#include "unicode/utypes.h"
Go to the source code of this file.
Defines | |
#define | U_UNICODE_VERSION "3.1.1" |
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) |
#define | U_GC_LL_MASK U_MASK(U_LOWERCASE_LETTER) |
#define | U_GC_LT_MASK U_MASK(U_TITLECASE_LETTER) |
#define | U_GC_LM_MASK U_MASK(U_MODIFIER_LETTER) |
#define | U_GC_LO_MASK U_MASK(U_OTHER_LETTER) |
#define | U_GC_MN_MASK U_MASK(U_NON_SPACING_MARK) |
#define | U_GC_ME_MASK U_MASK(U_ENCLOSING_MARK) |
#define | U_GC_MC_MASK U_MASK(U_COMBINING_SPACING_MARK) |
#define | U_GC_ND_MASK U_MASK(U_DECIMAL_DIGIT_NUMBER) |
#define | U_GC_NL_MASK U_MASK(U_LETTER_NUMBER) |
#define | U_GC_NO_MASK U_MASK(U_OTHER_NUMBER) |
#define | U_GC_ZS_MASK U_MASK(U_SPACE_SEPARATOR) |
#define | U_GC_ZL_MASK U_MASK(U_LINE_SEPARATOR) |
#define | U_GC_ZP_MASK U_MASK(U_PARAGRAPH_SEPARATOR) |
#define | U_GC_CC_MASK U_MASK(U_CONTROL_CHAR) |
#define | U_GC_CF_MASK U_MASK(U_FORMAT_CHAR) |
#define | U_GC_CO_MASK U_MASK(U_PRIVATE_USE_CHAR) |
#define | U_GC_CS_MASK U_MASK(U_SURROGATE) |
#define | U_GC_PD_MASK U_MASK(U_DASH_PUNCTUATION) |
#define | U_GC_PS_MASK U_MASK(U_START_PUNCTUATION) |
#define | U_GC_PE_MASK U_MASK(U_END_PUNCTUATION) |
#define | U_GC_PC_MASK U_MASK(U_CONNECTOR_PUNCTUATION) |
#define | U_GC_PO_MASK U_MASK(U_OTHER_PUNCTUATION) |
#define | U_GC_SM_MASK U_MASK(U_MATH_SYMBOL) |
#define | U_GC_SC_MASK U_MASK(U_CURRENCY_SYMBOL) |
#define | U_GC_SK_MASK U_MASK(U_MODIFIER_SYMBOL) |
#define | U_GC_SO_MASK U_MASK(U_OTHER_SYMBOL) |
#define | U_GC_PI_MASK U_MASK(U_INITIAL_PUNCTUATION) |
#define | U_GC_PF_MASK U_MASK(U_FINAL_PUNCTUATION) |
#define | U_GC_L_MASK (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK) |
#define | U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK) |
#define | U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK) |
#define | U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK) |
#define | U_GC_C_MASK (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK) |
#define | U_GC_P_MASK |
#define | U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK) |
#define | U_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 all mappings defined in CaseFolding.txt. | |
#define | U_FOLD_CASE_EXCLUDE_SPECIAL_I 1 |
Option value for case folding: exclude the mappings for dotted I and dotless i marked with 'I' in CaseFolding.txt. | |
#define | u_charScript ublock_getCode |
Typedefs | |
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. | |
typedef UBlockCode | UCharScript |
Enumerations | |
enum | UProperty { UCHAR_ALPHABETIC, 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 } |
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, U_BASIC_LATIN = 1, UBLOCK_LATIN_1_SUPPLEMENT = 2, U_LATIN_1_SUPPLEMENT = 2, UBLOCK_LATIN_EXTENDED_A = 3, U_LATIN_EXTENDED_A = 3, UBLOCK_LATIN_EXTENDED_B = 4, U_LATIN_EXTENDED_B = 4, UBLOCK_IPA_EXTENSIONS = 5, U_IPA_EXTENSIONS = 5, UBLOCK_SPACING_MODIFIER_LETTERS = 6, U_SPACING_MODIFIER_LETTERS = 6, UBLOCK_COMBINING_DIACRITICAL_MARKS = 7, U_COMBINING_DIACRITICAL_MARKS = 7, UBLOCK_GREEK = 8, U_GREEK = 8, UBLOCK_CYRILLIC = 9, U_CYRILLIC = 9, UBLOCK_ARMENIAN = 10, U_ARMENIAN = 10, UBLOCK_HEBREW = 11, U_HEBREW = 11, UBLOCK_ARABIC = 12, U_ARABIC = 12, UBLOCK_SYRIAC = 13, U_SYRIAC = 13, UBLOCK_THAANA = 14, U_THAANA = 14, UBLOCK_DEVANAGARI = 15, U_DEVANAGARI = 15, UBLOCK_BENGALI = 16, U_BENGALI = 16, UBLOCK_GURMUKHI = 17, U_GURMUKHI = 17, UBLOCK_GUJARATI = 18, U_GUJARATI = 18, UBLOCK_ORIYA = 19, U_ORIYA = 19, UBLOCK_TAMIL = 20, U_TAMIL = 20, UBLOCK_TELUGU = 21, U_TELUGU = 21, UBLOCK_KANNADA = 22, U_KANNADA = 22, UBLOCK_MALAYALAM = 23, U_MALAYALAM = 23, UBLOCK_SINHALA = 24, U_SINHALA = 24, UBLOCK_THAI = 25, U_THAI = 25, UBLOCK_LAO = 26, U_LAO = 26, UBLOCK_TIBETAN = 27, U_TIBETAN = 27, UBLOCK_MYANMAR = 28, U_MYANMAR = 28, UBLOCK_GEORGIAN = 29, U_GEORGIAN = 29, UBLOCK_HANGUL_JAMO = 30, U_HANGUL_JAMO = 30, UBLOCK_ETHIOPIC = 31, U_ETHIOPIC = 31, UBLOCK_CHEROKEE = 32, U_CHEROKEE = 32, UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 33, U_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS = 33, UBLOCK_OGHAM = 34, U_OGHAM = 34, UBLOCK_RUNIC = 35, U_RUNIC = 35, UBLOCK_KHMER = 36, U_KHMER = 36, UBLOCK_MONGOLIAN = 37, U_MONGOLIAN = 37, UBLOCK_LATIN_EXTENDED_ADDITIONAL = 38, U_LATIN_EXTENDED_ADDITIONAL = 38, UBLOCK_GREEK_EXTENDED = 39, U_GREEK_EXTENDED = 39, UBLOCK_GENERAL_PUNCTUATION = 40, U_GENERAL_PUNCTUATION = 40, UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS = 41, U_SUPERSCRIPTS_AND_SUBSCRIPTS = 41, UBLOCK_CURRENCY_SYMBOLS = 42, U_CURRENCY_SYMBOLS = 42, UBLOCK_COMBINING_MARKS_FOR_SYMBOLS = 43, U_COMBINING_MARKS_FOR_SYMBOLS = 43, UBLOCK_LETTERLIKE_SYMBOLS = 44, U_LETTERLIKE_SYMBOLS = 44, UBLOCK_NUMBER_FORMS = 45, U_NUMBER_FORMS = 45, UBLOCK_ARROWS = 46, U_ARROWS = 46, UBLOCK_MATHEMATICAL_OPERATORS = 47, U_MATHEMATICAL_OPERATORS = 47, UBLOCK_MISCELLANEOUS_TECHNICAL = 48, U_MISCELLANEOUS_TECHNICAL = 48, UBLOCK_CONTROL_PICTURES = 49, U_CONTROL_PICTURES = 49, UBLOCK_OPTICAL_CHARACTER_RECOGNITION = 50, U_OPTICAL_CHARACTER_RECOGNITION = 50, UBLOCK_ENCLOSED_ALPHANUMERICS = 51, U_ENCLOSED_ALPHANUMERICS = 51, UBLOCK_BOX_DRAWING = 52, U_BOX_DRAWING = 52, UBLOCK_BLOCK_ELEMENTS = 53, U_BLOCK_ELEMENTS = 53, UBLOCK_GEOMETRIC_SHAPES = 54, U_GEOMETRIC_SHAPES = 54, UBLOCK_MISCELLANEOUS_SYMBOLS = 55, U_MISCELLANEOUS_SYMBOLS = 55, UBLOCK_DINGBATS = 56, U_DINGBATS = 56, UBLOCK_BRAILLE_PATTERNS = 57, U_BRAILLE_PATTERNS = 57, UBLOCK_CJK_RADICALS_SUPPLEMENT = 58, U_CJK_RADICALS_SUPPLEMENT = 58, UBLOCK_KANGXI_RADICALS = 59, U_KANGXI_RADICALS = 59, UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 60, U_IDEOGRAPHIC_DESCRIPTION_CHARACTERS = 60, UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION = 61, U_CJK_SYMBOLS_AND_PUNCTUATION = 61, UBLOCK_HIRAGANA = 62, U_HIRAGANA = 62, UBLOCK_KATAKANA = 63, U_KATAKANA = 63, UBLOCK_BOPOMOFO = 64, U_BOPOMOFO = 64, UBLOCK_HANGUL_COMPATIBILITY_JAMO = 65, U_HANGUL_COMPATIBILITY_JAMO = 65, UBLOCK_KANBUN = 66, U_KANBUN = 66, UBLOCK_BOPOMOFO_EXTENDED = 67, U_BOPOMOFO_EXTENDED = 67, UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS = 68, U_ENCLOSED_CJK_LETTERS_AND_MONTHS = 68, UBLOCK_CJK_COMPATIBILITY = 69, U_CJK_COMPATIBILITY = 69, UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 70, U_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A = 70, UBLOCK_CJK_UNIFIED_IDEOGRAPHS = 71, U_CJK_UNIFIED_IDEOGRAPHS = 71, UBLOCK_YI_SYLLABLES = 72, U_YI_SYLLABLES = 72, UBLOCK_YI_RADICALS = 73, U_YI_RADICALS = 73, UBLOCK_HANGUL_SYLLABLES = 74, U_HANGUL_SYLLABLES = 74, UBLOCK_HIGH_SURROGATES = 75, U_HIGH_SURROGATES = 75, UBLOCK_HIGH_PRIVATE_USE_SURROGATES = 76, U_HIGH_PRIVATE_USE_SURROGATES = 76, UBLOCK_LOW_SURROGATES = 77, U_LOW_SURROGATES = 77, UBLOCK_PRIVATE_USE = 78, UBLOCK_PRIVATE_USE_AREA = UBLOCK_PRIVATE_USE, U_PRIVATE_USE_AREA = 78, UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS = 79, U_CJK_COMPATIBILITY_IDEOGRAPHS = 79, UBLOCK_ALPHABETIC_PRESENTATION_FORMS = 80, U_ALPHABETIC_PRESENTATION_FORMS = 80, UBLOCK_ARABIC_PRESENTATION_FORMS_A = 81, U_ARABIC_PRESENTATION_FORMS_A = 81, UBLOCK_COMBINING_HALF_MARKS = 82, U_COMBINING_HALF_MARKS = 82, UBLOCK_CJK_COMPATIBILITY_FORMS = 83, U_CJK_COMPATIBILITY_FORMS = 83, UBLOCK_SMALL_FORM_VARIANTS = 84, U_SMALL_FORM_VARIANTS = 84, UBLOCK_ARABIC_PRESENTATION_FORMS_B = 85, U_ARABIC_PRESENTATION_FORMS_B = 85, UBLOCK_SPECIALS = 86, U_SPECIALS = 86, UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS = 87, U_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_COUNT = 97, U_SCRIPT_COUNT = UBLOCK_COUNT, UBLOCK_INVALID_CODE = -1, U_CHAR_SCRIPT_COUNT = UBLOCK_COUNT, U_NO_SCRIPT = UBLOCK_COUNT } |
Constants for Unicode blocks, generated from Unicode Data file Blocks.txt These are the same values as Unicode::EUnicodeScript ICU 2.0. 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 | 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... | |
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 UBool U_EXPORT2 | u_islower (UChar32 c) |
Determines whether the specified UChar is a lowercase character according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isupper (UChar32 c) |
Determines whether the specified character is an uppercase character according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_istitle (UChar32 c) |
Determines whether the specified character is a titlecase character according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isdigit (UChar32 c) |
Determines whether the specified character is a digit according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isalnum (UChar32 c) |
Determines whether the specified character is an alphanumeric character (letter or digit)according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isdefined (UChar32 c) |
Determines whether the specified numeric value is actually a defined character according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isalpha (UChar32 c) |
Determines whether the specified character is a letter according to UnicodeData.txt. | |
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_isWhitespace (UChar32 c) |
Determines if the specified character is white space according to ICU. | |
U_CAPI UBool U_EXPORT2 | u_iscntrl (UChar32 c) |
Determines whether the specified character is a control character or not. | |
U_CAPI UBool U_EXPORT2 | u_isprint (UChar32 c) |
Determines whether the specified character is a printable character according to UnicodeData.txt. | |
U_CAPI UBool U_EXPORT2 | u_isbase (UChar32 c) |
Determines whether the specified character is of the base form according to UnicodeData.txt. | |
U_CAPI UCharDirection U_EXPORT2 | u_charDirection (UChar32 c) |
Returns the linguistic direction property of a character. | |
U_CAPI UBool U_EXPORT2 | u_isMirrored (UChar32 c) |
Determines whether the character has the "mirrored" property. | |
U_CAPI UChar32 U_EXPORT2 | u_charMirror (UChar32 c) |
Maps the specified character to a "mirror-image" character. | |
U_CAPI uint16_t U_EXPORT2 | u_charCellWidth (UChar32 c) |
Returns a value indicating the display-cell width of the character when used in Asian text, according to the Unicode standard (see p. | |
U_CAPI int8_t U_EXPORT2 | u_charType (UChar32 c) |
Returns a value indicating a character category. | |
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) |
Retrives the decimal numeric value of a digit character. | |
U_CAPI UBlockCode U_EXPORT2 | ublock_getCode (UChar32 ch) |
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 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 UBool U_EXPORT2 | u_isIDStart (UChar32 c) |
A convenience method for determining if a Unicode character is allowed to start in a Unicode identifier. | |
U_CAPI UBool U_EXPORT2 | 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. | |
U_CAPI UBool U_EXPORT2 | u_isIDIgnorable (UChar32 c) |
A convenience method for determining if a Unicode character should be regarded as an ignorable character in a Unicode identifier. | |
U_CAPI UBool U_EXPORT2 | u_isJavaIDStart (UChar32 c) |
A convenience method for determining if a Unicode character is allowed as the first character in a Java identifier. | |
U_CAPI UBool U_EXPORT2 | 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. | |
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. | |
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 numeric value of the character ch 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 info) |
Gets the Unicode version information. |
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.
|
|
|
Option value for case folding: use all mappings defined in CaseFolding.txt. ICU 1.8 |
|
Option value for case folding: exclude the mappings for dotted I and dotless i marked with 'I' in CaseFolding.txt. ICU 1.8 |
|
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.
|
|
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) |
|
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 |
|
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. |
|
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.
|
|
|
|
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.
|
|
Constants for Unicode blocks, generated from Unicode Data file Blocks.txt These are the same values as Unicode::EUnicodeScript ICU 2.0.
|
|
Values returned by the u_getCellWidth() function.
|
|
Data for enumerated Unicode general category types. See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
|
|
|
Selector constants for u_charName().
|
|
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.
|
|
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 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. |
|
Retrives the decimal numeric value of a digit character.
|
|
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.
|
|
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 "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 a value indicating a character category. The categories are taken from the Unicode Character Database (UCD) in UnicodeData.txt.
|
|
Returns the numeric value of the character
If the radix is not in the range
|
|
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. Only "simple", single-code point case folding mappings are used. "Full" mappings are used by u_strFoldCase().
|
|
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
|
|
Returns the combining class of the code point as specified in UnicodeData.txt.
|
|
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.
|
|
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. This API is 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. 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.
|
|
Determines whether the specified character is an alphanumeric character (letter or digit)according to UnicodeData.txt.
|
|
Determines whether the specified character is a letter according to UnicodeData.txt.
|
|
Determines whether the specified character is of the base form according to UnicodeData.txt.
|
|
Determines whether the specified character is a control character or not. A control character is one of the following:
|
|
Determines whether the specified numeric value is actually a defined character according to UnicodeData.txt.
|
|
Determines whether the specified character is a digit according to UnicodeData.txt.
|
|
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:
|
|
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 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.
|
|
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 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:
|
|
Determines whether the specified UChar is a lowercase character according to UnicodeData.txt.
|
|
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.
|
|
Determines whether the specified character is a printable character according to UnicodeData.txt.
|
|
Determines if the specified character is a space character or not.
|
|
Determines whether the specified character is a titlecase character according to UnicodeData.txt.
|
|
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 character is an uppercase character according to UnicodeData.txt.
|
|
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!
|
|
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:
java.lang.Character.isWhitespace() .
|
|
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.
|
|
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.
|
|
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.
|
|
Returns the Unicode allocation block that contains the character.
|