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31 * This API has been replaced by the Normalizer2 class and is only available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