File: TextBreakIterator.h

package info (click to toggle)
chromium-browser 57.0.2987.98-1~deb8u1
  • links: PTS, VCS
  • area: main
  • in suites: jessie
  • size: 2,637,852 kB
  • ctags: 2,544,394
  • sloc: cpp: 12,815,961; ansic: 3,676,222; python: 1,147,112; asm: 526,608; java: 523,212; xml: 286,794; perl: 92,654; sh: 86,408; objc: 73,271; makefile: 27,698; cs: 18,487; yacc: 13,031; tcl: 12,957; pascal: 4,875; ml: 4,716; lex: 3,904; sql: 3,862; ruby: 1,982; lisp: 1,508; php: 1,368; exp: 404; awk: 325; csh: 117; jsp: 39; sed: 37
file content (282 lines) | stat: -rw-r--r-- 9,735 bytes parent folder | download
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
/*
 * Copyright (C) 2006 Lars Knoll <lars@trolltech.com>
 * Copyright (C) 2007, 2011, 2012 Apple Inc. All rights reserved.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Library General Public License for more details.
 *
 * You should have received a copy of the GNU Library General Public License
 * along with this library; see the file COPYING.LIB.  If not, write to
 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
 * Boston, MA 02110-1301, USA.
 *
 */

#ifndef TextBreakIterator_h
#define TextBreakIterator_h

#include "platform/PlatformExport.h"
#include "wtf/text/AtomicString.h"
#include "wtf/text/Unicode.h"

#include <unicode/brkiter.h>

namespace blink {

typedef icu::BreakIterator TextBreakIterator;

// Note: The returned iterator is good only until you get another iterator, with
// the exception of acquireLineBreakIterator.

// This is similar to character break iterator in most cases, but is subject to
// platform UI conventions. One notable example where this can be different
// from character break iterator is Thai prepend characters, see bug 24342.
// Use this for insertion point and selection manipulations.
PLATFORM_EXPORT TextBreakIterator* cursorMovementIterator(const UChar*,
                                                          int length);

PLATFORM_EXPORT TextBreakIterator* wordBreakIterator(const String&,
                                                     int start,
                                                     int length);
PLATFORM_EXPORT TextBreakIterator* wordBreakIterator(const UChar*, int length);
PLATFORM_EXPORT TextBreakIterator* acquireLineBreakIterator(
    const LChar*,
    int length,
    const AtomicString& locale,
    const UChar* priorContext,
    unsigned priorContextLength);
PLATFORM_EXPORT TextBreakIterator* acquireLineBreakIterator(
    const UChar*,
    int length,
    const AtomicString& locale,
    const UChar* priorContext,
    unsigned priorContextLength);
PLATFORM_EXPORT void releaseLineBreakIterator(TextBreakIterator*);
PLATFORM_EXPORT TextBreakIterator* sentenceBreakIterator(const UChar*,
                                                         int length);

PLATFORM_EXPORT bool isWordTextBreak(TextBreakIterator*);

const int TextBreakDone = -1;

enum class LineBreakType {
  Normal,
  BreakAll,  // word-break:break-all allows breaks between letters/numbers
  KeepAll,   // word-break:keep-all doesn't allow breaks between all kind of
             // letters/numbers except some south east asians'.
};

class PLATFORM_EXPORT LazyLineBreakIterator final {
  STACK_ALLOCATED();

 public:
  LazyLineBreakIterator()
      : m_iterator(0), m_cachedPriorContext(0), m_cachedPriorContextLength(0) {
    resetPriorContext();
  }

  LazyLineBreakIterator(String string,
                        const AtomicString& locale = AtomicString())
      : m_string(string),
        m_locale(locale),
        m_iterator(0),
        m_cachedPriorContext(0),
        m_cachedPriorContextLength(0) {
    resetPriorContext();
  }

  ~LazyLineBreakIterator() {
    if (m_iterator)
      releaseLineBreakIterator(m_iterator);
  }

  String getString() const { return m_string; }

  UChar lastCharacter() const {
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    return m_priorContext[1];
  }

  UChar secondToLastCharacter() const {
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    return m_priorContext[0];
  }

  void setPriorContext(UChar last, UChar secondToLast) {
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    m_priorContext[0] = secondToLast;
    m_priorContext[1] = last;
  }

  void updatePriorContext(UChar last) {
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    m_priorContext[0] = m_priorContext[1];
    m_priorContext[1] = last;
  }

  void resetPriorContext() {
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    m_priorContext[0] = 0;
    m_priorContext[1] = 0;
  }

  unsigned priorContextLength() const {
    unsigned priorContextLength = 0;
    static_assert(WTF_ARRAY_LENGTH(m_priorContext) == 2,
                  "TextBreakIterator has unexpected prior context length");
    if (m_priorContext[1]) {
      ++priorContextLength;
      if (m_priorContext[0])
        ++priorContextLength;
    }
    return priorContextLength;
  }

  // Obtain text break iterator, possibly previously cached, where this iterator
  // is (or has been) initialized to use the previously stored string as the
  // primary breaking context and using previously stored prior context if
  // non-empty.
  TextBreakIterator* get(unsigned priorContextLength) {
    ASSERT(priorContextLength <= priorContextCapacity);
    const UChar* priorContext =
        priorContextLength
            ? &m_priorContext[priorContextCapacity - priorContextLength]
            : 0;
    if (!m_iterator) {
      if (m_string.is8Bit())
        m_iterator = acquireLineBreakIterator(m_string.characters8(),
                                              m_string.length(), m_locale,
                                              priorContext, priorContextLength);
      else
        m_iterator = acquireLineBreakIterator(m_string.characters16(),
                                              m_string.length(), m_locale,
                                              priorContext, priorContextLength);
      m_cachedPriorContext = priorContext;
      m_cachedPriorContextLength = priorContextLength;
    } else if (priorContext != m_cachedPriorContext ||
               priorContextLength != m_cachedPriorContextLength) {
      this->resetStringAndReleaseIterator(m_string, m_locale);
      return this->get(priorContextLength);
    }
    return m_iterator;
  }

  void resetStringAndReleaseIterator(String string,
                                     const AtomicString& locale) {
    if (m_iterator)
      releaseLineBreakIterator(m_iterator);

    m_string = string;
    m_locale = locale;
    m_iterator = 0;
    m_cachedPriorContext = 0;
    m_cachedPriorContextLength = 0;
  }

  inline bool isBreakable(int pos,
                          int& nextBreakable,
                          LineBreakType lineBreakType = LineBreakType::Normal) {
    if (pos > nextBreakable) {
      switch (lineBreakType) {
        case LineBreakType::BreakAll:
          nextBreakable = nextBreakablePositionBreakAll(pos);
          break;
        case LineBreakType::KeepAll:
          nextBreakable = nextBreakablePositionKeepAll(pos);
          break;
        default:
          nextBreakable = nextBreakablePositionIgnoringNBSP(pos);
      }
    }
    return pos == nextBreakable;
  }

 private:
  int nextBreakablePositionIgnoringNBSP(int pos);
  int nextBreakablePositionBreakAll(int pos);
  int nextBreakablePositionKeepAll(int pos);

  static const unsigned priorContextCapacity = 2;
  String m_string;
  AtomicString m_locale;
  TextBreakIterator* m_iterator;
  UChar m_priorContext[priorContextCapacity];
  const UChar* m_cachedPriorContext;
  unsigned m_cachedPriorContextLength;
};

// Iterates over "extended grapheme clusters", as defined in UAX #29.
// Note that platform implementations may be less sophisticated - e.g. ICU prior
// to version 4.0 only supports "legacy grapheme clusters".  Use this for
// general text processing, e.g. string truncation.

class PLATFORM_EXPORT NonSharedCharacterBreakIterator final {
  STACK_ALLOCATED();
  WTF_MAKE_NONCOPYABLE(NonSharedCharacterBreakIterator);

 public:
  explicit NonSharedCharacterBreakIterator(const String&);
  NonSharedCharacterBreakIterator(const UChar*, unsigned length);
  ~NonSharedCharacterBreakIterator();

  int next();
  int current();

  bool isBreak(int offset) const;
  int preceding(int offset) const;
  int following(int offset) const;

  bool operator!() const { return !m_is8Bit && !m_iterator; }

 private:
  void createIteratorForBuffer(const UChar*, unsigned length);

  unsigned clusterLengthStartingAt(unsigned offset) const {
    ASSERT(m_is8Bit);
    // The only Latin-1 Extended Grapheme Cluster is CR LF
    return isCRBeforeLF(offset) ? 2 : 1;
  }

  bool isCRBeforeLF(unsigned offset) const {
    ASSERT(m_is8Bit);
    return m_charaters8[offset] == '\r' && offset + 1 < m_length &&
           m_charaters8[offset + 1] == '\n';
  }

  bool isLFAfterCR(unsigned offset) const {
    ASSERT(m_is8Bit);
    return m_charaters8[offset] == '\n' && offset >= 1 &&
           m_charaters8[offset - 1] == '\r';
  }

  bool m_is8Bit;

  // For 8 bit strings, we implement the iterator ourselves.
  const LChar* m_charaters8;
  unsigned m_offset;
  unsigned m_length;

  // For 16 bit strings, we use a TextBreakIterator.
  TextBreakIterator* m_iterator;
};

// Counts the number of grapheme clusters. A surrogate pair or a sequence
// of a non-combining character and following combining characters is
// counted as 1 grapheme cluster.
PLATFORM_EXPORT unsigned numGraphemeClusters(const String&);

}  // namespace blink

#endif