1 /* 2 ******************************************************************************* 3 * Copyright (C) 1996-2006, International Business Machines Corporation and * 4 * others. All Rights Reserved. * 5 ******************************************************************************* 6 */ 7 8 #ifndef CANITER_H 9 #define CANITER_H 10 11 #include "unicode/utypes.h" 12 13 #if !UCONFIG_NO_NORMALIZATION 14 15 #include "unicode/uobject.h" 16 #include "unicode/unistr.h" 17 18 /** 19 * \file 20 * \brief C++ API: Canonical Iterator 21 */ 22 23 /** Should permutation skip characters with combining class zero 24 * Should be either TRUE or FALSE. This is a compile time option 25 * @stable ICU 2.4 26 */ 27 #ifndef CANITER_SKIP_ZEROES 28 #define CANITER_SKIP_ZEROES TRUE 29 #endif 30 31 U_NAMESPACE_BEGIN 32 33 class Hashtable; 34 35 /** 36 * This class allows one to iterate through all the strings that are canonically equivalent to a given 37 * string. For example, here are some sample results: 38 Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} 39 1: \\u0041\\u030A\\u0064\\u0307\\u0327 40 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} 41 2: \\u0041\\u030A\\u0064\\u0327\\u0307 42 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} 43 3: \\u0041\\u030A\\u1E0B\\u0327 44 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} 45 4: \\u0041\\u030A\\u1E11\\u0307 46 = {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} 47 5: \\u00C5\\u0064\\u0307\\u0327 48 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} 49 6: \\u00C5\\u0064\\u0327\\u0307 50 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} 51 7: \\u00C5\\u1E0B\\u0327 52 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} 53 8: \\u00C5\\u1E11\\u0307 54 = {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} 55 9: \\u212B\\u0064\\u0307\\u0327 56 = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA} 57 10: \\u212B\\u0064\\u0327\\u0307 58 = {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE} 59 11: \\u212B\\u1E0B\\u0327 60 = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA} 61 12: \\u212B\\u1E11\\u0307 62 = {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE} 63 *<br>Note: the code is intended for use with small strings, and is not suitable for larger ones, 64 * since it has not been optimized for that situation. 65 * Note, CanonicalIterator is not intended to be subclassed. 66 * @author M. Davis 67 * @author C++ port by V. Weinstein 68 * @stable ICU 2.4 69 */ 70 class U_COMMON_API CanonicalIterator : public UObject { 71 public: 72 /** 73 * Construct a CanonicalIterator object 74 * @param source string to get results for 75 * @param status Fill-in parameter which receives the status of this operation. 76 * @stable ICU 2.4 77 */ 78 CanonicalIterator(const UnicodeString &source, UErrorCode &status); 79 80 /** Destructor 81 * Cleans pieces 82 * @stable ICU 2.4 83 */ 84 virtual ~CanonicalIterator(); 85 86 /** 87 * Gets the NFD form of the current source we are iterating over. 88 * @return gets the source: NOTE: it is the NFD form of source 89 * @stable ICU 2.4 90 */ 91 UnicodeString getSource(); 92 93 /** 94 * Resets the iterator so that one can start again from the beginning. 95 * @stable ICU 2.4 96 */ 97 void reset(); 98 99 /** 100 * Get the next canonically equivalent string. 101 * <br><b>Warning: The strings are not guaranteed to be in any particular order.</b> 102 * @return the next string that is canonically equivalent. A bogus string is returned when 103 * the iteration is done. 104 * @stable ICU 2.4 105 */ 106 UnicodeString next(); 107 108 /** 109 * Set a new source for this iterator. Allows object reuse. 110 * @param newSource the source string to iterate against. This allows the same iterator to be used 111 * while changing the source string, saving object creation. 112 * @param status Fill-in parameter which receives the status of this operation. 113 * @stable ICU 2.4 114 */ 115 void setSource(const UnicodeString &newSource, UErrorCode &status); 116 117 /** 118 * Dumb recursive implementation of permutation. 119 * TODO: optimize 120 * @param source the string to find permutations for 121 * @param skipZeros determine if skip zeros 122 * @param result the results in a set. 123 * @param status Fill-in parameter which receives the status of this operation. 124 * @internal 125 */ 126 static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status); 127 128 /** 129 * ICU "poor man's RTTI", returns a UClassID for this class. 130 * 131 * @stable ICU 2.2 132 */ 133 static UClassID U_EXPORT2 getStaticClassID(); 134 135 /** 136 * ICU "poor man's RTTI", returns a UClassID for the actual class. 137 * 138 * @stable ICU 2.2 139 */ 140 virtual UClassID getDynamicClassID() const; 141 142 private: 143 // ===================== PRIVATES ============================== 144 // private default constructor 145 CanonicalIterator(); 146 147 148 /** 149 * Copy constructor. Private for now. 150 * @internal 151 */ 152 CanonicalIterator(const CanonicalIterator& other); 153 154 /** 155 * Assignment operator. Private for now. 156 * @internal 157 */ 158 CanonicalIterator& operator=(const CanonicalIterator& other); 159 160 // fields 161 UnicodeString source; 162 UBool done; 163 164 // 2 dimensional array holds the pieces of the string with 165 // their different canonically equivalent representations 166 UnicodeString **pieces; 167 int32_t pieces_length; 168 int32_t *pieces_lengths; 169 170 // current is used in iterating to combine pieces 171 int32_t *current; 172 int32_t current_length; 173 174 // transient fields 175 UnicodeString buffer; 176 177 // we have a segment, in NFD. Find all the strings that are canonically equivalent to it. 178 UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment) 179 180 //Set getEquivalents2(String segment); 181 Hashtable *getEquivalents2(Hashtable *fillinResult, const UChar *segment, int32_t segLen, UErrorCode &status); 182 //Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status); 183 184 /** 185 * See if the decomposition of cp2 is at segment starting at segmentPos 186 * (with canonical rearrangment!) 187 * If so, take the remainder, and return the equivalents 188 */ 189 //Set extract(int comp, String segment, int segmentPos, StringBuffer buffer); 190 Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); 191 //Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status); 192 193 void cleanPieces(); 194 195 }; 196 197 U_NAMESPACE_END 198 199 #endif /* #if !UCONFIG_NO_NORMALIZATION */ 200 201 #endif 202