#include "unicode/utypes.h"
Go to the source code of this file.
Defines | |
#define | U_UNICODE_VERSION "3.0.0" |
#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... | |
Typedefs | |
typedef enum UCharCategory | UCharCategory |
typedef enum UCharDirection | UCharDirection |
typedef enum UCharScript | UCharScript |
typedef enum UCellWidth | UCellWidth |
typedef enum UCharNameChoice | UCharNameChoice |
Enumerations | |
enum | UCharCategory { U_UNASSIGNED = 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_GENERAL_OTHER_TYPES = 30, 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 | UCharScript { U_BASIC_LATIN, U_LATIN_1_SUPPLEMENT, U_LATIN_EXTENDED_A, U_LATIN_EXTENDED_B, U_IPA_EXTENSIONS, U_SPACING_MODIFIER_LETTERS, U_COMBINING_DIACRITICAL_MARKS, U_GREEK, U_CYRILLIC, U_ARMENIAN, U_HEBREW, U_ARABIC, U_SYRIAC, U_THAANA, U_DEVANAGARI, U_BENGALI, U_GURMUKHI, U_GUJARATI, U_ORIYA, U_TAMIL, U_TELUGU, U_KANNADA, U_MALAYALAM, U_SINHALA, U_THAI, U_LAO, U_TIBETAN, U_MYANMAR, U_GEORGIAN, U_HANGUL_JAMO, U_ETHIOPIC, U_CHEROKEE, U_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS, U_OGHAM, U_RUNIC, U_KHMER, U_MONGOLIAN, U_LATIN_EXTENDED_ADDITIONAL, U_GREEK_EXTENDED, U_GENERAL_PUNCTUATION, U_SUPERSCRIPTS_AND_SUBSCRIPTS, U_CURRENCY_SYMBOLS, U_COMBINING_MARKS_FOR_SYMBOLS, U_LETTERLIKE_SYMBOLS, U_NUMBER_FORMS, U_ARROWS, U_MATHEMATICAL_OPERATORS, U_MISCELLANEOUS_TECHNICAL, U_CONTROL_PICTURES, U_OPTICAL_CHARACTER_RECOGNITION, U_ENCLOSED_ALPHANUMERICS, U_BOX_DRAWING, U_BLOCK_ELEMENTS, U_GEOMETRIC_SHAPES, U_MISCELLANEOUS_SYMBOLS, U_DINGBATS, U_BRAILLE_PATTERNS, U_CJK_RADICALS_SUPPLEMENT, U_KANGXI_RADICALS, U_IDEOGRAPHIC_DESCRIPTION_CHARACTERS, U_CJK_SYMBOLS_AND_PUNCTUATION, U_HIRAGANA, U_KATAKANA, U_BOPOMOFO, U_HANGUL_COMPATIBILITY_JAMO, U_KANBUN, U_BOPOMOFO_EXTENDED, U_ENCLOSED_CJK_LETTERS_AND_MONTHS, U_CJK_COMPATIBILITY, U_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A, U_CJK_UNIFIED_IDEOGRAPHS, U_YI_SYLLABLES, U_YI_RADICALS, U_HANGUL_SYLLABLES, U_HIGH_SURROGATES, U_HIGH_PRIVATE_USE_SURROGATES, U_LOW_SURROGATES, U_PRIVATE_USE_AREA, U_CJK_COMPATIBILITY_IDEOGRAPHS, U_ALPHABETIC_PRESENTATION_FORMS, U_ARABIC_PRESENTATION_FORMS_A, U_COMBINING_HALF_MARKS, U_CJK_COMPATIBILITY_FORMS, U_SMALL_FORM_VARIANTS, U_ARABIC_PRESENTATION_FORMS_B, U_SPECIALS, U_HALFWIDTH_AND_FULLWIDTH_FORMS, U_CHAR_SCRIPT_COUNT, U_NO_SCRIPT = U_CHAR_SCRIPT_COUNT } |
Generated from Unicode Data files 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 | UCharNameChoice { U_UNICODE_CHAR_NAME, U_UNICODE_10_CHAR_NAME, U_CHAR_NAME_CHOICE_COUNT } |
Selector constants for u_charName(). More... | |
Functions | |
U_CAPI UBool U_EXPORT2 | u_islower (UChar32 c) |
Determines whether the specified UChar is a lowercase character according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isupper (UChar32 c) |
Determines whether the specified character is an uppercase character according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_istitle (UChar32 c) |
Determines whether the specified character is a titlecase character according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isdigit (UChar32 c) |
Determines whether the specified character is a digit according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isalnum (UChar32 c) |
Determines whether the specified character is an alphanumeric character (letter or digit)according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isdefined (UChar32 c) |
Determines whether the specified numeric value is actually a defined character according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isalpha (UChar32 c) |
Determines whether the specified character is a letter according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isspace (UChar32 c) |
Determines if the specified character is a space character or not. More... | |
U_CAPI UBool U_EXPORT2 | u_isWhitespace (UChar32 c) |
Determines if the specified character is white space according to ICU. More... | |
U_CAPI UBool U_EXPORT2 | u_iscntrl (UChar32 c) |
Determines whether the specified character is a control character or not. More... | |
U_CAPI UBool U_EXPORT2 | u_isprint (UChar32 c) |
Determines whether the specified character is a printable character according to Unicode 2.1.2. More... | |
U_CAPI UBool U_EXPORT2 | u_isbase (UChar32 c) |
Determines whether the specified character is of the base form according to Unicode 2.1.2. More... | |
U_CAPI UCharDirection U_EXPORT2 | u_charDirection (UChar32 c) |
Returns the linguistic direction property of a character. More... | |
U_CAPI UBool U_EXPORT2 | u_isMirrored (UChar32 c) |
Determines whether the character has the "mirrored" property. More... | |
U_CAPI UChar32 U_EXPORT2 | u_charMirror (UChar32 c) |
Maps the specified character to a "mirror-image" character. More... | |
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. More... | |
U_CAPI int8_t U_EXPORT2 | u_charType (UChar32 c) |
Returns a value indicating a character category according to Unicode 2.1.2. More... | |
U_CAPI int32_t U_EXPORT2 | u_charDigitValue (UChar32 c) |
Retrives the decimal numeric value of a digit character. More... | |
U_CAPI UCharScript U_EXPORT2 | u_charScript (UChar32 ch) |
Returns the script associated with a character. More... | |
U_CAPI UTextOffset U_EXPORT2 | u_charName (UChar32 code, UCharNameChoice nameChoice, char *buffer, UTextOffset bufferLength, UErrorCode *pErrorCode) |
Retrieve the name of a Unicode character. More... | |
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. More... | |
U_CDECL_BEGIN typedef UBool | UEnumCharNamesFn (void *context, UChar32 code, UCharNameChoice nameChoice, const char *name, UTextOffset 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... | |
U_CDECL_END 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. More... | |
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. More... | |
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. More... | |
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. More... | |
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. More... | |
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. More... | |
U_CAPI UChar32 U_EXPORT2 | u_tolower (UChar32 c) |
The given character is mapped to its lowercase equivalent according to Unicode 2.1.2; if the character has no lowercase equivalent, the character itself is returned. More... | |
U_CAPI UChar32 U_EXPORT2 | u_toupper (UChar32 c) |
The given character is mapped to its uppercase equivalent according to Unicode 2.1.2; if the character has no uppercase equivalent, the character itself is returned. More... | |
U_CAPI UChar32 U_EXPORT2 | u_totitle (UChar32 c) |
The given character is mapped to its titlecase equivalent according to Unicode 2.1.2. More... | |
U_CAPI void U_EXPORT2 | u_getUnicodeVersion (UVersionInfo info) |
Gets the Unicode version information. More... |
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.
|
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. |
|
|
|
|
|
|
|
|
|
|
|
|
|
Values returned by the u_getCellWidth() function.
|
|
Data for enumerated Unicode general category types.
|
|
|
Selector constants for u_charName().
|
|
Generated from Unicode Data files These are the same values as Unicode::EUnicodeScript.
|
|
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.
|
|
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: 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 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 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 NEUTRAL: 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.
Referenced by Unicode::getCellWidth(). |
|
Retrives the decimal numeric value of a digit character.
Referenced by Unicode::digit(), and Unicode::digitValue(). |
|
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.
Referenced by Unicode::characterDirection(). |
|
Find a Unicode character by its name and return its code point value. The name is matched exactly and completely. A Unicode 1.0 name is matched only if it differs from the modern name. Unicode names are all uppercase.
|
|
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.
Referenced by Unicode::charMirror(). |
|
Retrieve the name of a Unicode character.
Depending on
Referenced by Unicode::getCharName(). |
|
Returns the script associated with a character.
Referenced by Unicode::getScript(). |
|
Returns a value indicating a character category according to Unicode 2.1.2.
Referenced by Unicode::getType(). |
|
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.
|
|
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.
Referenced by Unicode::getUnicodeVersion(). |
|
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:
Referenced by Unicode::isIdentifierIgnorable(). |
|
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:
Referenced by Unicode::isUnicodeIdentifierPart(). |
|
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.
Referenced by Unicode::isUnicodeIdentifierStart(). |
|
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:
Referenced by Unicode::isJavaIdentifierPart(). |
|
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:
Referenced by Unicode::isJavaIdentifierStart(). |
|
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.
Referenced by Unicode::isMirrored(). |
|
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() .
Referenced by Unicode::isWhitespace(). |
|
Determines whether the specified character is an alphanumeric character (letter or digit)according to Unicode 2.1.2.
|
|
Determines whether the specified character is a letter according to Unicode 2.1.2.
Referenced by Unicode::isLetter(). |
|
Determines whether the specified character is of the base form according to Unicode 2.1.2.
Referenced by Unicode::isBaseForm(). |
|
Determines whether the specified character is a control character or not.
Referenced by Unicode::isControl(). |
|
Determines whether the specified numeric value is actually a defined character according to Unicode 2.1.2.
Referenced by Unicode::isDefined(). |
|
Determines whether the specified character is a digit according to Unicode 2.1.2.
Referenced by Unicode::isDigit(). |
|
Determines whether the specified UChar is a lowercase character according to Unicode 2.1.2.
Referenced by Unicode::isLowerCase(). |
|
Determines whether the specified character is a printable character according to Unicode 2.1.2.
Referenced by Unicode::isPrintable(). |
|
Determines if the specified character is a space character or not.
Referenced by Unicode::isSpaceChar(). |
|
Determines whether the specified character is a titlecase character according to Unicode 2.1.2.
Referenced by Unicode::isTitleCase(). |
|
Determines whether the specified character is an uppercase character according to Unicode 2.1.2.
Referenced by Unicode::isUpperCase(). |
|
The given character is mapped to its lowercase equivalent according to Unicode 2.1.2; 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 Unicode 2.1.2 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.
Referenced by Unicode::toLowerCase(). |
|
The given character is mapped to its titlecase equivalent according to Unicode 2.1.2. 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 Unicode 2.1.2 data.
Referenced by Unicode::toTitleCase(). |
|
The given character is mapped to its uppercase equivalent according to Unicode 2.1.2; 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.
Referenced by Unicode::toUpperCase(). |