1 | // © 2016 and later: Unicode, Inc. and others. |
2 | // License & terms of use: http://www.unicode.org/copyright.html |
3 | /* |
4 | ****************************************************************************** |
5 | * Copyright (C) 1998-2012, International Business Machines Corporation and |
6 | * others. All Rights Reserved. |
7 | ****************************************************************************** |
8 | */ |
9 | |
10 | #include "utypeinfo.h" // for 'typeid' to work |
11 | |
12 | #include "unicode/uchriter.h" |
13 | #include "unicode/ustring.h" |
14 | #include "unicode/utf16.h" |
15 | #include "ustr_imp.h" |
16 | |
17 | U_NAMESPACE_BEGIN |
18 | |
19 | UOBJECT_DEFINE_RTTI_IMPLEMENTATION(UCharCharacterIterator) |
20 | |
21 | UCharCharacterIterator::UCharCharacterIterator() |
22 | : CharacterIterator(), |
23 | text(0) |
24 | { |
25 | // never default construct! |
26 | } |
27 | |
28 | UCharCharacterIterator::UCharCharacterIterator(ConstChar16Ptr textPtr, |
29 | int32_t length) |
30 | : CharacterIterator(textPtr != 0 ? (length>=0 ? length : u_strlen(textPtr)) : 0), |
31 | text(textPtr) |
32 | { |
33 | } |
34 | |
35 | UCharCharacterIterator::UCharCharacterIterator(ConstChar16Ptr textPtr, |
36 | int32_t length, |
37 | int32_t position) |
38 | : CharacterIterator(textPtr != 0 ? (length>=0 ? length : u_strlen(textPtr)) : 0, position), |
39 | text(textPtr) |
40 | { |
41 | } |
42 | |
43 | UCharCharacterIterator::UCharCharacterIterator(ConstChar16Ptr textPtr, |
44 | int32_t length, |
45 | int32_t textBegin, |
46 | int32_t textEnd, |
47 | int32_t position) |
48 | : CharacterIterator(textPtr != 0 ? (length>=0 ? length : u_strlen(textPtr)) : 0, textBegin, textEnd, position), |
49 | text(textPtr) |
50 | { |
51 | } |
52 | |
53 | UCharCharacterIterator::UCharCharacterIterator(const UCharCharacterIterator& that) |
54 | : CharacterIterator(that), |
55 | text(that.text) |
56 | { |
57 | } |
58 | |
59 | UCharCharacterIterator& |
60 | UCharCharacterIterator::operator=(const UCharCharacterIterator& that) { |
61 | CharacterIterator::operator=(that); |
62 | text = that.text; |
63 | return *this; |
64 | } |
65 | |
66 | UCharCharacterIterator::~UCharCharacterIterator() { |
67 | } |
68 | |
69 | bool |
70 | UCharCharacterIterator::operator==(const ForwardCharacterIterator& that) const { |
71 | if (this == &that) { |
72 | return true; |
73 | } |
74 | if (typeid(*this) != typeid(that)) { |
75 | return false; |
76 | } |
77 | |
78 | const UCharCharacterIterator& realThat = static_cast<const UCharCharacterIterator&>(that); |
79 | |
80 | return text == realThat.text |
81 | && textLength == realThat.textLength |
82 | && pos == realThat.pos |
83 | && begin == realThat.begin |
84 | && end == realThat.end; |
85 | } |
86 | |
87 | int32_t |
88 | UCharCharacterIterator::hashCode() const { |
89 | return ustr_hashUCharsN(text, textLength) ^ pos ^ begin ^ end; |
90 | } |
91 | |
92 | UCharCharacterIterator* |
93 | UCharCharacterIterator::clone() const { |
94 | return new UCharCharacterIterator(*this); |
95 | } |
96 | |
97 | char16_t |
98 | UCharCharacterIterator::first() { |
99 | pos = begin; |
100 | if(pos < end) { |
101 | return text[pos]; |
102 | } else { |
103 | return DONE; |
104 | } |
105 | } |
106 | |
107 | char16_t |
108 | UCharCharacterIterator::firstPostInc() { |
109 | pos = begin; |
110 | if(pos < end) { |
111 | return text[pos++]; |
112 | } else { |
113 | return DONE; |
114 | } |
115 | } |
116 | |
117 | char16_t |
118 | UCharCharacterIterator::last() { |
119 | pos = end; |
120 | if(pos > begin) { |
121 | return text[--pos]; |
122 | } else { |
123 | return DONE; |
124 | } |
125 | } |
126 | |
127 | char16_t |
128 | UCharCharacterIterator::setIndex(int32_t position) { |
129 | if(position < begin) { |
130 | pos = begin; |
131 | } else if(position > end) { |
132 | pos = end; |
133 | } else { |
134 | pos = position; |
135 | } |
136 | if(pos < end) { |
137 | return text[pos]; |
138 | } else { |
139 | return DONE; |
140 | } |
141 | } |
142 | |
143 | char16_t |
144 | UCharCharacterIterator::current() const { |
145 | if (pos >= begin && pos < end) { |
146 | return text[pos]; |
147 | } else { |
148 | return DONE; |
149 | } |
150 | } |
151 | |
152 | char16_t |
153 | UCharCharacterIterator::next() { |
154 | if (pos + 1 < end) { |
155 | return text[++pos]; |
156 | } else { |
157 | /* make current() return DONE */ |
158 | pos = end; |
159 | return DONE; |
160 | } |
161 | } |
162 | |
163 | char16_t |
164 | UCharCharacterIterator::nextPostInc() { |
165 | if (pos < end) { |
166 | return text[pos++]; |
167 | } else { |
168 | return DONE; |
169 | } |
170 | } |
171 | |
172 | UBool |
173 | UCharCharacterIterator::hasNext() { |
174 | return (UBool)(pos < end ? true : false); |
175 | } |
176 | |
177 | char16_t |
178 | UCharCharacterIterator::previous() { |
179 | if (pos > begin) { |
180 | return text[--pos]; |
181 | } else { |
182 | return DONE; |
183 | } |
184 | } |
185 | |
186 | UBool |
187 | UCharCharacterIterator::hasPrevious() { |
188 | return (UBool)(pos > begin ? true : false); |
189 | } |
190 | |
191 | UChar32 |
192 | UCharCharacterIterator::first32() { |
193 | pos = begin; |
194 | if(pos < end) { |
195 | int32_t i = pos; |
196 | UChar32 c; |
197 | U16_NEXT(text, i, end, c); |
198 | return c; |
199 | } else { |
200 | return DONE; |
201 | } |
202 | } |
203 | |
204 | UChar32 |
205 | UCharCharacterIterator::first32PostInc() { |
206 | pos = begin; |
207 | if(pos < end) { |
208 | UChar32 c; |
209 | U16_NEXT(text, pos, end, c); |
210 | return c; |
211 | } else { |
212 | return DONE; |
213 | } |
214 | } |
215 | |
216 | UChar32 |
217 | UCharCharacterIterator::last32() { |
218 | pos = end; |
219 | if(pos > begin) { |
220 | UChar32 c; |
221 | U16_PREV(text, begin, pos, c); |
222 | return c; |
223 | } else { |
224 | return DONE; |
225 | } |
226 | } |
227 | |
228 | UChar32 |
229 | UCharCharacterIterator::setIndex32(int32_t position) { |
230 | if(position < begin) { |
231 | position = begin; |
232 | } else if(position > end) { |
233 | position = end; |
234 | } |
235 | if(position < end) { |
236 | U16_SET_CP_START(text, begin, position); |
237 | int32_t i = this->pos = position; |
238 | UChar32 c; |
239 | U16_NEXT(text, i, end, c); |
240 | return c; |
241 | } else { |
242 | this->pos = position; |
243 | return DONE; |
244 | } |
245 | } |
246 | |
247 | UChar32 |
248 | UCharCharacterIterator::current32() const { |
249 | if (pos >= begin && pos < end) { |
250 | UChar32 c; |
251 | U16_GET(text, begin, pos, end, c); |
252 | return c; |
253 | } else { |
254 | return DONE; |
255 | } |
256 | } |
257 | |
258 | UChar32 |
259 | UCharCharacterIterator::next32() { |
260 | if (pos < end) { |
261 | U16_FWD_1(text, pos, end); |
262 | if(pos < end) { |
263 | int32_t i = pos; |
264 | UChar32 c; |
265 | U16_NEXT(text, i, end, c); |
266 | return c; |
267 | } |
268 | } |
269 | /* make current() return DONE */ |
270 | pos = end; |
271 | return DONE; |
272 | } |
273 | |
274 | UChar32 |
275 | UCharCharacterIterator::next32PostInc() { |
276 | if (pos < end) { |
277 | UChar32 c; |
278 | U16_NEXT(text, pos, end, c); |
279 | return c; |
280 | } else { |
281 | return DONE; |
282 | } |
283 | } |
284 | |
285 | UChar32 |
286 | UCharCharacterIterator::previous32() { |
287 | if (pos > begin) { |
288 | UChar32 c; |
289 | U16_PREV(text, begin, pos, c); |
290 | return c; |
291 | } else { |
292 | return DONE; |
293 | } |
294 | } |
295 | |
296 | int32_t |
297 | UCharCharacterIterator::move(int32_t delta, CharacterIterator::EOrigin origin) { |
298 | switch(origin) { |
299 | case kStart: |
300 | pos = begin + delta; |
301 | break; |
302 | case kCurrent: |
303 | pos += delta; |
304 | break; |
305 | case kEnd: |
306 | pos = end + delta; |
307 | break; |
308 | default: |
309 | break; |
310 | } |
311 | |
312 | if(pos < begin) { |
313 | pos = begin; |
314 | } else if(pos > end) { |
315 | pos = end; |
316 | } |
317 | |
318 | return pos; |
319 | } |
320 | |
321 | int32_t |
322 | UCharCharacterIterator::move32(int32_t delta, CharacterIterator::EOrigin origin) { |
323 | // this implementation relies on the "safe" version of the UTF macros |
324 | // (or the trustworthiness of the caller) |
325 | switch(origin) { |
326 | case kStart: |
327 | pos = begin; |
328 | if(delta > 0) { |
329 | U16_FWD_N(text, pos, end, delta); |
330 | } |
331 | break; |
332 | case kCurrent: |
333 | if(delta > 0) { |
334 | U16_FWD_N(text, pos, end, delta); |
335 | } else { |
336 | U16_BACK_N(text, begin, pos, -delta); |
337 | } |
338 | break; |
339 | case kEnd: |
340 | pos = end; |
341 | if(delta < 0) { |
342 | U16_BACK_N(text, begin, pos, -delta); |
343 | } |
344 | break; |
345 | default: |
346 | break; |
347 | } |
348 | |
349 | return pos; |
350 | } |
351 | |
352 | void UCharCharacterIterator::setText(ConstChar16Ptr newText, |
353 | int32_t newTextLength) { |
354 | text = newText; |
355 | if(newText == 0 || newTextLength < 0) { |
356 | newTextLength = 0; |
357 | } |
358 | end = textLength = newTextLength; |
359 | pos = begin = 0; |
360 | } |
361 | |
362 | void |
363 | UCharCharacterIterator::getText(UnicodeString& result) { |
364 | result = UnicodeString(text, textLength); |
365 | } |
366 | |
367 | U_NAMESPACE_END |
368 | |