umutablecptrie.h (8501B)
1 // © 2017 and later: Unicode, Inc. and others. 2 // License & terms of use: http://www.unicode.org/copyright.html 3 4 // umutablecptrie.h (split out of ucptrie.h) 5 // created: 2018jan24 Markus W. Scherer 6 7 #ifndef __UMUTABLECPTRIE_H__ 8 #define __UMUTABLECPTRIE_H__ 9 10 #include "unicode/utypes.h" 11 12 #include "unicode/ucpmap.h" 13 #include "unicode/ucptrie.h" 14 #include "unicode/utf8.h" 15 16 #if U_SHOW_CPLUSPLUS_API 17 #include "unicode/localpointer.h" 18 #endif // U_SHOW_CPLUSPLUS_API 19 20 U_CDECL_BEGIN 21 22 /** 23 * \file 24 * \brief C API: This file defines a mutable Unicode code point trie. 25 * 26 * @see UCPTrie 27 * @see UMutableCPTrie 28 */ 29 30 /** 31 * Mutable Unicode code point trie. 32 * Fast map from Unicode code points (U+0000..U+10FFFF) to 32-bit integer values. 33 * For details see https://icu.unicode.org/design/struct/utrie 34 * 35 * Setting values (especially ranges) and lookup is fast. 36 * The mutable trie is only somewhat space-efficient. 37 * It builds a compacted, immutable UCPTrie. 38 * 39 * This trie can be modified while iterating over its contents. 40 * For example, it is possible to merge its values with those from another 41 * set of ranges (e.g., another mutable or immutable trie): 42 * Iterate over those source ranges; for each of them iterate over this trie; 43 * add the source value into the value of each trie range. 44 * 45 * @see UCPTrie 46 * @see umutablecptrie_buildImmutable 47 * @stable ICU 63 48 */ 49 typedef struct UMutableCPTrie UMutableCPTrie; 50 51 /** 52 * Creates a mutable trie that initially maps each Unicode code point to the same value. 53 * It uses 32-bit data values until umutablecptrie_buildImmutable() is called. 54 * umutablecptrie_buildImmutable() takes a valueWidth parameter which 55 * determines the number of bits in the data value in the resulting UCPTrie. 56 * You must umutablecptrie_close() the trie once you are done using it. 57 * 58 * @param initialValue the initial value that is set for all code points 59 * @param errorValue the value for out-of-range code points and ill-formed UTF-8/16 60 * @param pErrorCode an in/out ICU UErrorCode 61 * @return the trie 62 * @stable ICU 63 63 */ 64 U_CAPI UMutableCPTrie * U_EXPORT2 65 umutablecptrie_open(uint32_t initialValue, uint32_t errorValue, UErrorCode *pErrorCode); 66 67 /** 68 * Clones a mutable trie. 69 * You must umutablecptrie_close() the clone once you are done using it. 70 * 71 * @param other the trie to clone 72 * @param pErrorCode an in/out ICU UErrorCode 73 * @return the trie clone 74 * @stable ICU 63 75 */ 76 U_CAPI UMutableCPTrie * U_EXPORT2 77 umutablecptrie_clone(const UMutableCPTrie *other, UErrorCode *pErrorCode); 78 79 /** 80 * Closes a mutable trie and releases associated memory. 81 * 82 * @param trie the trie 83 * @stable ICU 63 84 */ 85 U_CAPI void U_EXPORT2 86 umutablecptrie_close(UMutableCPTrie *trie); 87 88 /** 89 * Creates a mutable trie with the same contents as the UCPMap. 90 * You must umutablecptrie_close() the mutable trie once you are done using it. 91 * 92 * @param map the source map 93 * @param pErrorCode an in/out ICU UErrorCode 94 * @return the mutable trie 95 * @stable ICU 63 96 */ 97 U_CAPI UMutableCPTrie * U_EXPORT2 98 umutablecptrie_fromUCPMap(const UCPMap *map, UErrorCode *pErrorCode); 99 100 /** 101 * Creates a mutable trie with the same contents as the immutable one. 102 * You must umutablecptrie_close() the mutable trie once you are done using it. 103 * 104 * @param trie the immutable trie 105 * @param pErrorCode an in/out ICU UErrorCode 106 * @return the mutable trie 107 * @stable ICU 63 108 */ 109 U_CAPI UMutableCPTrie * U_EXPORT2 110 umutablecptrie_fromUCPTrie(const UCPTrie *trie, UErrorCode *pErrorCode); 111 112 /** 113 * Returns the value for a code point as stored in the trie. 114 * 115 * @param trie the trie 116 * @param c the code point 117 * @return the value 118 * @stable ICU 63 119 */ 120 U_CAPI uint32_t U_EXPORT2 121 umutablecptrie_get(const UMutableCPTrie *trie, UChar32 c); 122 123 /** 124 * Returns the last code point such that all those from start to there have the same value. 125 * Can be used to efficiently iterate over all same-value ranges in a trie. 126 * (This is normally faster than iterating over code points and get()ting each value, 127 * but much slower than a data structure that stores ranges directly.) 128 * 129 * The trie can be modified between calls to this function. 130 * 131 * If the UCPMapValueFilter function pointer is not NULL, then 132 * the value to be delivered is passed through that function, and the return value is the end 133 * of the range where all values are modified to the same actual value. 134 * The value is unchanged if that function pointer is NULL. 135 * 136 * See the same-signature ucptrie_getRange() for a code sample. 137 * 138 * @param trie the trie 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 trie data value, 144 * or NULL if the values from the trie 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, trie 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 umutablecptrie_getRange(const UMutableCPTrie *trie, UChar32 start, 154 UCPMapRangeOption option, uint32_t surrogateValue, 155 UCPMapValueFilter *filter, const void *context, uint32_t *pValue); 156 157 /** 158 * Sets a value for a code point. 159 * 160 * @param trie the trie 161 * @param c the code point 162 * @param value the value 163 * @param pErrorCode an in/out ICU UErrorCode 164 * @stable ICU 63 165 */ 166 U_CAPI void U_EXPORT2 167 umutablecptrie_set(UMutableCPTrie *trie, UChar32 c, uint32_t value, UErrorCode *pErrorCode); 168 169 /** 170 * Sets a value for each code point [start..end]. 171 * Faster and more space-efficient than setting the value for each code point separately. 172 * 173 * @param trie the trie 174 * @param start the first code point to get the value 175 * @param end the last code point to get the value (inclusive) 176 * @param value the value 177 * @param pErrorCode an in/out ICU UErrorCode 178 * @stable ICU 63 179 */ 180 U_CAPI void U_EXPORT2 181 umutablecptrie_setRange(UMutableCPTrie *trie, 182 UChar32 start, UChar32 end, 183 uint32_t value, UErrorCode *pErrorCode); 184 185 /** 186 * Compacts the data and builds an immutable UCPTrie according to the parameters. 187 * After this, the mutable trie will be empty. 188 * 189 * The mutable trie stores 32-bit values until buildImmutable() is called. 190 * If values shorter than 32 bits are to be stored in the immutable trie, 191 * then the upper bits are discarded. 192 * For example, when the mutable trie contains values 0x81, -0x7f, and 0xa581, 193 * and the value width is 8 bits, then each of these is stored as 0x81 194 * and the immutable trie will return that as an unsigned value. 195 * (Some implementations may want to make productive temporary use of the upper bits 196 * until buildImmutable() discards them.) 197 * 198 * Not every possible set of mappings can be built into a UCPTrie, 199 * because of limitations resulting from speed and space optimizations. 200 * Every Unicode assigned character can be mapped to a unique value. 201 * Typical data yields data structures far smaller than the limitations. 202 * 203 * It is possible to construct extremely unusual mappings that exceed the data structure limits. 204 * In such a case this function will fail with a U_INDEX_OUTOFBOUNDS_ERROR. 205 * 206 * @param trie the trie trie 207 * @param type selects the trie type 208 * @param valueWidth selects the number of bits in a trie data value; if smaller than 32 bits, 209 * then the values stored in the trie will be truncated first 210 * @param pErrorCode an in/out ICU UErrorCode 211 * 212 * @see umutablecptrie_fromUCPTrie 213 * @stable ICU 63 214 */ 215 U_CAPI UCPTrie * U_EXPORT2 216 umutablecptrie_buildImmutable(UMutableCPTrie *trie, UCPTrieType type, UCPTrieValueWidth valueWidth, 217 UErrorCode *pErrorCode); 218 219 U_CDECL_END 220 221 #if U_SHOW_CPLUSPLUS_API 222 223 U_NAMESPACE_BEGIN 224 225 /** 226 * \class LocalUMutableCPTriePointer 227 * "Smart pointer" class, closes a UMutableCPTrie via umutablecptrie_close(). 228 * For most methods see the LocalPointerBase base class. 229 * 230 * @see LocalPointerBase 231 * @see LocalPointer 232 * @stable ICU 63 233 */ 234 U_DEFINE_LOCAL_OPEN_POINTER(LocalUMutableCPTriePointer, UMutableCPTrie, umutablecptrie_close); 235 236 U_NAMESPACE_END 237 238 #endif 239 240 #endif