w32tex
About: TeX Live provides a comprehensive TeX system including all the major TeX-related programs, macro packages, and fonts that are free software. Windows sources.
  Fossies Dox: w32tex-src.tar.xz  ("unofficial" and yet experimental doxygen-generated source code documentation)  

uchar.h File Reference

C API: Unicode Properties. More...

Include dependency graph for uchar.h:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Macros

#define USET_DEFINED
 
#define U_UNICODE_VERSION   "13.0"
 
#define UCHAR_MIN_VALUE   0
 
#define UCHAR_MAX_VALUE   0x10ffff
 
#define U_MASK(x)   ((uint32_t)1<<(x))
 
#define U_GC_CN_MASK   U_MASK(U_GENERAL_OTHER_TYPES)
 
#define U_GC_LU_MASK   U_MASK(U_UPPERCASE_LETTER)
 
#define U_GC_LL_MASK   U_MASK(U_LOWERCASE_LETTER)
 
#define U_GC_LT_MASK   U_MASK(U_TITLECASE_LETTER)
 
#define U_GC_LM_MASK   U_MASK(U_MODIFIER_LETTER)
 
#define U_GC_LO_MASK   U_MASK(U_OTHER_LETTER)
 
#define U_GC_MN_MASK   U_MASK(U_NON_SPACING_MARK)
 
#define U_GC_ME_MASK   U_MASK(U_ENCLOSING_MARK)
 
#define U_GC_MC_MASK   U_MASK(U_COMBINING_SPACING_MARK)
 
#define U_GC_ND_MASK   U_MASK(U_DECIMAL_DIGIT_NUMBER)
 
#define U_GC_NL_MASK   U_MASK(U_LETTER_NUMBER)
 
#define U_GC_NO_MASK   U_MASK(U_OTHER_NUMBER)
 
#define U_GC_ZS_MASK   U_MASK(U_SPACE_SEPARATOR)
 
#define U_GC_ZL_MASK   U_MASK(U_LINE_SEPARATOR)
 
#define U_GC_ZP_MASK   U_MASK(U_PARAGRAPH_SEPARATOR)
 
#define U_GC_CC_MASK   U_MASK(U_CONTROL_CHAR)
 
#define U_GC_CF_MASK   U_MASK(U_FORMAT_CHAR)
 
#define U_GC_CO_MASK   U_MASK(U_PRIVATE_USE_CHAR)
 
#define U_GC_CS_MASK   U_MASK(U_SURROGATE)
 
#define U_GC_PD_MASK   U_MASK(U_DASH_PUNCTUATION)
 
#define U_GC_PS_MASK   U_MASK(U_START_PUNCTUATION)
 
#define U_GC_PE_MASK   U_MASK(U_END_PUNCTUATION)
 
#define U_GC_PC_MASK   U_MASK(U_CONNECTOR_PUNCTUATION)
 
#define U_GC_PO_MASK   U_MASK(U_OTHER_PUNCTUATION)
 
#define U_GC_SM_MASK   U_MASK(U_MATH_SYMBOL)
 
#define U_GC_SC_MASK   U_MASK(U_CURRENCY_SYMBOL)
 
#define U_GC_SK_MASK   U_MASK(U_MODIFIER_SYMBOL)
 
#define U_GC_SO_MASK   U_MASK(U_OTHER_SYMBOL)
 
#define U_GC_PI_MASK   U_MASK(U_INITIAL_PUNCTUATION)
 
#define U_GC_PF_MASK   U_MASK(U_FINAL_PUNCTUATION)
 
#define U_GC_L_MASK    (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)
 
#define U_GC_LC_MASK    (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
 
#define U_GC_M_MASK   (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
 
#define U_GC_N_MASK   (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
 
#define U_GC_Z_MASK   (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
 
#define U_GC_C_MASK    (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)
 
#define U_GC_P_MASK
 
#define U_GC_S_MASK   (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
 
#define U_NO_NUMERIC_VALUE   ((double)-123456789.)
 
#define U_GET_GC_MASK(c)   U_MASK(u_charType(c))
 

Typedefs

typedef struct USet USet
 
typedef enum UProperty UProperty
 
typedef enum UCharCategory UCharCategory
 
typedef enum UCharDirection UCharDirection
 
typedef enum UBidiPairedBracketType UBidiPairedBracketType
 
typedef enum UBlockCode UBlockCode
 
typedef enum UEastAsianWidth UEastAsianWidth
 
typedef enum UCharNameChoice UCharNameChoice
 
typedef enum UPropertyNameChoice UPropertyNameChoice
 
typedef enum UDecompositionType UDecompositionType
 
typedef enum UJoiningType UJoiningType
 
typedef enum UJoiningGroup UJoiningGroup
 
typedef enum UGraphemeClusterBreak UGraphemeClusterBreak
 
typedef enum UWordBreakValues UWordBreakValues
 
typedef enum USentenceBreak USentenceBreak
 
typedef enum ULineBreak ULineBreak
 
typedef enum UNumericType UNumericType
 
typedef enum UHangulSyllableType UHangulSyllableType
 
typedef enum UIndicPositionalCategory UIndicPositionalCategory
 
typedef enum UIndicSyllabicCategory UIndicSyllabicCategory
 
typedef enum UVerticalOrientation UVerticalOrientation
 
typedef UBool UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type)
 
typedef UBool UEnumCharNamesFn(void *context, UChar32 code, UCharNameChoice nameChoice, const char *name, int32_t length)
 

Enumerations

enum  UProperty {
  UCHAR_ALPHABETIC =0 , UCHAR_BINARY_START =UCHAR_ALPHABETIC , UCHAR_ASCII_HEX_DIGIT =1 , UCHAR_BIDI_CONTROL =2 ,
  UCHAR_BIDI_MIRRORED =3 , UCHAR_DASH =4 , UCHAR_DEFAULT_IGNORABLE_CODE_POINT =5 , UCHAR_DEPRECATED =6 ,
  UCHAR_DIACRITIC =7 , UCHAR_EXTENDER =8 , UCHAR_FULL_COMPOSITION_EXCLUSION =9 , UCHAR_GRAPHEME_BASE =10 ,
  UCHAR_GRAPHEME_EXTEND =11 , UCHAR_GRAPHEME_LINK =12 , UCHAR_HEX_DIGIT =13 , UCHAR_HYPHEN =14 ,
  UCHAR_ID_CONTINUE =15 , UCHAR_ID_START =16 , UCHAR_IDEOGRAPHIC =17 , UCHAR_IDS_BINARY_OPERATOR =18 ,
  UCHAR_IDS_TRINARY_OPERATOR =19 , UCHAR_JOIN_CONTROL =20 , UCHAR_LOGICAL_ORDER_EXCEPTION =21 , UCHAR_LOWERCASE =22 ,
  UCHAR_MATH =23 , UCHAR_NONCHARACTER_CODE_POINT =24 , UCHAR_QUOTATION_MARK =25 , UCHAR_RADICAL =26 ,
  UCHAR_SOFT_DOTTED =27 , UCHAR_TERMINAL_PUNCTUATION =28 , UCHAR_UNIFIED_IDEOGRAPH =29 , UCHAR_UPPERCASE =30 ,
  UCHAR_WHITE_SPACE =31 , UCHAR_XID_CONTINUE =32 , UCHAR_XID_START =33 , UCHAR_CASE_SENSITIVE =34 ,
  UCHAR_S_TERM =35 , UCHAR_VARIATION_SELECTOR =36 , UCHAR_NFD_INERT =37 , UCHAR_NFKD_INERT =38 ,
  UCHAR_NFC_INERT =39 , UCHAR_NFKC_INERT =40 , UCHAR_SEGMENT_STARTER =41 , UCHAR_PATTERN_SYNTAX =42 ,
  UCHAR_PATTERN_WHITE_SPACE =43 , UCHAR_POSIX_ALNUM =44 , UCHAR_POSIX_BLANK =45 , UCHAR_POSIX_GRAPH =46 ,
  UCHAR_POSIX_PRINT =47 , UCHAR_POSIX_XDIGIT =48 , UCHAR_CASED =49 , UCHAR_CASE_IGNORABLE =50 ,
  UCHAR_CHANGES_WHEN_LOWERCASED =51 , UCHAR_CHANGES_WHEN_UPPERCASED =52 , UCHAR_CHANGES_WHEN_TITLECASED =53 , UCHAR_CHANGES_WHEN_CASEFOLDED =54 ,
  UCHAR_CHANGES_WHEN_CASEMAPPED =55 , UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED =56 , UCHAR_EMOJI =57 , UCHAR_EMOJI_PRESENTATION =58 ,
  UCHAR_EMOJI_MODIFIER =59 , UCHAR_EMOJI_MODIFIER_BASE =60 , UCHAR_EMOJI_COMPONENT =61 , UCHAR_REGIONAL_INDICATOR =62 ,
  UCHAR_PREPENDED_CONCATENATION_MARK =63 , UCHAR_EXTENDED_PICTOGRAPHIC =64 , UCHAR_BINARY_LIMIT , UCHAR_BIDI_CLASS =0x1000 ,
  UCHAR_INT_START =UCHAR_BIDI_CLASS , UCHAR_BLOCK =0x1001 , UCHAR_CANONICAL_COMBINING_CLASS =0x1002 , UCHAR_DECOMPOSITION_TYPE =0x1003 ,
  UCHAR_EAST_ASIAN_WIDTH =0x1004 , UCHAR_GENERAL_CATEGORY =0x1005 , UCHAR_JOINING_GROUP =0x1006 , UCHAR_JOINING_TYPE =0x1007 ,
  UCHAR_LINE_BREAK =0x1008 , UCHAR_NUMERIC_TYPE =0x1009 , UCHAR_SCRIPT =0x100A , UCHAR_HANGUL_SYLLABLE_TYPE =0x100B ,
  UCHAR_NFD_QUICK_CHECK =0x100C , UCHAR_NFKD_QUICK_CHECK =0x100D , UCHAR_NFC_QUICK_CHECK =0x100E , UCHAR_NFKC_QUICK_CHECK =0x100F ,
  UCHAR_LEAD_CANONICAL_COMBINING_CLASS =0x1010 , UCHAR_TRAIL_CANONICAL_COMBINING_CLASS =0x1011 , UCHAR_GRAPHEME_CLUSTER_BREAK =0x1012 , UCHAR_SENTENCE_BREAK =0x1013 ,
  UCHAR_WORD_BREAK =0x1014 , UCHAR_BIDI_PAIRED_BRACKET_TYPE =0x1015 , UCHAR_INDIC_POSITIONAL_CATEGORY =0x1016 , UCHAR_INDIC_SYLLABIC_CATEGORY =0x1017 ,
  UCHAR_VERTICAL_ORIENTATION =0x1018 , UCHAR_INT_LIMIT =0x1019 , UCHAR_GENERAL_CATEGORY_MASK =0x2000 , UCHAR_MASK_START =UCHAR_GENERAL_CATEGORY_MASK ,
  UCHAR_MASK_LIMIT =0x2001 , UCHAR_NUMERIC_VALUE =0x3000 , UCHAR_DOUBLE_START =UCHAR_NUMERIC_VALUE , UCHAR_DOUBLE_LIMIT =0x3001 ,
  UCHAR_AGE =0x4000 , UCHAR_STRING_START =UCHAR_AGE , UCHAR_BIDI_MIRRORING_GLYPH =0x4001 , UCHAR_CASE_FOLDING =0x4002 ,
  UCHAR_ISO_COMMENT =0x4003 , UCHAR_LOWERCASE_MAPPING =0x4004 , UCHAR_NAME =0x4005 , UCHAR_SIMPLE_CASE_FOLDING =0x4006 ,
  UCHAR_SIMPLE_LOWERCASE_MAPPING =0x4007 , UCHAR_SIMPLE_TITLECASE_MAPPING =0x4008 , UCHAR_SIMPLE_UPPERCASE_MAPPING =0x4009 , UCHAR_TITLECASE_MAPPING =0x400A ,
  UCHAR_UNICODE_1_NAME =0x400B , UCHAR_UPPERCASE_MAPPING =0x400C , UCHAR_BIDI_PAIRED_BRACKET =0x400D , UCHAR_STRING_LIMIT =0x400E ,
  UCHAR_SCRIPT_EXTENSIONS =0x7000 , UCHAR_OTHER_PROPERTY_START =UCHAR_SCRIPT_EXTENSIONS , UCHAR_OTHER_PROPERTY_LIMIT =0x7001 , UCHAR_INVALID_CODE = -1
}
 
enum  UCharCategory {
  U_UNASSIGNED = 0 , U_GENERAL_OTHER_TYPES = 0 , U_UPPERCASE_LETTER = 1 , U_LOWERCASE_LETTER = 2 ,
  U_TITLECASE_LETTER = 3 , U_MODIFIER_LETTER = 4 , U_OTHER_LETTER = 5 , U_NON_SPACING_MARK = 6 ,
  U_ENCLOSING_MARK = 7 , U_COMBINING_SPACING_MARK = 8 , U_DECIMAL_DIGIT_NUMBER = 9 , U_LETTER_NUMBER = 10 ,
  U_OTHER_NUMBER = 11 , U_SPACE_SEPARATOR = 12 , U_LINE_SEPARATOR = 13 , U_PARAGRAPH_SEPARATOR = 14 ,
  U_CONTROL_CHAR = 15 , U_FORMAT_CHAR = 16 , U_PRIVATE_USE_CHAR = 17 , U_SURROGATE = 18 ,
  U_DASH_PUNCTUATION = 19 , U_START_PUNCTUATION = 20 , U_END_PUNCTUATION = 21 , U_CONNECTOR_PUNCTUATION = 22 ,
  U_OTHER_PUNCTUATION = 23 , U_MATH_SYMBOL = 24 , U_CURRENCY_SYMBOL = 25 , U_MODIFIER_SYMBOL = 26 ,
  U_OTHER_SYMBOL = 27 , U_INITIAL_PUNCTUATION = 28 , U_FINAL_PUNCTUATION = 29 , U_CHAR_CATEGORY_COUNT
}
 
enum  UCharDirection {
  U_LEFT_TO_RIGHT = 0 , U_RIGHT_TO_LEFT = 1 , U_EUROPEAN_NUMBER = 2 , U_EUROPEAN_NUMBER_SEPARATOR = 3 ,
  U_EUROPEAN_NUMBER_TERMINATOR = 4 , U_ARABIC_NUMBER = 5 , U_COMMON_NUMBER_SEPARATOR = 6 , U_BLOCK_SEPARATOR = 7 ,
  U_SEGMENT_SEPARATOR = 8 , U_WHITE_SPACE_NEUTRAL = 9 , U_OTHER_NEUTRAL = 10 , U_LEFT_TO_RIGHT_EMBEDDING = 11 ,
  U_LEFT_TO_RIGHT_OVERRIDE = 12 , U_RIGHT_TO_LEFT_ARABIC = 13 , U_RIGHT_TO_LEFT_EMBEDDING = 14 , U_RIGHT_TO_LEFT_OVERRIDE = 15 ,
  U_POP_DIRECTIONAL_FORMAT = 16 , U_DIR_NON_SPACING_MARK = 17 , U_BOUNDARY_NEUTRAL = 18 , U_FIRST_STRONG_ISOLATE = 19 ,
  U_LEFT_TO_RIGHT_ISOLATE = 20 , U_RIGHT_TO_LEFT_ISOLATE = 21 , U_POP_DIRECTIONAL_ISOLATE = 22 , U_CHAR_DIRECTION_COUNT
}
 
enum  UBidiPairedBracketType { U_BPT_NONE , U_BPT_OPEN , U_BPT_CLOSE , U_BPT_COUNT }
 
enum  UBlockCode {
  UBLOCK_NO_BLOCK = 0 , UBLOCK_BASIC_LATIN = 1 , UBLOCK_LATIN_1_SUPPLEMENT =2 , UBLOCK_LATIN_EXTENDED_A =3 ,
  UBLOCK_LATIN_EXTENDED_B =4 , UBLOCK_IPA_EXTENSIONS =5 , UBLOCK_SPACING_MODIFIER_LETTERS =6 , UBLOCK_COMBINING_DIACRITICAL_MARKS =7 ,
  UBLOCK_GREEK =8 , UBLOCK_CYRILLIC =9 , UBLOCK_ARMENIAN =10 , UBLOCK_HEBREW =11 ,
  UBLOCK_ARABIC =12 , UBLOCK_SYRIAC =13 , UBLOCK_THAANA =14 , UBLOCK_DEVANAGARI =15 ,
  UBLOCK_BENGALI =16 , UBLOCK_GURMUKHI =17 , UBLOCK_GUJARATI =18 , UBLOCK_ORIYA =19 ,
  UBLOCK_TAMIL =20 , UBLOCK_TELUGU =21 , UBLOCK_KANNADA =22 , UBLOCK_MALAYALAM =23 ,
  UBLOCK_SINHALA =24 , UBLOCK_THAI =25 , UBLOCK_LAO =26 , UBLOCK_TIBETAN =27 ,
  UBLOCK_MYANMAR =28 , UBLOCK_GEORGIAN =29 , UBLOCK_HANGUL_JAMO =30 , UBLOCK_ETHIOPIC =31 ,
  UBLOCK_CHEROKEE =32 , UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33 , UBLOCK_OGHAM =34 , UBLOCK_RUNIC =35 ,
  UBLOCK_KHMER =36 , UBLOCK_MONGOLIAN =37 , UBLOCK_LATIN_EXTENDED_ADDITIONAL =38 , UBLOCK_GREEK_EXTENDED =39 ,
  UBLOCK_GENERAL_PUNCTUATION =40 , UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41 , UBLOCK_CURRENCY_SYMBOLS =42 , UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43 ,
  UBLOCK_LETTERLIKE_SYMBOLS =44 , UBLOCK_NUMBER_FORMS =45 , UBLOCK_ARROWS =46 , UBLOCK_MATHEMATICAL_OPERATORS =47 ,
  UBLOCK_MISCELLANEOUS_TECHNICAL =48 , UBLOCK_CONTROL_PICTURES =49 , UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50 , UBLOCK_ENCLOSED_ALPHANUMERICS =51 ,
  UBLOCK_BOX_DRAWING =52 , UBLOCK_BLOCK_ELEMENTS =53 , UBLOCK_GEOMETRIC_SHAPES =54 , UBLOCK_MISCELLANEOUS_SYMBOLS =55 ,
  UBLOCK_DINGBATS =56 , UBLOCK_BRAILLE_PATTERNS =57 , UBLOCK_CJK_RADICALS_SUPPLEMENT =58 , UBLOCK_KANGXI_RADICALS =59 ,
  UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60 , UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61 , UBLOCK_HIRAGANA =62 , UBLOCK_KATAKANA =63 ,
  UBLOCK_BOPOMOFO =64 , UBLOCK_HANGUL_COMPATIBILITY_JAMO =65 , UBLOCK_KANBUN =66 , UBLOCK_BOPOMOFO_EXTENDED =67 ,
  UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68 , UBLOCK_CJK_COMPATIBILITY =69 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71 ,
  UBLOCK_YI_SYLLABLES =72 , UBLOCK_YI_RADICALS =73 , UBLOCK_HANGUL_SYLLABLES =74 , UBLOCK_HIGH_SURROGATES =75 ,
  UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76 , UBLOCK_LOW_SURROGATES =77 , UBLOCK_PRIVATE_USE_AREA =78 , UBLOCK_PRIVATE_USE = UBLOCK_PRIVATE_USE_AREA ,
  UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79 , UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80 , UBLOCK_ARABIC_PRESENTATION_FORMS_A =81 , UBLOCK_COMBINING_HALF_MARKS =82 ,
  UBLOCK_CJK_COMPATIBILITY_FORMS =83 , UBLOCK_SMALL_FORM_VARIANTS =84 , UBLOCK_ARABIC_PRESENTATION_FORMS_B =85 , UBLOCK_SPECIALS =86 ,
  UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87 , UBLOCK_OLD_ITALIC = 88 , UBLOCK_GOTHIC = 89 , UBLOCK_DESERET = 90 ,
  UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , UBLOCK_MUSICAL_SYMBOLS = 92 , UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B = 94 ,
  UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , UBLOCK_TAGS = 96 , UBLOCK_CYRILLIC_SUPPLEMENT = 97 , UBLOCK_CYRILLIC_SUPPLEMENTARY = UBLOCK_CYRILLIC_SUPPLEMENT ,
  UBLOCK_TAGALOG = 98 , UBLOCK_HANUNOO = 99 , UBLOCK_BUHID = 100 , UBLOCK_TAGBANWA = 101 ,
  UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102 , UBLOCK_SUPPLEMENTAL_ARROWS_A = 103 , UBLOCK_SUPPLEMENTAL_ARROWS_B = 104 , UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105 ,
  UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106 , UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107 , UBLOCK_VARIATION_SELECTORS = 108 , UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109 ,
  UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110 , UBLOCK_LIMBU = 111 , UBLOCK_TAI_LE = 112 , UBLOCK_KHMER_SYMBOLS = 113 ,
  UBLOCK_PHONETIC_EXTENSIONS = 114 , UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115 , UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116 , UBLOCK_LINEAR_B_SYLLABARY = 117 ,
  UBLOCK_LINEAR_B_IDEOGRAMS = 118 , UBLOCK_AEGEAN_NUMBERS = 119 , UBLOCK_UGARITIC = 120 , UBLOCK_SHAVIAN = 121 ,
  UBLOCK_OSMANYA = 122 , UBLOCK_CYPRIOT_SYLLABARY = 123 , UBLOCK_TAI_XUAN_JING_SYMBOLS = 124 , UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125 ,
  UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126 , UBLOCK_ANCIENT_GREEK_NUMBERS = 127 , UBLOCK_ARABIC_SUPPLEMENT = 128 , UBLOCK_BUGINESE = 129 ,
  UBLOCK_CJK_STROKES = 130 , UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131 , UBLOCK_COPTIC = 132 , UBLOCK_ETHIOPIC_EXTENDED = 133 ,
  UBLOCK_ETHIOPIC_SUPPLEMENT = 134 , UBLOCK_GEORGIAN_SUPPLEMENT = 135 , UBLOCK_GLAGOLITIC = 136 , UBLOCK_KHAROSHTHI = 137 ,
  UBLOCK_MODIFIER_TONE_LETTERS = 138 , UBLOCK_NEW_TAI_LUE = 139 , UBLOCK_OLD_PERSIAN = 140 , UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141 ,
  UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142 , UBLOCK_SYLOTI_NAGRI = 143 , UBLOCK_TIFINAGH = 144 , UBLOCK_VERTICAL_FORMS = 145 ,
  UBLOCK_NKO = 146 , UBLOCK_BALINESE = 147 , UBLOCK_LATIN_EXTENDED_C = 148 , UBLOCK_LATIN_EXTENDED_D = 149 ,
  UBLOCK_PHAGS_PA = 150 , UBLOCK_PHOENICIAN = 151 , UBLOCK_CUNEIFORM = 152 , UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153 ,
  UBLOCK_COUNTING_ROD_NUMERALS = 154 , UBLOCK_SUNDANESE = 155 , UBLOCK_LEPCHA = 156 , UBLOCK_OL_CHIKI = 157 ,
  UBLOCK_CYRILLIC_EXTENDED_A = 158 , UBLOCK_VAI = 159 , UBLOCK_CYRILLIC_EXTENDED_B = 160 , UBLOCK_SAURASHTRA = 161 ,
  UBLOCK_KAYAH_LI = 162 , UBLOCK_REJANG = 163 , UBLOCK_CHAM = 164 , UBLOCK_ANCIENT_SYMBOLS = 165 ,
  UBLOCK_PHAISTOS_DISC = 166 , UBLOCK_LYCIAN = 167 , UBLOCK_CARIAN = 168 , UBLOCK_LYDIAN = 169 ,
  UBLOCK_MAHJONG_TILES = 170 , UBLOCK_DOMINO_TILES = 171 , UBLOCK_SAMARITAN = 172 , UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173 ,
  UBLOCK_TAI_THAM = 174 , UBLOCK_VEDIC_EXTENSIONS = 175 , UBLOCK_LISU = 176 , UBLOCK_BAMUM = 177 ,
  UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178 , UBLOCK_DEVANAGARI_EXTENDED = 179 , UBLOCK_HANGUL_JAMO_EXTENDED_A = 180 , UBLOCK_JAVANESE = 181 ,
  UBLOCK_MYANMAR_EXTENDED_A = 182 , UBLOCK_TAI_VIET = 183 , UBLOCK_MEETEI_MAYEK = 184 , UBLOCK_HANGUL_JAMO_EXTENDED_B = 185 ,
  UBLOCK_IMPERIAL_ARAMAIC = 186 , UBLOCK_OLD_SOUTH_ARABIAN = 187 , UBLOCK_AVESTAN = 188 , UBLOCK_INSCRIPTIONAL_PARTHIAN = 189 ,
  UBLOCK_INSCRIPTIONAL_PAHLAVI = 190 , UBLOCK_OLD_TURKIC = 191 , UBLOCK_RUMI_NUMERAL_SYMBOLS = 192 , UBLOCK_KAITHI = 193 ,
  UBLOCK_EGYPTIAN_HIEROGLYPHS = 194 , UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195 , UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197 ,
  UBLOCK_MANDAIC = 198 , UBLOCK_BATAK = 199 , UBLOCK_ETHIOPIC_EXTENDED_A = 200 , UBLOCK_BRAHMI = 201 ,
  UBLOCK_BAMUM_SUPPLEMENT = 202 , UBLOCK_KANA_SUPPLEMENT = 203 , UBLOCK_PLAYING_CARDS = 204 , UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205 ,
  UBLOCK_EMOTICONS = 206 , UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207 , UBLOCK_ALCHEMICAL_SYMBOLS = 208 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209 ,
  UBLOCK_ARABIC_EXTENDED_A = 210 , UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS = 211 , UBLOCK_CHAKMA = 212 , UBLOCK_MEETEI_MAYEK_EXTENSIONS = 213 ,
  UBLOCK_MEROITIC_CURSIVE = 214 , UBLOCK_MEROITIC_HIEROGLYPHS = 215 , UBLOCK_MIAO = 216 , UBLOCK_SHARADA = 217 ,
  UBLOCK_SORA_SOMPENG = 218 , UBLOCK_SUNDANESE_SUPPLEMENT = 219 , UBLOCK_TAKRI = 220 , UBLOCK_BASSA_VAH = 221 ,
  UBLOCK_CAUCASIAN_ALBANIAN = 222 , UBLOCK_COPTIC_EPACT_NUMBERS = 223 , UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED = 224 , UBLOCK_DUPLOYAN = 225 ,
  UBLOCK_ELBASAN = 226 , UBLOCK_GEOMETRIC_SHAPES_EXTENDED = 227 , UBLOCK_GRANTHA = 228 , UBLOCK_KHOJKI = 229 ,
  UBLOCK_KHUDAWADI = 230 , UBLOCK_LATIN_EXTENDED_E = 231 , UBLOCK_LINEAR_A = 232 , UBLOCK_MAHAJANI = 233 ,
  UBLOCK_MANICHAEAN = 234 , UBLOCK_MENDE_KIKAKUI = 235 , UBLOCK_MODI = 236 , UBLOCK_MRO = 237 ,
  UBLOCK_MYANMAR_EXTENDED_B = 238 , UBLOCK_NABATAEAN = 239 , UBLOCK_OLD_NORTH_ARABIAN = 240 , UBLOCK_OLD_PERMIC = 241 ,
  UBLOCK_ORNAMENTAL_DINGBATS = 242 , UBLOCK_PAHAWH_HMONG = 243 , UBLOCK_PALMYRENE = 244 , UBLOCK_PAU_CIN_HAU = 245 ,
  UBLOCK_PSALTER_PAHLAVI = 246 , UBLOCK_SHORTHAND_FORMAT_CONTROLS = 247 , UBLOCK_SIDDHAM = 248 , UBLOCK_SINHALA_ARCHAIC_NUMBERS = 249 ,
  UBLOCK_SUPPLEMENTAL_ARROWS_C = 250 , UBLOCK_TIRHUTA = 251 , UBLOCK_WARANG_CITI = 252 , UBLOCK_AHOM = 253 ,
  UBLOCK_ANATOLIAN_HIEROGLYPHS = 254 , UBLOCK_CHEROKEE_SUPPLEMENT = 255 , UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E = 256 , UBLOCK_EARLY_DYNASTIC_CUNEIFORM = 257 ,
  UBLOCK_HATRAN = 258 , UBLOCK_MULTANI = 259 , UBLOCK_OLD_HUNGARIAN = 260 , UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS = 261 ,
  UBLOCK_SUTTON_SIGNWRITING = 262 , UBLOCK_ADLAM = 263 , UBLOCK_BHAIKSUKI = 264 , UBLOCK_CYRILLIC_EXTENDED_C = 265 ,
  UBLOCK_GLAGOLITIC_SUPPLEMENT = 266 , UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION = 267 , UBLOCK_MARCHEN = 268 , UBLOCK_MONGOLIAN_SUPPLEMENT = 269 ,
  UBLOCK_NEWA = 270 , UBLOCK_OSAGE = 271 , UBLOCK_TANGUT = 272 , UBLOCK_TANGUT_COMPONENTS = 273 ,
  UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F = 274 , UBLOCK_KANA_EXTENDED_A = 275 , UBLOCK_MASARAM_GONDI = 276 , UBLOCK_NUSHU = 277 ,
  UBLOCK_SOYOMBO = 278 , UBLOCK_SYRIAC_SUPPLEMENT = 279 , UBLOCK_ZANABAZAR_SQUARE = 280 , UBLOCK_CHESS_SYMBOLS = 281 ,
  UBLOCK_DOGRA = 282 , UBLOCK_GEORGIAN_EXTENDED = 283 , UBLOCK_GUNJALA_GONDI = 284 , UBLOCK_HANIFI_ROHINGYA = 285 ,
  UBLOCK_INDIC_SIYAQ_NUMBERS = 286 , UBLOCK_MAKASAR = 287 , UBLOCK_MAYAN_NUMERALS = 288 , UBLOCK_MEDEFAIDRIN = 289 ,
  UBLOCK_OLD_SOGDIAN = 290 , UBLOCK_SOGDIAN = 291 , UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS = 292 , UBLOCK_ELYMAIC = 293 ,
  UBLOCK_NANDINAGARI = 294 , UBLOCK_NYIAKENG_PUACHUE_HMONG = 295 , UBLOCK_OTTOMAN_SIYAQ_NUMBERS = 296 , UBLOCK_SMALL_KANA_EXTENSION = 297 ,
  UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A = 298 , UBLOCK_TAMIL_SUPPLEMENT = 299 , UBLOCK_WANCHO = 300 , UBLOCK_CHORASMIAN = 301 ,
  UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G = 302 , UBLOCK_DIVES_AKURU = 303 , UBLOCK_KHITAN_SMALL_SCRIPT = 304 , UBLOCK_LISU_SUPPLEMENT = 305 ,
  UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING = 306 , UBLOCK_TANGUT_SUPPLEMENT = 307 , UBLOCK_YEZIDI = 308 , UBLOCK_COUNT = 309 ,
  UBLOCK_INVALID_CODE =-1
}
 
enum  UEastAsianWidth {
  U_EA_NEUTRAL , U_EA_AMBIGUOUS , U_EA_HALFWIDTH , U_EA_FULLWIDTH ,
  U_EA_NARROW , U_EA_WIDE , U_EA_COUNT
}
 
enum  UCharNameChoice {
  U_UNICODE_CHAR_NAME , U_UNICODE_10_CHAR_NAME , U_EXTENDED_CHAR_NAME = U_UNICODE_CHAR_NAME+2 , U_CHAR_NAME_ALIAS ,
  U_CHAR_NAME_CHOICE_COUNT
}
 
enum  UPropertyNameChoice { U_SHORT_PROPERTY_NAME , U_LONG_PROPERTY_NAME , U_PROPERTY_NAME_CHOICE_COUNT }
 
enum  UDecompositionType {
  U_DT_NONE , U_DT_CANONICAL , U_DT_COMPAT , U_DT_CIRCLE ,
  U_DT_FINAL , U_DT_FONT , U_DT_FRACTION , U_DT_INITIAL ,
  U_DT_ISOLATED , U_DT_MEDIAL , U_DT_NARROW , U_DT_NOBREAK ,
  U_DT_SMALL , U_DT_SQUARE , U_DT_SUB , U_DT_SUPER ,
  U_DT_VERTICAL , U_DT_WIDE , U_DT_COUNT
}
 
enum  UJoiningType {
  U_JT_NON_JOINING , U_JT_JOIN_CAUSING , U_JT_DUAL_JOINING , U_JT_LEFT_JOINING ,
  U_JT_RIGHT_JOINING , U_JT_TRANSPARENT , U_JT_COUNT
}
 
enum  UJoiningGroup {
  U_JG_NO_JOINING_GROUP , U_JG_AIN , U_JG_ALAPH , U_JG_ALEF ,
  U_JG_BEH , U_JG_BETH , U_JG_DAL , U_JG_DALATH_RISH ,
  U_JG_E , U_JG_FEH , U_JG_FINAL_SEMKATH , U_JG_GAF ,
  U_JG_GAMAL , U_JG_HAH , U_JG_TEH_MARBUTA_GOAL , U_JG_HAMZA_ON_HEH_GOAL =U_JG_TEH_MARBUTA_GOAL ,
  U_JG_HE , U_JG_HEH , U_JG_HEH_GOAL , U_JG_HETH ,
  U_JG_KAF , U_JG_KAPH , U_JG_KNOTTED_HEH , U_JG_LAM ,
  U_JG_LAMADH , U_JG_MEEM , U_JG_MIM , U_JG_NOON ,
  U_JG_NUN , U_JG_PE , U_JG_QAF , U_JG_QAPH ,
  U_JG_REH , U_JG_REVERSED_PE , U_JG_SAD , U_JG_SADHE ,
  U_JG_SEEN , U_JG_SEMKATH , U_JG_SHIN , U_JG_SWASH_KAF ,
  U_JG_SYRIAC_WAW , U_JG_TAH , U_JG_TAW , U_JG_TEH_MARBUTA ,
  U_JG_TETH , U_JG_WAW , U_JG_YEH , U_JG_YEH_BARREE ,
  U_JG_YEH_WITH_TAIL , U_JG_YUDH , U_JG_YUDH_HE , U_JG_ZAIN ,
  U_JG_FE , U_JG_KHAPH , U_JG_ZHAIN , U_JG_BURUSHASKI_YEH_BARREE ,
  U_JG_FARSI_YEH , U_JG_NYA , U_JG_ROHINGYA_YEH , U_JG_MANICHAEAN_ALEPH ,
  U_JG_MANICHAEAN_AYIN , U_JG_MANICHAEAN_BETH , U_JG_MANICHAEAN_DALETH , U_JG_MANICHAEAN_DHAMEDH ,
  U_JG_MANICHAEAN_FIVE , U_JG_MANICHAEAN_GIMEL , U_JG_MANICHAEAN_HETH , U_JG_MANICHAEAN_HUNDRED ,
  U_JG_MANICHAEAN_KAPH , U_JG_MANICHAEAN_LAMEDH , U_JG_MANICHAEAN_MEM , U_JG_MANICHAEAN_NUN ,
  U_JG_MANICHAEAN_ONE , U_JG_MANICHAEAN_PE , U_JG_MANICHAEAN_QOPH , U_JG_MANICHAEAN_RESH ,
  U_JG_MANICHAEAN_SADHE , U_JG_MANICHAEAN_SAMEKH , U_JG_MANICHAEAN_TAW , U_JG_MANICHAEAN_TEN ,
  U_JG_MANICHAEAN_TETH , U_JG_MANICHAEAN_THAMEDH , U_JG_MANICHAEAN_TWENTY , U_JG_MANICHAEAN_WAW ,
  U_JG_MANICHAEAN_YODH , U_JG_MANICHAEAN_ZAYIN , U_JG_STRAIGHT_WAW , U_JG_AFRICAN_FEH ,
  U_JG_AFRICAN_NOON , U_JG_AFRICAN_QAF , U_JG_MALAYALAM_BHA , U_JG_MALAYALAM_JA ,
  U_JG_MALAYALAM_LLA , U_JG_MALAYALAM_LLLA , U_JG_MALAYALAM_NGA , U_JG_MALAYALAM_NNA ,
  U_JG_MALAYALAM_NNNA , U_JG_MALAYALAM_NYA , U_JG_MALAYALAM_RA , U_JG_MALAYALAM_SSA ,
  U_JG_MALAYALAM_TTA , U_JG_HANIFI_ROHINGYA_KINNA_YA , U_JG_HANIFI_ROHINGYA_PA , U_JG_COUNT
}
 
enum  UGraphemeClusterBreak {
  U_GCB_OTHER = 0 , U_GCB_CONTROL = 1 , U_GCB_CR = 2 , U_GCB_EXTEND = 3 ,
  U_GCB_L = 4 , U_GCB_LF = 5 , U_GCB_LV = 6 , U_GCB_LVT = 7 ,
  U_GCB_T = 8 , U_GCB_V = 9 , U_GCB_SPACING_MARK = 10 , U_GCB_PREPEND = 11 ,
  U_GCB_REGIONAL_INDICATOR = 12 , U_GCB_E_BASE = 13 , U_GCB_E_BASE_GAZ = 14 , U_GCB_E_MODIFIER = 15 ,
  U_GCB_GLUE_AFTER_ZWJ = 16 , U_GCB_ZWJ = 17 , U_GCB_COUNT = 18
}
 
enum  UWordBreakValues {
  U_WB_OTHER = 0 , U_WB_ALETTER = 1 , U_WB_FORMAT = 2 , U_WB_KATAKANA = 3 ,
  U_WB_MIDLETTER = 4 , U_WB_MIDNUM = 5 , U_WB_NUMERIC = 6 , U_WB_EXTENDNUMLET = 7 ,
  U_WB_CR = 8 , U_WB_EXTEND = 9 , U_WB_LF = 10 , U_WB_MIDNUMLET =11 ,
  U_WB_NEWLINE =12 , U_WB_REGIONAL_INDICATOR = 13 , U_WB_HEBREW_LETTER = 14 , U_WB_SINGLE_QUOTE = 15 ,
  U_WB_DOUBLE_QUOTE = 16 , U_WB_E_BASE = 17 , U_WB_E_BASE_GAZ = 18 , U_WB_E_MODIFIER = 19 ,
  U_WB_GLUE_AFTER_ZWJ = 20 , U_WB_ZWJ = 21 , U_WB_WSEGSPACE = 22 , U_WB_COUNT = 23
}
 
enum  USentenceBreak {
  U_SB_OTHER = 0 , U_SB_ATERM = 1 , U_SB_CLOSE = 2 , U_SB_FORMAT = 3 ,
  U_SB_LOWER = 4 , U_SB_NUMERIC = 5 , U_SB_OLETTER = 6 , U_SB_SEP = 7 ,
  U_SB_SP = 8 , U_SB_STERM = 9 , U_SB_UPPER = 10 , U_SB_CR = 11 ,
  U_SB_EXTEND = 12 , U_SB_LF = 13 , U_SB_SCONTINUE = 14 , U_SB_COUNT = 15
}
 
enum  ULineBreak {
  U_LB_UNKNOWN = 0 , U_LB_AMBIGUOUS = 1 , U_LB_ALPHABETIC = 2 , U_LB_BREAK_BOTH = 3 ,
  U_LB_BREAK_AFTER = 4 , U_LB_BREAK_BEFORE = 5 , U_LB_MANDATORY_BREAK = 6 , U_LB_CONTINGENT_BREAK = 7 ,
  U_LB_CLOSE_PUNCTUATION = 8 , U_LB_COMBINING_MARK = 9 , U_LB_CARRIAGE_RETURN = 10 , U_LB_EXCLAMATION = 11 ,
  U_LB_GLUE = 12 , U_LB_HYPHEN = 13 , U_LB_IDEOGRAPHIC = 14 , U_LB_INSEPARABLE = 15 ,
  U_LB_INSEPERABLE = U_LB_INSEPARABLE , U_LB_INFIX_NUMERIC = 16 , U_LB_LINE_FEED = 17 , U_LB_NONSTARTER = 18 ,
  U_LB_NUMERIC = 19 , U_LB_OPEN_PUNCTUATION = 20 , U_LB_POSTFIX_NUMERIC = 21 , U_LB_PREFIX_NUMERIC = 22 ,
  U_LB_QUOTATION = 23 , U_LB_COMPLEX_CONTEXT = 24 , U_LB_SURROGATE = 25 , U_LB_SPACE = 26 ,
  U_LB_BREAK_SYMBOLS = 27 , U_LB_ZWSPACE = 28 , U_LB_NEXT_LINE = 29 , U_LB_WORD_JOINER = 30 ,
  U_LB_H2 = 31 , U_LB_H3 = 32 , U_LB_JL = 33 , U_LB_JT = 34 ,
  U_LB_JV = 35 , U_LB_CLOSE_PARENTHESIS = 36 , U_LB_CONDITIONAL_JAPANESE_STARTER = 37 , U_LB_HEBREW_LETTER = 38 ,
  U_LB_REGIONAL_INDICATOR = 39 , U_LB_E_BASE = 40 , U_LB_E_MODIFIER = 41 , U_LB_ZWJ = 42 ,
  U_LB_COUNT = 43
}
 
enum  UNumericType {
  U_NT_NONE , U_NT_DECIMAL , U_NT_DIGIT , U_NT_NUMERIC ,
  U_NT_COUNT
}
 
enum  UHangulSyllableType {
  U_HST_NOT_APPLICABLE , U_HST_LEADING_JAMO , U_HST_VOWEL_JAMO , U_HST_TRAILING_JAMO ,
  U_HST_LV_SYLLABLE , U_HST_LVT_SYLLABLE , U_HST_COUNT
}
 
enum  UIndicPositionalCategory {
  U_INPC_NA , U_INPC_BOTTOM , U_INPC_BOTTOM_AND_LEFT , U_INPC_BOTTOM_AND_RIGHT ,
  U_INPC_LEFT , U_INPC_LEFT_AND_RIGHT , U_INPC_OVERSTRUCK , U_INPC_RIGHT ,
  U_INPC_TOP , U_INPC_TOP_AND_BOTTOM , U_INPC_TOP_AND_BOTTOM_AND_RIGHT , U_INPC_TOP_AND_LEFT ,
  U_INPC_TOP_AND_LEFT_AND_RIGHT , U_INPC_TOP_AND_RIGHT , U_INPC_VISUAL_ORDER_LEFT , U_INPC_TOP_AND_BOTTOM_AND_LEFT
}
 
enum  UIndicSyllabicCategory {
  U_INSC_OTHER , U_INSC_AVAGRAHA , U_INSC_BINDU , U_INSC_BRAHMI_JOINING_NUMBER ,
  U_INSC_CANTILLATION_MARK , U_INSC_CONSONANT , U_INSC_CONSONANT_DEAD , U_INSC_CONSONANT_FINAL ,
  U_INSC_CONSONANT_HEAD_LETTER , U_INSC_CONSONANT_INITIAL_POSTFIXED , U_INSC_CONSONANT_KILLER , U_INSC_CONSONANT_MEDIAL ,
  U_INSC_CONSONANT_PLACEHOLDER , U_INSC_CONSONANT_PRECEDING_REPHA , U_INSC_CONSONANT_PREFIXED , U_INSC_CONSONANT_SUBJOINED ,
  U_INSC_CONSONANT_SUCCEEDING_REPHA , U_INSC_CONSONANT_WITH_STACKER , U_INSC_GEMINATION_MARK , U_INSC_INVISIBLE_STACKER ,
  U_INSC_JOINER , U_INSC_MODIFYING_LETTER , U_INSC_NON_JOINER , U_INSC_NUKTA ,
  U_INSC_NUMBER , U_INSC_NUMBER_JOINER , U_INSC_PURE_KILLER , U_INSC_REGISTER_SHIFTER ,
  U_INSC_SYLLABLE_MODIFIER , U_INSC_TONE_LETTER , U_INSC_TONE_MARK , U_INSC_VIRAMA ,
  U_INSC_VISARGA , U_INSC_VOWEL , U_INSC_VOWEL_DEPENDENT , U_INSC_VOWEL_INDEPENDENT
}
 
enum  UVerticalOrientation { U_VO_ROTATED , U_VO_TRANSFORMED_ROTATED , U_VO_TRANSFORMED_UPRIGHT , U_VO_UPRIGHT }
 

Functions

UBool u_hasBinaryProperty_68 (UChar32 c, UProperty which)
 
const USetu_getBinaryPropertySet_68 (UProperty property, UErrorCode *pErrorCode)
 
UBool u_isUAlphabetic_68 (UChar32 c)
 
UBool u_isULowercase_68 (UChar32 c)
 
UBool u_isUUppercase_68 (UChar32 c)
 
UBool u_isUWhiteSpace_68 (UChar32 c)
 
int32_t u_getIntPropertyValue_68 (UChar32 c, UProperty which)
 
int32_t u_getIntPropertyMinValue_68 (UProperty which)
 
int32_t u_getIntPropertyMaxValue_68 (UProperty which)
 
const UCPMapu_getIntPropertyMap_68 (UProperty property, UErrorCode *pErrorCode)
 
double u_getNumericValue_68 (UChar32 c)
 
UBool u_islower_68 (UChar32 c)
 
UBool u_isupper_68 (UChar32 c)
 
UBool u_istitle_68 (UChar32 c)
 
UBool u_isdigit_68 (UChar32 c)
 
UBool u_isalpha_68 (UChar32 c)
 
UBool u_isalnum_68 (UChar32 c)
 
UBool u_isxdigit_68 (UChar32 c)
 
UBool u_ispunct_68 (UChar32 c)
 
UBool u_isgraph_68 (UChar32 c)
 
UBool u_isblank_68 (UChar32 c)
 
UBool u_isdefined_68 (UChar32 c)
 
UBool u_isspace_68 (UChar32 c)
 
UBool u_isJavaSpaceChar_68 (UChar32 c)
 
UBool u_isWhitespace_68 (UChar32 c)
 
UBool u_iscntrl_68 (UChar32 c)
 
UBool u_isISOControl_68 (UChar32 c)
 
UBool u_isprint_68 (UChar32 c)
 
UBool u_isbase_68 (UChar32 c)
 
UCharDirection u_charDirection_68 (UChar32 c)
 
UBool u_isMirrored_68 (UChar32 c)
 
UChar32 u_charMirror_68 (UChar32 c)
 
UChar32 u_getBidiPairedBracket_68 (UChar32 c)
 
int8_t u_charType_68 (UChar32 c)
 
void u_enumCharTypes_68 (UCharEnumTypeRange *enumRange, const void *context)
 
uint8_t u_getCombiningClass_68 (UChar32 c)
 
int32_t u_charDigitValue_68 (UChar32 c)
 
UBlockCode ublock_getCode_68 (UChar32 c)
 
int32_t u_charName_68 (UChar32 code, UCharNameChoice nameChoice, char *buffer, int32_t bufferLength, UErrorCode *pErrorCode)
 
int32_t u_getISOComment_68 (UChar32 c, char *dest, int32_t destCapacity, UErrorCode *pErrorCode)
 
UChar32 u_charFromName_68 (UCharNameChoice nameChoice, const char *name, UErrorCode *pErrorCode)
 
void u_enumCharNames_68 (UChar32 start, UChar32 limit, UEnumCharNamesFn *fn, void *context, UCharNameChoice nameChoice, UErrorCode *pErrorCode)
 
const char * u_getPropertyName_68 (UProperty property, UPropertyNameChoice nameChoice)
 
UProperty u_getPropertyEnum_68 (const char *alias)
 
const char * u_getPropertyValueName_68 (UProperty property, int32_t value, UPropertyNameChoice nameChoice)
 
int32_t u_getPropertyValueEnum_68 (UProperty property, const char *alias)
 
UBool u_isIDStart_68 (UChar32 c)
 
UBool u_isIDPart_68 (UChar32 c)
 
UBool u_isIDIgnorable_68 (UChar32 c)
 
UBool u_isJavaIDStart_68 (UChar32 c)
 
UBool u_isJavaIDPart_68 (UChar32 c)
 
UChar32 u_tolower_68 (UChar32 c)
 
UChar32 u_toupper_68 (UChar32 c)
 
UChar32 u_totitle_68 (UChar32 c)
 
UChar32 u_foldCase_68 (UChar32 c, uint32_t options)
 
int32_t u_digit_68 (UChar32 ch, int8_t radix)
 
UChar32 u_forDigit_68 (int32_t digit, int8_t radix)
 
void u_charAge_68 (UChar32 c, UVersionInfo versionArray)
 
void u_getUnicodeVersion_68 (UVersionInfo versionArray)
 
int32_t u_getFC_NFKC_Closure_68 (UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode)
 

Detailed Description

C API: Unicode Properties.

This C API provides low-level access to the Unicode Character Database. In addition to raw property values, some convenience functions calculate derived properties, for example for Java-style programming.

Unicode assigns each code point (not just assigned character) values for many properties. Most of them are simple boolean flags, or constants from a small enumerated list. For some properties, values are strings or other relatively more complex types.

For more information see "About the Unicode Character Database" (http://www.unicode.org/ucd/) and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).

Many properties are accessible via generic functions that take a UProperty selector.

  • u_hasBinaryProperty() returns a binary value (true/false) per property and code point.
  • u_getIntPropertyValue() returns an integer value per property and code point. For each supported enumerated or catalog property, there is an enum type for all of the property's values, and u_getIntPropertyValue() returns the numeric values of those constants.
  • u_getBinaryPropertySet() returns a set for each ICU-supported binary property with all code points for which the property is true.
  • u_getIntPropertyMap() returns a map for each ICU-supported enumerated/catalog/int-valued property which maps all Unicode code points to their values for that property.

Many functions are designed to match java.lang.Character functions. See the individual function documentation, and see the JDK 1.4 java.lang.Character documentation at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html

There are also functions that provide easy migration from C/POSIX functions like isblank(). Their use is generally discouraged because the C/POSIX standards do not define their semantics beyond the ASCII range, which means that different implementations exhibit very different behavior. Instead, Unicode properties should be used directly.

There are also only a few, broad C/POSIX character classes, and they tend to be used for conflicting purposes. For example, the "isalpha()" class is sometimes used to determine word boundaries, while a more sophisticated approach would at least distinguish initial letters from continuation characters (the latter including combining marks). (In ICU, BreakIterator is the most sophisticated API for word boundaries.) Another example: There is no "istitle()" class for titlecase characters.

ICU 3.4 and later provides API access for all twelve C/POSIX character classes. ICU implements them according to the Standard Recommendations in Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions (http://www.unicode.org/reports/tr18/#Compatibility_Properties).

API access for C/POSIX character classes is as follows:

Note: Some of the u_isxyz() functions in uchar.h predate, and do not match, the Standard Recommendations in UTS #18. Instead, they match Java functions according to their API documentation.

The C/POSIX character classes are also available in UnicodeSet patterns, using patterns like [:graph:] or \p{graph}.

Note: There are several ICU whitespace functions. Comparison:

  • u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property; most of general categories "Z" (separators) + most whitespace ISO controls (including no-break spaces, but excluding IS1..IS4)
  • u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
  • u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
  • u_isspace: Z + whitespace ISO controls (including no-break spaces)
  • u_isblank: "horizontal spaces" = TAB + Zs

Definition in file uchar.h.

Macro Definition Documentation

◆ U_GC_C_MASK

Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1

Definition at line 906 of file uchar.h.

◆ U_GC_CC_MASK

#define U_GC_CC_MASK   U_MASK(U_CONTROL_CHAR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 854 of file uchar.h.

◆ U_GC_CF_MASK

#define U_GC_CF_MASK   U_MASK(U_FORMAT_CHAR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 856 of file uchar.h.

◆ U_GC_CN_MASK

#define U_GC_CN_MASK   U_MASK(U_GENERAL_OTHER_TYPES)

U_GC_XX_MASK constants are bit flags corresponding to Unicode general category values. For each category, the nth bit is set if the numeric value of the corresponding UCharCategory constant is n.

There are also some U_GC_Y_MASK constants for groups of general categories like L for all letter categories.

See also
u_charType
U_GET_GC_MASK
UCharCategory @stable ICU 2.1

Definition at line 819 of file uchar.h.

◆ U_GC_CO_MASK

#define U_GC_CO_MASK   U_MASK(U_PRIVATE_USE_CHAR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 858 of file uchar.h.

◆ U_GC_CS_MASK

#define U_GC_CS_MASK   U_MASK(U_SURROGATE)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 860 of file uchar.h.

◆ U_GC_L_MASK

Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1

Definition at line 889 of file uchar.h.

◆ U_GC_LC_MASK

Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1

Definition at line 893 of file uchar.h.

◆ U_GC_LL_MASK

#define U_GC_LL_MASK   U_MASK(U_LOWERCASE_LETTER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 824 of file uchar.h.

◆ U_GC_LM_MASK

#define U_GC_LM_MASK   U_MASK(U_MODIFIER_LETTER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 828 of file uchar.h.

◆ U_GC_LO_MASK

#define U_GC_LO_MASK   U_MASK(U_OTHER_LETTER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 830 of file uchar.h.

◆ U_GC_LT_MASK

#define U_GC_LT_MASK   U_MASK(U_TITLECASE_LETTER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 826 of file uchar.h.

◆ U_GC_LU_MASK

#define U_GC_LU_MASK   U_MASK(U_UPPERCASE_LETTER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 822 of file uchar.h.

◆ U_GC_M_MASK

Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1

Definition at line 897 of file uchar.h.

◆ U_GC_MC_MASK

#define U_GC_MC_MASK   U_MASK(U_COMBINING_SPACING_MARK)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 837 of file uchar.h.

◆ U_GC_ME_MASK

#define U_GC_ME_MASK   U_MASK(U_ENCLOSING_MARK)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 835 of file uchar.h.

◆ U_GC_MN_MASK

#define U_GC_MN_MASK   U_MASK(U_NON_SPACING_MARK)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 833 of file uchar.h.

◆ U_GC_N_MASK

Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1

Definition at line 900 of file uchar.h.

◆ U_GC_ND_MASK

#define U_GC_ND_MASK   U_MASK(U_DECIMAL_DIGIT_NUMBER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 840 of file uchar.h.

◆ U_GC_NL_MASK

#define U_GC_NL_MASK   U_MASK(U_LETTER_NUMBER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 842 of file uchar.h.

◆ U_GC_NO_MASK

#define U_GC_NO_MASK   U_MASK(U_OTHER_NUMBER)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 844 of file uchar.h.

◆ U_GC_P_MASK

#define U_GC_P_MASK
Value:
U_GC_PI_MASK|U_GC_PF_MASK)
#define U_GC_PS_MASK
Definition: uchar.h:865
#define U_GC_PE_MASK
Definition: uchar.h:867
#define U_GC_PO_MASK
Definition: uchar.h:871
#define U_GC_PC_MASK
Definition: uchar.h:869
#define U_GC_PD_MASK
Definition: uchar.h:863
#define U_GC_PF_MASK
Definition: uchar.h:885

Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1

Definition at line 910 of file uchar.h.

◆ U_GC_PC_MASK

#define U_GC_PC_MASK   U_MASK(U_CONNECTOR_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 869 of file uchar.h.

◆ U_GC_PD_MASK

#define U_GC_PD_MASK   U_MASK(U_DASH_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 863 of file uchar.h.

◆ U_GC_PE_MASK

#define U_GC_PE_MASK   U_MASK(U_END_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 867 of file uchar.h.

◆ U_GC_PF_MASK

#define U_GC_PF_MASK   U_MASK(U_FINAL_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 885 of file uchar.h.

◆ U_GC_PI_MASK

#define U_GC_PI_MASK   U_MASK(U_INITIAL_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 883 of file uchar.h.

◆ U_GC_PO_MASK

#define U_GC_PO_MASK   U_MASK(U_OTHER_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 871 of file uchar.h.

◆ U_GC_PS_MASK

#define U_GC_PS_MASK   U_MASK(U_START_PUNCTUATION)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 865 of file uchar.h.

◆ U_GC_S_MASK

Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1

Definition at line 915 of file uchar.h.

◆ U_GC_SC_MASK

#define U_GC_SC_MASK   U_MASK(U_CURRENCY_SYMBOL)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 876 of file uchar.h.

◆ U_GC_SK_MASK

#define U_GC_SK_MASK   U_MASK(U_MODIFIER_SYMBOL)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 878 of file uchar.h.

◆ U_GC_SM_MASK

#define U_GC_SM_MASK   U_MASK(U_MATH_SYMBOL)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 874 of file uchar.h.

◆ U_GC_SO_MASK

#define U_GC_SO_MASK   U_MASK(U_OTHER_SYMBOL)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 880 of file uchar.h.

◆ U_GC_Z_MASK

Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1

Definition at line 903 of file uchar.h.

◆ U_GC_ZL_MASK

#define U_GC_ZL_MASK   U_MASK(U_LINE_SEPARATOR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 849 of file uchar.h.

◆ U_GC_ZP_MASK

#define U_GC_ZP_MASK   U_MASK(U_PARAGRAPH_SEPARATOR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 851 of file uchar.h.

◆ U_GC_ZS_MASK

#define U_GC_ZS_MASK   U_MASK(U_SPACE_SEPARATOR)

Mask constant for a UCharCategory. @stable ICU 2.1

Definition at line 847 of file uchar.h.

◆ U_GET_GC_MASK

#define U_GET_GC_MASK (   c)    U_MASK(u_charType(c))

Get a single-bit bit set for the general category of a character. This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc. Same as U_MASK(u_charType(c)).

Parameters
cthe code point to be tested
Returns
a single-bit mask corresponding to the general category (UCharCategory) value
See also
u_charType
UCharCategory
U_GC_CN_MASK @stable ICU 2.1

Definition at line 3337 of file uchar.h.

◆ U_MASK

#define U_MASK (   x)    ((uint32_t)1<<(x))

Get a single-bit bit set (a flag) from a bit number 0..31. @stable ICU 2.1

Definition at line 173 of file uchar.h.

◆ U_NO_NUMERIC_VALUE

#define U_NO_NUMERIC_VALUE   ((double)-123456789.)

Special value that is returned by u_getNumericValue when no numeric value is defined for a code point.

See also
u_getNumericValue @stable ICU 2.2

Definition at line 2827 of file uchar.h.

◆ U_UNICODE_VERSION

#define U_UNICODE_VERSION   "13.0"

Unicode version number, default for the current ICU version. The actual Unicode Character Database (UCD) data is stored in uprops.dat and may be generated from UCD files from a different Unicode version. Call u_getUnicodeVersion to get the actual Unicode version of the data.

See also
u_getUnicodeVersion @stable ICU 2.0

Definition at line 63 of file uchar.h.

◆ UCHAR_MAX_VALUE

#define UCHAR_MAX_VALUE   0x10ffff

The highest Unicode code point value (scalar value) according to The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up). For a single character, UChar32 is a simple type that can hold any code point value.

See also
UChar32 @stable ICU 2.0

Definition at line 167 of file uchar.h.

◆ UCHAR_MIN_VALUE

#define UCHAR_MIN_VALUE   0

Constants. The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0

Definition at line 157 of file uchar.h.

◆ USET_DEFINED

#define USET_DEFINED

Definition at line 34 of file uchar.h.

Typedef Documentation

◆ UBidiPairedBracketType

Bidi Paired Bracket Type constants.

See also
UCHAR_BIDI_PAIRED_BRACKET_TYPE @stable ICU 52

◆ UBlockCode

typedef enum UBlockCode UBlockCode

@stable ICU 2.0

Definition at line 1 of file uchar.h.

◆ UCharCategory

Data for enumerated Unicode general category types. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . @stable ICU 2.0

◆ UCharDirection

This specifies the language directional property of a character set. @stable ICU 2.0

◆ UCharEnumTypeRange

typedef UBool UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type)

Callback from u_enumCharTypes(), is called for each contiguous range of code points c (where start<=c<limit) with the same Unicode general category ("character type").

The callback function can stop the enumeration by returning false.

Parameters
contextan opaque pointer, as passed into utrie_enum()
startthe first code point in a contiguous range with value
limitone past the last code point in a contiguous range with value
typethe general category for all code points in [start..limit[
Returns
false to stop the enumeration

@stable ICU 2.1

See also
UCharCategory
u_enumCharTypes

Definition at line 3357 of file uchar.h.

◆ UCharNameChoice

Selector constants for u_charName(). u_charName() returns the "modern" name of a Unicode character; or the name that was defined in Unicode version 1.0, before the Unicode standard merged with ISO-10646; or an "extended" name that gives each Unicode code point a unique name.

See also
u_charName @stable ICU 2.0

◆ UDecompositionType

Decomposition Type constants.

See also
UCHAR_DECOMPOSITION_TYPE @stable ICU 2.2

◆ UEastAsianWidth

East Asian Width constants.

See also
UCHAR_EAST_ASIAN_WIDTH
u_getIntPropertyValue @stable ICU 2.2

◆ UEnumCharNamesFn

typedef UBool UEnumCharNamesFn(void *context, UChar32 code, UCharNameChoice nameChoice, const char *name, int32_t length)

Type of a callback function for u_enumCharNames() that gets called for each Unicode character with the code point value and the character name. If such a function returns false, then the enumeration is stopped.

Parameters
contextThe context pointer that was passed to u_enumCharNames().
codeThe Unicode code point for the character with this name.
nameChoiceSelector for which kind of names is enumerated.
nameThe character's name, zero-terminated.
lengthThe length of the name.
Returns
true if the enumeration should continue, false to stop it.
See also
UCharNameChoice
u_enumCharNames @stable ICU 1.7

Definition at line 3537 of file uchar.h.

◆ UGraphemeClusterBreak

Grapheme Cluster Break constants.

See also
UCHAR_GRAPHEME_CLUSTER_BREAK @stable ICU 3.4

◆ UHangulSyllableType

Hangul Syllable Type constants.

See also
UCHAR_HANGUL_SYLLABLE_TYPE @stable ICU 2.6

◆ UIndicPositionalCategory

Indic Positional Category constants.

See also
UCHAR_INDIC_POSITIONAL_CATEGORY @stable ICU 63

◆ UIndicSyllabicCategory

Indic Syllabic Category constants.

See also
UCHAR_INDIC_SYLLABIC_CATEGORY @stable ICU 63

◆ UJoiningGroup

Joining Group constants.

See also
UCHAR_JOINING_GROUP @stable ICU 2.2

◆ UJoiningType

typedef enum UJoiningType UJoiningType

Joining Type constants.

See also
UCHAR_JOINING_TYPE @stable ICU 2.2

◆ ULineBreak

typedef enum ULineBreak ULineBreak

Line Break constants.

See also
UCHAR_LINE_BREAK @stable ICU 2.2

◆ UNumericType

typedef enum UNumericType UNumericType

Numeric Type constants.

See also
UCHAR_NUMERIC_TYPE @stable ICU 2.2

◆ UProperty

typedef enum UProperty UProperty

Selection constants for Unicode properties. These constants are used in functions like u_hasBinaryProperty to select one of the Unicode properties.

The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).

For details about the properties see UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).

Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available. Check u_getUnicodeVersion to be sure.

See also
u_hasBinaryProperty
u_getIntPropertyValue
u_getUnicodeVersion @stable ICU 2.1

◆ UPropertyNameChoice

Selector constants for u_getPropertyName() and u_getPropertyValueName(). These selectors are used to choose which name is returned for a given property or value. All properties and values have a long name. Most have a short name, but some do not. Unicode allows for additional names, beyond the long and short name, which would be indicated by U_LONG_PROPERTY_NAME + i, where i=1, 2,...

See also
u_getPropertyName()
u_getPropertyValueName() @stable ICU 2.4

◆ USentenceBreak

Sentence Break constants.

See also
UCHAR_SENTENCE_BREAK @stable ICU 3.4

◆ USet

typedef struct USet USet

USet is the C API type corresponding to C++ class UnicodeSet. It is forward-declared here to avoid including unicode/uset.h file if related APIs are not used.

See also
ucnv_getUnicodeSet @stable ICU 2.4

Definition at line 1 of file uchar.h.

◆ UVerticalOrientation

Vertical Orientation constants.

See also
UCHAR_VERTICAL_ORIENTATION @stable ICU 63

◆ UWordBreakValues

Word Break constants. (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)

See also
UCHAR_WORD_BREAK @stable ICU 3.4

Enumeration Type Documentation

◆ UBidiPairedBracketType

Bidi Paired Bracket Type constants.

See also
UCHAR_BIDI_PAIRED_BRACKET_TYPE @stable ICU 52
Enumerator
U_BPT_NONE 

Not a paired bracket. @stable ICU 52

U_BPT_OPEN 

Open paired bracket. @stable ICU 52

U_BPT_CLOSE 

Close paired bracket. @stable ICU 52

U_BPT_COUNT 

One more than the highest normal UBidiPairedBracketType value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_PAIRED_BRACKET_TYPE).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 992 of file uchar.h.

◆ UBlockCode

enum UBlockCode

Constants for Unicode blocks, see the Unicode Data file Blocks.txt @stable ICU 2.0

Enumerator
UBLOCK_NO_BLOCK 

New No_Block value in Unicode 4. @stable ICU 2.6

UBLOCK_BASIC_LATIN 

@stable ICU 2.0

UBLOCK_LATIN_1_SUPPLEMENT 

@stable ICU 2.0

UBLOCK_LATIN_EXTENDED_A 

@stable ICU 2.0

UBLOCK_LATIN_EXTENDED_B 

@stable ICU 2.0

UBLOCK_IPA_EXTENSIONS 

@stable ICU 2.0

UBLOCK_SPACING_MODIFIER_LETTERS 

@stable ICU 2.0

UBLOCK_COMBINING_DIACRITICAL_MARKS 

@stable ICU 2.0

UBLOCK_GREEK 

Unicode 3.2 renames this block to "Greek and Coptic". @stable ICU 2.0

UBLOCK_CYRILLIC 

@stable ICU 2.0

UBLOCK_ARMENIAN 

@stable ICU 2.0

UBLOCK_HEBREW 

@stable ICU 2.0

UBLOCK_ARABIC 

@stable ICU 2.0

UBLOCK_SYRIAC 

@stable ICU 2.0

UBLOCK_THAANA 

@stable ICU 2.0

UBLOCK_DEVANAGARI 

@stable ICU 2.0

UBLOCK_BENGALI 

@stable ICU 2.0

UBLOCK_GURMUKHI 

@stable ICU 2.0

UBLOCK_GUJARATI 

@stable ICU 2.0

UBLOCK_ORIYA 

@stable ICU 2.0

UBLOCK_TAMIL 

@stable ICU 2.0

UBLOCK_TELUGU 

@stable ICU 2.0

UBLOCK_KANNADA 

@stable ICU 2.0

UBLOCK_MALAYALAM 

@stable ICU 2.0

UBLOCK_SINHALA 

@stable ICU 2.0

UBLOCK_THAI 

@stable ICU 2.0

UBLOCK_LAO 

@stable ICU 2.0

UBLOCK_TIBETAN 

@stable ICU 2.0

UBLOCK_MYANMAR 

@stable ICU 2.0

UBLOCK_GEORGIAN 

@stable ICU 2.0

UBLOCK_HANGUL_JAMO 

@stable ICU 2.0

UBLOCK_ETHIOPIC 

@stable ICU 2.0

UBLOCK_CHEROKEE 

@stable ICU 2.0

UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS 

@stable ICU 2.0

UBLOCK_OGHAM 

@stable ICU 2.0

UBLOCK_RUNIC 

@stable ICU 2.0

UBLOCK_KHMER 

@stable ICU 2.0

UBLOCK_MONGOLIAN 

@stable ICU 2.0

UBLOCK_LATIN_EXTENDED_ADDITIONAL 

@stable ICU 2.0

UBLOCK_GREEK_EXTENDED 

@stable ICU 2.0

UBLOCK_GENERAL_PUNCTUATION 

@stable ICU 2.0

UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS 

@stable ICU 2.0

UBLOCK_CURRENCY_SYMBOLS 

@stable ICU 2.0

UBLOCK_COMBINING_MARKS_FOR_SYMBOLS 

Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols". @stable ICU 2.0

UBLOCK_LETTERLIKE_SYMBOLS 

@stable ICU 2.0

UBLOCK_NUMBER_FORMS 

@stable ICU 2.0

UBLOCK_ARROWS 

@stable ICU 2.0

UBLOCK_MATHEMATICAL_OPERATORS 

@stable ICU 2.0

UBLOCK_MISCELLANEOUS_TECHNICAL 

@stable ICU 2.0

UBLOCK_CONTROL_PICTURES 

@stable ICU 2.0

UBLOCK_OPTICAL_CHARACTER_RECOGNITION 

@stable ICU 2.0

UBLOCK_ENCLOSED_ALPHANUMERICS 

@stable ICU 2.0

UBLOCK_BOX_DRAWING 

@stable ICU 2.0

UBLOCK_BLOCK_ELEMENTS 

@stable ICU 2.0

UBLOCK_GEOMETRIC_SHAPES 

@stable ICU 2.0

UBLOCK_MISCELLANEOUS_SYMBOLS 

@stable ICU 2.0

UBLOCK_DINGBATS 

@stable ICU 2.0

UBLOCK_BRAILLE_PATTERNS 

@stable ICU 2.0

UBLOCK_CJK_RADICALS_SUPPLEMENT 

@stable ICU 2.0

UBLOCK_KANGXI_RADICALS 

@stable ICU 2.0

UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS 

@stable ICU 2.0

UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION 

@stable ICU 2.0

UBLOCK_HIRAGANA 

@stable ICU 2.0

UBLOCK_KATAKANA 

@stable ICU 2.0

UBLOCK_BOPOMOFO 

@stable ICU 2.0

UBLOCK_HANGUL_COMPATIBILITY_JAMO 

@stable ICU 2.0

UBLOCK_KANBUN 

@stable ICU 2.0

UBLOCK_BOPOMOFO_EXTENDED 

@stable ICU 2.0

UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS 

@stable ICU 2.0

UBLOCK_CJK_COMPATIBILITY 

@stable ICU 2.0

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A 

@stable ICU 2.0

UBLOCK_CJK_UNIFIED_IDEOGRAPHS 

@stable ICU 2.0

UBLOCK_YI_SYLLABLES 

@stable ICU 2.0

UBLOCK_YI_RADICALS 

@stable ICU 2.0

UBLOCK_HANGUL_SYLLABLES 

@stable ICU 2.0

UBLOCK_HIGH_SURROGATES 

@stable ICU 2.0

UBLOCK_HIGH_PRIVATE_USE_SURROGATES 

@stable ICU 2.0

UBLOCK_LOW_SURROGATES 

@stable ICU 2.0

UBLOCK_PRIVATE_USE_AREA 

Same as UBLOCK_PRIVATE_USE. Until Unicode 3.1.1, the corresponding block name was "Private Use", and multiple code point ranges had this block. Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and adds separate blocks for the supplementary PUAs.

@stable ICU 2.0

UBLOCK_PRIVATE_USE 

Same as UBLOCK_PRIVATE_USE_AREA. Until Unicode 3.1.1, the corresponding block name was "Private Use", and multiple code point ranges had this block. Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and adds separate blocks for the supplementary PUAs.

@stable ICU 2.0

UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS 

@stable ICU 2.0

UBLOCK_ALPHABETIC_PRESENTATION_FORMS 

@stable ICU 2.0

UBLOCK_ARABIC_PRESENTATION_FORMS_A 

@stable ICU 2.0

UBLOCK_COMBINING_HALF_MARKS 

@stable ICU 2.0

UBLOCK_CJK_COMPATIBILITY_FORMS 

@stable ICU 2.0

UBLOCK_SMALL_FORM_VARIANTS 

@stable ICU 2.0

UBLOCK_ARABIC_PRESENTATION_FORMS_B 

@stable ICU 2.0

UBLOCK_SPECIALS 

@stable ICU 2.0

UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS 

@stable ICU 2.0

UBLOCK_OLD_ITALIC 

@stable ICU 2.0

UBLOCK_GOTHIC 

@stable ICU 2.0

UBLOCK_DESERET 

@stable ICU 2.0

UBLOCK_BYZANTINE_MUSICAL_SYMBOLS 

@stable ICU 2.0

UBLOCK_MUSICAL_SYMBOLS 

@stable ICU 2.0

UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS 

@stable ICU 2.0

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B 

@stable ICU 2.0

UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT 

@stable ICU 2.0

UBLOCK_TAGS 

@stable ICU 2.0

UBLOCK_CYRILLIC_SUPPLEMENT 

@stable ICU 3.0

UBLOCK_CYRILLIC_SUPPLEMENTARY 

Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement". @stable ICU 2.2

UBLOCK_TAGALOG 

@stable ICU 2.2

UBLOCK_HANUNOO 

@stable ICU 2.2

UBLOCK_BUHID 

@stable ICU 2.2

UBLOCK_TAGBANWA 

@stable ICU 2.2

UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A 

@stable ICU 2.2

UBLOCK_SUPPLEMENTAL_ARROWS_A 

@stable ICU 2.2

UBLOCK_SUPPLEMENTAL_ARROWS_B 

@stable ICU 2.2

UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B 

@stable ICU 2.2

UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS 

@stable ICU 2.2

UBLOCK_KATAKANA_PHONETIC_EXTENSIONS 

@stable ICU 2.2

UBLOCK_VARIATION_SELECTORS 

@stable ICU 2.2

UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A 

@stable ICU 2.2

UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B 

@stable ICU 2.2

UBLOCK_LIMBU 

@stable ICU 2.6

UBLOCK_TAI_LE 

@stable ICU 2.6

UBLOCK_KHMER_SYMBOLS 

@stable ICU 2.6

UBLOCK_PHONETIC_EXTENSIONS 

@stable ICU 2.6

UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS 

@stable ICU 2.6

UBLOCK_YIJING_HEXAGRAM_SYMBOLS 

@stable ICU 2.6

UBLOCK_LINEAR_B_SYLLABARY 

@stable ICU 2.6

UBLOCK_LINEAR_B_IDEOGRAMS 

@stable ICU 2.6

UBLOCK_AEGEAN_NUMBERS 

@stable ICU 2.6

UBLOCK_UGARITIC 

@stable ICU 2.6

UBLOCK_SHAVIAN 

@stable ICU 2.6

UBLOCK_OSMANYA 

@stable ICU 2.6

UBLOCK_CYPRIOT_SYLLABARY 

@stable ICU 2.6

UBLOCK_TAI_XUAN_JING_SYMBOLS 

@stable ICU 2.6

UBLOCK_VARIATION_SELECTORS_SUPPLEMENT 

@stable ICU 2.6

UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION 

@stable ICU 3.4

UBLOCK_ANCIENT_GREEK_NUMBERS 

@stable ICU 3.4

UBLOCK_ARABIC_SUPPLEMENT 

@stable ICU 3.4

UBLOCK_BUGINESE 

@stable ICU 3.4

UBLOCK_CJK_STROKES 

@stable ICU 3.4

UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT 

@stable ICU 3.4

UBLOCK_COPTIC 

@stable ICU 3.4

UBLOCK_ETHIOPIC_EXTENDED 

@stable ICU 3.4

UBLOCK_ETHIOPIC_SUPPLEMENT 

@stable ICU 3.4

UBLOCK_GEORGIAN_SUPPLEMENT 

@stable ICU 3.4

UBLOCK_GLAGOLITIC 

@stable ICU 3.4

UBLOCK_KHAROSHTHI 

@stable ICU 3.4

UBLOCK_MODIFIER_TONE_LETTERS 

@stable ICU 3.4

UBLOCK_NEW_TAI_LUE 

@stable ICU 3.4

UBLOCK_OLD_PERSIAN 

@stable ICU 3.4

UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT 

@stable ICU 3.4

UBLOCK_SUPPLEMENTAL_PUNCTUATION 

@stable ICU 3.4

UBLOCK_SYLOTI_NAGRI 

@stable ICU 3.4

UBLOCK_TIFINAGH 

@stable ICU 3.4

UBLOCK_VERTICAL_FORMS 

@stable ICU 3.4

UBLOCK_NKO 

@stable ICU 3.6

UBLOCK_BALINESE 

@stable ICU 3.6

UBLOCK_LATIN_EXTENDED_C 

@stable ICU 3.6

UBLOCK_LATIN_EXTENDED_D 

@stable ICU 3.6

UBLOCK_PHAGS_PA 

@stable ICU 3.6

UBLOCK_PHOENICIAN 

@stable ICU 3.6

UBLOCK_CUNEIFORM 

@stable ICU 3.6

UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION 

@stable ICU 3.6

UBLOCK_COUNTING_ROD_NUMERALS 

@stable ICU 3.6

UBLOCK_SUNDANESE 

@stable ICU 4.0

UBLOCK_LEPCHA 

@stable ICU 4.0

UBLOCK_OL_CHIKI 

@stable ICU 4.0

UBLOCK_CYRILLIC_EXTENDED_A 

@stable ICU 4.0

UBLOCK_VAI 

@stable ICU 4.0

UBLOCK_CYRILLIC_EXTENDED_B 

@stable ICU 4.0

UBLOCK_SAURASHTRA 

@stable ICU 4.0

UBLOCK_KAYAH_LI 

@stable ICU 4.0

UBLOCK_REJANG 

@stable ICU 4.0

UBLOCK_CHAM 

@stable ICU 4.0

UBLOCK_ANCIENT_SYMBOLS 

@stable ICU 4.0

UBLOCK_PHAISTOS_DISC 

@stable ICU 4.0

UBLOCK_LYCIAN 

@stable ICU 4.0

UBLOCK_CARIAN 

@stable ICU 4.0

UBLOCK_LYDIAN 

@stable ICU 4.0

UBLOCK_MAHJONG_TILES 

@stable ICU 4.0

UBLOCK_DOMINO_TILES 

@stable ICU 4.0

UBLOCK_SAMARITAN 

@stable ICU 4.4

UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED 

@stable ICU 4.4

UBLOCK_TAI_THAM 

@stable ICU 4.4

UBLOCK_VEDIC_EXTENSIONS 

@stable ICU 4.4

UBLOCK_LISU 

@stable ICU 4.4

UBLOCK_BAMUM 

@stable ICU 4.4

UBLOCK_COMMON_INDIC_NUMBER_FORMS 

@stable ICU 4.4

UBLOCK_DEVANAGARI_EXTENDED 

@stable ICU 4.4

UBLOCK_HANGUL_JAMO_EXTENDED_A 

@stable ICU 4.4

UBLOCK_JAVANESE 

@stable ICU 4.4

UBLOCK_MYANMAR_EXTENDED_A 

@stable ICU 4.4

UBLOCK_TAI_VIET 

@stable ICU 4.4

UBLOCK_MEETEI_MAYEK 

@stable ICU 4.4

UBLOCK_HANGUL_JAMO_EXTENDED_B 

@stable ICU 4.4

UBLOCK_IMPERIAL_ARAMAIC 

@stable ICU 4.4

UBLOCK_OLD_SOUTH_ARABIAN 

@stable ICU 4.4

UBLOCK_AVESTAN 

@stable ICU 4.4

UBLOCK_INSCRIPTIONAL_PARTHIAN 

@stable ICU 4.4

UBLOCK_INSCRIPTIONAL_PAHLAVI 

@stable ICU 4.4

UBLOCK_OLD_TURKIC 

@stable ICU 4.4

UBLOCK_RUMI_NUMERAL_SYMBOLS 

@stable ICU 4.4

UBLOCK_KAITHI 

@stable ICU 4.4

UBLOCK_EGYPTIAN_HIEROGLYPHS 

@stable ICU 4.4

UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT 

@stable ICU 4.4

UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT 

@stable ICU 4.4

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C 

@stable ICU 4.4

UBLOCK_MANDAIC 

@stable ICU 4.6

UBLOCK_BATAK 

@stable ICU 4.6

UBLOCK_ETHIOPIC_EXTENDED_A 

@stable ICU 4.6

UBLOCK_BRAHMI 

@stable ICU 4.6

UBLOCK_BAMUM_SUPPLEMENT 

@stable ICU 4.6

UBLOCK_KANA_SUPPLEMENT 

@stable ICU 4.6

UBLOCK_PLAYING_CARDS 

@stable ICU 4.6

UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS 

@stable ICU 4.6

UBLOCK_EMOTICONS 

@stable ICU 4.6

UBLOCK_TRANSPORT_AND_MAP_SYMBOLS 

@stable ICU 4.6

UBLOCK_ALCHEMICAL_SYMBOLS 

@stable ICU 4.6

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D 

@stable ICU 4.6

UBLOCK_ARABIC_EXTENDED_A 

@stable ICU 49

UBLOCK_ARABIC_MATHEMATICAL_ALPHABETIC_SYMBOLS 

@stable ICU 49

UBLOCK_CHAKMA 

@stable ICU 49

UBLOCK_MEETEI_MAYEK_EXTENSIONS 

@stable ICU 49

UBLOCK_MEROITIC_CURSIVE 

@stable ICU 49

UBLOCK_MEROITIC_HIEROGLYPHS 

@stable ICU 49

UBLOCK_MIAO 

@stable ICU 49

UBLOCK_SHARADA 

@stable ICU 49

UBLOCK_SORA_SOMPENG 

@stable ICU 49

UBLOCK_SUNDANESE_SUPPLEMENT 

@stable ICU 49

UBLOCK_TAKRI 

@stable ICU 49

UBLOCK_BASSA_VAH 

@stable ICU 54

UBLOCK_CAUCASIAN_ALBANIAN 

@stable ICU 54

UBLOCK_COPTIC_EPACT_NUMBERS 

@stable ICU 54

UBLOCK_COMBINING_DIACRITICAL_MARKS_EXTENDED 

@stable ICU 54

UBLOCK_DUPLOYAN 

@stable ICU 54

UBLOCK_ELBASAN 

@stable ICU 54

UBLOCK_GEOMETRIC_SHAPES_EXTENDED 

@stable ICU 54

UBLOCK_GRANTHA 

@stable ICU 54

UBLOCK_KHOJKI 

@stable ICU 54

UBLOCK_KHUDAWADI 

@stable ICU 54

UBLOCK_LATIN_EXTENDED_E 

@stable ICU 54

UBLOCK_LINEAR_A 

@stable ICU 54

UBLOCK_MAHAJANI 

@stable ICU 54

UBLOCK_MANICHAEAN 

@stable ICU 54

UBLOCK_MENDE_KIKAKUI 

@stable ICU 54

UBLOCK_MODI 

@stable ICU 54

UBLOCK_MRO 

@stable ICU 54

UBLOCK_MYANMAR_EXTENDED_B 

@stable ICU 54

UBLOCK_NABATAEAN 

@stable ICU 54

UBLOCK_OLD_NORTH_ARABIAN 

@stable ICU 54

UBLOCK_OLD_PERMIC 

@stable ICU 54

UBLOCK_ORNAMENTAL_DINGBATS 

@stable ICU 54

UBLOCK_PAHAWH_HMONG 

@stable ICU 54

UBLOCK_PALMYRENE 

@stable ICU 54

UBLOCK_PAU_CIN_HAU 

@stable ICU 54

UBLOCK_PSALTER_PAHLAVI 

@stable ICU 54

UBLOCK_SHORTHAND_FORMAT_CONTROLS 

@stable ICU 54

UBLOCK_SIDDHAM 

@stable ICU 54

UBLOCK_SINHALA_ARCHAIC_NUMBERS 

@stable ICU 54

UBLOCK_SUPPLEMENTAL_ARROWS_C 

@stable ICU 54

UBLOCK_TIRHUTA 

@stable ICU 54

UBLOCK_WARANG_CITI 

@stable ICU 54

UBLOCK_AHOM 

@stable ICU 56

UBLOCK_ANATOLIAN_HIEROGLYPHS 

@stable ICU 56

UBLOCK_CHEROKEE_SUPPLEMENT 

@stable ICU 56

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E 

@stable ICU 56

UBLOCK_EARLY_DYNASTIC_CUNEIFORM 

@stable ICU 56

UBLOCK_HATRAN 

@stable ICU 56

UBLOCK_MULTANI 

@stable ICU 56

UBLOCK_OLD_HUNGARIAN 

@stable ICU 56

UBLOCK_SUPPLEMENTAL_SYMBOLS_AND_PICTOGRAPHS 

@stable ICU 56

UBLOCK_SUTTON_SIGNWRITING 

@stable ICU 56

UBLOCK_ADLAM 

@stable ICU 58

UBLOCK_BHAIKSUKI 

@stable ICU 58

UBLOCK_CYRILLIC_EXTENDED_C 

@stable ICU 58

UBLOCK_GLAGOLITIC_SUPPLEMENT 

@stable ICU 58

UBLOCK_IDEOGRAPHIC_SYMBOLS_AND_PUNCTUATION 

@stable ICU 58

UBLOCK_MARCHEN 

@stable ICU 58

UBLOCK_MONGOLIAN_SUPPLEMENT 

@stable ICU 58

UBLOCK_NEWA 

@stable ICU 58

UBLOCK_OSAGE 

@stable ICU 58

UBLOCK_TANGUT 

@stable ICU 58

UBLOCK_TANGUT_COMPONENTS 

@stable ICU 58

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F 

@stable ICU 60

UBLOCK_KANA_EXTENDED_A 

@stable ICU 60

UBLOCK_MASARAM_GONDI 

@stable ICU 60

UBLOCK_NUSHU 

@stable ICU 60

UBLOCK_SOYOMBO 

@stable ICU 60

UBLOCK_SYRIAC_SUPPLEMENT 

@stable ICU 60

UBLOCK_ZANABAZAR_SQUARE 

@stable ICU 60

UBLOCK_CHESS_SYMBOLS 

@stable ICU 62

UBLOCK_DOGRA 

@stable ICU 62

UBLOCK_GEORGIAN_EXTENDED 

@stable ICU 62

UBLOCK_GUNJALA_GONDI 

@stable ICU 62

UBLOCK_HANIFI_ROHINGYA 

@stable ICU 62

UBLOCK_INDIC_SIYAQ_NUMBERS 

@stable ICU 62

UBLOCK_MAKASAR 

@stable ICU 62

UBLOCK_MAYAN_NUMERALS 

@stable ICU 62

UBLOCK_MEDEFAIDRIN 

@stable ICU 62

UBLOCK_OLD_SOGDIAN 

@stable ICU 62

UBLOCK_SOGDIAN 

@stable ICU 62

UBLOCK_EGYPTIAN_HIEROGLYPH_FORMAT_CONTROLS 

@stable ICU 64

UBLOCK_ELYMAIC 

@stable ICU 64

UBLOCK_NANDINAGARI 

@stable ICU 64

UBLOCK_NYIAKENG_PUACHUE_HMONG 

@stable ICU 64

UBLOCK_OTTOMAN_SIYAQ_NUMBERS 

@stable ICU 64

UBLOCK_SMALL_KANA_EXTENSION 

@stable ICU 64

UBLOCK_SYMBOLS_AND_PICTOGRAPHS_EXTENDED_A 

@stable ICU 64

UBLOCK_TAMIL_SUPPLEMENT 

@stable ICU 64

UBLOCK_WANCHO 

@stable ICU 64

UBLOCK_CHORASMIAN 

@stable ICU 66

UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_G 

@stable ICU 66

UBLOCK_DIVES_AKURU 

@stable ICU 66

UBLOCK_KHITAN_SMALL_SCRIPT 

@stable ICU 66

UBLOCK_LISU_SUPPLEMENT 

@stable ICU 66

UBLOCK_SYMBOLS_FOR_LEGACY_COMPUTING 

@stable ICU 66

UBLOCK_TANGUT_SUPPLEMENT 

@stable ICU 66

UBLOCK_YEZIDI 

@stable ICU 66

UBLOCK_COUNT 

One more than the highest normal UBlockCode value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_BLOCK).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UBLOCK_INVALID_CODE 

@stable ICU 2.0

Definition at line 1020 of file uchar.h.

◆ UCharCategory

Data for enumerated Unicode general category types. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . @stable ICU 2.0

Enumerator
U_UNASSIGNED 

Non-category for unassigned and non-character code points. @stable ICU 2.0

U_GENERAL_OTHER_TYPES 

Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0

U_UPPERCASE_LETTER 

Lu @stable ICU 2.0

U_LOWERCASE_LETTER 

Ll @stable ICU 2.0

U_TITLECASE_LETTER 

Lt @stable ICU 2.0

U_MODIFIER_LETTER 

Lm @stable ICU 2.0

U_OTHER_LETTER 

Lo @stable ICU 2.0

U_NON_SPACING_MARK 

Mn @stable ICU 2.0

U_ENCLOSING_MARK 

Me @stable ICU 2.0

U_COMBINING_SPACING_MARK 

Mc @stable ICU 2.0

U_DECIMAL_DIGIT_NUMBER 

Nd @stable ICU 2.0

U_LETTER_NUMBER 

Nl @stable ICU 2.0

U_OTHER_NUMBER 

No @stable ICU 2.0

U_SPACE_SEPARATOR 

Zs @stable ICU 2.0

U_LINE_SEPARATOR 

Zl @stable ICU 2.0

U_PARAGRAPH_SEPARATOR 

Zp @stable ICU 2.0

U_CONTROL_CHAR 

Cc @stable ICU 2.0

U_FORMAT_CHAR 

Cf @stable ICU 2.0

U_PRIVATE_USE_CHAR 

Co @stable ICU 2.0

U_SURROGATE 

Cs @stable ICU 2.0

U_DASH_PUNCTUATION 

Pd @stable ICU 2.0

U_START_PUNCTUATION 

Ps @stable ICU 2.0

U_END_PUNCTUATION 

Pe @stable ICU 2.0

U_CONNECTOR_PUNCTUATION 

Pc @stable ICU 2.0

U_OTHER_PUNCTUATION 

Po @stable ICU 2.0

U_MATH_SYMBOL 

Sm @stable ICU 2.0

U_CURRENCY_SYMBOL 

Sc @stable ICU 2.0

U_MODIFIER_SYMBOL 

Sk @stable ICU 2.0

U_OTHER_SYMBOL 

So @stable ICU 2.0

U_INITIAL_PUNCTUATION 

Pi @stable ICU 2.0

U_FINAL_PUNCTUATION 

Pf @stable ICU 2.0

U_CHAR_CATEGORY_COUNT 

One higher than the last enum UCharCategory constant. This numeric value is stable (will not change), see http://www.unicode.org/policies/stability_policy.html#Property_Value

@stable ICU 2.0

Definition at line 724 of file uchar.h.

◆ UCharDirection

This specifies the language directional property of a character set. @stable ICU 2.0

Enumerator
U_LEFT_TO_RIGHT 

L @stable ICU 2.0

U_RIGHT_TO_LEFT 

R @stable ICU 2.0

U_EUROPEAN_NUMBER 

EN @stable ICU 2.0

U_EUROPEAN_NUMBER_SEPARATOR 

ES @stable ICU 2.0

U_EUROPEAN_NUMBER_TERMINATOR 

ET @stable ICU 2.0

U_ARABIC_NUMBER 

AN @stable ICU 2.0

U_COMMON_NUMBER_SEPARATOR 

CS @stable ICU 2.0

U_BLOCK_SEPARATOR 

B @stable ICU 2.0

U_SEGMENT_SEPARATOR 

S @stable ICU 2.0

U_WHITE_SPACE_NEUTRAL 

WS @stable ICU 2.0

U_OTHER_NEUTRAL 

ON @stable ICU 2.0

U_LEFT_TO_RIGHT_EMBEDDING 

LRE @stable ICU 2.0

U_LEFT_TO_RIGHT_OVERRIDE 

LRO @stable ICU 2.0

U_RIGHT_TO_LEFT_ARABIC 

AL @stable ICU 2.0

U_RIGHT_TO_LEFT_EMBEDDING 

RLE @stable ICU 2.0

U_RIGHT_TO_LEFT_OVERRIDE 

RLO @stable ICU 2.0

U_POP_DIRECTIONAL_FORMAT 

PDF @stable ICU 2.0

U_DIR_NON_SPACING_MARK 

NSM @stable ICU 2.0

U_BOUNDARY_NEUTRAL 

BN @stable ICU 2.0

U_FIRST_STRONG_ISOLATE 

FSI @stable ICU 52

U_LEFT_TO_RIGHT_ISOLATE 

LRI @stable ICU 52

U_RIGHT_TO_LEFT_ISOLATE 

RLI @stable ICU 52

U_POP_DIRECTIONAL_ISOLATE 

PDI @stable ICU 52

U_CHAR_DIRECTION_COUNT 

One more than the highest UCharDirection value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_BIDI_CLASS).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 921 of file uchar.h.

◆ UCharNameChoice

Selector constants for u_charName(). u_charName() returns the "modern" name of a Unicode character; or the name that was defined in Unicode version 1.0, before the Unicode standard merged with ISO-10646; or an "extended" name that gives each Unicode code point a unique name.

See also
u_charName @stable ICU 2.0
Enumerator
U_UNICODE_CHAR_NAME 

Unicode character name (Name property). @stable ICU 2.0

U_UNICODE_10_CHAR_NAME 

The Unicode_1_Name property value which is of little practical value. Beginning with ICU 49, ICU APIs return an empty string for this name choice.

Deprecated:
ICU 49
U_EXTENDED_CHAR_NAME 

Standard or synthetic character name. @stable ICU 2.0

U_CHAR_NAME_ALIAS 

Corrected name from NameAliases.txt. @stable ICU 4.4

U_CHAR_NAME_CHOICE_COUNT 

One more than the highest normal UCharNameChoice value.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1869 of file uchar.h.

◆ UDecompositionType

Decomposition Type constants.

See also
UCHAR_DECOMPOSITION_TYPE @stable ICU 2.2
Enumerator
U_DT_NONE 
U_DT_CANONICAL 
U_DT_COMPAT 
U_DT_CIRCLE 
U_DT_FINAL 
U_DT_FONT 
U_DT_FRACTION 
U_DT_INITIAL 
U_DT_ISOLATED 
U_DT_MEDIAL 
U_DT_NARROW 
U_DT_NOBREAK 
U_DT_SMALL 
U_DT_SQUARE 
U_DT_SUB 
U_DT_SUPER 
U_DT_VERTICAL 
U_DT_WIDE 
U_DT_COUNT 

One more than the highest normal UDecompositionType value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_DECOMPOSITION_TYPE).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1924 of file uchar.h.

◆ UEastAsianWidth

East Asian Width constants.

See also
UCHAR_EAST_ASIAN_WIDTH
u_getIntPropertyValue @stable ICU 2.2
Enumerator
U_EA_NEUTRAL 
U_EA_AMBIGUOUS 
U_EA_HALFWIDTH 
U_EA_FULLWIDTH 
U_EA_NARROW 
U_EA_WIDE 
U_EA_COUNT 

One more than the highest normal UEastAsianWidth value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_EAST_ASIAN_WIDTH).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1834 of file uchar.h.

◆ UGraphemeClusterBreak

Grapheme Cluster Break constants.

See also
UCHAR_GRAPHEME_CLUSTER_BREAK @stable ICU 3.4
Enumerator
U_GCB_OTHER 
U_GCB_CONTROL 
U_GCB_CR 
U_GCB_EXTEND 
U_GCB_L 
U_GCB_LF 
U_GCB_LV 
U_GCB_LVT 
U_GCB_T 
U_GCB_V 
U_GCB_SPACING_MARK 

@stable ICU 4.0

U_GCB_PREPEND 

@stable ICU 4.0

U_GCB_REGIONAL_INDICATOR 

@stable ICU 50

U_GCB_E_BASE 

@stable ICU 58

U_GCB_E_BASE_GAZ 

@stable ICU 58

U_GCB_E_MODIFIER 

@stable ICU 58

U_GCB_GLUE_AFTER_ZWJ 

@stable ICU 58

U_GCB_ZWJ 

@stable ICU 58

U_GCB_COUNT 

One more than the highest normal UGraphemeClusterBreak value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_GRAPHEME_CLUSTER_BREAK).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2126 of file uchar.h.

◆ UHangulSyllableType

Hangul Syllable Type constants.

See also
UCHAR_HANGUL_SYLLABLE_TYPE @stable ICU 2.6
Enumerator
U_HST_NOT_APPLICABLE 
U_HST_LEADING_JAMO 
U_HST_VOWEL_JAMO 
U_HST_TRAILING_JAMO 
U_HST_LV_SYLLABLE 
U_HST_LVT_SYLLABLE 
U_HST_COUNT 

One more than the highest normal UHangulSyllableType value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_HANGUL_SYLLABLE_TYPE).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2391 of file uchar.h.

◆ UIndicPositionalCategory

Indic Positional Category constants.

See also
UCHAR_INDIC_POSITIONAL_CATEGORY @stable ICU 63
Enumerator
U_INPC_NA 

@stable ICU 63

U_INPC_BOTTOM 

@stable ICU 63

U_INPC_BOTTOM_AND_LEFT 

@stable ICU 63

U_INPC_BOTTOM_AND_RIGHT 

@stable ICU 63

U_INPC_LEFT 

@stable ICU 63

U_INPC_LEFT_AND_RIGHT 

@stable ICU 63

U_INPC_OVERSTRUCK 

@stable ICU 63

U_INPC_RIGHT 

@stable ICU 63

U_INPC_TOP 

@stable ICU 63

U_INPC_TOP_AND_BOTTOM 

@stable ICU 63

U_INPC_TOP_AND_BOTTOM_AND_RIGHT 

@stable ICU 63

U_INPC_TOP_AND_LEFT 

@stable ICU 63

U_INPC_TOP_AND_LEFT_AND_RIGHT 

@stable ICU 63

U_INPC_TOP_AND_RIGHT 

@stable ICU 63

U_INPC_VISUAL_ORDER_LEFT 

@stable ICU 63

U_INPC_TOP_AND_BOTTOM_AND_LEFT 

@stable ICU 66

Definition at line 2421 of file uchar.h.

◆ UIndicSyllabicCategory

Indic Syllabic Category constants.

See also
UCHAR_INDIC_SYLLABIC_CATEGORY @stable ICU 63
Enumerator
U_INSC_OTHER 

@stable ICU 63

U_INSC_AVAGRAHA 

@stable ICU 63

U_INSC_BINDU 

@stable ICU 63

U_INSC_BRAHMI_JOINING_NUMBER 

@stable ICU 63

U_INSC_CANTILLATION_MARK 

@stable ICU 63

U_INSC_CONSONANT 

@stable ICU 63

U_INSC_CONSONANT_DEAD 

@stable ICU 63

U_INSC_CONSONANT_FINAL 

@stable ICU 63

U_INSC_CONSONANT_HEAD_LETTER 

@stable ICU 63

U_INSC_CONSONANT_INITIAL_POSTFIXED 

@stable ICU 63

U_INSC_CONSONANT_KILLER 

@stable ICU 63

U_INSC_CONSONANT_MEDIAL 

@stable ICU 63

U_INSC_CONSONANT_PLACEHOLDER 

@stable ICU 63

U_INSC_CONSONANT_PRECEDING_REPHA 

@stable ICU 63

U_INSC_CONSONANT_PREFIXED 

@stable ICU 63

U_INSC_CONSONANT_SUBJOINED 

@stable ICU 63

U_INSC_CONSONANT_SUCCEEDING_REPHA 

@stable ICU 63

U_INSC_CONSONANT_WITH_STACKER 

@stable ICU 63

U_INSC_GEMINATION_MARK 

@stable ICU 63

U_INSC_INVISIBLE_STACKER 

@stable ICU 63

U_INSC_JOINER 

@stable ICU 63

U_INSC_MODIFYING_LETTER 

@stable ICU 63

U_INSC_NON_JOINER 

@stable ICU 63

U_INSC_NUKTA 

@stable ICU 63

U_INSC_NUMBER 

@stable ICU 63

U_INSC_NUMBER_JOINER 

@stable ICU 63

U_INSC_PURE_KILLER 

@stable ICU 63

U_INSC_REGISTER_SHIFTER 

@stable ICU 63

U_INSC_SYLLABLE_MODIFIER 

@stable ICU 63

U_INSC_TONE_LETTER 

@stable ICU 63

U_INSC_TONE_MARK 

@stable ICU 63

U_INSC_VIRAMA 

@stable ICU 63

U_INSC_VISARGA 

@stable ICU 63

U_INSC_VOWEL 

@stable ICU 63

U_INSC_VOWEL_DEPENDENT 

@stable ICU 63

U_INSC_VOWEL_INDEPENDENT 

@stable ICU 63

Definition at line 2468 of file uchar.h.

◆ UJoiningGroup

Joining Group constants.

See also
UCHAR_JOINING_GROUP @stable ICU 2.2
Enumerator
U_JG_NO_JOINING_GROUP 
U_JG_AIN 
U_JG_ALAPH 
U_JG_ALEF 
U_JG_BEH 
U_JG_BETH 
U_JG_DAL 
U_JG_DALATH_RISH 
U_JG_E 
U_JG_FEH 
U_JG_FINAL_SEMKATH 
U_JG_GAF 
U_JG_GAMAL 
U_JG_HAH 
U_JG_TEH_MARBUTA_GOAL 

@stable ICU 4.6

U_JG_HAMZA_ON_HEH_GOAL 
U_JG_HE 
U_JG_HEH 
U_JG_HEH_GOAL 
U_JG_HETH 
U_JG_KAF 
U_JG_KAPH 
U_JG_KNOTTED_HEH 
U_JG_LAM 
U_JG_LAMADH 
U_JG_MEEM 
U_JG_MIM 
U_JG_NOON 
U_JG_NUN 
U_JG_PE 
U_JG_QAF 
U_JG_QAPH 
U_JG_REH 
U_JG_REVERSED_PE 
U_JG_SAD 
U_JG_SADHE 
U_JG_SEEN 
U_JG_SEMKATH 
U_JG_SHIN 
U_JG_SWASH_KAF 
U_JG_SYRIAC_WAW 
U_JG_TAH 
U_JG_TAW 
U_JG_TEH_MARBUTA 
U_JG_TETH 
U_JG_WAW 
U_JG_YEH 
U_JG_YEH_BARREE 
U_JG_YEH_WITH_TAIL 
U_JG_YUDH 
U_JG_YUDH_HE 
U_JG_ZAIN 
U_JG_FE 

@stable ICU 2.6

U_JG_KHAPH 

@stable ICU 2.6

U_JG_ZHAIN 

@stable ICU 2.6

U_JG_BURUSHASKI_YEH_BARREE 

@stable ICU 4.0

U_JG_FARSI_YEH 

@stable ICU 4.4

U_JG_NYA 

@stable ICU 4.4

U_JG_ROHINGYA_YEH 

@stable ICU 49

U_JG_MANICHAEAN_ALEPH 

@stable ICU 54

U_JG_MANICHAEAN_AYIN 

@stable ICU 54

U_JG_MANICHAEAN_BETH 

@stable ICU 54

U_JG_MANICHAEAN_DALETH 

@stable ICU 54

U_JG_MANICHAEAN_DHAMEDH 

@stable ICU 54

U_JG_MANICHAEAN_FIVE 

@stable ICU 54

U_JG_MANICHAEAN_GIMEL 

@stable ICU 54

U_JG_MANICHAEAN_HETH 

@stable ICU 54

U_JG_MANICHAEAN_HUNDRED 

@stable ICU 54

U_JG_MANICHAEAN_KAPH 

@stable ICU 54

U_JG_MANICHAEAN_LAMEDH 

@stable ICU 54

U_JG_MANICHAEAN_MEM 

@stable ICU 54

U_JG_MANICHAEAN_NUN 

@stable ICU 54

U_JG_MANICHAEAN_ONE 

@stable ICU 54

U_JG_MANICHAEAN_PE 

@stable ICU 54

U_JG_MANICHAEAN_QOPH 

@stable ICU 54

U_JG_MANICHAEAN_RESH 

@stable ICU 54

U_JG_MANICHAEAN_SADHE 

@stable ICU 54

U_JG_MANICHAEAN_SAMEKH 

@stable ICU 54

U_JG_MANICHAEAN_TAW 

@stable ICU 54

U_JG_MANICHAEAN_TEN 

@stable ICU 54

U_JG_MANICHAEAN_TETH 

@stable ICU 54

U_JG_MANICHAEAN_THAMEDH 

@stable ICU 54

U_JG_MANICHAEAN_TWENTY 

@stable ICU 54

U_JG_MANICHAEAN_WAW 

@stable ICU 54

U_JG_MANICHAEAN_YODH 

@stable ICU 54

U_JG_MANICHAEAN_ZAYIN 

@stable ICU 54

U_JG_STRAIGHT_WAW 

@stable ICU 54

U_JG_AFRICAN_FEH 

@stable ICU 58

U_JG_AFRICAN_NOON 

@stable ICU 58

U_JG_AFRICAN_QAF 

@stable ICU 58

U_JG_MALAYALAM_BHA 

@stable ICU 60

U_JG_MALAYALAM_JA 

@stable ICU 60

U_JG_MALAYALAM_LLA 

@stable ICU 60

U_JG_MALAYALAM_LLLA 

@stable ICU 60

U_JG_MALAYALAM_NGA 

@stable ICU 60

U_JG_MALAYALAM_NNA 

@stable ICU 60

U_JG_MALAYALAM_NNNA 

@stable ICU 60

U_JG_MALAYALAM_NYA 

@stable ICU 60

U_JG_MALAYALAM_RA 

@stable ICU 60

U_JG_MALAYALAM_SSA 

@stable ICU 60

U_JG_MALAYALAM_TTA 

@stable ICU 60

U_JG_HANIFI_ROHINGYA_KINNA_YA 

@stable ICU 62

U_JG_HANIFI_ROHINGYA_PA 

@stable ICU 62

U_JG_COUNT 

One more than the highest normal UJoiningGroup value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_GROUP).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1996 of file uchar.h.

◆ UJoiningType

Joining Type constants.

See also
UCHAR_JOINING_TYPE @stable ICU 2.2
Enumerator
U_JT_NON_JOINING 
U_JT_JOIN_CAUSING 
U_JT_DUAL_JOINING 
U_JT_LEFT_JOINING 
U_JT_RIGHT_JOINING 
U_JT_TRANSPARENT 
U_JT_COUNT 

One more than the highest normal UJoiningType value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_JOINING_TYPE).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1966 of file uchar.h.

◆ ULineBreak

enum ULineBreak

Line Break constants.

See also
UCHAR_LINE_BREAK @stable ICU 2.2
Enumerator
U_LB_UNKNOWN 
U_LB_AMBIGUOUS 
U_LB_ALPHABETIC 
U_LB_BREAK_BOTH 
U_LB_BREAK_AFTER 
U_LB_BREAK_BEFORE 
U_LB_MANDATORY_BREAK 
U_LB_CONTINGENT_BREAK 
U_LB_CLOSE_PUNCTUATION 
U_LB_COMBINING_MARK 
U_LB_CARRIAGE_RETURN 
U_LB_EXCLAMATION 
U_LB_GLUE 
U_LB_HYPHEN 
U_LB_IDEOGRAPHIC 
U_LB_INSEPARABLE 

Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0

U_LB_INSEPERABLE 
U_LB_INFIX_NUMERIC 
U_LB_LINE_FEED 
U_LB_NONSTARTER 
U_LB_NUMERIC 
U_LB_OPEN_PUNCTUATION 
U_LB_POSTFIX_NUMERIC 
U_LB_PREFIX_NUMERIC 
U_LB_QUOTATION 
U_LB_COMPLEX_CONTEXT 
U_LB_SURROGATE 
U_LB_SPACE 
U_LB_BREAK_SYMBOLS 
U_LB_ZWSPACE 
U_LB_NEXT_LINE 

@stable ICU 2.6

U_LB_WORD_JOINER 

@stable ICU 2.6

U_LB_H2 

@stable ICU 3.4

U_LB_H3 

@stable ICU 3.4

U_LB_JL 

@stable ICU 3.4

U_LB_JT 

@stable ICU 3.4

U_LB_JV 

@stable ICU 3.4

U_LB_CLOSE_PARENTHESIS 

@stable ICU 4.4

U_LB_CONDITIONAL_JAPANESE_STARTER 

@stable ICU 49

U_LB_HEBREW_LETTER 

@stable ICU 49

U_LB_REGIONAL_INDICATOR 

@stable ICU 50

U_LB_E_BASE 

@stable ICU 58

U_LB_E_MODIFIER 

@stable ICU 58

U_LB_ZWJ 

@stable ICU 58

U_LB_COUNT 

One more than the highest normal ULineBreak value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_LINE_BREAK).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2280 of file uchar.h.

◆ UNumericType

Numeric Type constants.

See also
UCHAR_NUMERIC_TYPE @stable ICU 2.2
Enumerator
U_NT_NONE 
U_NT_DECIMAL 
U_NT_DIGIT 
U_NT_NUMERIC 
U_NT_COUNT 

One more than the highest normal UNumericType value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_NUMERIC_TYPE).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2363 of file uchar.h.

◆ UProperty

enum UProperty

Selection constants for Unicode properties. These constants are used in functions like u_hasBinaryProperty to select one of the Unicode properties.

The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).

For details about the properties see UAX #44: Unicode Character Database (http://www.unicode.org/reports/tr44/).

Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available. Check u_getUnicodeVersion to be sure.

See also
u_hasBinaryProperty
u_getIntPropertyValue
u_getUnicodeVersion @stable ICU 2.1
Enumerator
UCHAR_ALPHABETIC 

Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha. Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1

UCHAR_BINARY_START 

First constant for binary Unicode properties. @stable ICU 2.1

UCHAR_ASCII_HEX_DIGIT 

Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1

UCHAR_BIDI_CONTROL 

Binary property Bidi_Control. Format controls which have specific functions in the Bidi Algorithm. @stable ICU 2.1

UCHAR_BIDI_MIRRORED 

Binary property Bidi_Mirrored. Characters that may change display in RTL text. Same as u_isMirrored. See Bidi Algorithm, UTR 9. @stable ICU 2.1

UCHAR_DASH 

Binary property Dash. Variations of dashes. @stable ICU 2.1

UCHAR_DEFAULT_IGNORABLE_CODE_POINT 

Binary property Default_Ignorable_Code_Point (new in Unicode 3.2). Ignorable in most processing. <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1

UCHAR_DEPRECATED 

Binary property Deprecated (new in Unicode 3.2). The usage of deprecated characters is strongly discouraged. @stable ICU 2.1

UCHAR_DIACRITIC 

Binary property Diacritic. Characters that linguistically modify the meaning of another character to which they apply. @stable ICU 2.1

UCHAR_EXTENDER 

Binary property Extender. Extend the value or shape of a preceding alphabetic character, e.g., length and iteration marks. @stable ICU 2.1

UCHAR_FULL_COMPOSITION_EXCLUSION 

Binary property Full_Composition_Exclusion. CompositionExclusions.txt+Singleton Decompositions+ Non-Starter Decompositions. @stable ICU 2.1

UCHAR_GRAPHEME_BASE 

Binary property Grapheme_Base (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1

UCHAR_GRAPHEME_EXTEND 

Binary property Grapheme_Extend (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1

UCHAR_GRAPHEME_LINK 

Binary property Grapheme_Link (new in Unicode 3.2). For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1

UCHAR_HEX_DIGIT 

Binary property Hex_Digit. Characters commonly used for hexadecimal numbers. @stable ICU 2.1

UCHAR_HYPHEN 

Binary property Hyphen. Dashes used to mark connections between pieces of words, plus the Katakana middle dot. @stable ICU 2.1

UCHAR_ID_CONTINUE 

Binary property ID_Continue. Characters that can continue an identifier. DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out." ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1

UCHAR_ID_START 

Binary property ID_Start. Characters that can start an identifier. Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1

UCHAR_IDEOGRAPHIC 

Binary property Ideographic. CJKV ideographs. @stable ICU 2.1

UCHAR_IDS_BINARY_OPERATOR 

Binary property IDS_Binary_Operator (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1

UCHAR_IDS_TRINARY_OPERATOR 

Binary property IDS_Trinary_Operator (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1

UCHAR_JOIN_CONTROL 

Binary property Join_Control. Format controls for cursive joining and ligation. @stable ICU 2.1

UCHAR_LOGICAL_ORDER_EXCEPTION 

Binary property Logical_Order_Exception (new in Unicode 3.2). Characters that do not use logical order and require special handling in most processing. @stable ICU 2.1

UCHAR_LOWERCASE 

Binary property Lowercase. Same as u_isULowercase, different from u_islower. Ll+Other_Lowercase @stable ICU 2.1

UCHAR_MATH 

Binary property Math. Sm+Other_Math @stable ICU 2.1

UCHAR_NONCHARACTER_CODE_POINT 

Binary property Noncharacter_Code_Point. Code points that are explicitly defined as illegal for the encoding of characters. @stable ICU 2.1

UCHAR_QUOTATION_MARK 

Binary property Quotation_Mark. @stable ICU 2.1

UCHAR_RADICAL 

Binary property Radical (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1

UCHAR_SOFT_DOTTED 

Binary property Soft_Dotted (new in Unicode 3.2). Characters with a "soft dot", like i or j. An accent placed on these characters causes the dot to disappear. @stable ICU 2.1

UCHAR_TERMINAL_PUNCTUATION 

Binary property Terminal_Punctuation. Punctuation characters that generally mark the end of textual units. @stable ICU 2.1

UCHAR_UNIFIED_IDEOGRAPH 

Binary property Unified_Ideograph (new in Unicode 3.2). For programmatic determination of Ideographic Description Sequences. @stable ICU 2.1

UCHAR_UPPERCASE 

Binary property Uppercase. Same as u_isUUppercase, different from u_isupper. Lu+Other_Uppercase @stable ICU 2.1

UCHAR_WHITE_SPACE 

Binary property White_Space. Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace. Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1

UCHAR_XID_CONTINUE 

Binary property XID_Continue. ID_Continue modified to allow closure under normalization forms NFKC and NFKD. @stable ICU 2.1

UCHAR_XID_START 

Binary property XID_Start. ID_Start modified to allow closure under normalization forms NFKC and NFKD. @stable ICU 2.1

UCHAR_CASE_SENSITIVE 

Binary property Case_Sensitive. Either the source of a case mapping or in the target of a case mapping. Not the same as the general category Cased_Letter. @stable ICU 2.6

UCHAR_S_TERM 

Binary property STerm (new in Unicode 4.0.1). Sentence Terminal. Used in UAX #29: Text Boundaries (http://www.unicode.org/reports/tr29/) @stable ICU 3.0

UCHAR_VARIATION_SELECTOR 

Binary property Variation_Selector (new in Unicode 4.0.1). Indicates all those characters that qualify as Variation Selectors. For details on the behavior of these characters, see StandardizedVariants.html and 15.6 Variation Selectors. @stable ICU 3.0

UCHAR_NFD_INERT 

Binary property NFD_Inert. ICU-specific property for characters that are inert under NFD, i.e., they do not interact with adjacent characters. See the documentation for the Normalizer2 class and the Normalizer2::isInert() method. @stable ICU 3.0

UCHAR_NFKD_INERT 

Binary property NFKD_Inert. ICU-specific property for characters that are inert under NFKD, i.e., they do not interact with adjacent characters. See the documentation for the Normalizer2 class and the Normalizer2::isInert() method. @stable ICU 3.0

UCHAR_NFC_INERT 

Binary property NFC_Inert. ICU-specific property for characters that are inert under NFC, i.e., they do not interact with adjacent characters. See the documentation for the Normalizer2 class and the Normalizer2::isInert() method. @stable ICU 3.0

UCHAR_NFKC_INERT 

Binary property NFKC_Inert. ICU-specific property for characters that are inert under NFKC, i.e., they do not interact with adjacent characters. See the documentation for the Normalizer2 class and the Normalizer2::isInert() method. @stable ICU 3.0

UCHAR_SEGMENT_STARTER 

Binary Property Segment_Starter. ICU-specific property for characters that are starters in terms of Unicode normalization and combining character sequences. They have ccc=0 and do not occur in non-initial position of the canonical decomposition of any character (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)). ICU uses this property for segmenting a string for generating a set of canonically equivalent strings, e.g. for canonical closure while processing collation tailoring rules. @stable ICU 3.0

UCHAR_PATTERN_SYNTAX 

Binary property Pattern_Syntax (new in Unicode 4.1). See UAX #31 Identifier and Pattern Syntax (http://www.unicode.org/reports/tr31/) @stable ICU 3.4

UCHAR_PATTERN_WHITE_SPACE 

Binary property Pattern_White_Space (new in Unicode 4.1). See UAX #31 Identifier and Pattern Syntax (http://www.unicode.org/reports/tr31/) @stable ICU 3.4

UCHAR_POSIX_ALNUM 

Binary property alnum (a C/POSIX character class). Implemented according to the UTS #18 Annex C Standard Recommendation. See the uchar.h file documentation. @stable ICU 3.4

UCHAR_POSIX_BLANK 

Binary property blank (a C/POSIX character class). Implemented according to the UTS #18 Annex C Standard Recommendation. See the uchar.h file documentation. @stable ICU 3.4

UCHAR_POSIX_GRAPH 

Binary property graph (a C/POSIX character class). Implemented according to the UTS #18 Annex C Standard Recommendation. See the uchar.h file documentation. @stable ICU 3.4

UCHAR_POSIX_PRINT 

Binary property print (a C/POSIX character class). Implemented according to the UTS #18 Annex C Standard Recommendation. See the uchar.h file documentation. @stable ICU 3.4

UCHAR_POSIX_XDIGIT 

Binary property xdigit (a C/POSIX character class). Implemented according to the UTS #18 Annex C Standard Recommendation. See the uchar.h file documentation. @stable ICU 3.4

UCHAR_CASED 

Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4

UCHAR_CASE_IGNORABLE 

Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4

UCHAR_CHANGES_WHEN_LOWERCASED 

Binary property Changes_When_Lowercased. @stable ICU 4.4

UCHAR_CHANGES_WHEN_UPPERCASED 

Binary property Changes_When_Uppercased. @stable ICU 4.4

UCHAR_CHANGES_WHEN_TITLECASED 

Binary property Changes_When_Titlecased. @stable ICU 4.4

UCHAR_CHANGES_WHEN_CASEFOLDED 

Binary property Changes_When_Casefolded. @stable ICU 4.4

UCHAR_CHANGES_WHEN_CASEMAPPED 

Binary property Changes_When_Casemapped. @stable ICU 4.4

UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED 

Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4

UCHAR_EMOJI 

Binary property Emoji. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 57

UCHAR_EMOJI_PRESENTATION 

Binary property Emoji_Presentation. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 57

UCHAR_EMOJI_MODIFIER 

Binary property Emoji_Modifier. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 57

UCHAR_EMOJI_MODIFIER_BASE 

Binary property Emoji_Modifier_Base. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 57

UCHAR_EMOJI_COMPONENT 

Binary property Emoji_Component. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 60

UCHAR_REGIONAL_INDICATOR 

Binary property Regional_Indicator. @stable ICU 60

UCHAR_PREPENDED_CONCATENATION_MARK 

Binary property Prepended_Concatenation_Mark. @stable ICU 60

UCHAR_EXTENDED_PICTOGRAPHIC 

Binary property Extended_Pictographic. See http://www.unicode.org/reports/tr51/#Emoji_Properties

@stable ICU 62

UCHAR_BINARY_LIMIT 

One more than the last constant for binary Unicode properties.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_BIDI_CLASS 

Enumerated property Bidi_Class. Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2

UCHAR_INT_START 

First constant for enumerated/integer Unicode properties. @stable ICU 2.2

UCHAR_BLOCK 

Enumerated property Block. Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2

UCHAR_CANONICAL_COMBINING_CLASS 

Enumerated property Canonical_Combining_Class. Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2

UCHAR_DECOMPOSITION_TYPE 

Enumerated property Decomposition_Type. Returns UDecompositionType values. @stable ICU 2.2

UCHAR_EAST_ASIAN_WIDTH 

Enumerated property East_Asian_Width. See http://www.unicode.org/reports/tr11/ Returns UEastAsianWidth values. @stable ICU 2.2

UCHAR_GENERAL_CATEGORY 

Enumerated property General_Category. Same as u_charType, returns UCharCategory values. @stable ICU 2.2

UCHAR_JOINING_GROUP 

Enumerated property Joining_Group. Returns UJoiningGroup values. @stable ICU 2.2

UCHAR_JOINING_TYPE 

Enumerated property Joining_Type. Returns UJoiningType values. @stable ICU 2.2

UCHAR_LINE_BREAK 

Enumerated property Line_Break. Returns ULineBreak values. @stable ICU 2.2

UCHAR_NUMERIC_TYPE 

Enumerated property Numeric_Type. Returns UNumericType values. @stable ICU 2.2

UCHAR_SCRIPT 

Enumerated property Script. Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2

UCHAR_HANGUL_SYLLABLE_TYPE 

Enumerated property Hangul_Syllable_Type, new in Unicode 4. Returns UHangulSyllableType values. @stable ICU 2.6

UCHAR_NFD_QUICK_CHECK 

Enumerated property NFD_Quick_Check. Returns UNormalizationCheckResult values. @stable ICU 3.0

UCHAR_NFKD_QUICK_CHECK 

Enumerated property NFKD_Quick_Check. Returns UNormalizationCheckResult values. @stable ICU 3.0

UCHAR_NFC_QUICK_CHECK 

Enumerated property NFC_Quick_Check. Returns UNormalizationCheckResult values. @stable ICU 3.0

UCHAR_NFKC_QUICK_CHECK 

Enumerated property NFKC_Quick_Check. Returns UNormalizationCheckResult values. @stable ICU 3.0

UCHAR_LEAD_CANONICAL_COMBINING_CLASS 

Enumerated property Lead_Canonical_Combining_Class. ICU-specific property for the ccc of the first code point of the decomposition, or lccc(c)=ccc(NFD(c)[0]). Useful for checking for canonically ordered text; see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0

UCHAR_TRAIL_CANONICAL_COMBINING_CLASS 

Enumerated property Trail_Canonical_Combining_Class. ICU-specific property for the ccc of the last code point of the decomposition, or tccc(c)=ccc(NFD(c)[last]). Useful for checking for canonically ordered text; see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD . Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0

UCHAR_GRAPHEME_CLUSTER_BREAK 

Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1). Used in UAX #29: Text Boundaries (http://www.unicode.org/reports/tr29/) Returns UGraphemeClusterBreak values. @stable ICU 3.4

UCHAR_SENTENCE_BREAK 

Enumerated property Sentence_Break (new in Unicode 4.1). Used in UAX #29: Text Boundaries (http://www.unicode.org/reports/tr29/) Returns USentenceBreak values. @stable ICU 3.4

UCHAR_WORD_BREAK 

Enumerated property Word_Break (new in Unicode 4.1). Used in UAX #29: Text Boundaries (http://www.unicode.org/reports/tr29/) Returns UWordBreakValues values. @stable ICU 3.4

UCHAR_BIDI_PAIRED_BRACKET_TYPE 

Enumerated property Bidi_Paired_Bracket_Type (new in Unicode 6.3). Used in UAX #9: Unicode Bidirectional Algorithm (http://www.unicode.org/reports/tr9/) Returns UBidiPairedBracketType values. @stable ICU 52

UCHAR_INDIC_POSITIONAL_CATEGORY 

Enumerated property Indic_Positional_Category. New in Unicode 6.0 as provisional property Indic_Matra_Category; renamed and changed to informative in Unicode 8.0. See http://www.unicode.org/reports/tr44/#IndicPositionalCategory.txt @stable ICU 63

UCHAR_INDIC_SYLLABIC_CATEGORY 

Enumerated property Indic_Syllabic_Category. New in Unicode 6.0 as provisional; informative since Unicode 8.0. See http://www.unicode.org/reports/tr44/#IndicSyllabicCategory.txt @stable ICU 63

UCHAR_VERTICAL_ORIENTATION 

Enumerated property Vertical_Orientation. Used for UAX #50 Unicode Vertical Text Layout (https://www.unicode.org/reports/tr50/). New as a UCD property in Unicode 10.0. @stable ICU 63

UCHAR_INT_LIMIT 

One more than the last constant for enumerated/integer Unicode properties.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_GENERAL_CATEGORY_MASK 

Bitmask property General_Category_Mask. This is the General_Category property returned as a bit mask. When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)), returns bit masks for UCharCategory values where exactly one bit is set. When used with u_getPropertyValueName() and u_getPropertyValueEnum(), a multi-bit mask is used for sets of categories like "Letters". Mask values should be cast to uint32_t. @stable ICU 2.4

UCHAR_MASK_START 

First constant for bit-mask Unicode properties. @stable ICU 2.4

UCHAR_MASK_LIMIT 

One more than the last constant for bit-mask Unicode properties.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_NUMERIC_VALUE 

Double property Numeric_Value. Corresponds to u_getNumericValue. @stable ICU 2.4

UCHAR_DOUBLE_START 

First constant for double Unicode properties. @stable ICU 2.4

UCHAR_DOUBLE_LIMIT 

One more than the last constant for double Unicode properties.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_AGE 

String property Age. Corresponds to u_charAge. @stable ICU 2.4

UCHAR_STRING_START 

First constant for string Unicode properties. @stable ICU 2.4

UCHAR_BIDI_MIRRORING_GLYPH 

String property Bidi_Mirroring_Glyph. Corresponds to u_charMirror. @stable ICU 2.4

UCHAR_CASE_FOLDING 

String property Case_Folding. Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4

UCHAR_ISO_COMMENT 

Deprecated string property ISO_Comment. Corresponds to u_getISOComment.

Deprecated:
ICU 49
UCHAR_LOWERCASE_MAPPING 

String property Lowercase_Mapping. Corresponds to u_strToLower in ustring.h. @stable ICU 2.4

UCHAR_NAME 

String property Name. Corresponds to u_charName. @stable ICU 2.4

UCHAR_SIMPLE_CASE_FOLDING 

String property Simple_Case_Folding. Corresponds to u_foldCase. @stable ICU 2.4

UCHAR_SIMPLE_LOWERCASE_MAPPING 

String property Simple_Lowercase_Mapping. Corresponds to u_tolower. @stable ICU 2.4

UCHAR_SIMPLE_TITLECASE_MAPPING 

String property Simple_Titlecase_Mapping. Corresponds to u_totitle. @stable ICU 2.4

UCHAR_SIMPLE_UPPERCASE_MAPPING 

String property Simple_Uppercase_Mapping. Corresponds to u_toupper. @stable ICU 2.4

UCHAR_TITLECASE_MAPPING 

String property Titlecase_Mapping. Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4

UCHAR_UNICODE_1_NAME 

String property Unicode_1_Name. This property is of little practical value. Beginning with ICU 49, ICU APIs return an empty string for this property. Corresponds to u_charName(U_UNICODE_10_CHAR_NAME).

Deprecated:
ICU 49
UCHAR_UPPERCASE_MAPPING 

String property Uppercase_Mapping. Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4

UCHAR_BIDI_PAIRED_BRACKET 

String property Bidi_Paired_Bracket (new in Unicode 6.3). Corresponds to u_getBidiPairedBracket. @stable ICU 52

UCHAR_STRING_LIMIT 

One more than the last constant for string Unicode properties.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_SCRIPT_EXTENSIONS 

Miscellaneous property Script_Extensions (new in Unicode 6.0). Some characters are commonly used in multiple scripts. For more information, see UAX #24: http://www.unicode.org/reports/tr24/. Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h. @stable ICU 4.6

UCHAR_OTHER_PROPERTY_START 

First constant for Unicode properties with unusual value types. @stable ICU 4.6

UCHAR_OTHER_PROPERTY_LIMIT 

One more than the last constant for Unicode properties with unusual value types.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.
UCHAR_INVALID_CODE 

Represents a nonexistent or invalid property or property value. @stable ICU 2.4

Definition at line 195 of file uchar.h.

◆ UPropertyNameChoice

Selector constants for u_getPropertyName() and u_getPropertyValueName(). These selectors are used to choose which name is returned for a given property or value. All properties and values have a long name. Most have a short name, but some do not. Unicode allows for additional names, beyond the long and short name, which would be indicated by U_LONG_PROPERTY_NAME + i, where i=1, 2,...

See also
u_getPropertyName()
u_getPropertyValueName() @stable ICU 2.4
Enumerator
U_SHORT_PROPERTY_NAME 
U_LONG_PROPERTY_NAME 
U_PROPERTY_NAME_CHOICE_COUNT 

One more than the highest normal UPropertyNameChoice value.

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 1906 of file uchar.h.

◆ USentenceBreak

Sentence Break constants.

See also
UCHAR_SENTENCE_BREAK @stable ICU 3.4
Enumerator
U_SB_OTHER 
U_SB_ATERM 
U_SB_CLOSE 
U_SB_FORMAT 
U_SB_LOWER 
U_SB_NUMERIC 
U_SB_OLETTER 
U_SB_SEP 
U_SB_SP 
U_SB_STERM 
U_SB_UPPER 
U_SB_CR 
U_SB_EXTEND 
U_SB_LF 
U_SB_SCONTINUE 
U_SB_COUNT 

One more than the highest normal USentenceBreak value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_SENTENCE_BREAK).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2241 of file uchar.h.

◆ UVerticalOrientation

Vertical Orientation constants.

See also
UCHAR_VERTICAL_ORIENTATION @stable ICU 63
Enumerator
U_VO_ROTATED 

@stable ICU 63

U_VO_TRANSFORMED_ROTATED 

@stable ICU 63

U_VO_TRANSFORMED_UPRIGHT 

@stable ICU 63

U_VO_UPRIGHT 

@stable ICU 63

Definition at line 2555 of file uchar.h.

◆ UWordBreakValues

Word Break constants. (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)

See also
UCHAR_WORD_BREAK @stable ICU 3.4
Enumerator
U_WB_OTHER 
U_WB_ALETTER 
U_WB_FORMAT 
U_WB_KATAKANA 
U_WB_MIDLETTER 
U_WB_MIDNUM 
U_WB_NUMERIC 
U_WB_EXTENDNUMLET 
U_WB_CR 

@stable ICU 4.0

U_WB_EXTEND 

@stable ICU 4.0

U_WB_LF 

@stable ICU 4.0

U_WB_MIDNUMLET 

@stable ICU 4.0

U_WB_NEWLINE 

@stable ICU 4.0

U_WB_REGIONAL_INDICATOR 

@stable ICU 50

U_WB_HEBREW_LETTER 

@stable ICU 52

U_WB_SINGLE_QUOTE 

@stable ICU 52

U_WB_DOUBLE_QUOTE 

@stable ICU 52

U_WB_E_BASE 

@stable ICU 58

U_WB_E_BASE_GAZ 

@stable ICU 58

U_WB_E_MODIFIER 

@stable ICU 58

U_WB_GLUE_AFTER_ZWJ 

@stable ICU 58

U_WB_ZWJ 

@stable ICU 58

U_WB_WSEGSPACE 

@stable ICU 62

U_WB_COUNT 

One more than the highest normal UWordBreakValues value. The highest value is available via u_getIntPropertyMaxValue(UCHAR_WORD_BREAK).

Deprecated:
ICU 58 The numeric value may change over time, see ICU ticket #12420.

Definition at line 2178 of file uchar.h.

Function Documentation

◆ u_charAge_68()

void u_charAge_68 ( UChar32  c,
UVersionInfo  versionArray 
)

Get the "age" of the code point. The "age" is the Unicode version when the code point was first designated (as a non-character or for Private Use) or assigned a character. This can be useful to avoid emitting code points to receiving processes that do not accept newer characters. The data is from the UCD file DerivedAge.txt.

Parameters
cThe code point.
versionArrayThe Unicode version number array, to be filled in.

@stable ICU 2.1

Definition at line 548 of file uchar.cpp.

References c, NULL, u_getUnicodeProperties, uint8_t, UPROPS_AGE_SHIFT, and version.

◆ u_charDigitValue_68()

int32_t u_charDigitValue_68 ( UChar32  c)

Returns the decimal digit value of a decimal digit character. Such characters have the general category "Nd" (decimal digit numbers) and a Numeric_Type of Decimal.

Unlike ICU releases before 2.6, no digit values are returned for any Han characters because Han number characters are often used with a special Chinese-style number format (with characters for powers of 10 in between) instead of in decimal-positional notation. Unicode 4 explicitly assigns Han number characters the Numeric_Type Numeric instead of Decimal. See Jitterbug 1483 for more details.

Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() for complete numeric Unicode properties.

Parameters
cthe code point for which to get the decimal digit value
Returns
the decimal digit value of c, or -1 if c is not a decimal digit character
See also
u_getNumericValue @stable ICU 2.0

Definition at line 369 of file uchar.cpp.

References c, GET_NUMERIC_TYPE_VALUE, GET_PROPS, int32_t, and UPROPS_NTV_DECIMAL_START.

◆ u_charDirection_68()

UCharDirection u_charDirection_68 ( UChar32  c)

Returns the bidirectional category value for the code point, which is used in the Unicode bidirectional algorithm (UAX #9 http://www.unicode.org/reports/tr9/). Note that some unassigned code points have bidi values of R or AL because they are in blocks that are reserved for Right-To-Left scripts.

Same as java.lang.Character.getDirectionality()

Parameters
cthe code point to be tested
Returns
the bidirectional category (UCharDirection) value
See also
UCharDirection @stable ICU 2.0

Definition at line 237 of file ubidi_props.cpp.

References c, and ubidi_getClass.

◆ u_charFromName_68()

UChar32 u_charFromName_68 ( UCharNameChoice  nameChoice,
const char *  name,
UErrorCode pErrorCode 
)

Find a Unicode character by its name and return its code point value. The name is matched exactly and completely. If the name does not correspond to a code point, pErrorCode is set to U_INVALID_CHAR_FOUND. A Unicode 1.0 name is matched only if it differs from the modern name. Unicode names are all uppercase. Extended names are lowercase followed by an uppercase hexadecimal number, and within angle brackets.

Parameters
nameChoiceSelector for which name to match.
nameThe name to match.
pErrorCodePointer to a UErrorCode variable
Returns
The Unicode value of the code point with the given name, or an undefined value if there is no such code point.
See also
UCharNameChoice
u_charName
u_enumCharNames @stable ICU 1.7

Definition at line 1519 of file unames.cpp.

References UCharNames::algNamesOffset, charCatNames, FindName::code, cp, DO_FIND_NAME, enumNames(), error, findAlgName(), getCharCat(), i, isDataLoaded(), limit, lower, name, NULL, FindName::otherName, p, AlgorithmicRange::size, U_CHAR_NAME_CHOICE_COUNT, U_EXTENDED_CHAR_NAME, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, U_ILLEGAL_CHAR_FOUND, UCHAR_MAX_VALUE, uCharNames, upper(), UPRV_LENGTHOF, uprv_strcmp, uprv_tolower, and uprv_toupper.

◆ u_charMirror_68()

UChar32 u_charMirror_68 ( UChar32  c)

Maps the specified character to a "mirror-image" character. For characters with the Bidi_Mirrored property, implementations sometimes need a "poor man's" mapping to another Unicode character (code point) such that the default glyph may serve as the mirror-image of the default glyph of the specified character. This is useful for text conversion to and from codepages with visual order, and for displays without glyph selection capabilities.

Parameters
cthe code point to be mapped
Returns
another Unicode code point that may serve as a mirror-image substitute, or c itself if there is no such mapping or c does not have the Bidi_Mirrored property
See also
UCHAR_BIDI_MIRRORED
u_isMirrored @stable ICU 2.0

Definition at line 247 of file ubidi_props.cpp.

References c, and ubidi_getMirror.

◆ u_charName_68()

int32_t u_charName_68 ( UChar32  code,
UCharNameChoice  nameChoice,
char *  buffer,
int32_t  bufferLength,
UErrorCode pErrorCode 
)

Retrieve the name of a Unicode character. Depending on nameChoice, the character name written into the buffer is the "modern" name or the name that was defined in Unicode version 1.0. The name contains only "invariant" characters like A-Z, 0-9, space, and '-'. Unicode 1.0 names are only retrieved if they are different from the modern names and if the data file contains the data for them. gennames may or may not be called with a command line option to include 1.0 names in unames.dat.

Parameters
codeThe character (code point) for which to get the name. It must be 0<=code<=0x10ffff.
nameChoiceSelector for which name to get.
bufferDestination address for copying the name. The name will always be zero-terminated. If there is no name, then the buffer will be set to the empty string.
bufferLength==sizeof(buffer)
pErrorCodePointer to a UErrorCode variable; check for U_SUCCESS() after u_charName() returns.
Returns
The length of the name, or 0 if there is no name for this character. If the bufferLength is less than or equal to the length, then the buffer contains the truncated name and the returned length indicates the full length of the name. The length does not include the zero-termination.
See also
UCharNameChoice
u_charFromName
u_enumCharNames @stable ICU 2.0

Definition at line 1450 of file unames.cpp.

References UCharNames::algNamesOffset, end, getAlgName(), getExtName(), getName(), i, isDataLoaded(), length, NULL, p, AlgorithmicRange::size, AlgorithmicRange::start, U_CHAR_NAME_CHOICE_COUNT, U_EXTENDED_CHAR_NAME, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, u_terminateChars, UCHAR_MAX_VALUE, uCharNames, and uint32_t.

◆ u_charType_68()

int8_t u_charType_68 ( UChar32  c)

Returns the general category value for the code point.

Same as java.lang.Character.getType().

Parameters
cthe code point to be tested
Returns
the general category (UCharCategory) value
See also
UCharCategory @stable ICU 2.0

Definition at line 49 of file uchar.cpp.

References c, GET_CATEGORY, and GET_PROPS.

◆ u_digit_68()

int32_t u_digit_68 ( UChar32  ch,
int8_t  radix 
)

Returns the decimal digit value of the code point in the specified radix.

If the radix is not in the range 2<=radix<=36 or if the value of c is not a valid digit in the specified radix, -1 is returned. A character is a valid digit if at least one of the following is true:

  • The character has a decimal digit value. Such characters have the general category "Nd" (decimal digit numbers) and a Numeric_Type of Decimal. In this case the value is the character's decimal digit value.
  • The character is one of the uppercase Latin letters 'A' through 'Z'. In this case the value is c-'A'+10.
  • The character is one of the lowercase Latin letters 'a' through 'z'. In this case the value is ch-'a'+10.
  • Latin letters from both the ASCII range (0061..007A, 0041..005A) as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A) are recognized.

Same as java.lang.Character.digit().

Parameters
chthe code point to be tested.
radixthe radix.
Returns
the numeric value represented by the character in the specified radix, or -1 if there is no value or if the value exceeds the radix.
See also
UCHAR_NUMERIC_TYPE
u_forDigit
u_charDigitValue
u_isdigit @stable ICU 2.0

Definition at line 475 of file uchar.cpp.

References ch, int8_t, radix, and u_charDigitValue.

◆ u_enumCharNames_68()

void u_enumCharNames_68 ( UChar32  start,
UChar32  limit,
UEnumCharNamesFn fn,
void context,
UCharNameChoice  nameChoice,
UErrorCode pErrorCode 
)

Enumerate all assigned Unicode characters between the start and limit code points (start inclusive, limit exclusive) and call a function for each, passing the code point value and the character name. For Unicode 1.0 names, only those are enumerated that differ from the modern names.

Parameters
startThe first code point in the enumeration range.
limitOne more than the last code point in the enumeration range (the first one after the range).
fnThe function that is to be called for each character name.
contextAn arbitrary pointer that is passed to the function.
nameChoiceSelector for which kind of names to enumerate.
pErrorCodePointer to a UErrorCode variable
See also
UCharNameChoice
UEnumCharNamesFn
u_charName
u_charFromName @stable ICU 1.7

Definition at line 1635 of file unames.cpp.

References UCharNames::algNamesOffset, AlgorithmicRange::end, enumAlgNames(), enumNames(), fc-lang::fn, i, isDataLoaded(), limit, NULL, p, AlgorithmicRange::size, start, AlgorithmicRange::start, U_CHAR_NAME_CHOICE_COUNT, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, UCHAR_MAX_VALUE, and uCharNames.

◆ u_enumCharTypes_68()

void u_enumCharTypes_68 ( UCharEnumTypeRange enumRange,
const void context 
)

Enumerate efficiently all code points with their Unicode general categories.

This is useful for building data structures (e.g., UnicodeSet's), for enumerating all assigned code points (type!=U_UNASSIGNED), etc.

For each contiguous range of code points with a given general category ("character type"), the UCharEnumTypeRange function is called. Adjacent ranges have different types. The Unicode Standard guarantees that the numeric value of the type is 0..31.

Parameters
enumRangea pointer to a function that is called for each contiguous range of code points with the same general category
contextan opaque pointer that is passed on to the callback function

@stable ICU 2.1

See also
UCharCategory
UCharEnumTypeRange

Definition at line 76 of file uchar.cpp.

References _enumTypeRange(), _enumTypeValue(), _EnumTypeCallback::context, _EnumTypeCallback::enumRange, NULL, and utrie2_enum.

◆ u_foldCase_68()

UChar32 u_foldCase_68 ( UChar32  c,
uint32_t  options 
)

The given character is mapped to its case folding equivalent according to UnicodeData.txt and CaseFolding.txt; if the character has no case folding equivalent, the character itself is returned.

This function only returns the simple, single-code point case mapping. Full case mappings should be used whenever possible because they produce better results by working on whole strings. They take into account the string context and the language and can map to a result string with a different length as appropriate. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class. See also the User Guide chapter on C/POSIX migration: http://icu-project.org/userguide/posix.html#case_mappings

Parameters
cthe code point to be mapped
optionsEither U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
Returns
the Simple_Case_Folding of the code point, if any; otherwise the code point itself. @stable ICU 2.0

Definition at line 1560 of file ucase.cpp.

References c, and ucase_fold.

◆ u_forDigit_68()

UChar32 u_forDigit_68 ( int32_t  digit,
int8_t  radix 
)

Determines the character representation for a specific digit in the specified radix. If the value of radix is not a valid radix, or the value of digit is not a valid digit in the specified radix, the null character (U+0000) is returned.

The radix argument is valid if it is greater than or equal to 2 and less than or equal to 36. The digit argument is valid if 0 <= digit < radix.

If the digit is less than 10, then '0' + digit is returned. Otherwise, the value 'a' + digit - 10 is returned.

Same as java.lang.Character.forDigit().

Parameters
digitthe number to convert to a character.
radixthe radix.
Returns
the char representation of the specified digit in the specified radix.
See also
u_digit
u_charDigitValue
u_isdigit @stable ICU 2.0

Definition at line 498 of file uchar.cpp.

References digit, and radix.

◆ u_getBidiPairedBracket_68()

UChar32 u_getBidiPairedBracket_68 ( UChar32  c)

Maps the specified character to its paired bracket character. For Bidi_Paired_Bracket_Type!=None, this is the same as u_charMirror(). Otherwise c itself is returned. See http://www.unicode.org/reports/tr9/

Parameters
cthe code point to be mapped
Returns
the paired bracket code point, or c itself if there is no such mapping (Bidi_Paired_Bracket_Type=None)
See also
UCHAR_BIDI_PAIRED_BRACKET
UCHAR_BIDI_PAIRED_BRACKET_TYPE
u_charMirror @stable ICU 52

Definition at line 252 of file ubidi_props.cpp.

References c, and ubidi_getPairedBracket.

◆ u_getBinaryPropertySet_68()

const USet* u_getBinaryPropertySet_68 ( UProperty  property,
UErrorCode pErrorCode 
)

Returns a frozen USet for a binary property. The library retains ownership over the returned object. Sets an error code if the property number is not one for a binary property.

The returned set contains all code points for which the property is true.

Parameters
propertyUCHAR_BINARY_START..UCHAR_BINARY_LIMIT-1
pErrorCodean in/out ICU UErrorCode
Returns
the property as a set
See also
UProperty
u_hasBinaryProperty
Unicode::fromUSet @stable ICU 63

Definition at line 355 of file characterproperties.cpp.

References m, U_NAMESPACE_END::makeSet(), fc-lang::sets, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, and UCHAR_BINARY_LIMIT.

◆ u_getCombiningClass_68()

uint8_t u_getCombiningClass_68 ( UChar32  c)

Returns the combining class of the code point as specified in UnicodeData.txt.

Parameters
cthe code point of the character
Returns
the combining class of the character @stable ICU 2.0

Definition at line 551 of file normalizer2.cpp.

References c, errorCode, U_SUCCESS, and U_ZERO_ERROR.

◆ u_getFC_NFKC_Closure_68()

int32_t u_getFC_NFKC_Closure_68 ( UChar32  c,
UChar dest,
int32_t  destCapacity,
UErrorCode pErrorCode 
)

Get the FC_NFKC_Closure property string for a character. See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure" or for "FNC": http://www.unicode.org/reports/tr15/

Parameters
cThe character (code point) for which to get the FC_NFKC_Closure string. It must be 0<=c<=0x10ffff.
destDestination address for copying the string. The string will be zero-terminated if possible. If there is no FC_NFKC_Closure string, then the buffer will be set to the empty string.
destCapacity==sizeof(dest)
pErrorCodePointer to a UErrorCode variable.
Returns
The length of the string, or 0 if there is no FC_NFKC_Closure string for this character. If the destCapacity is less than or equal to the length, then the buffer contains the truncated name and the returned length indicates the full length of the name. The length does not include the zero-termination.

@stable ICU 2.2

Definition at line 750 of file uprops.cpp.

References c, dest, FALSE, Normalizer2Impl::getCompQuickCheck(), Normalizer2Factory::getImpl(), Normalizer2Impl::getNorm16(), NULL, U_FAILURE, U_FOLD_CASE_DEFAULT, U_ILLEGAL_ARGUMENT_ERROR, u_terminateUChars, UCASE_MAX_STRING_LENGTH, ucase_toFullFolding, and UNORM_NO.

◆ u_getIntPropertyMap_68()

const UCPMap* u_getIntPropertyMap_68 ( UProperty  property,
UErrorCode pErrorCode 
)

Returns an immutable UCPMap for an enumerated/catalog/int-valued property. The library retains ownership over the returned object. Sets an error code if the property number is not one for an "int property".

The returned object maps all Unicode code points to their values for that property. For documentation of the integer values see u_getIntPropertyValue().

Parameters
propertyUCHAR_INT_START..UCHAR_INT_LIMIT-1
pErrorCodean in/out ICU UErrorCode
Returns
the property as a map
See also
UProperty
u_getIntPropertyValue @stable ICU 63

Definition at line 371 of file characterproperties.cpp.

References m, U_NAMESPACE_END::makeMap(), map, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, UCHAR_INT_LIMIT, and UCHAR_INT_START.

◆ u_getIntPropertyMaxValue_68()

int32_t u_getIntPropertyMaxValue_68 ( UProperty  which)

Get the maximum value for an enumerated/integer/binary Unicode property. Can be used together with u_getIntPropertyMinValue to allocate arrays of UnicodeSet or similar.

Examples for min/max values (for Unicode 3.2):

  • UCHAR_BIDI_CLASS: 0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
  • UCHAR_SCRIPT: 0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
  • UCHAR_IDEOGRAPHIC: 0/1 (false/true)

For undefined UProperty constant values, min/max values will be 0/-1.

Parameters
whichUProperty selector constant, identifies which binary property to check. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
Returns
Maximum value returned by u_getIntPropertyValue for a Unicode property. <=0 if the property selector is out of range.
See also
UProperty
u_hasBinaryProperty
u_getUnicodeVersion
u_getIntPropertyMaxValue
u_getIntPropertyValue @stable ICU 2.2

Definition at line 637 of file uprops.cpp.

References intProps, prop, UCHAR_BINARY_LIMIT, UCHAR_BINARY_START, UCHAR_INT_LIMIT, and UCHAR_INT_START.

◆ u_getIntPropertyMinValue_68()

int32_t u_getIntPropertyMinValue_68 ( UProperty  which)

Get the minimum value for an enumerated/integer/binary Unicode property. Can be used together with u_getIntPropertyMaxValue to allocate arrays of UnicodeSet or similar.

Parameters
whichUProperty selector constant, identifies which binary property to check. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
Returns
Minimum value returned by u_getIntPropertyValue for a Unicode property. 0 if the property selector is out of range.
See also
UProperty
u_hasBinaryProperty
u_getUnicodeVersion
u_getIntPropertyMaxValue
u_getIntPropertyValue @stable ICU 2.2

Definition at line 632 of file uprops.cpp.

◆ u_getIntPropertyValue_68()

int32_t u_getIntPropertyValue_68 ( UChar32  c,
UProperty  which 
)

Get the property value for an enumerated or integer Unicode property for a code point. Also returns binary and mask property values.

Unicode, especially in version 3.2, defines many more properties than the original set in UnicodeData.txt.

The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). For details about the properties see http://www.unicode.org/ . For names of Unicode properties see the UCD file PropertyAliases.txt.

Sample usage: UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH); UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);

Parameters
cCode point to test.
whichUProperty selector constant, identifies which property to check. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT or UCHAR_INT_START<=which<UCHAR_INT_LIMIT or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
Returns
Numeric value that is directly the property value or, for enumerated properties, corresponds to the numeric value of the enumerated constant of the respective property value enumeration type (cast to enum type if necessary). Returns 0 or 1 (for false/true) for binary Unicode properties. Returns a bit-mask for mask properties. Returns 0 if 'which' is out of bounds or if the Unicode version does not have data for the property at all, or not for this code point.
See also
UProperty
u_hasBinaryProperty
u_getIntPropertyMinValue
u_getIntPropertyMaxValue
u_getIntPropertyMap
u_getUnicodeVersion @stable ICU 2.2

Definition at line 616 of file uprops.cpp.

References binProps, c, intProps, prop, u_charType, U_MASK, UCHAR_BINARY_LIMIT, UCHAR_BINARY_START, UCHAR_GENERAL_CATEGORY_MASK, UCHAR_INT_LIMIT, and UCHAR_INT_START.

◆ u_getISOComment_68()

int32_t u_getISOComment_68 ( UChar32  c,
char *  dest,
int32_t  destCapacity,
UErrorCode pErrorCode 
)

Returns an empty string. Used to return the ISO 10646 comment for a character. The Unicode ISO_Comment property is deprecated and has no values.

Parameters
cThe character (code point) for which to get the ISO comment. It must be 0<=c<=0x10ffff.
destDestination address for copying the comment. The comment will be zero-terminated if possible. If there is no comment, then the buffer will be set to the empty string.
destCapacity==sizeof(dest)
pErrorCodePointer to a UErrorCode variable; check for U_SUCCESS() after u_getISOComment() returns.
Returns
0
Deprecated:
ICU 49

Definition at line 1504 of file unames.cpp.

References dest, NULL, U_FAILURE, U_ILLEGAL_ARGUMENT_ERROR, and u_terminateChars.

◆ u_getNumericValue_68()

double u_getNumericValue_68 ( UChar32  c)

Get the numeric value for a Unicode code point as defined in the Unicode Character Database.

A "double" return type is necessary because some numeric values are fractions, negative, or too large for int32_t.

For characters without any numeric values in the Unicode Character Database, this function will return U_NO_NUMERIC_VALUE. Note: This is different from the Unicode Standard which specifies NaN as the default value. (NaN is not available on all platforms.)

Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() also supports negative values, large values, and fractions, while Java's getNumericValue() returns values 10..35 for ASCII letters.

Parameters
cCode point to get the numeric value for.
Returns
Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
See also
U_NO_NUMERIC_VALUE @stable ICU 2.2

Definition at line 382 of file uchar.cpp.

References c, denominator, exp(), GET_NUMERIC_TYPE_VALUE, GET_PROPS, int32_t, numerator, U_NO_NUMERIC_VALUE, UPROPS_NTV_BASE60_START, UPROPS_NTV_DECIMAL_START, UPROPS_NTV_DIGIT_START, UPROPS_NTV_FRACTION20_START, UPROPS_NTV_FRACTION32_START, UPROPS_NTV_FRACTION_START, UPROPS_NTV_LARGE_START, UPROPS_NTV_NONE, UPROPS_NTV_NUMERIC_START, and UPROPS_NTV_RESERVED_START.

◆ u_getPropertyEnum_68()

UProperty u_getPropertyEnum_68 ( const char *  alias)

Return the UProperty enum for a given property name, as specified in the Unicode database file PropertyAliases.txt. Short, long, and any other variants are recognized.

In addition, this function maps the synthetic names "gcm" / "General_Category_Mask" to the property UCHAR_GENERAL_CATEGORY_MASK. These names are not in PropertyAliases.txt.

Parameters
aliasthe property name to be matched. The name is compared using "loose matching" as described in PropertyAliases.txt.
Returns
a UProperty enum, or UCHAR_INVALID_CODE if the given name does not match any property.
See also
UProperty @stable ICU 2.4

Definition at line 298 of file propname.cpp.

References alias, and PropNameData::getPropertyEnum().

◆ u_getPropertyName_68()

const char* u_getPropertyName_68 ( UProperty  property,
UPropertyNameChoice  nameChoice 
)

Return the Unicode name for a given property, as given in the Unicode database file PropertyAliases.txt.

In addition, this function maps the property UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" / "General_Category_Mask". These names are not in PropertyAliases.txt.

Parameters
propertyUProperty selector other than UCHAR_INVALID_CODE. If out of range, NULL is returned.
nameChoiceselector for which name to get. If out of range, NULL is returned. All properties have a long name. Most have a short name, but some do not. Unicode allows for additional names; if present these will be returned by U_LONG_PROPERTY_NAME + i, where i=1, 2,...
Returns
a pointer to the name, or NULL if either the property or the nameChoice is out of range. If a given nameChoice returns NULL, then all larger values of nameChoice will return NULL, with one exception: if NULL is returned for U_SHORT_PROPERTY_NAME, then U_LONG_PROPERTY_NAME (and higher) may still return a non-NULL value. The returned pointer is valid until u_cleanup() is called.
See also
UProperty
UPropertyNameChoice @stable ICU 2.4

Definition at line 291 of file propname.cpp.

References PropNameData::getPropertyName().

◆ u_getPropertyValueEnum_68()

int32_t u_getPropertyValueEnum_68 ( UProperty  property,
const char *  alias 
)

Return the property value integer for a given value name, as specified in the Unicode database file PropertyValueAliases.txt. Short, long, and any other variants are recognized.

Note: Some of the names in PropertyValueAliases.txt will only be recognized with UCHAR_GENERAL_CATEGORY_MASK, not UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" / "Punctuation", "S" / "Symbol", and "Z" / "Separator".

Parameters
propertyUProperty selector constant. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT or UCHAR_INT_START<=which<UCHAR_INT_LIMIT or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. If out of range, UCHAR_INVALID_CODE is returned.
aliasthe value name to be matched. The name is compared using "loose matching" as described in PropertyValueAliases.txt.
Returns
a value integer or UCHAR_INVALID_CODE if the given name does not match any value of the given property, or if the property is invalid. Note: UCHAR_GENERAL_CATEGORY_MASK values are not values of UCharCategory, but rather mask values produced by U_GET_GC_MASK(). This allows grouped categories such as [:L:] to be represented.
See also
UProperty @stable ICU 2.4

Definition at line 312 of file propname.cpp.

References alias, and PropNameData::getPropertyValueEnum().

◆ u_getPropertyValueName_68()

const char* u_getPropertyValueName_68 ( UProperty  property,
int32_t  value,
UPropertyNameChoice  nameChoice 
)

Return the Unicode name for a given property value, as given in the Unicode database file PropertyValueAliases.txt.

Note: Some of the names in PropertyValueAliases.txt can only be retrieved using UCHAR_GENERAL_CATEGORY_MASK, not UCHAR_GENERAL_CATEGORY. These include: "C" / "Other", "L" / "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P" / "Punctuation", "S" / "Symbol", and "Z" / "Separator".

Parameters
propertyUProperty selector constant. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT or UCHAR_INT_START<=which<UCHAR_INT_LIMIT or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT. If out of range, NULL is returned.
valueselector for a value for the given property. If out of range, NULL is returned. In general, valid values range from 0 up to some maximum. There are a few exceptions: (1.) UCHAR_BLOCK values begin at the non-zero value UBLOCK_BASIC_LATIN. (2.) UCHAR_CANONICAL_COMBINING_CLASS values are not contiguous and range from 0..240. (3.) UCHAR_GENERAL_CATEGORY_MASK values are not values of UCharCategory, but rather mask values produced by U_GET_GC_MASK(). This allows grouped categories such as [:L:] to be represented. Mask values range non-contiguously from 1..U_GC_P_MASK.
nameChoiceselector for which name to get. If out of range, NULL is returned. All values have a long name. Most have a short name, but some do not. Unicode allows for additional names; if present these will be returned by U_LONG_PROPERTY_NAME + i, where i=1, 2,...
Returns
a pointer to the name, or NULL if either the property or the nameChoice is out of range. If a given nameChoice returns NULL, then all larger values of nameChoice will return NULL, with one exception: if NULL is returned for U_SHORT_PROPERTY_NAME, then U_LONG_PROPERTY_NAME (and higher) may still return a non-NULL value. The returned pointer is valid until u_cleanup() is called.
See also
UProperty
UPropertyNameChoice @stable ICU 2.4

Definition at line 304 of file propname.cpp.

References PropNameData::getPropertyValueName().

◆ u_getUnicodeVersion_68()

void u_getUnicodeVersion_68 ( UVersionInfo  versionArray)

Gets the Unicode version information. The version array is filled in with the version information for the Unicode standard that is currently used by ICU. For example, Unicode version 3.1.1 is represented as an array with the values { 3, 1, 1, 0 }.

Parameters
versionArrayan output array that will be filled in with the Unicode version number @stable ICU 2.0

Definition at line 511 of file uchar.cpp.

References dataVersion, NULL, U_MAX_VERSION_LENGTH, and uprv_memcpy.

◆ u_hasBinaryProperty_68()

UBool u_hasBinaryProperty_68 ( UChar32  c,
UProperty  which 
)

Check a binary Unicode property for a code point.

Unicode, especially in version 3.2, defines many more properties than the original set in UnicodeData.txt.

The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). For details about the properties see http://www.unicode.org/ucd/ . For names of Unicode properties see the UCD file PropertyAliases.txt.

Important: If ICU is built with UCD files from Unicode versions below 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available.

Parameters
cCode point to test.
whichUProperty selector constant, identifies which binary property to check. Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
Returns
true or false according to the binary Unicode property value for c. Also false if 'which' is out of bounds or if the Unicode version does not have data for the property at all, or not for this code point.
See also
UProperty
u_getBinaryPropertySet
u_getIntPropertyValue
u_getUnicodeVersion @stable ICU 2.1

Definition at line 402 of file uprops.cpp.

References binProps, c, FALSE, prop, UCHAR_BINARY_LIMIT, and UCHAR_BINARY_START.

◆ u_isalnum_68()

UBool u_isalnum_68 ( UChar32  c)

Determines whether the specified code point is an alphanumeric character (letter or digit) according to Java. True for characters with general categories "L" (letters) and "Nd" (decimal digit numbers).

Same as java.lang.Character.isLetterOrDigit().

In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is an alphanumeric character according to Character.isLetterOrDigit()

@stable ICU 2.0

Definition at line 151 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, and U_GC_ND_MASK.

◆ u_isalpha_68()

UBool u_isalpha_68 ( UChar32  c)

Determines whether the specified code point is a letter character. True for general categories "L" (letters).

Same as java.lang.Character.isLetter().

In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a letter character
See also
u_isdigit
u_isalnum @stable ICU 2.0

Definition at line 138 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, and U_GC_L_MASK.

◆ u_isbase_68()

UBool u_isbase_68 ( UChar32  c)

Non-standard: Determines whether the specified code point is a base character. True for general categories "L" (letters), "N" (numbers), "Mc" (spacing combining marks), and "Me" (enclosing marks).

Note that this is different from the Unicode Standard definition in chapter 3.6, conformance clause D51 “Base character”, which defines base characters as the code points with general categories Letter (L), Number (N), Punctuation (P), Symbol (S), or Space Separator (Zs).

Parameters
cthe code point to be tested
Returns
true if the code point is a base character according to this function
See also
u_isalpha
u_isdigit @stable ICU 2.0

Definition at line 176 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, U_GC_MC_MASK, U_GC_ME_MASK, and U_GC_N_MASK.

◆ u_isblank_68()

UBool u_isblank_68 ( UChar32  c)

Determines whether the specified code point is a "blank" or "horizontal space", a character that visibly separates words on a line. The following are equivalent definitions:

true for Unicode White_Space characters except for "vertical space controls" where "vertical space controls" are the following characters: U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)

same as

true for U+0009 (TAB) and characters with general category "Zs" (space separators).

Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a "blank"

@stable ICU 2.6

Definition at line 231 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, and U_SPACE_SEPARATOR.

◆ u_iscntrl_68()

UBool u_iscntrl_68 ( UChar32  c)

Determines whether the specified code point is a control character (as defined by this function). A control character is one of the following:

  • ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
  • U_CONTROL_CHAR (Cc)
  • U_FORMAT_CHAR (Cf)
  • U_LINE_SEPARATOR (Zl)
  • U_PARAGRAPH_SEPARATOR (Zp)

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a control character
See also
UCHAR_DEFAULT_IGNORABLE_CODE_POINT
u_isprint @stable ICU 2.0

Definition at line 184 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_CC_MASK, U_GC_CF_MASK, U_GC_ZL_MASK, and U_GC_ZP_MASK.

◆ u_isdefined_68()

UBool u_isdefined_68 ( UChar32  c)

Determines whether the specified code point is "defined", which usually means that it is assigned a character. True for general categories other than "Cn" (other, not assigned), i.e., true for all code points mentioned in UnicodeData.txt.

Note that non-character code points (e.g., U+FDD0) are not "defined" (they are Cn), but surrogate code points are "defined" (Cs).

Same as java.lang.Character.isDefined().

Parameters
cthe code point to be tested
Returns
true if the code point is assigned a character
See also
u_isdigit
u_isalpha
u_isalnum
u_isupper
u_islower
u_istitle @stable ICU 2.0

Definition at line 168 of file uchar.cpp.

References c, GET_CATEGORY, and GET_PROPS.

◆ u_isdigit_68()

UBool u_isdigit_68 ( UChar32  c)

Determines whether the specified code point is a digit character according to Java. True for characters with general category "Nd" (decimal digit numbers). Beginning with Unicode 4, this is the same as testing for the Numeric_Type of Decimal.

Same as java.lang.Character.isDigit().

In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a digit character according to Character.isDigit()

@stable ICU 2.0

Definition at line 114 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, and U_DECIMAL_DIGIT_NUMBER.

◆ u_isgraph_68()

UBool u_isgraph_68 ( UChar32  c)

Determines whether the specified code point is a "graphic" character (printable, excluding spaces). true for all characters except those with general categories "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), "Cn" (unassigned), and "Z" (separators).

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a "graphic" character

@stable ICU 2.6

Definition at line 273 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_CC_MASK, U_GC_CF_MASK, U_GC_CN_MASK, U_GC_CS_MASK, and U_GC_Z_MASK.

◆ u_isIDIgnorable_68()

UBool u_isIDIgnorable_68 ( UChar32  c)

Determines if the specified character should be regarded as an ignorable character in an identifier, according to Java. True for characters with general category "Cf" (format controls) as well as non-whitespace ISO controls (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).

Same as java.lang.Character.isIdentifierIgnorable().

Note that Unicode just recommends to ignore Cf (format controls).

Parameters
cthe code point to be tested
Returns
true if the code point is ignorable in identifiers according to Java
See also
UCHAR_DEFAULT_IGNORABLE_CODE_POINT
u_isIDStart
u_isIDPart @stable ICU 2.0

Definition at line 333 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, IS_THAT_ASCII_CONTROL_SPACE, U_FORMAT_CHAR, and u_isISOControl.

◆ u_isIDPart_68()

UBool u_isIDPart_68 ( UChar32  c)

Determines if the specified character is permissible in an identifier according to Java. True for characters with general categories "L" (letters), "Nl" (letter numbers), "Nd" (decimal digits), "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and u_isIDIgnorable(c).

Same as java.lang.Character.isUnicodeIdentifierPart(). Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) except that Unicode recommends to ignore Cf which is less than u_isIDIgnorable(c).

Parameters
cthe code point to be tested
Returns
true if the code point may occur in an identifier according to Java
See also
UCHAR_ID_CONTINUE
u_isIDStart
u_isIDIgnorable @stable ICU 2.0

Definition at line 319 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, U_GC_MC_MASK, U_GC_MN_MASK, U_GC_ND_MASK, U_GC_NL_MASK, U_GC_PC_MASK, and u_isIDIgnorable.

◆ u_isIDStart_68()

UBool u_isIDStart_68 ( UChar32  c)

Determines if the specified character is permissible as the first character in an identifier according to Unicode (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). True for characters with general categories "L" (letters) and "Nl" (letter numbers).

Same as java.lang.Character.isUnicodeIdentifierStart(). Same as UCHAR_ID_START

Parameters
cthe code point to be tested
Returns
true if the code point may start an identifier
See also
UCHAR_ID_START
u_isalpha
u_isIDPart @stable ICU 2.0

Definition at line 309 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, and U_GC_NL_MASK.

◆ u_isISOControl_68()

UBool u_isISOControl_68 ( UChar32  c)

Determines whether the specified code point is an ISO control code. True for U+0000..U+001f and U+007f..U+009f (general category "Cc").

Same as java.lang.Character.isISOControl().

Parameters
cthe code point to be tested
Returns
true if the code point is an ISO control code
See also
u_iscntrl @stable ICU 2.6

Definition at line 191 of file uchar.cpp.

References c.

◆ u_isJavaIDPart_68()

UBool u_isJavaIDPart_68 ( UChar32  c)

Determines if the specified character is permissible in a Java identifier. In addition to u_isIDPart(c), true for characters with general category "Sc" (currency symbols).

Same as java.lang.Character.isJavaIdentifierPart().

Parameters
cthe code point to be tested
Returns
true if the code point may occur in a Java identifier
See also
u_isIDIgnorable
u_isJavaIDStart
u_isalpha
u_isdigit
u_isIDPart @stable ICU 2.0

Definition at line 355 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, U_GC_MC_MASK, U_GC_MN_MASK, U_GC_ND_MASK, U_GC_NL_MASK, U_GC_PC_MASK, U_GC_SC_MASK, and u_isIDIgnorable.

◆ u_isJavaIDStart_68()

UBool u_isJavaIDStart_68 ( UChar32  c)

Determines if the specified character is permissible as the first character in a Java identifier. In addition to u_isIDStart(c), true for characters with general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).

Same as java.lang.Character.isJavaIdentifierStart().

Parameters
cthe code point to be tested
Returns
true if the code point may start a Java identifier
See also
u_isJavaIDPart
u_isalpha
u_isIDStart @stable ICU 2.0

Definition at line 345 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, U_GC_L_MASK, U_GC_PC_MASK, and U_GC_SC_MASK.

◆ u_isJavaSpaceChar_68()

UBool u_isJavaSpaceChar_68 ( UChar32  c)

Determine if the specified code point is a space character according to Java. True for characters with general categories "Z" (separators), which does not include control codes (e.g., TAB or Line Feed).

Same as java.lang.Character.isSpaceChar().

Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.

Parameters
cthe code point to be tested
Returns
true if the code point is a space character according to Character.isSpaceChar()
See also
u_isspace
u_isWhitespace
u_isUWhiteSpace @stable ICU 2.6

Definition at line 212 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, and U_GC_Z_MASK.

◆ u_islower_68()

UBool u_islower_68 ( UChar32  c)

Determines whether the specified code point has the general category "Ll" (lowercase letter).

Same as java.lang.Character.isLowerCase().

This misses some characters that are also lowercase but have a different general category value. In order to include those, use UCHAR_LOWERCASE.

In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is an Ll lowercase letter
See also
UCHAR_LOWERCASE
u_isupper
u_istitle @stable ICU 2.0

Definition at line 90 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, and U_LOWERCASE_LETTER.

◆ u_isMirrored_68()

UBool u_isMirrored_68 ( UChar32  c)

Determines whether the code point has the Bidi_Mirrored property. This property is set for characters that are commonly used in Right-To-Left contexts and need to be displayed with a "mirrored" glyph.

Same as java.lang.Character.isMirrored(). Same as UCHAR_BIDI_MIRRORED

Parameters
cthe code point to be tested
Returns
true if the character has the Bidi_Mirrored property
See also
UCHAR_BIDI_MIRRORED @stable ICU 2.0

Definition at line 242 of file ubidi_props.cpp.

References c, and ubidi_isMirrored.

◆ u_isprint_68()

UBool u_isprint_68 ( UChar32  c)

Determines whether the specified code point is a printable character. True for general categories other than "C" (controls).

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a printable character
See also
UCHAR_DEFAULT_IGNORABLE_CODE_POINT
u_iscntrl @stable ICU 2.0

Definition at line 249 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, and U_GC_C_MASK.

◆ u_ispunct_68()

UBool u_ispunct_68 ( UChar32  c)

Determines whether the specified code point is a punctuation character. True for characters with general categories "P" (punctuation).

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a punctuation character

@stable ICU 2.6

Definition at line 301 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, and U_GC_P_MASK.

◆ u_isspace_68()

UBool u_isspace_68 ( UChar32  c)

Determines if the specified character is a space character or not.

Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe character to be tested
Returns
true if the character is a space character; false otherwise.
See also
u_isJavaSpaceChar
u_isWhitespace
u_isUWhiteSpace @stable ICU 2.0

Definition at line 205 of file uchar.cpp.

References c, CAT_MASK, GET_PROPS, IS_THAT_CONTROL_SPACE, and U_GC_Z_MASK.

◆ u_istitle_68()

UBool u_istitle_68 ( UChar32  c)

Determines whether the specified code point is a titlecase letter. True for general category "Lt" (titlecase letter).

Same as java.lang.Character.isTitleCase().

Parameters
cthe code point to be tested
Returns
true if the code point is an Lt titlecase letter
See also
u_isupper
u_islower
u_totitle @stable ICU 2.0

Definition at line 106 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, and U_TITLECASE_LETTER.

◆ u_isUAlphabetic_68()

UBool u_isUAlphabetic_68 ( UChar32  c)

Check if a code point has the Alphabetic Unicode property. Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). This is different from u_isalpha!

Parameters
cCode point to test
Returns
true if the code point has the Alphabetic Unicode property, false otherwise
See also
UCHAR_ALPHABETIC
u_isalpha
u_hasBinaryProperty @stable ICU 2.1

Definition at line 145 of file uchar.cpp.

References c, u_getUnicodeProperties, U_MASK, and UPROPS_ALPHABETIC.

◆ u_isULowercase_68()

UBool u_isULowercase_68 ( UChar32  c)

Check if a code point has the Lowercase Unicode property. Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). This is different from u_islower!

Parameters
cCode point to test
Returns
true if the code point has the Lowercase Unicode property, false otherwise
See also
UCHAR_LOWERCASE
u_islower
u_hasBinaryProperty @stable ICU 2.1

Definition at line 1531 of file ucase.cpp.

References c, ucase_getType, and UCASE_LOWER.

◆ u_isupper_68()

UBool u_isupper_68 ( UChar32  c)

Determines whether the specified code point has the general category "Lu" (uppercase letter).

Same as java.lang.Character.isUpperCase().

This misses some characters that are also uppercase but have a different general category value. In order to include those, use UCHAR_UPPERCASE.

In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is an Lu uppercase letter
See also
UCHAR_UPPERCASE
u_islower
u_istitle
u_tolower @stable ICU 2.0

Definition at line 98 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, and U_UPPERCASE_LETTER.

◆ u_isUUppercase_68()

UBool u_isUUppercase_68 ( UChar32  c)

Check if a code point has the Uppercase Unicode property. Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). This is different from u_isupper!

Parameters
cCode point to test
Returns
true if the code point has the Uppercase Unicode property, false otherwise
See also
UCHAR_UPPERCASE
u_isupper
u_hasBinaryProperty @stable ICU 2.1

Definition at line 1536 of file ucase.cpp.

References c, ucase_getType, and UCASE_UPPER.

◆ u_isUWhiteSpace_68()

UBool u_isUWhiteSpace_68 ( UChar32  c)

Check if a code point has the White_Space Unicode property. Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). This is different from both u_isspace and u_isWhitespace!

Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.

Parameters
cCode point to test
Returns
true if the code point has the White_Space Unicode property, false otherwise.
See also
UCHAR_WHITE_SPACE
u_isWhitespace
u_isspace
u_isJavaSpaceChar
u_hasBinaryProperty @stable ICU 2.1

Definition at line 243 of file uchar.cpp.

References c, u_getUnicodeProperties, U_MASK, and UPROPS_WHITE_SPACE.

◆ u_isWhitespace_68()

UBool u_isWhitespace_68 ( UChar32  c)

Determines if the specified code point is a whitespace character according to Java/ICU. A character is considered to be a Java whitespace character if and only if it satisfies one of the following criteria:

  • It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
  • It is U+0009 HORIZONTAL TABULATION.
  • It is U+000A LINE FEED.
  • It is U+000B VERTICAL TABULATION.
  • It is U+000C FORM FEED.
  • It is U+000D CARRIAGE RETURN.
  • It is U+001C FILE SEPARATOR.
  • It is U+001D GROUP SEPARATOR.
  • It is U+001E RECORD SEPARATOR.
  • It is U+001F UNIT SEPARATOR.

This API tries to sync with the semantics of Java's java.lang.Character.isWhitespace(), but it may not return the exact same results because of the Unicode version difference.

Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs) to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false. See http://www.unicode.org/versions/Unicode4.0.1/

Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.

Parameters
cthe code point to be tested
Returns
true if the code point is a whitespace character according to Java/ICU
See also
u_isspace
u_isJavaSpaceChar
u_isUWhiteSpace @stable ICU 2.0

Definition at line 220 of file uchar.cpp.

References c, CAT_MASK, FIGURESP, GET_PROPS, IS_THAT_ASCII_CONTROL_SPACE, NBSP, NNBSP, and U_GC_Z_MASK.

◆ u_isxdigit_68()

UBool u_isxdigit_68 ( UChar32  c)

Determines whether the specified code point is a hexadecimal digit. This is equivalent to u_digit(c, 16)>=0. True for characters with general category "Nd" (decimal digit numbers) as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. (That is, for letters with code points 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)

In order to narrow the definition of hexadecimal digits to only ASCII characters, use (c<=0x7f && u_isxdigit(c)).

This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.

Parameters
cthe code point to be tested
Returns
true if the code point is a hexadecimal digit

@stable ICU 2.6

Definition at line 121 of file uchar.cpp.

References c, GET_CATEGORY, GET_PROPS, TRUE, and U_DECIMAL_DIGIT_NUMBER.

◆ u_tolower_68()

UChar32 u_tolower_68 ( UChar32  c)

The given character is mapped to its lowercase equivalent according to UnicodeData.txt; if the character has no lowercase equivalent, the character itself is returned.

Same as java.lang.Character.toLowerCase().

This function only returns the simple, single-code point case mapping. Full case mappings should be used whenever possible because they produce better results by working on whole strings. They take into account the string context and the language and can map to a result string with a different length as appropriate. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class. See also the User Guide chapter on C/POSIX migration: http://icu-project.org/userguide/posix.html#case_mappings

Parameters
cthe code point to be mapped
Returns
the Simple_Lowercase_Mapping of the code point, if any; otherwise the code point itself. @stable ICU 2.0

Definition at line 1542 of file ucase.cpp.

References c, and ucase_tolower.

◆ u_totitle_68()

UChar32 u_totitle_68 ( UChar32  c)

The given character is mapped to its titlecase equivalent according to UnicodeData.txt; if none is defined, the character itself is returned.

Same as java.lang.Character.toTitleCase().

This function only returns the simple, single-code point case mapping. Full case mappings should be used whenever possible because they produce better results by working on whole strings. They take into account the string context and the language and can map to a result string with a different length as appropriate. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class. See also the User Guide chapter on C/POSIX migration: http://icu-project.org/userguide/posix.html#case_mappings

Parameters
cthe code point to be mapped
Returns
the Simple_Titlecase_Mapping of the code point, if any; otherwise the code point itself. @stable ICU 2.0

Definition at line 1554 of file ucase.cpp.

References c, and ucase_totitle.

◆ u_toupper_68()

UChar32 u_toupper_68 ( UChar32  c)

The given character is mapped to its uppercase equivalent according to UnicodeData.txt; if the character has no uppercase equivalent, the character itself is returned.

Same as java.lang.Character.toUpperCase().

This function only returns the simple, single-code point case mapping. Full case mappings should be used whenever possible because they produce better results by working on whole strings. They take into account the string context and the language and can map to a result string with a different length as appropriate. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class. See also the User Guide chapter on C/POSIX migration: http://icu-project.org/userguide/posix.html#case_mappings

Parameters
cthe code point to be mapped
Returns
the Simple_Uppercase_Mapping of the code point, if any; otherwise the code point itself. @stable ICU 2.0

Definition at line 1548 of file ucase.cpp.

References c, and ucase_toupper.

◆ ublock_getCode_68()

UBlockCode ublock_getCode_68 ( UChar32  c)

Returns the Unicode allocation block that contains the character.

Parameters
cthe code point to be tested
Returns
the block value (UBlockCode) for c
See also
UBlockCode @stable ICU 2.0

Definition at line 644 of file uchar.cpp.

References c, u_getUnicodeProperties, UPROPS_BLOCK_MASK, and UPROPS_BLOCK_SHIFT.