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