| 1 | // © 2016 and later: Unicode, Inc. and others. | 
|---|
| 2 | // License & terms of use: http://www.unicode.org/copyright.html | 
|---|
| 3 | /* | 
|---|
| 4 | ******************************************************************************* | 
|---|
| 5 | *   Copyright (C) 1997-2011,2014-2015 International Business Machines | 
|---|
| 6 | *   Corporation and others.  All Rights Reserved. | 
|---|
| 7 | ******************************************************************************* | 
|---|
| 8 | *   Date        Name        Description | 
|---|
| 9 | *   06/21/00    aliu        Creation. | 
|---|
| 10 | ******************************************************************************* | 
|---|
| 11 | */ | 
|---|
| 12 |  | 
|---|
| 13 | #ifndef UTRANS_H | 
|---|
| 14 | #define UTRANS_H | 
|---|
| 15 |  | 
|---|
| 16 | #include "unicode/utypes.h" | 
|---|
| 17 |  | 
|---|
| 18 | #if !UCONFIG_NO_TRANSLITERATION | 
|---|
| 19 |  | 
|---|
| 20 | #include "unicode/localpointer.h" | 
|---|
| 21 | #include "unicode/urep.h" | 
|---|
| 22 | #include "unicode/parseerr.h" | 
|---|
| 23 | #include "unicode/uenum.h" | 
|---|
| 24 | #include "unicode/uset.h" | 
|---|
| 25 |  | 
|---|
| 26 | /******************************************************************** | 
|---|
| 27 | * General Notes | 
|---|
| 28 | ******************************************************************** | 
|---|
| 29 | */ | 
|---|
| 30 | /** | 
|---|
| 31 | * \file | 
|---|
| 32 | * \brief C API: Transliterator | 
|---|
| 33 | * | 
|---|
| 34 | * <h2> Transliteration </h2> | 
|---|
| 35 | * The data structures and functions described in this header provide | 
|---|
| 36 | * transliteration services.  Transliteration services are implemented | 
|---|
| 37 | * as C++ classes.  The comments and documentation in this header | 
|---|
| 38 | * assume the reader is familiar with the C++ headers translit.h and | 
|---|
| 39 | * associated documentation. | 
|---|
| 40 | * | 
|---|
| 41 | * A significant but incomplete subset of the C++ transliteration | 
|---|
| 42 | * services are available to C code through this header.  In order to | 
|---|
| 43 | * access more complex transliteration services, refer to the C++ | 
|---|
| 44 | * headers and documentation. | 
|---|
| 45 | * | 
|---|
| 46 | * There are two sets of functions for working with transliterator IDs: | 
|---|
| 47 | * | 
|---|
| 48 | * An old, deprecated set uses char * IDs, which works for true and pure | 
|---|
| 49 | * identifiers that these APIs were designed for, | 
|---|
| 50 | * for example "Cyrillic-Latin". | 
|---|
| 51 | * It does not work when the ID contains filters ("[:Script=Cyrl:]") | 
|---|
| 52 | * or even a complete set of rules because then the ID string contains more | 
|---|
| 53 | * than just "invariant" characters (see utypes.h). | 
|---|
| 54 | * | 
|---|
| 55 | * A new set of functions replaces the old ones and uses UChar * IDs, | 
|---|
| 56 | * paralleling the UnicodeString IDs in the C++ API. (New in ICU 2.8.) | 
|---|
| 57 | */ | 
|---|
| 58 |  | 
|---|
| 59 | /******************************************************************** | 
|---|
| 60 | * Data Structures | 
|---|
| 61 | ********************************************************************/ | 
|---|
| 62 |  | 
|---|
| 63 | /** | 
|---|
| 64 | * An opaque transliterator for use in C.  Open with utrans_openxxx() | 
|---|
| 65 | * and close with utrans_close() when done.  Equivalent to the C++ class | 
|---|
| 66 | * Transliterator and its subclasses. | 
|---|
| 67 | * @see Transliterator | 
|---|
| 68 | * @stable ICU 2.0 | 
|---|
| 69 | */ | 
|---|
| 70 | typedef void* UTransliterator; | 
|---|
| 71 |  | 
|---|
| 72 | /** | 
|---|
| 73 | * Direction constant indicating the direction in a transliterator, | 
|---|
| 74 | * e.g., the forward or reverse rules of a RuleBasedTransliterator. | 
|---|
| 75 | * Specified when a transliterator is opened.  An "A-B" transliterator | 
|---|
| 76 | * transliterates A to B when operating in the forward direction, and | 
|---|
| 77 | * B to A when operating in the reverse direction. | 
|---|
| 78 | * @stable ICU 2.0 | 
|---|
| 79 | */ | 
|---|
| 80 | typedef enum UTransDirection { | 
|---|
| 81 |  | 
|---|
| 82 | /** | 
|---|
| 83 | * UTRANS_FORWARD means from <source> to <target> for a | 
|---|
| 84 | * transliterator with ID <source>-<target>.  For a transliterator | 
|---|
| 85 | * opened using a rule, it means forward direction rules, e.g., | 
|---|
| 86 | * "A > B". | 
|---|
| 87 | */ | 
|---|
| 88 | UTRANS_FORWARD, | 
|---|
| 89 |  | 
|---|
| 90 | /** | 
|---|
| 91 | * UTRANS_REVERSE means from <target> to <source> for a | 
|---|
| 92 | * transliterator with ID <source>-<target>.  For a transliterator | 
|---|
| 93 | * opened using a rule, it means reverse direction rules, e.g., | 
|---|
| 94 | * "A < B". | 
|---|
| 95 | */ | 
|---|
| 96 | UTRANS_REVERSE | 
|---|
| 97 |  | 
|---|
| 98 | } UTransDirection; | 
|---|
| 99 |  | 
|---|
| 100 | /** | 
|---|
| 101 | * Position structure for utrans_transIncremental() incremental | 
|---|
| 102 | * transliteration.  This structure defines two substrings of the text | 
|---|
| 103 | * being transliterated.  The first region, [contextStart, | 
|---|
| 104 | * contextLimit), defines what characters the transliterator will read | 
|---|
| 105 | * as context.  The second region, [start, limit), defines what | 
|---|
| 106 | * characters will actually be transliterated.  The second region | 
|---|
| 107 | * should be a subset of the first. | 
|---|
| 108 | * | 
|---|
| 109 | * <p>After a transliteration operation, some of the indices in this | 
|---|
| 110 | * structure will be modified.  See the field descriptions for | 
|---|
| 111 | * details. | 
|---|
| 112 | * | 
|---|
| 113 | * <p>contextStart <= start <= limit <= contextLimit | 
|---|
| 114 | * | 
|---|
| 115 | * <p>Note: All index values in this structure must be at code point | 
|---|
| 116 | * boundaries.  That is, none of them may occur between two code units | 
|---|
| 117 | * of a surrogate pair.  If any index does split a surrogate pair, | 
|---|
| 118 | * results are unspecified. | 
|---|
| 119 | * | 
|---|
| 120 | * @stable ICU 2.0 | 
|---|
| 121 | */ | 
|---|
| 122 | typedef struct UTransPosition { | 
|---|
| 123 |  | 
|---|
| 124 | /** | 
|---|
| 125 | * Beginning index, inclusive, of the context to be considered for | 
|---|
| 126 | * a transliteration operation.  The transliterator will ignore | 
|---|
| 127 | * anything before this index.  INPUT/OUTPUT parameter: This parameter | 
|---|
| 128 | * is updated by a transliteration operation to reflect the maximum | 
|---|
| 129 | * amount of antecontext needed by a transliterator. | 
|---|
| 130 | * @stable ICU 2.4 | 
|---|
| 131 | */ | 
|---|
| 132 | int32_t contextStart; | 
|---|
| 133 |  | 
|---|
| 134 | /** | 
|---|
| 135 | * Ending index, exclusive, of the context to be considered for a | 
|---|
| 136 | * transliteration operation.  The transliterator will ignore | 
|---|
| 137 | * anything at or after this index.  INPUT/OUTPUT parameter: This | 
|---|
| 138 | * parameter is updated to reflect changes in the length of the | 
|---|
| 139 | * text, but points to the same logical position in the text. | 
|---|
| 140 | * @stable ICU 2.4 | 
|---|
| 141 | */ | 
|---|
| 142 | int32_t contextLimit; | 
|---|
| 143 |  | 
|---|
| 144 | /** | 
|---|
| 145 | * Beginning index, inclusive, of the text to be transliterated. | 
|---|
| 146 | * INPUT/OUTPUT parameter: This parameter is advanced past | 
|---|
| 147 | * characters that have already been transliterated by a | 
|---|
| 148 | * transliteration operation. | 
|---|
| 149 | * @stable ICU 2.4 | 
|---|
| 150 | */ | 
|---|
| 151 | int32_t start; | 
|---|
| 152 |  | 
|---|
| 153 | /** | 
|---|
| 154 | * Ending index, exclusive, of the text to be transliterated. | 
|---|
| 155 | * INPUT/OUTPUT parameter: This parameter is updated to reflect | 
|---|
| 156 | * changes in the length of the text, but points to the same | 
|---|
| 157 | * logical position in the text. | 
|---|
| 158 | * @stable ICU 2.4 | 
|---|
| 159 | */ | 
|---|
| 160 | int32_t limit; | 
|---|
| 161 |  | 
|---|
| 162 | } UTransPosition; | 
|---|
| 163 |  | 
|---|
| 164 | /******************************************************************** | 
|---|
| 165 | * General API | 
|---|
| 166 | ********************************************************************/ | 
|---|
| 167 |  | 
|---|
| 168 | /** | 
|---|
| 169 | * Open a custom transliterator, given a custom rules string | 
|---|
| 170 | * OR | 
|---|
| 171 | * a system transliterator, given its ID. | 
|---|
| 172 | * Any non-NULL result from this function should later be closed with | 
|---|
| 173 | * utrans_close(). | 
|---|
| 174 | * | 
|---|
| 175 | * @param id a valid transliterator ID | 
|---|
| 176 | * @param idLength the length of the ID string, or -1 if NUL-terminated | 
|---|
| 177 | * @param dir the desired direction | 
|---|
| 178 | * @param rules the transliterator rules.  See the C++ header rbt.h for | 
|---|
| 179 | *              rules syntax. If NULL then a system transliterator matching | 
|---|
| 180 | *              the ID is returned. | 
|---|
| 181 | * @param rulesLength the length of the rules, or -1 if the rules | 
|---|
| 182 | *                    are NUL-terminated. | 
|---|
| 183 | * @param parseError a pointer to a UParseError struct to receive the details | 
|---|
| 184 | *                   of any parsing errors. This parameter may be NULL if no | 
|---|
| 185 | *                   parsing error details are desired. | 
|---|
| 186 | * @param pErrorCode a pointer to the UErrorCode | 
|---|
| 187 | * @return a transliterator pointer that may be passed to other | 
|---|
| 188 | *         utrans_xxx() functions, or NULL if the open call fails. | 
|---|
| 189 | * @stable ICU 2.8 | 
|---|
| 190 | */ | 
|---|
| 191 | U_STABLE UTransliterator* U_EXPORT2 | 
|---|
| 192 | utrans_openU(const UChar *id, | 
|---|
| 193 | int32_t idLength, | 
|---|
| 194 | UTransDirection dir, | 
|---|
| 195 | const UChar *rules, | 
|---|
| 196 | int32_t rulesLength, | 
|---|
| 197 | UParseError *parseError, | 
|---|
| 198 | UErrorCode *pErrorCode); | 
|---|
| 199 |  | 
|---|
| 200 | /** | 
|---|
| 201 | * Open an inverse of an existing transliterator.  For this to work, | 
|---|
| 202 | * the inverse must be registered with the system.  For example, if | 
|---|
| 203 | * the Transliterator "A-B" is opened, and then its inverse is opened, | 
|---|
| 204 | * the result is the Transliterator "B-A", if such a transliterator is | 
|---|
| 205 | * registered with the system.  Otherwise the result is NULL and a | 
|---|
| 206 | * failing UErrorCode is set.  Any non-NULL result from this function | 
|---|
| 207 | * should later be closed with utrans_close(). | 
|---|
| 208 | * | 
|---|
| 209 | * @param trans the transliterator to open the inverse of. | 
|---|
| 210 | * @param status a pointer to the UErrorCode | 
|---|
| 211 | * @return a pointer to a newly-opened transliterator that is the | 
|---|
| 212 | * inverse of trans, or NULL if the open call fails. | 
|---|
| 213 | * @stable ICU 2.0 | 
|---|
| 214 | */ | 
|---|
| 215 | U_STABLE UTransliterator* U_EXPORT2 | 
|---|
| 216 | utrans_openInverse(const UTransliterator* trans, | 
|---|
| 217 | UErrorCode* status); | 
|---|
| 218 |  | 
|---|
| 219 | /** | 
|---|
| 220 | * Create a copy of a transliterator.  Any non-NULL result from this | 
|---|
| 221 | * function should later be closed with utrans_close(). | 
|---|
| 222 | * | 
|---|
| 223 | * @param trans the transliterator to be copied. | 
|---|
| 224 | * @param status a pointer to the UErrorCode | 
|---|
| 225 | * @return a transliterator pointer that may be passed to other | 
|---|
| 226 | * utrans_xxx() functions, or NULL if the clone call fails. | 
|---|
| 227 | * @stable ICU 2.0 | 
|---|
| 228 | */ | 
|---|
| 229 | U_STABLE UTransliterator* U_EXPORT2 | 
|---|
| 230 | utrans_clone(const UTransliterator* trans, | 
|---|
| 231 | UErrorCode* status); | 
|---|
| 232 |  | 
|---|
| 233 | /** | 
|---|
| 234 | * Close a transliterator.  Any non-NULL pointer returned by | 
|---|
| 235 | * utrans_openXxx() or utrans_clone() should eventually be closed. | 
|---|
| 236 | * @param trans the transliterator to be closed. | 
|---|
| 237 | * @stable ICU 2.0 | 
|---|
| 238 | */ | 
|---|
| 239 | U_STABLE void U_EXPORT2 | 
|---|
| 240 | utrans_close(UTransliterator* trans); | 
|---|
| 241 |  | 
|---|
| 242 | #if U_SHOW_CPLUSPLUS_API | 
|---|
| 243 |  | 
|---|
| 244 | U_NAMESPACE_BEGIN | 
|---|
| 245 |  | 
|---|
| 246 | /** | 
|---|
| 247 | * \class LocalUTransliteratorPointer | 
|---|
| 248 | * "Smart pointer" class, closes a UTransliterator via utrans_close(). | 
|---|
| 249 | * For most methods see the LocalPointerBase base class. | 
|---|
| 250 | * | 
|---|
| 251 | * @see LocalPointerBase | 
|---|
| 252 | * @see LocalPointer | 
|---|
| 253 | * @stable ICU 4.4 | 
|---|
| 254 | */ | 
|---|
| 255 | U_DEFINE_LOCAL_OPEN_POINTER(LocalUTransliteratorPointer, UTransliterator, utrans_close); | 
|---|
| 256 |  | 
|---|
| 257 | U_NAMESPACE_END | 
|---|
| 258 |  | 
|---|
| 259 | #endif | 
|---|
| 260 |  | 
|---|
| 261 | /** | 
|---|
| 262 | * Return the programmatic identifier for this transliterator. | 
|---|
| 263 | * If this identifier is passed to utrans_openU(), it will open | 
|---|
| 264 | * a transliterator equivalent to this one, if the ID has been | 
|---|
| 265 | * registered. | 
|---|
| 266 | * | 
|---|
| 267 | * @param trans the transliterator to return the ID of. | 
|---|
| 268 | * @param resultLength pointer to an output variable receiving the length | 
|---|
| 269 | *        of the ID string; can be NULL | 
|---|
| 270 | * @return the NUL-terminated ID string. This pointer remains | 
|---|
| 271 | * valid until utrans_close() is called on this transliterator. | 
|---|
| 272 | * | 
|---|
| 273 | * @stable ICU 2.8 | 
|---|
| 274 | */ | 
|---|
| 275 | U_STABLE const UChar * U_EXPORT2 | 
|---|
| 276 | utrans_getUnicodeID(const UTransliterator *trans, | 
|---|
| 277 | int32_t *resultLength); | 
|---|
| 278 |  | 
|---|
| 279 | /** | 
|---|
| 280 | * Register an open transliterator with the system.  When | 
|---|
| 281 | * utrans_open() is called with an ID string that is equal to that | 
|---|
| 282 | * returned by utrans_getID(adoptedTrans,...), then | 
|---|
| 283 | * utrans_clone(adoptedTrans,...) is returned. | 
|---|
| 284 | * | 
|---|
| 285 | * <p>NOTE: After this call the system owns the adoptedTrans and will | 
|---|
| 286 | * close it.  The user must not call utrans_close() on adoptedTrans. | 
|---|
| 287 | * | 
|---|
| 288 | * @param adoptedTrans a transliterator, typically the result of | 
|---|
| 289 | * utrans_openRules(), to be registered with the system. | 
|---|
| 290 | * @param status a pointer to the UErrorCode | 
|---|
| 291 | * @stable ICU 2.0 | 
|---|
| 292 | */ | 
|---|
| 293 | U_STABLE void U_EXPORT2 | 
|---|
| 294 | utrans_register(UTransliterator* adoptedTrans, | 
|---|
| 295 | UErrorCode* status); | 
|---|
| 296 |  | 
|---|
| 297 | /** | 
|---|
| 298 | * Unregister a transliterator from the system.  After this call the | 
|---|
| 299 | * system will no longer recognize the given ID when passed to | 
|---|
| 300 | * utrans_open(). If the ID is invalid then nothing is done. | 
|---|
| 301 | * | 
|---|
| 302 | * @param id an ID to unregister | 
|---|
| 303 | * @param idLength the length of id, or -1 if id is zero-terminated | 
|---|
| 304 | * @stable ICU 2.8 | 
|---|
| 305 | */ | 
|---|
| 306 | U_STABLE void U_EXPORT2 | 
|---|
| 307 | utrans_unregisterID(const UChar* id, int32_t idLength); | 
|---|
| 308 |  | 
|---|
| 309 | /** | 
|---|
| 310 | * Set the filter used by a transliterator.  A filter can be used to | 
|---|
| 311 | * make the transliterator pass certain characters through untouched. | 
|---|
| 312 | * The filter is expressed using a UnicodeSet pattern.  If the | 
|---|
| 313 | * filterPattern is NULL or the empty string, then the transliterator | 
|---|
| 314 | * will be reset to use no filter. | 
|---|
| 315 | * | 
|---|
| 316 | * @param trans the transliterator | 
|---|
| 317 | * @param filterPattern a pattern string, in the form accepted by | 
|---|
| 318 | * UnicodeSet, specifying which characters to apply the | 
|---|
| 319 | * transliteration to.  May be NULL or the empty string to indicate no | 
|---|
| 320 | * filter. | 
|---|
| 321 | * @param filterPatternLen the length of filterPattern, or -1 if | 
|---|
| 322 | * filterPattern is zero-terminated | 
|---|
| 323 | * @param status a pointer to the UErrorCode | 
|---|
| 324 | * @see UnicodeSet | 
|---|
| 325 | * @stable ICU 2.0 | 
|---|
| 326 | */ | 
|---|
| 327 | U_STABLE void U_EXPORT2 | 
|---|
| 328 | utrans_setFilter(UTransliterator* trans, | 
|---|
| 329 | const UChar* filterPattern, | 
|---|
| 330 | int32_t filterPatternLen, | 
|---|
| 331 | UErrorCode* status); | 
|---|
| 332 |  | 
|---|
| 333 | /** | 
|---|
| 334 | * Return the number of system transliterators. | 
|---|
| 335 | * It is recommended to use utrans_openIDs() instead. | 
|---|
| 336 | * | 
|---|
| 337 | * @return the number of system transliterators. | 
|---|
| 338 | * @stable ICU 2.0 | 
|---|
| 339 | */ | 
|---|
| 340 | U_STABLE int32_t U_EXPORT2 | 
|---|
| 341 | utrans_countAvailableIDs(void); | 
|---|
| 342 |  | 
|---|
| 343 | /** | 
|---|
| 344 | * Return a UEnumeration for the available transliterators. | 
|---|
| 345 | * | 
|---|
| 346 | * @param pErrorCode Pointer to the UErrorCode in/out parameter. | 
|---|
| 347 | * @return UEnumeration for the available transliterators. | 
|---|
| 348 | *         Close with uenum_close(). | 
|---|
| 349 | * | 
|---|
| 350 | * @stable ICU 2.8 | 
|---|
| 351 | */ | 
|---|
| 352 | U_STABLE UEnumeration * U_EXPORT2 | 
|---|
| 353 | utrans_openIDs(UErrorCode *pErrorCode); | 
|---|
| 354 |  | 
|---|
| 355 | /******************************************************************** | 
|---|
| 356 | * Transliteration API | 
|---|
| 357 | ********************************************************************/ | 
|---|
| 358 |  | 
|---|
| 359 | /** | 
|---|
| 360 | * Transliterate a segment of a UReplaceable string.  The string is | 
|---|
| 361 | * passed in as a UReplaceable pointer rep and a UReplaceableCallbacks | 
|---|
| 362 | * function pointer struct repFunc.  Functions in the repFunc struct | 
|---|
| 363 | * will be called in order to modify the rep string. | 
|---|
| 364 | * | 
|---|
| 365 | * @param trans the transliterator | 
|---|
| 366 | * @param rep a pointer to the string.  This will be passed to the | 
|---|
| 367 | * repFunc functions. | 
|---|
| 368 | * @param repFunc a set of function pointers that will be used to | 
|---|
| 369 | * modify the string pointed to by rep. | 
|---|
| 370 | * @param start the beginning index, inclusive; <code>0 <= start <= | 
|---|
| 371 | * limit</code>. | 
|---|
| 372 | * @param limit pointer to the ending index, exclusive; <code>start <= | 
|---|
| 373 | * limit <= repFunc->length(rep)</code>.  Upon return, *limit will | 
|---|
| 374 | * contain the new limit index.  The text previously occupying | 
|---|
| 375 | * <code>[start, limit)</code> has been transliterated, possibly to a | 
|---|
| 376 | * string of a different length, at <code>[start, | 
|---|
| 377 | * </code><em>new-limit</em><code>)</code>, where <em>new-limit</em> | 
|---|
| 378 | * is the return value. | 
|---|
| 379 | * @param status a pointer to the UErrorCode | 
|---|
| 380 | * @stable ICU 2.0 | 
|---|
| 381 | */ | 
|---|
| 382 | U_STABLE void U_EXPORT2 | 
|---|
| 383 | utrans_trans(const UTransliterator* trans, | 
|---|
| 384 | UReplaceable* rep, | 
|---|
| 385 | const UReplaceableCallbacks* repFunc, | 
|---|
| 386 | int32_t start, | 
|---|
| 387 | int32_t* limit, | 
|---|
| 388 | UErrorCode* status); | 
|---|
| 389 |  | 
|---|
| 390 | /** | 
|---|
| 391 | * Transliterate the portion of the UReplaceable text buffer that can | 
|---|
| 392 | * be transliterated unambiguously.  This method is typically called | 
|---|
| 393 | * after new text has been inserted, e.g. as a result of a keyboard | 
|---|
| 394 | * event.  The transliterator will try to transliterate characters of | 
|---|
| 395 | * <code>rep</code> between <code>index.cursor</code> and | 
|---|
| 396 | * <code>index.limit</code>.  Characters before | 
|---|
| 397 | * <code>index.cursor</code> will not be changed. | 
|---|
| 398 | * | 
|---|
| 399 | * <p>Upon return, values in <code>index</code> will be updated. | 
|---|
| 400 | * <code>index.start</code> will be advanced to the first | 
|---|
| 401 | * character that future calls to this method will read. | 
|---|
| 402 | * <code>index.cursor</code> and <code>index.limit</code> will | 
|---|
| 403 | * be adjusted to delimit the range of text that future calls to | 
|---|
| 404 | * this method may change. | 
|---|
| 405 | * | 
|---|
| 406 | * <p>Typical usage of this method begins with an initial call | 
|---|
| 407 | * with <code>index.start</code> and <code>index.limit</code> | 
|---|
| 408 | * set to indicate the portion of <code>text</code> to be | 
|---|
| 409 | * transliterated, and <code>index.cursor == index.start</code>. | 
|---|
| 410 | * Thereafter, <code>index</code> can be used without | 
|---|
| 411 | * modification in future calls, provided that all changes to | 
|---|
| 412 | * <code>text</code> are made via this method. | 
|---|
| 413 | * | 
|---|
| 414 | * <p>This method assumes that future calls may be made that will | 
|---|
| 415 | * insert new text into the buffer.  As a result, it only performs | 
|---|
| 416 | * unambiguous transliterations.  After the last call to this method, | 
|---|
| 417 | * there may be untransliterated text that is waiting for more input | 
|---|
| 418 | * to resolve an ambiguity.  In order to perform these pending | 
|---|
| 419 | * transliterations, clients should call utrans_trans() with a start | 
|---|
| 420 | * of index.start and a limit of index.end after the last call to this | 
|---|
| 421 | * method has been made. | 
|---|
| 422 | * | 
|---|
| 423 | * @param trans the transliterator | 
|---|
| 424 | * @param rep a pointer to the string.  This will be passed to the | 
|---|
| 425 | * repFunc functions. | 
|---|
| 426 | * @param repFunc a set of function pointers that will be used to | 
|---|
| 427 | * modify the string pointed to by rep. | 
|---|
| 428 | * @param pos a struct containing the start and limit indices of the | 
|---|
| 429 | * text to be read and the text to be transliterated | 
|---|
| 430 | * @param status a pointer to the UErrorCode | 
|---|
| 431 | * @stable ICU 2.0 | 
|---|
| 432 | */ | 
|---|
| 433 | U_STABLE void U_EXPORT2 | 
|---|
| 434 | utrans_transIncremental(const UTransliterator* trans, | 
|---|
| 435 | UReplaceable* rep, | 
|---|
| 436 | const UReplaceableCallbacks* repFunc, | 
|---|
| 437 | UTransPosition* pos, | 
|---|
| 438 | UErrorCode* status); | 
|---|
| 439 |  | 
|---|
| 440 | /** | 
|---|
| 441 | * Transliterate a segment of a UChar* string.  The string is passed | 
|---|
| 442 | * in in a UChar* buffer.  The string is modified in place.  If the | 
|---|
| 443 | * result is longer than textCapacity, it is truncated.  The actual | 
|---|
| 444 | * length of the result is returned in *textLength, if textLength is | 
|---|
| 445 | * non-NULL. *textLength may be greater than textCapacity, but only | 
|---|
| 446 | * textCapacity UChars will be written to *text, including the zero | 
|---|
| 447 | * terminator. | 
|---|
| 448 | * | 
|---|
| 449 | * @param trans the transliterator | 
|---|
| 450 | * @param text a pointer to a buffer containing the text to be | 
|---|
| 451 | * transliterated on input and the result text on output. | 
|---|
| 452 | * @param textLength a pointer to the length of the string in text. | 
|---|
| 453 | * If the length is -1 then the string is assumed to be | 
|---|
| 454 | * zero-terminated.  Upon return, the new length is stored in | 
|---|
| 455 | * *textLength.  If textLength is NULL then the string is assumed to | 
|---|
| 456 | * be zero-terminated. | 
|---|
| 457 | * @param textCapacity the length of the text buffer | 
|---|
| 458 | * @param start the beginning index, inclusive; <code>0 <= start <= | 
|---|
| 459 | * limit</code>. | 
|---|
| 460 | * @param limit pointer to the ending index, exclusive; <code>start <= | 
|---|
| 461 | * limit <= repFunc->length(rep)</code>.  Upon return, *limit will | 
|---|
| 462 | * contain the new limit index.  The text previously occupying | 
|---|
| 463 | * <code>[start, limit)</code> has been transliterated, possibly to a | 
|---|
| 464 | * string of a different length, at <code>[start, | 
|---|
| 465 | * </code><em>new-limit</em><code>)</code>, where <em>new-limit</em> | 
|---|
| 466 | * is the return value. | 
|---|
| 467 | * @param status a pointer to the UErrorCode | 
|---|
| 468 | * @stable ICU 2.0 | 
|---|
| 469 | */ | 
|---|
| 470 | U_STABLE void U_EXPORT2 | 
|---|
| 471 | utrans_transUChars(const UTransliterator* trans, | 
|---|
| 472 | UChar* text, | 
|---|
| 473 | int32_t* textLength, | 
|---|
| 474 | int32_t textCapacity, | 
|---|
| 475 | int32_t start, | 
|---|
| 476 | int32_t* limit, | 
|---|
| 477 | UErrorCode* status); | 
|---|
| 478 |  | 
|---|
| 479 | /** | 
|---|
| 480 | * Transliterate the portion of the UChar* text buffer that can be | 
|---|
| 481 | * transliterated unambiguously.  See utrans_transIncremental().  The | 
|---|
| 482 | * string is passed in in a UChar* buffer.  The string is modified in | 
|---|
| 483 | * place.  If the result is longer than textCapacity, it is truncated. | 
|---|
| 484 | * The actual length of the result is returned in *textLength, if | 
|---|
| 485 | * textLength is non-NULL. *textLength may be greater than | 
|---|
| 486 | * textCapacity, but only textCapacity UChars will be written to | 
|---|
| 487 | * *text, including the zero terminator.  See utrans_transIncremental() | 
|---|
| 488 | * for usage details. | 
|---|
| 489 | * | 
|---|
| 490 | * @param trans the transliterator | 
|---|
| 491 | * @param text a pointer to a buffer containing the text to be | 
|---|
| 492 | * transliterated on input and the result text on output. | 
|---|
| 493 | * @param textLength a pointer to the length of the string in text. | 
|---|
| 494 | * If the length is -1 then the string is assumed to be | 
|---|
| 495 | * zero-terminated.  Upon return, the new length is stored in | 
|---|
| 496 | * *textLength.  If textLength is NULL then the string is assumed to | 
|---|
| 497 | * be zero-terminated. | 
|---|
| 498 | * @param textCapacity the length of the text buffer | 
|---|
| 499 | * @param pos a struct containing the start and limit indices of the | 
|---|
| 500 | * text to be read and the text to be transliterated | 
|---|
| 501 | * @param status a pointer to the UErrorCode | 
|---|
| 502 | * @see utrans_transIncremental | 
|---|
| 503 | * @stable ICU 2.0 | 
|---|
| 504 | */ | 
|---|
| 505 | U_STABLE void U_EXPORT2 | 
|---|
| 506 | utrans_transIncrementalUChars(const UTransliterator* trans, | 
|---|
| 507 | UChar* text, | 
|---|
| 508 | int32_t* textLength, | 
|---|
| 509 | int32_t textCapacity, | 
|---|
| 510 | UTransPosition* pos, | 
|---|
| 511 | UErrorCode* status); | 
|---|
| 512 |  | 
|---|
| 513 | /** | 
|---|
| 514 | * Create a rule string that can be passed to utrans_openU to recreate this | 
|---|
| 515 | * transliterator. | 
|---|
| 516 | * | 
|---|
| 517 | * @param trans     The transliterator | 
|---|
| 518 | * @param escapeUnprintable if TRUE then convert unprintable characters to their | 
|---|
| 519 | *                  hex escape representations, \\uxxxx or \\Uxxxxxxxx. | 
|---|
| 520 | *                  Unprintable characters are those other than | 
|---|
| 521 | *                  U+000A, U+0020..U+007E. | 
|---|
| 522 | * @param result    A pointer to a buffer to receive the rules. | 
|---|
| 523 | * @param resultLength The maximum size of result. | 
|---|
| 524 | * @param status    A pointer to the UErrorCode. In case of error status, the | 
|---|
| 525 | *                  contents of result are undefined. | 
|---|
| 526 | * @return int32_t   The length of the rule string (may be greater than resultLength, | 
|---|
| 527 | *                  in which case an error is returned). | 
|---|
| 528 | * @stable ICU 53 | 
|---|
| 529 | */ | 
|---|
| 530 | U_STABLE int32_t U_EXPORT2 | 
|---|
| 531 | utrans_toRules(     const UTransliterator* trans, | 
|---|
| 532 | UBool escapeUnprintable, | 
|---|
| 533 | UChar* result, int32_t resultLength, | 
|---|
| 534 | UErrorCode* status); | 
|---|
| 535 |  | 
|---|
| 536 | /** | 
|---|
| 537 | * Returns the set of all characters that may be modified in the input text by | 
|---|
| 538 | * this UTransliterator, optionally ignoring the transliterator's current filter. | 
|---|
| 539 | * @param trans     The transliterator. | 
|---|
| 540 | * @param ignoreFilter If FALSE, the returned set incorporates the | 
|---|
| 541 | *                  UTransliterator's current filter; if the filter is changed, | 
|---|
| 542 | *                  the return value of this function will change. If TRUE, the | 
|---|
| 543 | *                  returned set ignores the effect of the UTransliterator's | 
|---|
| 544 | *                  current filter. | 
|---|
| 545 | * @param fillIn    Pointer to a USet object to receive the modifiable characters | 
|---|
| 546 | *                  set. Previous contents of fillIn are lost. <em>If fillIn is | 
|---|
| 547 | *                  NULL, then a new USet is created and returned. The caller | 
|---|
| 548 | *                  owns the result and must dispose of it by calling uset_close.</em> | 
|---|
| 549 | * @param status    A pointer to the UErrorCode. | 
|---|
| 550 | * @return USet*    Either fillIn, or if fillIn is NULL, a pointer to a | 
|---|
| 551 | *                  newly-allocated USet that the user must close. In case of | 
|---|
| 552 | *                  error, NULL is returned. | 
|---|
| 553 | * @stable ICU 53 | 
|---|
| 554 | */ | 
|---|
| 555 | U_STABLE USet* U_EXPORT2 | 
|---|
| 556 | utrans_getSourceSet(const UTransliterator* trans, | 
|---|
| 557 | UBool ignoreFilter, | 
|---|
| 558 | USet* fillIn, | 
|---|
| 559 | UErrorCode* status); | 
|---|
| 560 |  | 
|---|
| 561 | /* deprecated API ----------------------------------------------------------- */ | 
|---|
| 562 |  | 
|---|
| 563 | #ifndef U_HIDE_DEPRECATED_API | 
|---|
| 564 |  | 
|---|
| 565 | /* see utrans.h documentation for why these functions are deprecated */ | 
|---|
| 566 |  | 
|---|
| 567 | /** | 
|---|
| 568 | * Deprecated, use utrans_openU() instead. | 
|---|
| 569 | * Open a custom transliterator, given a custom rules string | 
|---|
| 570 | * OR | 
|---|
| 571 | * a system transliterator, given its ID. | 
|---|
| 572 | * Any non-NULL result from this function should later be closed with | 
|---|
| 573 | * utrans_close(). | 
|---|
| 574 | * | 
|---|
| 575 | * @param id a valid ID, as returned by utrans_getAvailableID() | 
|---|
| 576 | * @param dir the desired direction | 
|---|
| 577 | * @param rules the transliterator rules.  See the C++ header rbt.h | 
|---|
| 578 | * for rules syntax. If NULL then a system transliterator matching | 
|---|
| 579 | * the ID is returned. | 
|---|
| 580 | * @param rulesLength the length of the rules, or -1 if the rules | 
|---|
| 581 | * are zero-terminated. | 
|---|
| 582 | * @param parseError a pointer to a UParseError struct to receive the | 
|---|
| 583 | * details of any parsing errors. This parameter may be NULL if no | 
|---|
| 584 | * parsing error details are desired. | 
|---|
| 585 | * @param status a pointer to the UErrorCode | 
|---|
| 586 | * @return a transliterator pointer that may be passed to other | 
|---|
| 587 | * utrans_xxx() functions, or NULL if the open call fails. | 
|---|
| 588 | * @deprecated ICU 2.8 Use utrans_openU() instead, see utrans.h | 
|---|
| 589 | */ | 
|---|
| 590 | U_DEPRECATED UTransliterator* U_EXPORT2 | 
|---|
| 591 | utrans_open(const char* id, | 
|---|
| 592 | UTransDirection dir, | 
|---|
| 593 | const UChar* rules,         /* may be Null */ | 
|---|
| 594 | int32_t rulesLength,        /* -1 if null-terminated */ | 
|---|
| 595 | UParseError* parseError,    /* may be Null */ | 
|---|
| 596 | UErrorCode* status); | 
|---|
| 597 |  | 
|---|
| 598 | /** | 
|---|
| 599 | * Deprecated, use utrans_getUnicodeID() instead. | 
|---|
| 600 | * Return the programmatic identifier for this transliterator. | 
|---|
| 601 | * If this identifier is passed to utrans_open(), it will open | 
|---|
| 602 | * a transliterator equivalent to this one, if the ID has been | 
|---|
| 603 | * registered. | 
|---|
| 604 | * @param trans the transliterator to return the ID of. | 
|---|
| 605 | * @param buf the buffer in which to receive the ID.  This may be | 
|---|
| 606 | * NULL, in which case no characters are copied. | 
|---|
| 607 | * @param bufCapacity the capacity of the buffer.  Ignored if buf is | 
|---|
| 608 | * NULL. | 
|---|
| 609 | * @return the actual length of the ID, not including | 
|---|
| 610 | * zero-termination.  This may be greater than bufCapacity. | 
|---|
| 611 | * @deprecated ICU 2.8 Use utrans_getUnicodeID() instead, see utrans.h | 
|---|
| 612 | */ | 
|---|
| 613 | U_DEPRECATED int32_t U_EXPORT2 | 
|---|
| 614 | utrans_getID(const UTransliterator* trans, | 
|---|
| 615 | char* buf, | 
|---|
| 616 | int32_t bufCapacity); | 
|---|
| 617 |  | 
|---|
| 618 | /** | 
|---|
| 619 | * Deprecated, use utrans_unregisterID() instead. | 
|---|
| 620 | * Unregister a transliterator from the system.  After this call the | 
|---|
| 621 | * system will no longer recognize the given ID when passed to | 
|---|
| 622 | * utrans_open().  If the id is invalid then nothing is done. | 
|---|
| 623 | * | 
|---|
| 624 | * @param id a zero-terminated ID | 
|---|
| 625 | * @deprecated ICU 2.8 Use utrans_unregisterID() instead, see utrans.h | 
|---|
| 626 | */ | 
|---|
| 627 | U_DEPRECATED void U_EXPORT2 | 
|---|
| 628 | utrans_unregister(const char* id); | 
|---|
| 629 |  | 
|---|
| 630 | /** | 
|---|
| 631 | * Deprecated, use utrans_openIDs() instead. | 
|---|
| 632 | * Return the ID of the index-th system transliterator.  The result | 
|---|
| 633 | * is placed in the given buffer.  If the given buffer is too small, | 
|---|
| 634 | * the initial substring is copied to buf.  The result in buf is | 
|---|
| 635 | * always zero-terminated. | 
|---|
| 636 | * | 
|---|
| 637 | * @param index the number of the transliterator to return.  Must | 
|---|
| 638 | * satisfy 0 <= index < utrans_countAvailableIDs().  If index is out | 
|---|
| 639 | * of range then it is treated as if it were 0. | 
|---|
| 640 | * @param buf the buffer in which to receive the ID.  This may be | 
|---|
| 641 | * NULL, in which case no characters are copied. | 
|---|
| 642 | * @param bufCapacity the capacity of the buffer.  Ignored if buf is | 
|---|
| 643 | * NULL. | 
|---|
| 644 | * @return the actual length of the index-th ID, not including | 
|---|
| 645 | * zero-termination.  This may be greater than bufCapacity. | 
|---|
| 646 | * @deprecated ICU 2.8 Use utrans_openIDs() instead, see utrans.h | 
|---|
| 647 | */ | 
|---|
| 648 | U_DEPRECATED int32_t U_EXPORT2 | 
|---|
| 649 | utrans_getAvailableID(int32_t index, | 
|---|
| 650 | char* buf, | 
|---|
| 651 | int32_t bufCapacity); | 
|---|
| 652 |  | 
|---|
| 653 | #endif  /* U_HIDE_DEPRECATED_API */ | 
|---|
| 654 |  | 
|---|
| 655 | #endif /* #if !UCONFIG_NO_TRANSLITERATION */ | 
|---|
| 656 |  | 
|---|
| 657 | #endif | 
|---|
| 658 |  | 
|---|