DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (5b81998bb7ab)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532
/*
*******************************************************************************
*
*   Copyright (C) 2009-2012, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  unorm2.h
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2009dec15
*   created by: Markus W. Scherer
*/

#ifndef __UNORM2_H__
#define __UNORM2_H__

/**
 * \file
 * \brief C API: New API for Unicode Normalization.
 *
 * Unicode normalization functionality for standard Unicode normalization or
 * for using custom mapping tables.
 * All instances of UNormalizer2 are unmodifiable/immutable.
 * Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller.
 * For more details see the Normalizer2 C++ class.
 */

#include "unicode/utypes.h"
#include "unicode/localpointer.h"
#include "unicode/uset.h"

/**
 * Constants for normalization modes.
 * For details about standard Unicode normalization forms
 * and about the algorithms which are also used with custom mapping tables
 * see http://www.unicode.org/unicode/reports/tr15/
 * @stable ICU 4.4
 */
typedef enum {
    /**
     * Decomposition followed by composition.
     * Same as standard NFC when using an "nfc" instance.
     * Same as standard NFKC when using an "nfkc" instance.
     * For details about standard Unicode normalization forms
     * see http://www.unicode.org/unicode/reports/tr15/
     * @stable ICU 4.4
     */
    UNORM2_COMPOSE,
    /**
     * Map, and reorder canonically.
     * Same as standard NFD when using an "nfc" instance.
     * Same as standard NFKD when using an "nfkc" instance.
     * For details about standard Unicode normalization forms
     * see http://www.unicode.org/unicode/reports/tr15/
     * @stable ICU 4.4
     */
    UNORM2_DECOMPOSE,
    /**
     * "Fast C or D" form.
     * If a string is in this form, then further decomposition <i>without reordering</i>
     * would yield the same form as DECOMPOSE.
     * Text in "Fast C or D" form can be processed efficiently with data tables
     * that are "canonically closed", that is, that provide equivalent data for
     * equivalent text, without having to be fully normalized.
     * Not a standard Unicode normalization form.
     * Not a unique form: Different FCD strings can be canonically equivalent.
     * For details see http://www.unicode.org/notes/tn5/#FCD
     * @stable ICU 4.4
     */
    UNORM2_FCD,
    /**
     * Compose only contiguously.
     * Also known as "FCC" or "Fast C Contiguous".
     * The result will often but not always be in NFC.
     * The result will conform to FCD which is useful for processing.
     * Not a standard Unicode normalization form.
     * For details see http://www.unicode.org/notes/tn5/#FCC
     * @stable ICU 4.4
     */
    UNORM2_COMPOSE_CONTIGUOUS
} UNormalization2Mode;

/**
 * Result values for normalization quick check functions.
 * For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms
 * @stable ICU 2.0
 */
typedef enum UNormalizationCheckResult {
  /**
   * The input string is not in the normalization form.
   * @stable ICU 2.0
   */
  UNORM_NO,
  /**
   * The input string is in the normalization form.
   * @stable ICU 2.0
   */
  UNORM_YES,
  /**
   * The input string may or may not be in the normalization form.
   * This value is only returned for composition forms like NFC and FCC,
   * when a backward-combining character is found for which the surrounding text
   * would have to be analyzed further.
   * @stable ICU 2.0
   */
  UNORM_MAYBE
} UNormalizationCheckResult;

/**
 * Opaque C service object type for the new normalization API.
 * @stable ICU 4.4
 */
struct UNormalizer2;
typedef struct UNormalizer2 UNormalizer2;  /**< C typedef for struct UNormalizer2. @stable ICU 4.4 */

#if !UCONFIG_NO_NORMALIZATION

#ifndef U_HIDE_DRAFT_API
/**
 * Returns a UNormalizer2 instance for Unicode NFC normalization.
 * Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode).
 * Returns an unmodifiable singleton instance. Do not delete it.
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested Normalizer2, if successful
 * @draft ICU 49
 */
U_DRAFT const UNormalizer2 * U_EXPORT2
unorm2_getNFCInstance(UErrorCode *pErrorCode);

/**
 * Returns a UNormalizer2 instance for Unicode NFD normalization.
 * Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode).
 * Returns an unmodifiable singleton instance. Do not delete it.
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested Normalizer2, if successful
 * @draft ICU 49
 */
U_DRAFT const UNormalizer2 * U_EXPORT2
unorm2_getNFDInstance(UErrorCode *pErrorCode);

/**
 * Returns a UNormalizer2 instance for Unicode NFKC normalization.
 * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode).
 * Returns an unmodifiable singleton instance. Do not delete it.
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested Normalizer2, if successful
 * @draft ICU 49
 */
U_DRAFT const UNormalizer2 * U_EXPORT2
unorm2_getNFKCInstance(UErrorCode *pErrorCode);

/**
 * Returns a UNormalizer2 instance for Unicode NFKD normalization.
 * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode).
 * Returns an unmodifiable singleton instance. Do not delete it.
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested Normalizer2, if successful
 * @draft ICU 49
 */
U_DRAFT const UNormalizer2 * U_EXPORT2
unorm2_getNFKDInstance(UErrorCode *pErrorCode);

/**
 * Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization.
 * Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode).
 * Returns an unmodifiable singleton instance. Do not delete it.
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested Normalizer2, if successful
 * @draft ICU 49
 */
U_DRAFT const UNormalizer2 * U_EXPORT2
unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode);
#endif  /* U_HIDE_DRAFT_API */

/**
 * Returns a UNormalizer2 instance which uses the specified data file
 * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle)
 * and which composes or decomposes text according to the specified mode.
 * Returns an unmodifiable singleton instance. Do not delete it.
 *
 * Use packageName=NULL for data files that are part of ICU's own data.
 * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD.
 * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD.
 * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold.
 *
 * @param packageName NULL for ICU built-in data, otherwise application data package name
 * @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file
 * @param mode normalization mode (compose or decompose etc.)
 * @param pErrorCode Standard ICU error code. Its input value must
 *                  pass the U_SUCCESS() test, or else the function returns
 *                  immediately. Check for U_FAILURE() on output or use with
 *                  function chaining. (See User Guide for details.)
 * @return the requested UNormalizer2, if successful
 * @stable ICU 4.4
 */
U_STABLE const UNormalizer2 * U_EXPORT2
unorm2_getInstance(const char *packageName,
                   const char *name,
                   UNormalization2Mode mode,
                   UErrorCode *pErrorCode);

/**
 * Constructs a filtered normalizer wrapping any UNormalizer2 instance
 * and a filter set.
 * Both are aliased and must not be modified or deleted while this object
 * is used.
 * The filter set should be frozen; otherwise the performance will suffer greatly.
 * @param norm2 wrapped UNormalizer2 instance
 * @param filterSet USet which determines the characters to be normalized
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return the requested UNormalizer2, if successful
 * @stable ICU 4.4
 */
U_STABLE UNormalizer2 * U_EXPORT2
unorm2_openFiltered(const UNormalizer2 *norm2, const USet *filterSet, UErrorCode *pErrorCode);

/**
 * Closes a UNormalizer2 instance from unorm2_openFiltered().
 * Do not close instances from unorm2_getInstance()!
 * @param norm2 UNormalizer2 instance to be closed
 * @stable ICU 4.4
 */
U_STABLE void U_EXPORT2
unorm2_close(UNormalizer2 *norm2);

#if U_SHOW_CPLUSPLUS_API

U_NAMESPACE_BEGIN

/**
 * \class LocalUNormalizer2Pointer
 * "Smart pointer" class, closes a UNormalizer2 via unorm2_close().
 * For most methods see the LocalPointerBase base class.
 *
 * @see LocalPointerBase
 * @see LocalPointer
 * @stable ICU 4.4
 */
U_DEFINE_LOCAL_OPEN_POINTER(LocalUNormalizer2Pointer, UNormalizer2, unorm2_close);

U_NAMESPACE_END

#endif

/**
 * Writes the normalized form of the source string to the destination string
 * (replacing its contents) and returns the length of the destination string.
 * The source and destination strings must be different buffers.
 * @param norm2 UNormalizer2 instance
 * @param src source string
 * @param length length of the source string, or -1 if NUL-terminated
 * @param dest destination string; its contents is replaced with normalized src
 * @param capacity number of UChars that can be written to dest
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return dest
 * @stable ICU 4.4
 */
U_STABLE int32_t U_EXPORT2
unorm2_normalize(const UNormalizer2 *norm2,
                 const UChar *src, int32_t length,
                 UChar *dest, int32_t capacity,
                 UErrorCode *pErrorCode);
/**
 * Appends the normalized form of the second string to the first string
 * (merging them at the boundary) and returns the length of the first string.
 * The result is normalized if the first string was normalized.
 * The first and second strings must be different buffers.
 * @param norm2 UNormalizer2 instance
 * @param first string, should be normalized
 * @param firstLength length of the first string, or -1 if NUL-terminated
 * @param firstCapacity number of UChars that can be written to first
 * @param second string, will be normalized
 * @param secondLength length of the source string, or -1 if NUL-terminated
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return first
 * @stable ICU 4.4
 */
U_STABLE int32_t U_EXPORT2
unorm2_normalizeSecondAndAppend(const UNormalizer2 *norm2,
                                UChar *first, int32_t firstLength, int32_t firstCapacity,
                                const UChar *second, int32_t secondLength,
                                UErrorCode *pErrorCode);
/**
 * Appends the second string to the first string
 * (merging them at the boundary) and returns the length of the first string.
 * The result is normalized if both the strings were normalized.
 * The first and second strings must be different buffers.
 * @param norm2 UNormalizer2 instance
 * @param first string, should be normalized
 * @param firstLength length of the first string, or -1 if NUL-terminated
 * @param firstCapacity number of UChars that can be written to first
 * @param second string, should be normalized
 * @param secondLength length of the source string, or -1 if NUL-terminated
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return first
 * @stable ICU 4.4
 */
U_STABLE int32_t U_EXPORT2
unorm2_append(const UNormalizer2 *norm2,
              UChar *first, int32_t firstLength, int32_t firstCapacity,
              const UChar *second, int32_t secondLength,
              UErrorCode *pErrorCode);

/**
 * Gets the decomposition mapping of c.
 * Roughly equivalent to normalizing the String form of c
 * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function
 * returns a negative value and does not write a string
 * if c does not have a decomposition mapping in this instance's data.
 * This function is independent of the mode of the UNormalizer2.
 * @param norm2 UNormalizer2 instance
 * @param c code point
 * @param decomposition String buffer which will be set to c's
 *                      decomposition mapping, if there is one.
 * @param capacity number of UChars that can be written to decomposition
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return the non-negative length of c's decomposition, if there is one; otherwise a negative value
 * @stable ICU 4.6
 */
U_STABLE int32_t U_EXPORT2
unorm2_getDecomposition(const UNormalizer2 *norm2,
                        UChar32 c, UChar *decomposition, int32_t capacity,
                        UErrorCode *pErrorCode);

#ifndef U_HIDE_DRAFT_API
/**
 * Gets the raw decomposition mapping of c.
 *
 * This is similar to the unorm2_getDecomposition() function but returns the
 * raw decomposition mapping as specified in UnicodeData.txt or
 * (for custom data) in the mapping files processed by the gennorm2 tool.
 * By contrast, unorm2_getDecomposition() returns the processed,
 * recursively-decomposed version of this mapping.
 *
 * When used on a standard NFKC Normalizer2 instance,
 * unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property.
 *
 * When used on a standard NFC Normalizer2 instance,
 * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can);
 * in this case, the result contains either one or two code points (=1..4 UChars).
 *
 * This function is independent of the mode of the UNormalizer2.
 * @param norm2 UNormalizer2 instance
 * @param c code point
 * @param decomposition String buffer which will be set to c's
 *                      raw decomposition mapping, if there is one.
 * @param capacity number of UChars that can be written to decomposition
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return the non-negative length of c's raw decomposition, if there is one; otherwise a negative value
 * @draft ICU 49
 */
U_DRAFT int32_t U_EXPORT2
unorm2_getRawDecomposition(const UNormalizer2 *norm2,
                           UChar32 c, UChar *decomposition, int32_t capacity,
                           UErrorCode *pErrorCode);

/**
 * Performs pairwise composition of a & b and returns the composite if there is one.
 *
 * Returns a composite code point c only if c has a two-way mapping to a+b.
 * In standard Unicode normalization, this means that
 * c has a canonical decomposition to a+b
 * and c does not have the Full_Composition_Exclusion property.
 *
 * This function is independent of the mode of the UNormalizer2.
 * @param norm2 UNormalizer2 instance
 * @param a A (normalization starter) code point.
 * @param b Another code point.
 * @return The non-negative composite code point if there is one; otherwise a negative value.
 * @draft ICU 49
 */
U_DRAFT UChar32 U_EXPORT2
unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b);

/**
 * Gets the combining class of c.
 * The default implementation returns 0
 * but all standard implementations return the Unicode Canonical_Combining_Class value.
 * @param norm2 UNormalizer2 instance
 * @param c code point
 * @return c's combining class
 * @draft ICU 49
 */
U_DRAFT uint8_t U_EXPORT2
unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c);
#endif  /* U_HIDE_DRAFT_API */

/**
 * Tests if the string is normalized.
 * Internally, in cases where the quickCheck() method would return "maybe"
 * (which is only possible for the two COMPOSE modes) this method
 * resolves to "yes" or "no" to provide a definitive result,
 * at the cost of doing more work in those cases.
 * @param norm2 UNormalizer2 instance
 * @param s input string
 * @param length length of the string, or -1 if NUL-terminated
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return TRUE if s is normalized
 * @stable ICU 4.4
 */
U_STABLE UBool U_EXPORT2
unorm2_isNormalized(const UNormalizer2 *norm2,
                    const UChar *s, int32_t length,
                    UErrorCode *pErrorCode);

/**
 * Tests if the string is normalized.
 * For the two COMPOSE modes, the result could be "maybe" in cases that
 * would take a little more work to resolve definitively.
 * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster
 * combination of quick check + normalization, to avoid
 * re-checking the "yes" prefix.
 * @param norm2 UNormalizer2 instance
 * @param s input string
 * @param length length of the string, or -1 if NUL-terminated
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return UNormalizationCheckResult
 * @stable ICU 4.4
 */
U_STABLE UNormalizationCheckResult U_EXPORT2
unorm2_quickCheck(const UNormalizer2 *norm2,
                  const UChar *s, int32_t length,
                  UErrorCode *pErrorCode);

/**
 * Returns the end of the normalized substring of the input string.
 * In other words, with <code>end=spanQuickCheckYes(s, ec);</code>
 * the substring <code>UnicodeString(s, 0, end)</code>
 * will pass the quick check with a "yes" result.
 *
 * The returned end index is usually one or more characters before the
 * "no" or "maybe" character: The end index is at a normalization boundary.
 * (See the class documentation for more about normalization boundaries.)
 *
 * When the goal is a normalized string and most input strings are expected
 * to be normalized already, then call this method,
 * and if it returns a prefix shorter than the input string,
 * copy that prefix and use normalizeSecondAndAppend() for the remainder.
 * @param norm2 UNormalizer2 instance
 * @param s input string
 * @param length length of the string, or -1 if NUL-terminated
 * @param pErrorCode Standard ICU error code. Its input value must
 *                   pass the U_SUCCESS() test, or else the function returns
 *                   immediately. Check for U_FAILURE() on output or use with
 *                   function chaining. (See User Guide for details.)
 * @return "yes" span end index
 * @stable ICU 4.4
 */
U_STABLE int32_t U_EXPORT2
unorm2_spanQuickCheckYes(const UNormalizer2 *norm2,
                         const UChar *s, int32_t length,
                         UErrorCode *pErrorCode);

/**
 * Tests if the character always has a normalization boundary before it,
 * regardless of context.
 * For details see the Normalizer2 base class documentation.
 * @param norm2 UNormalizer2 instance
 * @param c character to test
 * @return TRUE if c has a normalization boundary before it
 * @stable ICU 4.4
 */
U_STABLE UBool U_EXPORT2
unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c);

/**
 * Tests if the character always has a normalization boundary after it,
 * regardless of context.
 * For details see the Normalizer2 base class documentation.
 * @param norm2 UNormalizer2 instance
 * @param c character to test
 * @return TRUE if c has a normalization boundary after it
 * @stable ICU 4.4
 */
U_STABLE UBool U_EXPORT2
unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c);

/**
 * Tests if the character is normalization-inert.
 * For details see the Normalizer2 base class documentation.
 * @param norm2 UNormalizer2 instance
 * @param c character to test
 * @return TRUE if c is normalization-inert
 * @stable ICU 4.4
 */
U_STABLE UBool U_EXPORT2
unorm2_isInert(const UNormalizer2 *norm2, UChar32 c);

#endif  /* !UCONFIG_NO_NORMALIZATION */
#endif  /* __UNORM2_H__ */