xref: /aosp_15_r20/external/icu/libicu/ndk_headers/unicode/ucpmap.h (revision 0e209d3975ff4a8c132096b14b0e9364a753506e)

// © 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

/**
 * @addtogroup icu4c ICU4C
 * @{
 * \file
 * \brief C API: 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
 * \xrefitem stable "Stable" "Stable List" 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
 * \xrefitem stable "Stable" "Stable List" ICU 63
 */
enum UCPMapRangeOption {
    /**
     * ucpmap_getRange() enumerates all same-value ranges as stored in the map.
     * Most users should use this option.
     * \xrefitem stable "Stable" "Stable List" 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*.
     * \xrefitem stable "Stable" "Stable List" 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*.
     * \xrefitem stable "Stable" "Stable List" ICU 63
     */
    UCPMAP_RANGE_FIXED_ALL_SURROGATES
};
#ifndef U_IN_DOXYGEN
typedef enum UCPMapRangeOption UCPMapRangeOption;
#endif



/**
 * 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
 * \xrefitem stable "Stable" "Stable List" ICU 63
 */
typedef uint32_t U_CALLCONV
UCPMapValueFilter(const void *context, uint32_t value);



U_CDECL_END

#endif

/** @} */ // addtogroup