243   h 0 * lY> j- m_I|+ // © 2018 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html // ucpmap.h // created: 2018sep03 Markus W. Scherer #ifndef __UCPMAP_H__ #define __UCPMAP_H__ #include "unicode/utypes.h" U_CDECL_BEGIN /** * \file * * This file defines an abstract map from Unicode code points to integer values. * * @see UCPMap * @see UCPTrie * @see UMutableCPTrie */ /** * Abstract map from Unicode code points (U+0000..U+10FFFF) to integer values. * * @see UCPTrie * @see UMutableCPTrie * @stable ICU 63 */ typedef struct UCPMap UCPMap; /** * Selectors for how ucpmap_getRange() etc. should report value ranges overlapping with surrogates. * Most users should use UCPMAP_RANGE_NORMAL. * * @see ucpmap_getRange * @see ucptrie_getRange * @see umutablecptrie_getRange * @stable ICU 63 */ enum UCPMapRangeOption { /** * ucpmap_getRange() enumerates all same-value ranges as stored in the map. * Most users should use this option. * @stable ICU 63 */ UCPMAP_RANGE_NORMAL, /** * ucpmap_getRange() enumerates all same-value ranges as stored in the map, * except that lead surrogates (U+D800..U+DBFF) are treated as having the * surrogateValue, which is passed to getRange() as a separate parameter. * The surrogateValue is not transformed via filter(). * See U_IS_LEAD(c). * * Most users should use UCPMAP_RANGE_NORMAL instead. * * This option is useful for maps that map surrogate code *units* to * special values optimized for UTF-16 string processing * or for special error behavior for unpaired surrogates, * but those values are not to be associated with the lead surrogate code *points*. * @stable ICU 63 */ UCPMAP_RANGE_FIXED_LEAD_SURROGATES, /** * ucpmap_getRange() enumerates all same-value ranges as stored in the map, * except that all surrogates (U+D800..U+DFFF) are treated as having the * surrogateValue, which is passed to getRange() as a separate parameter. * The surrogateValue is not transformed via filter(). * See U_IS_SURROGATE(c). * * Most users should use UCPMAP_RANGE_NORMAL instead. * * This option is useful for maps that map surrogate code *units* to * special values optimized for UTF-16 string processing * or for special error behavior for unpaired surrogates, * but those values are not to be associated with the lead surrogate code *points*. * @stable ICU 63 */ UCPMAP_RANGE_FIXED_ALL_SURROGATES }; #ifndef U_IN_DOXYGEN typedef enum UCPMapRangeOption UCPMapRangeOption; #endif /** * Returns the value for a code point as stored in the map, with range checking. * Returns an implementation-defined error value if c is not in the range 0..U+10FFFF. * * @param map the map * @param c the code point * @return the map value, * or an implementation-defined error value if the code point is not in the range 0..U+10FFFF * @stable ICU 63 */ U_CAPI uint32_t U_EXPORT2 ucpmap_get(const UCPMap *map, UChar32 c); /** * Callback function type: Modifies a map value. * Optionally called by ucpmap_getRange()/ucptrie_getRange()/umutablecptrie_getRange(). * The modified value will be returned by the getRange function. * * Can be used to ignore some of the value bits, * make a filter for one of several values, * return a value index computed from the map value, etc. * * @param context an opaque pointer, as passed into the getRange function * @param value a value from the map * @return the modified value * @stable ICU 63 */ typedef uint32_t U_CALLCONV UCPMapValueFilter(const void *context, uint32_t value); /** * Returns the last code point such that all those from start to there have the same value. * Can be used to efficiently iterate over all same-value ranges in a map. * (This is normally faster than iterating over code points and get()ting each value, * but much slower than a data structure