|
1 /* |
|
2 ******************************************************************************* |
|
3 * |
|
4 * Copyright (C) 2002-2004, International Business Machines |
|
5 * Corporation and others. All Rights Reserved. |
|
6 * |
|
7 ******************************************************************************* |
|
8 * file name: uset.h |
|
9 * encoding: US-ASCII |
|
10 * tab size: 8 (not used) |
|
11 * indentation:4 |
|
12 * |
|
13 * created on: 2002mar07 |
|
14 * created by: Markus W. Scherer |
|
15 * |
|
16 * C version of UnicodeSet. |
|
17 */ |
|
18 |
|
19 |
|
20 /** |
|
21 * \file |
|
22 * \brief C API: Unicode Set |
|
23 * |
|
24 * <p>This is a C wrapper around the C++ UnicodeSet class.</p> |
|
25 */ |
|
26 |
|
27 #ifndef __USET_H__ |
|
28 #define __USET_H__ |
|
29 |
|
30 #include "unicode/utypes.h" |
|
31 #include "unicode/uchar.h" |
|
32 |
|
33 #ifndef UCNV_H |
|
34 struct USet; |
|
35 /** |
|
36 * A UnicodeSet. Use the uset_* API to manipulate. Create with |
|
37 * uset_open*, and destroy with uset_close. |
|
38 * @stable ICU 2.4 |
|
39 */ |
|
40 typedef struct USet USet; |
|
41 #endif |
|
42 |
|
43 /** |
|
44 * Bitmask values to be passed to uset_openPatternOptions() or |
|
45 * uset_applyPattern() taking an option parameter. |
|
46 * @stable ICU 2.4 |
|
47 */ |
|
48 enum { |
|
49 /** |
|
50 * Ignore white space within patterns unless quoted or escaped. |
|
51 * @stable ICU 2.4 |
|
52 */ |
|
53 USET_IGNORE_SPACE = 1, |
|
54 |
|
55 /** |
|
56 * Enable case insensitive matching. E.g., "[ab]" with this flag |
|
57 * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will |
|
58 * match all except 'a', 'A', 'b', and 'B'. This performs a full |
|
59 * closure over case mappings, e.g. U+017F for s. |
|
60 * @stable ICU 2.4 |
|
61 */ |
|
62 USET_CASE_INSENSITIVE = 2, |
|
63 |
|
64 /** |
|
65 * Bitmask for UnicodeSet::closeOver() indicating letter case. |
|
66 * This may be ORed together with other selectors. |
|
67 * @internal |
|
68 */ |
|
69 USET_CASE = 2, |
|
70 |
|
71 /** |
|
72 * Enable case insensitive matching. E.g., "[ab]" with this flag |
|
73 * will match 'a', 'A', 'b', and 'B'. "[^ab]" with this flag will |
|
74 * match all except 'a', 'A', 'b', and 'B'. This adds the lower-, |
|
75 * title-, and uppercase mappings as well as the case folding |
|
76 * of each existing element in the set. |
|
77 * @draft ICU 3.2 |
|
78 */ |
|
79 USET_ADD_CASE_MAPPINGS = 4, |
|
80 |
|
81 /** |
|
82 * Enough for any single-code point set |
|
83 * @internal |
|
84 */ |
|
85 USET_SERIALIZED_STATIC_ARRAY_CAPACITY=8 |
|
86 }; |
|
87 |
|
88 /** |
|
89 * A serialized form of a Unicode set. Limited manipulations are |
|
90 * possible directly on a serialized set. See below. |
|
91 * @stable ICU 2.4 |
|
92 */ |
|
93 typedef struct USerializedSet { |
|
94 /** |
|
95 * The serialized Unicode Set. |
|
96 * @stable ICU 2.4 |
|
97 */ |
|
98 const uint16_t *array; |
|
99 /** |
|
100 * The length of the array that contains BMP characters. |
|
101 * @stable ICU 2.4 |
|
102 */ |
|
103 int32_t bmpLength; |
|
104 /** |
|
105 * The total length of the array. |
|
106 * @stable ICU 2.4 |
|
107 */ |
|
108 int32_t length; |
|
109 /** |
|
110 * A small buffer for the array to reduce memory allocations. |
|
111 * @stable ICU 2.4 |
|
112 */ |
|
113 uint16_t staticArray[USET_SERIALIZED_STATIC_ARRAY_CAPACITY]; |
|
114 } USerializedSet; |
|
115 |
|
116 /********************************************************************* |
|
117 * USet API |
|
118 *********************************************************************/ |
|
119 |
|
120 /** |
|
121 * Creates a USet object that contains the range of characters |
|
122 * start..end, inclusive. |
|
123 * @param start first character of the range, inclusive |
|
124 * @param end last character of the range, inclusive |
|
125 * @return a newly created USet. The caller must call uset_close() on |
|
126 * it when done. |
|
127 * @stable ICU 2.4 |
|
128 */ |
|
129 U_STABLE USet* U_EXPORT2 |
|
130 uset_open(UChar32 start, UChar32 end); |
|
131 |
|
132 /** |
|
133 * Creates a set from the given pattern. See the UnicodeSet class |
|
134 * description for the syntax of the pattern language. |
|
135 * @param pattern a string specifying what characters are in the set |
|
136 * @param patternLength the length of the pattern, or -1 if null |
|
137 * terminated |
|
138 * @param ec the error code |
|
139 * @stable ICU 2.4 |
|
140 */ |
|
141 U_STABLE USet* U_EXPORT2 |
|
142 uset_openPattern(const UChar* pattern, int32_t patternLength, |
|
143 UErrorCode* ec); |
|
144 |
|
145 /** |
|
146 * Creates a set from the given pattern. See the UnicodeSet class |
|
147 * description for the syntax of the pattern language. |
|
148 * @param pattern a string specifying what characters are in the set |
|
149 * @param patternLength the length of the pattern, or -1 if null |
|
150 * terminated |
|
151 * @param options bitmask for options to apply to the pattern. |
|
152 * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. |
|
153 * @param ec the error code |
|
154 * @stable ICU 2.4 |
|
155 */ |
|
156 U_STABLE USet* U_EXPORT2 |
|
157 uset_openPatternOptions(const UChar* pattern, int32_t patternLength, |
|
158 uint32_t options, |
|
159 UErrorCode* ec); |
|
160 |
|
161 /** |
|
162 * Disposes of the storage used by a USet object. This function should |
|
163 * be called exactly once for objects returned by uset_open(). |
|
164 * @param set the object to dispose of |
|
165 * @stable ICU 2.4 |
|
166 */ |
|
167 U_STABLE void U_EXPORT2 |
|
168 uset_close(USet* set); |
|
169 |
|
170 /** |
|
171 * Causes the USet object to represent the range <code>start - end</code>. |
|
172 * If <code>start > end</code> then this USet is set to an empty range. |
|
173 * @param set the object to set to the given range |
|
174 * @param start first character in the set, inclusive |
|
175 * @param end last character in the set, inclusive |
|
176 * @draft ICU 3.2 |
|
177 */ |
|
178 U_DRAFT void U_EXPORT2 |
|
179 uset_set(USet* set, |
|
180 UChar32 start, UChar32 end); |
|
181 |
|
182 /** |
|
183 * Modifies the set to represent the set specified by the given |
|
184 * pattern. See the UnicodeSet class description for the syntax of |
|
185 * the pattern language. See also the User Guide chapter about UnicodeSet. |
|
186 * <em>Empties the set passed before applying the pattern.</em> |
|
187 * @param set The set to which the pattern is to be applied. |
|
188 * @param pattern A pointer to UChar string specifying what characters are in the set. |
|
189 * The character at pattern[0] must be a '['. |
|
190 * @param patternLength The length of the UChar string. -1 if NUL terminated. |
|
191 * @param options A bitmask for options to apply to the pattern. |
|
192 * Valid options are USET_IGNORE_SPACE and USET_CASE_INSENSITIVE. |
|
193 * @param status Returns an error if the pattern cannot be parsed. |
|
194 * @return Upon successful parse, the value is either |
|
195 * the index of the character after the closing ']' |
|
196 * of the parsed pattern. |
|
197 * If the status code indicates failure, then the return value |
|
198 * is the index of the error in the source. |
|
199 * |
|
200 * @draft ICU 2.8 |
|
201 */ |
|
202 U_DRAFT int32_t U_EXPORT2 |
|
203 uset_applyPattern(USet *set, |
|
204 const UChar *pattern, int32_t patternLength, |
|
205 uint32_t options, |
|
206 UErrorCode *status); |
|
207 |
|
208 /** |
|
209 * Modifies the set to contain those code points which have the given value |
|
210 * for the given binary or enumerated property, as returned by |
|
211 * u_getIntPropertyValue. Prior contents of this set are lost. |
|
212 * |
|
213 * @param set the object to contain the code points defined by the property |
|
214 * |
|
215 * @param prop a property in the range UCHAR_BIN_START..UCHAR_BIN_LIMIT-1 |
|
216 * or UCHAR_INT_START..UCHAR_INT_LIMIT-1 |
|
217 * or UCHAR_MASK_START..UCHAR_MASK_LIMIT-1. |
|
218 * |
|
219 * @param value a value in the range u_getIntPropertyMinValue(prop).. |
|
220 * u_getIntPropertyMaxValue(prop), with one exception. If prop is |
|
221 * UCHAR_GENERAL_CATEGORY_MASK, then value should not be a UCharCategory, but |
|
222 * rather a mask value produced by U_GET_GC_MASK(). This allows grouped |
|
223 * categories such as [:L:] to be represented. |
|
224 * |
|
225 * @param ec error code input/output parameter |
|
226 * |
|
227 * @draft ICU 3.2 |
|
228 */ |
|
229 U_DRAFT void U_EXPORT2 |
|
230 uset_applyIntPropertyValue(USet* set, |
|
231 UProperty prop, int32_t value, UErrorCode* ec); |
|
232 |
|
233 /** |
|
234 * Modifies the set to contain those code points which have the |
|
235 * given value for the given property. Prior contents of this |
|
236 * set are lost. |
|
237 * |
|
238 * @param set the object to contain the code points defined by the given |
|
239 * property and value alias |
|
240 * |
|
241 * @param prop a string specifying a property alias, either short or long. |
|
242 * The name is matched loosely. See PropertyAliases.txt for names and a |
|
243 * description of loose matching. If the value string is empty, then this |
|
244 * string is interpreted as either a General_Category value alias, a Script |
|
245 * value alias, a binary property alias, or a special ID. Special IDs are |
|
246 * matched loosely and correspond to the following sets: |
|
247 * |
|
248 * "ANY" = [\\u0000-\\U0010FFFF], |
|
249 * "ASCII" = [\\u0000-\\u007F]. |
|
250 * |
|
251 * @param propLength the length of the prop, or -1 if NULL |
|
252 * |
|
253 * @param value a string specifying a value alias, either short or long. |
|
254 * The name is matched loosely. See PropertyValueAliases.txt for names |
|
255 * and a description of loose matching. In addition to aliases listed, |
|
256 * numeric values and canonical combining classes may be expressed |
|
257 * numerically, e.g., ("nv", "0.5") or ("ccc", "220"). The value string |
|
258 * may also be empty. |
|
259 * |
|
260 * @param valueLength the length of the value, or -1 if NULL |
|
261 * |
|
262 * @param ec error code input/output parameter |
|
263 * |
|
264 * @draft ICU 3.2 |
|
265 */ |
|
266 U_DRAFT void U_EXPORT2 |
|
267 uset_applyPropertyAlias(USet* set, |
|
268 const UChar *prop, int32_t propLength, |
|
269 const UChar *value, int32_t valueLength, |
|
270 UErrorCode* ec); |
|
271 |
|
272 /** |
|
273 * Return true if the given position, in the given pattern, appears |
|
274 * to be the start of a UnicodeSet pattern. |
|
275 * |
|
276 * @param pattern a string specifying the pattern |
|
277 * @param patternLength the length of the pattern, or -1 if NULL |
|
278 * @param pos the given position |
|
279 * @draft ICU 3.2 |
|
280 */ |
|
281 U_DRAFT UBool U_EXPORT2 |
|
282 uset_resemblesPattern(const UChar *pattern, int32_t patternLength, |
|
283 int32_t pos); |
|
284 |
|
285 /** |
|
286 * Returns a string representation of this set. If the result of |
|
287 * calling this function is passed to a uset_openPattern(), it |
|
288 * will produce another set that is equal to this one. |
|
289 * @param set the set |
|
290 * @param result the string to receive the rules, may be NULL |
|
291 * @param resultCapacity the capacity of result, may be 0 if result is NULL |
|
292 * @param escapeUnprintable if TRUE then convert unprintable |
|
293 * character to their hex escape representations, \\uxxxx or |
|
294 * \\Uxxxxxxxx. Unprintable characters are those other than |
|
295 * U+000A, U+0020..U+007E. |
|
296 * @param ec error code. |
|
297 * @return length of string, possibly larger than resultCapacity |
|
298 * @stable ICU 2.4 |
|
299 */ |
|
300 U_STABLE int32_t U_EXPORT2 |
|
301 uset_toPattern(const USet* set, |
|
302 UChar* result, int32_t resultCapacity, |
|
303 UBool escapeUnprintable, |
|
304 UErrorCode* ec); |
|
305 |
|
306 /** |
|
307 * Adds the given character to the given USet. After this call, |
|
308 * uset_contains(set, c) will return TRUE. |
|
309 * @param set the object to which to add the character |
|
310 * @param c the character to add |
|
311 * @stable ICU 2.4 |
|
312 */ |
|
313 U_STABLE void U_EXPORT2 |
|
314 uset_add(USet* set, UChar32 c); |
|
315 |
|
316 /** |
|
317 * Adds all of the elements in the specified set to this set if |
|
318 * they're not already present. This operation effectively |
|
319 * modifies this set so that its value is the <i>union</i> of the two |
|
320 * sets. The behavior of this operation is unspecified if the specified |
|
321 * collection is modified while the operation is in progress. |
|
322 * |
|
323 * @param set the object to which to add the set |
|
324 * @param additionalSet the source set whose elements are to be added to this set. |
|
325 * @stable ICU 2.6 |
|
326 */ |
|
327 U_STABLE void U_EXPORT2 |
|
328 uset_addAll(USet* set, const USet *additionalSet); |
|
329 |
|
330 /** |
|
331 * Adds the given range of characters to the given USet. After this call, |
|
332 * uset_contains(set, start, end) will return TRUE. |
|
333 * @param set the object to which to add the character |
|
334 * @param start the first character of the range to add, inclusive |
|
335 * @param end the last character of the range to add, inclusive |
|
336 * @stable ICU 2.2 |
|
337 */ |
|
338 U_STABLE void U_EXPORT2 |
|
339 uset_addRange(USet* set, UChar32 start, UChar32 end); |
|
340 |
|
341 /** |
|
342 * Adds the given string to the given USet. After this call, |
|
343 * uset_containsString(set, str, strLen) will return TRUE. |
|
344 * @param set the object to which to add the character |
|
345 * @param str the string to add |
|
346 * @param strLen the length of the string or -1 if null terminated. |
|
347 * @stable ICU 2.4 |
|
348 */ |
|
349 U_STABLE void U_EXPORT2 |
|
350 uset_addString(USet* set, const UChar* str, int32_t strLen); |
|
351 |
|
352 /** |
|
353 * Removes the given character from the given USet. After this call, |
|
354 * uset_contains(set, c) will return FALSE. |
|
355 * @param set the object from which to remove the character |
|
356 * @param c the character to remove |
|
357 * @stable ICU 2.4 |
|
358 */ |
|
359 U_STABLE void U_EXPORT2 |
|
360 uset_remove(USet* set, UChar32 c); |
|
361 |
|
362 /** |
|
363 * Removes the given range of characters from the given USet. After this call, |
|
364 * uset_contains(set, start, end) will return FALSE. |
|
365 * @param set the object to which to add the character |
|
366 * @param start the first character of the range to remove, inclusive |
|
367 * @param end the last character of the range to remove, inclusive |
|
368 * @stable ICU 2.2 |
|
369 */ |
|
370 U_STABLE void U_EXPORT2 |
|
371 uset_removeRange(USet* set, UChar32 start, UChar32 end); |
|
372 |
|
373 /** |
|
374 * Removes the given string to the given USet. After this call, |
|
375 * uset_containsString(set, str, strLen) will return FALSE. |
|
376 * @param set the object to which to add the character |
|
377 * @param str the string to remove |
|
378 * @param strLen the length of the string or -1 if null terminated. |
|
379 * @stable ICU 2.4 |
|
380 */ |
|
381 U_STABLE void U_EXPORT2 |
|
382 uset_removeString(USet* set, const UChar* str, int32_t strLen); |
|
383 |
|
384 /** |
|
385 * Removes from this set all of its elements that are contained in the |
|
386 * specified set. This operation effectively modifies this |
|
387 * set so that its value is the <i>asymmetric set difference</i> of |
|
388 * the two sets. |
|
389 * @param set the object from which the elements are to be removed |
|
390 * @param removeSet the object that defines which elements will be |
|
391 * removed from this set |
|
392 * @draft ICU 3.2 |
|
393 */ |
|
394 U_DRAFT void U_EXPORT2 |
|
395 uset_removeAll(USet* set, const USet* removeSet); |
|
396 |
|
397 /** |
|
398 * Retain only the elements in this set that are contained in the |
|
399 * specified range. If <code>start > end</code> then an empty range is |
|
400 * retained, leaving the set empty. This is equivalent to |
|
401 * a boolean logic AND, or a set INTERSECTION. |
|
402 * |
|
403 * @param set the object for which to retain only the specified range |
|
404 * @param start first character, inclusive, of range to be retained |
|
405 * to this set. |
|
406 * @param end last character, inclusive, of range to be retained |
|
407 * to this set. |
|
408 * @draft ICU 3.2 |
|
409 */ |
|
410 U_DRAFT void U_EXPORT2 |
|
411 uset_retain(USet* set, UChar32 start, UChar32 end); |
|
412 |
|
413 /** |
|
414 * Retains only the elements in this set that are contained in the |
|
415 * specified set. In other words, removes from this set all of |
|
416 * its elements that are not contained in the specified set. This |
|
417 * operation effectively modifies this set so that its value is |
|
418 * the <i>intersection</i> of the two sets. |
|
419 * |
|
420 * @param set the object on which to perform the retain |
|
421 * @param retain set that defines which elements this set will retain |
|
422 * @draft ICU 3.2 |
|
423 */ |
|
424 U_DRAFT void U_EXPORT2 |
|
425 uset_retainAll(USet* set, const USet* retain); |
|
426 |
|
427 /** |
|
428 * Reallocate this objects internal structures to take up the least |
|
429 * possible space, without changing this object's value. |
|
430 * |
|
431 * @param set the object on which to perfrom the compact |
|
432 * @draft ICU 3.2 |
|
433 */ |
|
434 U_DRAFT void U_EXPORT2 |
|
435 uset_compact(USet* set); |
|
436 |
|
437 /** |
|
438 * Inverts this set. This operation modifies this set so that |
|
439 * its value is its complement. This operation does not affect |
|
440 * the multicharacter strings, if any. |
|
441 * @param set the set |
|
442 * @stable ICU 2.4 |
|
443 */ |
|
444 U_STABLE void U_EXPORT2 |
|
445 uset_complement(USet* set); |
|
446 |
|
447 /** |
|
448 * Complements in this set all elements contained in the specified |
|
449 * set. Any character in the other set will be removed if it is |
|
450 * in this set, or will be added if it is not in this set. |
|
451 * |
|
452 * @param set the set with which to complement |
|
453 * @param complement set that defines which elements will be xor'ed |
|
454 * from this set. |
|
455 * @draft ICU 3.2 |
|
456 */ |
|
457 U_DRAFT void U_EXPORT2 |
|
458 uset_complementAll(USet* set, const USet* complement); |
|
459 |
|
460 /** |
|
461 * Removes all of the elements from this set. This set will be |
|
462 * empty after this call returns. |
|
463 * @param set the set |
|
464 * @stable ICU 2.4 |
|
465 */ |
|
466 U_STABLE void U_EXPORT2 |
|
467 uset_clear(USet* set); |
|
468 |
|
469 /** |
|
470 * Returns TRUE if the given USet contains no characters and no |
|
471 * strings. |
|
472 * @param set the set |
|
473 * @return true if set is empty |
|
474 * @stable ICU 2.4 |
|
475 */ |
|
476 U_STABLE UBool U_EXPORT2 |
|
477 uset_isEmpty(const USet* set); |
|
478 |
|
479 /** |
|
480 * Returns TRUE if the given USet contains the given character. |
|
481 * @param set the set |
|
482 * @param c The codepoint to check for within the set |
|
483 * @return true if set contains c |
|
484 * @stable ICU 2.4 |
|
485 */ |
|
486 U_STABLE UBool U_EXPORT2 |
|
487 uset_contains(const USet* set, UChar32 c); |
|
488 |
|
489 /** |
|
490 * Returns TRUE if the given USet contains all characters c |
|
491 * where start <= c && c <= end. |
|
492 * @param set the set |
|
493 * @param start the first character of the range to test, inclusive |
|
494 * @param end the last character of the range to test, inclusive |
|
495 * @return TRUE if set contains the range |
|
496 * @stable ICU 2.2 |
|
497 */ |
|
498 U_STABLE UBool U_EXPORT2 |
|
499 uset_containsRange(const USet* set, UChar32 start, UChar32 end); |
|
500 |
|
501 /** |
|
502 * Returns TRUE if the given USet contains the given string. |
|
503 * @param set the set |
|
504 * @param str the string |
|
505 * @param strLen the length of the string or -1 if null terminated. |
|
506 * @return true if set contains str |
|
507 * @stable ICU 2.4 |
|
508 */ |
|
509 U_STABLE UBool U_EXPORT2 |
|
510 uset_containsString(const USet* set, const UChar* str, int32_t strLen); |
|
511 |
|
512 /** |
|
513 * Returns the index of the given character within this set, where |
|
514 * the set is ordered by ascending code point. If the character |
|
515 * is not in this set, return -1. The inverse of this method is |
|
516 * <code>charAt()</code>. |
|
517 * @param set the set |
|
518 * @param c the character to obtain the index for |
|
519 * @return an index from 0..size()-1, or -1 |
|
520 * @draft ICU 3.2 |
|
521 */ |
|
522 U_DRAFT int32_t U_EXPORT2 |
|
523 uset_indexOf(const USet* set, UChar32 c); |
|
524 |
|
525 /** |
|
526 * Returns the character at the given index within this set, where |
|
527 * the set is ordered by ascending code point. If the index is |
|
528 * out of range, return (UChar32)-1. The inverse of this method is |
|
529 * <code>indexOf()</code>. |
|
530 * @param set the set |
|
531 * @param index an index from 0..size()-1 to obtain the char for |
|
532 * @return the character at the given index, or (UChar32)-1. |
|
533 * @draft ICU 3.2 |
|
534 */ |
|
535 U_DRAFT UChar32 U_EXPORT2 |
|
536 uset_charAt(const USet* set, int32_t index); |
|
537 |
|
538 /** |
|
539 * Returns the number of characters and strings contained in the given |
|
540 * USet. |
|
541 * @param set the set |
|
542 * @return a non-negative integer counting the characters and strings |
|
543 * contained in set |
|
544 * @stable ICU 2.4 |
|
545 */ |
|
546 U_STABLE int32_t U_EXPORT2 |
|
547 uset_size(const USet* set); |
|
548 |
|
549 /** |
|
550 * Returns the number of items in this set. An item is either a range |
|
551 * of characters or a single multicharacter string. |
|
552 * @param set the set |
|
553 * @return a non-negative integer counting the character ranges |
|
554 * and/or strings contained in set |
|
555 * @stable ICU 2.4 |
|
556 */ |
|
557 U_STABLE int32_t U_EXPORT2 |
|
558 uset_getItemCount(const USet* set); |
|
559 |
|
560 /** |
|
561 * Returns an item of this set. An item is either a range of |
|
562 * characters or a single multicharacter string. |
|
563 * @param set the set |
|
564 * @param itemIndex a non-negative integer in the range 0.. |
|
565 * uset_getItemCount(set)-1 |
|
566 * @param start pointer to variable to receive first character |
|
567 * in range, inclusive |
|
568 * @param end pointer to variable to receive last character in range, |
|
569 * inclusive |
|
570 * @param str buffer to receive the string, may be NULL |
|
571 * @param strCapacity capacity of str, or 0 if str is NULL |
|
572 * @param ec error code |
|
573 * @return the length of the string (>= 2), or 0 if the item is a |
|
574 * range, in which case it is the range *start..*end, or -1 if |
|
575 * itemIndex is out of range |
|
576 * @stable ICU 2.4 |
|
577 */ |
|
578 U_STABLE int32_t U_EXPORT2 |
|
579 uset_getItem(const USet* set, int32_t itemIndex, |
|
580 UChar32* start, UChar32* end, |
|
581 UChar* str, int32_t strCapacity, |
|
582 UErrorCode* ec); |
|
583 |
|
584 /** |
|
585 * Returns true if set1 contains all the characters and strings |
|
586 * of set2. It answers the question, 'Is set1 a subset of set2?' |
|
587 * @param set1 set to be checked for containment |
|
588 * @param set2 set to be checked for containment |
|
589 * @return true if the test condition is met |
|
590 * @draft ICU 3.2 |
|
591 */ |
|
592 U_DRAFT UBool U_EXPORT2 |
|
593 uset_containsAll(const USet* set1, const USet* set2); |
|
594 |
|
595 /** |
|
596 * Returns true if set1 contains none of the characters and strings |
|
597 * of set2. It answers the question, 'Is set1 a disjoint set of set2?' |
|
598 * @param set1 set to be checked for containment |
|
599 * @param set2 set to be checked for containment |
|
600 * @return true if the test condition is met |
|
601 * @draft ICU 3.2 |
|
602 */ |
|
603 U_DRAFT UBool U_EXPORT2 |
|
604 uset_containsNone(const USet* set1, const USet* set2); |
|
605 |
|
606 /** |
|
607 * Returns true if set1 contains some of the characters and strings |
|
608 * of set2. It answers the question, 'Does set1 and set2 have an intersection?' |
|
609 * @param set1 set to be checked for containment |
|
610 * @param set2 set to be checked for containment |
|
611 * @return true if the test condition is met |
|
612 * @draft ICU 3.2 |
|
613 */ |
|
614 U_DRAFT UBool U_EXPORT2 |
|
615 uset_containsSome(const USet* set1, const USet* set2); |
|
616 |
|
617 /** |
|
618 * Returns true if set1 contains all of the characters and strings |
|
619 * of set2, and vis versa. It answers the question, 'Is set1 equal to set2?' |
|
620 * @param set1 set to be checked for containment |
|
621 * @param set2 set to be checked for containment |
|
622 * @return true if the test condition is met |
|
623 * @draft ICU 3.2 |
|
624 */ |
|
625 U_DRAFT UBool U_EXPORT2 |
|
626 uset_equals(const USet* set1, const USet* set2); |
|
627 |
|
628 /********************************************************************* |
|
629 * Serialized set API |
|
630 *********************************************************************/ |
|
631 |
|
632 /** |
|
633 * Serializes this set into an array of 16-bit integers. Serialization |
|
634 * (currently) only records the characters in the set; multicharacter |
|
635 * strings are ignored. |
|
636 * |
|
637 * The array |
|
638 * has following format (each line is one 16-bit integer): |
|
639 * |
|
640 * length = (n+2*m) | (m!=0?0x8000:0) |
|
641 * bmpLength = n; present if m!=0 |
|
642 * bmp[0] |
|
643 * bmp[1] |
|
644 * ... |
|
645 * bmp[n-1] |
|
646 * supp-high[0] |
|
647 * supp-low[0] |
|
648 * supp-high[1] |
|
649 * supp-low[1] |
|
650 * ... |
|
651 * supp-high[m-1] |
|
652 * supp-low[m-1] |
|
653 * |
|
654 * The array starts with a header. After the header are n bmp |
|
655 * code points, then m supplementary code points. Either n or m |
|
656 * or both may be zero. n+2*m is always <= 0x7FFF. |
|
657 * |
|
658 * If there are no supplementary characters (if m==0) then the |
|
659 * header is one 16-bit integer, 'length', with value n. |
|
660 * |
|
661 * If there are supplementary characters (if m!=0) then the header |
|
662 * is two 16-bit integers. The first, 'length', has value |
|
663 * (n+2*m)|0x8000. The second, 'bmpLength', has value n. |
|
664 * |
|
665 * After the header the code points are stored in ascending order. |
|
666 * Supplementary code points are stored as most significant 16 |
|
667 * bits followed by least significant 16 bits. |
|
668 * |
|
669 * @param set the set |
|
670 * @param dest pointer to buffer of destCapacity 16-bit integers. |
|
671 * May be NULL only if destCapacity is zero. |
|
672 * @param destCapacity size of dest, or zero. Must not be negative. |
|
673 * @param pErrorCode pointer to the error code. Will be set to |
|
674 * U_INDEX_OUTOFBOUNDS_ERROR if n+2*m > 0x7FFF. Will be set to |
|
675 * U_BUFFER_OVERFLOW_ERROR if n+2*m+(m!=0?2:1) > destCapacity. |
|
676 * @return the total length of the serialized format, including |
|
677 * the header, that is, n+2*m+(m!=0?2:1), or 0 on error other |
|
678 * than U_BUFFER_OVERFLOW_ERROR. |
|
679 * @stable ICU 2.4 |
|
680 */ |
|
681 U_STABLE int32_t U_EXPORT2 |
|
682 uset_serialize(const USet* set, uint16_t* dest, int32_t destCapacity, UErrorCode* pErrorCode); |
|
683 |
|
684 /** |
|
685 * Given a serialized array, fill in the given serialized set object. |
|
686 * @param fillSet pointer to result |
|
687 * @param src pointer to start of array |
|
688 * @param srcLength length of array |
|
689 * @return true if the given array is valid, otherwise false |
|
690 * @stable ICU 2.4 |
|
691 */ |
|
692 U_STABLE UBool U_EXPORT2 |
|
693 uset_getSerializedSet(USerializedSet* fillSet, const uint16_t* src, int32_t srcLength); |
|
694 |
|
695 /** |
|
696 * Set the USerializedSet to contain the given character (and nothing |
|
697 * else). |
|
698 * @param fillSet pointer to result |
|
699 * @param c The codepoint to set |
|
700 * @stable ICU 2.4 |
|
701 */ |
|
702 U_STABLE void U_EXPORT2 |
|
703 uset_setSerializedToOne(USerializedSet* fillSet, UChar32 c); |
|
704 |
|
705 /** |
|
706 * Returns TRUE if the given USerializedSet contains the given |
|
707 * character. |
|
708 * @param set the serialized set |
|
709 * @param c The codepoint to check for within the set |
|
710 * @return true if set contains c |
|
711 * @stable ICU 2.4 |
|
712 */ |
|
713 U_STABLE UBool U_EXPORT2 |
|
714 uset_serializedContains(const USerializedSet* set, UChar32 c); |
|
715 |
|
716 /** |
|
717 * Returns the number of disjoint ranges of characters contained in |
|
718 * the given serialized set. Ignores any strings contained in the |
|
719 * set. |
|
720 * @param set the serialized set |
|
721 * @return a non-negative integer counting the character ranges |
|
722 * contained in set |
|
723 * @stable ICU 2.4 |
|
724 */ |
|
725 U_STABLE int32_t U_EXPORT2 |
|
726 uset_getSerializedRangeCount(const USerializedSet* set); |
|
727 |
|
728 /** |
|
729 * Returns a range of characters contained in the given serialized |
|
730 * set. |
|
731 * @param set the serialized set |
|
732 * @param rangeIndex a non-negative integer in the range 0.. |
|
733 * uset_getSerializedRangeCount(set)-1 |
|
734 * @param pStart pointer to variable to receive first character |
|
735 * in range, inclusive |
|
736 * @param pEnd pointer to variable to receive last character in range, |
|
737 * inclusive |
|
738 * @return true if rangeIndex is valid, otherwise false |
|
739 * @stable ICU 2.4 |
|
740 */ |
|
741 U_STABLE UBool U_EXPORT2 |
|
742 uset_getSerializedRange(const USerializedSet* set, int32_t rangeIndex, |
|
743 UChar32* pStart, UChar32* pEnd); |
|
744 |
|
745 #endif |