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) 2001-2014, International Business Machines 6 * Corporation and others. All Rights Reserved. 7 ******************************************************************************* 8 * 9 * File ucoleitr.h 10 * 11 * Modification History: 12 * 13 * Date Name Description 14 * 02/15/2001 synwee Modified all methods to process its own function 15 * instead of calling the equivalent c++ api (coleitr.h) 16 *******************************************************************************/ 17 18 #ifndef UCOLEITR_H 19 #define UCOLEITR_H 20 21 #include "unicode/utypes.h" 22 23 #if !UCONFIG_NO_COLLATION 24 25 /** 26 * This indicates an error has occured during processing or if no more CEs is 27 * to be returned. 28 * @stable ICU 2.0 29 */ 30 #define UCOL_NULLORDER ((int32_t)0xFFFFFFFF) 31 32 #include "unicode/ucol.h" 33 34 /** 35 * The UCollationElements struct. 36 * For usage in C programs. 37 * @stable ICU 2.0 38 */ 39 typedef struct UCollationElements UCollationElements; 40 41 /** 42 * \file 43 * \brief C API: UCollationElements 44 * 45 * The UCollationElements API is used as an iterator to walk through each 46 * character of an international string. Use the iterator to return the 47 * ordering priority of the positioned character. The ordering priority of a 48 * character, which we refer to as a key, defines how a character is collated 49 * in the given collation object. 50 * For example, consider the following in Slovak and in traditional Spanish collation: 51 * <pre> 52 * . "ca" -> the first key is key('c') and second key is key('a'). 53 * . "cha" -> the first key is key('ch') and second key is key('a'). 54 * </pre> 55 * And in German phonebook collation, 56 * <pre> 57 * . "<ae ligature>b"-> the first key is key('a'), the second key is key('e'), and 58 * . the third key is key('b'). 59 * </pre> 60 * <p>Example of the iterator usage: (without error checking) 61 * <pre> 62 * . void CollationElementIterator_Example() 63 * . { 64 * . UChar *s; 65 * . t_int32 order, primaryOrder; 66 * . UCollationElements *c; 67 * . UCollatorOld *coll; 68 * . UErrorCode success = U_ZERO_ERROR; 69 * . s=(UChar*)malloc(sizeof(UChar) * (strlen("This is a test")+1) ); 70 * . u_uastrcpy(s, "This is a test"); 71 * . coll = ucol_open(NULL, &success); 72 * . c = ucol_openElements(coll, str, u_strlen(str), &status); 73 * . order = ucol_next(c, &success); 74 * . ucol_reset(c); 75 * . order = ucol_prev(c, &success); 76 * . free(s); 77 * . ucol_close(coll); 78 * . ucol_closeElements(c); 79 * . } 80 * </pre> 81 * <p> 82 * ucol_next() returns the collation order of the next. 83 * ucol_prev() returns the collation order of the previous character. 84 * The Collation Element Iterator moves only in one direction between calls to 85 * ucol_reset. That is, ucol_next() and ucol_prev can not be inter-used. 86 * Whenever ucol_prev is to be called after ucol_next() or vice versa, 87 * ucol_reset has to be called first to reset the status, shifting pointers to 88 * either the end or the start of the string. Hence at the next call of 89 * ucol_prev or ucol_next, the first or last collation order will be returned. 90 * If a change of direction is done without a ucol_reset, the result is 91 * undefined. 92 * The result of a forward iterate (ucol_next) and reversed result of the 93 * backward iterate (ucol_prev) on the same string are equivalent, if 94 * collation orders with the value 0 are ignored. 95 * Character based on the comparison level of the collator. A collation order 96 * consists of primary order, secondary order and tertiary order. The data 97 * type of the collation order is <strong>int32_t</strong>. 98 * 99 * @see UCollator 100 */ 101 102 /** 103 * Open the collation elements for a string. 104 * 105 * @param coll The collator containing the desired collation rules. 106 * @param text The text to iterate over. 107 * @param textLength The number of characters in text, or -1 if null-terminated 108 * @param status A pointer to a UErrorCode to receive any errors. 109 * @return a struct containing collation element information 110 * @stable ICU 2.0 111 */ 112 U_STABLE UCollationElements* U_EXPORT2 113 ucol_openElements(const UCollator *coll, 114 const UChar *text, 115 int32_t textLength, 116 UErrorCode *status); 117 118 119 /** 120 * get a hash code for a key... Not very useful! 121 * @param key the given key. 122 * @param length the size of the key array. 123 * @return the hash code. 124 * @stable ICU 2.0 125 */ 126 U_STABLE int32_t U_EXPORT2 127 ucol_keyHashCode(const uint8_t* key, int32_t length); 128 129 /** 130 * Close a UCollationElements. 131 * Once closed, a UCollationElements may no longer be used. 132 * @param elems The UCollationElements to close. 133 * @stable ICU 2.0 134 */ 135 U_STABLE void U_EXPORT2 136 ucol_closeElements(UCollationElements *elems); 137 138 /** 139 * Reset the collation elements to their initial state. 140 * This will move the 'cursor' to the beginning of the text. 141 * Property settings for collation will be reset to the current status. 142 * @param elems The UCollationElements to reset. 143 * @see ucol_next 144 * @see ucol_previous 145 * @stable ICU 2.0 146 */ 147 U_STABLE void U_EXPORT2 148 ucol_reset(UCollationElements *elems); 149 150 /** 151 * Get the ordering priority of the next collation element in the text. 152 * A single character may contain more than one collation element. 153 * @param elems The UCollationElements containing the text. 154 * @param status A pointer to a UErrorCode to receive any errors. 155 * @return The next collation elements ordering, otherwise returns NULLORDER 156 * if an error has occured or if the end of string has been reached 157 * @stable ICU 2.0 158 */ 159 U_STABLE int32_t U_EXPORT2 160 ucol_next(UCollationElements *elems, UErrorCode *status); 161 162 /** 163 * Get the ordering priority of the previous collation element in the text. 164 * A single character may contain more than one collation element. 165 * Note that internally a stack is used to store buffered collation elements. 166 * @param elems The UCollationElements containing the text. 167 * @param status A pointer to a UErrorCode to receive any errors. Noteably 168 * a U_BUFFER_OVERFLOW_ERROR is returned if the internal stack 169 * buffer has been exhausted. 170 * @return The previous collation elements ordering, otherwise returns 171 * NULLORDER if an error has occured or if the start of string has 172 * been reached. 173 * @stable ICU 2.0 174 */ 175 U_STABLE int32_t U_EXPORT2 176 ucol_previous(UCollationElements *elems, UErrorCode *status); 177 178 /** 179 * Get the maximum length of any expansion sequences that end with the 180 * specified comparison order. 181 * This is useful for .... ? 182 * @param elems The UCollationElements containing the text. 183 * @param order A collation order returned by previous or next. 184 * @return maximum size of the expansion sequences ending with the collation 185 * element or 1 if collation element does not occur at the end of any 186 * expansion sequence 187 * @stable ICU 2.0 188 */ 189 U_STABLE int32_t U_EXPORT2 190 ucol_getMaxExpansion(const UCollationElements *elems, int32_t order); 191 192 /** 193 * Set the text containing the collation elements. 194 * Property settings for collation will remain the same. 195 * In order to reset the iterator to the current collation property settings, 196 * the API reset() has to be called. 197 * @param elems The UCollationElements to set. 198 * @param text The source text containing the collation elements. 199 * @param textLength The length of text, or -1 if null-terminated. 200 * @param status A pointer to a UErrorCode to receive any errors. 201 * @see ucol_getText 202 * @stable ICU 2.0 203 */ 204 U_STABLE void U_EXPORT2 205 ucol_setText( UCollationElements *elems, 206 const UChar *text, 207 int32_t textLength, 208 UErrorCode *status); 209 210 /** 211 * Get the offset of the current source character. 212 * This is an offset into the text of the character containing the current 213 * collation elements. 214 * @param elems The UCollationElements to query. 215 * @return The offset of the current source character. 216 * @see ucol_setOffset 217 * @stable ICU 2.0 218 */ 219 U_STABLE int32_t U_EXPORT2 220 ucol_getOffset(const UCollationElements *elems); 221 222 /** 223 * Set the offset of the current source character. 224 * This is an offset into the text of the character to be processed. 225 * Property settings for collation will remain the same. 226 * In order to reset the iterator to the current collation property settings, 227 * the API reset() has to be called. 228 * @param elems The UCollationElements to set. 229 * @param offset The desired character offset. 230 * @param status A pointer to a UErrorCode to receive any errors. 231 * @see ucol_getOffset 232 * @stable ICU 2.0 233 */ 234 U_STABLE void U_EXPORT2 235 ucol_setOffset(UCollationElements *elems, 236 int32_t offset, 237 UErrorCode *status); 238 239 /** 240 * Get the primary order of a collation order. 241 * @param order the collation order 242 * @return the primary order of a collation order. 243 * @stable ICU 2.6 244 */ 245 U_STABLE int32_t U_EXPORT2 246 ucol_primaryOrder (int32_t order); 247 248 /** 249 * Get the secondary order of a collation order. 250 * @param order the collation order 251 * @return the secondary order of a collation order. 252 * @stable ICU 2.6 253 */ 254 U_STABLE int32_t U_EXPORT2 255 ucol_secondaryOrder (int32_t order); 256 257 /** 258 * Get the tertiary order of a collation order. 259 * @param order the collation order 260 * @return the tertiary order of a collation order. 261 * @stable ICU 2.6 262 */ 263 U_STABLE int32_t U_EXPORT2 264 ucol_tertiaryOrder (int32_t order); 265 266 #endif /* #if !UCONFIG_NO_COLLATION */ 267 268 #endif 269