uchar.h

linux下开源浏览器WebKit的源码,市面上的很多商用浏览器都是移植自WebKit

 *         constant of the respective property value enumeration type
 *         (cast to enum type if necessary).
 *         Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
 *         Returns a bit-mask for mask properties.
 *         Returns 0 if 'which' is out of bounds or if the Unicode version
 *         does not have data for the property at all, or not for this code point.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getIntPropertyMinValue
 * @see u_getIntPropertyMaxValue
 * @see u_getUnicodeVersion
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyValue(UChar32 c, UProperty which);

/**
 * Get the minimum value for an enumerated/integer/binary Unicode property.
 * Can be used together with u_getIntPropertyMaxValue
 * to allocate arrays of UnicodeSet or similar.
 *
 * @param which UProperty selector constant, identifies which binary property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
 *         0 if the property selector is out of range.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getUnicodeVersion
 * @see u_getIntPropertyMaxValue
 * @see u_getIntPropertyValue
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyMinValue(UProperty which);

/**
 * Get the maximum value for an enumerated/integer/binary Unicode property.
 * Can be used together with u_getIntPropertyMinValue
 * to allocate arrays of UnicodeSet or similar.
 *
 * Examples for min/max values (for Unicode 3.2):
 *
 * - UCHAR_BIDI_CLASS:    0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
 * - UCHAR_SCRIPT:        0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
 * - UCHAR_IDEOGRAPHIC:   0/1  (FALSE/TRUE)
 *
 * For undefined UProperty constant values, min/max values will be 0/-1.
 *
 * @param which UProperty selector constant, identifies which binary property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
 *         <=0 if the property selector is out of range.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getUnicodeVersion
 * @see u_getIntPropertyMaxValue
 * @see u_getIntPropertyValue
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyMaxValue(UProperty which);

/**
 * 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.
 *
 * @param c Code point to get the numeric value for.
 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
 *
 * @see U_NO_NUMERIC_VALUE
 * @stable ICU 2.2
 */
U_STABLE double U_EXPORT2
u_getNumericValue(UChar32 c);

/**
 * Special value that is returned by u_getNumericValue when
 * no numeric value is defined for a code point.
 *
 * @see u_getNumericValue
 * @stable ICU 2.2
 */
#define U_NO_NUMERIC_VALUE ((double)-123456789.)

/**
 * 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.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Ll lowercase letter
 *
 * @see UCHAR_LOWERCASE
 * @see u_isupper
 * @see u_istitle
 * @see u_islower
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_islower(UChar32 c);

/**
 * Determines whether the specified code point has the general category "Lu"
 * (uppercase letter).
 *
 * Same as java.lang.Character.isUpperCase().
 *
 * This misses some characters that are also uppercase but
 * have a different general category value.
 * In order to include those, use UCHAR_UPPERCASE.
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Lu uppercase letter
 *
 * @see UCHAR_UPPERCASE
 * @see u_islower
 * @see u_istitle
 * @see u_tolower
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isupper(UChar32 c);

/**
 * Determines whether the specified code point is a titlecase letter.
 * True for general category "Lt" (titlecase letter).
 *
 * Same as java.lang.Character.isTitleCase().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Lt titlecase letter
 *
 * @see u_isupper
 * @see u_islower
 * @see u_totitle
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_istitle(UChar32 c);

/**
 * Determines whether the specified code point is a digit character according to Java.
 * True for characters with general category "Nd" (decimal digit numbers).
 * Beginning with Unicode 4, this is the same as
 * testing for the Numeric_Type of Decimal.
 *
 * Same as java.lang.Character.isDigit().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a digit character according to Character.isDigit()
 *
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isdigit(UChar32 c);

/**
 * Determines whether the specified code point is a letter character.
 * True for general categories "L" (letters).
 *
 * Same as java.lang.Character.isLetter().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a letter character
 *
 * @see u_isdigit
 * @see u_isalnum
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isalpha(UChar32 c);

/**
 * Determines whether the specified code point is an alphanumeric character
 * (letter or digit) according to Java.
 * True for characters with general categories
 * "L" (letters) and "Nd" (decimal digit numbers).
 *
 * Same as java.lang.Character.isLetterOrDigit().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
 *
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isalnum(UChar32 c);

/**
 * Determines whether the specified code point is a hexadecimal digit.
 * This is equivalent to u_digit(c, 16)>=0.
 * True for characters with general category "Nd" (decimal digit numbers)
 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
 * (That is, for letters with code points
 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
 *
 * In order to narrow the definition of hexadecimal digits to only ASCII
 * characters, use (c<=0x7f && u_isxdigit(c)).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a hexadecimal digit
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isxdigit(UChar32 c);

/**
 * Determines whether the specified code point is a punctuation character.
 * True for characters with general categories "P" (punctuation).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a punctuation character
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_ispunct(UChar32 c);

/**
 * Determines whether the specified code point is a "graphic" character
 * (printable, excluding spaces).
 * TRUE for all characters except those with general categories
 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
 * "Cn" (unassigned), and "Z" (separators).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a "graphic" character
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isgraph(UChar32 c);

/**
 * Determines whether the specified code point is a "blank" or "horizontal space",
 * a character that visibly separates words on a line.
 * The following are equivalent definitions:
 *
 * TRUE for Unicode White_Space characters except for "vertical space controls"
 * where "vertical space controls" are the following characters:
 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
 *
 * same as
 *
 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
 * 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.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a "blank"
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isblank(UChar32 c);

/**
 * Determines whether the specified code point is "defined",
 * which usually means that it is assigned a character.
 * True for general categories other than "Cn" (other, not assigned),
 * i.e., true for all code points mentioned in UnicodeData.txt.
 *
 * Note that non-character code points (e.g., U+FDD0) are not "defined"
 * (they are Cn), but surrogate code points are "defined" (Cs).
 *
 * Same as java.lang.Character.isDefined().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is assigned a character
 *
 * @see u_isdigit
 * @see u_isalpha
 * @see u_isalnum
 * @see u_isupper
 * @see u_islower
 * @see u_istitle
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isdefined(UChar32 c);

/**
 * Determines if the specified character is a space character or not.
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c    the character to be tested
 * @return  true if the character is a space character; false otherwise.
 *
 * @see u_isJavaSpaceChar
 * @see u_isWhitespace
 * @see u_isUWhiteSpace
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isspace(UChar32 c);

/**