icuSources/common/unicode/caniter.h

   1 // © 2016 and later: Unicode, Inc. and others.
   2 // License & terms of use: http://www.unicode.org/copyright.html
   3 /*
   4  *******************************************************************************
   5  * Copyright (C) 1996-2014, International Business Machines Corporation and
   6  * others. All Rights Reserved.
   7  *******************************************************************************
   8  */
   9
  10 #ifndef CANITER_H
  11 #define CANITER_H
  12
  13 #include "unicode/utypes.h"
  14
  15 #if !UCONFIG_NO_NORMALIZATION
  16
  17 #include "unicode/uobject.h"
  18 #include "unicode/unistr.h"
  19
  20 /**
  21  * \file
  22  * \brief C++ API: Canonical Iterator
  23  */
  24
  25 /** Should permutation skip characters with combining class zero
  26  *  Should be either TRUE or FALSE. This is a compile time option
  27  *  @stable ICU 2.4
  28  */
  29 #ifndef CANITER_SKIP_ZEROES
  30 #define CANITER_SKIP_ZEROES TRUE
  31 #endif
  32
  33 #if U_SHOW_CPLUSPLUS_API
  34 U_NAMESPACE_BEGIN
  35
  36 class Hashtable;
  37 class Normalizer2;
  38 class Normalizer2Impl;
  39
  40 /**
  41  * This class allows one to iterate through all the strings that are canonically equivalent to a given
  42  * string. For example, here are some sample results:
  43 Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
  44 1: \\u0041\\u030A\\u0064\\u0307\\u0327
  45  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
  46 2: \\u0041\\u030A\\u0064\\u0327\\u0307
  47  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
  48 3: \\u0041\\u030A\\u1E0B\\u0327
  49  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
  50 4: \\u0041\\u030A\\u1E11\\u0307
  51  = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
  52 5: \\u00C5\\u0064\\u0307\\u0327
  53  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
  54 6: \\u00C5\\u0064\\u0327\\u0307
  55  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
  56 7: \\u00C5\\u1E0B\\u0327
  57  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
  58 8: \\u00C5\\u1E11\\u0307
  59  = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
  60 9: \\u212B\\u0064\\u0307\\u0327
  61  = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
  62 10: \\u212B\\u0064\\u0327\\u0307
  63  = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
  64 11: \\u212B\\u1E0B\\u0327
  65  = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
  66 12: \\u212B\\u1E11\\u0307
  67  = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
  68  *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
  69  * since it has not been optimized for that situation.
  70  * Note, CanonicalIterator is not intended to be subclassed.
  71  * @author M. Davis
  72  * @author C++ port by V. Weinstein
  73  * @stable ICU 2.4
  74  */
  75 class U_COMMON_API CanonicalIterator U_FINAL : public UObject {
  76 public:
  77     /**
  78      * Construct a CanonicalIterator object
  79      * @param source    string to get results for
  80      * @param status    Fill-in parameter which receives the status of this operation.
  81      * @stable ICU 2.4
  82      */
  83     CanonicalIterator(const UnicodeString &source, UErrorCode &status);
  84
  85     /** Destructor
  86      *  Cleans pieces
  87      * @stable ICU 2.4
  88      */
  89     virtual ~CanonicalIterator();
  90
  91     /**
  92      * Gets the NFD form of the current source we are iterating over.
  93      * @return gets the source: NOTE: it is the NFD form of source
  94      * @stable ICU 2.4
  95      */
  96     UnicodeString getSource();
  97
  98     /**
  99      * Resets the iterator so that one can start again from the beginning.
 100      * @stable ICU 2.4
 101      */
 102     void reset();
 103
 104     /**
 105      * Get the next canonically equivalent string.
 106      * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
 107      * @return the next string that is canonically equivalent. A bogus string is returned when
 108      * the iteration is done.
 109      * @stable ICU 2.4
 110      */
 111     UnicodeString next();
 112
 113     /**
 114      * Set a new source for this iterator. Allows object reuse.
 115      * @param newSource     the source string to iterate against. This allows the same iterator to be used
 116      *                     while changing the source string, saving object creation.
 117      * @param status        Fill-in parameter which receives the status of this operation.
 118      * @stable ICU 2.4
 119      */
 120     void setSource(const UnicodeString &newSource, UErrorCode &status);
 121
 122 #ifndef U_HIDE_INTERNAL_API
 123     /**
 124      * Dumb recursive implementation of permutation.
 125      * TODO: optimize
 126      * @param source     the string to find permutations for
 127      * @param skipZeros  determine if skip zeros
 128      * @param result     the results in a set.
 129      * @param status       Fill-in parameter which receives the status of this operation.
 130      * @internal
 131      */
 132     static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status);
 133 #endif  /* U_HIDE_INTERNAL_API */
 134
 135     /**
 136      * ICU "poor man's RTTI", returns a UClassID for this class.
 137      *
 138      * @stable ICU 2.2
 139      */
 140     static UClassID U_EXPORT2 getStaticClassID();
 141
 142     /**
 143      * ICU "poor man's RTTI", returns a UClassID for the actual class.
 144      *
 145      * @stable ICU 2.2
 146      */
 147     virtual UClassID getDynamicClassID() const;
 148
 149 private:
 150     // ===================== PRIVATES ==============================
 151     // private default constructor
 152     CanonicalIterator();
 153
 154
 155     /**
 156      * Copy constructor. Private for now.
 157      * @internal (private)
 158      */
 159     CanonicalIterator(const CanonicalIterator& other);
 160
 161     /**
 162      * Assignment operator. Private for now.
 163      * @internal (private)
 164      */
 165     CanonicalIterator& operator=(const CanonicalIterator& other);
 166
 167     // fields
 168     UnicodeString source;
 169     UBool done;
 170
 171     // 2 dimensional array holds the pieces of the string with
 172     // their different canonically equivalent representations
 173     UnicodeString **pieces;
 174     int32_t pieces_length;
 175     int32_t *pieces_lengths;
 176
 177     // current is used in iterating to combine pieces
 178     int32_t *current;
 179     int32_t current_length;
 180
 181     // transient fields
 182     UnicodeString buffer;
 183
 184     const Normalizer2 &nfd;
 185     const Normalizer2Impl &nfcImpl;
 186
 187     // we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
 188     UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)
 189
 190     //Set getEquivalents2(String segment);
 191     Hashtable *getEquivalents2(Hashtable *fillinResult, const char16_t *segment, int32_t segLen, UErrorCode &status);
 192     //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);
 193
 194     /**
 195      * See if the decomposition of cp2 is at segment starting at segmentPos
 196      * (with canonical rearrangment!)
 197      * If so, take the remainder, and return the equivalents
 198      */
 199     //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
 200     Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const char16_t *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
 201     //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
 202
 203     void cleanPieces();
 204
 205 };
 206
 207 U_NAMESPACE_END
 208 #endif // U_SHOW_CPLUSPLUS_API
 209
 210 #endif /* #if !UCONFIG_NO_NORMALIZATION */
 211
 212 #endif