#include "unicode/utypes.h"
Go to the source code of this file.
Defines | |
#define | U_UNICODE_VERSION "4" |
Unicode version number, default for the current ICU version. | |
#define | UCHAR_MIN_VALUE 0 |
The lowest Unicode code point value. | |
#define | UCHAR_MAX_VALUE 0x10ffff |
The highest Unicode code point value (scalar value) according to The Unicode Standard. | |
#define | U_MASK(x) ((uint32_t)1<<(x)) |
Get a single-bit bit set (a flag) from a bit number 0..31. | |
#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. | |
#define | U_GC_LU_MASK U_MASK(U_UPPERCASE_LETTER) |
Mask constant for a UCharCategory. | |
#define | U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) |
Mask constant for a UCharCategory. | |
#define | U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) |
Mask constant for a UCharCategory. | |
#define | U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) |
Mask constant for a UCharCategory. | |
#define | U_GC_LO_MASK U_MASK(U_OTHER_LETTER) |
Mask constant for a UCharCategory. | |
#define | U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) |
Mask constant for a UCharCategory. | |
#define | U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) |
Mask constant for a UCharCategory. | |
#define | U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) |
Mask constant for a UCharCategory. | |
#define | U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) |
Mask constant for a UCharCategory. | |
#define | U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) |
Mask constant for a UCharCategory. | |
#define | U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) |
Mask constant for a UCharCategory. | |
#define | U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) |
Mask constant for a UCharCategory. | |
#define | U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) |
Mask constant for a UCharCategory. | |
#define | U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) |
Mask constant for a UCharCategory. | |
#define | U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) |
Mask constant for a UCharCategory. | |
#define | U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) |
Mask constant for a UCharCategory. | |
#define | U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) |
Mask constant for a UCharCategory. | |
#define | U_GC_CS_MASK U_MASK(U_SURROGATE) |
Mask constant for a UCharCategory. | |
#define | U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) |
Mask constant for a UCharCategory. | |
#define | U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) |
Mask constant for a UCharCategory. | |
#define | U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) |
Mask constant for a UCharCategory. | |
#define | U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) |
Mask constant for a UCharCategory. | |
#define | U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#define | U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) |
Mask constant for a UCharCategory. | |
#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). | |
#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). | |
#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). | |
#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). | |
#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). | |
#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). | |
#define | U_GC_P_MASK |
Mask constant for multiple UCharCategory bits (P Punctuation). | |
#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). | |
#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. | |
#define | U_GET_GC_MASK(c) U_MASK(u_charType(c)) |
Get a single-bit bit set for the general category of a character. | |
#define | U_FOLD_CASE_DEFAULT 0 |
Option value for case folding: use default mappings defined in CaseFolding.txt. | |
#define | U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 |
Option value for case folding:. | |
Typedefs | |
typedef enum UProperty | UProperty |
Selection constants for Unicode properties. | |
typedef enum UCharCategory | UCharCategory |
Data for enumerated Unicode general category types. | |
typedef enum UCharDirection | UCharDirection |
This specifies the language directional property of a character set. | |
typedef enum UEastAsianWidth | UEastAsianWidth |
East Asian Width constants. | |
typedef enum UCharNameChoice | UCharNameChoice |
Selector constants for u_charName(). | |
typedef enum UPropertyNameChoice | UPropertyNameChoice |
Selector constants for u_getPropertyName() and u_getPropertyValueName(). | |
typedef enum UDecompositionType | UDecompositionType |
Decomposition Type constants. | |
typedef enum UJoiningType | UJoiningType |
Joining Type constants. | |
typedef enum UJoiningGroup | UJoiningGroup |
Joining Group constants. | |
typedef enum ULineBreak | ULineBreak |
Line Break constants. | |
typedef enum UNumericType | UNumericType |
Numeric Type constants. | |
typedef enum UHangulSyllableType | UHangulSyllableType |
Hangul Syllable Type constants. | |
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"). | |
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. | |
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_CASE_SENSITIVE, 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_HANGUL_SYLLABLE_TYPE, 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_NO_BLOCK = 0, UBLOCK_BASIC_LATIN = 1, UBLOCK_LATIN_1_SUPPLEMENT = 2, UBLOCK_LATIN_EXTENDED_A = 3, UBLOCK_LATIN_EXTENDED_B = 4, UBLOCK_IPA_EXTENSIONS = 5, UBLOCK_SPACING_MODIFIER_LETTERS = 6, UBLOCK_COMBINING_DIACRITICAL_MARKS = 7, UBLOCK_GREEK = 8, UBLOCK_CYRILLIC = 9, UBLOCK_ARMENIAN = 10, UBLOCK_HEBREW = 11, UBLOCK_ARABIC = 12, UBLOCK_SYRIAC = 13, UBLOCK_THAANA = 14, UBLOCK_DEVANAGARI = 15, UBLOCK_BENGALI = 16, UBLOCK_GURMUKHI = 17, UBLOCK_GUJARATI = 18, UBLOCK_ORIYA = 19, UBLOCK_TAMIL = 20, UBLOCK_TELUGU = 21, UBLOCK_KANNADA = 22, UBLOCK_MALAYALAM = 23, UBLOCK_SINHALA = 24, UBLOCK_THAI = 25, UBLOCK_LAO = 26, UBLOCK_TIBETAN = 27, UBLOCK_MYANMAR = 28, UBLOCK_GEORGIAN = 29, UBLOCK_HANGUL_JAMO = 30, UBLOCK_ETHIOPIC = 31, UBLOCK_CHEROKEE = 32, UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 33, UBLOCK_OGHAM = 34, UBLOCK_RUNIC = 35, UBLOCK_KHMER = 36, UBLOCK_MONGOLIAN = 37, UBLOCK_LATIN_EXTENDED_ADDITIONAL = 38, UBLOCK_GREEK_EXTENDED = 39, UBLOCK_GENERAL_PUNCTUATION = 40, UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS = 41, UBLOCK_CURRENCY_SYMBOLS = 42, UBLOCK_COMBINING_MARKS_FOR_SYMBOLS = 43, UBLOCK_LETTERLIKE_SYMBOLS = 44, UBLOCK_NUMBER_FORMS = 45, UBLOCK_ARROWS = 46, UBLOCK_MATHEMATICAL_OPERATORS = 47, UBLOCK_MISCELLANEOUS_TECHNICAL = 48, UBLOCK_CONTROL_PICTURES = 49, UBLOCK_OPTICAL_CHARACTER_RECOGNITION = 50, UBLOCK_ENCLOSED_ALPHANUMERICS = 51, UBLOCK_BOX_DRAWING = 52, UBLOCK_BLOCK_ELEMENTS = 53, UBLOCK_GEOMETRIC_SHAPES = 54, UBLOCK_MISCELLANEOUS_SYMBOLS = 55, UBLOCK_DINGBATS = 56, UBLOCK_BRAILLE_PATTERNS = 57, UBLOCK_CJK_RADICALS_SUPPLEMENT = 58, UBLOCK_KANGXI_RADICALS = 59, UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 60, UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION = 61, UBLOCK_HIRAGANA = 62, UBLOCK_KATAKANA = 63, UBLOCK_BOPOMOFO = 64, UBLOCK_HANGUL_COMPATIBILITY_JAMO = 65, UBLOCK_KANBUN = 66, UBLOCK_BOPOMOFO_EXTENDED = 67, UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS = 68, UBLOCK_CJK_COMPATIBILITY = 69, UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 70, UBLOCK_CJK_UNIFIED_IDEOGRAPHS = 71, UBLOCK_YI_SYLLABLES = 72, UBLOCK_YI_RADICALS = 73, UBLOCK_HANGUL_SYLLABLES = 74, UBLOCK_HIGH_SURROGATES = 75, UBLOCK_HIGH_PRIVATE_USE_SURROGATES = 76, UBLOCK_LOW_SURROGATES = 77, UBLOCK_PRIVATE_USE = 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_LIMBU = 111, UBLOCK_TAI_LE = 112, UBLOCK_KHMER_SYMBOLS = 113, UBLOCK_PHONETIC_EXTENSIONS = 114, UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, UBLOCK_LINEAR_B_SYLLABARY = 117, UBLOCK_LINEAR_B_IDEOGRAMS = 118, UBLOCK_AEGEAN_NUMBERS = 119, UBLOCK_UGARITIC = 120, UBLOCK_SHAVIAN = 121, UBLOCK_OSMANYA = 122, UBLOCK_CYPRIOT_SYLLABARY = 123, UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, UBLOCK_COUNT, UBLOCK_INVALID_CODE = -1 } |
Constants for Unicode blocks, see the Unicode Data file Blocks.txt ICU 2.0. 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_FE, U_JG_KHAPH, U_JG_ZHAIN, 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_NEXT_LINE, U_LB_WORD_JOINER, 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... | |
enum | UHangulSyllableType { U_HST_NOT_APPLICABLE, U_HST_LEADING_JAMO, U_HST_VOWEL_JAMO, U_HST_TRAILING_JAMO, U_HST_LV_SYLLABLE, U_HST_LVT_SYLLABLE, U_HST_COUNT } |
Hangul Syllable Type constants. More... | |
Functions | |
U_CAPI UBool U_EXPORT2 | u_hasBinaryProperty (UChar32 c, UProperty which) |
Check a binary Unicode property for a code point. | |
U_CAPI UBool U_EXPORT2 | u_isUAlphabetic (UChar32 c) |
Check if a code point has the Alphabetic Unicode property. | |
U_CAPI UBool U_EXPORT2 | u_isULowercase (UChar32 c) |
Check if a code point has the Lowercase Unicode property. | |
U_CAPI UBool U_EXPORT2 | u_isUUppercase (UChar32 c) |
Check if a code point has the Uppercase Unicode property. | |
U_CAPI UBool U_EXPORT2 | u_isUWhiteSpace (UChar32 c) |
Check if a code point has the White_Space Unicode property. | |
U_CAPI int32_t U_EXPORT2 | u_getIntPropertyValue (UChar32 c, UProperty which) |
Get the property value for an enumerated or integer Unicode property for a code point. | |
U_CAPI int32_t U_EXPORT2 | u_getIntPropertyMinValue (UProperty which) |
Get the minimum value for an enumerated/integer/binary Unicode property. | |
U_CAPI int32_t U_EXPORT2 | u_getIntPropertyMaxValue (UProperty which) |
Get the maximum value for an enumerated/integer/binary Unicode property. | |
U_CAPI double U_EXPORT2 | u_getNumericValue (UChar32 c) |
Get the numeric value for a Unicode code point as defined in the Unicode Character Database. | |
U_CAPI UBool U_EXPORT2 | u_islower (UChar32 c) |
Determines whether the specified code point has the general category "Ll" (lowercase letter). | |
U_CAPI UBool U_EXPORT2 | u_isupper (UChar32 c) |
Determines whether the specified code point has the general category "Lu" (uppercase letter). | |
U_CAPI UBool U_EXPORT2 | u_istitle (UChar32 c) |
Determines whether the specified code point is a titlecase letter. | |
U_CAPI UBool U_EXPORT2 | u_isdigit (UChar32 c) |
Determines whether the specified code point is a digit character according to Java. | |
U_CAPI UBool U_EXPORT2 | u_isalpha (UChar32 c) |
Determines whether the specified code point is a letter character. | |
U_CAPI UBool U_EXPORT2 | u_isalnum (UChar32 c) |
Determines whether the specified code point is an alphanumeric character (letter or digit) according to Java. | |
U_CAPI UBool U_EXPORT2 | u_isxdigit (UChar32 c) |
Determines whether the specified code point is a hexadecimal digit. | |
U_CAPI UBool U_EXPORT2 | u_ispunct (UChar32 c) |
Determines whether the specified code point is a punctuation character. | |
U_CAPI UBool U_EXPORT2 | u_isgraph (UChar32 c) |
Determines whether the specified code point is a "graphic" character (printable, excluding spaces). | |
U_CAPI UBool U_EXPORT2 | u_isblank (UChar32 c) |
Determines whether the specified code point is a "blank" or "horizontal space", a character that visibly separates words on a line. | |
U_CAPI UBool U_EXPORT2 | u_isdefined (UChar32 c) |
Determines whether the specified code point is "defined", which usually means that it is assigned a character. | |
U_CAPI UBool U_EXPORT2 | u_isspace (UChar32 c) |
Determines if the specified character is a space character or not. | |
U_CAPI UBool U_EXPORT2 | u_isJavaSpaceChar (UChar32 c) |
Determine if the specified code point is a space character according to Java. | |
U_CAPI UBool U_EXPORT2 | u_isWhitespace (UChar32 c) |
Determines if the specified code point is a whitespace character according to Java/ICU. | |
U_CAPI UBool U_EXPORT2 | u_iscntrl (UChar32 c) |
Determines whether the specified code point is a control character (as defined by this function). | |
U_CAPI UBool U_EXPORT2 | u_isISOControl (UChar32 c) |
Determines whether the specified code point is an ISO control code. | |
U_CAPI UBool U_EXPORT2 | u_isprint (UChar32 c) |
Determines whether the specified code point is a printable character. | |
U_CAPI UBool U_EXPORT2 | u_isbase (UChar32 c) |
Determines whether the specified code point is a base character. | |
U_CAPI UCharDirection U_EXPORT2 | u_charDirection (UChar32 c) |
Returns the bidirectional category value for the code point, which is used in the Unicode bidirectional algorithm (UAX #9 http://www.unicode.org/reports/tr9/). | |
U_CAPI UBool U_EXPORT2 | u_isMirrored (UChar32 c) |
Determines whether the code point has the Bidi_Mirrored property. | |
U_CAPI UChar32 U_EXPORT2 | u_charMirror (UChar32 c) |
Maps the specified character to a "mirror-image" character. | |
U_CAPI int8_t U_EXPORT2 | u_charType (UChar32 c) |
Returns the general category value for the code point. | |
U_CAPI void U_EXPORT2 | u_enumCharTypes (UCharEnumTypeRange *enumRange, const void *context) |
Enumerate efficiently all code points with their Unicode general categories. | |
U_CAPI uint8_t U_EXPORT2 | u_getCombiningClass (UChar32 c) |
Returns the combining class of the code point as specified in UnicodeData.txt. | |
U_CAPI int32_t U_EXPORT2 | u_charDigitValue (UChar32 c) |
Returns the decimal digit value of a decimal digit character. | |
U_CAPI UBlockCode U_EXPORT2 | ublock_getCode (UChar32 c) |
Returns the Unicode allocation block that contains the character. | |
U_CAPI int32_t U_EXPORT2 | u_charName (UChar32 code, UCharNameChoice nameChoice, char *buffer, int32_t bufferLength, UErrorCode *pErrorCode) |
Retrieve the name of a Unicode character. | |
U_CAPI int32_t U_EXPORT2 | u_getISOComment (UChar32 c, char *dest, int32_t destCapacity, UErrorCode *pErrorCode) |
Get the ISO 10646 comment for a character. | |
U_CAPI UChar32 U_EXPORT2 | u_charFromName (UCharNameChoice nameChoice, const char *name, UErrorCode *pErrorCode) |
Find a Unicode character by its name and return its code point value. | |
U_CAPI void U_EXPORT2 | 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. | |
U_CAPI const char *U_EXPORT2 | u_getPropertyName (UProperty property, UPropertyNameChoice nameChoice) |
Return the Unicode name for a given property, as given in the Unicode database file PropertyAliases.txt. | |
U_CAPI UProperty U_EXPORT2 | u_getPropertyEnum (const char *alias) |
Return the UProperty enum for a given property name, as specified in the Unicode database file PropertyAliases.txt. | |
U_CAPI const char *U_EXPORT2 | 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. | |
U_CAPI int32_t U_EXPORT2 | 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. | |
U_CAPI UBool U_EXPORT2 | u_isIDStart (UChar32 c) |
Determines if the specified character is permissible as the first character in an identifier according to Unicode (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). | |
U_CAPI UBool U_EXPORT2 | u_isIDPart (UChar32 c) |
Determines if the specified character is permissible in an identifier according to Java. | |
U_CAPI UBool U_EXPORT2 | u_isIDIgnorable (UChar32 c) |
Determines if the specified character should be regarded as an ignorable character in an identifier, according to Java. | |
U_CAPI UBool U_EXPORT2 | u_isJavaIDStart (UChar32 c) |
Determines if the specified character is permissible as the first character in a Java identifier. | |
U_CAPI UBool U_EXPORT2 | u_isJavaIDPart (UChar32 c) |
Determines if the specified character is permissible in a Java identifier. | |
U_CAPI UChar32 U_EXPORT2 | 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. | |
U_CAPI UChar32 U_EXPORT2 | 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_CAPI UChar32 U_EXPORT2 | u_totitle (UChar32 c) |
The given character is mapped to its titlecase equivalent according to UnicodeData.txt; if none is defined, the character itself is returned. | |
U_CAPI UChar32 U_EXPORT2 | 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. | |
U_CAPI int32_t U_EXPORT2 | u_digit (UChar32 ch, int8_t radix) |
Returns the decimal digit value of the code point in the specified radix. | |
U_CAPI UChar32 U_EXPORT2 | u_forDigit (int32_t digit, int8_t radix) |
Determines the character representation for a specific digit in the specified radix. | |
U_CAPI void U_EXPORT2 | u_charAge (UChar32 c, UVersionInfo versionArray) |
Get the "age" of the code point. | |
U_CAPI void U_EXPORT2 | u_getUnicodeVersion (UVersionInfo versionArray) |
Gets the Unicode version information. | |
U_CAPI int32_t U_EXPORT2 | u_getFC_NFKC_Closure (UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode) |
Get the FC_NFKC_Closure property string for a character. |
This C API provides low-level access to the Unicode Character Database. In addition to raw property values, some convenience functions calculate derived properties, for example for Java-style programming.
Unicode assigns each code point (not just assigned character) values for many properties. Most of them are simple boolean flags, or constants from a small enumerated list. For some properties, values are strings or other relatively more complex types.
For more information see "About the Unicode Character Database" (http://www.unicode.org/ucd/) and the ICU User Guide chapter on Properties (http://oss.software.ibm.com/icu/userguide/properties.html).
Many functions are designed to match java.lang.Character functions. See the individual function documentation, and see the JDK 1.4.1 java.lang.Character documentation at http://java.sun.com/j2se/1.4.1/docs/api/java/lang/Character.html
There are also functions that provide easy migration from C/POSIX functions like isblank(). Their use is generally discouraged because the C/POSIX standards do not define their semantics beyond the ASCII range, which means that different implementations exhibit very different behavior. Instead, Unicode properties should be used directly.
There are also only a few, broad C/POSIX character classes, and they tend to be used for conflicting purposes. For example, the "isalpha()" class is sometimes used to determine word boundaries, while a more sophisticated approach would at least distinguish initial letters from continuation characters (the latter including combining marks). (In ICU, BreakIterator is the most sophisticated API for word boundaries.) Another example: There is no "istitle()" class for titlecase characters.
A summary of the behavior of some C/POSIX character classification implementations for Unicode is available at http://oss.software.ibm.com/cvs/icu/~checkout~/icuhtml/design/posix_classes.html
Important: The behavior of the ICU C/POSIX-style character classification functions is subject to change according to discussion of the above summary.
Note: There are several ICU whitespace functions. Comparison:
|
Option value for case folding: use default mappings defined in CaseFolding.txt. ICU 2.0 |
|
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. ICU 2.0 |
|
Mask constant for multiple UCharCategory bits (C Others). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
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.
|
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (L Letters). ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (LC Cased Letters). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (M Marks). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (N Numbers). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Value: (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \ U_GC_PI_MASK|U_GC_PF_MASK) ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (S Symbols). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for multiple UCharCategory bits (Z Separators). ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
Mask constant for a UCharCategory. ICU 2.1 |
|
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)).
|
|
Get a single-bit bit set (a flag) from a bit number 0..31. ICU 2.1 |
|
Special value that is returned by u_getNumericValue when no numeric value is defined for a code point.
|
|
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.
|
|
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.
|
|
The lowest Unicode code point value. Code points are non-negative. ICU 2.0 |
|
Data for enumerated Unicode general category types. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . ICU 2.0 |
|
This specifies the language directional property of a character set. ICU 2.0 |
|
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.
|
|
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.
|
|
Decomposition Type constants.
|
|
East Asian Width constants.
|
|
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.
|
|
Hangul Syllable Type constants.
|
|
Joining Group constants.
|
|
Joining Type constants.
|
|
Line Break constants.
|
|
Numeric Type constants.
|
|
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/ucd/ . For names of Unicode properties see the UCD file PropertyAliases.txt. Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available. Check u_getUnicodeVersion to be sure.
|
|
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,...
|
|
|
Data for enumerated Unicode general category types. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html . ICU 2.0
|
|
This specifies the language directional property of a character set. ICU 2.0
|
|
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.
|
|
Decomposition Type constants.
|
|
East Asian Width constants.
|
|
Hangul Syllable Type constants.
|
|
Joining Group constants.
|
|
Joining Type constants.
|
|
Line Break constants.
|
|
Numeric Type constants.
|
|
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/ucd/ . For names of Unicode properties see the UCD file PropertyAliases.txt. Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available. Check u_getUnicodeVersion to be sure.
|
|
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,...
|
|
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.
|
|
Returns the decimal digit value of a decimal digit character. Such characters have the general category "Nd" (decimal digit numbers) and a Numeric_Type of Decimal. Unlike ICU releases before 2.6, no digit values are returned for any Han characters because Han number characters are often used with a special Chinese-style number format (with characters for powers of 10 in between) instead of in decimal-positional notation. Unicode 4 explicitly assigns Han number characters the Numeric_Type Numeric instead of Decimal. See Jitterbug 1483 for more details. Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue() for complete numeric Unicode properties.
|
|
Returns the bidirectional category value for the code point, which is used in the Unicode bidirectional algorithm (UAX #9 http://www.unicode.org/reports/tr9/). Note that some unassigned code points have bidi values of R or AL because they are in blocks that are reserved for Right-To-Left scripts. Same as java.lang.Character.getDirectionality()
|
|
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
|
|
Maps the specified character to a "mirror-image" character. For characters with the Bidi_Mirrored property, implementations sometimes need a "poor man's" mapping to another Unicode character (code point) such that the default glyph may serve as the mirror-image of the default glyph of the specified character. This is useful for text conversion to and from codepages with visual order, and for displays without glyph selecetion capabilities.
|
|
Retrieve the name of a Unicode character.
Depending on
|
|
Returns the general category value for the code point. Same as java.lang.Character.getType().
|
|
Returns the decimal digit value of the code point in the specified radix.
If the radix is not in the range
Same as java.lang.Character.digit().
|
|
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.
|
|
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.
|
|
The given character is mapped to its case folding equivalent according to UnicodeData.txt and CaseFolding.txt; if the character has no case folding equivalent, the character itself is returned. This function only returns the simple, single-code point case mapping. Full case mappings may result in zero, one or more code points and depend on context or language etc. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class.
|
|
Determines the character representation for a specific digit in the specified radix.
If the value of
The
If the digit is less than 10, then Same as java.lang.Character.forDigit().
|
|
Returns the combining class of the code point as specified in UnicodeData.txt.
|
|
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/
|
|
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):
For undefined UProperty constant values, min/max values will be 0/-1.
|
|
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.
|
|
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);
|
|
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.
|
|
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. Similar to java.lang.Character.getNumericValue(), but u_getNumericValue() also supports negative values, large values, and fractions, while Java's getNumericValue() returns values 10..35 for ASCII letters.
|
|
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.
|
|
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.
|
|
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".
|
|
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".
|
|
Gets the Unicode version information. The version array is filled in with the version information for the Unicode standard that is currently used by ICU. For example, Unicode version 3.1.1 is represented as an array with the values { 3, 1, 1, 0 }.
|
|
Check a binary Unicode property for a code point. Unicode, especially in version 3.2, defines many more properties than the original set in UnicodeData.txt. The properties APIs are intended to reflect Unicode properties as defined in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR). For details about the properties see http://www.unicode.org/ucd/ . For names of Unicode properties see the UCD file PropertyAliases.txt. Important: If ICU is built with UCD files from Unicode versions below 3.2, then properties marked with "new in Unicode 3.2" are not or not fully available.
|
|
Determines whether the specified code point is an alphanumeric character (letter or digit) according to Java. True for characters with general categories "L" (letters) and "Nd" (decimal digit numbers). Same as java.lang.Character.isLetterOrDigit(). In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a letter character. True for general categories "L" (letters). Same as java.lang.Character.isLetter(). In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a base character. True for general categories "L" (letters), "N" (numbers), "Mc" (spacing combining marks), and "Me" (enclosing marks). Note that this is different from the Unicode definition in chapter 3.5, conformance clause D13, which defines base characters to be all characters (not Cn) that do not graphically combine with preceding characters (M) and that are neither control (Cc) or format (Cf) characters.
|
|
Determines whether the specified code point is a "blank" or "horizontal space", a character that visibly separates words on a line. The following are equivalent definitions: TRUE for Unicode White_Space characters except for "vertical space controls" where "vertical space controls" are the following characters: U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS) same as TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators) except Zero Width Space (ZWSP, U+200B). Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison. This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a control character (as defined by this function). A control character is one of the following:
This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is "defined", which usually means that it is assigned a character. True for general categories other than "Cn" (other, not assigned), i.e., true for all code points mentioned in UnicodeData.txt. Note that non-character code points (e.g., U+FDD0) are not "defined" (they are Cn), but surrogate code points are "defined" (Cs). Same as java.lang.Character.isDefined().
|
|
Determines whether the specified code point is a digit character according to Java. True for characters with general category "Nd" (decimal digit numbers). Beginning with Unicode 4, this is the same as testing for the Numeric_Type of Decimal. Same as java.lang.Character.isDigit(). In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a "graphic" character (printable, excluding spaces). TRUE for all characters except those with general categories "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates), "Cn" (unassigned), and "Z" (separators). This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines if the specified character should be regarded as an ignorable character in an identifier, according to Java. True for characters with general category "Cf" (format controls) as well as non-whitespace ISO controls (U+0000..U+0008, U+000E..U+001B, U+007F..U+0084, U+0086..U+009F). Same as java.lang.Character.isIdentifierIgnorable() except that Java also returns TRUE for U+0085 Next Line (it omits U+0085 from whitespace ISO controls). Note that Unicode just recommends to ignore Cf (format controls).
|
|
Determines if the specified character is permissible in an identifier according to Java. True for characters with general categories "L" (letters), "Nl" (letter numbers), "Nd" (decimal digits), "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and u_isIDIgnorable(c). Same as java.lang.Character.isUnicodeIdentifierPart(). Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE) except that Unicode recommends to ignore Cf which is less than u_isIDIgnorable(c).
|
|
Determines if the specified character is permissible as the first character in an identifier according to Unicode (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers). True for characters with general categories "L" (letters) and "Nl" (letter numbers). Same as java.lang.Character.isUnicodeIdentifierStart(). Same as UCHAR_ID_START
|
|
Determines whether the specified code point is an ISO control code. True for U+0000..U+001f and U+007f..U+009f (general category "Cc"). Same as java.lang.Character.isISOControl().
|
|
Determines if the specified character is permissible in a Java identifier. In addition to u_isIDPart(c), true for characters with general category "Sc" (currency symbols). Same as java.lang.Character.isJavaIdentifierPart().
|
|
Determines if the specified character is permissible as the first character in a Java identifier. In addition to u_isIDStart(c), true for characters with general categories "Sc" (currency symbols) and "Pc" (connecting punctuation). Same as java.lang.Character.isJavaIdentifierStart().
|
|
Determine if the specified code point is a space character according to Java. True for characters with general categories "Z" (separators), which does not include control codes (e.g., TAB or Line Feed). Same as java.lang.Character.isSpaceChar(). Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.
|
|
Determines whether the specified code point has the general category "Ll" (lowercase letter). Same as java.lang.Character.isLowerCase(). This misses some characters that are also lowercase but have a different general category value. In order to include those, use UCHAR_LOWERCASE. In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the code point has the Bidi_Mirrored property. This property is set for characters that are commonly used in Right-To-Left contexts and need to be displayed with a "mirrored" glyph. Same as java.lang.Character.isMirrored(). Same as UCHAR_BIDI_MIRRORED
|
|
Determines whether the specified code point is a printable character. True for general categories other than "C" (controls). This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a punctuation character. True for characters with general categories "P" (punctuation). This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines if the specified character is a space character or not. Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison. This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Determines whether the specified code point is a titlecase letter. True for general category "Lt" (titlecase letter). Same as java.lang.Character.isTitleCase().
|
|
Check if a code point has the Alphabetic Unicode property. Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC). This is different from u_isalpha!
|
|
Check if a code point has the Lowercase Unicode property. Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE). This is different from u_islower!
|
|
Determines whether the specified code point has the general category "Lu" (uppercase letter). Same as java.lang.Character.isUpperCase(). This misses some characters that are also uppercase but have a different general category value. In order to include those, use UCHAR_UPPERCASE. In addition to being equivalent to a Java function, this also serves as a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
Check if a code point has the Uppercase Unicode property. Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE). This is different from u_isupper!
|
|
Check if a code point has the White_Space Unicode property. Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE). This is different from both u_isspace and u_isWhitespace! Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.
|
|
Determines if the specified code point is a whitespace character according to Java/ICU. A character is considered to be a Java whitespace character if and only if it satisfies one of the following criteria:
Same as java.lang.Character.isWhitespace() except that Java omits U+0085. Note: There are several ICU whitespace functions; please see the uchar.h file documentation for a detailed comparison.
|
|
Determines whether the specified code point is a hexadecimal digit. This is equivalent to u_digit(c, 16)>=0. True for characters with general category "Nd" (decimal digit numbers) as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII. (That is, for letters with code points 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.) In order to narrow the definition of hexadecimal digits to only ASCII characters, use (c<=0x7f && u_isxdigit(c)). This is a C/POSIX migration function. See the comments about C/POSIX character classification functions in the documentation at the top of this header file.
|
|
The given character is mapped to its lowercase equivalent according to UnicodeData.txt; if the character has no lowercase equivalent, the character itself is returned. Same as java.lang.Character.toLowerCase(). This function only returns the simple, single-code point case mapping. Full case mappings may result in zero, one or more code points and depend on context or language etc. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class.
|
|
The given character is mapped to its titlecase equivalent according to UnicodeData.txt; if none is defined, the character itself is returned. Same as java.lang.Character.toTitleCase(). This function only returns the simple, single-code point case mapping. Full case mappings may result in zero, one or more code points and depend on context or language etc. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class.
|
|
The given character is mapped to its uppercase equivalent according to UnicodeData.txt; if the character has no uppercase equivalent, the character itself is returned. Same as java.lang.Character.toUpperCase(). This function only returns the simple, single-code point case mapping. Full case mappings may result in zero, one or more code points and depend on context or language etc. Full case mappings are applied by the string case mapping functions, see ustring.h and the UnicodeString class.
|
|
Returns the Unicode allocation block that contains the character.
|