OLD | NEW |
1 /* | 1 /* |
2 ******************************************************************************* | 2 ******************************************************************************* |
3 * Copyright (c) 1996-2010, International Business Machines Corporation | 3 * Copyright (c) 1996-2015, International Business Machines Corporation |
4 * and others. All Rights Reserved. | 4 * and others. All Rights Reserved. |
5 ******************************************************************************* | 5 ******************************************************************************* |
6 * File unorm.h | 6 * File unorm.h |
7 * | 7 * |
8 * Created by: Vladimir Weinstein 12052000 | 8 * Created by: Vladimir Weinstein 12052000 |
9 * | 9 * |
10 * Modification history : | 10 * Modification history : |
11 * | 11 * |
12 * Date Name Description | 12 * Date Name Description |
13 * 02/01/01 synwee Added normalization quickcheck enum and method. | 13 * 02/01/01 synwee Added normalization quickcheck enum and method. |
14 */ | 14 */ |
15 #ifndef UNORM_H | 15 #ifndef UNORM_H |
16 #define UNORM_H | 16 #define UNORM_H |
17 | 17 |
18 #include "unicode/utypes.h" | 18 #include "unicode/utypes.h" |
19 | 19 |
20 #if !UCONFIG_NO_NORMALIZATION | 20 #if !UCONFIG_NO_NORMALIZATION |
21 | 21 |
22 #include "unicode/uiter.h" | 22 #include "unicode/uiter.h" |
23 #include "unicode/unorm2.h" | 23 #include "unicode/unorm2.h" |
24 | 24 |
| 25 #ifndef U_HIDE_DEPRECATED_API |
| 26 |
25 /** | 27 /** |
26 * \file | 28 * \file |
27 * \brief C API: Unicode Normalization | 29 * \brief C API: Unicode Normalization |
28 * | 30 * |
29 * <h2>Unicode normalization API</h2> | 31 * Old Unicode normalization API. |
30 * | 32 * |
31 * Note: This API has been replaced by the unorm2.h API and is only available | 33 * This API has been replaced by the unorm2.h API and is only available |
32 * for backward compatibility. The functions here simply delegate to the | 34 * for backward compatibility. The functions here simply delegate to the |
33 * unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize(). | 35 * unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize(). |
34 * There is one exception: The new API does not provide a replacement for unorm_
compare(). | 36 * There is one exception: The new API does not provide a replacement for unorm_
compare(). |
| 37 * Its declaration has been moved to unorm2.h. |
35 * | 38 * |
36 * <code>unorm_normalize</code> transforms Unicode text into an equivalent compo
sed or | 39 * <code>unorm_normalize</code> transforms Unicode text into an equivalent compo
sed or |
37 * decomposed form, allowing for easier sorting and searching of text. | 40 * decomposed form, allowing for easier sorting and searching of text. |
38 * <code>unorm_normalize</code> supports the standard normalization forms descri
bed in | 41 * <code>unorm_normalize</code> supports the standard normalization forms descri
bed in |
39 * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> | 42 * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> |
40 * Unicode Standard Annex #15: Unicode Normalization Forms</a>. | 43 * Unicode Standard Annex #15: Unicode Normalization Forms</a>. |
41 * | 44 * |
42 * Characters with accents or other adornments can be encoded in | 45 * Characters with accents or other adornments can be encoded in |
43 * several different ways in Unicode. For example, take the character A-acute. | 46 * several different ways in Unicode. For example, take the character A-acute. |
44 * In Unicode, this can be encoded as a single character (the | 47 * In Unicode, this can be encoded as a single character (the |
(...skipping 74 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
119 * Beyond collation and string search, normalized strings may be useful for stri
ng equivalence comparisons, | 122 * Beyond collation and string search, normalized strings may be useful for stri
ng equivalence comparisons, |
120 * transliteration/transcription, unique representations, etc. | 123 * transliteration/transcription, unique representations, etc. |
121 * | 124 * |
122 * The W3C generally recommends to exchange texts in NFC. | 125 * The W3C generally recommends to exchange texts in NFC. |
123 * Note also that most legacy character encodings use only precomposed forms and
often do not | 126 * Note also that most legacy character encodings use only precomposed forms and
often do not |
124 * encode any combining marks by themselves. For conversion to such character en
codings the | 127 * encode any combining marks by themselves. For conversion to such character en
codings the |
125 * Unicode text needs to be normalized to NFC. | 128 * Unicode text needs to be normalized to NFC. |
126 * For more usage examples, see the Unicode Standard Annex. | 129 * For more usage examples, see the Unicode Standard Annex. |
127 */ | 130 */ |
128 | 131 |
| 132 #ifndef U_HIDE_DEPRECATED_API |
129 /** | 133 /** |
130 * Constants for normalization modes. | 134 * Constants for normalization modes. |
131 * @stable ICU 2.0 | 135 * @deprecated ICU 56 Use unorm2.h instead. |
132 */ | 136 */ |
133 typedef enum { | 137 typedef enum { |
134 /** No decomposition/composition. @stable ICU 2.0 */ | 138 /** No decomposition/composition. @deprecated ICU 56 Use unorm2.h instead. */ |
135 UNORM_NONE = 1, | 139 UNORM_NONE = 1, |
136 /** Canonical decomposition. @stable ICU 2.0 */ | 140 /** Canonical decomposition. @deprecated ICU 56 Use unorm2.h instead. */ |
137 UNORM_NFD = 2, | 141 UNORM_NFD = 2, |
138 /** Compatibility decomposition. @stable ICU 2.0 */ | 142 /** Compatibility decomposition. @deprecated ICU 56 Use unorm2.h instead. */ |
139 UNORM_NFKD = 3, | 143 UNORM_NFKD = 3, |
140 /** Canonical decomposition followed by canonical composition. @stable ICU 2.0
*/ | 144 /** Canonical decomposition followed by canonical composition. @deprecated ICU
56 Use unorm2.h instead. */ |
141 UNORM_NFC = 4, | 145 UNORM_NFC = 4, |
142 /** Default normalization. @stable ICU 2.0 */ | 146 /** Default normalization. @deprecated ICU 56 Use unorm2.h instead. */ |
143 UNORM_DEFAULT = UNORM_NFC, | 147 UNORM_DEFAULT = UNORM_NFC, |
144 /** Compatibility decomposition followed by canonical composition. @stable ICU
2.0 */ | 148 /** Compatibility decomposition followed by canonical composition. @deprecated
ICU 56 Use unorm2.h instead. */ |
145 UNORM_NFKC =5, | 149 UNORM_NFKC =5, |
146 /** "Fast C or D" form. @stable ICU 2.0 */ | 150 /** "Fast C or D" form. @deprecated ICU 56 Use unorm2.h instead. */ |
147 UNORM_FCD = 6, | 151 UNORM_FCD = 6, |
148 | 152 |
149 /** One more than the highest normalization mode constant. @stable ICU 2.0 */ | 153 /** One more than the highest normalization mode constant. @deprecated ICU 56
Use unorm2.h instead. */ |
150 UNORM_MODE_COUNT | 154 UNORM_MODE_COUNT |
151 } UNormalizationMode; | 155 } UNormalizationMode; |
| 156 #endif /* U_HIDE_DEPRECATED_API */ |
152 | 157 |
153 /** | 158 /** |
154 * Constants for options flags for normalization. | 159 * Constants for options flags for normalization. |
155 * Use 0 for default options, | 160 * Use 0 for default options, |
156 * including normalization according to the Unicode version | 161 * including normalization according to the Unicode version |
157 * that is currently supported by ICU (see u_getUnicodeVersion). | 162 * that is currently supported by ICU (see u_getUnicodeVersion). |
158 * @stable ICU 2.6 | 163 * @deprecated ICU 56 Use unorm2.h instead. |
159 */ | 164 */ |
160 enum { | 165 enum { |
161 /** | 166 /** |
162 * Options bit set value to select Unicode 3.2 normalization | 167 * Options bit set value to select Unicode 3.2 normalization |
163 * (except NormalizationCorrections). | 168 * (except NormalizationCorrections). |
164 * At most one Unicode version can be selected at a time. | 169 * At most one Unicode version can be selected at a time. |
165 * @stable ICU 2.6 | 170 * @deprecated ICU 56 Use unorm2.h instead. |
166 */ | 171 */ |
167 UNORM_UNICODE_3_2=0x20 | 172 UNORM_UNICODE_3_2=0x20 |
168 }; | 173 }; |
169 | 174 |
170 /** | 175 /** |
171 * Lowest-order bit number of unorm_compare() options bits corresponding to | 176 * Lowest-order bit number of unorm_compare() options bits corresponding to |
172 * normalization options bits. | 177 * normalization options bits. |
173 * | 178 * |
174 * The options parameter for unorm_compare() uses most bits for | 179 * The options parameter for unorm_compare() uses most bits for |
175 * itself and for various comparison and folding flags. | 180 * itself and for various comparison and folding flags. |
176 * The most significant bits, however, are shifted down and passed on | 181 * The most significant bits, however, are shifted down and passed on |
177 * to the normalization implementation. | 182 * to the normalization implementation. |
178 * (That is, from unorm_compare(..., options, ...), | 183 * (That is, from unorm_compare(..., options, ...), |
179 * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the | 184 * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the |
180 * internal normalization functions.) | 185 * internal normalization functions.) |
181 * | 186 * |
182 * @see unorm_compare | 187 * @see unorm_compare |
183 * @stable ICU 2.6 | 188 * @deprecated ICU 56 Use unorm2.h instead. |
184 */ | 189 */ |
185 #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 | 190 #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 |
186 | 191 |
187 /** | 192 /** |
188 * Normalize a string. | 193 * Normalize a string. |
189 * The string will be normalized according the specified normalization mode | 194 * The string will be normalized according the specified normalization mode |
190 * and options. | 195 * and options. |
191 * The source and result buffers must not be the same, nor overlap. | 196 * The source and result buffers must not be the same, nor overlap. |
192 * | 197 * |
193 * @param source The string to normalize. | 198 * @param source The string to normalize. |
194 * @param sourceLength The length of source, or -1 if NUL-terminated. | 199 * @param sourceLength The length of source, or -1 if NUL-terminated. |
195 * @param mode The normalization mode; one of UNORM_NONE, | 200 * @param mode The normalization mode; one of UNORM_NONE, |
196 * UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT. | 201 * UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT. |
197 * @param options The normalization options, ORed together (0 for no options). | 202 * @param options The normalization options, ORed together (0 for no options). |
198 * @param result A pointer to a buffer to receive the result string. | 203 * @param result A pointer to a buffer to receive the result string. |
199 * The result string is NUL-terminated if possible. | 204 * The result string is NUL-terminated if possible. |
200 * @param resultLength The maximum size of result. | 205 * @param resultLength The maximum size of result. |
201 * @param status A pointer to a UErrorCode to receive any errors. | 206 * @param status A pointer to a UErrorCode to receive any errors. |
202 * @return The total buffer size needed; if greater than resultLength, | 207 * @return The total buffer size needed; if greater than resultLength, |
203 * the output was truncated, and the error code is set to U_BUFFER_OVERF
LOW_ERROR. | 208 * the output was truncated, and the error code is set to U_BUFFER_OVERF
LOW_ERROR. |
204 * @stable ICU 2.0 | 209 * @deprecated ICU 56 Use unorm2.h instead. |
205 */ | 210 */ |
206 U_STABLE int32_t U_EXPORT2 | 211 U_STABLE int32_t U_EXPORT2 |
207 unorm_normalize(const UChar *source, int32_t sourceLength, | 212 unorm_normalize(const UChar *source, int32_t sourceLength, |
208 UNormalizationMode mode, int32_t options, | 213 UNormalizationMode mode, int32_t options, |
209 UChar *result, int32_t resultLength, | 214 UChar *result, int32_t resultLength, |
210 UErrorCode *status); | 215 UErrorCode *status); |
211 | 216 |
212 /** | 217 /** |
213 * Performing quick check on a string, to quickly determine if the string is | 218 * Performing quick check on a string, to quickly determine if the string is |
214 * in a particular normalization format. | 219 * in a particular normalization format. |
215 * Three types of result can be returned UNORM_YES, UNORM_NO or | 220 * Three types of result can be returned UNORM_YES, UNORM_NO or |
216 * UNORM_MAYBE. Result UNORM_YES indicates that the argument | 221 * UNORM_MAYBE. Result UNORM_YES indicates that the argument |
217 * string is in the desired normalized format, UNORM_NO determines that | 222 * string is in the desired normalized format, UNORM_NO determines that |
218 * argument string is not in the desired normalized format. A | 223 * argument string is not in the desired normalized format. A |
219 * UNORM_MAYBE result indicates that a more thorough check is required, | 224 * UNORM_MAYBE result indicates that a more thorough check is required, |
220 * the user may have to put the string in its normalized form and compare the | 225 * the user may have to put the string in its normalized form and compare the |
221 * results. | 226 * results. |
222 * | 227 * |
223 * @param source string for determining if it is in a normalized format | 228 * @param source string for determining if it is in a normalized format |
224 * @param sourcelength length of source to test, or -1 if NUL-terminated | 229 * @param sourcelength length of source to test, or -1 if NUL-terminated |
225 * @param mode which normalization form to test for | 230 * @param mode which normalization form to test for |
226 * @param status a pointer to a UErrorCode to receive any errors | 231 * @param status a pointer to a UErrorCode to receive any errors |
227 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE | 232 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE |
228 * | 233 * |
229 * @see unorm_isNormalized | 234 * @see unorm_isNormalized |
230 * @stable ICU 2.0 | 235 * @deprecated ICU 56 Use unorm2.h instead. |
231 */ | 236 */ |
232 U_STABLE UNormalizationCheckResult U_EXPORT2 | 237 U_STABLE UNormalizationCheckResult U_EXPORT2 |
233 unorm_quickCheck(const UChar *source, int32_t sourcelength, | 238 unorm_quickCheck(const UChar *source, int32_t sourcelength, |
234 UNormalizationMode mode, | 239 UNormalizationMode mode, |
235 UErrorCode *status); | 240 UErrorCode *status); |
236 | 241 |
237 /** | 242 /** |
238 * Performing quick check on a string; same as unorm_quickCheck but | 243 * Performing quick check on a string; same as unorm_quickCheck but |
239 * takes an extra options parameter like most normalization functions. | 244 * takes an extra options parameter like most normalization functions. |
240 * | 245 * |
241 * @param src String that is to be tested if it is in a normalization for
mat. | 246 * @param src String that is to be tested if it is in a normalization for
mat. |
242 * @param srcLength Length of source to test, or -1 if NUL-terminated. | 247 * @param srcLength Length of source to test, or -1 if NUL-terminated. |
243 * @param mode Which normalization form to test for. | 248 * @param mode Which normalization form to test for. |
244 * @param options The normalization options, ORed together (0 for no options)
. | 249 * @param options The normalization options, ORed together (0 for no options)
. |
245 * @param pErrorCode ICU error code in/out parameter. | 250 * @param pErrorCode ICU error code in/out parameter. |
246 * Must fulfill U_SUCCESS before the function call. | 251 * Must fulfill U_SUCCESS before the function call. |
247 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE | 252 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE |
248 * | 253 * |
249 * @see unorm_quickCheck | 254 * @see unorm_quickCheck |
250 * @see unorm_isNormalized | 255 * @see unorm_isNormalized |
251 * @stable ICU 2.6 | 256 * @deprecated ICU 56 Use unorm2.h instead. |
252 */ | 257 */ |
253 U_STABLE UNormalizationCheckResult U_EXPORT2 | 258 U_STABLE UNormalizationCheckResult U_EXPORT2 |
254 unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength, | 259 unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength, |
255 UNormalizationMode mode, int32_t options, | 260 UNormalizationMode mode, int32_t options, |
256 UErrorCode *pErrorCode); | 261 UErrorCode *pErrorCode); |
257 | 262 |
258 /** | 263 /** |
259 * Test if a string is in a given normalization form. | 264 * Test if a string is in a given normalization form. |
260 * This is semantically equivalent to source.equals(normalize(source, mode)) . | 265 * This is semantically equivalent to source.equals(normalize(source, mode)) . |
261 * | 266 * |
262 * Unlike unorm_quickCheck(), this function returns a definitive result, | 267 * Unlike unorm_quickCheck(), this function returns a definitive result, |
263 * never a "maybe". | 268 * never a "maybe". |
264 * For NFD, NFKD, and FCD, both functions work exactly the same. | 269 * For NFD, NFKD, and FCD, both functions work exactly the same. |
265 * For NFC and NFKC where quickCheck may return "maybe", this function will | 270 * For NFC and NFKC where quickCheck may return "maybe", this function will |
266 * perform further tests to arrive at a TRUE/FALSE result. | 271 * perform further tests to arrive at a TRUE/FALSE result. |
267 * | 272 * |
268 * @param src String that is to be tested if it is in a normalization for
mat. | 273 * @param src String that is to be tested if it is in a normalization for
mat. |
269 * @param srcLength Length of source to test, or -1 if NUL-terminated. | 274 * @param srcLength Length of source to test, or -1 if NUL-terminated. |
270 * @param mode Which normalization form to test for. | 275 * @param mode Which normalization form to test for. |
271 * @param pErrorCode ICU error code in/out parameter. | 276 * @param pErrorCode ICU error code in/out parameter. |
272 * Must fulfill U_SUCCESS before the function call. | 277 * Must fulfill U_SUCCESS before the function call. |
273 * @return Boolean value indicating whether the source string is in the | 278 * @return Boolean value indicating whether the source string is in the |
274 * "mode" normalization form. | 279 * "mode" normalization form. |
275 * | 280 * |
276 * @see unorm_quickCheck | 281 * @see unorm_quickCheck |
277 * @stable ICU 2.2 | 282 * @deprecated ICU 56 Use unorm2.h instead. |
278 */ | 283 */ |
279 U_STABLE UBool U_EXPORT2 | 284 U_STABLE UBool U_EXPORT2 |
280 unorm_isNormalized(const UChar *src, int32_t srcLength, | 285 unorm_isNormalized(const UChar *src, int32_t srcLength, |
281 UNormalizationMode mode, | 286 UNormalizationMode mode, |
282 UErrorCode *pErrorCode); | 287 UErrorCode *pErrorCode); |
283 | 288 |
284 /** | 289 /** |
285 * Test if a string is in a given normalization form; same as unorm_isNormalized
but | 290 * Test if a string is in a given normalization form; same as unorm_isNormalized
but |
286 * takes an extra options parameter like most normalization functions. | 291 * takes an extra options parameter like most normalization functions. |
287 * | 292 * |
288 * @param src String that is to be tested if it is in a normalization for
mat. | 293 * @param src String that is to be tested if it is in a normalization for
mat. |
289 * @param srcLength Length of source to test, or -1 if NUL-terminated. | 294 * @param srcLength Length of source to test, or -1 if NUL-terminated. |
290 * @param mode Which normalization form to test for. | 295 * @param mode Which normalization form to test for. |
291 * @param options The normalization options, ORed together (0 for no options)
. | 296 * @param options The normalization options, ORed together (0 for no options)
. |
292 * @param pErrorCode ICU error code in/out parameter. | 297 * @param pErrorCode ICU error code in/out parameter. |
293 * Must fulfill U_SUCCESS before the function call. | 298 * Must fulfill U_SUCCESS before the function call. |
294 * @return Boolean value indicating whether the source string is in the | 299 * @return Boolean value indicating whether the source string is in the |
295 * "mode/options" normalization form. | 300 * "mode/options" normalization form. |
296 * | 301 * |
297 * @see unorm_quickCheck | 302 * @see unorm_quickCheck |
298 * @see unorm_isNormalized | 303 * @see unorm_isNormalized |
299 * @stable ICU 2.6 | 304 * @deprecated ICU 56 Use unorm2.h instead. |
300 */ | 305 */ |
301 U_STABLE UBool U_EXPORT2 | 306 U_STABLE UBool U_EXPORT2 |
302 unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength, | 307 unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength, |
303 UNormalizationMode mode, int32_t options, | 308 UNormalizationMode mode, int32_t options, |
304 UErrorCode *pErrorCode); | 309 UErrorCode *pErrorCode); |
305 | 310 |
306 /** | 311 /** |
307 * Iterative normalization forward. | 312 * Iterative normalization forward. |
308 * This function (together with unorm_previous) is somewhat | 313 * This function (together with unorm_previous) is somewhat |
309 * similar to the C++ Normalizer class (see its non-static functions). | 314 * similar to the C++ Normalizer class (see its non-static functions). |
(...skipping 57 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
367 * different text from the input. | 372 * different text from the input. |
368 * Not defined if an error occurs including buffer ove
rflow. | 373 * Not defined if an error occurs including buffer ove
rflow. |
369 * Always FALSE if !doNormalize. | 374 * Always FALSE if !doNormalize. |
370 * @param pErrorCode ICU error code in/out parameter. | 375 * @param pErrorCode ICU error code in/out parameter. |
371 * Must fulfill U_SUCCESS before the function call. | 376 * Must fulfill U_SUCCESS before the function call. |
372 * @return Length of output (number of UChars) when successful or buffer overflo
w. | 377 * @return Length of output (number of UChars) when successful or buffer overflo
w. |
373 * | 378 * |
374 * @see unorm_previous | 379 * @see unorm_previous |
375 * @see unorm_normalize | 380 * @see unorm_normalize |
376 * | 381 * |
377 * @stable ICU 2.1 | 382 * @deprecated ICU 56 Use unorm2.h instead. |
378 */ | 383 */ |
379 U_STABLE int32_t U_EXPORT2 | 384 U_STABLE int32_t U_EXPORT2 |
380 unorm_next(UCharIterator *src, | 385 unorm_next(UCharIterator *src, |
381 UChar *dest, int32_t destCapacity, | 386 UChar *dest, int32_t destCapacity, |
382 UNormalizationMode mode, int32_t options, | 387 UNormalizationMode mode, int32_t options, |
383 UBool doNormalize, UBool *pNeededToNormalize, | 388 UBool doNormalize, UBool *pNeededToNormalize, |
384 UErrorCode *pErrorCode); | 389 UErrorCode *pErrorCode); |
385 | 390 |
386 /** | 391 /** |
387 * Iterative normalization backward. | 392 * Iterative normalization backward. |
(...skipping 12 matching lines...) Expand all Loading... |
400 * different text from the input. | 405 * different text from the input. |
401 * Not defined if an error occurs including buffer ove
rflow. | 406 * Not defined if an error occurs including buffer ove
rflow. |
402 * Always FALSE if !doNormalize. | 407 * Always FALSE if !doNormalize. |
403 * @param pErrorCode ICU error code in/out parameter. | 408 * @param pErrorCode ICU error code in/out parameter. |
404 * Must fulfill U_SUCCESS before the function call. | 409 * Must fulfill U_SUCCESS before the function call. |
405 * @return Length of output (number of UChars) when successful or buffer overflo
w. | 410 * @return Length of output (number of UChars) when successful or buffer overflo
w. |
406 * | 411 * |
407 * @see unorm_next | 412 * @see unorm_next |
408 * @see unorm_normalize | 413 * @see unorm_normalize |
409 * | 414 * |
410 * @stable ICU 2.1 | 415 * @deprecated ICU 56 Use unorm2.h instead. |
411 */ | 416 */ |
412 U_STABLE int32_t U_EXPORT2 | 417 U_STABLE int32_t U_EXPORT2 |
413 unorm_previous(UCharIterator *src, | 418 unorm_previous(UCharIterator *src, |
414 UChar *dest, int32_t destCapacity, | 419 UChar *dest, int32_t destCapacity, |
415 UNormalizationMode mode, int32_t options, | 420 UNormalizationMode mode, int32_t options, |
416 UBool doNormalize, UBool *pNeededToNormalize, | 421 UBool doNormalize, UBool *pNeededToNormalize, |
417 UErrorCode *pErrorCode); | 422 UErrorCode *pErrorCode); |
418 | 423 |
419 /** | 424 /** |
420 * Concatenate normalized strings, making sure that the result is normalized as
well. | 425 * Concatenate normalized strings, making sure that the result is normalized as
well. |
(...skipping 23 matching lines...) Expand all Loading... |
444 * @param mode The normalization mode. | 449 * @param mode The normalization mode. |
445 * @param options The normalization options, ORed together (0 for no options). | 450 * @param options The normalization options, ORed together (0 for no options). |
446 * @param pErrorCode ICU error code in/out parameter. | 451 * @param pErrorCode ICU error code in/out parameter. |
447 * Must fulfill U_SUCCESS before the function call. | 452 * Must fulfill U_SUCCESS before the function call. |
448 * @return Length of output (number of UChars) when successful or buffer overflo
w. | 453 * @return Length of output (number of UChars) when successful or buffer overflo
w. |
449 * | 454 * |
450 * @see unorm_normalize | 455 * @see unorm_normalize |
451 * @see unorm_next | 456 * @see unorm_next |
452 * @see unorm_previous | 457 * @see unorm_previous |
453 * | 458 * |
454 * @stable ICU 2.1 | 459 * @deprecated ICU 56 Use unorm2.h instead. |
455 */ | 460 */ |
456 U_STABLE int32_t U_EXPORT2 | 461 U_STABLE int32_t U_EXPORT2 |
457 unorm_concatenate(const UChar *left, int32_t leftLength, | 462 unorm_concatenate(const UChar *left, int32_t leftLength, |
458 const UChar *right, int32_t rightLength, | 463 const UChar *right, int32_t rightLength, |
459 UChar *dest, int32_t destCapacity, | 464 UChar *dest, int32_t destCapacity, |
460 UNormalizationMode mode, int32_t options, | 465 UNormalizationMode mode, int32_t options, |
461 UErrorCode *pErrorCode); | 466 UErrorCode *pErrorCode); |
462 | 467 |
463 /** | 468 #endif /* U_HIDE_DEPRECATED_API */ |
464 * Option bit for unorm_compare: | 469 #endif /* #if !UCONFIG_NO_NORMALIZATION */ |
465 * Both input strings are assumed to fulfill FCD conditions. | |
466 * @stable ICU 2.2 | |
467 */ | |
468 #define UNORM_INPUT_IS_FCD 0x20000 | |
469 | |
470 /** | |
471 * Option bit for unorm_compare: | |
472 * Perform case-insensitive comparison. | |
473 * @stable ICU 2.2 | |
474 */ | |
475 #define U_COMPARE_IGNORE_CASE 0x10000 | |
476 | |
477 #ifndef U_COMPARE_CODE_POINT_ORDER | |
478 /* see also unistr.h and ustring.h */ | |
479 /** | |
480 * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: | |
481 * Compare strings in code point order instead of code unit order. | |
482 * @stable ICU 2.2 | |
483 */ | |
484 #define U_COMPARE_CODE_POINT_ORDER 0x8000 | |
485 #endif | 470 #endif |
486 | |
487 /** | |
488 * Compare two strings for canonical equivalence. | |
489 * Further options include case-insensitive comparison and | |
490 * code point order (as opposed to code unit order). | |
491 * | |
492 * Canonical equivalence between two strings is defined as their normalized | |
493 * forms (NFD or NFC) being identical. | |
494 * This function compares strings incrementally instead of normalizing | |
495 * (and optionally case-folding) both strings entirely, | |
496 * improving performance significantly. | |
497 * | |
498 * Bulk normalization is only necessary if the strings do not fulfill the FCD | |
499 * conditions. Only in this case, and only if the strings are relatively long, | |
500 * is memory allocated temporarily. | |
501 * For FCD strings and short non-FCD strings there is no memory allocation. | |
502 * | |
503 * Semantically, this is equivalent to | |
504 * strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2)))) | |
505 * where code point order and foldCase are all optional. | |
506 * | |
507 * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match | |
508 * the case folding must be performed first, then the normalization. | |
509 * | |
510 * @param s1 First source string. | |
511 * @param length1 Length of first source string, or -1 if NUL-terminated. | |
512 * | |
513 * @param s2 Second source string. | |
514 * @param length2 Length of second source string, or -1 if NUL-terminated. | |
515 * | |
516 * @param options A bit set of options: | |
517 * - U_FOLD_CASE_DEFAULT or 0 is used for default options: | |
518 * Case-sensitive comparison in code unit order, and the input strings | |
519 * are quick-checked for FCD. | |
520 * | |
521 * - UNORM_INPUT_IS_FCD | |
522 * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. | |
523 * If not set, the function will quickCheck for FCD | |
524 * and normalize if necessary. | |
525 * | |
526 * - U_COMPARE_CODE_POINT_ORDER | |
527 * Set to choose code point order instead of code unit order | |
528 * (see u_strCompare for details). | |
529 * | |
530 * - U_COMPARE_IGNORE_CASE | |
531 * Set to compare strings case-insensitively using case folding, | |
532 * instead of case-sensitively. | |
533 * If set, then the following case folding options are used. | |
534 * | |
535 * - Options as used with case-insensitive comparisons, currently: | |
536 * | |
537 * - U_FOLD_CASE_EXCLUDE_SPECIAL_I | |
538 * (see u_strCaseCompare for details) | |
539 * | |
540 * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_
SHIFT | |
541 * | |
542 * @param pErrorCode ICU error code in/out parameter. | |
543 * Must fulfill U_SUCCESS before the function call. | |
544 * @return <0 or 0 or >0 as usual for string comparisons | |
545 * | |
546 * @see unorm_normalize | |
547 * @see UNORM_FCD | |
548 * @see u_strCompare | |
549 * @see u_strCaseCompare | |
550 * | |
551 * @stable ICU 2.2 | |
552 */ | |
553 U_STABLE int32_t U_EXPORT2 | |
554 unorm_compare(const UChar *s1, int32_t length1, | |
555 const UChar *s2, int32_t length2, | |
556 uint32_t options, | |
557 UErrorCode *pErrorCode); | |
558 | |
559 #endif /* #if !UCONFIG_NO_NORMALIZATION */ | |
560 | |
561 #endif | |
OLD | NEW |