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
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html lang="en">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>LCOV - lcov.info - /usr/include/xapian/unicode.h</title>
<link rel="stylesheet" type="text/css" href="../../../gcov.css">
</head>
<body>
<table width="100%" border=0 cellspacing=0 cellpadding=0>
<tr><td class="title">LTP GCOV extension - code coverage report</td></tr>
<tr><td class="ruler"><img src="../../../glass.png" width=3 height=3 alt=""></td></tr>
<tr>
<td width="100%">
<table cellpadding=1 border=0 width="100%">
<tr>
<td class="headerItem" width="20%">Current view:</td>
<td class="headerValue" width="80%" colspan=4><a href="../../../index.html">directory</a> - <a href="index.html">usr/include/xapian</a> - unicode.h</td>
</tr>
<tr>
<td class="headerItem" width="20%">Test:</td>
<td class="headerValue" width="80%" colspan=4>lcov.info</td>
</tr>
<tr>
<td class="headerItem" width="20%">Date:</td>
<td class="headerValue" width="20%">2008-08-14</td>
<td width="20%"></td>
<td class="headerItem" width="20%">Instrumented lines:</td>
<td class="headerValue" width="20%">8</td>
</tr>
<tr>
<td class="headerItem" width="20%">Code covered:</td>
<td class="headerValue" width="20%">87.5 %</td>
<td width="20%"></td>
<td class="headerItem" width="20%">Executed lines:</td>
<td class="headerValue" width="20%">7</td>
</tr>
</table>
</td>
</tr>
<tr><td class="ruler"><img src="../../../glass.png" width=3 height=3 alt=""></td></tr>
</table>
<table cellpadding=0 cellspacing=0 border=0>
<tr>
<td><br></td>
</tr>
<tr>
<td><pre class="source">
<span class="lineNum"> 1 </span> : /** @file unicode.h
<span class="lineNum"> 2 </span> : * @brief Unicode and UTF-8 related classes and functions.
<span class="lineNum"> 3 </span> : */
<span class="lineNum"> 4 </span> : /* Copyright (C) 2006,2007,2008 Olly Betts
<span class="lineNum"> 5 </span> : *
<span class="lineNum"> 6 </span> : * This program is free software; you can redistribute it and/or modify
<span class="lineNum"> 7 </span> : * it under the terms of the GNU General Public License as published by
<span class="lineNum"> 8 </span> : * the Free Software Foundation; either version 2 of the License, or
<span class="lineNum"> 9 </span> : * (at your option) any later version.
<span class="lineNum"> 10 </span> : *
<span class="lineNum"> 11 </span> : * This program is distributed in the hope that it will be useful,
<span class="lineNum"> 12 </span> : * but WITHOUT ANY WARRANTY; without even the implied warranty of
<span class="lineNum"> 13 </span> : * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
<span class="lineNum"> 14 </span> : * GNU General Public License for more details.
<span class="lineNum"> 15 </span> : *
<span class="lineNum"> 16 </span> : * You should have received a copy of the GNU General Public License
<span class="lineNum"> 17 </span> : * along with this program; if not, write to the Free Software
<span class="lineNum"> 18 </span> : * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
<span class="lineNum"> 19 </span> : */
<span class="lineNum"> 20 </span> :
<span class="lineNum"> 21 </span> : #ifndef XAPIAN_INCLUDED_UNICODE_H
<span class="lineNum"> 22 </span> : #define XAPIAN_INCLUDED_UNICODE_H
<span class="lineNum"> 23 </span> :
<span class="lineNum"> 24 </span> : #include <xapian/visibility.h>
<span class="lineNum"> 25 </span> :
<span class="lineNum"> 26 </span> : #include <string>
<span class="lineNum"> 27 </span> :
<span class="lineNum"> 28 </span> : namespace Xapian {
<span class="lineNum"> 29 </span> :
<span class="lineNum"> 30 </span> : /** An iterator which returns unicode character values from a UTF-8 encoded
<span class="lineNum"> 31 </span> : * string.
<span class="lineNum"> 32 </span> : */
<span class="lineNum"> 33 </span> : class XAPIAN_VISIBILITY_DEFAULT Utf8Iterator {
<span class="lineNum"> 34 </span> : const unsigned char *p;
<span class="lineNum"> 35 </span> : const unsigned char *end;
<span class="lineNum"> 36 </span> : mutable unsigned seqlen;
<span class="lineNum"> 37 </span> :
<span class="lineNum"> 38 </span> : void calculate_sequence_length() const;
<span class="lineNum"> 39 </span> :
<span class="lineNum"> 40 </span> : unsigned get_char() const;
<span class="lineNum"> 41 </span> :
<span class="lineNum"> 42 </span> : Utf8Iterator(const unsigned char *p_, const unsigned char *end_, unsigned seqlen_)
<span class="lineNum"> 43 </span> : : p(p_), end(end_), seqlen(seqlen_) { }
<span class="lineNum"> 44 </span> :
<span class="lineNum"> 45 </span> : public:
<span class="lineNum"> 46 </span> : /** Return the raw const char * pointer for the current position. */
<span class="lineNum"> 47 </span> : const char * raw() const {
<span class="lineNum"> 48 </span> : return reinterpret_cast<const char *>(p ? p : end);
<span class="lineNum"> 49 </span> : }
<span class="lineNum"> 50 </span> :
<span class="lineNum"> 51 </span> : /** Return the number of bytes left in the iterator's buffer. */
<span class="lineNum"> 52 </span> : size_t left() const { return p ? end - p : 0; }
<span class="lineNum"> 53 </span> :
<span class="lineNum"> 54 </span> : /** Assign a new string to the iterator.
<span class="lineNum"> 55 </span> : *
<span class="lineNum"> 56 </span> : * The iterator will forget the string it was iterating through, and
<span class="lineNum"> 57 </span> : * return characters from the start of the new string when next called.
<span class="lineNum"> 58 </span> : * The string is not copied into the iterator, so it must remain valid
<span class="lineNum"> 59 </span> : * while the iteration is in progress.
<span class="lineNum"> 60 </span> : *
<span class="lineNum"> 61 </span> : * @param p A pointer to the start of the string to read.
<span class="lineNum"> 62 </span> : *
<span class="lineNum"> 63 </span> : * @param len The length of the string to read.
<span class="lineNum"> 64 </span> : */
<span class="lineNum"> 65 </span><span class="lineCov"> 5208 : void assign(const char *p_, size_t len) {</span>
<span class="lineNum"> 66 </span><span class="lineCov"> 5208 : if (len) {</span>
<span class="lineNum"> 67 </span><span class="lineCov"> 5208 : p = reinterpret_cast<const unsigned char*>(p_);</span>
<span class="lineNum"> 68 </span><span class="lineCov"> 5208 : end = p + len;</span>
<span class="lineNum"> 69 </span><span class="lineCov"> 5208 : seqlen = 0;</span>
<span class="lineNum"> 70 </span> : } else {
<span class="lineNum"> 71 </span><span class="lineNoCov"> 0 : p = NULL;</span>
<span class="lineNum"> 72 </span> : }
<span class="lineNum"> 73 </span><span class="lineCov"> 5208 : }</span>
<span class="lineNum"> 74 </span> :
<span class="lineNum"> 75 </span> : /** Assign a new string to the iterator.
<span class="lineNum"> 76 </span> : *
<span class="lineNum"> 77 </span> : * The iterator will forget the string it was iterating through, and
<span class="lineNum"> 78 </span> : * return characters from the start of the new string when next called.
<span class="lineNum"> 79 </span> : * The string is not copied into the iterator, so it must remain valid
<span class="lineNum"> 80 </span> : * while the iteration is in progress.
<span class="lineNum"> 81 </span> : *
<span class="lineNum"> 82 </span> : * @param s The string to read. Must not be modified while the iteration
<span class="lineNum"> 83 </span> : * is in progress.
<span class="lineNum"> 84 </span> : */
<span class="lineNum"> 85 </span> : void assign(const std::string &s) { assign(s.data(), s.size()); }
<span class="lineNum"> 86 </span> :
<span class="lineNum"> 87 </span> : /** Create an iterator given a pointer to a null terminated string.
<span class="lineNum"> 88 </span> : *
<span class="lineNum"> 89 </span> : * The iterator will return characters from the start of the string when
<span class="lineNum"> 90 </span> : * next called. The string is not copied into the iterator, so it must
<span class="lineNum"> 91 </span> : * remain valid while the iteration is in progress.
<span class="lineNum"> 92 </span> : *
<span class="lineNum"> 93 </span> : * @param p A pointer to the start of the null terminated string to read.
<span class="lineNum"> 94 </span> : */
<span class="lineNum"> 95 </span> : explicit Utf8Iterator(const char *p_);
<span class="lineNum"> 96 </span> :
<span class="lineNum"> 97 </span> : /** Create an iterator given a pointer and a length.
<span class="lineNum"> 98 </span> : *
<span class="lineNum"> 99 </span> : * The iterator will return characters from the start of the string when
<span class="lineNum"> 100 </span> : * next called. The string is not copied into the iterator, so it must
<span class="lineNum"> 101 </span> : * remain valid while the iteration is in progress.
<span class="lineNum"> 102 </span> : *
<span class="lineNum"> 103 </span> : * @param p A pointer to the start of the string to read.
<span class="lineNum"> 104 </span> : *
<span class="lineNum"> 105 </span> : * @param len The length of the string to read.
<span class="lineNum"> 106 </span> : */
<span class="lineNum"> 107 </span> : Utf8Iterator(const char *p_, size_t len) { assign(p_, len); }
<span class="lineNum"> 108 </span> :
<span class="lineNum"> 109 </span> : /** Create an iterator given a string.
<span class="lineNum"> 110 </span> : *
<span class="lineNum"> 111 </span> : * The iterator will return characters from the start of the string when
<span class="lineNum"> 112 </span> : * next called. The string is not copied into the iterator, so it must
<span class="lineNum"> 113 </span> : * remain valid while the iteration is in progress.
<span class="lineNum"> 114 </span> : *
<span class="lineNum"> 115 </span> : * @param s The string to read. Must not be modified while the iteration
<span class="lineNum"> 116 </span> : * is in progress.
<span class="lineNum"> 117 </span> : */
<span class="lineNum"> 118 </span><span class="lineCov"> 5208 : Utf8Iterator(const std::string &s) { assign(s.data(), s.size()); }</span>
<span class="lineNum"> 119 </span> :
<span class="lineNum"> 120 </span> : /** Create an iterator which is at the end of its iteration.
<span class="lineNum"> 121 </span> : *
<span class="lineNum"> 122 </span> : * This can be compared to another iterator to check if the other iterator
<span class="lineNum"> 123 </span> : * has reached its end.
<span class="lineNum"> 124 </span> : */
<span class="lineNum"> 125 </span> : Utf8Iterator() : p(NULL), end(0), seqlen(0) { }
<span class="lineNum"> 126 </span> :
<span class="lineNum"> 127 </span> : /** Get the current unicode character value pointed to by the iterator.
<span class="lineNum"> 128 </span> : *
<span class="lineNum"> 129 </span> : * Returns unsigned(-1) if the iterator has reached the end of its buffer.
<span class="lineNum"> 130 </span> : */
<span class="lineNum"> 131 </span> : unsigned operator*() const;
<span class="lineNum"> 132 </span> :
<span class="lineNum"> 133 </span> : /** Move forward to the next unicode character.
<span class="lineNum"> 134 </span> : *
<span class="lineNum"> 135 </span> : * @return An iterator pointing to the position before the move.
<span class="lineNum"> 136 </span> : */
<span class="lineNum"> 137 </span> : Utf8Iterator operator++(int) {
<span class="lineNum"> 138 </span> : // If we've not calculated seqlen yet, do so.
<span class="lineNum"> 139 </span> : if (seqlen == 0) calculate_sequence_length();
<span class="lineNum"> 140 </span> : const unsigned char *old_p = p;
<span class="lineNum"> 141 </span> : unsigned old_seqlen = seqlen;
<span class="lineNum"> 142 </span> : p += seqlen;
<span class="lineNum"> 143 </span> : if (p == end) p = NULL;
<span class="lineNum"> 144 </span> : seqlen = 0;
<span class="lineNum"> 145 </span> : return Utf8Iterator(old_p, end, old_seqlen);
<span class="lineNum"> 146 </span> : }
<span class="lineNum"> 147 </span> :
<span class="lineNum"> 148 </span> : /** Move forward to the next unicode character.
<span class="lineNum"> 149 </span> : *
<span class="lineNum"> 150 </span> : * @return A reference to this object.
<span class="lineNum"> 151 </span> : */
<span class="lineNum"> 152 </span> : Utf8Iterator & operator++() {
<span class="lineNum"> 153 </span> : if (seqlen == 0) calculate_sequence_length();
<span class="lineNum"> 154 </span> : p += seqlen;
<span class="lineNum"> 155 </span> : if (p == end) p = NULL;
<span class="lineNum"> 156 </span> : seqlen = 0;
<span class="lineNum"> 157 </span> : return *this;
<span class="lineNum"> 158 </span> : }
<span class="lineNum"> 159 </span> :
<span class="lineNum"> 160 </span> : /** Test two Utf8Iterators for equality.
<span class="lineNum"> 161 </span> : *
<span class="lineNum"> 162 </span> : * @return true iff the iterators point to the same position.
<span class="lineNum"> 163 </span> : */
<span class="lineNum"> 164 </span> : bool operator==(const Utf8Iterator &other) const { return p == other.p; }
<span class="lineNum"> 165 </span> :
<span class="lineNum"> 166 </span> : /** Test two Utf8Iterators for inequality.
<span class="lineNum"> 167 </span> : *
<span class="lineNum"> 168 </span> : * @return true iff the iterators do not point to the same position.
<span class="lineNum"> 169 </span> : */
<span class="lineNum"> 170 </span> : bool operator!=(const Utf8Iterator &other) const { return p != other.p; }
<span class="lineNum"> 171 </span> :
<span class="lineNum"> 172 </span> : /// We implement the semantics of an STL input_iterator.
<span class="lineNum"> 173 </span> : //@{
<span class="lineNum"> 174 </span> : typedef std::input_iterator_tag iterator_category;
<span class="lineNum"> 175 </span> : typedef unsigned value_type;
<span class="lineNum"> 176 </span> : typedef size_t difference_type;
<span class="lineNum"> 177 </span> : typedef const unsigned * pointer;
<span class="lineNum"> 178 </span> : typedef const unsigned & reference;
<span class="lineNum"> 179 </span> : //@}
<span class="lineNum"> 180 </span> : };
<span class="lineNum"> 181 </span> :
<span class="lineNum"> 182 </span> : namespace Unicode {
<span class="lineNum"> 183 </span> :
<span class="lineNum"> 184 </span> : /** Each unicode character is in one of these categories. */
<span class="lineNum"> 185 </span> : typedef enum {
<span class="lineNum"> 186 </span> : UNASSIGNED,
<span class="lineNum"> 187 </span> : UPPERCASE_LETTER,
<span class="lineNum"> 188 </span> : LOWERCASE_LETTER,
<span class="lineNum"> 189 </span> : TITLECASE_LETTER,
<span class="lineNum"> 190 </span> : MODIFIER_LETTER,
<span class="lineNum"> 191 </span> : OTHER_LETTER,
<span class="lineNum"> 192 </span> : NON_SPACING_MARK,
<span class="lineNum"> 193 </span> : ENCLOSING_MARK,
<span class="lineNum"> 194 </span> : COMBINING_SPACING_MARK,
<span class="lineNum"> 195 </span> : DECIMAL_DIGIT_NUMBER,
<span class="lineNum"> 196 </span> : LETTER_NUMBER,
<span class="lineNum"> 197 </span> : OTHER_NUMBER,
<span class="lineNum"> 198 </span> : SPACE_SEPARATOR,
<span class="lineNum"> 199 </span> : LINE_SEPARATOR,
<span class="lineNum"> 200 </span> : PARAGRAPH_SEPARATOR,
<span class="lineNum"> 201 </span> : CONTROL,
<span class="lineNum"> 202 </span> : FORMAT,
<span class="lineNum"> 203 </span> : PRIVATE_USE,
<span class="lineNum"> 204 </span> : SURROGATE,
<span class="lineNum"> 205 </span> : CONNECTOR_PUNCTUATION,
<span class="lineNum"> 206 </span> : DASH_PUNCTUATION,
<span class="lineNum"> 207 </span> : OPEN_PUNCTUATION,
<span class="lineNum"> 208 </span> : CLOSE_PUNCTUATION,
<span class="lineNum"> 209 </span> : INITIAL_QUOTE_PUNCTUATION,
<span class="lineNum"> 210 </span> : FINAL_QUOTE_PUNCTUATION,
<span class="lineNum"> 211 </span> : OTHER_PUNCTUATION,
<span class="lineNum"> 212 </span> : MATH_SYMBOL,
<span class="lineNum"> 213 </span> : CURRENCY_SYMBOL,
<span class="lineNum"> 214 </span> : MODIFIER_SYMBOL,
<span class="lineNum"> 215 </span> : OTHER_SYMBOL
<span class="lineNum"> 216 </span> : } category;
<span class="lineNum"> 217 </span> :
<span class="lineNum"> 218 </span> : namespace Internal {
<span class="lineNum"> 219 </span> : /** @internal Extract the information about a character from the Unicode
<span class="lineNum"> 220 </span> : * character tables.
<span class="lineNum"> 221 </span> : *
<span class="lineNum"> 222 </span> : * ch must be a valid Unicode character value (i.e. < 0x110000)
<span class="lineNum"> 223 </span> : */
<span class="lineNum"> 224 </span> : XAPIAN_VISIBILITY_DEFAULT
<span class="lineNum"> 225 </span> : int get_character_info(unsigned ch);
<span class="lineNum"> 226 </span> :
<span class="lineNum"> 227 </span> : /** @internal Extract how to convert the case of a unicode character from
<span class="lineNum"> 228 </span> : * its info.
<span class="lineNum"> 229 </span> : */
<span class="lineNum"> 230 </span> : inline int get_case_type(int info) { return ((info & 0xe0) >> 5); }
<span class="lineNum"> 231 </span> :
<span class="lineNum"> 232 </span> : /// @internal Extract the category of a unicode character from its info.
<span class="lineNum"> 233 </span> : inline category get_category(int info) { return static_cast<category>(info & 0x1f); }
<span class="lineNum"> 234 </span> :
<span class="lineNum"> 235 </span> : /** @internal Extract the delta to use for case conversion of a character
<span class="lineNum"> 236 </span> : * from its info.
<span class="lineNum"> 237 </span> : */
<span class="lineNum"> 238 </span> : inline int get_delta(int info) {
<span class="lineNum"> 239 </span> : /* It's implementation defined if sign extension happens on right shift
<span class="lineNum"> 240 </span> : * of a signed int, hence the conditional (hopefully the compiler will
<span class="lineNum"> 241 </span> : * spot this and optimise it to a sign-extending shift on architectures
<span class="lineNum"> 242 </span> : * with a suitable instruction).
<span class="lineNum"> 243 </span> : */
<span class="lineNum"> 244 </span> : return (info >= 0) ? (info >> 15) : (~(~info >> 15));
<span class="lineNum"> 245 </span> : }
<span class="lineNum"> 246 </span> : }
<span class="lineNum"> 247 </span> :
<span class="lineNum"> 248 </span> : /** Convert a single non-ASCII unicode character to UTF-8.
<span class="lineNum"> 249 </span> : *
<span class="lineNum"> 250 </span> : * This is intended mainly as a helper method for to_utf8().
<span class="lineNum"> 251 </span> : *
<span class="lineNum"> 252 </span> : * The character @a ch (which must be > 128) is written to the buffer @a buf
<span class="lineNum"> 253 </span> : * and the length of the resultant UTF-8 character is returned.
<span class="lineNum"> 254 </span> : *
<span class="lineNum"> 255 </span> : * NB buf must have space for (at least) 4 bytes.
<span class="lineNum"> 256 </span> : */
<span class="lineNum"> 257 </span> : XAPIAN_VISIBILITY_DEFAULT
<span class="lineNum"> 258 </span> : unsigned nonascii_to_utf8(unsigned ch, char * buf);
<span class="lineNum"> 259 </span> :
<span class="lineNum"> 260 </span> : /** Convert a single unicode character to UTF-8.
<span class="lineNum"> 261 </span> : *
<span class="lineNum"> 262 </span> : * The character @a ch is written to the buffer @a buf and the length of the
<span class="lineNum"> 263 </span> : * resultant UTF-8 character is returned.
<span class="lineNum"> 264 </span> : *
<span class="lineNum"> 265 </span> : * NB buf must have space for (at least) 4 bytes.
<span class="lineNum"> 266 </span> : */
<span class="lineNum"> 267 </span> : inline unsigned to_utf8(unsigned ch, char *buf) {
<span class="lineNum"> 268 </span> : if (ch < 128) {
<span class="lineNum"> 269 </span> : *buf = static_cast<unsigned char>(ch);
<span class="lineNum"> 270 </span> : return 1;
<span class="lineNum"> 271 </span> : }
<span class="lineNum"> 272 </span> : return Xapian::Unicode::nonascii_to_utf8(ch, buf);
<span class="lineNum"> 273 </span> : }
<span class="lineNum"> 274 </span> :
<span class="lineNum"> 275 </span> : /** Append the UTF-8 representation of a single unicode character to a
<span class="lineNum"> 276 </span> : * std::string.
<span class="lineNum"> 277 </span> : */
<span class="lineNum"> 278 </span> : inline void append_utf8(std::string &s, unsigned ch) {
<span class="lineNum"> 279 </span> : char buf[4];
<span class="lineNum"> 280 </span> : s.append(buf, to_utf8(ch, buf));
<span class="lineNum"> 281 </span> : }
<span class="lineNum"> 282 </span> :
<span class="lineNum"> 283 </span> : /// Return the category which a given unicode character falls into.
<span class="lineNum"> 284 </span> : inline category get_category(unsigned ch) {
<span class="lineNum"> 285 </span> : // Categorise non-Unicode values as UNASSIGNED.
<span class="lineNum"> 286 </span> : if (ch >= 0x110000) return Xapian::Unicode::UNASSIGNED;
<span class="lineNum"> 287 </span> : return Internal::get_category(Internal::get_character_info(ch));
<span class="lineNum"> 288 </span> : }
<span class="lineNum"> 289 </span> :
<span class="lineNum"> 290 </span> : /// Test is a given unicode character is a letter or number.
<span class="lineNum"> 291 </span> : inline bool is_wordchar(unsigned ch) {
<span class="lineNum"> 292 </span> : const unsigned int WORDCHAR_MASK =
<span class="lineNum"> 293 </span> : (1 << Xapian::Unicode::UPPERCASE_LETTER) |
<span class="lineNum"> 294 </span> : (1 << Xapian::Unicode::LOWERCASE_LETTER) |
<span class="lineNum"> 295 </span> : (1 << Xapian::Unicode::TITLECASE_LETTER) |
<span class="lineNum"> 296 </span> : (1 << Xapian::Unicode::MODIFIER_LETTER) |
<span class="lineNum"> 297 </span> : (1 << Xapian::Unicode::OTHER_LETTER) |
<span class="lineNum"> 298 </span> : (1 << Xapian::Unicode::DECIMAL_DIGIT_NUMBER) |
<span class="lineNum"> 299 </span> : (1 << Xapian::Unicode::LETTER_NUMBER) |
<span class="lineNum"> 300 </span> : (1 << Xapian::Unicode::OTHER_NUMBER) |
<span class="lineNum"> 301 </span> : (1 << Xapian::Unicode::CONNECTOR_PUNCTUATION);
<span class="lineNum"> 302 </span> : return ((WORDCHAR_MASK >> get_category(ch)) & 1);
<span class="lineNum"> 303 </span> : }
<span class="lineNum"> 304 </span> :
<span class="lineNum"> 305 </span> : /// Test is a given unicode character is a whitespace character.
<span class="lineNum"> 306 </span> : inline bool is_whitespace(unsigned ch) {
<span class="lineNum"> 307 </span> : const unsigned int WHITESPACE_MASK =
<span class="lineNum"> 308 </span> : (1 << Xapian::Unicode::CONTROL) | // For TAB, CR, LF, FF.
<span class="lineNum"> 309 </span> : (1 << Xapian::Unicode::SPACE_SEPARATOR) |
<span class="lineNum"> 310 </span> : (1 << Xapian::Unicode::LINE_SEPARATOR) |
<span class="lineNum"> 311 </span> : (1 << Xapian::Unicode::PARAGRAPH_SEPARATOR);
<span class="lineNum"> 312 </span> : return ((WHITESPACE_MASK >> get_category(ch)) & 1);
<span class="lineNum"> 313 </span> : }
<span class="lineNum"> 314 </span> :
<span class="lineNum"> 315 </span> : /// Test is a given unicode character is a currency symbol.
<span class="lineNum"> 316 </span> : inline bool is_currency(unsigned ch) {
<span class="lineNum"> 317 </span> : return (get_category(ch) == Xapian::Unicode::CURRENCY_SYMBOL);
<span class="lineNum"> 318 </span> : }
<span class="lineNum"> 319 </span> :
<span class="lineNum"> 320 </span> : /// Convert a unicode character to lowercase.
<span class="lineNum"> 321 </span> : inline unsigned tolower(unsigned ch) {
<span class="lineNum"> 322 </span> : int info;
<span class="lineNum"> 323 </span> : // Leave non-Unicode values unchanged.
<span class="lineNum"> 324 </span> : if (ch >= 0x110000 || !(Internal::get_case_type((info = Xapian::Unicode::Internal::get_character_info(ch))) & 2))
<span class="lineNum"> 325 </span> : return ch;
<span class="lineNum"> 326 </span> : return ch + Internal::get_delta(info);
<span class="lineNum"> 327 </span> : }
<span class="lineNum"> 328 </span> :
<span class="lineNum"> 329 </span> : /// Convert a unicode character to uppercase.
<span class="lineNum"> 330 </span> : inline unsigned toupper(unsigned ch) {
<span class="lineNum"> 331 </span> : int info;
<span class="lineNum"> 332 </span> : // Leave non-Unicode values unchanged.
<span class="lineNum"> 333 </span> : if (ch >= 0x110000 || !(Internal::get_case_type((info = Xapian::Unicode::Internal::get_character_info(ch))) & 4))
<span class="lineNum"> 334 </span> : return ch;
<span class="lineNum"> 335 </span> : return ch - Internal::get_delta(info);
<span class="lineNum"> 336 </span> : }
<span class="lineNum"> 337 </span> :
<span class="lineNum"> 338 </span> : /// Convert a UTF-8 std::string to lowercase.
<span class="lineNum"> 339 </span> : inline std::string
<span class="lineNum"> 340 </span> : tolower(const std::string &term)
<span class="lineNum"> 341 </span> : {
<span class="lineNum"> 342 </span> : std::string result;
<span class="lineNum"> 343 </span> : result.reserve(term.size());
<span class="lineNum"> 344 </span> : for (Utf8Iterator i(term); i != Utf8Iterator(); ++i) {
<span class="lineNum"> 345 </span> : append_utf8(result, tolower(*i));
<span class="lineNum"> 346 </span> : }
<span class="lineNum"> 347 </span> : return result;
<span class="lineNum"> 348 </span> : }
<span class="lineNum"> 349 </span> :
<span class="lineNum"> 350 </span> : /// Convert a UTF-8 std::string to uppercase.
<span class="lineNum"> 351 </span> : inline std::string
<span class="lineNum"> 352 </span> : toupper(const std::string &term)
<span class="lineNum"> 353 </span> : {
<span class="lineNum"> 354 </span> : std::string result;
<span class="lineNum"> 355 </span> : result.reserve(term.size());
<span class="lineNum"> 356 </span> : for (Utf8Iterator i(term); i != Utf8Iterator(); ++i) {
<span class="lineNum"> 357 </span> : append_utf8(result, toupper(*i));
<span class="lineNum"> 358 </span> : }
<span class="lineNum"> 359 </span> : return result;
<span class="lineNum"> 360 </span> : }
<span class="lineNum"> 361 </span> :
<span class="lineNum"> 362 </span> : }
<span class="lineNum"> 363 </span> :
<span class="lineNum"> 364 </span> : }
<span class="lineNum"> 365 </span> :
<span class="lineNum"> 366 </span> : #endif // XAPIAN_INCLUDED_UNICODE_H
</pre>
</td>
</tr>
</table>
<br>
<table width="100%" border=0 cellspacing=0 cellpadding=0>
<tr><td class="ruler"><img src="../../../glass.png" width=3 height=3 alt=""></td></tr>
<tr><td class="versionInfo">Generated by: <a href="http://ltp.sourceforge.net/coverage/lcov.php" target="_parent">LTP GCOV extension version 1.6</a></td></tr>
</table>
<br>
</body>
</html>
|
