icuSources/common/unicode/normlzr.h

   1 /*
   2  ********************************************************************
   3  * COPYRIGHT:
   4  * Copyright (c) 1996-2004, International Business Machines Corporation and
   5  * others. All Rights Reserved.
   6  ********************************************************************
   7  */
   8
   9 #ifndef NORMLZR_H
  10 #define NORMLZR_H
  11
  12 #include "unicode/utypes.h"
  13
  14 #if !UCONFIG_NO_NORMALIZATION
  15
  16 #include "unicode/uobject.h"
  17 #include "unicode/unistr.h"
  18 #include "unicode/chariter.h"
  19 #include "unicode/unorm.h"
  20
  21 struct UCharIterator;
  22 typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */
  23
  24 U_NAMESPACE_BEGIN
  25 /**
  26  * \brief C++ API: Unicode Normalization
  27  *
  28  * The Normalizer class consists of two parts:
  29  * - static functions that normalize strings or test if strings are normalized
  30  * - a Normalizer object is an iterator that takes any kind of text and
  31  *   provides iteration over its normalized form
  32  *
  33  * The Normalizer class is not suitable for subclassing.
  34  *
  35  * The static functions are basically wrappers around the C implementation,
  36  * using UnicodeString instead of UChar*.
  37  * For basic information about normalization forms and details about the C API
  38  * please see the documentation in unorm.h.
  39  *
  40  * The iterator API with the Normalizer constructors and the non-static functions
  41  * uses a CharacterIterator as input. It is possible to pass a string which
  42  * is then internally wrapped in a CharacterIterator.
  43  * The input text is not normalized all at once, but incrementally where needed
  44  * (providing efficient random access).
  45  * This allows to pass in a large text but spend only a small amount of time
  46  * normalizing a small part of that text.
  47  * However, if the entire text is normalized, then the iterator will be
  48  * slower than normalizing the entire text at once and iterating over the result.
  49  * A possible use of the Normalizer iterator is also to report an index into the
  50  * original text that is close to where the normalized characters come from.
  51  *
  52  * <em>Important:</em> The iterator API was cleaned up significantly for ICU 2.0.
  53  * The earlier implementation reported the getIndex() inconsistently,
  54  * and previous() could not be used after setIndex(), next(), first(), and current().
  55  *
  56  * Normalizer allows to start normalizing from anywhere in the input text by
  57  * calling setIndexOnly(), first(), or last().
  58  * Without calling any of these, the iterator will start at the beginning of the text.
  59  *
  60  * At any time, next() returns the next normalized code point (UChar32),
  61  * with post-increment semantics (like CharacterIterator::next32PostInc()).
  62  * previous() returns the previous normalized code point (UChar32),
  63  * with pre-decrement semantics (like CharacterIterator::previous32()).
  64  *
  65  * current() returns the current code point
  66  * (respectively the one at the newly set index) without moving
  67  * the getIndex(). Note that if the text at the current position
  68  * needs to be normalized, then these functions will do that.
  69  * (This is why current() is not const.)
  70  * It is more efficient to call setIndexOnly() instead, which does not
  71  * normalize.
  72  *
  73  * getIndex() always refers to the position in the input text where the normalized
  74  * code points are returned from. It does not always change with each returned
  75  * code point.
  76  * The code point that is returned from any of the functions
  77  * corresponds to text at or after getIndex(), according to the
  78  * function's iteration semantics (post-increment or pre-decrement).
  79  *
  80  * next() returns a code point from at or after the getIndex()
  81  * from before the next() call. After the next() call, the getIndex()
  82  * might have moved to where the next code point will be returned from
  83  * (from a next() or current() call).
  84  * This is semantically equivalent to array access with array[index++]
  85  * (post-increment semantics).
  86  *
  87  * previous() returns a code point from at or after the getIndex()
  88  * from after the previous() call.
  89  * This is semantically equivalent to array access with array[--index]
  90  * (pre-decrement semantics).
  91  *
  92  * Internally, the Normalizer iterator normalizes a small piece of text
  93  * starting at the getIndex() and ending at a following "safe" index.
  94  * The normalized results is stored in an internal string buffer, and
  95  * the code points are iterated from there.
  96  * With multiple iteration calls, this is repeated until the next piece
  97  * of text needs to be normalized, and the getIndex() needs to be moved.
  98  *
  99  * The following "safe" index, the internal buffer, and the secondary
 100  * iteration index into that buffer are not exposed on the API.
 101  * This also means that it is currently not practical to return to
 102  * a particular, arbitrary position in the text because one would need to
 103  * know, and be able to set, in addition to the getIndex(), at least also the
 104  * current index into the internal buffer.
 105  * It is currently only possible to observe when getIndex() changes
 106  * (with careful consideration of the iteration semantics),
 107  * at which time the internal index will be 0.
 108  * For example, if getIndex() is different after next() than before it,
 109  * then the internal index is 0 and one can return to this getIndex()
 110  * later with setIndexOnly().
 111  *
 112  * @author Laura Werner, Mark Davis, Markus Scherer
 113  * @stable ICU 2.0
 114  */
 115 class U_COMMON_API Normalizer : public UObject {
 116 public:
 117   /**
 118    * If DONE is returned from an iteration function that returns a code point,
 119    * then there are no more normalization results available.
 120    * @stable ICU 2.0
 121    */
 122   enum {
 123       DONE=0xffff
 124   };
 125
 126   // Constructors
 127
 128   /**
 129    * Creates a new <code>Normalizer</code> object for iterating over the
 130    * normalized form of a given string.
 131    * <p>
 132    * @param str   The string to be normalized.  The normalization
 133    *              will start at the beginning of the string.
 134    *
 135    * @param mode  The normalization mode.
 136    * @stable ICU 2.0
 137    */
 138   Normalizer(const UnicodeString& str, UNormalizationMode mode);
 139
 140   /**
 141    * Creates a new <code>Normalizer</code> object for iterating over the
 142    * normalized form of a given string.
 143    * <p>
 144    * @param str   The string to be normalized.  The normalization
 145    *              will start at the beginning of the string.
 146    *
 147    * @param length Length of the string, or -1 if NUL-terminated.
 148    * @param mode  The normalization mode.
 149    * @stable ICU 2.0
 150    */
 151   Normalizer(const UChar* str, int32_t length, UNormalizationMode mode);
 152
 153   /**
 154    * Creates a new <code>Normalizer</code> object for iterating over the
 155    * normalized form of the given text.
 156    * <p>
 157    * @param iter  The input text to be normalized.  The normalization
 158    *              will start at the beginning of the string.
 159    *
 160    * @param mode  The normalization mode.
 161    * @stable ICU 2.0
 162    */
 163   Normalizer(const CharacterIterator& iter, UNormalizationMode mode);
 164
 165   /**
 166    * Copy constructor.
 167    * @param copy The object to be copied.
 168    * @stable ICU 2.0
 169    */
 170   Normalizer(const Normalizer& copy);
 171
 172   /**
 173    * Destructor
 174    * @stable ICU 2.0
 175    */
 176   virtual ~Normalizer();
 177
 178
 179   //-------------------------------------------------------------------------
 180   // Static utility methods
 181   //-------------------------------------------------------------------------
 182
 183   /**
 184    * Normalizes a <code>UnicodeString</code> according to the specified normalization mode.
 185    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 186    *
 187    * The <code>options</code> parameter specifies which optional
 188    * <code>Normalizer</code> features are to be enabled for this operation.
 189    *
 190    * @param source    the input string to be normalized.
 191    * @param mode      the normalization mode
 192    * @param options   the optional features to be enabled (0 for no options)
 193    * @param result    The normalized string (on output).
 194    * @param status    The error code.
 195    * @stable ICU 2.0
 196    */
 197   static void U_EXPORT2 normalize(const UnicodeString& source,
 198                         UNormalizationMode mode, int32_t options,
 199                         UnicodeString& result,
 200                         UErrorCode &status);
 201
 202   /**
 203    * Compose a <code>UnicodeString</code>.
 204    * This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC.
 205    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 206    *
 207    * The <code>options</code> parameter specifies which optional
 208    * <code>Normalizer</code> features are to be enabled for this operation.
 209    *
 210    * @param source    the string to be composed.
 211    * @param compat    Perform compatibility decomposition before composition.
 212    *                  If this argument is <code>FALSE</code>, only canonical
 213    *                  decomposition will be performed.
 214    * @param options   the optional features to be enabled (0 for no options)
 215    * @param result    The composed string (on output).
 216    * @param status    The error code.
 217    * @stable ICU 2.0
 218    */
 219   static void U_EXPORT2 compose(const UnicodeString& source,
 220                       UBool compat, int32_t options,
 221                       UnicodeString& result,
 222                       UErrorCode &status);
 223
 224   /**
 225    * Static method to decompose a <code>UnicodeString</code>.
 226    * This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD.
 227    * This is a wrapper for unorm_normalize(), using UnicodeString's.
 228    *
 229    * The <code>options</code> parameter specifies which optional
 230    * <code>Normalizer</code> features are to be enabled for this operation.
 231    *
 232    * @param source    the string to be decomposed.
 233    * @param compat    Perform compatibility decomposition.
 234    *                  If this argument is <code>FALSE</code>, only canonical
 235    *                  decomposition will be performed.
 236    * @param options   the optional features to be enabled (0 for no options)
 237    * @param result    The decomposed string (on output).
 238    * @param status    The error code.
 239    * @stable ICU 2.0
 240    */
 241   static void U_EXPORT2 decompose(const UnicodeString& source,
 242                         UBool compat, int32_t options,
 243                         UnicodeString& result,
 244                         UErrorCode &status);
 245
 246   /**
 247    * Performing quick check on a string, to quickly determine if the string is
 248    * in a particular normalization format.
 249    * This is a wrapper for unorm_quickCheck(), using a UnicodeString.
 250    *
 251    * Three types of result can be returned UNORM_YES, UNORM_NO or
 252    * UNORM_MAYBE. Result UNORM_YES indicates that the argument
 253    * string is in the desired normalized format, UNORM_NO determines that
 254    * argument string is not in the desired normalized format. A
 255    * UNORM_MAYBE result indicates that a more thorough check is required,
 256    * the user may have to put the string in its normalized form and compare the
 257    * results.
 258    * @param source       string for determining if it is in a normalized format
 259    * @param mode         normalization format
 260    * @param status A reference to a UErrorCode to receive any errors
 261    * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 262    *
 263    * @see isNormalized
 264    * @stable ICU 2.0
 265    */
 266   static inline UNormalizationCheckResult
 267   quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status);
 268
 269   /**
 270    * Performing quick check on a string; same as the other version of quickCheck
 271    * but takes an extra options parameter like most normalization functions.
 272    *
 273    * @param source       string for determining if it is in a normalized format
 274    * @param mode         normalization format
 275    * @param options      the optional features to be enabled (0 for no options)
 276    * @param status A reference to a UErrorCode to receive any errors
 277    * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 278    *
 279    * @see isNormalized
 280    * @stable ICU 2.6
 281    */
 282   static inline UNormalizationCheckResult
 283   quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status);
 284
 285   /**
 286    * Test if a string is in a given normalization form.
 287    * This is semantically equivalent to source.equals(normalize(source, mode)) .
 288    *
 289    * Unlike unorm_quickCheck(), this function returns a definitive result,
 290    * never a "maybe".
 291    * For NFD, NFKD, and FCD, both functions work exactly the same.
 292    * For NFC and NFKC where quickCheck may return "maybe", this function will
 293    * perform further tests to arrive at a TRUE/FALSE result.
 294    *
 295    * @param src        String that is to be tested if it is in a normalization format.
 296    * @param mode       Which normalization form to test for.
 297    * @param errorCode  ICU error code in/out parameter.
 298    *                   Must fulfill U_SUCCESS before the function call.
 299    * @return Boolean value indicating whether the source string is in the
 300    *         "mode" normalization form.
 301    *
 302    * @see quickCheck
 303    * @stable ICU 2.2
 304    */
 305   static inline UBool
 306   isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode);
 307
 308   /**
 309    * Test if a string is in a given normalization form; same as the other version of isNormalized
 310    * but takes an extra options parameter like most normalization functions.
 311    *
 312    * @param src        String that is to be tested if it is in a normalization format.
 313    * @param mode       Which normalization form to test for.
 314    * @param options      the optional features to be enabled (0 for no options)
 315    * @param errorCode  ICU error code in/out parameter.
 316    *                   Must fulfill U_SUCCESS before the function call.
 317    * @return Boolean value indicating whether the source string is in the
 318    *         "mode" normalization form.
 319    *
 320    * @see quickCheck
 321    * @stable ICU 2.6
 322    */
 323   static inline UBool
 324   isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode);
 325
 326   /**
 327    * Concatenate normalized strings, making sure that the result is normalized as well.
 328    *
 329    * If both the left and the right strings are in
 330    * the normalization form according to "mode/options",
 331    * then the result will be
 332    *
 333    * \code
 334    *     dest=normalize(left+right, mode, options)
 335    * \endcode
 336    *
 337    * For details see unorm_concatenate in unorm.h.
 338    *
 339    * @param left Left source string.
 340    * @param right Right source string.
 341    * @param result The output string.
 342    * @param mode The normalization mode.
 343    * @param options A bit set of normalization options.
 344    * @param errorCode ICU error code in/out parameter.
 345    *                   Must fulfill U_SUCCESS before the function call.
 346    * @return result
 347    *
 348    * @see unorm_concatenate
 349    * @see normalize
 350    * @see unorm_next
 351    * @see unorm_previous
 352    *
 353    * @stable ICU 2.1
 354    */
 355   static UnicodeString &
 356   U_EXPORT2 concatenate(UnicodeString &left, UnicodeString &right,
 357               UnicodeString &result,
 358               UNormalizationMode mode, int32_t options,
 359               UErrorCode &errorCode);
 360
 361   /**
 362    * Compare two strings for canonical equivalence.
 363    * Further options include case-insensitive comparison and
 364    * code point order (as opposed to code unit order).
 365    *
 366    * Canonical equivalence between two strings is defined as their normalized
 367    * forms (NFD or NFC) being identical.
 368    * This function compares strings incrementally instead of normalizing
 369    * (and optionally case-folding) both strings entirely,
 370    * improving performance significantly.
 371    *
 372    * Bulk normalization is only necessary if the strings do not fulfill the FCD
 373    * conditions. Only in this case, and only if the strings are relatively long,
 374    * is memory allocated temporarily.
 375    * For FCD strings and short non-FCD strings there is no memory allocation.
 376    *
 377    * Semantically, this is equivalent to
 378    *   strcmp[CodePointOrder](NFD(foldCase(s1)), NFD(foldCase(s2)))
 379    * where code point order and foldCase are all optional.
 380    *
 381    * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match
 382    * the case folding must be performed first, then the normalization.
 383    *
 384    * @param s1 First source string.
 385    * @param s2 Second source string.
 386    *
 387    * @param options A bit set of options:
 388    *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 389    *     Case-sensitive comparison in code unit order, and the input strings
 390    *     are quick-checked for FCD.
 391    *
 392    *   - UNORM_INPUT_IS_FCD
 393    *     Set if the caller knows that both s1 and s2 fulfill the FCD conditions.
 394    *     If not set, the function will quickCheck for FCD
 395    *     and normalize if necessary.
 396    *
 397    *   - U_COMPARE_CODE_POINT_ORDER
 398    *     Set to choose code point order instead of code unit order
 399    *     (see u_strCompare for details).
 400    *
 401    *   - U_COMPARE_IGNORE_CASE
 402    *     Set to compare strings case-insensitively using case folding,
 403    *     instead of case-sensitively.
 404    *     If set, then the following case folding options are used.
 405    *
 406    *   - Options as used with case-insensitive comparisons, currently:
 407    *
 408    *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 409    *    (see u_strCaseCompare for details)
 410    *
 411    *   - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT
 412    *
 413    * @param errorCode ICU error code in/out parameter.
 414    *                  Must fulfill U_SUCCESS before the function call.
 415    * @return <0 or 0 or >0 as usual for string comparisons
 416    *
 417    * @see unorm_compare
 418    * @see normalize
 419    * @see UNORM_FCD
 420    * @see u_strCompare
 421    * @see u_strCaseCompare
 422    *
 423    * @stable ICU 2.2
 424    */
 425   static inline int32_t
 426   compare(const UnicodeString &s1, const UnicodeString &s2,
 427           uint32_t options,
 428           UErrorCode &errorCode);
 429
 430   //-------------------------------------------------------------------------
 431   // Iteration API
 432   //-------------------------------------------------------------------------
 433
 434   /**
 435    * Return the current character in the normalized text.
 436    * current() may need to normalize some text at getIndex().
 437    * The getIndex() is not changed.
 438    *
 439    * @return the current normalized code point
 440    * @stable ICU 2.0
 441    */
 442   UChar32              current(void);
 443
 444   /**
 445    * Return the first character in the normalized text.
 446    * This is equivalent to setIndexOnly(startIndex()) followed by next().
 447    * (Post-increment semantics.)
 448    *
 449    * @return the first normalized code point
 450    * @stable ICU 2.0
 451    */
 452   UChar32              first(void);
 453
 454   /**
 455    * Return the last character in the normalized text.
 456    * This is equivalent to setIndexOnly(endIndex()) followed by previous().
 457    * (Pre-decrement semantics.)
 458    *
 459    * @return the last normalized code point
 460    * @stable ICU 2.0
 461    */
 462   UChar32              last(void);
 463
 464   /**
 465    * Return the next character in the normalized text.
 466    * (Post-increment semantics.)
 467    * If the end of the text has already been reached, DONE is returned.
 468    * The DONE value could be confused with a U+FFFF non-character code point
 469    * in the text. If this is possible, you can test getIndex()<endIndex()
 470    * before calling next(), or (getIndex()<endIndex() || last()!=DONE)
 471    * after calling next(). (Calling last() will change the iterator state!)
 472    *
 473    * The C API unorm_next() is more efficient and does not have this ambiguity.
 474    *
 475    * @return the next normalized code point
 476    * @stable ICU 2.0
 477    */
 478   UChar32              next(void);
 479
 480   /**
 481    * Return the previous character in the normalized text and decrement.
 482    * (Pre-decrement semantics.)
 483    * If the beginning of the text has already been reached, DONE is returned.
 484    * The DONE value could be confused with a U+FFFF non-character code point
 485    * in the text. If this is possible, you can test
 486    * (getIndex()>startIndex() || first()!=DONE). (Calling first() will change
 487    * the iterator state!)
 488    *
 489    * The C API unorm_previous() is more efficient and does not have this ambiguity.
 490    *
 491    * @return the previous normalized code point
 492    * @stable ICU 2.0
 493    */
 494   UChar32              previous(void);
 495
 496   /**
 497    * Set the iteration position in the input text that is being normalized,
 498    * without any immediate normalization.
 499    * After setIndexOnly(), getIndex() will return the same index that is
 500    * specified here.
 501    *
 502    * @param index the desired index in the input text.
 503    * @stable ICU 2.0
 504    */
 505   void                 setIndexOnly(int32_t index);
 506
 507   /**
 508    * Reset the index to the beginning of the text.
 509    * This is equivalent to setIndexOnly(startIndex)).
 510    * @stable ICU 2.0
 511    */
 512   void                reset(void);
 513
 514   /**
 515    * Retrieve the current iteration position in the input text that is
 516    * being normalized.
 517    *
 518    * A following call to next() will return a normalized code point from
 519    * the input text at or after this index.
 520    *
 521    * After a call to previous(), getIndex() will point at or before the
 522    * position in the input text where the normalized code point
 523    * was returned from with previous().
 524    *
 525    * @return the current index in the input text
 526    * @stable ICU 2.0
 527    */
 528   int32_t            getIndex(void) const;
 529
 530   /**
 531    * Retrieve the index of the start of the input text. This is the begin index
 532    * of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string
 533    * over which this <code>Normalizer</code> is iterating.
 534    *
 535    * @return the smallest index in the input text where the Normalizer operates
 536    * @stable ICU 2.0
 537    */
 538   int32_t            startIndex(void) const;
 539
 540   /**
 541    * Retrieve the index of the end of the input text. This is the end index
 542    * of the <code>CharacterIterator</code> or the length of the string
 543    * over which this <code>Normalizer</code> is iterating.
 544    * This end index is exclusive, i.e., the Normalizer operates only on characters
 545    * before this index.
 546    *
 547    * @return the first index in the input text where the Normalizer does not operate
 548    * @stable ICU 2.0
 549    */
 550   int32_t            endIndex(void) const;
 551
 552   /**
 553    * Returns TRUE when both iterators refer to the same character in the same
 554    * input text.
 555    *
 556    * @param that a Normalizer object to compare this one to
 557    * @return comparison result
 558    * @stable ICU 2.0
 559    */
 560   UBool        operator==(const Normalizer& that) const;
 561
 562   /**
 563    * Returns FALSE when both iterators refer to the same character in the same
 564    * input text.
 565    *
 566    * @param that a Normalizer object to compare this one to
 567    * @return comparison result
 568    * @stable ICU 2.0
 569    */
 570   inline UBool        operator!=(const Normalizer& that) const;
 571
 572   /**
 573    * Returns a pointer to a new Normalizer that is a clone of this one.
 574    * The caller is responsible for deleting the new clone.
 575    * @return a pointer to a new Normalizer
 576    * @stable ICU 2.0
 577    */
 578   Normalizer*        clone(void) const;
 579
 580   /**
 581    * Generates a hash code for this iterator.
 582    *
 583    * @return the hash code
 584    * @stable ICU 2.0
 585    */
 586   int32_t                hashCode(void) const;
 587
 588   //-------------------------------------------------------------------------
 589   // Property access methods
 590   //-------------------------------------------------------------------------
 591
 592   /**
 593    * Set the normalization mode for this object.
 594    * <p>
 595    * <b>Note:</b>If the normalization mode is changed while iterating
 596    * over a string, calls to {@link #next() } and {@link #previous() } may
 597    * return previously buffers characters in the old normalization mode
 598    * until the iteration is able to re-sync at the next base character.
 599    * It is safest to call {@link #setIndexOnly }, {@link #reset() },
 600    * {@link #setText }, {@link #first() },
 601    * {@link #last() }, etc. after calling <code>setMode</code>.
 602    * <p>
 603    * @param newMode the new mode for this <code>Normalizer</code>.
 604    * @see #getUMode
 605    * @stable ICU 2.0
 606    */
 607   void setMode(UNormalizationMode newMode);
 608
 609   /**
 610    * Return the normalization mode for this object.
 611    *
 612    * This is an unusual name because there used to be a getMode() that
 613    * returned a different type.
 614    *
 615    * @return the mode for this <code>Normalizer</code>
 616    * @see #setMode
 617    * @stable ICU 2.0
 618    */
 619   UNormalizationMode getUMode(void) const;
 620
 621   /**
 622    * Set options that affect this <code>Normalizer</code>'s operation.
 623    * Options do not change the basic composition or decomposition operation
 624    * that is being performed, but they control whether
 625    * certain optional portions of the operation are done.
 626    * Currently the only available option is obsolete.
 627    *
 628    * It is possible to specify multiple options that are all turned on or off.
 629    *
 630    * @param   option  the option(s) whose value is/are to be set.
 631    * @param   value   the new setting for the option.  Use <code>TRUE</code> to
 632    *                  turn the option(s) on and <code>FALSE</code> to turn it/them off.
 633    *
 634    * @see #getOption
 635    * @stable ICU 2.0
 636    */
 637   void setOption(int32_t option,
 638          UBool value);
 639
 640   /**
 641    * Determine whether an option is turned on or off.
 642    * If multiple options are specified, then the result is TRUE if any
 643    * of them are set.
 644    * <p>
 645    * @param option the option(s) that are to be checked
 646    * @return TRUE if any of the option(s) are set
 647    * @see #setOption
 648    * @stable ICU 2.0
 649    */
 650   UBool getOption(int32_t option) const;
 651
 652   /**
 653    * Set the input text over which this <code>Normalizer</code> will iterate.
 654    * The iteration position is set to the beginning.
 655    *
 656    * @param newText a string that replaces the current input text
 657    * @param status a UErrorCode
 658    * @stable ICU 2.0
 659    */
 660   void setText(const UnicodeString& newText,
 661            UErrorCode &status);
 662
 663   /**
 664    * Set the input text over which this <code>Normalizer</code> will iterate.
 665    * The iteration position is set to the beginning.
 666    *
 667    * @param newText a CharacterIterator object that replaces the current input text
 668    * @param status a UErrorCode
 669    * @stable ICU 2.0
 670    */
 671   void setText(const CharacterIterator& newText,
 672            UErrorCode &status);
 673
 674   /**
 675    * Set the input text over which this <code>Normalizer</code> will iterate.
 676    * The iteration position is set to the beginning.
 677    *
 678    * @param newText a string that replaces the current input text
 679    * @param length the length of the string, or -1 if NUL-terminated
 680    * @param status a UErrorCode
 681    * @stable ICU 2.0
 682    */
 683   void setText(const UChar* newText,
 684                     int32_t length,
 685             UErrorCode &status);
 686   /**
 687    * Copies the input text into the UnicodeString argument.
 688    *
 689    * @param result Receives a copy of the text under iteration.
 690    * @stable ICU 2.0
 691    */
 692   void            getText(UnicodeString&  result);
 693
 694   /**
 695    * ICU "poor man's RTTI", returns a UClassID for this class.
 696    * @returns a UClassID for this class.
 697    * @stable ICU 2.2
 698    */
 699   static UClassID U_EXPORT2 getStaticClassID();
 700
 701   /**
 702    * ICU "poor man's RTTI", returns a UClassID for the actual class.
 703    * @return a UClassID for the actual class.
 704    * @stable ICU 2.2
 705    */
 706   virtual UClassID getDynamicClassID() const;
 707
 708 private:
 709   //-------------------------------------------------------------------------
 710   // Private functions
 711   //-------------------------------------------------------------------------
 712
 713   Normalizer(); // default constructor not implemented
 714   Normalizer &operator=(const Normalizer &that); // assignment operator not implemented
 715
 716   // Private utility methods for iteration
 717   // For documentation, see the source code
 718   UBool nextNormalize();
 719   UBool previousNormalize();
 720
 721   void    init(CharacterIterator *iter);
 722   void    clearBuffer(void);
 723
 724   //-------------------------------------------------------------------------
 725   // Private data
 726   //-------------------------------------------------------------------------
 727
 728   UNormalizationMode  fUMode;
 729   int32_t             fOptions;
 730
 731   // The input text and our position in it
 732   UCharIterator       *text;
 733
 734   // The normalization buffer is the result of normalization
 735   // of the source in [currentIndex..nextIndex[ .
 736   int32_t         currentIndex, nextIndex;
 737
 738   // A buffer for holding intermediate results
 739   UnicodeString       buffer;
 740   int32_t         bufferPos;
 741
 742 };
 743
 744 //-------------------------------------------------------------------------
 745 // Inline implementations
 746 //-------------------------------------------------------------------------
 747
 748 inline UBool
 749 Normalizer::operator!= (const Normalizer& other) const
 750 { return ! operator==(other); }
 751
 752 inline UNormalizationCheckResult
 753 Normalizer::quickCheck(const UnicodeString& source,
 754                        UNormalizationMode mode,
 755                        UErrorCode &status) {
 756     if(U_FAILURE(status)) {
 757         return UNORM_MAYBE;
 758     }
 759
 760     return unorm_quickCheck(source.getBuffer(), source.length(),
 761                             mode, &status);
 762 }
 763
 764 inline UNormalizationCheckResult
 765 Normalizer::quickCheck(const UnicodeString& source,
 766                        UNormalizationMode mode, int32_t options,
 767                        UErrorCode &status) {
 768     if(U_FAILURE(status)) {
 769         return UNORM_MAYBE;
 770     }
 771
 772     return unorm_quickCheckWithOptions(source.getBuffer(), source.length(),
 773                                        mode, options, &status);
 774 }
 775
 776 inline UBool
 777 Normalizer::isNormalized(const UnicodeString& source,
 778                          UNormalizationMode mode,
 779                          UErrorCode &status) {
 780     if(U_FAILURE(status)) {
 781         return FALSE;
 782     }
 783
 784     return unorm_isNormalized(source.getBuffer(), source.length(),
 785                               mode, &status);
 786 }
 787
 788 inline UBool
 789 Normalizer::isNormalized(const UnicodeString& source,
 790                          UNormalizationMode mode, int32_t options,
 791                          UErrorCode &status) {
 792     if(U_FAILURE(status)) {
 793         return FALSE;
 794     }
 795
 796     return unorm_isNormalizedWithOptions(source.getBuffer(), source.length(),
 797                                          mode, options, &status);
 798 }
 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(s1.getBuffer(), s1.length(),
 806                        s2.getBuffer(), s2.length(),
 807                        options,
 808                        &errorCode);
 809 }
 810
 811 U_NAMESPACE_END
 812
 813 #endif /* #if !UCONFIG_NO_NORMALIZATION */
 814
 815 #endif // NORMLZR_H