1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
|
// Copyright 2014 the V8 project authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
// ES6 extends the \uxxxx escape and also allows \u{xxxxx}.
// Flags: --harmony-unicode-regexps --harmony-regexps
function testRegexpHelper(r) {
assertTrue(r.test("foo"));
assertTrue(r.test("boo"));
assertFalse(r.test("moo"));
}
(function TestUnicodeEscapes() {
testRegexpHelper(/(\u0066|\u0062)oo/);
testRegexpHelper(/(\u0066|\u0062)oo/u);
testRegexpHelper(/(\u{0066}|\u{0062})oo/u);
testRegexpHelper(/(\u{66}|\u{000062})oo/u);
// Note that we need \\ inside a string, otherwise it's interpreted as a
// unicode escape inside a string.
testRegexpHelper(new RegExp("(\\u0066|\\u0062)oo"));
testRegexpHelper(new RegExp("(\\u0066|\\u0062)oo", "u"));
testRegexpHelper(new RegExp("(\\u{0066}|\\u{0062})oo", "u"));
testRegexpHelper(new RegExp("(\\u{66}|\\u{000062})oo", "u"));
// Though, unicode escapes via strings should work too.
testRegexpHelper(new RegExp("(\u0066|\u0062)oo"));
testRegexpHelper(new RegExp("(\u0066|\u0062)oo", "u"));
testRegexpHelper(new RegExp("(\u{0066}|\u{0062})oo", "u"));
testRegexpHelper(new RegExp("(\u{66}|\u{000062})oo", "u"));
})();
(function TestUnicodeEscapesInCharacterClasses() {
testRegexpHelper(/[\u0062-\u0066]oo/);
testRegexpHelper(/[\u0062-\u0066]oo/u);
testRegexpHelper(/[\u{0062}-\u{0066}]oo/u);
testRegexpHelper(/[\u{62}-\u{00000066}]oo/u);
// Note that we need \\ inside a string, otherwise it's interpreted as a
// unicode escape inside a string.
testRegexpHelper(new RegExp("[\\u0062-\\u0066]oo"));
testRegexpHelper(new RegExp("[\\u0062-\\u0066]oo", "u"));
testRegexpHelper(new RegExp("[\\u{0062}-\\u{0066}]oo", "u"));
testRegexpHelper(new RegExp("[\\u{62}-\\u{00000066}]oo", "u"));
// Though, unicode escapes via strings should work too.
testRegexpHelper(new RegExp("[\u0062-\u0066]oo"));
testRegexpHelper(new RegExp("[\u0062-\u0066]oo", "u"));
testRegexpHelper(new RegExp("[\u{0062}-\u{0066}]oo", "u"));
testRegexpHelper(new RegExp("[\u{62}-\u{00000066}]oo", "u"));
})();
(function TestBraceEscapesWithoutUnicodeFlag() {
// \u followed by illegal escape will be parsed as u. {x} will be the
// character count.
function helper1(r) {
assertFalse(r.test("fbar"));
assertFalse(r.test("fubar"));
assertTrue(r.test("fuubar"));
assertFalse(r.test("fuuubar"));
}
helper1(/f\u{2}bar/);
helper1(new RegExp("f\\u{2}bar"));
function helper2(r) {
assertFalse(r.test("fbar"));
assertTrue(r.test("fubar"));
assertTrue(r.test("fuubar"));
assertFalse(r.test("fuuubar"));
}
helper2(/f\u{1,2}bar/);
helper2(new RegExp("f\\u{1,2}bar"));
function helper3(r) {
assertTrue(r.test("u"));
assertTrue(r.test("{"));
assertTrue(r.test("2"));
assertTrue(r.test("}"));
assertFalse(r.test("q"));
assertFalse(r.test("("));
assertFalse(r.test(")"));
}
helper3(/[\u{2}]/);
helper3(new RegExp("[\\u{2}]"));
})();
(function TestInvalidEscapes() {
// Without the u flag, invalid unicode escapes and other invalid escapes are
// treated as identity escapes.
function helper1(r) {
assertTrue(r.test("firstuxz89second"));
}
helper1(/first\u\x\z\8\9second/);
helper1(new RegExp("first\\u\\x\\z\\8\\9second"));
function helper2(r) {
assertTrue(r.test("u"));
assertTrue(r.test("x"));
assertTrue(r.test("z"));
assertTrue(r.test("8"));
assertTrue(r.test("9"));
assertFalse(r.test("q"));
assertFalse(r.test("7"));
}
helper2(/[\u\x\z\8\9]/);
helper2(new RegExp("[\\u\\x\\z\\8\\9]"));
// However, with the u flag, these are treated as invalid escapes.
assertThrows("/\\u/u", SyntaxError);
assertThrows("/\\u12/u", SyntaxError);
assertThrows("/\\ufoo/u", SyntaxError);
assertThrows("/\\x/u", SyntaxError);
assertThrows("/\\xfoo/u", SyntaxError);
assertThrows("/\\z/u", SyntaxError);
assertThrows("/\\8/u", SyntaxError);
assertThrows("/\\9/u", SyntaxError);
assertThrows("new RegExp('\\\\u', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\u12', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\ufoo', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\x', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\xfoo', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\z', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\8', 'u')", SyntaxError);
assertThrows("new RegExp('\\\\9', 'u')", SyntaxError);
})();
(function TestTooBigHexEscape() {
// The hex number inside \u{} has a maximum value.
/\u{10ffff}/u
new RegExp("\\u{10ffff}", "u")
assertThrows("/\\u{110000}/u", SyntaxError);
assertThrows("new RegExp('\\\\u{110000}', 'u')", SyntaxError);
// Without the u flag, they're of course fine ({x} is the count).
/\u{110000}/
new RegExp("\\u{110000}")
})();
(function TestSyntaxEscapes() {
// Syntax escapes work the same with or without the u flag.
function helper(r) {
assertTrue(r.test("foo[bar"));
assertFalse(r.test("foo]bar"));
}
helper(/foo\[bar/);
helper(new RegExp("foo\\[bar"));
helper(/foo\[bar/u);
helper(new RegExp("foo\\[bar", "u"));
})();
(function TestUnicodeSurrogates() {
// U+10E6D corresponds to the surrogate pair [U+D803, U+DE6D].
function helper(r) {
assertTrue(r.test("foo\u{10e6d}bar"));
}
helper(/foo\ud803\ude6dbar/u);
helper(new RegExp("foo\\ud803\\ude6dbar", "u"));
})();
(function AllFlags() {
// Test that we can pass all possible regexp flags and they work properly.
function helper1(r) {
assertTrue(r.global);
assertTrue(r.ignoreCase);
assertTrue(r.multiline);
assertTrue(r.sticky);
assertTrue(r.unicode);
}
helper1(/foo/gimyu);
helper1(new RegExp("foo", "gimyu"));
function helper2(r) {
assertFalse(r.global);
assertFalse(r.ignoreCase);
assertFalse(r.multiline);
assertFalse(r.sticky);
assertFalse(r.unicode);
}
helper2(/foo/);
helper2(new RegExp("foo"));
})();
(function DuplicatedFlags() {
// Test that duplicating the u flag is not allowed.
assertThrows("/foo/ugu");
assertThrows("new RegExp('foo', 'ugu')");
})();
(function ToString() {
// Test that the u flag is included in the string representation of regexps.
function helper(r) {
assertEquals(r.toString(), "/foo/u");
}
helper(/foo/u);
helper(new RegExp("foo", "u"));
})();
// Non-BMP patterns.
// Single character atom.
assertTrue(new RegExp("\u{12345}", "u").test("\u{12345}"));
assertTrue(/\u{12345}/u.test("\u{12345}"));
assertTrue(new RegExp("\u{12345}", "u").test("\ud808\udf45"));
assertTrue(/\u{12345}/u.test("\ud808\udf45"));
assertFalse(new RegExp("\u{12345}", "u").test("\udf45"));
assertFalse(/\u{12345}/u.test("\udf45"));
// Multi-character atom.
assertTrue(new RegExp("\u{12345}\u{23456}", "u").test("a\u{12345}\u{23456}b"));
assertTrue(/\u{12345}\u{23456}/u.test("b\u{12345}\u{23456}c"));
assertFalse(new RegExp("\u{12345}\u{23456}", "u").test("a\udf45\u{23456}b"));
assertFalse(/\u{12345}\u{23456}/u.test("b\udf45\u{23456}c"));
// Disjunction.
assertTrue(new RegExp("\u{12345}(?:\u{23456})", "u").test(
"a\u{12345}\u{23456}b"));
assertTrue(/\u{12345}(?:\u{23456})/u.test("b\u{12345}\u{23456}c"));
assertFalse(new RegExp("\u{12345}(?:\u{23456})", "u").test(
"a\udf45\u{23456}b"));
assertFalse(/\u{12345}(?:\u{23456})/u.test("b\udf45\u{23456}c"));
// Alternative.
assertTrue(new RegExp("\u{12345}|\u{23456}", "u").test("a\u{12345}b"));
assertTrue(/\u{12345}|\u{23456}/u.test("b\u{23456}c"));
assertFalse(new RegExp("\u{12345}|\u{23456}", "u").test("a\udf45\ud84db"));
assertFalse(/\u{12345}|\u{23456}/u.test("b\udf45\ud808c"));
// Capture.
assertTrue(new RegExp("(\u{12345}|\u{23456}).\\1", "u").test(
"\u{12345}b\u{12345}"));
assertTrue(/(\u{12345}|\u{23456}).\1/u.test("\u{12345}b\u{12345}"));
assertFalse(new RegExp("(\u{12345}|\u{23456}).\\1", "u").test(
"\u{12345}b\u{23456}"));
assertFalse(/(\u{12345}|\u{23456}).\1/u.test("\u{12345}b\u{23456}"));
// Quantifier.
assertTrue(new RegExp("\u{12345}{3}", "u").test("\u{12345}\u{12345}\u{12345}"));
assertTrue(/\u{12345}{3}/u.test("\u{12345}\u{12345}\u{12345}"));
assertTrue(new RegExp("\u{12345}{3}").test("\u{12345}\udf45\udf45"));
assertFalse(/\ud808\udf45{3}/u.test("\u{12345}\udf45\udf45"));
assertTrue(/\ud808\udf45{3}/u.test("\u{12345}\u{12345}\u{12345}"));
assertFalse(new RegExp("\u{12345}{3}", "u").test("\u{12345}\udf45\udf45"));
assertFalse(/\u{12345}{3}/u.test("\u{12345}\udf45\udf45"));
// Literal surrogates.
assertEquals(["\u{10000}\u{10000}"],
new RegExp("\ud800\udc00+", "u").exec("\u{10000}\u{10000}"));
assertEquals(["\u{10000}\u{10000}"],
new RegExp("\\ud800\\udc00+", "u").exec("\u{10000}\u{10000}"));
assertEquals(["\u{10003}\u{50001}"],
new RegExp("[\\ud800\\udc03-\\ud900\\udc01\]+", "u").exec(
"\u{10003}\u{50001}"));
assertEquals(["\u{10003}\u{50001}"],
new RegExp("[\ud800\udc03-\u{50001}\]+", "u").exec(
"\u{10003}\u{50001}"));
// Unicode escape sequences to represent a non-BMP character cannot have
// mixed notation, and must follow the rules for RegExpUnicodeEscapeSequence.
assertThrows(() => new RegExp("[\\ud800\udc03-\ud900\\udc01\]+", "u"));
assertThrows(() => new RegExp("[\\ud800\udc03-\ud900\\udc01\]+", "u"));
assertNull(new RegExp("\\ud800\udc00+", "u").exec("\u{10000}\u{10000}"));
assertNull(new RegExp("\ud800\\udc00+", "u").exec("\u{10000}\u{10000}"));
assertNull(new RegExp("[\\ud800\udc00]", "u").exec("\u{10000}"));
assertNull(new RegExp("[\\{ud800}\udc00]", "u").exec("\u{10000}"));
assertNull(new RegExp("[\ud800\\udc00]", "u").exec("\u{10000}"));
assertNull(new RegExp("[\ud800\\{udc00}]", "u").exec("\u{10000}"));
assertNull(/\u{d800}\u{dc00}+/u.exec("\ud800\udc00\udc00"));
assertNull(/\ud800\u{dc00}+/u.exec("\ud800\udc00\udc00"));
assertNull(/\u{d800}\udc00+/u.exec("\ud800\udc00\udc00"));
|
