1 | // © 2016 and later: Unicode, Inc. and others. |
2 | // License & terms of use: http://www.unicode.org/copyright.html |
3 | /* |
4 | ******************************************************************** |
5 | * COPYRIGHT: |
6 | * Copyright (c) 1996-2015, International Business Machines Corporation and |
7 | * others. All Rights Reserved. |
8 | ******************************************************************** |
9 | */ |
10 | |
11 | #ifndef NORMLZR_H |
12 | #define NORMLZR_H |
13 | |
14 | #include "unicode/utypes.h" |
15 | |
16 | #if U_SHOW_CPLUSPLUS_API |
17 | |
18 | /** |
19 | * \file |
20 | * \brief C++ API: Unicode Normalization |
21 | */ |
22 | |
23 | #if !UCONFIG_NO_NORMALIZATION |
24 | |
25 | #include "unicode/chariter.h" |
26 | #include "unicode/normalizer2.h" |
27 | #include "unicode/unistr.h" |
28 | #include "unicode/unorm.h" |
29 | #include "unicode/uobject.h" |
30 | |
31 | U_NAMESPACE_BEGIN |
32 | /** |
33 | * Old Unicode normalization API. |
34 | * |
35 | * This API has been replaced by the Normalizer2 class and is only available |
36 | * for backward compatibility. This class simply delegates to the Normalizer2 class. |
37 | * There is one exception: The new API does not provide a replacement for Normalizer::compare(). |
38 | * |
39 | * The Normalizer class supports the standard normalization forms described in |
40 | * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> |
41 | * Unicode Standard Annex #15: Unicode Normalization Forms</a>. |
42 | * |
43 | * The Normalizer class consists of two parts: |
44 | * - static functions that normalize strings or test if strings are normalized |
45 | * - a Normalizer object is an iterator that takes any kind of text and |
46 | * provides iteration over its normalized form |
47 | * |
48 | * The Normalizer class is not suitable for subclassing. |
49 | * |
50 | * For basic information about normalization forms and details about the C API |
51 | * please see the documentation in unorm.h. |
52 | * |
53 | * The iterator API with the Normalizer constructors and the non-static functions |
54 | * use a CharacterIterator as input. It is possible to pass a string which |
55 | * is then internally wrapped in a CharacterIterator. |
56 | * The input text is not normalized all at once, but incrementally where needed |
57 | * (providing efficient random access). |
58 | * This allows to pass in a large text but spend only a small amount of time |
59 | * normalizing a small part of that text. |
60 | * However, if the entire text is normalized, then the iterator will be |
61 | * slower than normalizing the entire text at once and iterating over the result. |
62 | * A possible use of the Normalizer iterator is also to report an index into the |
63 | * original text that is close to where the normalized characters come from. |
64 | * |
65 | * <em>Important:</em> The iterator API was cleaned up significantly for ICU 2.0. |
66 | * The earlier implementation reported the getIndex() inconsistently, |
67 | * and previous() could not be used after setIndex(), next(), first(), and current(). |
68 | * |
69 | * Normalizer allows to start normalizing from anywhere in the input text by |
70 | * calling setIndexOnly(), first(), or last(). |
71 | * Without calling any of these, the iterator will start at the beginning of the text. |
72 | * |
73 | * At any time, next() returns the next normalized code point (UChar32), |
74 | * with post-increment semantics (like CharacterIterator::next32PostInc()). |
75 | * previous() returns the previous normalized code point (UChar32), |
76 | * with pre-decrement semantics (like CharacterIterator::previous32()). |
77 | * |
78 | * current() returns the current code point |
79 | * (respectively the one at the newly set index) without moving |
80 | * the getIndex(). Note that if the text at the current position |
81 | * needs to be normalized, then these functions will do that. |
82 | * (This is why current() is not const.) |
83 | * It is more efficient to call setIndexOnly() instead, which does not |
84 | * normalize. |
85 | * |
86 | * getIndex() always refers to the position in the input text where the normalized |
87 | * code points are returned from. It does not always change with each returned |
88 | * code point. |
89 | * The code point that is returned from any of the functions |
90 | * corresponds to text at or after getIndex(), according to the |
91 | * function's iteration semantics (post-increment or pre-decrement). |
92 | * |
93 | * next() returns a code point from at or after the getIndex() |
94 | * from before the next() call. After the next() call, the getIndex() |
95 | * might have moved to where the next code point will be returned from |
96 | * (from a next() or current() call). |
97 | * This is semantically equivalent to array access with array[index++] |
98 | * (post-increment semantics). |
99 | * |
100 | * previous() returns a code point from at or after the getIndex() |
101 | * from after the previous() call. |
102 | * This is semantically equivalent to array access with array[--index] |
103 | * (pre-decrement semantics). |
104 | * |
105 | * Internally, the Normalizer iterator normalizes a small piece of text |
106 | * starting at the getIndex() and ending at a following "safe" index. |
107 | * The normalized results is stored in an internal string buffer, and |
108 | * the code points are iterated from there. |
109 | * With multiple iteration calls, this is repeated until the next piece |
110 | * of text needs to be normalized, and the getIndex() needs to be moved. |
111 | * |
112 | * The following "safe" index, the internal buffer, and the secondary |
113 | * iteration index into that buffer are not exposed on the API. |
114 | * This also means that it is currently not practical to return to |
115 | * a particular, arbitrary position in the text because one would need to |
116 | * know, and be able to set, in addition to the getIndex(), at least also the |
117 | * current index into the internal buffer. |
118 | * It is currently only possible to observe when getIndex() changes |
119 | * (with careful consideration of the iteration semantics), |
120 | * at which time the internal index will be 0. |
121 | * For example, if getIndex() is different after next() than before it, |
122 | * then the internal index is 0 and one can return to this getIndex() |
123 | * later with setIndexOnly(). |
124 | * |
125 | * Note: While the setIndex() and getIndex() refer to indices in the |
126 | * underlying Unicode input text, the next() and previous() methods |
127 | * iterate through characters in the normalized output. |
128 | * This means that there is not necessarily a one-to-one correspondence |
129 | * between characters returned by next() and previous() and the indices |
130 | * passed to and returned from setIndex() and getIndex(). |
131 | * It is for this reason that Normalizer does not implement the CharacterIterator interface. |
132 | * |
133 | * @author Laura Werner, Mark Davis, Markus Scherer |
134 | * @stable ICU 2.0 |
135 | */ |
136 | class U_COMMON_API Normalizer : public UObject { |
137 | public: |
138 | #ifndef U_HIDE_DEPRECATED_API |
139 | /** |
140 | * If DONE is returned from an iteration function that returns a code point, |
141 | * then there are no more normalization results available. |
142 | * @deprecated ICU 56 Use Normalizer2 instead. |
143 | */ |
144 | enum { |
145 | DONE=0xffff |
146 | }; |
147 | |
148 | // Constructors |
149 | |
150 | /** |
151 | * Creates a new <code>Normalizer</code> object for iterating over the |
152 | * normalized form of a given string. |
153 | * <p> |
154 | * @param str The string to be normalized. The normalization |
155 | * will start at the beginning of the string. |
156 | * |
157 | * @param mode The normalization mode. |
158 | * @deprecated ICU 56 Use Normalizer2 instead. |
159 | */ |
160 | Normalizer(const UnicodeString& str, UNormalizationMode mode); |
161 | |
162 | /** |
163 | * Creates a new <code>Normalizer</code> object for iterating over the |
164 | * normalized form of a given string. |
165 | * <p> |
166 | * @param str The string to be normalized. The normalization |
167 | * will start at the beginning of the string. |
168 | * |
169 | * @param length Length of the string, or -1 if NUL-terminated. |
170 | * @param mode The normalization mode. |
171 | * @deprecated ICU 56 Use Normalizer2 instead. |
172 | */ |
173 | Normalizer(ConstChar16Ptr str, int32_t length, UNormalizationMode mode); |
174 | |
175 | /** |
176 | * Creates a new <code>Normalizer</code> object for iterating over the |
177 | * normalized form of the given text. |
178 | * <p> |
179 | * @param iter The input text to be normalized. The normalization |
180 | * will start at the beginning of the string. |
181 | * |
182 | * @param mode The normalization mode. |
183 | * @deprecated ICU 56 Use Normalizer2 instead. |
184 | */ |
185 | Normalizer(const CharacterIterator& iter, UNormalizationMode mode); |
186 | #endif /* U_HIDE_DEPRECATED_API */ |
187 | |
188 | #ifndef U_FORCE_HIDE_DEPRECATED_API |
189 | /** |
190 | * Copy constructor. |
191 | * @param copy The object to be copied. |
192 | * @deprecated ICU 56 Use Normalizer2 instead. |
193 | */ |
194 | Normalizer(const Normalizer& copy); |
195 | |
196 | /** |
197 | * Destructor |
198 | * @deprecated ICU 56 Use Normalizer2 instead. |
199 | */ |
200 | virtual ~Normalizer(); |
201 | #endif // U_FORCE_HIDE_DEPRECATED_API |
202 | |
203 | //------------------------------------------------------------------------- |
204 | // Static utility methods |
205 | //------------------------------------------------------------------------- |
206 | |
207 | #ifndef U_HIDE_DEPRECATED_API |
208 | /** |
209 | * Normalizes a <code>UnicodeString</code> according to the specified normalization mode. |
210 | * This is a wrapper for unorm_normalize(), using UnicodeString's. |
211 | * |
212 | * The <code>options</code> parameter specifies which optional |
213 | * <code>Normalizer</code> features are to be enabled for this operation. |
214 | * |
215 | * @param source the input string to be normalized. |
216 | * @param mode the normalization mode |
217 | * @param options the optional features to be enabled (0 for no options) |
218 | * @param result The normalized string (on output). |
219 | * @param status The error code. |
220 | * @deprecated ICU 56 Use Normalizer2 instead. |
221 | */ |
222 | static void U_EXPORT2 normalize(const UnicodeString& source, |
223 | UNormalizationMode mode, int32_t options, |
224 | UnicodeString& result, |
225 | UErrorCode &status); |
226 | |
227 | /** |
228 | * Compose a <code>UnicodeString</code>. |
229 | * This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC. |
230 | * This is a wrapper for unorm_normalize(), using UnicodeString's. |
231 | * |
232 | * The <code>options</code> parameter specifies which optional |
233 | * <code>Normalizer</code> features are to be enabled for this operation. |
234 | * |
235 | * @param source the string to be composed. |
236 | * @param compat Perform compatibility decomposition before composition. |
237 | * If this argument is <code>false</code>, only canonical |
238 | * decomposition will be performed. |
239 | * @param options the optional features to be enabled (0 for no options) |
240 | * @param result The composed string (on output). |
241 | * @param status The error code. |
242 | * @deprecated ICU 56 Use Normalizer2 instead. |
243 | */ |
244 | static void U_EXPORT2 compose(const UnicodeString& source, |
245 | UBool compat, int32_t options, |
246 | UnicodeString& result, |
247 | UErrorCode &status); |
248 | |
249 | /** |
250 | * Static method to decompose a <code>UnicodeString</code>. |
251 | * This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD. |
252 | * This is a wrapper for unorm_normalize(), using UnicodeString's. |
253 | * |
254 | * The <code>options</code> parameter specifies which optional |
255 | * <code>Normalizer</code> features are to be enabled for this operation. |
256 | * |
257 | * @param source the string to be decomposed. |
258 | * @param compat Perform compatibility decomposition. |
259 | * If this argument is <code>false</code>, only canonical |
260 | * decomposition will be performed. |
261 | * @param options the optional features to be enabled (0 for no options) |
262 | * @param result The decomposed string (on output). |
263 | * @param status The error code. |
264 | * @deprecated ICU 56 Use Normalizer2 instead. |
265 | */ |
266 | static void U_EXPORT2 decompose(const UnicodeString& source, |
267 | UBool compat, int32_t options, |
268 | UnicodeString& result, |
269 | UErrorCode &status); |
270 | |
271 | /** |
272 | * Performing quick check on a string, to quickly determine if the string is |
273 | * in a particular normalization format. |
274 | * This is a wrapper for unorm_quickCheck(), using a UnicodeString. |
275 | * |
276 | * Three types of result can be returned UNORM_YES, UNORM_NO or |
277 | * UNORM_MAYBE. Result UNORM_YES indicates that the argument |
278 | * string is in the desired normalized format, UNORM_NO determines that |
279 | * argument string is not in the desired normalized format. A |
280 | * UNORM_MAYBE result indicates that a more thorough check is required, |
281 | * the user may have to put the string in its normalized form and compare the |
282 | * results. |
283 | * @param source string for determining if it is in a normalized format |
284 | * @param mode normalization format |
285 | * @param status A reference to a UErrorCode to receive any errors |
286 | * @return UNORM_YES, UNORM_NO or UNORM_MAYBE |
287 | * |
288 | * @see isNormalized |
289 | * @deprecated ICU 56 Use Normalizer2 instead. |
290 | */ |
291 | static inline UNormalizationCheckResult |
292 | quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status); |
293 | |
294 | /** |
295 | * Performing quick check on a string; same as the other version of quickCheck |
296 | * but takes an extra options parameter like most normalization functions. |
297 | * |
298 | * @param source string for determining if it is in a normalized format |
299 | * @param mode normalization format |
300 | * @param options the optional features to be enabled (0 for no options) |
301 | * @param status A reference to a UErrorCode to receive any errors |
302 | * @return UNORM_YES, UNORM_NO or UNORM_MAYBE |
303 | * |
304 | * @see isNormalized |
305 | * @deprecated ICU 56 Use Normalizer2 instead. |
306 | */ |
307 | static UNormalizationCheckResult |
308 | quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status); |
309 | |
310 | /** |
311 | * Test if a string is in a given normalization form. |
312 | * This is semantically equivalent to source.equals(normalize(source, mode)) . |
313 | * |
314 | * Unlike unorm_quickCheck(), this function returns a definitive result, |
315 | * never a "maybe". |
316 | * For NFD, NFKD, and FCD, both functions work exactly the same. |
317 | * For NFC and NFKC where quickCheck may return "maybe", this function will |
318 | * perform further tests to arrive at a true/false result. |
319 | * |
320 | * @param src String that is to be tested if it is in a normalization format. |
321 | * @param mode Which normalization form to test for. |
322 | * @param errorCode ICU error code in/out parameter. |
323 | * Must fulfill U_SUCCESS before the function call. |
324 | * @return Boolean value indicating whether the source string is in the |
325 | * "mode" normalization form. |
326 | * |
327 | * @see quickCheck |
328 | * @deprecated ICU 56 Use Normalizer2 instead. |
329 | */ |
330 | static inline UBool |
331 | isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode); |
332 | |
333 | /** |
334 | * Test if a string is in a given normalization form; same as the other version of isNormalized |
335 | * but takes an extra options parameter like most normalization functions. |
336 | * |
337 | * @param src String that is to be tested if it is in a normalization format. |
338 | * @param mode Which normalization form to test for. |
339 | * @param options the optional features to be enabled (0 for no options) |
340 | * @param errorCode ICU error code in/out parameter. |
341 | * Must fulfill U_SUCCESS before the function call. |
342 | * @return Boolean value indicating whether the source string is in the |
343 | * "mode" normalization form. |
344 | * |
345 | * @see quickCheck |
346 | * @deprecated ICU 56 Use Normalizer2 instead. |
347 | */ |
348 | static UBool |
349 | isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode); |
350 | |
351 | /** |
352 | * Concatenate normalized strings, making sure that the result is normalized as well. |
353 | * |
354 | * If both the left and the right strings are in |
355 | * the normalization form according to "mode/options", |
356 | * then the result will be |
357 | * |
358 | * \code |
359 | * dest=normalize(left+right, mode, options) |
360 | * \endcode |
361 | * |
362 | * For details see unorm_concatenate in unorm.h. |
363 | * |
364 | * @param left Left source string. |
365 | * @param right Right source string. |
366 | * @param result The output string. |
367 | * @param mode The normalization mode. |
368 | * @param options A bit set of normalization options. |
369 | * @param errorCode ICU error code in/out parameter. |
370 | * Must fulfill U_SUCCESS before the function call. |
371 | * @return result |
372 | * |
373 | * @see unorm_concatenate |
374 | * @see normalize |
375 | * @see unorm_next |
376 | * @see unorm_previous |
377 | * |
378 | * @deprecated ICU 56 Use Normalizer2 instead. |
379 | */ |
380 | static UnicodeString & |
381 | U_EXPORT2 concatenate(const UnicodeString &left, const UnicodeString &right, |
382 | UnicodeString &result, |
383 | UNormalizationMode mode, int32_t options, |
384 | UErrorCode &errorCode); |
385 | #endif /* U_HIDE_DEPRECATED_API */ |
386 | |
387 | /** |
388 | * Compare two strings for canonical equivalence. |
389 | * Further options include case-insensitive comparison and |
390 | * code point order (as opposed to code unit order). |
391 | * |
392 | * Canonical equivalence between two strings is defined as their normalized |
393 | * forms (NFD or NFC) being identical. |
394 | * This function compares strings incrementally instead of normalizing |
395 | * (and optionally case-folding) both strings entirely, |
396 | * improving performance significantly. |
397 | * |
398 | * Bulk normalization is only necessary if the strings do not fulfill the FCD |
399 | * conditions. Only in this case, and only if the strings are relatively long, |
400 | * is memory allocated temporarily. |
401 | * For FCD strings and short non-FCD strings there is no memory allocation. |
402 | * |
403 | * Semantically, this is equivalent to |
404 | * strcmp[CodePointOrder](NFD(foldCase(s1)), NFD(foldCase(s2))) |
405 | * where code point order and foldCase are all optional. |
406 | * |
407 | * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match |
408 | * the case folding must be performed first, then the normalization. |
409 | * |
410 | * @param s1 First source string. |
411 | * @param s2 Second source string. |
412 | * |
413 | * @param options A bit set of options: |
414 | * - U_FOLD_CASE_DEFAULT or 0 is used for default options: |
415 | * Case-sensitive comparison in code unit order, and the input strings |
416 | * are quick-checked for FCD. |
417 | * |
418 | * - UNORM_INPUT_IS_FCD |
419 | * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. |
420 | * If not set, the function will quickCheck for FCD |
421 | * and normalize if necessary. |
422 | * |
423 | * - U_COMPARE_CODE_POINT_ORDER |
424 | * Set to choose code point order instead of code unit order |
425 | * (see u_strCompare for details). |
426 | * |
427 | * - U_COMPARE_IGNORE_CASE |
428 | * Set to compare strings case-insensitively using case folding, |
429 | * instead of case-sensitively. |
430 | * If set, then the following case folding options are used. |
431 | * |
432 | * - Options as used with case-insensitive comparisons, currently: |
433 | * |
434 | * - U_FOLD_CASE_EXCLUDE_SPECIAL_I |
435 | * (see u_strCaseCompare for details) |
436 | * |
437 | * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT |
438 | * |
439 | * @param errorCode ICU error code in/out parameter. |
440 | * Must fulfill U_SUCCESS before the function call. |
441 | * @return <0 or 0 or >0 as usual for string comparisons |
442 | * |
443 | * @see unorm_compare |
444 | * @see normalize |
445 | * @see UNORM_FCD |
446 | * @see u_strCompare |
447 | * @see u_strCaseCompare |
448 | * |
449 | * @stable ICU 2.2 |
450 | */ |
451 | static inline int32_t |
452 | compare(const UnicodeString &s1, const UnicodeString &s2, |
453 | uint32_t options, |
454 | UErrorCode &errorCode); |
455 | |
456 | #ifndef U_HIDE_DEPRECATED_API |
457 | //------------------------------------------------------------------------- |
458 | // Iteration API |
459 | //------------------------------------------------------------------------- |
460 | |
461 | /** |
462 | * Return the current character in the normalized text. |
463 | * current() may need to normalize some text at getIndex(). |
464 | * The getIndex() is not changed. |
465 | * |
466 | * @return the current normalized code point |
467 | * @deprecated ICU 56 Use Normalizer2 instead. |
468 | */ |
469 | UChar32 current(void); |
470 | |
471 | /** |
472 | * Return the first character in the normalized text. |
473 | * This is equivalent to setIndexOnly(startIndex()) followed by next(). |
474 | * (Post-increment semantics.) |
475 | * |
476 | * @return the first normalized code point |
477 | * @deprecated ICU 56 Use Normalizer2 instead. |
478 | */ |
479 | UChar32 first(void); |
480 | |
481 | /** |
482 | * Return the last character in the normalized text. |
483 | * This is equivalent to setIndexOnly(endIndex()) followed by previous(). |
484 | * (Pre-decrement semantics.) |
485 | * |
486 | * @return the last normalized code point |
487 | * @deprecated ICU 56 Use Normalizer2 instead. |
488 | */ |
489 | UChar32 last(void); |
490 | |
491 | /** |
492 | * Return the next character in the normalized text. |
493 | * (Post-increment semantics.) |
494 | * If the end of the text has already been reached, DONE is returned. |
495 | * The DONE value could be confused with a U+FFFF non-character code point |
496 | * in the text. If this is possible, you can test getIndex()<endIndex() |
497 | * before calling next(), or (getIndex()<endIndex() || last()!=DONE) |
498 | * after calling next(). (Calling last() will change the iterator state!) |
499 | * |
500 | * The C API unorm_next() is more efficient and does not have this ambiguity. |
501 | * |
502 | * @return the next normalized code point |
503 | * @deprecated ICU 56 Use Normalizer2 instead. |
504 | */ |
505 | UChar32 next(void); |
506 | |
507 | /** |
508 | * Return the previous character in the normalized text and decrement. |
509 | * (Pre-decrement semantics.) |
510 | * If the beginning of the text has already been reached, DONE is returned. |
511 | * The DONE value could be confused with a U+FFFF non-character code point |
512 | * in the text. If this is possible, you can test |
513 | * (getIndex()>startIndex() || first()!=DONE). (Calling first() will change |
514 | * the iterator state!) |
515 | * |
516 | * The C API unorm_previous() is more efficient and does not have this ambiguity. |
517 | * |
518 | * @return the previous normalized code point |
519 | * @deprecated ICU 56 Use Normalizer2 instead. |
520 | */ |
521 | UChar32 previous(void); |
522 | |
523 | /** |
524 | * Set the iteration position in the input text that is being normalized, |
525 | * without any immediate normalization. |
526 | * After setIndexOnly(), getIndex() will return the same index that is |
527 | * specified here. |
528 | * |
529 | * @param index the desired index in the input text. |
530 | * @deprecated ICU 56 Use Normalizer2 instead. |
531 | */ |
532 | void setIndexOnly(int32_t index); |
533 | |
534 | /** |
535 | * Reset the index to the beginning of the text. |
536 | * This is equivalent to setIndexOnly(startIndex)). |
537 | * @deprecated ICU 56 Use Normalizer2 instead. |
538 | */ |
539 | void reset(void); |
540 | |
541 | /** |
542 | * Retrieve the current iteration position in the input text that is |
543 | * being normalized. |
544 | * |
545 | * A following call to next() will return a normalized code point from |
546 | * the input text at or after this index. |
547 | * |
548 | * After a call to previous(), getIndex() will point at or before the |
549 | * position in the input text where the normalized code point |
550 | * was returned from with previous(). |
551 | * |
552 | * @return the current index in the input text |
553 | * @deprecated ICU 56 Use Normalizer2 instead. |
554 | */ |
555 | int32_t getIndex(void) const; |
556 | |
557 | /** |
558 | * Retrieve the index of the start of the input text. This is the begin index |
559 | * of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string |
560 | * over which this <code>Normalizer</code> is iterating. |
561 | * |
562 | * @return the smallest index in the input text where the Normalizer operates |
563 | * @deprecated ICU 56 Use Normalizer2 instead. |
564 | */ |
565 | int32_t startIndex(void) const; |
566 | |
567 | /** |
568 | * Retrieve the index of the end of the input text. This is the end index |
569 | * of the <code>CharacterIterator</code> or the length of the string |
570 | * over which this <code>Normalizer</code> is iterating. |
571 | * This end index is exclusive, i.e., the Normalizer operates only on characters |
572 | * before this index. |
573 | * |
574 | * @return the first index in the input text where the Normalizer does not operate |
575 | * @deprecated ICU 56 Use Normalizer2 instead. |
576 | */ |
577 | int32_t endIndex(void) const; |
578 | |
579 | /** |
580 | * Returns true when both iterators refer to the same character in the same |
581 | * input text. |
582 | * |
583 | * @param that a Normalizer object to compare this one to |
584 | * @return comparison result |
585 | * @deprecated ICU 56 Use Normalizer2 instead. |
586 | */ |
587 | bool operator==(const Normalizer& that) const; |
588 | |
589 | /** |
590 | * Returns false when both iterators refer to the same character in the same |
591 | * input text. |
592 | * |
593 | * @param that a Normalizer object to compare this one to |
594 | * @return comparison result |
595 | * @deprecated ICU 56 Use Normalizer2 instead. |
596 | */ |
597 | inline bool operator!=(const Normalizer& that) const; |
598 | |
599 | /** |
600 | * Returns a pointer to a new Normalizer that is a clone of this one. |
601 | * The caller is responsible for deleting the new clone. |
602 | * @return a pointer to a new Normalizer |
603 | * @deprecated ICU 56 Use Normalizer2 instead. |
604 | */ |
605 | Normalizer* clone() const; |
606 | |
607 | /** |
608 | * Generates a hash code for this iterator. |
609 | * |
610 | * @return the hash code |
611 | * @deprecated ICU 56 Use Normalizer2 instead. |
612 | */ |
613 | int32_t hashCode(void) const; |
614 | |
615 | //------------------------------------------------------------------------- |
616 | // Property access methods |
617 | //------------------------------------------------------------------------- |
618 | |
619 | /** |
620 | * Set the normalization mode for this object. |
621 | * <p> |
622 | * <b>Note:</b>If the normalization mode is changed while iterating |
623 | * over a string, calls to {@link #next() } and {@link #previous() } may |
624 | * return previously buffers characters in the old normalization mode |
625 | * until the iteration is able to re-sync at the next base character. |
626 | * It is safest to call {@link #setIndexOnly }, {@link #reset() }, |
627 | * {@link #setText }, {@link #first() }, |
628 | * {@link #last() }, etc. after calling <code>setMode</code>. |
629 | * <p> |
630 | * @param newMode the new mode for this <code>Normalizer</code>. |
631 | * @see #getUMode |
632 | * @deprecated ICU 56 Use Normalizer2 instead. |
633 | */ |
634 | void setMode(UNormalizationMode newMode); |
635 | |
636 | /** |
637 | * Return the normalization mode for this object. |
638 | * |
639 | * This is an unusual name because there used to be a getMode() that |
640 | * returned a different type. |
641 | * |
642 | * @return the mode for this <code>Normalizer</code> |
643 | * @see #setMode |
644 | * @deprecated ICU 56 Use Normalizer2 instead. |
645 | */ |
646 | UNormalizationMode getUMode(void) const; |
647 | |
648 | /** |
649 | * Set options that affect this <code>Normalizer</code>'s operation. |
650 | * Options do not change the basic composition or decomposition operation |
651 | * that is being performed, but they control whether |
652 | * certain optional portions of the operation are done. |
653 | * Currently the only available option is obsolete. |
654 | * |
655 | * It is possible to specify multiple options that are all turned on or off. |
656 | * |
657 | * @param option the option(s) whose value is/are to be set. |
658 | * @param value the new setting for the option. Use <code>true</code> to |
659 | * turn the option(s) on and <code>false</code> to turn it/them off. |
660 | * |
661 | * @see #getOption |
662 | * @deprecated ICU 56 Use Normalizer2 instead. |
663 | */ |
664 | void setOption(int32_t option, |
665 | UBool value); |
666 | |
667 | /** |
668 | * Determine whether an option is turned on or off. |
669 | * If multiple options are specified, then the result is true if any |
670 | * of them are set. |
671 | * <p> |
672 | * @param option the option(s) that are to be checked |
673 | * @return true if any of the option(s) are set |
674 | * @see #setOption |
675 | * @deprecated ICU 56 Use Normalizer2 instead. |
676 | */ |
677 | UBool getOption(int32_t option) const; |
678 | |
679 | /** |
680 | * Set the input text over which this <code>Normalizer</code> will iterate. |
681 | * The iteration position is set to the beginning. |
682 | * |
683 | * @param newText a string that replaces the current input text |
684 | * @param status a UErrorCode |
685 | * @deprecated ICU 56 Use Normalizer2 instead. |
686 | */ |
687 | void setText(const UnicodeString& newText, |
688 | UErrorCode &status); |
689 | |
690 | /** |
691 | * Set the input text over which this <code>Normalizer</code> will iterate. |
692 | * The iteration position is set to the beginning. |
693 | * |
694 | * @param newText a CharacterIterator object that replaces the current input text |
695 | * @param status a UErrorCode |
696 | * @deprecated ICU 56 Use Normalizer2 instead. |
697 | */ |
698 | void setText(const CharacterIterator& newText, |
699 | UErrorCode &status); |
700 | |
701 | /** |
702 | * Set the input text over which this <code>Normalizer</code> will iterate. |
703 | * The iteration position is set to the beginning. |
704 | * |
705 | * @param newText a string that replaces the current input text |
706 | * @param length the length of the string, or -1 if NUL-terminated |
707 | * @param status a UErrorCode |
708 | * @deprecated ICU 56 Use Normalizer2 instead. |
709 | */ |
710 | void setText(ConstChar16Ptr newText, |
711 | int32_t length, |
712 | UErrorCode &status); |
713 | /** |
714 | * Copies the input text into the UnicodeString argument. |
715 | * |
716 | * @param result Receives a copy of the text under iteration. |
717 | * @deprecated ICU 56 Use Normalizer2 instead. |
718 | */ |
719 | void getText(UnicodeString& result); |
720 | |
721 | /** |
722 | * ICU "poor man's RTTI", returns a UClassID for this class. |
723 | * @returns a UClassID for this class. |
724 | * @deprecated ICU 56 Use Normalizer2 instead. |
725 | */ |
726 | static UClassID U_EXPORT2 getStaticClassID(); |
727 | #endif /* U_HIDE_DEPRECATED_API */ |
728 | |
729 | #ifndef U_FORCE_HIDE_DEPRECATED_API |
730 | /** |
731 | * ICU "poor man's RTTI", returns a UClassID for the actual class. |
732 | * @return a UClassID for the actual class. |
733 | * @deprecated ICU 56 Use Normalizer2 instead. |
734 | */ |
735 | virtual UClassID getDynamicClassID() const override; |
736 | #endif // U_FORCE_HIDE_DEPRECATED_API |
737 | |
738 | private: |
739 | //------------------------------------------------------------------------- |
740 | // Private functions |
741 | //------------------------------------------------------------------------- |
742 | |
743 | Normalizer(); // default constructor not implemented |
744 | Normalizer &operator=(const Normalizer &that); // assignment operator not implemented |
745 | |
746 | // Private utility methods for iteration |
747 | // For documentation, see the source code |
748 | UBool nextNormalize(); |
749 | UBool previousNormalize(); |
750 | |
751 | void init(); |
752 | void clearBuffer(void); |
753 | |
754 | //------------------------------------------------------------------------- |
755 | // Private data |
756 | //------------------------------------------------------------------------- |
757 | |
758 | FilteredNormalizer2*fFilteredNorm2; // owned if not NULL |
759 | const Normalizer2 *fNorm2; // not owned; may be equal to fFilteredNorm2 |
760 | UNormalizationMode fUMode; // deprecated |
761 | int32_t fOptions; |
762 | |
763 | // The input text and our position in it |
764 | CharacterIterator *text; |
765 | |
766 | // The normalization buffer is the result of normalization |
767 | // of the source in [currentIndex..nextIndex[ . |
768 | int32_t currentIndex, nextIndex; |
769 | |
770 | // A buffer for holding intermediate results |
771 | UnicodeString buffer; |
772 | int32_t bufferPos; |
773 | }; |
774 | |
775 | //------------------------------------------------------------------------- |
776 | // Inline implementations |
777 | //------------------------------------------------------------------------- |
778 | |
779 | #ifndef U_HIDE_DEPRECATED_API |
780 | inline bool |
781 | Normalizer::operator!= (const Normalizer& other) const |
782 | { return ! operator==(that: other); } |
783 | |
784 | inline UNormalizationCheckResult |
785 | Normalizer::quickCheck(const UnicodeString& source, |
786 | UNormalizationMode mode, |
787 | UErrorCode &status) { |
788 | return quickCheck(source, mode, options: 0, status); |
789 | } |
790 | |
791 | inline UBool |
792 | Normalizer::isNormalized(const UnicodeString& source, |
793 | UNormalizationMode mode, |
794 | UErrorCode &status) { |
795 | return isNormalized(src: source, mode, options: 0, errorCode&: status); |
796 | } |
797 | #endif /* U_HIDE_DEPRECATED_API */ |
798 | |
799 | inline int32_t |
800 | Normalizer::compare(const UnicodeString &s1, const UnicodeString &s2, |
801 | uint32_t options, |
802 | UErrorCode &errorCode) { |
803 | // all argument checking is done in unorm_compare |
804 | return unorm_compare(s1: toUCharPtr(p: s1.getBuffer()), length1: s1.length(), |
805 | s2: toUCharPtr(p: s2.getBuffer()), length2: s2.length(), |
806 | options, |
807 | pErrorCode: &errorCode); |
808 | } |
809 | |
810 | U_NAMESPACE_END |
811 | |
812 | #endif /* #if !UCONFIG_NO_NORMALIZATION */ |
813 | |
814 | #endif // NORMLZR_H |
815 | |
816 | #endif /* U_SHOW_CPLUSPLUS_API */ |
817 | |