1 // © 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 occurred 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 * . str=(UChar*)malloc(sizeof(UChar) * (strlen("This is a test")+1) ); 70 * . u_uastrcpy(str, "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(str); 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 * The UCollationElements retains a pointer to the supplied text. 106 * The caller must not modify or delete the text while the UCollationElements 107 * object is used to iterate over this text. 108 * 109 * @param coll The collator containing the desired collation rules. 110 * @param text The text to iterate over. 111 * @param textLength The number of characters in text, or -1 if null-terminated 112 * @param status A pointer to a UErrorCode to receive any errors. 113 * @return a struct containing collation element information 114 * @stable ICU 2.0 115 */ 116 U_CAPI UCollationElements* U_EXPORT2 117 ucol_openElements(const UCollator *coll, 118 const UChar *text, 119 int32_t textLength, 120 UErrorCode *status); 121 122 /** 123 * get a hash code for a key... Not very useful! 124 * @param key the given key. 125 * @param length the size of the key array. 126 * @return the hash code. 127 * @stable ICU 2.0 128 */ 129 U_CAPI int32_t U_EXPORT2 130 ucol_keyHashCode(const uint8_t* key, int32_t length); 131 132 /** 133 * Close a UCollationElements. 134 * Once closed, a UCollationElements may no longer be used. 135 * @param elems The UCollationElements to close. 136 * @stable ICU 2.0 137 */ 138 U_CAPI void U_EXPORT2 139 ucol_closeElements(UCollationElements *elems); 140 141 /** 142 * Reset the collation elements to their initial state. 143 * This will move the 'cursor' to the beginning of the text. 144 * Property settings for collation will be reset to the current status. 145 * @param elems The UCollationElements to reset. 146 * @see ucol_next 147 * @see ucol_previous 148 * @stable ICU 2.0 149 */ 150 U_CAPI void U_EXPORT2 151 ucol_reset(UCollationElements *elems); 152 153 /** 154 * Get the ordering priority of the next collation element in the text. 155 * A single character may contain more than one collation element. 156 * @param elems The UCollationElements containing the text. 157 * @param status A pointer to a UErrorCode to receive any errors. 158 * @return The next collation elements ordering, otherwise returns UCOL_NULLORDER 159 * if an error has occurred or if the end of string has been reached 160 * @stable ICU 2.0 161 */ 162 U_CAPI int32_t U_EXPORT2 163 ucol_next(UCollationElements *elems, UErrorCode *status); 164 165 /** 166 * Get the ordering priority of the previous collation element in the text. 167 * A single character may contain more than one collation element. 168 * Note that internally a stack is used to store buffered collation elements. 169 * @param elems The UCollationElements containing the text. 170 * @param status A pointer to a UErrorCode to receive any errors. Noteably 171 * a U_BUFFER_OVERFLOW_ERROR is returned if the internal stack 172 * buffer has been exhausted. 173 * @return The previous collation elements ordering, otherwise returns 174 * UCOL_NULLORDER if an error has occurred or if the start of string has 175 * been reached. 176 * @stable ICU 2.0 177 */ 178 U_CAPI int32_t U_EXPORT2 179 ucol_previous(UCollationElements *elems, UErrorCode *status); 180 181 /** 182 * Get the maximum length of any expansion sequences that end with the 183 * specified comparison order. 184 * This is useful for .... ? 185 * @param elems The UCollationElements containing the text. 186 * @param order A collation order returned by previous or next. 187 * @return maximum size of the expansion sequences ending with the collation 188 * element or 1 if collation element does not occur at the end of any 189 * expansion sequence 190 * @stable ICU 2.0 191 */ 192 U_CAPI int32_t U_EXPORT2 193 ucol_getMaxExpansion(const UCollationElements *elems, int32_t order); 194 195 /** 196 * Set the text containing the collation elements. 197 * Property settings for collation will remain the same. 198 * In order to reset the iterator to the current collation property settings, 199 * the API reset() has to be called. 200 * 201 * The UCollationElements retains a pointer to the supplied text. 202 * The caller must not modify or delete the text while the UCollationElements 203 * object is used to iterate over this text. 204 * 205 * @param elems The UCollationElements to set. 206 * @param text The source text containing the collation elements. 207 * @param textLength The length of text, or -1 if null-terminated. 208 * @param status A pointer to a UErrorCode to receive any errors. 209 * @see ucol_getText 210 * @stable ICU 2.0 211 */ 212 U_CAPI void U_EXPORT2 213 ucol_setText( UCollationElements *elems, 214 const UChar *text, 215 int32_t textLength, 216 UErrorCode *status); 217 218 /** 219 * Get the offset of the current source character. 220 * This is an offset into the text of the character containing the current 221 * collation elements. 222 * @param elems The UCollationElements to query. 223 * @return The offset of the current source character. 224 * @see ucol_setOffset 225 * @stable ICU 2.0 226 */ 227 U_CAPI int32_t U_EXPORT2 228 ucol_getOffset(const UCollationElements *elems); 229 230 /** 231 * Set the offset of the current source character. 232 * This is an offset into the text of the character to be processed. 233 * Property settings for collation will remain the same. 234 * In order to reset the iterator to the current collation property settings, 235 * the API reset() has to be called. 236 * @param elems The UCollationElements to set. 237 * @param offset The desired character offset. 238 * @param status A pointer to a UErrorCode to receive any errors. 239 * @see ucol_getOffset 240 * @stable ICU 2.0 241 */ 242 U_CAPI void U_EXPORT2 243 ucol_setOffset(UCollationElements *elems, 244 int32_t offset, 245 UErrorCode *status); 246 247 /** 248 * Get the primary order of a collation order. 249 * @param order the collation order 250 * @return the primary order of a collation order. 251 * @stable ICU 2.6 252 */ 253 U_CAPI int32_t U_EXPORT2 254 ucol_primaryOrder (int32_t order); 255 256 /** 257 * Get the secondary order of a collation order. 258 * @param order the collation order 259 * @return the secondary order of a collation order. 260 * @stable ICU 2.6 261 */ 262 U_CAPI int32_t U_EXPORT2 263 ucol_secondaryOrder (int32_t order); 264 265 /** 266 * Get the tertiary order of a collation order. 267 * @param order the collation order 268 * @return the tertiary order of a collation order. 269 * @stable ICU 2.6 270 */ 271 U_CAPI int32_t U_EXPORT2 272 ucol_tertiaryOrder (int32_t order); 273 274 #endif /* #if !UCONFIG_NO_COLLATION */ 275 276 #endif 277