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
434
435
436
437
438
439
440
441
442
443
444
445
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2001-2008,2010 IBM and others. All rights reserved.
**********************************************************************
* Date Name Description
* 03/22/2000 helena Creation.
**********************************************************************
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_BREAK_ITERATION
#include "unicode/brkiter.h"
#include "unicode/schriter.h"
#include "unicode/search.h"
#include "usrchimp.h"
#include "cmemory.h"
// public constructors and destructors -----------------------------------
U_NAMESPACE_BEGIN
SearchIterator::SearchIterator(const SearchIterator &other)
: UObject(other)
{
m_breakiterator_ = other.m_breakiterator_;
m_text_ = other.m_text_;
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
m_search_->breakIter = other.m_search_->breakIter;
m_search_->isCanonicalMatch = other.m_search_->isCanonicalMatch;
m_search_->isOverlap = other.m_search_->isOverlap;
m_search_->elementComparisonType = other.m_search_->elementComparisonType;
m_search_->matchedIndex = other.m_search_->matchedIndex;
m_search_->matchedLength = other.m_search_->matchedLength;
m_search_->text = other.m_search_->text;
m_search_->textLength = other.m_search_->textLength;
}
SearchIterator::~SearchIterator()
{
if (m_search_ != nullptr) {
uprv_free(m_search_);
}
}
// public get and set methods ----------------------------------------
void SearchIterator::setAttribute(USearchAttribute attribute,
USearchAttributeValue value,
UErrorCode &status)
{
if (U_SUCCESS(status)) {
switch (attribute)
{
case USEARCH_OVERLAP :
m_search_->isOverlap = (value == USEARCH_ON ? true : false);
break;
case USEARCH_CANONICAL_MATCH :
m_search_->isCanonicalMatch = (value == USEARCH_ON ? true : false);
break;
case USEARCH_ELEMENT_COMPARISON :
if (value == USEARCH_PATTERN_BASE_WEIGHT_IS_WILDCARD || value == USEARCH_ANY_BASE_WEIGHT_IS_WILDCARD) {
m_search_->elementComparisonType = (int16_t)value;
} else {
m_search_->elementComparisonType = 0;
}
break;
default:
status = U_ILLEGAL_ARGUMENT_ERROR;
}
}
if (value == USEARCH_ATTRIBUTE_VALUE_COUNT) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
}
USearchAttributeValue SearchIterator::getAttribute(
USearchAttribute attribute) const
{
switch (attribute) {
case USEARCH_OVERLAP :
return (m_search_->isOverlap ? USEARCH_ON : USEARCH_OFF);
case USEARCH_CANONICAL_MATCH :
return (m_search_->isCanonicalMatch ? USEARCH_ON : USEARCH_OFF);
case USEARCH_ELEMENT_COMPARISON :
{
int16_t value = m_search_->elementComparisonType;
if (value == USEARCH_PATTERN_BASE_WEIGHT_IS_WILDCARD || value == USEARCH_ANY_BASE_WEIGHT_IS_WILDCARD) {
return (USearchAttributeValue)value;
} else {
return USEARCH_STANDARD_ELEMENT_COMPARISON;
}
}
default :
return USEARCH_DEFAULT;
}
}
int32_t SearchIterator::getMatchedStart() const
{
return m_search_->matchedIndex;
}
int32_t SearchIterator::getMatchedLength() const
{
return m_search_->matchedLength;
}
void SearchIterator::getMatchedText(UnicodeString &result) const
{
int32_t matchedindex = m_search_->matchedIndex;
int32_t matchedlength = m_search_->matchedLength;
if (matchedindex != USEARCH_DONE && matchedlength != 0) {
result.setTo(m_search_->text + matchedindex, matchedlength);
}
else {
result.remove();
}
}
void SearchIterator::setBreakIterator(BreakIterator *breakiter,
UErrorCode &status)
{
if (U_SUCCESS(status)) {
#if 0
m_search_->breakIter = nullptr;
// the c++ breakiterator may not make use of ubreakiterator.
// so we'll have to keep track of it ourselves.
#else
// Well, gee... the Constructors that take a BreakIterator
// all cast the BreakIterator to a UBreakIterator and
// pass it to the corresponding usearch_openFromXXX
// routine, so there's no reason not to do this.
//
// Besides, a UBreakIterator is a BreakIterator, so
// any subclass of BreakIterator should work fine here...
m_search_->breakIter = (UBreakIterator *) breakiter;
#endif
m_breakiterator_ = breakiter;
}
}
const BreakIterator * SearchIterator::getBreakIterator() const
{
return m_breakiterator_;
}
void SearchIterator::setText(const UnicodeString &text, UErrorCode &status)
{
if (U_SUCCESS(status)) {
if (text.length() == 0) {
status = U_ILLEGAL_ARGUMENT_ERROR;
}
else {
m_text_ = text;
m_search_->text = m_text_.getBuffer();
m_search_->textLength = m_text_.length();
}
}
}
void SearchIterator::setText(CharacterIterator &text, UErrorCode &status)
{
if (U_SUCCESS(status)) {
text.getText(m_text_);
setText(m_text_, status);
}
}
const UnicodeString & SearchIterator::getText() const
{
return m_text_;
}
// operator overloading ----------------------------------------------
bool SearchIterator::operator==(const SearchIterator &that) const
{
if (this == &that) {
return true;
}
return (m_breakiterator_ == that.m_breakiterator_ &&
m_search_->isCanonicalMatch == that.m_search_->isCanonicalMatch &&
m_search_->isOverlap == that.m_search_->isOverlap &&
m_search_->elementComparisonType == that.m_search_->elementComparisonType &&
m_search_->matchedIndex == that.m_search_->matchedIndex &&
m_search_->matchedLength == that.m_search_->matchedLength &&
m_search_->textLength == that.m_search_->textLength &&
getOffset() == that.getOffset() &&
(m_search_->textLength == 0 ||
(uprv_memcmp(m_search_->text, that.m_search_->text,
m_search_->textLength * sizeof(char16_t)) == 0)));
}
// public methods ----------------------------------------------------
int32_t SearchIterator::first(UErrorCode &status)
{
if (U_FAILURE(status)) {
return USEARCH_DONE;
}
setOffset(0, status);
return handleNext(0, status);
}
int32_t SearchIterator::following(int32_t position,
UErrorCode &status)
{
if (U_FAILURE(status)) {
return USEARCH_DONE;
}
setOffset(position, status);
return handleNext(position, status);
}
int32_t SearchIterator::last(UErrorCode &status)
{
if (U_FAILURE(status)) {
return USEARCH_DONE;
}
setOffset(m_search_->textLength, status);
return handlePrev(m_search_->textLength, status);
}
int32_t SearchIterator::preceding(int32_t position,
UErrorCode &status)
{
if (U_FAILURE(status)) {
return USEARCH_DONE;
}
setOffset(position, status);
return handlePrev(position, status);
}
int32_t SearchIterator::next(UErrorCode &status)
{
if (U_SUCCESS(status)) {
int32_t offset = getOffset();
int32_t matchindex = m_search_->matchedIndex;
int32_t matchlength = m_search_->matchedLength;
m_search_->reset = false;
if (m_search_->isForwardSearching) {
int32_t textlength = m_search_->textLength;
if (offset == textlength || matchindex == textlength ||
(matchindex != USEARCH_DONE &&
matchindex + matchlength >= textlength)) {
// not enough characters to match
setMatchNotFound();
return USEARCH_DONE;
}
}
else {
// switching direction.
// if matchedIndex == USEARCH_DONE, it means that either a
// setOffset has been called or that previous ran off the text
// string. the iterator would have been set to offset 0 if a
// match is not found.
m_search_->isForwardSearching = true;
if (m_search_->matchedIndex != USEARCH_DONE) {
// there's no need to set the collation element iterator
// the next call to next will set the offset.
return matchindex;
}
}
if (matchlength > 0) {
// if matchlength is 0 we are at the start of the iteration
if (m_search_->isOverlap) {
offset ++;
}
else {
offset += matchlength;
}
}
return handleNext(offset, status);
}
return USEARCH_DONE;
}
int32_t SearchIterator::previous(UErrorCode &status)
{
if (U_SUCCESS(status)) {
int32_t offset;
if (m_search_->reset) {
offset = m_search_->textLength;
m_search_->isForwardSearching = false;
m_search_->reset = false;
setOffset(offset, status);
}
else {
offset = getOffset();
}
int32_t matchindex = m_search_->matchedIndex;
if (m_search_->isForwardSearching) {
// switching direction.
// if matchedIndex == USEARCH_DONE, it means that either a
// setOffset has been called or that next ran off the text
// string. the iterator would have been set to offset textLength if
// a match is not found.
m_search_->isForwardSearching = false;
if (matchindex != USEARCH_DONE) {
return matchindex;
}
}
else {
if (offset == 0 || matchindex == 0) {
// not enough characters to match
setMatchNotFound();
return USEARCH_DONE;
}
}
if (matchindex != USEARCH_DONE) {
if (m_search_->isOverlap) {
matchindex += m_search_->matchedLength - 2;
}
return handlePrev(matchindex, status);
}
return handlePrev(offset, status);
}
return USEARCH_DONE;
}
void SearchIterator::reset()
{
UErrorCode status = U_ZERO_ERROR;
setMatchNotFound();
setOffset(0, status);
m_search_->isOverlap = false;
m_search_->isCanonicalMatch = false;
m_search_->elementComparisonType = 0;
m_search_->isForwardSearching = true;
m_search_->reset = true;
}
// protected constructors and destructors -----------------------------
SearchIterator::SearchIterator()
{
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
m_search_->breakIter = nullptr;
m_search_->isOverlap = false;
m_search_->isCanonicalMatch = false;
m_search_->elementComparisonType = 0;
m_search_->isForwardSearching = true;
m_search_->reset = true;
m_search_->matchedIndex = USEARCH_DONE;
m_search_->matchedLength = 0;
m_search_->text = nullptr;
m_search_->textLength = 0;
m_breakiterator_ = nullptr;
}
SearchIterator::SearchIterator(const UnicodeString &text,
BreakIterator *breakiter) :
m_breakiterator_(breakiter),
m_text_(text)
{
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
m_search_->breakIter = nullptr;
m_search_->isOverlap = false;
m_search_->isCanonicalMatch = false;
m_search_->elementComparisonType = 0;
m_search_->isForwardSearching = true;
m_search_->reset = true;
m_search_->matchedIndex = USEARCH_DONE;
m_search_->matchedLength = 0;
m_search_->text = m_text_.getBuffer();
m_search_->textLength = text.length();
}
SearchIterator::SearchIterator(CharacterIterator &text,
BreakIterator *breakiter) :
m_breakiterator_(breakiter)
{
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
m_search_->breakIter = nullptr;
m_search_->isOverlap = false;
m_search_->isCanonicalMatch = false;
m_search_->elementComparisonType = 0;
m_search_->isForwardSearching = true;
m_search_->reset = true;
m_search_->matchedIndex = USEARCH_DONE;
m_search_->matchedLength = 0;
text.getText(m_text_);
m_search_->text = m_text_.getBuffer();
m_search_->textLength = m_text_.length();
m_breakiterator_ = breakiter;
}
// protected methods ------------------------------------------------------
SearchIterator & SearchIterator::operator=(const SearchIterator &that)
{
if (this != &that) {
m_breakiterator_ = that.m_breakiterator_;
m_text_ = that.m_text_;
m_search_->breakIter = that.m_search_->breakIter;
m_search_->isCanonicalMatch = that.m_search_->isCanonicalMatch;
m_search_->isOverlap = that.m_search_->isOverlap;
m_search_->elementComparisonType = that.m_search_->elementComparisonType;
m_search_->matchedIndex = that.m_search_->matchedIndex;
m_search_->matchedLength = that.m_search_->matchedLength;
m_search_->text = that.m_search_->text;
m_search_->textLength = that.m_search_->textLength;
}
return *this;
}
void SearchIterator::setMatchLength(int32_t length)
{
m_search_->matchedLength = length;
}
void SearchIterator::setMatchStart(int32_t position)
{
m_search_->matchedIndex = position;
}
void SearchIterator::setMatchNotFound()
{
setMatchStart(USEARCH_DONE);
setMatchLength(0);
UErrorCode status = U_ZERO_ERROR;
// by default no errors should be returned here since offsets are within
// range.
if (m_search_->isForwardSearching) {
setOffset(m_search_->textLength, status);
}
else {
setOffset(0, status);
}
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_COLLATION */
|