053
1101
|
|
1054
|
-
|
1055
|
-
|
1056
|
-
|
1057
|
-
|
1058
|
-
|
1059
|
-
|
1060
|
-
|
1102
|
+
/*
|
1103
|
+
* Returns a copy of +str+ with the first occurrence +pattern+
|
1104
|
+
* replaced with +rewrite+.
|
1105
|
+
*
|
1106
|
+
* @param [String] str the string to modify
|
1107
|
+
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
1108
|
+
* @param [String] rewrite the string to replace with
|
1109
|
+
* @return [String] the resulting string
|
1110
|
+
* @example
|
1111
|
+
* RE2.Replace("hello there", "hello", "howdy") #=> "howdy there"
|
1112
|
+
* re2 = RE2.new("hel+o")
|
1113
|
+
* RE2.Replace("hello there", re2, "yo") #=> "yo there"
|
1114
|
+
*/
|
1115
|
+
static VALUE re2_Replace(VALUE self, VALUE str, VALUE pattern,
|
1116
|
+
VALUE rewrite) {
|
1117
|
+
UNUSED(self);
|
1118
|
+
re2_pattern *p;
|
1061
1119
|
|
1062
|
-
/*
|
1063
|
-
|
1064
|
-
* Equivalent to +re2.match(text, 0)+.
|
1065
|
-
*
|
1066
|
-
* @return [Boolean] whether the match was successful
|
1067
|
-
*/
|
1068
|
-
static VALUE re2_regexp_match_query(VALUE self, VALUE text) {
|
1069
|
-
VALUE argv[2];
|
1070
|
-
argv[0] = text;
|
1071
|
-
argv[1] = INT2FIX(0);
|
1072
|
-
|
1073
|
-
return re2_regexp_match(2, argv, self);
|
1074
|
-
}
|
1120
|
+
/* Convert all the inputs to be pumped into RE2::Replace. */
|
1121
|
+
string str_as_string(StringValuePtr(str));
|
1075
1122
|
|
1076
|
-
/*
|
1077
|
-
|
1078
|
-
|
1079
|
-
|
1080
|
-
|
1081
|
-
|
1082
|
-
|
1083
|
-
|
1084
|
-
|
1085
|
-
|
1086
|
-
|
1087
|
-
|
1088
|
-
|
1089
|
-
Data_Get_Struct(scanner, re2_scanner, c);
|
1090
|
-
|
1091
|
-
c->input = new(nothrow) re2::StringPiece(StringValuePtr(text));
|
1092
|
-
c->regexp = self;
|
1093
|
-
c->text = text;
|
1094
|
-
c->number_of_capturing_groups = p->pattern->NumberOfCapturingGroups();
|
1095
|
-
|
1096
|
-
return scanner;
|
1123
|
+
/* Do the replacement. */
|
1124
|
+
if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
|
1125
|
+
Data_Get_Struct(pattern, re2_pattern, p);
|
1126
|
+
RE2::Replace(&str_as_string, *p->pattern, StringValuePtr(rewrite));
|
1127
|
+
|
1128
|
+
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
1129
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
1130
|
+
} else {
|
1131
|
+
RE2::Replace(&str_as_string, StringValuePtr(pattern),
|
1132
|
+
StringValuePtr(rewrite));
|
1133
|
+
|
1134
|
+
return ENCODED_STR_NEW2(str_as_string.data(), str_as_string.size(),
|
1135
|
+
pattern);
|
1097
1136
|
}
|
1098
1137
|
|
1099
|
-
|
1100
|
-
* Returns a copy of +str+ with the first occurrence +pattern+
|
1101
|
-
* replaced with +rewrite+.
|
1102
|
-
*
|
1103
|
-
* @param [String] str the string to modify
|
1104
|
-
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
1105
|
-
* @param [String] rewrite the string to replace with
|
1106
|
-
* @return [String] the resulting string
|
1107
|
-
* @example
|
1108
|
-
* RE2.Replace("hello there", "hello", "howdy") #=> "howdy there"
|
1109
|
-
* re2 = RE2.new("hel+o")
|
1110
|
-
* RE2.Replace("hello there", re2, "yo") #=> "yo there"
|
1111
|
-
*/
|
1112
|
-
static VALUE re2_Replace(VALUE self, VALUE str, VALUE pattern,
|
1113
|
-
VALUE rewrite) {
|
1114
|
-
UNUSED(self);
|
1115
|
-
re2_pattern *p;
|
1116
|
-
|
1117
|
-
/* Convert all the inputs to be pumped into RE2::Replace. */
|
1118
|
-
string str_as_string(StringValuePtr(str));
|
1119
|
-
|
1120
|
-
/* Do the replacement. */
|
1121
|
-
if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
|
1122
|
-
Data_Get_Struct(pattern, re2_pattern, p);
|
1123
|
-
RE2::Replace(&str_as_string, *p->pattern, StringValuePtr(rewrite));
|
1124
|
-
|
1125
|
-
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
1126
|
-
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
1127
|
-
} else {
|
1128
|
-
RE2::Replace(&str_as_string, StringValuePtr(pattern),
|
1129
|
-
StringValuePtr(rewrite));
|
1138
|
+
}
|
1130
1139
|
|
1131
|
-
|
1132
|
-
|
1133
|
-
|
1140
|
+
/*
|
1141
|
+
* Return a copy of +str+ with +pattern+ replaced by +rewrite+.
|
1142
|
+
*
|
1143
|
+
* @param [String] str the string to modify
|
1144
|
+
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
1145
|
+
* @param [String] rewrite the string to replace with
|
1146
|
+
* @return [String] the resulting string
|
1147
|
+
* @example
|
1148
|
+
* re2 = RE2.new("oo?")
|
1149
|
+
* RE2.GlobalReplace("whoops-doops", re2, "e") #=> "wheps-deps"
|
1150
|
+
* RE2.GlobalReplace("hello there", "e", "i") #=> "hillo thiri"
|
1151
|
+
*/
|
1152
|
+
static VALUE re2_GlobalReplace(VALUE self, VALUE str, VALUE pattern,
|
1153
|
+
VALUE rewrite) {
|
1154
|
+
UNUSED(self);
|
1134
1155
|
|
1135
|
-
|
1156
|
+
/* Convert all the inputs to be pumped into RE2::GlobalReplace. */
|
1157
|
+
re2_pattern *p;
|
1158
|
+
string str_as_string(StringValuePtr(str));
|
1136
1159
|
|
1137
|
-
/*
|
1138
|
-
|
1139
|
-
|
1140
|
-
|
1141
|
-
* @param [String, RE2::Regexp] pattern a regexp matching text to be replaced
|
1142
|
-
* @param [String] rewrite the string to replace with
|
1143
|
-
* @return [String] the resulting string
|
1144
|
-
* @example
|
1145
|
-
* re2 = RE2.new("oo?")
|
1146
|
-
* RE2.GlobalReplace("whoops-doops", re2, "e") #=> "wheps-deps"
|
1147
|
-
* RE2.GlobalReplace("hello there", "e", "i") #=> "hillo thiri"
|
1148
|
-
*/
|
1149
|
-
static VALUE re2_GlobalReplace(VALUE self, VALUE str, VALUE pattern,
|
1150
|
-
VALUE rewrite) {
|
1151
|
-
UNUSED(self);
|
1152
|
-
|
1153
|
-
/* Convert all the inputs to be pumped into RE2::GlobalReplace. */
|
1154
|
-
re2_pattern *p;
|
1155
|
-
string str_as_string(StringValuePtr(str));
|
1156
|
-
|
1157
|
-
/* Do the replacement. */
|
1158
|
-
if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
|
1159
|
-
Data_Get_Struct(pattern, re2_pattern, p);
|
1160
|
-
RE2::GlobalReplace(&str_as_string, *p->pattern, StringValuePtr(rewrite));
|
1161
|
-
|
1162
|
-
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
1163
|
-
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
1164
|
-
} else {
|
1165
|
-
RE2::GlobalReplace(&str_as_string, StringValuePtr(pattern),
|
1166
|
-
StringValuePtr(rewrite));
|
1160
|
+
/* Do the replacement. */
|
1161
|
+
if (rb_obj_is_kind_of(pattern, re2_cRegexp)) {
|
1162
|
+
Data_Get_Struct(pattern, re2_pattern, p);
|
1163
|
+
RE2::GlobalReplace(&str_as_string, *p->pattern, StringValuePtr(rewrite));
|
1167
1164
|
|
1168
|
-
|
1169
|
-
|
1170
|
-
|
1171
|
-
|
1165
|
+
return ENCODED_STR_NEW(str_as_string.data(), str_as_string.size(),
|
1166
|
+
p->pattern->options().utf8() ? "UTF-8" : "ISO-8859-1");
|
1167
|
+
} else {
|
1168
|
+
RE2::GlobalReplace(&str_as_string, StringValuePtr(pattern),
|
1169
|
+
StringValuePtr(rewrite));
|
1172
1170
|
|
1173
|
-
|
1174
|
-
|
1175
|
-
* characters escaped. The returned string, used as a regular
|
1176
|
-
* expression, will exactly match the original string.
|
1177
|
-
*
|
1178
|
-
* @param [String] unquoted the unquoted string
|
1179
|
-
* @return [String] the escaped string
|
1180
|
-
* @example
|
1181
|
-
* RE2::Regexp.escape("1.5-2.0?") #=> "1\.5\-2\.0\?"
|
1182
|
-
*/
|
1183
|
-
static VALUE re2_QuoteMeta(VALUE self, VALUE unquoted) {
|
1184
|
-
UNUSED(self);
|
1185
|
-
string quoted_string = RE2::QuoteMeta(StringValuePtr(unquoted));
|
1186
|
-
return rb_str_new(quoted_string.data(), quoted_string.size());
|
1171
|
+
return ENCODED_STR_NEW2(str_as_string.data(), str_as_string.size(),
|
1172
|
+
pattern);
|
1187
1173
|
}
|
1174
|
+
}
|
1188
1175
|
|
1189
|
-
|
1190
|
-
|
1191
|
-
|
1192
|
-
|
1193
|
-
|
1194
|
-
|
1195
|
-
|
1196
|
-
|
1197
|
-
|
1198
|
-
|
1199
|
-
|
1200
|
-
|
1201
|
-
|
1202
|
-
|
1203
|
-
|
1204
|
-
|
1205
|
-
|
1206
|
-
|
1207
|
-
|
1208
|
-
|
1209
|
-
|
1210
|
-
|
1211
|
-
|
1212
|
-
|
1213
|
-
|
1214
|
-
|
1215
|
-
|
1216
|
-
|
1217
|
-
|
1218
|
-
|
1219
|
-
|
1220
|
-
|
1221
|
-
|
1222
|
-
|
1223
|
-
|
1224
|
-
|
1225
|
-
|
1226
|
-
|
1227
|
-
|
1228
|
-
|
1229
|
-
|
1230
|
-
|
1231
|
-
|
1232
|
-
|
1233
|
-
|
1234
|
-
RUBY_METHOD_FUNC(
|
1235
|
-
|
1236
|
-
|
1237
|
-
|
1238
|
-
|
1239
|
-
|
1240
|
-
|
1241
|
-
|
1242
|
-
|
1243
|
-
|
1244
|
-
|
1245
|
-
|
1246
|
-
|
1247
|
-
|
1248
|
-
|
1249
|
-
|
1250
|
-
|
1251
|
-
|
1252
|
-
|
1253
|
-
|
1254
|
-
|
1255
|
-
|
1256
|
-
|
1257
|
-
|
1258
|
-
|
1259
|
-
|
1260
|
-
|
1261
|
-
|
1262
|
-
|
1263
|
-
|
1264
|
-
|
1265
|
-
|
1266
|
-
|
1267
|
-
|
1268
|
-
|
1269
|
-
|
1270
|
-
|
1271
|
-
|
1272
|
-
|
1273
|
-
|
1274
|
-
|
1275
|
-
|
1276
|
-
|
1277
|
-
|
1278
|
-
|
1279
|
-
|
1280
|
-
|
1281
|
-
|
1282
|
-
|
1283
|
-
|
1284
|
-
|
1285
|
-
|
1286
|
-
|
1287
|
-
|
1288
|
-
|
1289
|
-
|
1290
|
-
|
1291
|
-
|
1292
|
-
|
1293
|
-
|
1294
|
-
|
1295
|
-
|
1296
|
-
|
1297
|
-
|
1298
|
-
|
1299
|
-
|
1300
|
-
|
1301
|
-
|
1302
|
-
|
1303
|
-
|
1304
|
-
|
1305
|
-
|
1306
|
-
|
1307
|
-
|
1308
|
-
|
1309
|
-
|
1310
|
-
|
1311
|
-
|
1312
|
-
|
1313
|
-
|
1314
|
-
|
1315
|
-
|
1316
|
-
|
1317
|
-
|
1318
|
-
|
1319
|
-
|
1176
|
+
/*
|
1177
|
+
* Returns a version of str with all potentially meaningful regexp
|
1178
|
+
* characters escaped. The returned string, used as a regular
|
1179
|
+
* expression, will exactly match the original string.
|
1180
|
+
*
|
1181
|
+
* @param [String] unquoted the unquoted string
|
1182
|
+
* @return [String] the escaped string
|
1183
|
+
* @example
|
1184
|
+
* RE2::Regexp.escape("1.5-2.0?") #=> "1\.5\-2\.0\?"
|
1185
|
+
*/
|
1186
|
+
static VALUE re2_QuoteMeta(VALUE self, VALUE unquoted) {
|
1187
|
+
UNUSED(self);
|
1188
|
+
string quoted_string = RE2::QuoteMeta(StringValuePtr(unquoted));
|
1189
|
+
return rb_str_new(quoted_string.data(), quoted_string.size());
|
1190
|
+
}
|
1191
|
+
|
1192
|
+
/* Forward declare Init_re2 to be called by C code but define it separately so
|
1193
|
+
* that YARD can parse it.
|
1194
|
+
*/
|
1195
|
+
extern "C" void Init_re2(void);
|
1196
|
+
|
1197
|
+
void Init_re2(void) {
|
1198
|
+
re2_mRE2 = rb_define_module("RE2");
|
1199
|
+
re2_cRegexp = rb_define_class_under(re2_mRE2, "Regexp", rb_cObject);
|
1200
|
+
re2_cMatchData = rb_define_class_under(re2_mRE2, "MatchData", rb_cObject);
|
1201
|
+
re2_cScanner = rb_define_class_under(re2_mRE2, "Scanner", rb_cObject);
|
1202
|
+
|
1203
|
+
rb_define_alloc_func(re2_cRegexp, (VALUE (*)(VALUE))re2_regexp_allocate);
|
1204
|
+
rb_define_alloc_func(re2_cMatchData,
|
1205
|
+
(VALUE (*)(VALUE))re2_matchdata_allocate);
|
1206
|
+
rb_define_alloc_func(re2_cScanner,
|
1207
|
+
(VALUE (*)(VALUE))re2_scanner_allocate);
|
1208
|
+
|
1209
|
+
rb_define_method(re2_cMatchData, "string",
|
1210
|
+
RUBY_METHOD_FUNC(re2_matchdata_string), 0);
|
1211
|
+
rb_define_method(re2_cMatchData, "regexp",
|
1212
|
+
RUBY_METHOD_FUNC(re2_matchdata_regexp), 0);
|
1213
|
+
rb_define_method(re2_cMatchData, "to_a",
|
1214
|
+
RUBY_METHOD_FUNC(re2_matchdata_to_a), 0);
|
1215
|
+
rb_define_method(re2_cMatchData, "size",
|
1216
|
+
RUBY_METHOD_FUNC(re2_matchdata_size), 0);
|
1217
|
+
rb_define_method(re2_cMatchData, "length",
|
1218
|
+
RUBY_METHOD_FUNC(re2_matchdata_size), 0);
|
1219
|
+
rb_define_method(re2_cMatchData, "[]", RUBY_METHOD_FUNC(re2_matchdata_aref),
|
1220
|
+
-1); rb_define_method(re2_cMatchData, "to_s",
|
1221
|
+
RUBY_METHOD_FUNC(re2_matchdata_to_s), 0);
|
1222
|
+
rb_define_method(re2_cMatchData, "inspect",
|
1223
|
+
RUBY_METHOD_FUNC(re2_matchdata_inspect), 0);
|
1224
|
+
|
1225
|
+
rb_define_method(re2_cScanner, "string",
|
1226
|
+
RUBY_METHOD_FUNC(re2_scanner_string), 0);
|
1227
|
+
rb_define_method(re2_cScanner, "regexp",
|
1228
|
+
RUBY_METHOD_FUNC(re2_scanner_regexp), 0);
|
1229
|
+
rb_define_method(re2_cScanner, "scan",
|
1230
|
+
RUBY_METHOD_FUNC(re2_scanner_scan), 0);
|
1231
|
+
rb_define_method(re2_cScanner, "rewind",
|
1232
|
+
RUBY_METHOD_FUNC(re2_scanner_rewind), 0);
|
1233
|
+
|
1234
|
+
rb_define_method(re2_cRegexp, "initialize",
|
1235
|
+
RUBY_METHOD_FUNC(re2_regexp_initialize), -1);
|
1236
|
+
rb_define_method(re2_cRegexp, "ok?", RUBY_METHOD_FUNC(re2_regexp_ok), 0);
|
1237
|
+
rb_define_method(re2_cRegexp, "error", RUBY_METHOD_FUNC(re2_regexp_error),
|
1238
|
+
0);
|
1239
|
+
rb_define_method(re2_cRegexp, "error_arg",
|
1240
|
+
RUBY_METHOD_FUNC(re2_regexp_error_arg), 0);
|
1241
|
+
rb_define_method(re2_cRegexp, "program_size",
|
1242
|
+
RUBY_METHOD_FUNC(re2_regexp_program_size), 0);
|
1243
|
+
rb_define_method(re2_cRegexp, "options",
|
1244
|
+
RUBY_METHOD_FUNC(re2_regexp_options), 0);
|
1245
|
+
rb_define_method(re2_cRegexp, "number_of_capturing_groups",
|
1246
|
+
RUBY_METHOD_FUNC(re2_regexp_number_of_capturing_groups), 0);
|
1247
|
+
rb_define_method(re2_cRegexp, "named_capturing_groups",
|
1248
|
+
RUBY_METHOD_FUNC(re2_regexp_named_capturing_groups), 0);
|
1249
|
+
rb_define_method(re2_cRegexp, "match", RUBY_METHOD_FUNC(re2_regexp_match),
|
1250
|
+
-1);
|
1251
|
+
rb_define_method(re2_cRegexp, "match?",
|
1252
|
+
RUBY_METHOD_FUNC(re2_regexp_match_query), 1);
|
1253
|
+
rb_define_method(re2_cRegexp, "=~",
|
1254
|
+
RUBY_METHOD_FUNC(re2_regexp_match_query), 1);
|
1255
|
+
rb_define_method(re2_cRegexp, "===",
|
1256
|
+
RUBY_METHOD_FUNC(re2_regexp_match_query), 1);
|
1257
|
+
rb_define_method(re2_cRegexp, "scan",
|
1258
|
+
RUBY_METHOD_FUNC(re2_regexp_scan), 1);
|
1259
|
+
rb_define_method(re2_cRegexp, "to_s", RUBY_METHOD_FUNC(re2_regexp_to_s), 0);
|
1260
|
+
rb_define_method(re2_cRegexp, "to_str", RUBY_METHOD_FUNC(re2_regexp_to_s),
|
1261
|
+
0);
|
1262
|
+
rb_define_method(re2_cRegexp, "pattern", RUBY_METHOD_FUNC(re2_regexp_to_s),
|
1263
|
+
0);
|
1264
|
+
rb_define_method(re2_cRegexp, "source", RUBY_METHOD_FUNC(re2_regexp_to_s),
|
1265
|
+
0);
|
1266
|
+
rb_define_method(re2_cRegexp, "inspect",
|
1267
|
+
RUBY_METHOD_FUNC(re2_regexp_inspect), 0);
|
1268
|
+
rb_define_method(re2_cRegexp, "utf8?", RUBY_METHOD_FUNC(re2_regexp_utf8),
|
1269
|
+
0);
|
1270
|
+
rb_define_method(re2_cRegexp, "posix_syntax?",
|
1271
|
+
RUBY_METHOD_FUNC(re2_regexp_posix_syntax), 0);
|
1272
|
+
rb_define_method(re2_cRegexp, "longest_match?",
|
1273
|
+
RUBY_METHOD_FUNC(re2_regexp_longest_match), 0);
|
1274
|
+
rb_define_method(re2_cRegexp, "log_errors?",
|
1275
|
+
RUBY_METHOD_FUNC(re2_regexp_log_errors), 0);
|
1276
|
+
rb_define_method(re2_cRegexp, "max_mem",
|
1277
|
+
RUBY_METHOD_FUNC(re2_regexp_max_mem), 0);
|
1278
|
+
rb_define_method(re2_cRegexp, "literal?",
|
1279
|
+
RUBY_METHOD_FUNC(re2_regexp_literal), 0);
|
1280
|
+
rb_define_method(re2_cRegexp, "never_nl?",
|
1281
|
+
RUBY_METHOD_FUNC(re2_regexp_never_nl), 0);
|
1282
|
+
rb_define_method(re2_cRegexp, "case_sensitive?",
|
1283
|
+
RUBY_METHOD_FUNC(re2_regexp_case_sensitive), 0);
|
1284
|
+
rb_define_method(re2_cRegexp, "case_insensitive?",
|
1285
|
+
RUBY_METHOD_FUNC(re2_regexp_case_insensitive), 0);
|
1286
|
+
rb_define_method(re2_cRegexp, "casefold?",
|
1287
|
+
RUBY_METHOD_FUNC(re2_regexp_case_insensitive), 0);
|
1288
|
+
rb_define_method(re2_cRegexp, "perl_classes?",
|
1289
|
+
RUBY_METHOD_FUNC(re2_regexp_perl_classes), 0);
|
1290
|
+
rb_define_method(re2_cRegexp, "word_boundary?",
|
1291
|
+
RUBY_METHOD_FUNC(re2_regexp_word_boundary), 0);
|
1292
|
+
rb_define_method(re2_cRegexp, "one_line?",
|
1293
|
+
RUBY_METHOD_FUNC(re2_regexp_one_line), 0);
|
1294
|
+
|
1295
|
+
rb_define_module_function(re2_mRE2, "Replace",
|
1296
|
+
RUBY_METHOD_FUNC(re2_Replace), 3);
|
1297
|
+
rb_define_module_function(re2_mRE2, "GlobalReplace",
|
1298
|
+
RUBY_METHOD_FUNC(re2_GlobalReplace), 3);
|
1299
|
+
rb_define_module_function(re2_mRE2, "QuoteMeta",
|
1300
|
+
RUBY_METHOD_FUNC(re2_QuoteMeta), 1);
|
1301
|
+
rb_define_singleton_method(re2_cRegexp, "escape",
|
1302
|
+
RUBY_METHOD_FUNC(re2_QuoteMeta), 1);
|
1303
|
+
rb_define_singleton_method(re2_cRegexp, "quote",
|
1304
|
+
RUBY_METHOD_FUNC(re2_QuoteMeta), 1);
|
1305
|
+
rb_define_singleton_method(re2_cRegexp, "compile",
|
1306
|
+
RUBY_METHOD_FUNC(rb_class_new_instance), -1);
|
1307
|
+
|
1308
|
+
rb_define_global_function("RE2", RUBY_METHOD_FUNC(re2_re2), -1);
|
1309
|
+
|
1310
|
+
/* Create the symbols used in options. */
|
1311
|
+
id_utf8 = rb_intern("utf8");
|
1312
|
+
id_posix_syntax = rb_intern("posix_syntax");
|
1313
|
+
id_longest_match = rb_intern("longest_match");
|
1314
|
+
id_log_errors = rb_intern("log_errors");
|
1315
|
+
id_max_mem = rb_intern("max_mem");
|
1316
|
+
id_literal = rb_intern("literal");
|
1317
|
+
id_never_nl = rb_intern("never_nl");
|
1318
|
+
id_case_sensitive = rb_intern("case_sensitive");
|
1319
|
+
id_perl_classes = rb_intern("perl_classes");
|
1320
|
+
id_word_boundary = rb_intern("word_boundary");
|
1321
|
+
id_one_line = rb_intern("one_line");
|
1322
|
+
|
1323
|
+
#if 0
|
1324
|
+
/* Fake so YARD generates the file. */
|
1325
|
+
rb_mKernel = rb_define_module("Kernel");
|
1326
|
+
#endif
|
1320
1327
|
}
|