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
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
|
// Copyright (c) 2011 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
#include "base/i18n/break_iterator.h"
#include "base/strings/string_piece.h"
#include "base/strings/stringprintf.h"
#include "base/strings/utf_string_conversions.h"
#include "testing/gtest/include/gtest/gtest.h"
namespace base {
namespace i18n {
TEST(BreakIteratorTest, BreakWordEmpty) {
string16 empty;
BreakIterator iter(empty, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakWord) {
string16 space(UTF8ToUTF16(" "));
string16 str(UTF8ToUTF16(" foo bar! \npouet boom"));
BreakIterator iter(str, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(space, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("foo"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(space, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("bar"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("!"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(space, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("\n"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("pouet"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(space, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("boom"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakWide16) {
// Two greek words separated by space.
const string16 str(WideToUTF16(
L"\x03a0\x03b1\x03b3\x03ba\x03cc\x03c3\x03bc\x03b9"
L"\x03bf\x03c2\x0020\x0399\x03c3\x03c4\x03cc\x03c2"));
const string16 word1(str.substr(0, 10));
const string16 word2(str.substr(11, 5));
BreakIterator iter(str, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(word1, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16(" "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(word2, iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakWide32) {
// U+1D49C MATHEMATICAL SCRIPT CAPITAL A
const char very_wide_char[] = "\xF0\x9D\x92\x9C";
const string16 str(
UTF8ToUTF16(base::StringPrintf("%s a", very_wide_char)));
const string16 very_wide_word(str.substr(0, 2));
BreakIterator iter(str, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(very_wide_word, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16(" "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("a"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakSpaceEmpty) {
string16 empty;
BreakIterator iter(empty, BreakIterator::BREAK_SPACE);
ASSERT_TRUE(iter.Init());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakSpace) {
string16 str(UTF8ToUTF16(" foo bar! \npouet boom"));
BreakIterator iter(str, BreakIterator::BREAK_SPACE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16(" "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("foo "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("bar! \n"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("pouet "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("boom"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakSpaceSP) {
string16 str(UTF8ToUTF16(" foo bar! \npouet boom "));
BreakIterator iter(str, BreakIterator::BREAK_SPACE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16(" "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("foo "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("bar! \n"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("pouet "), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("boom "), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakSpacekWide16) {
// Two Greek words.
const string16 str(WideToUTF16(
L"\x03a0\x03b1\x03b3\x03ba\x03cc\x03c3\x03bc\x03b9"
L"\x03bf\x03c2\x0020\x0399\x03c3\x03c4\x03cc\x03c2"));
const string16 word1(str.substr(0, 11));
const string16 word2(str.substr(11, 5));
BreakIterator iter(str, BreakIterator::BREAK_SPACE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(word1, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(word2, iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakSpaceWide32) {
// U+1D49C MATHEMATICAL SCRIPT CAPITAL A
const char very_wide_char[] = "\xF0\x9D\x92\x9C";
const string16 str(
UTF8ToUTF16(base::StringPrintf("%s a", very_wide_char)));
const string16 very_wide_word(str.substr(0, 3));
BreakIterator iter(str, BreakIterator::BREAK_SPACE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(very_wide_word, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("a"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakLineEmpty) {
string16 empty;
BreakIterator iter(empty, BreakIterator::BREAK_NEWLINE);
ASSERT_TRUE(iter.Init());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakLine) {
string16 nl(UTF8ToUTF16("\n"));
string16 str(UTF8ToUTF16("\nfoo bar!\n\npouet boom"));
BreakIterator iter(str, BreakIterator::BREAK_NEWLINE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(nl, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("foo bar!\n"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(nl, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("pouet boom"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakLineNL) {
string16 nl(UTF8ToUTF16("\n"));
string16 str(UTF8ToUTF16("\nfoo bar!\n\npouet boom\n"));
BreakIterator iter(str, BreakIterator::BREAK_NEWLINE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(nl, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("foo bar!\n"), iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(nl, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("pouet boom\n"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakLineWide16) {
// Two Greek words separated by newline.
const string16 str(WideToUTF16(
L"\x03a0\x03b1\x03b3\x03ba\x03cc\x03c3\x03bc\x03b9"
L"\x03bf\x03c2\x000a\x0399\x03c3\x03c4\x03cc\x03c2"));
const string16 line1(str.substr(0, 11));
const string16 line2(str.substr(11, 5));
BreakIterator iter(str, BreakIterator::BREAK_NEWLINE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(line1, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(line2, iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakLineWide32) {
// U+1D49C MATHEMATICAL SCRIPT CAPITAL A
const char very_wide_char[] = "\xF0\x9D\x92\x9C";
const string16 str(
UTF8ToUTF16(base::StringPrintf("%s\na", very_wide_char)));
const string16 very_wide_line(str.substr(0, 3));
BreakIterator iter(str, BreakIterator::BREAK_NEWLINE);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(very_wide_line, iter.GetString());
EXPECT_TRUE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_EQ(UTF8ToUTF16("a"), iter.GetString());
EXPECT_FALSE(iter.Advance());
EXPECT_FALSE(iter.IsWord());
EXPECT_FALSE(iter.Advance()); // Test unexpected advance after end.
EXPECT_FALSE(iter.IsWord());
}
TEST(BreakIteratorTest, BreakCharacter) {
static const wchar_t* kCharacters[] = {
// An English word consisting of four ASCII characters.
L"w", L"o", L"r", L"d", L" ",
// A Hindi word (which means "Hindi") consisting of three Devanagari
// characters.
L"\x0939\x093F", L"\x0928\x094D", L"\x0926\x0940", L" ",
// A Thai word (which means "feel") consisting of three Thai characters.
L"\x0E23\x0E39\x0E49", L"\x0E2A\x0E36", L"\x0E01", L" ",
};
std::vector<string16> characters;
string16 text;
for (size_t i = 0; i < arraysize(kCharacters); ++i) {
characters.push_back(WideToUTF16(kCharacters[i]));
text.append(characters.back());
}
BreakIterator iter(text, BreakIterator::BREAK_CHARACTER);
ASSERT_TRUE(iter.Init());
for (size_t i = 0; i < arraysize(kCharacters); ++i) {
EXPECT_TRUE(iter.Advance());
EXPECT_EQ(characters[i], iter.GetString());
}
}
// Test for https://code.google.com/p/chromium/issues/detail?id=411213
// We should be able to get valid substrings with GetString() function
// after setting new content by calling SetText().
TEST(BreakIteratorTest, GetStringAfterSetText) {
const string16 initial_string(ASCIIToUTF16("str"));
BreakIterator iter(initial_string, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
const string16 long_string(ASCIIToUTF16("another,string"));
EXPECT_TRUE(iter.SetText(long_string.c_str(), long_string.size()));
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.Advance()); // Advance to ',' in |long_string|
// Check that the current position is out of bounds of the |initial_string|.
EXPECT_LT(initial_string.size(), iter.pos());
// Check that we can get a valid substring of |long_string|.
EXPECT_EQ(ASCIIToUTF16(","), iter.GetString());
}
TEST(BreakIteratorTest, GetStringPiece) {
const string16 initial_string(ASCIIToUTF16("some string"));
BreakIterator iter(initial_string, BreakIterator::BREAK_WORD);
ASSERT_TRUE(iter.Init());
EXPECT_TRUE(iter.Advance());
EXPECT_EQ(iter.GetString(), iter.GetStringPiece().as_string());
EXPECT_EQ(StringPiece16(ASCIIToUTF16("some")), iter.GetStringPiece());
EXPECT_TRUE(iter.Advance());
EXPECT_TRUE(iter.Advance());
EXPECT_EQ(iter.GetString(), iter.GetStringPiece().as_string());
EXPECT_EQ(StringPiece16(ASCIIToUTF16("string")), iter.GetStringPiece());
}
} // namespace i18n
} // namespace base
|
