| 1 | // © 2017 and later: Unicode, Inc. and others. | 
|---|
| 2 | // License & terms of use: http://www.unicode.org/copyright.html | 
|---|
| 3 |  | 
|---|
| 4 | // stringoptions.h | 
|---|
| 5 | // created: 2017jun08 Markus W. Scherer | 
|---|
| 6 |  | 
|---|
| 7 | #ifndef __STRINGOPTIONS_H__ | 
|---|
| 8 | #define __STRINGOPTIONS_H__ | 
|---|
| 9 |  | 
|---|
| 10 | #include "unicode/utypes.h" | 
|---|
| 11 |  | 
|---|
| 12 | /** | 
|---|
| 13 | * \file | 
|---|
| 14 | * \brief C API: Bit set option bit constants for various string and character processing functions. | 
|---|
| 15 | */ | 
|---|
| 16 |  | 
|---|
| 17 | /** | 
|---|
| 18 | * Option value for case folding: Use default mappings defined in CaseFolding.txt. | 
|---|
| 19 | * | 
|---|
| 20 | * @stable ICU 2.0 | 
|---|
| 21 | */ | 
|---|
| 22 | #define U_FOLD_CASE_DEFAULT 0 | 
|---|
| 23 |  | 
|---|
| 24 | /** | 
|---|
| 25 | * Option value for case folding: | 
|---|
| 26 | * | 
|---|
| 27 | * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I | 
|---|
| 28 | * and dotless i appropriately for Turkic languages (tr, az). | 
|---|
| 29 | * | 
|---|
| 30 | * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that | 
|---|
| 31 | * are to be included for default mappings and | 
|---|
| 32 | * excluded for the Turkic-specific mappings. | 
|---|
| 33 | * | 
|---|
| 34 | * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that | 
|---|
| 35 | * are to be excluded for default mappings and | 
|---|
| 36 | * included for the Turkic-specific mappings. | 
|---|
| 37 | * | 
|---|
| 38 | * @stable ICU 2.0 | 
|---|
| 39 | */ | 
|---|
| 40 | #define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 | 
|---|
| 41 |  | 
|---|
| 42 | /** | 
|---|
| 43 | * Titlecase the string as a whole rather than each word. | 
|---|
| 44 | * (Titlecase only the character at index 0, possibly adjusted.) | 
|---|
| 45 | * Option bits value for titlecasing APIs that take an options bit set. | 
|---|
| 46 | * | 
|---|
| 47 | * It is an error to specify multiple titlecasing iterator options together, | 
|---|
| 48 | * including both an options bit and an explicit BreakIterator. | 
|---|
| 49 | * | 
|---|
| 50 | * @see U_TITLECASE_ADJUST_TO_CASED | 
|---|
| 51 | * @stable ICU 60 | 
|---|
| 52 | */ | 
|---|
| 53 | #define U_TITLECASE_WHOLE_STRING 0x20 | 
|---|
| 54 |  | 
|---|
| 55 | /** | 
|---|
| 56 | * Titlecase sentences rather than words. | 
|---|
| 57 | * (Titlecase only the first character of each sentence, possibly adjusted.) | 
|---|
| 58 | * Option bits value for titlecasing APIs that take an options bit set. | 
|---|
| 59 | * | 
|---|
| 60 | * It is an error to specify multiple titlecasing iterator options together, | 
|---|
| 61 | * including both an options bit and an explicit BreakIterator. | 
|---|
| 62 | * | 
|---|
| 63 | * @see U_TITLECASE_ADJUST_TO_CASED | 
|---|
| 64 | * @stable ICU 60 | 
|---|
| 65 | */ | 
|---|
| 66 | #define U_TITLECASE_SENTENCES 0x40 | 
|---|
| 67 |  | 
|---|
| 68 | /** | 
|---|
| 69 | * Do not lowercase non-initial parts of words when titlecasing. | 
|---|
| 70 | * Option bit for titlecasing APIs that take an options bit set. | 
|---|
| 71 | * | 
|---|
| 72 | * By default, titlecasing will titlecase the character at each | 
|---|
| 73 | * (possibly adjusted) BreakIterator index and | 
|---|
| 74 | * lowercase all other characters up to the next iterator index. | 
|---|
| 75 | * With this option, the other characters will not be modified. | 
|---|
| 76 | * | 
|---|
| 77 | * @see U_TITLECASE_ADJUST_TO_CASED | 
|---|
| 78 | * @see UnicodeString::toTitle | 
|---|
| 79 | * @see CaseMap::toTitle | 
|---|
| 80 | * @see ucasemap_setOptions | 
|---|
| 81 | * @see ucasemap_toTitle | 
|---|
| 82 | * @see ucasemap_utf8ToTitle | 
|---|
| 83 | * @stable ICU 3.8 | 
|---|
| 84 | */ | 
|---|
| 85 | #define U_TITLECASE_NO_LOWERCASE 0x100 | 
|---|
| 86 |  | 
|---|
| 87 | /** | 
|---|
| 88 | * Do not adjust the titlecasing BreakIterator indexes; | 
|---|
| 89 | * titlecase exactly the characters at breaks from the iterator. | 
|---|
| 90 | * Option bit for titlecasing APIs that take an options bit set. | 
|---|
| 91 | * | 
|---|
| 92 | * By default, titlecasing will take each break iterator index, | 
|---|
| 93 | * adjust it to the next relevant character (see U_TITLECASE_ADJUST_TO_CASED), | 
|---|
| 94 | * and titlecase that one. | 
|---|
| 95 | * | 
|---|
| 96 | * Other characters are lowercased. | 
|---|
| 97 | * | 
|---|
| 98 | * It is an error to specify multiple titlecasing adjustment options together. | 
|---|
| 99 | * | 
|---|
| 100 | * @see U_TITLECASE_ADJUST_TO_CASED | 
|---|
| 101 | * @see U_TITLECASE_NO_LOWERCASE | 
|---|
| 102 | * @see UnicodeString::toTitle | 
|---|
| 103 | * @see CaseMap::toTitle | 
|---|
| 104 | * @see ucasemap_setOptions | 
|---|
| 105 | * @see ucasemap_toTitle | 
|---|
| 106 | * @see ucasemap_utf8ToTitle | 
|---|
| 107 | * @stable ICU 3.8 | 
|---|
| 108 | */ | 
|---|
| 109 | #define U_TITLECASE_NO_BREAK_ADJUSTMENT 0x200 | 
|---|
| 110 |  | 
|---|
| 111 | /** | 
|---|
| 112 | * Adjust each titlecasing BreakIterator index to the next cased character. | 
|---|
| 113 | * (See the Unicode Standard, chapter 3, Default Case Conversion, R3 toTitlecase(X).) | 
|---|
| 114 | * Option bit for titlecasing APIs that take an options bit set. | 
|---|
| 115 | * | 
|---|
| 116 | * This used to be the default index adjustment in ICU. | 
|---|
| 117 | * Since ICU 60, the default index adjustment is to the next character that is | 
|---|
| 118 | * a letter, number, symbol, or private use code point. | 
|---|
| 119 | * (Uncased modifier letters are skipped.) | 
|---|
| 120 | * The difference in behavior is small for word titlecasing, | 
|---|
| 121 | * but the new adjustment is much better for whole-string and sentence titlecasing: | 
|---|
| 122 | * It yields "49ers" and "«丰(abc)»" instead of "49Ers" and "«丰(Abc)»". | 
|---|
| 123 | * | 
|---|
| 124 | * It is an error to specify multiple titlecasing adjustment options together. | 
|---|
| 125 | * | 
|---|
| 126 | * @see U_TITLECASE_NO_BREAK_ADJUSTMENT | 
|---|
| 127 | * @stable ICU 60 | 
|---|
| 128 | */ | 
|---|
| 129 | #define U_TITLECASE_ADJUST_TO_CASED 0x400 | 
|---|
| 130 |  | 
|---|
| 131 | /** | 
|---|
| 132 | * Option for string transformation functions to not first reset the Edits object. | 
|---|
| 133 | * Used for example in some case-mapping and normalization functions. | 
|---|
| 134 | * | 
|---|
| 135 | * @see CaseMap | 
|---|
| 136 | * @see Edits | 
|---|
| 137 | * @see Normalizer2 | 
|---|
| 138 | * @stable ICU 60 | 
|---|
| 139 | */ | 
|---|
| 140 | #define U_EDITS_NO_RESET 0x2000 | 
|---|
| 141 |  | 
|---|
| 142 | /** | 
|---|
| 143 | * Omit unchanged text when recording how source substrings | 
|---|
| 144 | * relate to changed and unchanged result substrings. | 
|---|
| 145 | * Used for example in some case-mapping and normalization functions. | 
|---|
| 146 | * | 
|---|
| 147 | * @see CaseMap | 
|---|
| 148 | * @see Edits | 
|---|
| 149 | * @see Normalizer2 | 
|---|
| 150 | * @stable ICU 60 | 
|---|
| 151 | */ | 
|---|
| 152 | #define U_OMIT_UNCHANGED_TEXT 0x4000 | 
|---|
| 153 |  | 
|---|
| 154 | /** | 
|---|
| 155 | * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: | 
|---|
| 156 | * Compare strings in code point order instead of code unit order. | 
|---|
| 157 | * @stable ICU 2.2 | 
|---|
| 158 | */ | 
|---|
| 159 | #define U_COMPARE_CODE_POINT_ORDER  0x8000 | 
|---|
| 160 |  | 
|---|
| 161 | /** | 
|---|
| 162 | * Option bit for unorm_compare: | 
|---|
| 163 | * Perform case-insensitive comparison. | 
|---|
| 164 | * @stable ICU 2.2 | 
|---|
| 165 | */ | 
|---|
| 166 | #define U_COMPARE_IGNORE_CASE       0x10000 | 
|---|
| 167 |  | 
|---|
| 168 | /** | 
|---|
| 169 | * Option bit for unorm_compare: | 
|---|
| 170 | * Both input strings are assumed to fulfill FCD conditions. | 
|---|
| 171 | * @stable ICU 2.2 | 
|---|
| 172 | */ | 
|---|
| 173 | #define UNORM_INPUT_IS_FCD          0x20000 | 
|---|
| 174 |  | 
|---|
| 175 | // Related definitions elsewhere. | 
|---|
| 176 | // Options that are not meaningful in the same functions | 
|---|
| 177 | // can share the same bits. | 
|---|
| 178 | // | 
|---|
| 179 | // Public: | 
|---|
| 180 | // unicode/unorm.h #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 | 
|---|
| 181 | // | 
|---|
| 182 | // Internal: (may change or be removed) | 
|---|
| 183 | // ucase.h #define _STRCASECMP_OPTIONS_MASK 0xffff | 
|---|
| 184 | // ucase.h #define _FOLD_CASE_OPTIONS_MASK 7 | 
|---|
| 185 | // ucasemap_imp.h #define U_TITLECASE_ITERATOR_MASK 0xe0 | 
|---|
| 186 | // ucasemap_imp.h #define U_TITLECASE_ADJUSTMENT_MASK 0x600 | 
|---|
| 187 | // ustr_imp.h #define _STRNCMP_STYLE 0x1000 | 
|---|
| 188 | // unormcmp.cpp #define _COMPARE_EQUIV 0x80000 | 
|---|
| 189 |  | 
|---|
| 190 | #endif  // __STRINGOPTIONS_H__ | 
|---|
| 191 |  | 
|---|