1 // © 2018 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 4 // ucpmap.h 5 // created: 2018sep03 Markus W. Scherer 6 7 #ifndef __UCPMAP_H__ 8 #define __UCPMAP_H__ 9 10 #include "unicode/utypes.h" 11 12 U_CDECL_BEGIN 13 14 /** 15 * \file 16 * 17 * This file defines an abstract map from Unicode code points to integer values. 18 * 19 * @see UCPMap 20 * @see UCPTrie 21 * @see UMutableCPTrie 22 */ 23 24 /** 25 * Abstract map from Unicode code points (U+0000..U+10FFFF) to integer values. 26 * 27 * @see UCPTrie 28 * @see UMutableCPTrie 29 * @stable ICU 63 30 */ 31 typedef struct UCPMap UCPMap; 32 33 /** 34 * Selectors for how ucpmap_getRange() etc. should report value ranges overlapping with surrogates. 35 * Most users should use UCPMAP_RANGE_NORMAL. 36 * 37 * @see ucpmap_getRange 38 * @see ucptrie_getRange 39 * @see umutablecptrie_getRange 40 * @stable ICU 63 41 */ 42 enum UCPMapRangeOption { 43 /** 44 * ucpmap_getRange() enumerates all same-value ranges as stored in the map. 45 * Most users should use this option. 46 * @stable ICU 63 47 */ 48 UCPMAP_RANGE_NORMAL, 49 /** 50 * ucpmap_getRange() enumerates all same-value ranges as stored in the map, 51 * except that lead surrogates (U+D800..U+DBFF) are treated as having the 52 * surrogateValue, which is passed to getRange() as a separate parameter. 53 * The surrogateValue is not transformed via filter(). 54 * See U_IS_LEAD(c). 55 * 56 * Most users should use UCPMAP_RANGE_NORMAL instead. 57 * 58 * This option is useful for maps that map surrogate code *units* to 59 * special values optimized for UTF-16 string processing 60 * or for special error behavior for unpaired surrogates, 61 * but those values are not to be associated with the lead surrogate code *points*. 62 * @stable ICU 63 63 */ 64 UCPMAP_RANGE_FIXED_LEAD_SURROGATES, 65 /** 66 * ucpmap_getRange() enumerates all same-value ranges as stored in the map, 67 * except that all surrogates (U+D800..U+DFFF) are treated as having the 68 * surrogateValue, which is passed to getRange() as a separate parameter. 69 * The surrogateValue is not transformed via filter(). 70 * See U_IS_SURROGATE(c). 71 * 72 * Most users should use UCPMAP_RANGE_NORMAL instead. 73 * 74 * This option is useful for maps that map surrogate code *units* to 75 * special values optimized for UTF-16 string processing 76 * or for special error behavior for unpaired surrogates, 77 * but those values are not to be associated with the lead surrogate code *points*. 78 * @stable ICU 63 79 */ 80 UCPMAP_RANGE_FIXED_ALL_SURROGATES 81 }; 82 #ifndef U_IN_DOXYGEN 83 typedef enum UCPMapRangeOption UCPMapRangeOption; 84 #endif 85 86 /** 87 * Returns the value for a code point as stored in the map, with range checking. 88 * Returns an implementation-defined error value if c is not in the range 0..U+10FFFF. 89 * 90 * @param map the map 91 * @param c the code point 92 * @return the map value, 93 * or an implementation-defined error value if the code point is not in the range 0..U+10FFFF 94 * @stable ICU 63 95 */ 96 U_CAPI uint32_t U_EXPORT2 97 ucpmap_get(const UCPMap *map, UChar32 c); 98 99 /** 100 * Callback function type: Modifies a map value. 101 * Optionally called by ucpmap_getRange()/ucptrie_getRange()/umutablecptrie_getRange(). 102 * The modified value will be returned by the getRange function. 103 * 104 * Can be used to ignore some of the value bits, 105 * make a filter for one of several values, 106 * return a value index computed from the map value, etc. 107 * 108 * @param context an opaque pointer, as passed into the getRange function 109 * @param value a value from the map 110 * @return the modified value 111 * @stable ICU 63 112 */ 113 typedef uint32_t U_CALLCONV 114 UCPMapValueFilter(const void *context, uint32_t value); 115 116 /** 117 * Returns the last code point such that all those from start to there have the same value. 118 * Can be used to efficiently iterate over all same-value ranges in a map. 119 * (This is normally faster than iterating over code points and get()ting each value, 120 * but much slower than a data structure that stores ranges directly.) 121 * 122 * If the UCPMapValueFilter function pointer is not NULL, then 123 * the value to be delivered is passed through that function, and the return value is the end 124 * of the range where all values are modified to the same actual value. 125 * The value is unchanged if that function pointer is NULL. 126 * 127 * Example: 128 * \code 129 * UChar32 start = 0, end; 130 * uint32_t value; 131 * while ((end = ucpmap_getRange(map, start, UCPMAP_RANGE_NORMAL, 0, 132 * NULL, NULL, &value)) >= 0) { 133 * // Work with the range start..end and its value. 134 * start = end + 1; 135 * } 136 * \endcode 137 * 138 * @param map the map 139 * @param start range start 140 * @param option defines whether surrogates are treated normally, 141 * or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL 142 * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL 143 * @param filter a pointer to a function that may modify the map data value, 144 * or NULL if the values from the map are to be used unmodified 145 * @param context an opaque pointer that is passed on to the filter function 146 * @param pValue if not NULL, receives the value that every code point start..end has; 147 * may have been modified by filter(context, map value) 148 * if that function pointer is not NULL 149 * @return the range end code point, or -1 if start is not a valid code point 150 * @stable ICU 63 151 */ 152 U_CAPI UChar32 U_EXPORT2 153 ucpmap_getRange(const UCPMap *map, UChar32 start, 154 UCPMapRangeOption option, uint32_t surrogateValue, 155 UCPMapValueFilter *filter, const void *context, uint32_t *pValue); 156 157 U_CDECL_END 158 159 #endif 160