icuSources/common/unicode/umutablecptrie.h

   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 #ifndef U_HIDE_DRAFT_API
  13
  14 #include "unicode/localpointer.h"
  15 #include "unicode/ucpmap.h"
  16 #include "unicode/ucptrie.h"
  17 #include "unicode/utf8.h"
  18
  19 U_CDECL_BEGIN
  20
  21 /**
  22  * \file
  23  *
  24  * 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 http://site.icu-project.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  * @draft 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  * @draft 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  * @draft 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  * @draft ICU 63
  84  */
  85 U_CAPI void U_EXPORT2
  86 umutablecptrie_close(UMutableCPTrie *trie);
  87
  88 #if U_SHOW_CPLUSPLUS_API
  89
  90 U_NAMESPACE_BEGIN
  91
  92 /**
  93  * \class LocalUMutableCPTriePointer
  94  * "Smart pointer" class, closes a UMutableCPTrie via umutablecptrie_close().
  95  * For most methods see the LocalPointerBase base class.
  96  *
  97  * @see LocalPointerBase
  98  * @see LocalPointer
  99  * @draft ICU 63
 100  */
 101 U_DEFINE_LOCAL_OPEN_POINTER(LocalUMutableCPTriePointer, UMutableCPTrie, umutablecptrie_close);
 102
 103 U_NAMESPACE_END
 104
 105 #endif
 106
 107 /**
 108  * Creates a mutable trie with the same contents as the UCPMap.
 109  * You must umutablecptrie_close() the mutable trie once you are done using it.
 110  *
 111  * @param map the source map
 112  * @param pErrorCode an in/out ICU UErrorCode
 113  * @return the mutable trie
 114  * @draft ICU 63
 115  */
 116 U_CAPI UMutableCPTrie * U_EXPORT2
 117 umutablecptrie_fromUCPMap(const UCPMap *map, UErrorCode *pErrorCode);
 118
 119 /**
 120  * Creates a mutable trie with the same contents as the immutable one.
 121  * You must umutablecptrie_close() the mutable trie once you are done using it.
 122  *
 123  * @param trie the immutable trie
 124  * @param pErrorCode an in/out ICU UErrorCode
 125  * @return the mutable trie
 126  * @draft ICU 63
 127  */
 128 U_CAPI UMutableCPTrie * U_EXPORT2
 129 umutablecptrie_fromUCPTrie(const UCPTrie *trie, UErrorCode *pErrorCode);
 130
 131 /**
 132  * Returns the value for a code point as stored in the trie.
 133  *
 134  * @param trie the trie
 135  * @param c the code point
 136  * @return the value
 137  * @draft ICU 63
 138  */
 139 U_CAPI uint32_t U_EXPORT2
 140 umutablecptrie_get(const UMutableCPTrie *trie, UChar32 c);
 141
 142 /**
 143  * Returns the last code point such that all those from start to there have the same value.
 144  * Can be used to efficiently iterate over all same-value ranges in a trie.
 145  * (This is normally faster than iterating over code points and get()ting each value,
 146  * but much slower than a data structure that stores ranges directly.)
 147  *
 148  * The trie can be modified between calls to this function.
 149  *
 150  * If the UCPMapValueFilter function pointer is not NULL, then
 151  * the value to be delivered is passed through that function, and the return value is the end
 152  * of the range where all values are modified to the same actual value.
 153  * The value is unchanged if that function pointer is NULL.
 154  *
 155  * See the same-signature ucptrie_getRange() for a code sample.
 156  *
 157  * @param trie the trie
 158  * @param start range start
 159  * @param option defines whether surrogates are treated normally,
 160  *               or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL
 161  * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL
 162  * @param filter a pointer to a function that may modify the trie data value,
 163  *     or NULL if the values from the trie are to be used unmodified
 164  * @param context an opaque pointer that is passed on to the filter function
 165  * @param pValue if not NULL, receives the value that every code point start..end has;
 166  *     may have been modified by filter(context, trie value)
 167  *     if that function pointer is not NULL
 168  * @return the range end code point, or -1 if start is not a valid code point
 169  * @draft ICU 63
 170  */
 171 U_CAPI UChar32 U_EXPORT2
 172 umutablecptrie_getRange(const UMutableCPTrie *trie, UChar32 start,
 173                         UCPMapRangeOption option, uint32_t surrogateValue,
 174                         UCPMapValueFilter *filter, const void *context, uint32_t *pValue);
 175
 176 /**
 177  * Sets a value for a code point.
 178  *
 179  * @param trie the trie
 180  * @param c the code point
 181  * @param value the value
 182  * @param pErrorCode an in/out ICU UErrorCode
 183  * @draft ICU 63
 184  */
 185 U_CAPI void U_EXPORT2
 186 umutablecptrie_set(UMutableCPTrie *trie, UChar32 c, uint32_t value, UErrorCode *pErrorCode);
 187
 188 /**
 189  * Sets a value for each code point [start..end].
 190  * Faster and more space-efficient than setting the value for each code point separately.
 191  *
 192  * @param trie the trie
 193  * @param start the first code point to get the value
 194  * @param end the last code point to get the value (inclusive)
 195  * @param value the value
 196  * @param pErrorCode an in/out ICU UErrorCode
 197  * @draft ICU 63
 198  */
 199 U_CAPI void U_EXPORT2
 200 umutablecptrie_setRange(UMutableCPTrie *trie,
 201                         UChar32 start, UChar32 end,
 202                         uint32_t value, UErrorCode *pErrorCode);
 203
 204 /**
 205  * Compacts the data and builds an immutable UCPTrie according to the parameters.
 206  * After this, the mutable trie will be empty.
 207  *
 208  * The mutable trie stores 32-bit values until buildImmutable() is called.
 209  * If values shorter than 32 bits are to be stored in the immutable trie,
 210  * then the upper bits are discarded.
 211  * For example, when the mutable trie contains values 0x81, -0x7f, and 0xa581,
 212  * and the value width is 8 bits, then each of these is stored as 0x81
 213  * and the immutable trie will return that as an unsigned value.
 214  * (Some implementations may want to make productive temporary use of the upper bits
 215  * until buildImmutable() discards them.)
 216  *
 217  * Not every possible set of mappings can be built into a UCPTrie,
 218  * because of limitations resulting from speed and space optimizations.
 219  * Every Unicode assigned character can be mapped to a unique value.
 220  * Typical data yields data structures far smaller than the limitations.
 221  *
 222  * It is possible to construct extremely unusual mappings that exceed the data structure limits.
 223  * In such a case this function will fail with a U_INDEX_OUTOFBOUNDS_ERROR.
 224  *
 225  * @param trie the trie trie
 226  * @param type selects the trie type
 227  * @param valueWidth selects the number of bits in a trie data value; if smaller than 32 bits,
 228  *                   then the values stored in the trie will be truncated first
 229  * @param pErrorCode an in/out ICU UErrorCode
 230  *
 231  * @see umutablecptrie_fromUCPTrie
 232  * @draft ICU 63
 233  */
 234 U_CAPI UCPTrie * U_EXPORT2
 235 umutablecptrie_buildImmutable(UMutableCPTrie *trie, UCPTrieType type, UCPTrieValueWidth valueWidth,
 236                               UErrorCode *pErrorCode);
 237
 238 U_CDECL_END
 239
 240 #endif  // U_HIDE_DRAFT_API
 241 #endif