1 /* 2 ******************************************************************************* 3 * 4 * Copyright (C) 2003-2014, International Business Machines 5 * Corporation and others. All Rights Reserved. 6 * 7 ******************************************************************************* 8 * file name: uidna.h 9 * encoding: US-ASCII 10 * tab size: 8 (not used) 11 * indentation:4 12 * 13 * created on: 2003feb1 14 * created by: Ram Viswanadha 15 */ 16 17 #ifndef __UIDNA_H__ 18 #define __UIDNA_H__ 19 20 #include "unicode/utypes.h" 21 22 #if !UCONFIG_NO_IDNA 23 24 #include "unicode/localpointer.h" 25 #include "unicode/parseerr.h" 26 27 /** 28 * \file 29 * \brief C API: Internationalizing Domain Names in Applications (IDNA) 30 * 31 * IDNA2008 is implemented according to UTS #46, see the IDNA C++ class in idna.h. 32 * 33 * The C API functions which do take a UIDNA * service object pointer 34 * implement UTS #46 and IDNA2008. 35 * 36 * IDNA2003 is obsolete. 37 * The C API functions which do not take a service object pointer 38 * implement IDNA2003. They are all deprecated. 39 */ 40 41 /* 42 * IDNA option bit set values. 43 */ 44 enum { 45 /** 46 * Default options value: None of the other options are set. 47 * For use in static worker and factory methods. 48 * @stable ICU 2.6 49 */ 50 UIDNA_DEFAULT=0, 51 #ifndef U_HIDE_DEPRECATED_API 52 /** 53 * Option to allow unassigned code points in domain names and labels. 54 * For use in static worker and factory methods. 55 * <p>This option is ignored by the UTS46 implementation. 56 * (UTS #46 disallows unassigned code points.) 57 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 58 */ 59 UIDNA_ALLOW_UNASSIGNED=1, 60 #endif /* U_HIDE_DEPRECATED_API */ 61 /** 62 * Option to check whether the input conforms to the STD3 ASCII rules, 63 * for example the restriction of labels to LDH characters 64 * (ASCII Letters, Digits and Hyphen-Minus). 65 * For use in static worker and factory methods. 66 * @stable ICU 2.6 67 */ 68 UIDNA_USE_STD3_RULES=2, 69 /** 70 * IDNA option to check for whether the input conforms to the BiDi rules. 71 * For use in static worker and factory methods. 72 * <p>This option is ignored by the IDNA2003 implementation. 73 * (IDNA2003 always performs a BiDi check.) 74 * @stable ICU 4.6 75 */ 76 UIDNA_CHECK_BIDI=4, 77 /** 78 * IDNA option to check for whether the input conforms to the CONTEXTJ rules. 79 * For use in static worker and factory methods. 80 * <p>This option is ignored by the IDNA2003 implementation. 81 * (The CONTEXTJ check is new in IDNA2008.) 82 * @stable ICU 4.6 83 */ 84 UIDNA_CHECK_CONTEXTJ=8, 85 /** 86 * IDNA option for nontransitional processing in ToASCII(). 87 * For use in static worker and factory methods. 88 * <p>By default, ToASCII() uses transitional processing. 89 * <p>This option is ignored by the IDNA2003 implementation. 90 * (This is only relevant for compatibility of newer IDNA implementations with IDNA2003.) 91 * @stable ICU 4.6 92 */ 93 UIDNA_NONTRANSITIONAL_TO_ASCII=0x10, 94 /** 95 * IDNA option for nontransitional processing in ToUnicode(). 96 * For use in static worker and factory methods. 97 * <p>By default, ToUnicode() uses transitional processing. 98 * <p>This option is ignored by the IDNA2003 implementation. 99 * (This is only relevant for compatibility of newer IDNA implementations with IDNA2003.) 100 * @stable ICU 4.6 101 */ 102 UIDNA_NONTRANSITIONAL_TO_UNICODE=0x20, 103 /** 104 * IDNA option to check for whether the input conforms to the CONTEXTO rules. 105 * For use in static worker and factory methods. 106 * <p>This option is ignored by the IDNA2003 implementation. 107 * (The CONTEXTO check is new in IDNA2008.) 108 * <p>This is for use by registries for IDNA2008 conformance. 109 * UTS #46 does not require the CONTEXTO check. 110 * @stable ICU 49 111 */ 112 UIDNA_CHECK_CONTEXTO=0x40 113 }; 114 115 /** 116 * Opaque C service object type for the new IDNA API. 117 * @stable ICU 4.6 118 */ 119 struct UIDNA; 120 typedef struct UIDNA UIDNA; /**< C typedef for struct UIDNA. @stable ICU 4.6 */ 121 122 /** 123 * Returns a UIDNA instance which implements UTS #46. 124 * Returns an unmodifiable instance, owned by the caller. 125 * Cache it for multiple operations, and uidna_close() it when done. 126 * The instance is thread-safe, that is, it can be used concurrently. 127 * 128 * For details about the UTS #46 implementation see the IDNA C++ class in idna.h. 129 * 130 * @param options Bit set to modify the processing and error checking. 131 * See option bit set values in uidna.h. 132 * @param pErrorCode Standard ICU error code. Its input value must 133 * pass the U_SUCCESS() test, or else the function returns 134 * immediately. Check for U_FAILURE() on output or use with 135 * function chaining. (See User Guide for details.) 136 * @return the UTS #46 UIDNA instance, if successful 137 * @stable ICU 4.6 138 */ 139 U_STABLE UIDNA * U_EXPORT2 140 uidna_openUTS46(uint32_t options, UErrorCode *pErrorCode); 141 142 /** 143 * Closes a UIDNA instance. 144 * @param idna UIDNA instance to be closed 145 * @stable ICU 4.6 146 */ 147 U_STABLE void U_EXPORT2 148 uidna_close(UIDNA *idna); 149 150 #if U_SHOW_CPLUSPLUS_API 151 152 U_NAMESPACE_BEGIN 153 154 /** 155 * \class LocalUIDNAPointer 156 * "Smart pointer" class, closes a UIDNA via uidna_close(). 157 * For most methods see the LocalPointerBase base class. 158 * 159 * @see LocalPointerBase 160 * @see LocalPointer 161 * @stable ICU 4.6 162 */ 163 U_DEFINE_LOCAL_OPEN_POINTER(LocalUIDNAPointer, UIDNA, uidna_close); 164 165 U_NAMESPACE_END 166 167 #endif 168 169 /** 170 * Output container for IDNA processing errors. 171 * Initialize with UIDNA_INFO_INITIALIZER: 172 * \code 173 * UIDNAInfo info = UIDNA_INFO_INITIALIZER; 174 * int32_t length = uidna_nameToASCII(..., &info, &errorCode); 175 * if(U_SUCCESS(errorCode) && info.errors!=0) { ... } 176 * \endcode 177 * @stable ICU 4.6 178 */ 179 typedef struct UIDNAInfo { 180 /** sizeof(UIDNAInfo) @stable ICU 4.6 */ 181 int16_t size; 182 /** 183 * Set to TRUE if transitional and nontransitional processing produce different results. 184 * For details see C++ IDNAInfo::isTransitionalDifferent(). 185 * @stable ICU 4.6 186 */ 187 UBool isTransitionalDifferent; 188 UBool reservedB3; /**< Reserved field, do not use. @internal */ 189 /** 190 * Bit set indicating IDNA processing errors. 0 if no errors. 191 * See UIDNA_ERROR_... constants. 192 * @stable ICU 4.6 193 */ 194 uint32_t errors; 195 int32_t reservedI2; /**< Reserved field, do not use. @internal */ 196 int32_t reservedI3; /**< Reserved field, do not use. @internal */ 197 } UIDNAInfo; 198 199 /** 200 * Static initializer for a UIDNAInfo struct. 201 * @stable ICU 4.6 202 */ 203 #define UIDNA_INFO_INITIALIZER { \ 204 (int16_t)sizeof(UIDNAInfo), \ 205 FALSE, FALSE, \ 206 0, 0, 0 } 207 208 /** 209 * Converts a single domain name label into its ASCII form for DNS lookup. 210 * If any processing step fails, then pInfo->errors will be non-zero and 211 * the result might not be an ASCII string. 212 * The label might be modified according to the types of errors. 213 * Labels with severe errors will be left in (or turned into) their Unicode form. 214 * 215 * The UErrorCode indicates an error only in exceptional cases, 216 * such as a U_MEMORY_ALLOCATION_ERROR. 217 * 218 * @param idna UIDNA instance 219 * @param label Input domain name label 220 * @param length Label length, or -1 if NUL-terminated 221 * @param dest Destination string buffer 222 * @param capacity Destination buffer capacity 223 * @param pInfo Output container of IDNA processing details. 224 * @param pErrorCode Standard ICU error code. Its input value must 225 * pass the U_SUCCESS() test, or else the function returns 226 * immediately. Check for U_FAILURE() on output or use with 227 * function chaining. (See User Guide for details.) 228 * @return destination string length 229 * @stable ICU 4.6 230 */ 231 U_STABLE int32_t U_EXPORT2 232 uidna_labelToASCII(const UIDNA *idna, 233 const UChar *label, int32_t length, 234 UChar *dest, int32_t capacity, 235 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 236 237 /** 238 * Converts a single domain name label into its Unicode form for human-readable display. 239 * If any processing step fails, then pInfo->errors will be non-zero. 240 * The label might be modified according to the types of errors. 241 * 242 * The UErrorCode indicates an error only in exceptional cases, 243 * such as a U_MEMORY_ALLOCATION_ERROR. 244 * 245 * @param idna UIDNA instance 246 * @param label Input domain name label 247 * @param length Label length, or -1 if NUL-terminated 248 * @param dest Destination string buffer 249 * @param capacity Destination buffer capacity 250 * @param pInfo Output container of IDNA processing details. 251 * @param pErrorCode Standard ICU error code. Its input value must 252 * pass the U_SUCCESS() test, or else the function returns 253 * immediately. Check for U_FAILURE() on output or use with 254 * function chaining. (See User Guide for details.) 255 * @return destination string length 256 * @stable ICU 4.6 257 */ 258 U_STABLE int32_t U_EXPORT2 259 uidna_labelToUnicode(const UIDNA *idna, 260 const UChar *label, int32_t length, 261 UChar *dest, int32_t capacity, 262 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 263 264 /** 265 * Converts a whole domain name into its ASCII form for DNS lookup. 266 * If any processing step fails, then pInfo->errors will be non-zero and 267 * the result might not be an ASCII string. 268 * The domain name might be modified according to the types of errors. 269 * Labels with severe errors will be left in (or turned into) their Unicode form. 270 * 271 * The UErrorCode indicates an error only in exceptional cases, 272 * such as a U_MEMORY_ALLOCATION_ERROR. 273 * 274 * @param idna UIDNA instance 275 * @param name Input domain name 276 * @param length Domain name length, or -1 if NUL-terminated 277 * @param dest Destination string buffer 278 * @param capacity Destination buffer capacity 279 * @param pInfo Output container of IDNA processing details. 280 * @param pErrorCode Standard ICU error code. Its input value must 281 * pass the U_SUCCESS() test, or else the function returns 282 * immediately. Check for U_FAILURE() on output or use with 283 * function chaining. (See User Guide for details.) 284 * @return destination string length 285 * @stable ICU 4.6 286 */ 287 U_STABLE int32_t U_EXPORT2 288 uidna_nameToASCII(const UIDNA *idna, 289 const UChar *name, int32_t length, 290 UChar *dest, int32_t capacity, 291 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 292 293 /** 294 * Converts a whole domain name into its Unicode form for human-readable display. 295 * If any processing step fails, then pInfo->errors will be non-zero. 296 * The domain name might be modified according to the types of errors. 297 * 298 * The UErrorCode indicates an error only in exceptional cases, 299 * such as a U_MEMORY_ALLOCATION_ERROR. 300 * 301 * @param idna UIDNA instance 302 * @param name Input domain name 303 * @param length Domain name length, or -1 if NUL-terminated 304 * @param dest Destination string buffer 305 * @param capacity Destination buffer capacity 306 * @param pInfo Output container of IDNA processing details. 307 * @param pErrorCode Standard ICU error code. Its input value must 308 * pass the U_SUCCESS() test, or else the function returns 309 * immediately. Check for U_FAILURE() on output or use with 310 * function chaining. (See User Guide for details.) 311 * @return destination string length 312 * @stable ICU 4.6 313 */ 314 U_STABLE int32_t U_EXPORT2 315 uidna_nameToUnicode(const UIDNA *idna, 316 const UChar *name, int32_t length, 317 UChar *dest, int32_t capacity, 318 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 319 320 /* UTF-8 versions of the processing methods --------------------------------- */ 321 322 /** 323 * Converts a single domain name label into its ASCII form for DNS lookup. 324 * UTF-8 version of uidna_labelToASCII(), same behavior. 325 * 326 * @param idna UIDNA instance 327 * @param label Input domain name label 328 * @param length Label length, or -1 if NUL-terminated 329 * @param dest Destination string buffer 330 * @param capacity Destination buffer capacity 331 * @param pInfo Output container of IDNA processing details. 332 * @param pErrorCode Standard ICU error code. Its input value must 333 * pass the U_SUCCESS() test, or else the function returns 334 * immediately. Check for U_FAILURE() on output or use with 335 * function chaining. (See User Guide for details.) 336 * @return destination string length 337 * @stable ICU 4.6 338 */ 339 U_STABLE int32_t U_EXPORT2 340 uidna_labelToASCII_UTF8(const UIDNA *idna, 341 const char *label, int32_t length, 342 char *dest, int32_t capacity, 343 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 344 345 /** 346 * Converts a single domain name label into its Unicode form for human-readable display. 347 * UTF-8 version of uidna_labelToUnicode(), same behavior. 348 * 349 * @param idna UIDNA instance 350 * @param label Input domain name label 351 * @param length Label length, or -1 if NUL-terminated 352 * @param dest Destination string buffer 353 * @param capacity Destination buffer capacity 354 * @param pInfo Output container of IDNA processing details. 355 * @param pErrorCode Standard ICU error code. Its input value must 356 * pass the U_SUCCESS() test, or else the function returns 357 * immediately. Check for U_FAILURE() on output or use with 358 * function chaining. (See User Guide for details.) 359 * @return destination string length 360 * @stable ICU 4.6 361 */ 362 U_STABLE int32_t U_EXPORT2 363 uidna_labelToUnicodeUTF8(const UIDNA *idna, 364 const char *label, int32_t length, 365 char *dest, int32_t capacity, 366 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 367 368 /** 369 * Converts a whole domain name into its ASCII form for DNS lookup. 370 * UTF-8 version of uidna_nameToASCII(), same behavior. 371 * 372 * @param idna UIDNA instance 373 * @param name Input domain name 374 * @param length Domain name length, or -1 if NUL-terminated 375 * @param dest Destination string buffer 376 * @param capacity Destination buffer capacity 377 * @param pInfo Output container of IDNA processing details. 378 * @param pErrorCode Standard ICU error code. Its input value must 379 * pass the U_SUCCESS() test, or else the function returns 380 * immediately. Check for U_FAILURE() on output or use with 381 * function chaining. (See User Guide for details.) 382 * @return destination string length 383 * @stable ICU 4.6 384 */ 385 U_STABLE int32_t U_EXPORT2 386 uidna_nameToASCII_UTF8(const UIDNA *idna, 387 const char *name, int32_t length, 388 char *dest, int32_t capacity, 389 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 390 391 /** 392 * Converts a whole domain name into its Unicode form for human-readable display. 393 * UTF-8 version of uidna_nameToUnicode(), same behavior. 394 * 395 * @param idna UIDNA instance 396 * @param name Input domain name 397 * @param length Domain name length, or -1 if NUL-terminated 398 * @param dest Destination string buffer 399 * @param capacity Destination buffer capacity 400 * @param pInfo Output container of IDNA processing details. 401 * @param pErrorCode Standard ICU error code. Its input value must 402 * pass the U_SUCCESS() test, or else the function returns 403 * immediately. Check for U_FAILURE() on output or use with 404 * function chaining. (See User Guide for details.) 405 * @return destination string length 406 * @stable ICU 4.6 407 */ 408 U_STABLE int32_t U_EXPORT2 409 uidna_nameToUnicodeUTF8(const UIDNA *idna, 410 const char *name, int32_t length, 411 char *dest, int32_t capacity, 412 UIDNAInfo *pInfo, UErrorCode *pErrorCode); 413 414 /* 415 * IDNA error bit set values. 416 * When a domain name or label fails a processing step or does not meet the 417 * validity criteria, then one or more of these error bits are set. 418 */ 419 enum { 420 /** 421 * A non-final domain name label (or the whole domain name) is empty. 422 * @stable ICU 4.6 423 */ 424 UIDNA_ERROR_EMPTY_LABEL=1, 425 /** 426 * A domain name label is longer than 63 bytes. 427 * (See STD13/RFC1034 3.1. Name space specifications and terminology.) 428 * This is only checked in ToASCII operations, and only if the output label is all-ASCII. 429 * @stable ICU 4.6 430 */ 431 UIDNA_ERROR_LABEL_TOO_LONG=2, 432 /** 433 * A domain name is longer than 255 bytes in its storage form. 434 * (See STD13/RFC1034 3.1. Name space specifications and terminology.) 435 * This is only checked in ToASCII operations, and only if the output domain name is all-ASCII. 436 * @stable ICU 4.6 437 */ 438 UIDNA_ERROR_DOMAIN_NAME_TOO_LONG=4, 439 /** 440 * A label starts with a hyphen-minus ('-'). 441 * @stable ICU 4.6 442 */ 443 UIDNA_ERROR_LEADING_HYPHEN=8, 444 /** 445 * A label ends with a hyphen-minus ('-'). 446 * @stable ICU 4.6 447 */ 448 UIDNA_ERROR_TRAILING_HYPHEN=0x10, 449 /** 450 * A label contains hyphen-minus ('-') in the third and fourth positions. 451 * @stable ICU 4.6 452 */ 453 UIDNA_ERROR_HYPHEN_3_4=0x20, 454 /** 455 * A label starts with a combining mark. 456 * @stable ICU 4.6 457 */ 458 UIDNA_ERROR_LEADING_COMBINING_MARK=0x40, 459 /** 460 * A label or domain name contains disallowed characters. 461 * @stable ICU 4.6 462 */ 463 UIDNA_ERROR_DISALLOWED=0x80, 464 /** 465 * A label starts with "xn--" but does not contain valid Punycode. 466 * That is, an xn-- label failed Punycode decoding. 467 * @stable ICU 4.6 468 */ 469 UIDNA_ERROR_PUNYCODE=0x100, 470 /** 471 * A label contains a dot=full stop. 472 * This can occur in an input string for a single-label function. 473 * @stable ICU 4.6 474 */ 475 UIDNA_ERROR_LABEL_HAS_DOT=0x200, 476 /** 477 * An ACE label does not contain a valid label string. 478 * The label was successfully ACE (Punycode) decoded but the resulting 479 * string had severe validation errors. For example, 480 * it might contain characters that are not allowed in ACE labels, 481 * or it might not be normalized. 482 * @stable ICU 4.6 483 */ 484 UIDNA_ERROR_INVALID_ACE_LABEL=0x400, 485 /** 486 * A label does not meet the IDNA BiDi requirements (for right-to-left characters). 487 * @stable ICU 4.6 488 */ 489 UIDNA_ERROR_BIDI=0x800, 490 /** 491 * A label does not meet the IDNA CONTEXTJ requirements. 492 * @stable ICU 4.6 493 */ 494 UIDNA_ERROR_CONTEXTJ=0x1000, 495 /** 496 * A label does not meet the IDNA CONTEXTO requirements for punctuation characters. 497 * Some punctuation characters "Would otherwise have been DISALLOWED" 498 * but are allowed in certain contexts. (RFC 5892) 499 * @stable ICU 49 500 */ 501 UIDNA_ERROR_CONTEXTO_PUNCTUATION=0x2000, 502 /** 503 * A label does not meet the IDNA CONTEXTO requirements for digits. 504 * Arabic-Indic Digits (U+066x) must not be mixed with Extended Arabic-Indic Digits (U+06Fx). 505 * @stable ICU 49 506 */ 507 UIDNA_ERROR_CONTEXTO_DIGITS=0x4000 508 }; 509 510 #ifndef U_HIDE_DEPRECATED_API 511 512 /* IDNA2003 API ------------------------------------------------------------- */ 513 514 /** 515 * IDNA2003: This function implements the ToASCII operation as defined in the IDNA RFC. 516 * This operation is done on <b>single labels</b> before sending it to something that expects 517 * ASCII names. A label is an individual part of a domain name. Labels are usually 518 * separated by dots; e.g. "www.example.com" is composed of 3 labels "www","example", and "com". 519 * 520 * IDNA2003 API Overview: 521 * 522 * The uidna_ API implements the IDNA protocol as defined in the IDNA RFC 523 * (http://www.ietf.org/rfc/rfc3490.txt). 524 * The RFC defines 2 operations: ToASCII and ToUnicode. Domain name labels 525 * containing non-ASCII code points are processed by the 526 * ToASCII operation before passing it to resolver libraries. Domain names 527 * that are obtained from resolver libraries are processed by the 528 * ToUnicode operation before displaying the domain name to the user. 529 * IDNA requires that implementations process input strings with Nameprep 530 * (http://www.ietf.org/rfc/rfc3491.txt), 531 * which is a profile of Stringprep (http://www.ietf.org/rfc/rfc3454.txt), 532 * and then with Punycode (http://www.ietf.org/rfc/rfc3492.txt). 533 * Implementations of IDNA MUST fully implement Nameprep and Punycode; 534 * neither Nameprep nor Punycode are optional. 535 * The input and output of ToASCII and ToUnicode operations are Unicode 536 * and are designed to be chainable, i.e., applying ToASCII or ToUnicode operations 537 * multiple times to an input string will yield the same result as applying the operation 538 * once. 539 * ToUnicode(ToUnicode(ToUnicode...(ToUnicode(string)))) == ToUnicode(string) 540 * ToASCII(ToASCII(ToASCII...(ToASCII(string))) == ToASCII(string). 541 * 542 * @param src Input UChar array containing label in Unicode. 543 * @param srcLength Number of UChars in src, or -1 if NUL-terminated. 544 * @param dest Output UChar array with ASCII (ACE encoded) label. 545 * @param destCapacity Size of dest. 546 * @param options A bit set of options: 547 * 548 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points 549 * and do not use STD3 ASCII rules 550 * If unassigned code points are found the operation fails with 551 * U_UNASSIGNED_ERROR error code. 552 * 553 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations 554 * If this option is set, the unassigned code points are in the input 555 * are treated as normal Unicode code points. 556 * 557 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions 558 * If this option is set and the input does not satisfy STD3 rules, 559 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR 560 * 561 * @param parseError Pointer to UParseError struct to receive information on position 562 * of error if an error is encountered. Can be NULL. 563 * @param status ICU in/out error code parameter. 564 * U_INVALID_CHAR_FOUND if src contains 565 * unmatched single surrogates. 566 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 567 * too many code points. 568 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 569 * @return The length of the result string, if successful - or in case of a buffer overflow, 570 * in which case it will be greater than destCapacity. 571 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 572 */ 573 U_DEPRECATED int32_t U_EXPORT2 574 uidna_toASCII(const UChar* src, int32_t srcLength, 575 UChar* dest, int32_t destCapacity, 576 int32_t options, 577 UParseError* parseError, 578 UErrorCode* status); 579 580 581 /** 582 * IDNA2003: This function implements the ToUnicode operation as defined in the IDNA RFC. 583 * This operation is done on <b>single labels</b> before sending it to something that expects 584 * Unicode names. A label is an individual part of a domain name. Labels are usually 585 * separated by dots; for e.g. "www.example.com" is composed of 3 labels "www","example", and "com". 586 * 587 * @param src Input UChar array containing ASCII (ACE encoded) label. 588 * @param srcLength Number of UChars in src, or -1 if NUL-terminated. 589 * @param dest Output Converted UChar array containing Unicode equivalent of label. 590 * @param destCapacity Size of dest. 591 * @param options A bit set of options: 592 * 593 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points 594 * and do not use STD3 ASCII rules 595 * If unassigned code points are found the operation fails with 596 * U_UNASSIGNED_ERROR error code. 597 * 598 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations 599 * If this option is set, the unassigned code points are in the input 600 * are treated as normal Unicode code points. <b> Note: </b> This option is 601 * required on toUnicode operation because the RFC mandates 602 * verification of decoded ACE input by applying toASCII and comparing 603 * its output with source 604 * 605 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions 606 * If this option is set and the input does not satisfy STD3 rules, 607 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR 608 * 609 * @param parseError Pointer to UParseError struct to receive information on position 610 * of error if an error is encountered. Can be NULL. 611 * @param status ICU in/out error code parameter. 612 * U_INVALID_CHAR_FOUND if src contains 613 * unmatched single surrogates. 614 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 615 * too many code points. 616 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 617 * @return The length of the result string, if successful - or in case of a buffer overflow, 618 * in which case it will be greater than destCapacity. 619 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 620 */ 621 U_DEPRECATED int32_t U_EXPORT2 622 uidna_toUnicode(const UChar* src, int32_t srcLength, 623 UChar* dest, int32_t destCapacity, 624 int32_t options, 625 UParseError* parseError, 626 UErrorCode* status); 627 628 629 /** 630 * IDNA2003: Convenience function that implements the IDNToASCII operation as defined in the IDNA RFC. 631 * This operation is done on complete domain names, e.g: "www.example.com". 632 * It is important to note that this operation can fail. If it fails, then the input 633 * domain name cannot be used as an Internationalized Domain Name and the application 634 * should have methods defined to deal with the failure. 635 * 636 * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name 637 * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, 638 * and then convert. This function does not offer that level of granularity. The options once 639 * set will apply to all labels in the domain name 640 * 641 * @param src Input UChar array containing IDN in Unicode. 642 * @param srcLength Number of UChars in src, or -1 if NUL-terminated. 643 * @param dest Output UChar array with ASCII (ACE encoded) IDN. 644 * @param destCapacity Size of dest. 645 * @param options A bit set of options: 646 * 647 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points 648 * and do not use STD3 ASCII rules 649 * If unassigned code points are found the operation fails with 650 * U_UNASSIGNED_CODE_POINT_FOUND error code. 651 * 652 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations 653 * If this option is set, the unassigned code points are in the input 654 * are treated as normal Unicode code points. 655 * 656 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions 657 * If this option is set and the input does not satisfy STD3 rules, 658 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR 659 * 660 * @param parseError Pointer to UParseError struct to receive information on position 661 * of error if an error is encountered. Can be NULL. 662 * @param status ICU in/out error code parameter. 663 * U_INVALID_CHAR_FOUND if src contains 664 * unmatched single surrogates. 665 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 666 * too many code points. 667 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 668 * @return The length of the result string, if successful - or in case of a buffer overflow, 669 * in which case it will be greater than destCapacity. 670 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 671 */ 672 U_DEPRECATED int32_t U_EXPORT2 673 uidna_IDNToASCII( const UChar* src, int32_t srcLength, 674 UChar* dest, int32_t destCapacity, 675 int32_t options, 676 UParseError* parseError, 677 UErrorCode* status); 678 679 /** 680 * IDNA2003: Convenience function that implements the IDNToUnicode operation as defined in the IDNA RFC. 681 * This operation is done on complete domain names, e.g: "www.example.com". 682 * 683 * <b>Note:</b> IDNA RFC specifies that a conformant application should divide a domain name 684 * into separate labels, decide whether to apply allowUnassigned and useSTD3ASCIIRules on each, 685 * and then convert. This function does not offer that level of granularity. The options once 686 * set will apply to all labels in the domain name 687 * 688 * @param src Input UChar array containing IDN in ASCII (ACE encoded) form. 689 * @param srcLength Number of UChars in src, or -1 if NUL-terminated. 690 * @param dest Output UChar array containing Unicode equivalent of source IDN. 691 * @param destCapacity Size of dest. 692 * @param options A bit set of options: 693 * 694 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points 695 * and do not use STD3 ASCII rules 696 * If unassigned code points are found the operation fails with 697 * U_UNASSIGNED_CODE_POINT_FOUND error code. 698 * 699 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations 700 * If this option is set, the unassigned code points are in the input 701 * are treated as normal Unicode code points. 702 * 703 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions 704 * If this option is set and the input does not satisfy STD3 rules, 705 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR 706 * 707 * @param parseError Pointer to UParseError struct to receive information on position 708 * of error if an error is encountered. Can be NULL. 709 * @param status ICU in/out error code parameter. 710 * U_INVALID_CHAR_FOUND if src contains 711 * unmatched single surrogates. 712 * U_INDEX_OUTOFBOUNDS_ERROR if src contains 713 * too many code points. 714 * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough 715 * @return The length of the result string, if successful - or in case of a buffer overflow, 716 * in which case it will be greater than destCapacity. 717 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 718 */ 719 U_DEPRECATED int32_t U_EXPORT2 720 uidna_IDNToUnicode( const UChar* src, int32_t srcLength, 721 UChar* dest, int32_t destCapacity, 722 int32_t options, 723 UParseError* parseError, 724 UErrorCode* status); 725 726 /** 727 * IDNA2003: Compare two IDN strings for equivalence. 728 * This function splits the domain names into labels and compares them. 729 * According to IDN RFC, whenever two labels are compared, they are 730 * considered equal if and only if their ASCII forms (obtained by 731 * applying toASCII) match using an case-insensitive ASCII comparison. 732 * Two domain names are considered a match if and only if all labels 733 * match regardless of whether label separators match. 734 * 735 * @param s1 First source string. 736 * @param length1 Length of first source string, or -1 if NUL-terminated. 737 * 738 * @param s2 Second source string. 739 * @param length2 Length of second source string, or -1 if NUL-terminated. 740 * @param options A bit set of options: 741 * 742 * - UIDNA_DEFAULT Use default options, i.e., do not process unassigned code points 743 * and do not use STD3 ASCII rules 744 * If unassigned code points are found the operation fails with 745 * U_UNASSIGNED_CODE_POINT_FOUND error code. 746 * 747 * - UIDNA_ALLOW_UNASSIGNED Unassigned values can be converted to ASCII for query operations 748 * If this option is set, the unassigned code points are in the input 749 * are treated as normal Unicode code points. 750 * 751 * - UIDNA_USE_STD3_RULES Use STD3 ASCII rules for host name syntax restrictions 752 * If this option is set and the input does not satisfy STD3 rules, 753 * the operation will fail with U_IDNA_STD3_ASCII_RULES_ERROR 754 * 755 * @param status ICU error code in/out parameter. 756 * Must fulfill U_SUCCESS before the function call. 757 * @return <0 or 0 or >0 as usual for string comparisons 758 * @deprecated ICU 55 Use UTS #46 instead via uidna_openUTS46() or class IDNA. 759 */ 760 U_DEPRECATED int32_t U_EXPORT2 761 uidna_compare( const UChar *s1, int32_t length1, 762 const UChar *s2, int32_t length2, 763 int32_t options, 764 UErrorCode* status); 765 766 #endif /* U_HIDE_DEPRECATED_API */ 767 768 #endif /* #if !UCONFIG_NO_IDNA */ 769 770 #endif 771