1// Copyright 2009 the V8 project authors. All rights reserved.
2// Redistribution and use in source and binary forms, with or without
3// modification, are permitted provided that the following conditions are
4// met:
5//
6//     * Redistributions of source code must retain the above copyright
7//       notice, this list of conditions and the following disclaimer.
8//     * Redistributions in binary form must reproduce the above
9//       copyright notice, this list of conditions and the following
10//       disclaimer in the documentation and/or other materials provided
11//       with the distribution.
12//     * Neither the name of Google Inc. nor the names of its
13//       contributors may be used to endorse or promote products derived
14//       from this software without specific prior written permission.
15//
16// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
17// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
18// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
19// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
20// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
21// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
22// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
23// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
24// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
25// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
26// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
27
28// Test Unicode character ranges in regexps.
29
30
31// Cyrillic.
32var cyrillic = {
33  FIRST: "\u0410",   // A
34  first: "\u0430",   // a
35  LAST: "\u042f",    // YA
36  last: "\u044f",    // ya
37  MIDDLE: "\u0427",  // CHE
38  middle: "\u0447",   // che
39  // Actually no characters are between the cases in Cyrillic.
40  BetweenCases: false};
41
42var SIGMA = "\u03a3";
43var sigma = "\u03c3";
44var alternative_sigma = "\u03c2";
45
46// Greek.
47var greek = {
48  FIRST: "\u0391",     // ALPHA
49  first: "\u03b1",     // alpha
50  LAST: "\u03a9",      // OMEGA
51  last: "\u03c9",      // omega
52  MIDDLE: SIGMA,       // SIGMA
53  middle: sigma,       // sigma
54  // Epsilon acute is between ALPHA-OMEGA and alpha-omega, ie it
55  // is between OMEGA and alpha.
56  BetweenCases: "\u03ad"};
57
58
59function Range(from, to, flags) {
60  return new RegExp("[" + from + "-" + to + "]", flags);
61}
62
63// Test Cyrillic and Greek separately.
64for (var lang = 0; lang < 2; lang++) {
65  var chars = (lang == 0) ? cyrillic : greek;
66
67  for (var i = 0; i < 2; i++) {
68    var lc = (i == 0);  // Lower case.
69    var first = lc ? chars.first : chars.FIRST;
70    var middle = lc ? chars.middle : chars.MIDDLE;
71    var last = lc ? chars.last : chars.LAST;
72    var first_other_case = lc ? chars.FIRST : chars.first;
73    var middle_other_case = lc ? chars.MIDDLE : chars.middle;
74    var last_other_case = lc ? chars.LAST : chars.last;
75
76    assertTrue(Range(first, last).test(first), 1);
77    assertTrue(Range(first, last).test(middle), 2);
78    assertTrue(Range(first, last).test(last), 3);
79
80    assertFalse(Range(first, last).test(first_other_case), 4);
81    assertFalse(Range(first, last).test(middle_other_case), 5);
82    assertFalse(Range(first, last).test(last_other_case), 6);
83
84    assertTrue(Range(first, last, "i").test(first), 7);
85    assertTrue(Range(first, last, "i").test(middle), 8);
86    assertTrue(Range(first, last, "i").test(last), 9);
87
88    assertTrue(Range(first, last, "i").test(first_other_case), 10);
89    assertTrue(Range(first, last, "i").test(middle_other_case), 11);
90    assertTrue(Range(first, last, "i").test(last_other_case), 12);
91
92    if (chars.BetweenCases) {
93      assertFalse(Range(first, last).test(chars.BetweenCases), 13);
94      assertFalse(Range(first, last, "i").test(chars.BetweenCases), 14);
95    }
96  }
97  if (chars.BetweenCases) {
98    assertTrue(Range(chars.FIRST, chars.last).test(chars.BetweenCases), 15);
99    assertTrue(Range(chars.FIRST, chars.last, "i").test(chars.BetweenCases), 16);
100  }
101}
102
103// Test range that covers both greek and cyrillic characters.
104for (key in greek) {
105  assertTrue(Range(greek.FIRST, cyrillic.last).test(greek[key]), 17 + key);
106  if (cyrillic[key]) {
107    assertTrue(Range(greek.FIRST, cyrillic.last).test(cyrillic[key]), 18 + key);
108  }
109}
110
111for (var i = 0; i < 2; i++) {
112  var ignore_case = (i == 0);
113  var flag = ignore_case ? "i" : "";
114  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(greek.first), 19);
115  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(greek.middle), 20);
116  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(greek.last), 21);
117
118  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(cyrillic.FIRST), 22);
119  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(cyrillic.MIDDLE), 23);
120  assertTrue(Range(greek.first, cyrillic.LAST, flag).test(cyrillic.LAST), 24);
121
122  // A range that covers the lower case greek letters and the upper case cyrillic
123  // letters.
124  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(greek.FIRST), 25);
125  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(greek.MIDDLE), 26);
126  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(greek.LAST), 27);
127
128  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(cyrillic.first), 28);
129  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(cyrillic.middle), 29);
130  assertEquals(ignore_case, Range(greek.first, cyrillic.LAST, flag).test(cyrillic.last), 30);
131}
132
133
134// Sigma is special because there are two lower case versions of the same upper
135// case character.  JS requires that case independece means that you should
136// convert everything to upper case, so the two sigma variants are equal to each
137// other in a case independt comparison.
138for (var i = 0; i < 2; i++) {
139  var simple = (i != 0);
140  var name = simple ? "" : "[]";
141  var regex = simple ? SIGMA : "[" + SIGMA + "]";
142
143  assertFalse(new RegExp(regex).test(sigma), 31 + name);
144  assertFalse(new RegExp(regex).test(alternative_sigma), 32 + name);
145  assertTrue(new RegExp(regex).test(SIGMA), 33 + name);
146
147  assertTrue(new RegExp(regex, "i").test(sigma), 34 + name);
148  // JSC and Tracemonkey fail this one.
149  assertTrue(new RegExp(regex, "i").test(alternative_sigma), 35 + name);
150  assertTrue(new RegExp(regex, "i").test(SIGMA), 36 + name);
151
152  regex = simple ? sigma : "[" + sigma + "]";
153
154  assertTrue(new RegExp(regex).test(sigma), 41 + name);
155  assertFalse(new RegExp(regex).test(alternative_sigma), 42 + name);
156  assertFalse(new RegExp(regex).test(SIGMA), 43 + name);
157
158  assertTrue(new RegExp(regex, "i").test(sigma), 44 + name);
159  // JSC and Tracemonkey fail this one.
160  assertTrue(new RegExp(regex, "i").test(alternative_sigma), 45 + name);
161  assertTrue(new RegExp(regex, "i").test(SIGMA), 46 + name);
162
163  regex = simple ? alternative_sigma : "[" + alternative_sigma + "]";
164
165  assertFalse(new RegExp(regex).test(sigma), 51 + name);
166  assertTrue(new RegExp(regex).test(alternative_sigma), 52 + name);
167  assertFalse(new RegExp(regex).test(SIGMA), 53 + name);
168
169  // JSC and Tracemonkey fail this one.
170  assertTrue(new RegExp(regex, "i").test(sigma), 54 + name);
171  assertTrue(new RegExp(regex, "i").test(alternative_sigma), 55 + name);
172  // JSC and Tracemonkey fail this one.
173  assertTrue(new RegExp(regex, "i").test(SIGMA), 56 + name);
174}
175
176
177for (var add_non_ascii_character_to_subject = 0;
178     add_non_ascii_character_to_subject < 2;
179     add_non_ascii_character_to_subject++) {
180  var suffix = add_non_ascii_character_to_subject ? "\ufffe" : "";
181  // A range that covers both ASCII and non-ASCII.
182  for (var i = 0; i < 2; i++) {
183    var full = (i != 0);
184    var mixed = full ? "[a-\uffff]" : "[a-" + cyrillic.LAST + "]";
185    var f = full ? "f" : "c";
186    for (var j = 0; j < 2; j++) {
187      var ignore_case = (j == 0);
188      var flag = ignore_case ? "i" : "";
189      var re = new RegExp(mixed, flag);
190      var expected =
191          ignore_case || (full && !!add_non_ascii_character_to_subject);
192      assertEquals(expected, re.test("A" + suffix), 58 + flag + f);
193      assertTrue(re.test("a" + suffix), 59 + flag + f);
194      assertTrue(re.test("~" + suffix), 60 + flag + f);
195      assertTrue(re.test(cyrillic.MIDDLE), 61 + flag + f);
196      assertEquals(ignore_case || full, re.test(cyrillic.middle), 62 + flag + f);
197    }
198  }
199}
200