ustring.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

 * @param string The string in which to search, NUL-terminated.
 * @param matchSet A NUL-terminated string defining a set of code points
 *                 for which to search in the text string.
 * @return A pointer to the  character in <code>string</code> that matches one of the
 *         characters in <code>matchSet</code>, or NULL if no such character is found.
 * @stable ICU 2.0
 */
U_STABLE UChar * U_EXPORT2
u_strpbrk(const UChar *string, const UChar *matchSet);

/**
 * Returns the number of consecutive characters in <code>string</code>,
 * beginning with the first, that do not occur somewhere in <code>matchSet</code>.
 * Works just like C's strcspn but with Unicode.
 *
 * @param string The string in which to search, NUL-terminated.
 * @param matchSet A NUL-terminated string defining a set of code points
 *                 for which to search in the text string.
 * @return The number of initial characters in <code>string</code> that do not
 *         occur in <code>matchSet</code>.
 * @see u_strspn
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strcspn(const UChar *string, const UChar *matchSet);

/**
 * Returns the number of consecutive characters in <code>string</code>,
 * beginning with the first, that occur somewhere in <code>matchSet</code>.
 * Works just like C's strspn but with Unicode.
 *
 * @param string The string in which to search, NUL-terminated.
 * @param matchSet A NUL-terminated string defining a set of code points
 *                 for which to search in the text string.
 * @return The number of initial characters in <code>string</code> that do
 *         occur in <code>matchSet</code>.
 * @see u_strcspn
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strspn(const UChar *string, const UChar *matchSet);

/**
 * The string tokenizer API allows an application to break a string into
 * tokens. Unlike strtok(), the saveState (the current pointer within the
 * original string) is maintained in saveState. In the first call, the
 * argument src is a pointer to the string. In subsequent calls to
 * return successive tokens of that string, src must be specified as
 * NULL. The value saveState is set by this function to maintain the
 * function's position within the string, and on each subsequent call
 * you must give this argument the same variable. This function does
 * handle surrogate pairs. This function is similar to the strtok_r()
 * the POSIX Threads Extension (1003.1c-1995) version.
 *
 * @param src String containing token(s). This string will be modified.
 *            After the first call to u_strtok_r(), this argument must
 *            be NULL to get to the next token.
 * @param delim Set of delimiter characters (Unicode code points).
 * @param saveState The current pointer within the original string,
 *              which is set by this function. The saveState
 *              parameter should the address of a local variable of type
 *              UChar *. (i.e. defined "Uhar *myLocalSaveState" and use
 *              &myLocalSaveState for this parameter).
 * @return A pointer to the next token found in src, or NULL
 *         when there are no more tokens.
 * @stable ICU 2.0
 */
U_STABLE UChar * U_EXPORT2
u_strtok_r(UChar    *src, 
     const UChar    *delim,
           UChar   **saveState);

/**
 * Compare two Unicode strings for bitwise equality (code unit order).
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative
 * value if <code>s1</code> is bitwise less than <code>s2,</code>; a positive
 * value if <code>s1</code> is bitwise greater than <code>s2</code>.
 * @stable ICU 2.0
 */
U_STABLE int32_t  U_EXPORT2
u_strcmp(const UChar     *s1, 
         const UChar     *s2);

/**
 * Compare two Unicode strings in code point order.
 * See u_strCompare for details.
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @return a negative/zero/positive integer corresponding to whether
 * the first string is less than/equal to/greater than the second one
 * in code point order
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strcmpCodePointOrder(const UChar *s1, const UChar *s2);

/**
 * Compare two Unicode strings (binary order).
 *
 * The comparison can be done in code unit order or in code point order.
 * They differ only in UTF-16 when
 * comparing supplementary code points (U+10000..U+10ffff)
 * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff).
 * In code unit order, high BMP code points sort after supplementary code points
 * because they are stored as pairs of surrogates which are at U+d800..U+dfff.
 *
 * This functions works with strings of different explicitly specified lengths
 * unlike the ANSI C-like u_strcmp() and u_memcmp() etc.
 * NUL-terminated strings are possible with length arguments of -1.
 *
 * @param s1 First source string.
 * @param length1 Length of first source string, or -1 if NUL-terminated.
 *
 * @param s2 Second source string.
 * @param length2 Length of second source string, or -1 if NUL-terminated.
 *
 * @param codePointOrder Choose between code unit order (FALSE)
 *                       and code point order (TRUE).
 *
 * @return <0 or 0 or >0 as usual for string comparisons
 *
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_strCompare(const UChar *s1, int32_t length1,
             const UChar *s2, int32_t length2,
             UBool codePointOrder);

/**
 * Compare two Unicode strings (binary order)
 * as presented by UCharIterator objects.
 * Works otherwise just like u_strCompare().
 *
 * Both iterators are reset to their start positions.
 * When the function returns, it is undefined where the iterators
 * have stopped.
 *
 * @param iter1 First source string iterator.
 * @param iter2 Second source string iterator.
 * @param codePointOrder Choose between code unit order (FALSE)
 *                       and code point order (TRUE).
 *
 * @return <0 or 0 or >0 as usual for string comparisons
 *
 * @see u_strCompare
 *
 * @stable ICU 2.6
 */
U_STABLE int32_t U_EXPORT2
u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder);

#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also unistr.h and unorm.h */
/**
 * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
 * Compare strings in code point order instead of code unit order.
 * @stable ICU 2.2
 */
#define U_COMPARE_CODE_POINT_ORDER  0x8000
#endif

/**
 * Compare two strings case-insensitively using full case folding.
 * This is equivalent to
 *   u_strCompare(u_strFoldCase(s1, options),
 *                u_strFoldCase(s2, options),
 *                (options&U_COMPARE_CODE_POINT_ORDER)!=0).
 *
 * The comparison can be done in UTF-16 code unit order or in code point order.
 * They differ only when comparing supplementary code points (U+10000..U+10ffff)
 * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff).
 * In code unit order, high BMP code points sort after supplementary code points
 * because they are stored as pairs of surrogates which are at U+d800..U+dfff.
 *
 * This functions works with strings of different explicitly specified lengths
 * unlike the ANSI C-like u_strcmp() and u_memcmp() etc.
 * NUL-terminated strings are possible with length arguments of -1.
 *
 * @param s1 First source string.
 * @param length1 Length of first source string, or -1 if NUL-terminated.
 *
 * @param s2 Second source string.
 * @param length2 Length of second source string, or -1 if NUL-terminated.
 *
 * @param options A bit set of options:
 *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 *     Comparison in code unit order with default case folding.
 *
 *   - U_COMPARE_CODE_POINT_ORDER
 *     Set to choose code point order instead of code unit order
 *     (see u_strCompare for details).
 *
 *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 *
 * @param pErrorCode Must be a valid pointer to an error code value,
 *                  which must not indicate a failure before the function call.
 *
 * @return <0 or 0 or >0 as usual for string comparisons
 *
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_strCaseCompare(const UChar *s1, int32_t length1,
                 const UChar *s2, int32_t length2,
                 uint32_t options,
                 UErrorCode *pErrorCode);

/**
 * Compare two ustrings for bitwise equality. 
 * Compares at most <code>n</code> characters.
 *
 * @param ucs1 A string to compare.
 * @param ucs2 A string to compare.
 * @param n The maximum number of characters to compare.
 * @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative
 * value if <code>s1</code> is bitwise less than <code>s2</code>; a positive
 * value if <code>s1</code> is bitwise greater than <code>s2</code>.
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strncmp(const UChar     *ucs1, 
     const UChar     *ucs2, 
     int32_t     n);

/**
 * Compare two Unicode strings in code point order.
 * This is different in UTF-16 from u_strncmp() if supplementary characters are present.
 * For details, see u_strCompare().
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @param n The maximum number of characters to compare.
 * @return a negative/zero/positive integer corresponding to whether
 * the first string is less than/equal to/greater than the second one
 * in code point order
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strncmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t n);

/**
 * Compare two strings case-insensitively using full case folding.
 * This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)).
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @param options A bit set of options:
 *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 *     Comparison in code unit order with default case folding.
 *
 *   - U_COMPARE_CODE_POINT_ORDER
 *     Set to choose code point order instead of code unit order
 *     (see u_strCompare for details).
 *
 *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 *
 * @return A negative, zero, or positive integer indicating the comparison result.
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strcasecmp(const UChar *s1, const UChar *s2, uint32_t options);

/**
 * Compare two strings case-insensitively using full case folding.
 * This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options),
 * u_strFoldCase(s2, at most n, options)).
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @param n The maximum number of characters each string to case-fold and then compare.
 * @param options A bit set of options:
 *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 *     Comparison in code unit order with default case folding.
 *
 *   - U_COMPARE_CODE_POINT_ORDER
 *     Set to choose code point order instead of code unit order
 *     (see u_strCompare for details).
 *
 *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 *
 * @return A negative, zero, or positive integer indicating the comparison result.
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_strncasecmp(const UChar *s1, const UChar *s2, int32_t n, uint32_t options);

/**
 * Compare two strings case-insensitively using full case folding.
 * This is equivalent to u_strcmp(u_strFoldCase(s1, n, options),
 * u_strFoldCase(s2, n, options)).
 *
 * @param s1 A string to compare.
 * @param s2 A string to compare.
 * @param length The number of characters in each string to case-fold and then compare.
 * @param options A bit set of options:
 *   - U_FOLD_CASE_DEFAULT or 0 is used for default options:
 *     Comparison in code unit order with default case folding.
 *
 *   - U_COMPARE_CODE_POINT_ORDER
 *     Set to choose code point order instead of code unit order
 *     (see u_strCompare for details).
 *
 *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 *
 * @return A negative, zero, or positive integer indicating the comparison result.
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_memcasecmp(const UChar *s1, const UChar *s2, int32_t length, uint32_t options);

/**
 * Copy a ustring. Adds a null terminator.
 *
 * @param dst The destination string.
 * @param src The source string.
 * @return A pointer to <code>dst</code>.
 * @stable ICU 2.0
 */
U_STABLE UChar* U_EXPORT2
u_strcpy(UChar     *dst, 
    const UChar     *src);

/**
 * Copy a ustring.
 * Copies at most <code>n</code> characters.  The result will be null terminated
 * if the length of <code>src</code> is less than <code>n</code>.
 *