unorm.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

 *
 * @see unorm_quickCheck
 * @stable ICU 2.2
 */
U_STABLE UBool U_EXPORT2
unorm_isNormalized(const UChar *src, int32_t srcLength,
                   UNormalizationMode mode,
                   UErrorCode *pErrorCode);

/**
 * Test if a string is in a given normalization form; same as unorm_isNormalized but
 * takes an extra options parameter like most normalization functions.
 *
 * @param src        String that is to be tested if it is in a normalization format.
 * @param srcLength  Length of source to test, or -1 if NUL-terminated.
 * @param mode       Which normalization form to test for.
 * @param options    The normalization options, ORed together (0 for no options).
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Boolean value indicating whether the source string is in the
 *         "mode/options" normalization form.
 *
 * @see unorm_quickCheck
 * @see unorm_isNormalized
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength,
                              UNormalizationMode mode, int32_t options,
                              UErrorCode *pErrorCode);

/**
 * Iterative normalization forward.
 * This function (together with unorm_previous) is somewhat
 * similar to the C++ Normalizer class (see its non-static functions).
 *
 * Iterative normalization is useful when only a small portion of a longer
 * string/text needs to be processed.
 *
 * For example, the likelihood may be high that processing the first 10% of some
 * text will be sufficient to find certain data.
 * Another example: When one wants to concatenate two normalized strings and get a
 * normalized result, it is much more efficient to normalize just a small part of
 * the result around the concatenation place instead of re-normalizing everything.
 *
 * The input text is an instance of the C character iteration API UCharIterator.
 * It may wrap around a simple string, a CharacterIterator, a Replaceable, or any
 * other kind of text object.
 *
 * If a buffer overflow occurs, then the caller needs to reset the iterator to the
 * old index and call the function again with a larger buffer - if the caller cares
 * for the actual output.
 * Regardless of the output buffer, the iterator will always be moved to the next
 * normalization boundary.
 *
 * This function (like unorm_previous) serves two purposes:
 *
 * 1) To find the next boundary so that the normalization of the part of the text
 * from the current position to that boundary does not affect and is not affected
 * by the part of the text beyond that boundary.
 *
 * 2) To normalize the text up to the boundary.
 *
 * The second step is optional, per the doNormalize parameter.
 * It is omitted for operations like string concatenation, where the two adjacent
 * string ends need to be normalized together.
 * In such a case, the output buffer will just contain a copy of the text up to the
 * boundary.
 *
 * pNeededToNormalize is an output-only parameter. Its output value is only defined
 * if normalization was requested (doNormalize) and successful (especially, no
 * buffer overflow).
 * It is useful for operations like a normalizing transliterator, where one would
 * not want to replace a piece of text if it is not modified.
 *
 * If doNormalize==TRUE and pNeededToNormalize!=NULL then *pNeeded... is set TRUE
 * if the normalization was necessary.
 *
 * If doNormalize==FALSE then *pNeededToNormalize will be set to FALSE.
 *
 * If the buffer overflows, then *pNeededToNormalize will be undefined;
 * essentially, whenever U_FAILURE is true (like in buffer overflows), this result
 * will be undefined.
 *
 * @param src The input text in the form of a C character iterator.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param doNormalize Indicates if the source text up to the next boundary
 *                    is to be normalized (TRUE) or just copied (FALSE).
 * @param pNeededToNormalize Output flag indicating if the normalization resulted in
 *                           different text from the input.
 *                           Not defined if an error occurs including buffer overflow.
 *                           Always FALSE if !doNormalize.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_previous
 * @see unorm_normalize
 *
 * @stable ICU 2.1
 */
U_STABLE int32_t U_EXPORT2
unorm_next(UCharIterator *src,
           UChar *dest, int32_t destCapacity,
           UNormalizationMode mode, int32_t options,
           UBool doNormalize, UBool *pNeededToNormalize,
           UErrorCode *pErrorCode);

/**
 * Iterative normalization backward.
 * This function (together with unorm_next) is somewhat
 * similar to the C++ Normalizer class (see its non-static functions).
 * For all details see unorm_next.
 *
 * @param src The input text in the form of a C character iterator.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param doNormalize Indicates if the source text up to the next boundary
 *                    is to be normalized (TRUE) or just copied (FALSE).
 * @param pNeededToNormalize Output flag indicating if the normalization resulted in
 *                           different text from the input.
 *                           Not defined if an error occurs including buffer overflow.
 *                           Always FALSE if !doNormalize.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_next
 * @see unorm_normalize
 *
 * @stable ICU 2.1
 */
U_STABLE int32_t U_EXPORT2
unorm_previous(UCharIterator *src,
               UChar *dest, int32_t destCapacity,
               UNormalizationMode mode, int32_t options,
               UBool doNormalize, UBool *pNeededToNormalize,
               UErrorCode *pErrorCode);

/**
 * Concatenate normalized strings, making sure that the result is normalized as well.
 *
 * If both the left and the right strings are in
 * the normalization form according to "mode/options",
 * then the result will be
 *
 * \code
 *     dest=normalize(left+right, mode, options)
 * \endcode
 *
 * With the input strings already being normalized,
 * this function will use unorm_next() and unorm_previous()
 * to find the adjacent end pieces of the input strings.
 * Only the concatenation of these end pieces will be normalized and
 * then concatenated with the remaining parts of the input strings.
 *
 * It is allowed to have dest==left to avoid copying the entire left string.
 *
 * @param left Left source string, may be same as dest.
 * @param leftLength Length of left source string, or -1 if NUL-terminated.
 * @param right Right source string.
 * @param rightLength Length of right source string, or -1 if NUL-terminated.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_normalize
 * @see unorm_next
 * @see unorm_previous
 *
 * @stable ICU 2.1
 */
U_STABLE int32_t U_EXPORT2
unorm_concatenate(const UChar *left, int32_t leftLength,
                  const UChar *right, int32_t rightLength,
                  UChar *dest, int32_t destCapacity,
                  UNormalizationMode mode, int32_t options,
                  UErrorCode *pErrorCode);

/**
 * Option bit for unorm_compare:
 * Both input strings are assumed to fulfill FCD conditions.
 * @stable ICU 2.2
 */
#define UNORM_INPUT_IS_FCD          0x20000

/**
 * Option bit for unorm_compare:
 * Perform case-insensitive comparison.
 * @stable ICU 2.2
 */
#define U_COMPARE_IGNORE_CASE       0x10000

#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also unistr.h and ustring.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 for canonical equivalence.
 * Further options include case-insensitive comparison and
 * code point order (as opposed to code unit order).
 *
 * Canonical equivalence between two strings is defined as their normalized
 * forms (NFD or NFC) being identical.
 * This function compares strings incrementally instead of normalizing
 * (and optionally case-folding) both strings entirely,
 * improving performance significantly.
 *
 * Bulk normalization is only necessary if the strings do not fulfill the FCD
 * conditions. Only in this case, and only if the strings are relatively long,
 * is memory allocated temporarily.
 * For FCD strings and short non-FCD strings there is no memory allocation.
 *
 * Semantically, this is equivalent to
 *   strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2))))
 * where code point order and foldCase are all optional.
 *
 * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match
 * the case folding must be performed first, then the normalization.
 *
 * @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:
 *     Case-sensitive comparison in code unit order, and the input strings
 *     are quick-checked for FCD.
 *
 *   - UNORM_INPUT_IS_FCD
 *     Set if the caller knows that both s1 and s2 fulfill the FCD conditions.
 *     If not set, the function will quickCheck for FCD
 *     and normalize if necessary.
 *
 *   - U_COMPARE_CODE_POINT_ORDER
 *     Set to choose code point order instead of code unit order
 *     (see u_strCompare for details).
 *
 *   - U_COMPARE_IGNORE_CASE
 *     Set to compare strings case-insensitively using case folding,
 *     instead of case-sensitively.
 *     If set, then the following case folding options are used.
 *
 *   - Options as used with case-insensitive comparisons, currently:
 *
 *   - U_FOLD_CASE_EXCLUDE_SPECIAL_I
 *    (see u_strCaseCompare for details)
 *
 *   - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT
 *
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return <0 or 0 or >0 as usual for string comparisons
 *
 * @see unorm_normalize
 * @see UNORM_FCD
 * @see u_strCompare
 * @see u_strCaseCompare
 *
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
unorm_compare(const UChar *s1, int32_t length1,
              const UChar *s2, int32_t length2,
              uint32_t options,
              UErrorCode *pErrorCode);

#endif /* #if !UCONFIG_NO_NORMALIZATION */

#endif