Main Page   Class Hierarchy   Alphabetical List   Compound List   File List   Compound Members   File Members   Search  

uchar.h File Reference

C API: Unicode Char. More...

#include "unicode/utypes.h"

Go to the source code of this file.

Defines

#define U_UNICODE_VERSION   "3.2"
 Unicode version number, default for the current ICU version. More...

#define UCHAR_MIN_VALUE   0
 The lowest Unicode code point value. More...

#define UCHAR_MAX_VALUE   0x10ffff
 The highest Unicode code point value (scalar value) according to The Unicode Standard. More...

#define U_MASK(x)   ((uint32_t)1<<(x))
 Get a single-bit bit set (a flag) from a bit number 0..31. More...

#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. More...

#define U_GC_LU_MASK   U_MASK(U_UPPERCASE_LETTER)
 Mask constant for a UCharCategory. More...

#define U_GC_LL_MASK   U_MASK(U_LOWERCASE_LETTER)
 Mask constant for a UCharCategory. More...

#define U_GC_LT_MASK   U_MASK(U_TITLECASE_LETTER)
 Mask constant for a UCharCategory. More...

#define U_GC_LM_MASK   U_MASK(U_MODIFIER_LETTER)
 Mask constant for a UCharCategory. More...

#define U_GC_LO_MASK   U_MASK(U_OTHER_LETTER)
 Mask constant for a UCharCategory. More...

#define U_GC_MN_MASK   U_MASK(U_NON_SPACING_MARK)
 Mask constant for a UCharCategory. More...

#define U_GC_ME_MASK   U_MASK(U_ENCLOSING_MARK)
 Mask constant for a UCharCategory. More...

#define U_GC_MC_MASK   U_MASK(U_COMBINING_SPACING_MARK)
 Mask constant for a UCharCategory. More...

#define U_GC_ND_MASK   U_MASK(U_DECIMAL_DIGIT_NUMBER)
 Mask constant for a UCharCategory. More...

#define U_GC_NL_MASK   U_MASK(U_LETTER_NUMBER)
 Mask constant for a UCharCategory. More...

#define U_GC_NO_MASK   U_MASK(U_OTHER_NUMBER)
 Mask constant for a UCharCategory. More...

#define U_GC_ZS_MASK   U_MASK(U_SPACE_SEPARATOR)
 Mask constant for a UCharCategory. More...

#define U_GC_ZL_MASK   U_MASK(U_LINE_SEPARATOR)
 Mask constant for a UCharCategory. More...

#define U_GC_ZP_MASK   U_MASK(U_PARAGRAPH_SEPARATOR)
 Mask constant for a UCharCategory. More...

#define U_GC_CC_MASK   U_MASK(U_CONTROL_CHAR)
 Mask constant for a UCharCategory. More...

#define U_GC_CF_MASK   U_MASK(U_FORMAT_CHAR)
 Mask constant for a UCharCategory. More...

#define U_GC_CO_MASK   U_MASK(U_PRIVATE_USE_CHAR)
 Mask constant for a UCharCategory. More...

#define U_GC_CS_MASK   U_MASK(U_SURROGATE)
 Mask constant for a UCharCategory. More...

#define U_GC_PD_MASK   U_MASK(U_DASH_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_PS_MASK   U_MASK(U_START_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_PE_MASK   U_MASK(U_END_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_PC_MASK   U_MASK(U_CONNECTOR_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_PO_MASK   U_MASK(U_OTHER_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_SM_MASK   U_MASK(U_MATH_SYMBOL)
 Mask constant for a UCharCategory. More...

#define U_GC_SC_MASK   U_MASK(U_CURRENCY_SYMBOL)
 Mask constant for a UCharCategory. More...

#define U_GC_SK_MASK   U_MASK(U_MODIFIER_SYMBOL)
 Mask constant for a UCharCategory. More...

#define U_GC_SO_MASK   U_MASK(U_OTHER_SYMBOL)
 Mask constant for a UCharCategory. More...

#define U_GC_PI_MASK   U_MASK(U_INITIAL_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#define U_GC_PF_MASK   U_MASK(U_FINAL_PUNCTUATION)
 Mask constant for a UCharCategory. More...

#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)
 Mask constant for multiple UCharCategory bits (L Letters). More...

#define U_GC_LC_MASK   (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
 Mask constant for multiple UCharCategory bits (LC Cased Letters). More...

#define U_GC_M_MASK   (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
 Mask constant for multiple UCharCategory bits (M Marks). More...

#define U_GC_N_MASK   (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
 Mask constant for multiple UCharCategory bits (N Numbers). More...

#define U_GC_Z_MASK   (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
 Mask constant for multiple UCharCategory bits (Z Separators). More...

#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)
 Mask constant for multiple UCharCategory bits (C Others). More...

#define U_GC_P_MASK
 Mask constant for multiple UCharCategory bits (P Punctuation). More...

#define U_GC_S_MASK   (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
 Mask constant for multiple UCharCategory bits (S Symbols). More...

#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. More...

#define U_GET_GC_MASK(c)   U_MASK(u_charType(c))
 Get a single-bit bit set for the general category of a character. More...

#define U_FOLD_CASE_DEFAULT   0
 Option value for case folding: use default mappings defined in CaseFolding.txt. More...

#define U_FOLD_CASE_EXCLUDE_SPECIAL_I   1
 Option value for case folding:. More...


Typedefs

typedef enum UProperty UProperty
 Selection constants for Unicode properties. More...

typedef enum UCharCategory UCharCategory
 Data for enumerated Unicode general category types. More...

typedef enum UCharDirection UCharDirection
 This specifies the language directional property of a character set. More...

typedef enum UBlockCode UBlockCode
typedef enum UCellWidth UCellWidth
 C typedef for struct UCellWidth. More...

typedef enum UEastAsianWidth UEastAsianWidth
 East Asian Width constants. More...

typedef enum UCharNameChoice UCharNameChoice
 Selector constants for u_charName(). More...

typedef enum UPropertyNameChoice UPropertyNameChoice
 Selector constants for u_getPropertyName() and u_getPropertyValueName(). More...

typedef enum UDecompositionType UDecompositionType
 Decomposition Type constants. More...

typedef enum UJoiningType UJoiningType
 Joining Type constants. More...

typedef enum UJoiningGroup UJoiningGroup
 Joining Group constants. More...

typedef enum ULineBreak ULineBreak
 Line Break constants. More...

typedef enum UNumericType UNumericType
 Numeric Type constants. More...

typedef UBool U_CALLCONV 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"). More...

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. More...


Enumerations

enum  UProperty {
  UCHAR_ALPHABETIC = 0, UCHAR_BINARY_START = UCHAR_ALPHABETIC, UCHAR_ASCII_HEX_DIGIT, UCHAR_BIDI_CONTROL,
  UCHAR_BIDI_MIRRORED, UCHAR_DASH, UCHAR_DEFAULT_IGNORABLE_CODE_POINT, UCHAR_DEPRECATED,
  UCHAR_DIACRITIC, UCHAR_EXTENDER, UCHAR_FULL_COMPOSITION_EXCLUSION, UCHAR_GRAPHEME_BASE,
  UCHAR_GRAPHEME_EXTEND, UCHAR_GRAPHEME_LINK, UCHAR_HEX_DIGIT, UCHAR_HYPHEN,
  UCHAR_ID_CONTINUE, UCHAR_ID_START, UCHAR_IDEOGRAPHIC, UCHAR_IDS_BINARY_OPERATOR,
  UCHAR_IDS_TRINARY_OPERATOR, UCHAR_JOIN_CONTROL, UCHAR_LOGICAL_ORDER_EXCEPTION, UCHAR_LOWERCASE,
  UCHAR_MATH, UCHAR_NONCHARACTER_CODE_POINT, UCHAR_QUOTATION_MARK, UCHAR_RADICAL,
  UCHAR_SOFT_DOTTED, UCHAR_TERMINAL_PUNCTUATION, UCHAR_UNIFIED_IDEOGRAPH, UCHAR_UPPERCASE,
  UCHAR_WHITE_SPACE, UCHAR_XID_CONTINUE, UCHAR_XID_START, UCHAR_BINARY_LIMIT,
  UCHAR_BIDI_CLASS = 0x1000, UCHAR_INT_START = UCHAR_BIDI_CLASS, UCHAR_BLOCK, UCHAR_CANONICAL_COMBINING_CLASS,
  UCHAR_DECOMPOSITION_TYPE, UCHAR_EAST_ASIAN_WIDTH, UCHAR_GENERAL_CATEGORY, UCHAR_JOINING_GROUP,
  UCHAR_JOINING_TYPE, UCHAR_LINE_BREAK, UCHAR_NUMERIC_TYPE, UCHAR_SCRIPT,
  UCHAR_INT_LIMIT, UCHAR_GENERAL_CATEGORY_MASK = 0x2000, UCHAR_MASK_START = UCHAR_GENERAL_CATEGORY_MASK, UCHAR_MASK_LIMIT,
  UCHAR_NUMERIC_VALUE = 0x3000, UCHAR_DOUBLE_START = UCHAR_NUMERIC_VALUE, UCHAR_DOUBLE_LIMIT, UCHAR_AGE = 0x4000,
  UCHAR_STRING_START = UCHAR_AGE, UCHAR_BIDI_MIRRORING_GLYPH, UCHAR_CASE_FOLDING, UCHAR_ISO_COMMENT,
  UCHAR_LOWERCASE_MAPPING, UCHAR_NAME, UCHAR_SIMPLE_CASE_FOLDING, UCHAR_SIMPLE_LOWERCASE_MAPPING,
  UCHAR_SIMPLE_TITLECASE_MAPPING, UCHAR_SIMPLE_UPPERCASE_MAPPING, UCHAR_TITLECASE_MAPPING, UCHAR_UNICODE_1_NAME,
  UCHAR_UPPERCASE_MAPPING, UCHAR_STRING_LIMIT, UCHAR_INVALID_CODE = -1
}
 Selection constants for Unicode properties. More...

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
}
 Data for enumerated Unicode general category types. More...

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_CHAR_DIRECTION_COUNT
}
 This specifies the language directional property of a character set. More...

enum  UBlockCode {
  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 = 78, UBLOCK_PRIVATE_USE_AREA = UBLOCK_PRIVATE_USE, 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_SUPPLEMENTARY = 97, 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_COUNT,
  UBLOCK_INVALID_CODE = -1
}
 Constants for Unicode blocks, generated from Unicode Data file Blocks.txt These are the same values as Unicode::EUnicodeScript. More...

enum  UCellWidth {
  U_ZERO_WIDTH = 0, U_HALF_WIDTH = 1, U_FULL_WIDTH = 2, U_NEUTRAL_WIDTH = 3,
  U_CELL_WIDTH_COUNT
}
 Values returned by the u_getCellWidth() function. More...

enum  UEastAsianWidth {
  U_EA_NEUTRAL, U_EA_AMBIGUOUS, U_EA_HALFWIDTH, U_EA_FULLWIDTH,
  U_EA_NARROW, U_EA_WIDE, U_EA_COUNT
}
 East Asian Width constants. More...

enum  UCharNameChoice { U_UNICODE_CHAR_NAME, U_UNICODE_10_CHAR_NAME, U_EXTENDED_CHAR_NAME, U_CHAR_NAME_CHOICE_COUNT }
 Selector constants for u_charName(). More...

enum  UPropertyNameChoice { U_SHORT_PROPERTY_NAME, U_LONG_PROPERTY_NAME, U_PROPERTY_NAME_CHOICE_COUNT }
 Selector constants for u_getPropertyName() and u_getPropertyValueName(). More...

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
}
 Decomposition Type constants. More...

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
}
 Joining Type constants. More...

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_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_COUNT
}
 Joining Group constants. More...

enum  ULineBreak {
  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_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_COUNT
}
 Line Break constants. More...

enum  UNumericType {
  U_NT_NONE, U_NT_DECIMAL, U_NT_DIGIT, U_NT_NUMERIC,
  U_NT_COUNT
}
 Numeric Type constants. More...


Functions

UBool u_hasBinaryProperty (UChar32 c, UProperty which)
 Check a binary Unicode property for a code point. More...

UBool u_isUAlphabetic (UChar32 c)
 Check if a code point has the Alphabetic Unicode property. More...

UBool u_isULowercase (UChar32 c)
 Check if a code point has the Lowercase Unicode property. More...

UBool u_isUUppercase (UChar32 c)
 Check if a code point has the Uppercase Unicode property. More...

UBool u_isUWhiteSpace (UChar32 c)
 Check if a code point has the White_Space Unicode property. More...

int32_t u_getIntPropertyValue (UChar32 c, UProperty which)
 Get the property value for an enumerated or integer Unicode property for a code point. More...

int32_t u_getIntPropertyMinValue (UProperty which)
 Get the minimum value for an enumerated/integer/binary Unicode property. More...

int32_t u_getIntPropertyMaxValue (UProperty which)
 Get the maximum value for an enumerated/integer/binary Unicode property. More...

double u_getNumericValue (UChar32 c)
 Get the numeric value for a Unicode code point as defined in the Unicode Character Database. More...

UBool u_islower (UChar32 c)
 Determines whether the specified UChar is a lowercase character according to UnicodeData.txt. More...

UBool u_isupper (UChar32 c)
 Determines whether the specified character is an uppercase character according to UnicodeData.txt. More...

UBool u_istitle (UChar32 c)
 Determines whether the specified character is a titlecase character according to UnicodeData.txt. More...

UBool u_isdigit (UChar32 c)
 Determines whether the specified character is a digit according to UnicodeData.txt. More...

UBool u_isalnum (UChar32 c)
 Determines whether the specified character is an alphanumeric character (letter or digit)according to UnicodeData.txt. More...

UBool u_isdefined (UChar32 c)
 Determines whether the specified numeric value is actually a defined character according to UnicodeData.txt. More...

UBool u_isalpha (UChar32 c)
 Determines whether the specified character is a letter according to UnicodeData.txt. More...

UBool u_isspace (UChar32 c)
 Determines if the specified character is a space character or not. More...

UBool u_isWhitespace (UChar32 c)
 Determines if the specified character is white space according to ICU. More...

UBool u_iscntrl (UChar32 c)
 Determines whether the specified character is a control character or not. More...

UBool u_isprint (UChar32 c)
 Determines whether the specified character is a printable character according to UnicodeData.txt. More...

UBool u_isbase (UChar32 c)
 Determines whether the specified character is of the base form according to UnicodeData.txt. More...

UCharDirection u_charDirection (UChar32 c)
 Returns the linguistic direction property of a character. More...

UBool u_isMirrored (UChar32 c)
 Determines whether the character has the "mirrored" property. More...

UChar32 u_charMirror (UChar32 c)
 Maps the specified character to a "mirror-image" character. More...

uint16_t u_charCellWidth (UChar32 c)
 Obsolete because the "cell width" functions and implementation are out of date compared with Unicode Standard Annex #11. More...

int8_t u_charType (UChar32 c)
 Returns a value indicating a character category. More...

void u_enumCharTypes (UCharEnumTypeRange *enumRange, const void *context)
 Enumerate efficiently all code points with their Unicode general categories. More...

uint8_t u_getCombiningClass (UChar32 c)
 Returns the combining class of the code point as specified in UnicodeData.txt. More...

int32_t u_charDigitValue (UChar32 c)
 Returns the decimal numeric value of a digit character. More...

UBlockCode ublock_getCode (UChar32 ch)
 Returns the Unicode allocation block that contains the character. More...

int32_t u_charName (UChar32 code, UCharNameChoice nameChoice, char *buffer, int32_t bufferLength, UErrorCode *pErrorCode)
 Retrieve the name of a Unicode character. More...

int32_t u_getISOComment (UChar32 c, char *dest, int32_t destCapacity, UErrorCode *pErrorCode)
 Get the ISO 10646 comment for a character. More...

UChar32 u_charFromName (UCharNameChoice nameChoice, const char *name, UErrorCode *pErrorCode)
 Find a Unicode character by its name and return its code point value. More...

void u_enumCharNames (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. More...

const char * u_getPropertyName (UProperty property, UPropertyNameChoice nameChoice)
 Return the Unicode name for a given property, as given in the Unicode database file PropertyAliases.txt. More...

UProperty u_getPropertyEnum (const char *alias)
 Return the UProperty enum for a given property name, as specified in the Unicode database file PropertyAliases.txt. More...

const char * u_getPropertyValueName (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. More...

int32_t u_getPropertyValueEnum (UProperty property, const char *alias)
 Return the property value integer for a given value name, as specified in the Unicode database file PropertyValueAliases.txt. More...

UBool u_isIDStart (UChar32 c)
 A convenience method for determining if a Unicode character is allowed to start in a Unicode identifier. More...

UBool u_isIDPart (UChar32 c)
 A convenience method for determining if a Unicode character may be part of a Unicode identifier other than the starting character. More...

UBool u_isIDIgnorable (UChar32 c)
 A convenience method for determining if a Unicode character should be regarded as an ignorable character in a Unicode identifier. More...

UBool u_isJavaIDStart (UChar32 c)
 A convenience method for determining if a Unicode character is allowed as the first character in a Java identifier. More...

UBool u_isJavaIDPart (UChar32 c)
 A convenience method for determining if a Unicode character may be part of a Java identifier other than the starting character. More...

UChar32 u_tolower (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. More...

UChar32 u_toupper (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. More...

UChar32 u_totitle (UChar32 c)
 The given character is mapped to its titlecase equivalent according to UnicodeData.txt. More...

UChar32 u_foldCase (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. More...

int32_t u_digit (UChar32 ch, int8_t radix)
 Returns the numeric value of the character ch in the specified radix. More...

UChar32 u_forDigit (int32_t digit, int8_t radix)
 Determines the character representation for a specific digit in the specified radix. More...

void u_charAge (UChar32 c, UVersionInfo versionArray)
 Get the "age" of the code point. More...

void u_getUnicodeVersion (UVersionInfo info)
 Gets the Unicode version information. More...

int32_t u_getFC_NFKC_Closure (UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode)
 Get the FC_NFKC_Closure property string for a character. More...


Detailed Description

C API: Unicode Char.

Unicode C API

The Unicode C API allows you to query the properties associated with individual Unicode character values.

The Unicode character information, provided implicitly by the Unicode character encoding standard, includes information about the script (for example, symbols or control characters) to which the character belongs, as well as semantic information such as whether a character is a digit or uppercase, lowercase, or uncased.

Definition in file uchar.h.


Define Documentation

#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.

Stable:
ICU 2.0

Definition at line 73 of file uchar.h.

#define UCHAR_MIN_VALUE   0
 

The lowest Unicode code point value.

Code points are non-negative.

Stable:
ICU 2.0

Definition at line 65 of file uchar.h.

#define U_FOLD_CASE_DEFAULT   0
 

Option value for case folding: use default mappings defined in CaseFolding.txt.

Stable:
ICU 2.0

Definition at line 2438 of file uchar.h.

#define U_FOLD_CASE_EXCLUDE_SPECIAL_I   1
 

Option value for case folding:.

Use the modified set of mappings provided in CaseFolding.txt to handle dotted I and dotless i appropriately for Turkic languages (tr, az).

Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that are to be included for default mappings and excluded for the Turkic-specific mappings.

Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that are to be excluded for default mappings and included for the Turkic-specific mappings.

Stable:
ICU 2.0

Definition at line 2456 of file uchar.h.

#define U_GC_CC_MASK   U_MASK(U_CONTROL_CHAR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 479 of file uchar.h.

#define U_GC_CF_MASK   U_MASK(U_FORMAT_CHAR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 481 of file uchar.h.

#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
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 444 of file uchar.h.

#define U_GC_CO_MASK   U_MASK(U_PRIVATE_USE_CHAR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 483 of file uchar.h.

#define U_GC_CS_MASK   U_MASK(U_SURROGATE)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 485 of file uchar.h.

#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)
 

Mask constant for multiple UCharCategory bits (C Others).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 531 of file uchar.h.

#define U_GC_LC_MASK   (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)
 

Mask constant for multiple UCharCategory bits (LC Cased Letters).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 518 of file uchar.h.

#define U_GC_LL_MASK   U_MASK(U_LOWERCASE_LETTER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 449 of file uchar.h.

#define U_GC_LM_MASK   U_MASK(U_MODIFIER_LETTER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 453 of file uchar.h.

#define U_GC_LO_MASK   U_MASK(U_OTHER_LETTER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 455 of file uchar.h.

#define U_GC_LT_MASK   U_MASK(U_TITLECASE_LETTER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 451 of file uchar.h.

#define U_GC_LU_MASK   U_MASK(U_UPPERCASE_LETTER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 447 of file uchar.h.

#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)
 

Mask constant for multiple UCharCategory bits (L Letters).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 514 of file uchar.h.

#define U_GC_MC_MASK   U_MASK(U_COMBINING_SPACING_MARK)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 462 of file uchar.h.

#define U_GC_ME_MASK   U_MASK(U_ENCLOSING_MARK)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 460 of file uchar.h.

#define U_GC_MN_MASK   U_MASK(U_NON_SPACING_MARK)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 458 of file uchar.h.

#define U_GC_M_MASK   (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)
 

Mask constant for multiple UCharCategory bits (M Marks).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 522 of file uchar.h.

#define U_GC_ND_MASK   U_MASK(U_DECIMAL_DIGIT_NUMBER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 465 of file uchar.h.

#define U_GC_NL_MASK   U_MASK(U_LETTER_NUMBER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 467 of file uchar.h.

#define U_GC_NO_MASK   U_MASK(U_OTHER_NUMBER)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 469 of file uchar.h.

#define U_GC_N_MASK   (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)
 

Mask constant for multiple UCharCategory bits (N Numbers).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 525 of file uchar.h.

#define U_GC_PC_MASK   U_MASK(U_CONNECTOR_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 494 of file uchar.h.

#define U_GC_PD_MASK   U_MASK(U_DASH_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 488 of file uchar.h.

#define U_GC_PE_MASK   U_MASK(U_END_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 492 of file uchar.h.

#define U_GC_PF_MASK   U_MASK(U_FINAL_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 510 of file uchar.h.

#define U_GC_PI_MASK   U_MASK(U_INITIAL_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 508 of file uchar.h.

#define U_GC_PO_MASK   U_MASK(U_OTHER_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 496 of file uchar.h.

#define U_GC_PS_MASK   U_MASK(U_START_PUNCTUATION)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 490 of file uchar.h.

#define U_GC_P_MASK
 

Value:

Mask constant for multiple UCharCategory bits (P Punctuation).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 535 of file uchar.h.

#define U_GC_SC_MASK   U_MASK(U_CURRENCY_SYMBOL)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 501 of file uchar.h.

#define U_GC_SK_MASK   U_MASK(U_MODIFIER_SYMBOL)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 503 of file uchar.h.

#define U_GC_SM_MASK   U_MASK(U_MATH_SYMBOL)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 499 of file uchar.h.

#define U_GC_SO_MASK   U_MASK(U_OTHER_SYMBOL)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 505 of file uchar.h.

#define U_GC_S_MASK   (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)
 

Mask constant for multiple UCharCategory bits (S Symbols).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 540 of file uchar.h.

#define U_GC_ZL_MASK   U_MASK(U_LINE_SEPARATOR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 474 of file uchar.h.

#define U_GC_ZP_MASK   U_MASK(U_PARAGRAPH_SEPARATOR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 476 of file uchar.h.

#define U_GC_ZS_MASK   U_MASK(U_SPACE_SEPARATOR)
 

Mask constant for a UCharCategory.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 472 of file uchar.h.

#define U_GC_Z_MASK   (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)
 

Mask constant for multiple UCharCategory bits (Z Separators).

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 528 of file uchar.h.

#define U_GET_GC_MASK      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)).

See also:
u_charType , UCharCategory , U_GC_CN_MASK
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 1890 of file uchar.h.

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

Get a single-bit bit set (a flag) from a bit number 0..31.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

Definition at line 79 of file uchar.h.

#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
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

Definition at line 1574 of file uchar.h.

#define U_UNICODE_VERSION   "3.2"
 

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 42 of file uchar.h.


Typedef Documentation

typedef enum UBlockCode UBlockCode
 

Stable:
ICU 2.0

Definition at line 1125 of file uchar.h.

typedef enum UCellWidth UCellWidth
 

C typedef for struct UCellWidth.

Obsolete:
ICU 2.6. Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

Definition at line 1145 of file uchar.h.

typedef enum UCharCategory UCharCategory
 

Data for enumerated Unicode general category types.

See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .

Stable:
ICU 2.0

typedef enum UCharDirection UCharDirection
 

This specifies the language directional property of a character set.

Stable:
ICU 2.0

typedef UBool U_CALLCONV 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:
context  an opaque pointer, as passed into utrie_enum()
start  the first code point in a contiguous range with value
limit  one past the last code point in a contiguous range with value
type  the general category for all code points in [start..limit[
Returns:
FALSE to stop the enumeration
Draft:
This API has been introduced in ICU 2.1 @see UCharCategory @see u_enumCharTypes. It is still in draft state and may be modified in a future release.

Definition at line 1910 of file uchar.h.

typedef enum UCharNameChoice 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

typedef enum UDecompositionType UDecompositionType
 

Decomposition Type constants.

See also:
UCHAR_DECOMPOSITION_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

typedef enum UEastAsianWidth UEastAsianWidth
 

East Asian Width constants.

See also:
UCHAR_EAST_ASIAN_WIDTH , u_getIntPropertyValue
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

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:
context  The context pointer that was passed to u_enumCharNames().
code  The Unicode code point for the character with this name.
nameChoice  Selector for which kind of names is enumerated.
name  The character's name, zero-terminated.
length  The 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 2072 of file uchar.h.

typedef enum UJoiningGroup UJoiningGroup
 

Joining Group constants.

See also:
UCHAR_JOINING_GROUP
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

typedef enum UJoiningType UJoiningType
 

Joining Type constants.

See also:
UCHAR_JOINING_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

typedef enum ULineBreak ULineBreak
 

Line Break constants.

See also:
UCHAR_LINE_BREAK
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

typedef enum UNumericType UNumericType
 

Numeric Type constants.

See also:
UCHAR_NUMERIC_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

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 http://www.unicode.org/ . 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. Check u_getUnicodeVersion to be sure.

See also:
u_hasBinaryProperty , u_getIntPropertyValue , u_getUnicodeVersion
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

typedef enum UPropertyNameChoice 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()
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.


Enumeration Type Documentation

enum UBlockCode
 

Constants for Unicode blocks, generated from Unicode Data file Blocks.txt These are the same values as Unicode::EUnicodeScript.

Stable:
ICU 2.0
Enumeration values:
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  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_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_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_SUPPLEMENTARY 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_TAGALOG 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_HANUNOO 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_BUHID 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_TAGBANWA 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_SUPPLEMENTAL_ARROWS_A 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_SUPPLEMENTAL_ARROWS_B 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_KATAKANA_PHONETIC_EXTENSIONS 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_VARIATION_SELECTORS 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B 
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UBLOCK_COUNT 
Stable:
ICU 2.0
UBLOCK_INVALID_CODE 
Stable:
ICU 2.0

Definition at line 596 of file uchar.h.

enum UCellWidth
 

Values returned by the u_getCellWidth() function.

Obsolete:
ICU 2.6. Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.
Enumeration values:
U_ZERO_WIDTH 
Obsolete:
ICU 2.6.

Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

U_HALF_WIDTH 
Obsolete:
ICU 2.6.

Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

U_FULL_WIDTH 
Obsolete:
ICU 2.6.

Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

U_NEUTRAL_WIDTH 
Obsolete:
ICU 2.6.

Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

U_CELL_WIDTH_COUNT 
Obsolete:
ICU 2.6.

Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

Definition at line 1131 of file uchar.h.

enum UCharCategory
 

Data for enumerated Unicode general category types.

See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .

Stable:
ICU 2.0
Enumeration values:
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.

Stable:
ICU 2.0

Definition at line 360 of file uchar.h.

enum UCharDirection
 

This specifies the language directional property of a character set.

Stable:
ICU 2.0
Enumeration values:
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_CHAR_DIRECTION_COUNT 
Stable:
ICU 2.0

Definition at line 546 of file uchar.h.

enum 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
Enumeration values:
U_UNICODE_CHAR_NAME 
U_UNICODE_10_CHAR_NAME 
U_EXTENDED_CHAR_NAME 
U_CHAR_NAME_CHOICE_COUNT 

Definition at line 1179 of file uchar.h.

enum UDecompositionType
 

Decomposition Type constants.

See also:
UCHAR_DECOMPOSITION_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
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 

Definition at line 1211 of file uchar.h.

enum UEastAsianWidth
 

East Asian Width constants.

See also:
UCHAR_EAST_ASIAN_WIDTH , u_getIntPropertyValue
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
U_EA_NEUTRAL 
U_EA_AMBIGUOUS 
U_EA_HALFWIDTH 
U_EA_FULLWIDTH 
U_EA_NARROW 
U_EA_WIDE 
U_EA_COUNT 

Definition at line 1154 of file uchar.h.

enum UJoiningGroup
 

Joining Group constants.

See also:
UCHAR_JOINING_GROUP
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
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_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_COUNT 

Definition at line 1255 of file uchar.h.

enum UJoiningType
 

Joining Type constants.

See also:
UCHAR_JOINING_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
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 

Definition at line 1239 of file uchar.h.

enum ULineBreak
 

Line Break constants.

See also:
UCHAR_LINE_BREAK
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
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_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_COUNT 

Definition at line 1316 of file uchar.h.

enum UNumericType
 

Numeric Type constants.

See also:
UCHAR_NUMERIC_TYPE
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
Enumeration values:
U_NT_NONE 
U_NT_DECIMAL 
U_NT_DIGIT 
U_NT_NUMERIC 
U_NT_COUNT 

Definition at line 1355 of file uchar.h.

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 http://www.unicode.org/ . 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. Check u_getUnicodeVersion to be sure.

See also:
u_hasBinaryProperty , u_getIntPropertyValue , u_getUnicodeVersion
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
Enumeration values:
UCHAR_ALPHABETIC  Binary property Alphabetic.

Same as u_isUAlphabetic, different from u_isalpha. Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_BINARY_START  First constant for binary Unicode properties.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_ASCII_HEX_DIGIT  Binary property ASCII_Hex_Digit.

0-9 A-F a-f

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_BIDI_CONTROL  Binary property Bidi_Control.

Format controls which have specific functions in the Bidi Algorithm.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_BIDI_MIRRORED  Binary property Bidi_Mirrored.

Characters that may change display in RTL text. Same as u_isMirrored. See Bidi Algorithm, UTR 9.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_DASH  Binary property Dash.

Variations of dashes.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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)

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_DEPRECATED  Binary property Deprecated (new in Unicode 3.2).

The usage of deprecated characters is strongly discouraged.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_DIACRITIC  Binary property Diacritic.

Characters that linguistically modify the meaning of another character to which they apply.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_EXTENDER  Binary property Extender.

Extend the value or shape of a preceding alphabetic character, e.g., length and iteration marks.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_FULL_COMPOSITION_EXCLUSION  Binary property Full_Composition_Exclusion.

CompositionExclusions.txt+Singleton Decompositions+ Non-Starter Decompositions.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_GRAPHEME_LINK  Binary property Grapheme_Link (new in Unicode 3.2).

For programmatic determination of grapheme cluster boundaries.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_HEX_DIGIT  Binary property Hex_Digit.

Characters commonly used for hexadecimal numbers.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_HYPHEN  Binary property Hyphen.

Dashes used to mark connections between pieces of words, plus the Katakana middle dot.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_ID_CONTINUE  Binary property ID_Continue.

Characters that can continue an identifier. ID_Start+Mn+Mc+Nd+Pc

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_ID_START  Binary property ID_Start.

Characters that can start an identifier. Lu+Ll+Lt+Lm+Lo+Nl

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_IDEOGRAPHIC  Binary property Ideographic.

CJKV ideographs.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_IDS_BINARY_OPERATOR  Binary property IDS_Binary_Operator (new in Unicode 3.2).

For programmatic determination of Ideographic Description Sequences.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_IDS_TRINARY_OPERATOR  Binary property IDS_Trinary_Operator (new in Unicode 3.2).

For programmatic determination of Ideographic Description Sequences.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_JOIN_CONTROL  Binary property Join_Control.

Format controls for cursive joining and ligation.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_LOWERCASE  Binary property Lowercase.

Same as u_isULowercase, different from u_islower. Ll+Other_Lowercase

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_MATH  Binary property Math.

Sm+Other_Math

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_NONCHARACTER_CODE_POINT  Binary property Noncharacter_Code_Point.

Code points that are explicitly defined as illegal for the encoding of characters.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_QUOTATION_MARK  Binary property Quotation_Mark.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_RADICAL  Binary property Radical (new in Unicode 3.2).

For programmatic determination of Ideographic Description Sequences.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_TERMINAL_PUNCTUATION  Binary property Terminal_Punctuation.

Punctuation characters that generally mark the end of textual units.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_UNIFIED_IDEOGRAPH  Binary property Unified_Ideograph (new in Unicode 3.2).

For programmatic determination of Ideographic Description Sequences.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_UPPERCASE  Binary property Uppercase.

Same as u_isUUppercase, different from u_isupper. Lu+Other_Uppercase

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
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

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_XID_CONTINUE  Binary property XID_Continue.

ID_Continue modified to allow closure under normalization forms NFKC and NFKD.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_XID_START  Binary property XID_Start.

ID_Start modified to allow closure under normalization forms NFKC and NFKD.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_BINARY_LIMIT  One more than the last constant for binary Unicode properties.

Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.
UCHAR_BIDI_CLASS  Enumerated property Bidi_Class.

Same as u_charDirection, returns UCharDirection values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_INT_START  First constant for enumerated/integer Unicode properties.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_BLOCK  Enumerated property Block.

Same as ublock_getCode, returns UBlockCode values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_CANONICAL_COMBINING_CLASS  Enumerated property Canonical_Combining_Class.

Same as u_getCombiningClass, returns 8-bit numeric values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_DECOMPOSITION_TYPE  Enumerated property Decomposition_Type.

Returns UDecompositionType values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_EAST_ASIAN_WIDTH  Enumerated property East_Asian_Width.

See http://www.unicode.org/reports/tr11/ Returns UEastAsianWidth values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_GENERAL_CATEGORY  Enumerated property General_Category.

Same as u_charType, returns UCharCategory values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_JOINING_GROUP  Enumerated property Joining_Group.

Returns UJoiningGroup values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_JOINING_TYPE  Enumerated property Joining_Type.

Returns UJoiningType values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_LINE_BREAK  Enumerated property Line_Break.

Returns ULineBreak values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_NUMERIC_TYPE  Enumerated property Numeric_Type.

Returns UNumericType values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_SCRIPT  Enumerated property Script.

Same as uscript_getScript, returns UScriptCode values.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_INT_LIMIT  One more than the last constant for enumerated/integer Unicode properties.

Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.
UCHAR_GENERAL_CATEGORY_MASK  Enumerated property General_Category, 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.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_MASK_START  First constant for bit-mask Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_MASK_LIMIT  One more than the last constant for bit-mask Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_NUMERIC_VALUE  Double property Numeric_Value.

Corresponds to u_getNumericValue.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_DOUBLE_START  First constant for double Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_DOUBLE_LIMIT  One more than the last constant for double Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_AGE  String property Age.

Corresponds to u_charAge.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_STRING_START  First constant for string Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_BIDI_MIRRORING_GLYPH  String property Bidi_Mirroring_Glyph.

Corresponds to u_charMirror.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_CASE_FOLDING  String property Case_Folding.

Corresponds to u_strFoldCase in ustring.h.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_ISO_COMMENT  String property ISO_Comment.

Corresponds to u_getISOComment.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_LOWERCASE_MAPPING  String property Lowercase_Mapping.

Corresponds to u_strToLower in ustring.h.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_NAME  String property Name.

Corresponds to u_charName.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_SIMPLE_CASE_FOLDING  String property Simple_Case_Folding.

Corresponds to u_foldCase.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_SIMPLE_LOWERCASE_MAPPING  String property Simple_Lowercase_Mapping.

Corresponds to u_tolower.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_SIMPLE_TITLECASE_MAPPING  String property Simple_Titlecase_Mapping.

Corresponds to u_totitle.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_SIMPLE_UPPERCASE_MAPPING  String property Simple_Uppercase_Mapping.

Corresponds to u_toupper.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_TITLECASE_MAPPING  String property Titlecase_Mapping.

Corresponds to u_strToTitle in ustring.h.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_UNICODE_1_NAME  String property Unicode_1_Name.

Corresponds to u_charName.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_UPPERCASE_MAPPING  String property Uppercase_Mapping.

Corresponds to u_strToUpper in ustring.h.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_STRING_LIMIT  One more than the last constant for string Unicode properties.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
UCHAR_INVALID_CODE  Represents a nonexistent or invalid property or property value.

Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.

Definition at line 113 of file uchar.h.

enum 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()
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.
Enumeration values:
U_SHORT_PROPERTY_NAME 
U_LONG_PROPERTY_NAME 
U_PROPERTY_NAME_CHOICE_COUNT 

Definition at line 1199 of file uchar.h.


Function Documentation

void u_charAge 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:
c  The code point.
versionArray  The Unicode version number array, to be filled in.
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

uint16_t u_charCellWidth UChar32    c
 

Obsolete because the "cell width" functions and implementation are out of date compared with Unicode Standard Annex #11.

Use u_getIntPropertyValue with UCHAR_EAST_ASIAN_WIDTH. See http://www.unicode.org/reports/tr11/

Returns a value indicating the display-cell width of the character when used in Asian text, according to the Unicode standard (see p. 6-130 of The Unicode Standard, Version 2.0). The results for various characters are as follows:

U_ZERO_WIDTH: Characters which are considered to take up no display-cell space: control characters format characters line and paragraph separators non-spacing marks combining Hangul jungseong combining Hangul jongseong unassigned Unicode values

U_HALF_WIDTH: Characters which take up half a cell in standard Asian text: all characters in the General Scripts Area except combining Hangul choseong and the characters called out specifically above as ZERO_WIDTH alphabetic and Arabic presentation forms halfwidth CJK punctuation halfwidth Katakana halfwidth Hangul Jamo halfwidth forms, arrows, and shapes

U_FULL_WIDTH: Characters which take up a full cell in standard Asian text: combining Hangul choseong all characters in the CJK Phonetics and Symbols Area all characters in the CJK Ideographs Area all characters in the Hangul Syllables Area CJK compatibility ideographs CJK compatibility forms small form variants fullwidth ASCII fullwidth punctuation and currency signs

U_NEUTRAL_WIDTH: Characters whose cell width is context-dependent: all characters in the Symbols Area, except those specifically called out above all characters in the Surrogates Area all charcaters in the Private Use Area

For Korean text, this algorithm should work properly with properly normalized Korean text. Precomposed Hangul syllables and non-combining jamo are all considered full- width characters. For combining jamo, we treat we treat choseong (initial consonants) as double-width characters and junseong (vowels) and jongseong (final consonants) as non-spacing marks. This will work right in text that uses the precomposed choseong characters instead of teo choseong characters in a row, and which uses the choseong filler character at the beginning of syllables that don't have an initial consonant. The results may be slightly off with Korean text following different conventions.

Parameters:
c  The character to be tested
Returns:
a value indicating the display-cell width of the character when used in Asian text
Obsolete:
ICU 2.6. Use UCHAR_EAST_ASIAN_WIDTH instead since this API will be removed in that release.

int32_t u_charDigitValue UChar32    c
 

Returns the decimal numeric value of a digit character.

Parameters:
c  the decimal digit character for which to get the numeric value
Returns:
the numeric value of c in decimal radix. This method returns -1 if c is not a valid digit character.
Stable:
ICU 2.0

UCharDirection u_charDirection UChar32    c
 

Returns the linguistic direction property of a character.

Returns the linguistic direction property of a character. For example, 0x0041 (letter A) has the LEFT_TO_RIGHT directional property.

Parameters:
c  The character to be tested
Returns:
the linguistic direction property of a character.
See also:
UCharDirection , UCharDirection
Stable:
ICU 2.0

UChar32 u_charFromName 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:
nameChoice  Selector for which name to match.
name  The name to match.
pErrorCode  Pointer 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

UChar32 u_charMirror UChar32    c
 

Maps the specified character to a "mirror-image" character.

For characters with the "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 selecetion capabilities.

Parameters:
c  the character (code point, Unicode scalar value) 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 "mirrored" property
Stable:
ICU 2.0

int32_t u_charName 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:
code  The character (code point) for which to get the name. It must be 0<=code<=0x10ffff.
nameChoice  Selector for which name to get.
buffer  Destination 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)
pErrorCode  Pointer 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

int8_t u_charType UChar32    c
 

Returns a value indicating a character category.

The categories are taken from the Unicode Character Database (UCD) in UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
a value of type int, the character category.
See also:
UCharCategory
Stable:
ICU 2.0

int32_t u_digit UChar32    ch,
int8_t    radix
 

Returns the numeric value of the character ch in the specified radix.

If the radix is not in the range 2 <= radix <= 36 or if the value of ch 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 method u_isdigit is true of the character and the Unicode decimal digit value of the character (or its single-character decomposition) is less than the specified radix. In this case the decimal digit value is returned.
  • The character is one of the uppercase Latin letters 'A' through 'Z' and its code is less than radix + 'A' - 10. In this case, ch - 'A' + 10 is returned.
  • The character is one of the lowercase Latin letters 'a' through 'z' and its code is less than radix + 'a' - 10. In this case, ch - 'a' + 10 is returned.
Parameters:
ch  the character to be converted.
radix  the radix.
Returns:
the numeric value represented by the character in the specified radix.
See also:
u_forDigit , u_charDigitValue , u_isdigit
Stable:
ICU 2.0

void u_enumCharNames 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:
start  The first code point in the enumeration range.
limit  One more than the last code point in the enumeration range (the first one after the range).
fn  The function that is to be called for each character name.
context  An arbitrary pointer that is passed to the function.
nameChoice  Selector for which kind of names to enumerate.
pErrorCode  Pointer to a UErrorCode variable
See also:
UCharNameChoice , UEnumCharNamesFn , u_charName , u_charFromName
Stable:
ICU 1.7

void u_enumCharTypes 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:
enumRange  a pointer to a function that is called for each contiguous range of code points with the same general category
context  an opaque pointer that is passed on to the callback function
Draft:
This API has been introduced in ICU 2.1 @see UCharCategory @see UCharEnumTypeRange. It is still in draft state and may be modified in a future release.

UChar32 u_foldCase 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.

Only "simple", single-code point case folding mappings are used. "Full" mappings are used by u_strFoldCase().

Parameters:
c  the character to be converted
options  Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
Returns:
the case folding equivalent of the character, if any; otherwise the character itself.
Stable:
ICU 2.0

UChar32 u_forDigit 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.

Parameters:
digit  the number to convert to a character.
radix  the 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

uint8_t u_getCombiningClass UChar32    c
 

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

Parameters:
c  the code point of the character
Returns:
the combining class of the character
Stable:
ICU 2.0

int32_t u_getFC_NFKC_Closure 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:
c  The character (code point) for which to get the FC_NFKC_Closure string. It must be 0<=c<=0x10ffff.
dest  Destination 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)
pErrorCode  Pointer 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.
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

int32_t u_getISOComment UChar32    c,
char *    dest,
int32_t    destCapacity,
UErrorCode   pErrorCode
 

Get the ISO 10646 comment for a character.

The ISO 10646 comment is an informative field in the Unicode Character Database (UnicodeData.txt field 11) and is from the ISO 10646 names list.

Parameters:
c  The character (code point) for which to get the ISO comment. It must be 0<=c<=0x10ffff.
dest  Destination 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)
pErrorCode  Pointer to a UErrorCode variable; check for U_SUCCESS() after u_getISOComment() returns.
Returns:
The length of the comment, or 0 if there is no comment 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.
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

int32_t u_getIntPropertyMaxValue 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:
which  UProperty 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
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

int32_t u_getIntPropertyMinValue 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:
which  UProperty 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
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

int32_t u_getIntPropertyValue 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:
c  Code point to test.
which  UProperty 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_getUnicodeVersion
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

double u_getNumericValue 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.

Parameters:
c  Code 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
Draft:
This API has been introduced in ICU 2.2. It is still in draft state and may be modified in a future release.

UProperty u_getPropertyEnum 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:
alias  the 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
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.

const char* u_getPropertyName 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:
property  UProperty selector other than UCHAR_INVALID_CODE. If out of range, NULL is returned.
nameChoice  selector 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
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.

int32_t u_getPropertyValueEnum 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:
property  UProperty 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.
alias  the 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: U CHAR_GENERAL_CATEGORY 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
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.

const char* u_getPropertyValueName 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:
property  UProperty 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.
value  selector 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.
nameChoice  selector 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
Draft:
This API has been introduced in ICU 2.4. It is still in draft state and may be modified in a future release.

void u_getUnicodeVersion UVersionInfo    info
 

Gets the Unicode version information.

The version array stores the version information for the Unicode standard that is currently used by ICU. For example, release "1.3.31.2" is then represented as 0x01031F02.

Parameters:
versionArray  the version # information, the result will be filled in
Stable:
ICU 2.0

UBool u_hasBinaryProperty 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/ . 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:
c  Code point to test.
which  UProperty 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_getIntPropertyValue , u_getUnicodeVersion
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

UBool u_isIDIgnorable UChar32    c
 

A convenience method for determining if a Unicode character should be regarded as an ignorable character in a Unicode identifier.

The following Unicode characters are ignorable in a Unicode identifier:
0x0000 through 0x0008, ISO control characters that
0x000E through 0x001B, are not whitespace
and 0x007F through 0x009F
0x200C through 0x200F join controls
0x200A through 0x200E bidirectional controls
0x206A through 0x206F format controls
0xFEFF zero-width no-break space

Parameters:
c  the Unicode character.
Returns:
TRUE if the character may be part of a Unicode identifier; FALSE otherwise.
See also:
u_isIDPart
Stable:
ICU 2.0

UBool u_isIDPart UChar32    c
 

A convenience method for determining if a Unicode character may be part of a Unicode identifier other than the starting character.

A character may be part of a Unicode identifier if and only if it is one of the following:

  • a letter
  • a connecting punctuation character (such as "_").
  • a digit
  • a numeric letter (such as a Roman numeral character)
  • a combining mark
  • a non-spacing mark
  • an ignorable control character
Parameters:
c  the Unicode character.
Returns:
TRUE if the character may be part of a Unicode identifier; FALSE otherwise.
See also:
u_isIDIgnorable , u_isIDStart
Stable:
ICU 2.0

UBool u_isIDStart UChar32    c
 

A convenience method for determining if a Unicode character is allowed to start in a Unicode identifier.

A character may start a Unicode identifier if and only if it is a letter.

Parameters:
c  the Unicode character.
Returns:
TRUE if the character may start a Unicode identifier; FALSE otherwise.
See also:
u_isalpha , u_isIDPart
Stable:
ICU 2.0

UBool u_isJavaIDPart UChar32    c
 

A convenience method for determining if a Unicode character may be part of a Java identifier other than the starting character.

A character may be part of a Java identifier if and only if it is one of the following:

  • a letter
  • a currency symbol (such as "$")
  • a connecting punctuation character (such as "_").
  • a digit
  • a numeric letter (such as a Roman numeral character)
  • a combining mark
  • a non-spacing mark
  • an ignorable control character
Parameters:
c  the Unicode character.
Returns:
TRUE if the character may be part of a Unicode identifier; FALSE otherwise.
See also:
u_isIDIgnorable , u_isJavaIDStart , u_isalpha , u_isdigit , u_isIDPart
Stable:
ICU 2.0

UBool u_isJavaIDStart UChar32    c
 

A convenience method for determining if a Unicode character is allowed as the first character in a Java identifier.

A character may start a Java identifier if and only if it is one of the following:

  • a letter
  • a currency symbol (such as "$")
  • a connecting punctuation symbol (such as "_").
Parameters:
c  the Unicode character.
Returns:
TRUE if the character may start a Java identifier; FALSE otherwise.
See also:
u_isJavaIDPart , u_isalpha , u_isIDStart
Stable:
ICU 2.0

UBool u_isMirrored UChar32    c
 

Determines whether the character has the "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.

Parameters:
c  the character (code point, Unicode scalar value) to be tested
Returns:
TRUE if the character has the "mirrored" property
Stable:
ICU 2.0

UBool u_isUAlphabetic 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:
c  Code point to test
Returns:
true if the code point has the Alphabetic Unicode property, false otherwise
See also:
UCHAR_ALPHABETIC , u_isalpha , u_hasBinaryProperty
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

UBool u_isULowercase 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:
c  Code point to test
Returns:
true if the code point has the Lowercase Unicode property, false otherwise
See also:
UCHAR_LOWERCASE , u_islower , u_hasBinaryProperty
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

UBool u_isUUppercase 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:
c  Code point to test
Returns:
true if the code point has the Uppercase Unicode property, false otherwise
See also:
UCHAR_UPPERCASE , u_isupper , u_hasBinaryProperty
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

UBool u_isUWhiteSpace 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!

Parameters:
c  Code 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_hasBinaryProperty
Draft:
This API has been introduced in ICU 2.1. It is still in draft state and may be modified in a future release.

UBool u_isWhitespace UChar32    c
 

Determines if the specified character is white space according to ICU.

A character is considered to be an ICU whitespace character if and only if it satisfies one of the following criteria:

  • It is a Unicode space separator (category "Zs"), but is not a no-break space (&#92;u00A0 or &#92;uFEFF).
  • It is a Unicode line separator (category "Zl").
  • It is a Unicode paragraph separator (category "Zp").
  • It is &#92;u0009, HORIZONTAL TABULATION.
  • It is &#92;u000A, LINE FEED.
  • It is &#92;u000B, VERTICAL TABULATION.
  • It is &#92;u000C, FORM FEED.
  • It is &#92;u000D, CARRIAGE RETURN.
  • It is &#92;u001C, FILE SEPARATOR.
  • It is &#92;u001D, GROUP SEPARATOR.
  • It is &#92;u001E, RECORD SEPARATOR.
  • It is &#92;u001F, UNIT SEPARATOR.
Note: This method corresponds to the Java method java.lang.Character.isWhitespace().
Parameters:
ch  the character to be tested.
Returns:
true if the character is an ICU whitespace character; false otherwise.
See also:
u_isspace
Stable:
ICU 2.0

UBool u_isalnum UChar32    c
 

Determines whether the specified character is an alphanumeric character (letter or digit)according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is a letter or a digit; false otherwise.
Stable:
ICU 2.0

UBool u_isalpha UChar32    c
 

Determines whether the specified character is a letter according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is a letter; false otherwise.
See also:
u_isdigit , u_isalnum
Stable:
ICU 2.0

UBool u_isbase UChar32    c
 

Determines whether the specified character is of the base form according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the Unicode character is of the base form; false otherwise.
See also:
u_isalpha , u_isdigit
Stable:
ICU 2.0

UBool u_iscntrl UChar32    c
 

Determines whether the specified character is a control character or not.

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)
Parameters:
c  the character to be tested
Returns:
true if the Unicode character is a control character; false otherwise.
See also:
u_isprint
Stable:
ICU 2.0

UBool u_isdefined UChar32    c
 

Determines whether the specified numeric value is actually a defined character according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character has a defined Unicode meaning; false otherwise.
See also:
u_isdigit , u_isalpha , u_isalnum , u_isupper , u_islower , u_istitle
Stable:
ICU 2.0

UBool u_isdigit UChar32    c
 

Determines whether the specified character is a digit according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is a digit; false otherwise.
Stable:
ICU 2.0

UBool u_islower UChar32    c
 

Determines whether the specified UChar is a lowercase character according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is lowercase; false otherwise.
See also:
UNICODE_VERSION , u_isupper , u_istitle , u_islower
Stable:
ICU 2.0

UBool u_isprint UChar32    c
 

Determines whether the specified character is a printable character according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the Unicode character is a printable character; false otherwise.
See also:
u_iscntrl
Stable:
ICU 2.0

UBool u_isspace UChar32    c
 

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

Parameters:
c  the character to be tested
Returns:
true if the character is a space character; false otherwise.
Stable:
ICU 2.0

UBool u_istitle UChar32    c
 

Determines whether the specified character is a titlecase character according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is titlecase; false otherwise.
See also:
u_isupper , u_islower , u_totitle
Stable:
ICU 2.0

UBool u_isupper UChar32    c
 

Determines whether the specified character is an uppercase character according to UnicodeData.txt.

Parameters:
c  the character to be tested
Returns:
true if the character is uppercase; false otherwise.
See also:
u_islower , u_istitle , u_tolower
Stable:
ICU 2.0

UChar32 u_tolower 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.

A character has a lowercase equivalent if and only if a lowercase mapping is specified for the character in the UnicodeData.txt attribute table.

u_tolower() only deals with the general letter case conversion. For language specific case conversion behavior, use ustrToUpper(). For example, the case conversion for dot-less i and dotted I in Turkish, or for final sigma in Greek.

Parameters:
c  the character to be converted
Returns:
the lowercase equivalent of the character, if any; otherwise the character itself.
Stable:
ICU 2.0

UChar32 u_totitle UChar32    c
 

The given character is mapped to its titlecase equivalent according to UnicodeData.txt.

There are only four Unicode characters that are truly titlecase forms that are distinct from uppercase forms. As a rule, if a character has no true titlecase equivalent, its uppercase equivalent is returned.

A character has a titlecase equivalent if and only if a titlecase mapping is specified for the character in the UnicodeData.txt data.

Parameters:
c  the character to be converted
Returns:
the titlecase equivalent of the character, if any; otherwise the character itself.
Stable:
ICU 2.0

UChar32 u_toupper 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.

u_toupper() only deals with the general letter case conversion. For language specific case conversion behavior, use ustrToUpper(). For example, the case conversion for dot-less i and dotted I in Turkish, or ess-zed (i.e., "sharp S") in German.

Parameters:
c  the character to be converted
Returns:
the uppercase equivalent of the character, if any; otherwise the character itself.
Stable:
ICU 2.0

UBlockCode ublock_getCode UChar32    ch
 

Returns the Unicode allocation block that contains the character.

Parameters:
ch  The character to be tested
Returns:
the Unicode allocation block that contains the character
See also:
UBlockCode
Stable:
ICU 2.0


Generated on Wed Dec 18 16:50:23 2002 for ICU 2.4 by doxygen1.2.11.1 written by Dimitri van Heesch, © 1997-2001