icuSources/common/unicode/normlzr.h

   1 // © 2016 and later: Unicode, Inc. and others.
   2 // License & terms of use: http://www.unicode.org/copyright.html
   3 /*
   4  ********************************************************************
   5  * COPYRIGHT:
   6  * Copyright (c) 1996-2015, International Business Machines Corporation and
   7  * others. All Rights Reserved.
   8  ********************************************************************
   9  */
  10
  11 #ifndef NORMLZR_H
  12 #define NORMLZR_H
  13
  14 #include "unicode/utypes.h"
  15
  16 #if U_SHOW_CPLUSPLUS_API
  17
  18 /**
  19  * \file
  20  * \brief C++ API: Unicode Normalization
  21  */
  22
  23 #if !UCONFIG_NO_NORMALIZATION
  24
  25 #include "unicode/chariter.h"
  26 #include "unicode/normalizer2.h"
  27 #include "unicode/unistr.h"
  28 #include "unicode/unorm.h"
  29 #include "unicode/uobject.h"
  30
  31 #if U_SHOW_CPLUSPLUS_API
  32 U_NAMESPACE_BEGIN
  33 /**
  34  * Old Unicode normalization API.
  35  *
  36  * This API has been replaced by the Normalizer2 class and is only available
  37  * for backward compatibility. This class simply delegates to the Normalizer2 class.
  38  * There is one exception: The new API does not provide a replacement for Normalizer::compare().
  39  *
  40  * The Normalizer class supports the standard normalization forms described in
  41  * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode">
  42  * Unicode Standard Annex #15: Unicode Normalization Forms</a>.
  43  *
  44  * The Normalizer class consists of two parts:
  45  * - static functions that normalize strings or test if strings are normalized
  46  * - a Normalizer object is an iterator that takes any kind of text and
  47  *   provides iteration over its normalized form
  48  *
  49  * The Normalizer class is not suitable for subclassing.
  50  *
  51  * For basic information about normalization forms and details about the C API
  52  * please see the documentation in unorm.h.
  53  *
  54  * The iterator API with the Normalizer constructors and the non-static functions
  55  * use a CharacterIterator as input. It is possible to pass a string which
  56  * is then internally wrapped in a CharacterIterator.
  57  * The input text is not normalized all at once, but incrementally where needed
  58  * (providing efficient random access).
  59  * This allows to pass in a large text but spend only a small amount of time
  60  * normalizing a small part of that text.
  61  * However, if the entire text is normalized, then the iterator will be
  62  * slower than normalizing the entire text at once and iterating over the result.
  63  * A possible use of the Normalizer iterator is also to report an index into the
  64  * original text that is close to where the normalized characters come from.
  65  *
  66  * <em>Important:</em> The iterator API was cleaned up significantly for ICU 2.0.
  67  * The earlier implementation reported the getIndex() inconsistently,
  68  * and previous() could not be used after setIndex(), next(), first(), and current().
  69  *
  70  * Normalizer allows to start normalizing from anywhere in the input text by
  71  * calling setIndexOnly(), first(), or last().
  72  * Without calling any of these, the iterator will start at the beginning of the text.
  73  *
  74  * At any time, next() returns the next normalized code point (UChar32),
  75  * with post-increment semantics (like CharacterIterator::next32PostInc()).
  76  * previous() returns the previous normalized code point (UChar32),
  77  * with pre-decrement semantics (like CharacterIterator::previous32()).
  78  *
  79  * current() returns the current code point
  80  * (respectively the one at the newly set index) without moving
  81  * the getIndex(). Note that if the text at the current position
  82  * needs to be normalized, then these functions will do that.
  83  * (This is why current() is not const.)
  84  * It is more efficient to call setIndexOnly() instead, which does not
  85  * normalize.
  86  *
  87  * getIndex() always refers to the position in the input text where the normalized
  88  * code points are returned from. It does not always change with each returned
  89  * code point.
  90  * The code point that is returned from any of the functions
  91  * corresponds to text at or after getIndex(), according to the
  92  * function's iteration semantics (post-increment or pre-decrement).
  93  *
  94  * next() returns a code point from at or after the getIndex()
  95  * from before the next() call. After the next() call, the getIndex()
  96  * might have moved to where the next code point will be returned from
  97  * (from a next() or current() call).
  98  * This is semantically equivalent to array access with array[index++]
  99  * (post-increment semantics).
 100  *
 101  * previous() returns a code point from at or after the getIndex()
 102  * from after the previous() call.
 103  * This is semantically equivalent to array access with array[--index]
 104  * (pre-decrement semantics).
 105  *
 106  * Internally, the Normalizer iterator normalizes a small piece of text
 107  * starting at the getIndex() and ending at a following "safe" index.
 108  * The normalized results is stored in an internal string buffer, and
 109  * the code points are iterated from there.
 110  * With multiple iteration calls, this is repeated until the next piece
 111  * of text needs to be normalized, and the getIndex() needs to be moved.
 112  *
 113  * The following "safe" index, the internal buffer, and the secondary
 114  * iteration index into that buffer are not exposed on the API.
 115  * This also means that it is currently not practical to return to
 116  * a particular, arbitrary position in the text because one would need to
 117  * know, and be able to set, in addition to the getIndex(), at least also the
 118  * current index into the internal buffer.
 119  * It is currently only possible to observe when getIndex() changes
 120  * (with careful consideration of the iteration semantics),
 121  * at which time the internal index will be 0.
 122  * For example, if getIndex() is different after next() than before it,
 123  * then the internal index is 0 and one can return to this getIndex()
 124  * later with setIndexOnly().
 125  *
 126  * Note: While the setIndex() and getIndex() refer to indices in the
 127  * underlying Unicode input text, the next() and previous() methods
 128  * iterate through characters in the normalized output.
 129  * This means that there is not necessarily a one-to-one correspondence
 130  * between characters returned by next() and previous() and the indices
 131  * passed to and returned from setIndex() and getIndex().
 132  * It is for this reason that Normalizer does not implement the CharacterIterator interface.
 133  *
 134  * @author Laura Werner, Mark Davis, Markus Scherer
 135  * @stable ICU 2.0
 136  */
 137 class U_COMMON_API Normalizer : public UObject {
 138 public:
 139 #ifndef U_HIDE_DEPRECATED_API
 140   /**
 141    * If DONE is returned from an iteration function that returns a code point,
 142    * then there are no more normalization results available.
 143    * @deprecated ICU 56 Use Normalizer2 instead.
 144    */
 145   enum {
 146       DONE=0xffff
 147   };
 148
 149   // Constructors
 150
 151   /**
 152    * Creates a new <code>Normalizer</code> object for iterating over the
 153    * normalized form of a given string.
 154    * <p>
 155    * @param str   The string to be normalized.  The normalization
 156    *              will start at the beginning of the string.
 157    *
 158    * @param mode  The normalization mode.
 159    * @deprecated ICU 56 Use Normalizer2 instead.
 160    */
 161   Normalizer(const UnicodeString& str, UNormalizationMode mode);
 162
 163   /**
 164    * Creates a new <code>Normalizer</code> object for iterating over the
 165    * normalized form of a given string.
 166    * <p>
 167    * @param str   The string to be normalized.  The normalization
 168    *              will start at the beginning of the string.
 169    *
 170    * @param length Length of the string, or -1 if NUL-terminated.
 171    * @param mode  The normalization mode.
 172    * @deprecated ICU 56 Use Normalizer2 instead.
 173    */
 174   Normalizer(ConstChar16Ptr str, int32_t length, UNormalizationMode mode);
 175
 176   /**
 177    * Creates a new <code>Normalizer</code> object for iterating over the
 178    * normalized form of the given text.
 179    * <p>
 180    * @param iter  The input text to be normalized.  The normalization
 181    *              will start at the beginning of the string.
 182    *
 183    * @param mode  The normalization mode.
 184    * @deprecated ICU 56 Use Normalizer2 instead.
 185    */
 186   Normalizer(const CharacterIterator& iter, UNormalizationMode mode);
 187 #endif  /* U_HIDE_DEPRECATED_API */
 188
 189 #ifndef U_FORCE_HIDE_DEPRECATED_API
 190   /**
 191    * Copy constructor.
 192    * @param copy The object to be copied.
 193    * @deprecated ICU 56 Use Normalizer2 instead.
 194    */
 195   Normalizer(const Normalizer& copy);
 196
 197   /**
 198    * Destructor
 199    * @deprecated ICU 56 Use Normalizer2 instead.
 200    */
 201   virtual ~Normalizer();
 202 #endif  // U_FORCE_HIDE_DEPRECATED_API
 203
 204   //-------------------------------------------------------------------------
 205   // Static utility methods
 206   //-------------------------------------------------------------------------
 207
 208 #ifndef U_HIDE_DEPRECATED_API
 209   /**
 210    * Normalizes a <code>UnicodeString</code> according to the specified normalization mode.
 211    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 212    *
 213    * The <code>options</code> parameter specifies which optional
 214    * <code>Normalizer</code> features are to be enabled for this operation.
 215    *
 216    * @param source    the input string to be normalized.
 217    * @param mode      the normalization mode
 218    * @param options   the optional features to be enabled (0 for no options)
 219    * @param result    The normalized string (on output).
 220    * @param status    The error code.
 221    * @deprecated ICU 56 Use Normalizer2 instead.
 222    */
 223   static void U_EXPORT2 normalize(const UnicodeString& source,
 224                         UNormalizationMode mode, int32_t options,
 225                         UnicodeString& result,
 226                         UErrorCode &status);
 227
 228   /**
 229    * Compose a <code>UnicodeString</code>.
 230    * This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC.
 231    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 232    *
 233    * The <code>options</code> parameter specifies which optional
 234    * <code>Normalizer</code> features are to be enabled for this operation.
 235    *
 236    * @param source    the string to be composed.
 237    * @param compat    Perform compatibility decomposition before composition.
 238    *                  If this argument is <code>FALSE</code>, only canonical
 239    *                  decomposition will be performed.
 240    * @param options   the optional features to be enabled (0 for no options)
 241    * @param result    The composed string (on output).
 242    * @param status    The error code.
 243    * @deprecated ICU 56 Use Normalizer2 instead.
 244    */
 245   static void U_EXPORT2 compose(const UnicodeString& source,
 246                       UBool compat, int32_t options,
 247                       UnicodeString& result,
 248                       UErrorCode &status);
 249
 250   /**
 251    * Static method to decompose a <code>UnicodeString</code>.
 252    * This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD.
 253    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 254    *
 255    * The <code>options</code> parameter specifies which optional
 256    * <code>Normalizer</code> features are to be enabled for this operation.
 257    *
 258    * @param source    the string to be decomposed.
 259    * @param compat    Perform compatibility decomposition.
 260    *                  If this argument is <code>FALSE</code>, only canonical
 261    *                  decomposition will be performed.
 262    * @param options   the optional features to be enabled (0 for no options)
 263    * @param result    The decomposed string (on output).
 264    * @param status    The error code.
 265    * @deprecated ICU 56 Use Normalizer2 instead.
 266    */
 267   static void U_EXPORT2 decompose(const UnicodeString& source,
 268                         UBool compat, int32_t options,
 269                         UnicodeString& result,
 270                         UErrorCode &status);
 271
 272   /**
 273    * Performing quick check on a string, to quickly determine if the string is
 274    * in a particular normalization format.
 275    * This is a wrapper for unorm_quickCheck(), using a UnicodeString.
 276    *
 277    * Three types of result can be returned UNORM_YES, UNORM_NO or
 278    * UNORM_MAYBE. Result UNORM_YES indicates that the argument
 279    * string is in the desired normalized format, UNORM_NO determines that
 280    * argument string is not in the desired normalized format. A
 281    * UNORM_MAYBE result indicates that a more thorough check is required,
 282    * the user may have to put the string in its normalized form and compare the
 283    * results.
 284    * @param source       string for determining if it is in a normalized format
 285    * @param mode         normalization format
 286    * @param status A reference to a UErrorCode to receive any errors
 287    * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 288    *
 289    * @see isNormalized
 290    * @deprecated ICU 56 Use Normalizer2 instead.
 291    */
 292   static inline UNormalizationCheckResult
 293   quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status);
 294
 295   /**
 296    * Performing quick check on a string; same as the other version of quickCheck
 297    * but takes an extra options parameter like most normalization functions.
 298    *
 299    * @param source       string for determining if it is in a normalized format
 300    * @param mode         normalization format
 301    * @param options      the optional features to be enabled (0 for no options)
 302    * @param status A reference to a UErrorCode to receive any errors
 303    * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 304    *
 305    * @see isNormalized
 306    * @deprecated ICU 56 Use Normalizer2 instead.
 307    */
 308   static UNormalizationCheckResult
 309   quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status);
 310
 311   /**
 312    * Test if a string is in a given normalization form.
 313    * This is semantically equivalent to source.equals(normalize(source, mode)) .
 314    *
 315    * Unlike unorm_quickCheck(), this function returns a definitive result,
 316    * never a "maybe".
 317    * For NFD, NFKD, and FCD, both functions work exactly the same.
 318    * For NFC and NFKC where quickCheck may return "maybe", this function will
 319    * perform further tests to arrive at a TRUE/FALSE result.
 320    *
 321    * @param src        String that is to be tested if it is in a normalization format.
 322    * @param mode       Which normalization form to test for.
 323    * @param errorCode  ICU error code in/out parameter.
 324    *                   Must fulfill U_SUCCESS before the function call.
 325    * @return Boolean value indicating whether the source string is in the
 326    *         "mode" normalization form.
 327    *
 328    * @see quickCheck
 329    * @deprecated ICU 56 Use Normalizer2 instead.
 330    */
 331   static inline UBool
 332   isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode);
 333
 334   /**
 335    * Test if a string is in a given normalization form; same as the other version of isNormalized
 336    * but takes an extra options parameter like most normalization functions.
 337    *
 338    * @param src        String that is to be tested if it is in a normalization format.
 339    * @param mode       Which normalization form to test for.
 340    * @param options      the optional features to be enabled (0 for no options)
 341    * @param errorCode  ICU error code in/out parameter.
 342    *                   Must fulfill U_SUCCESS before the function call.
 343    * @return Boolean value indicating whether the source string is in the
 344    *         "mode" normalization form.
 345    *
 346    * @see quickCheck
 347    * @deprecated ICU 56 Use Normalizer2 instead.
 348    */
 349   static UBool
 350   isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode);
 351
 352   /**
 353    * Concatenate normalized strings, making sure that the result is normalized as well.
 354    *
 355    * If both the left and the right strings are in
 356    * the normalization form according to "mode/options",
 357    * then the result will be
 358    *
 359    * \code
 360    *     dest=normalize(left+right, mode, options)
 361    * \endcode
 362    *
 363    * For details see unorm_concatenate in unorm.h.
 364    *
 365    * @param left Left source string.
 366    * @param right Right source string.
 367    * @param result The output string.
 368    * @param mode The normalization mode.
 369    * @param options A bit set of normalization options.
 370    * @param errorCode ICU error code in/out parameter.
 371    *                   Must fulfill U_SUCCESS before the function call.
 372    * @return result
 373    *
 374    * @see unorm_concatenate
 375    * @see normalize
 376    * @see unorm_next
 377    * @see unorm_previous
 378    *
 379    * @deprecated ICU 56 Use Normalizer2 instead.
 380    */
 381   static UnicodeString &
 382   U_EXPORT2 concatenate(const UnicodeString &left, const UnicodeString &right,
 383               UnicodeString &result,
 384               UNormalizationMode mode, int32_t options,
 385               UErrorCode &errorCode);
 386 #endif  /* U_HIDE_DEPRECATED_API */
 387
 388   /**
 389    * Compare two strings for canonical equivalence.
 390    * Further options include case-insensitive comparison and
 391    * code point order (as opposed to code unit order).
 392    *
 393    * Canonical equivalence between two strings is defined as their normalized
 394    * forms (NFD or NFC) being identical.
 395    * This function compares strings incrementally instead of normalizing
 396    * (and optionally case-folding) both strings entirely,
 397    * improving performance significantly.
 398    *
 399    * Bulk normalization is only necessary if the strings do not fulfill the FCD
 400    * conditions. Only in this case, and only if the strings are relatively long,
 401    * is memory allocated temporarily.
 402    * For FCD strings and short non-FCD strings there is no memory allocation.
 403    *
 404    * Semantically, this is equivalent to
 405    *   strcmp[CodePointOrder](NFD(foldCase(s1)), NFD(foldCase(s2)))
 406    * where code point order and foldCase are all optional.
 407    *
 408    * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match
 409    * the case folding must be performed first, then the normalization.
 410    *
 411    * @param s1 First source string.
 412    * @param s2 Second source string.
 413    *
 414    * @param options A bit set of options:
 415    *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 416    *     Case-sensitive comparison in code unit order, and the input strings
 417    *     are quick-checked for FCD.
 418    *
 419    *   - UNORM_INPUT_IS_FCD
 420    *     Set if the caller knows that both s1 and s2 fulfill the FCD conditions.
 421    *     If not set, the function will quickCheck for FCD
 422    *     and normalize if necessary.
 423    *
 424    *   - U_COMPARE_CODE_POINT_ORDER
 425    *     Set to choose code point order instead of code unit order
 426    *     (see u_strCompare for details).
 427    *
 428    *   - U_COMPARE_IGNORE_CASE
 429    *     Set to compare strings case-insensitively using case folding,
 430    *     instead of case-sensitively.
 431    *     If set, then the following case folding options are used.
 432    *
 433    *   - Options as used with case-insensitive comparisons, currently:
 434    *
 435    *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 436    *    (see u_strCaseCompare for details)
 437    *
 438    *   - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT
 439    *
 440    * @param errorCode ICU error code in/out parameter.
 441    *                  Must fulfill U_SUCCESS before the function call.
 442    * @return <0 or 0 or >0 as usual for string comparisons
 443    *
 444    * @see unorm_compare
 445    * @see normalize
 446    * @see UNORM_FCD
 447    * @see u_strCompare
 448    * @see u_strCaseCompare
 449    *
 450    * @stable ICU 2.2
 451    */
 452   static inline int32_t
 453   compare(const UnicodeString &s1, const UnicodeString &s2,
 454           uint32_t options,
 455           UErrorCode &errorCode);
 456
 457 #ifndef U_HIDE_DEPRECATED_API
 458   //-------------------------------------------------------------------------
 459   // Iteration API
 460   //-------------------------------------------------------------------------
 461
 462   /**
 463    * Return the current character in the normalized text.
 464    * current() may need to normalize some text at getIndex().
 465    * The getIndex() is not changed.
 466    *
 467    * @return the current normalized code point
 468    * @deprecated ICU 56 Use Normalizer2 instead.
 469    */
 470   UChar32              current(void);
 471
 472   /**
 473    * Return the first character in the normalized text.
 474    * This is equivalent to setIndexOnly(startIndex()) followed by next().
 475    * (Post-increment semantics.)
 476    *
 477    * @return the first normalized code point
 478    * @deprecated ICU 56 Use Normalizer2 instead.
 479    */
 480   UChar32              first(void);
 481
 482   /**
 483    * Return the last character in the normalized text.
 484    * This is equivalent to setIndexOnly(endIndex()) followed by previous().
 485    * (Pre-decrement semantics.)
 486    *
 487    * @return the last normalized code point
 488    * @deprecated ICU 56 Use Normalizer2 instead.
 489    */
 490   UChar32              last(void);
 491
 492   /**
 493    * Return the next character in the normalized text.
 494    * (Post-increment semantics.)
 495    * If the end of the text has already been reached, DONE is returned.
 496    * The DONE value could be confused with a U+FFFF non-character code point
 497    * in the text. If this is possible, you can test getIndex()<endIndex()
 498    * before calling next(), or (getIndex()<endIndex() || last()!=DONE)
 499    * after calling next(). (Calling last() will change the iterator state!)
 500    *
 501    * The C API unorm_next() is more efficient and does not have this ambiguity.
 502    *
 503    * @return the next normalized code point
 504    * @deprecated ICU 56 Use Normalizer2 instead.
 505    */
 506   UChar32              next(void);
 507
 508   /**
 509    * Return the previous character in the normalized text and decrement.
 510    * (Pre-decrement semantics.)
 511    * If the beginning of the text has already been reached, DONE is returned.
 512    * The DONE value could be confused with a U+FFFF non-character code point
 513    * in the text. If this is possible, you can test
 514    * (getIndex()>startIndex() || first()!=DONE). (Calling first() will change
 515    * the iterator state!)
 516    *
 517    * The C API unorm_previous() is more efficient and does not have this ambiguity.
 518    *
 519    * @return the previous normalized code point
 520    * @deprecated ICU 56 Use Normalizer2 instead.
 521    */
 522   UChar32              previous(void);
 523
 524   /**
 525    * Set the iteration position in the input text that is being normalized,
 526    * without any immediate normalization.
 527    * After setIndexOnly(), getIndex() will return the same index that is
 528    * specified here.
 529    *
 530    * @param index the desired index in the input text.
 531    * @deprecated ICU 56 Use Normalizer2 instead.
 532    */
 533   void                 setIndexOnly(int32_t index);
 534
 535   /**
 536    * Reset the index to the beginning of the text.
 537    * This is equivalent to setIndexOnly(startIndex)).
 538    * @deprecated ICU 56 Use Normalizer2 instead.
 539    */
 540   void                reset(void);
 541
 542   /**
 543    * Retrieve the current iteration position in the input text that is
 544    * being normalized.
 545    *
 546    * A following call to next() will return a normalized code point from
 547    * the input text at or after this index.
 548    *
 549    * After a call to previous(), getIndex() will point at or before the
 550    * position in the input text where the normalized code point
 551    * was returned from with previous().
 552    *
 553    * @return the current index in the input text
 554    * @deprecated ICU 56 Use Normalizer2 instead.
 555    */
 556   int32_t            getIndex(void) const;
 557
 558   /**
 559    * Retrieve the index of the start of the input text. This is the begin index
 560    * of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string
 561    * over which this <code>Normalizer</code> is iterating.
 562    *
 563    * @return the smallest index in the input text where the Normalizer operates
 564    * @deprecated ICU 56 Use Normalizer2 instead.
 565    */
 566   int32_t            startIndex(void) const;
 567
 568   /**
 569    * Retrieve the index of the end of the input text. This is the end index
 570    * of the <code>CharacterIterator</code> or the length of the string
 571    * over which this <code>Normalizer</code> is iterating.
 572    * This end index is exclusive, i.e., the Normalizer operates only on characters
 573    * before this index.
 574    *
 575    * @return the first index in the input text where the Normalizer does not operate
 576    * @deprecated ICU 56 Use Normalizer2 instead.
 577    */
 578   int32_t            endIndex(void) const;
 579
 580   /**
 581    * Returns TRUE when both iterators refer to the same character in the same
 582    * input text.
 583    *
 584    * @param that a Normalizer object to compare this one to
 585    * @return comparison result
 586    * @deprecated ICU 56 Use Normalizer2 instead.
 587    */
 588   UBool        operator==(const Normalizer& that) const;
 589
 590   /**
 591    * Returns FALSE when both iterators refer to the same character in the same
 592    * input text.
 593    *
 594    * @param that a Normalizer object to compare this one to
 595    * @return comparison result
 596    * @deprecated ICU 56 Use Normalizer2 instead.
 597    */
 598   inline UBool        operator!=(const Normalizer& that) const;
 599
 600   /**
 601    * Returns a pointer to a new Normalizer that is a clone of this one.
 602    * The caller is responsible for deleting the new clone.
 603    * @return a pointer to a new Normalizer
 604    * @deprecated ICU 56 Use Normalizer2 instead.
 605    */
 606   Normalizer*        clone() const;
 607
 608   /**
 609    * Generates a hash code for this iterator.
 610    *
 611    * @return the hash code
 612    * @deprecated ICU 56 Use Normalizer2 instead.
 613    */
 614   int32_t                hashCode(void) const;
 615
 616   //-------------------------------------------------------------------------
 617   // Property access methods
 618   //-------------------------------------------------------------------------
 619
 620   /**
 621    * Set the normalization mode for this object.
 622    * <p>
 623    * <b>Note:</b>If the normalization mode is changed while iterating
 624    * over a string, calls to {@link #next() } and {@link #previous() } may
 625    * return previously buffers characters in the old normalization mode
 626    * until the iteration is able to re-sync at the next base character.
 627    * It is safest to call {@link #setIndexOnly }, {@link #reset() },
 628    * {@link #setText }, {@link #first() },
 629    * {@link #last() }, etc. after calling <code>setMode</code>.
 630    * <p>
 631    * @param newMode the new mode for this <code>Normalizer</code>.
 632    * @see #getUMode
 633    * @deprecated ICU 56 Use Normalizer2 instead.
 634    */
 635   void setMode(UNormalizationMode newMode);
 636
 637   /**
 638    * Return the normalization mode for this object.
 639    *
 640    * This is an unusual name because there used to be a getMode() that
 641    * returned a different type.
 642    *
 643    * @return the mode for this <code>Normalizer</code>
 644    * @see #setMode
 645    * @deprecated ICU 56 Use Normalizer2 instead.
 646    */
 647   UNormalizationMode getUMode(void) const;
 648
 649   /**
 650    * Set options that affect this <code>Normalizer</code>'s operation.
 651    * Options do not change the basic composition or decomposition operation
 652    * that is being performed, but they control whether
 653    * certain optional portions of the operation are done.
 654    * Currently the only available option is obsolete.
 655    *
 656    * It is possible to specify multiple options that are all turned on or off.
 657    *
 658    * @param   option  the option(s) whose value is/are to be set.
 659    * @param   value   the new setting for the option.  Use <code>TRUE</code> to
 660    *                  turn the option(s) on and <code>FALSE</code> to turn it/them off.
 661    *
 662    * @see #getOption
 663    * @deprecated ICU 56 Use Normalizer2 instead.
 664    */
 665   void setOption(int32_t option,
 666          UBool value);
 667
 668   /**
 669    * Determine whether an option is turned on or off.
 670    * If multiple options are specified, then the result is TRUE if any
 671    * of them are set.
 672    * <p>
 673    * @param option the option(s) that are to be checked
 674    * @return TRUE if any of the option(s) are set
 675    * @see #setOption
 676    * @deprecated ICU 56 Use Normalizer2 instead.
 677    */
 678   UBool getOption(int32_t option) const;
 679
 680   /**
 681    * Set the input text over which this <code>Normalizer</code> will iterate.
 682    * The iteration position is set to the beginning.
 683    *
 684    * @param newText a string that replaces the current input text
 685    * @param status a UErrorCode
 686    * @deprecated ICU 56 Use Normalizer2 instead.
 687    */
 688   void setText(const UnicodeString& newText,
 689            UErrorCode &status);
 690
 691   /**
 692    * Set the input text over which this <code>Normalizer</code> will iterate.
 693    * The iteration position is set to the beginning.
 694    *
 695    * @param newText a CharacterIterator object that replaces the current input text
 696    * @param status a UErrorCode
 697    * @deprecated ICU 56 Use Normalizer2 instead.
 698    */
 699   void setText(const CharacterIterator& newText,
 700            UErrorCode &status);
 701
 702   /**
 703    * Set the input text over which this <code>Normalizer</code> will iterate.
 704    * The iteration position is set to the beginning.
 705    *
 706    * @param newText a string that replaces the current input text
 707    * @param length the length of the string, or -1 if NUL-terminated
 708    * @param status a UErrorCode
 709    * @deprecated ICU 56 Use Normalizer2 instead.
 710    */
 711   void setText(ConstChar16Ptr newText,
 712                     int32_t length,
 713             UErrorCode &status);
 714   /**
 715    * Copies the input text into the UnicodeString argument.
 716    *
 717    * @param result Receives a copy of the text under iteration.
 718    * @deprecated ICU 56 Use Normalizer2 instead.
 719    */
 720   void            getText(UnicodeString&  result);
 721
 722   /**
 723    * ICU "poor man's RTTI", returns a UClassID for this class.
 724    * @returns a UClassID for this class.
 725    * @deprecated ICU 56 Use Normalizer2 instead.
 726    */
 727   static UClassID U_EXPORT2 getStaticClassID();
 728 #endif  /* U_HIDE_DEPRECATED_API */
 729
 730 #ifndef U_FORCE_HIDE_DEPRECATED_API
 731   /**
 732    * ICU "poor man's RTTI", returns a UClassID for the actual class.
 733    * @return a UClassID for the actual class.
 734    * @deprecated ICU 56 Use Normalizer2 instead.
 735    */
 736   virtual UClassID getDynamicClassID() const;
 737 #endif  // U_FORCE_HIDE_DEPRECATED_API
 738
 739 private:
 740   //-------------------------------------------------------------------------
 741   // Private functions
 742   //-------------------------------------------------------------------------
 743
 744   Normalizer(); // default constructor not implemented
 745   Normalizer &operator=(const Normalizer &that); // assignment operator not implemented
 746
 747   // Private utility methods for iteration
 748   // For documentation, see the source code
 749   UBool nextNormalize();
 750   UBool previousNormalize();
 751
 752   void    init();
 753   void    clearBuffer(void);
 754
 755   //-------------------------------------------------------------------------
 756   // Private data
 757   //-------------------------------------------------------------------------
 758
 759   FilteredNormalizer2*fFilteredNorm2;  // owned if not NULL
 760   const Normalizer2  *fNorm2;  // not owned; may be equal to fFilteredNorm2
 761   UNormalizationMode  fUMode;  // deprecated
 762   int32_t             fOptions;
 763
 764   // The input text and our position in it
 765   CharacterIterator  *text;
 766
 767   // The normalization buffer is the result of normalization
 768   // of the source in [currentIndex..nextIndex[ .
 769   int32_t         currentIndex, nextIndex;
 770
 771   // A buffer for holding intermediate results
 772   UnicodeString       buffer;
 773   int32_t         bufferPos;
 774 };
 775
 776 //-------------------------------------------------------------------------
 777 // Inline implementations
 778 //-------------------------------------------------------------------------
 779
 780 #ifndef U_HIDE_DEPRECATED_API
 781 inline UBool
 782 Normalizer::operator!= (const Normalizer& other) const
 783 { return ! operator==(other); }
 784
 785 inline UNormalizationCheckResult
 786 Normalizer::quickCheck(const UnicodeString& source,
 787                        UNormalizationMode mode,
 788                        UErrorCode &status) {
 789     return quickCheck(source, mode, 0, status);
 790 }
 791
 792 inline UBool
 793 Normalizer::isNormalized(const UnicodeString& source,
 794                          UNormalizationMode mode,
 795                          UErrorCode &status) {
 796     return isNormalized(source, mode, 0, status);
 797 }
 798 #endif  /* U_HIDE_DEPRECATED_API */
 799
 800 inline int32_t
 801 Normalizer::compare(const UnicodeString &s1, const UnicodeString &s2,
 802                     uint32_t options,
 803                     UErrorCode &errorCode) {
 804   // all argument checking is done in unorm_compare
 805   return unorm_compare(toUCharPtr(s1.getBuffer()), s1.length(),
 806                        toUCharPtr(s2.getBuffer()), s2.length(),
 807                        options,
 808                        &errorCode);
 809 }
 810
 811 U_NAMESPACE_END
 812 #endif // U_SHOW_CPLUSPLUS_API
 813
 814 #endif /* #if !UCONFIG_NO_NORMALIZATION */
 815
 816 #endif // NORMLZR_H
 817
 818 #endif /* U_SHOW_CPLUSPLUS_API */