ucnv.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

 * @return The maximum number of bytes per UChar that are output by ucnv_fromUnicode(),
 *         to be used together with UCNV_GET_MAX_BYTES_FOR_STRING for buffer allocation.
 *
 * @see UCNV_GET_MAX_BYTES_FOR_STRING
 * @see ucnv_getMinCharSize
 * @stable ICU 2.0
 */
U_STABLE int8_t U_EXPORT2
ucnv_getMaxCharSize(const UConverter *converter);

#ifndef U_HIDE_DRAFT_API

/**
 * Calculates the size of a buffer for conversion from Unicode to a charset.
 * The calculated size is guaranteed to be sufficient for this conversion.
 *
 * It takes into account initial and final non-character bytes that are output
 * by some converters.
 * It does not take into account callbacks which output more than one charset
 * character sequence per call, like escape callbacks.
 * The default (substitution) callback only outputs one charset character sequence.
 *
 * @param length Number of UChars to be converted.
 * @param maxCharSize Return value from ucnv_getMaxCharSize() for the converter
 *                    that will be used.
 * @return Size of a buffer that will be large enough to hold the output bytes of
 *         converting length UChars with the converter that returned the maxCharSize.
 *
 * @see ucnv_getMaxCharSize
 * @draft ICU 2.8
 */
#define UCNV_GET_MAX_BYTES_FOR_STRING(length, maxCharSize) \
     (((int32_t)(length)+10)*(int32_t)(maxCharSize))

#endif /*U_HIDE_DRAFT_API*/

/**
 * Returns the minimum byte length for characters in this codepage. 
 * This is usually either 1 or 2.
 * @param converter the Unicode converter
 * @return the minimum number of bytes allowed by this particular converter
 * @see ucnv_getMaxCharSize
 * @stable ICU 2.0
 */
U_STABLE int8_t U_EXPORT2
ucnv_getMinCharSize(const UConverter *converter);

/**
 * Returns the display name of the converter passed in based on the Locale 
 * passed in. If the locale contains no display name, the internal ASCII
 * name will be filled in.
 *
 * @param converter the Unicode converter.
 * @param displayLocale is the specific Locale we want to localised for
 * @param displayName user provided buffer to be filled in
 * @param displayNameCapacity size of displayName Buffer
 * @param err error status code
 * @return displayNameLength number of UChar needed in displayName
 * @see ucnv_getName
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ucnv_getDisplayName(const UConverter *converter,
                    const char *displayLocale,
                    UChar *displayName,
                    int32_t displayNameCapacity,
                    UErrorCode *err);

/**
 * Gets the internal, canonical name of the converter (zero-terminated).
 * The lifetime of the returned string will be that of the converter 
 * passed to this function.
 * @param converter the Unicode converter
 * @param err UErrorCode status
 * @return the internal name of the converter
 * @see ucnv_getDisplayName
 * @stable ICU 2.0
 */
U_STABLE const char * U_EXPORT2 
ucnv_getName(const UConverter *converter, UErrorCode *err);

/**
 * Gets a codepage number associated with the converter. This is not guaranteed
 * to be the one used to create the converter. Some converters do not represent
 * platform registered codepages and return zero for the codepage number.
 * The error code fill-in parameter indicates if the codepage number
 * is available.
 * Does not check if the converter is <TT>NULL</TT> or if converter's data
 * table is <TT>NULL</TT>.
 *
 * Important: The use of CCSIDs is not recommended because it is limited
 * to only two platforms in principle and only one (UCNV_IBM) in the current
 * ICU converter API.
 * Also, CCSIDs are insufficient to identify IBM Unicode conversion tables precisely.
 * For more details see ucnv_openCCSID().
 *
 * @param converter the Unicode converter
 * @param err the error status code.
 * @return If any error occurrs, -1 will be returned otherwise, the codepage number
 * will be returned
 * @see ucnv_openCCSID
 * @see ucnv_getPlatform
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ucnv_getCCSID(const UConverter *converter,
              UErrorCode *err);

/**
 * Gets a codepage platform associated with the converter. Currently, 
 * only <TT>UCNV_IBM</TT> will be returned.
 * Does not test if the converter is <TT>NULL</TT> or if converter's data 
 * table is <TT>NULL</TT>. 
 * @param converter the Unicode converter
 * @param err the error status code.
 * @return The codepage platform
 * @stable ICU 2.0
 */
U_STABLE UConverterPlatform U_EXPORT2
ucnv_getPlatform(const UConverter *converter,
                 UErrorCode *err);

/**
 * Gets the type of the converter
 * e.g. SBCS, MBCS, DBCS, UTF8, UTF16_BE, UTF16_LE, ISO_2022, 
 * EBCDIC_STATEFUL, LATIN_1
 * @param converter a valid, opened converter
 * @return the type of the converter
 * @stable ICU 2.0
 */
U_STABLE UConverterType U_EXPORT2
ucnv_getType(const UConverter * converter);

/**
 * Gets the "starter" (lead) bytes for converters of type MBCS.
 * Will fill in an <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if converter passed in
 * is not MBCS. Fills in an array of type UBool, with the value of the byte 
 * as offset to the array. For example, if (starters[0x20] == TRUE) at return,
 * it means that the byte 0x20 is a starter byte in this converter.
 * Context pointers are always owned by the caller.
 * 
 * @param converter a valid, opened converter of type MBCS
 * @param starters an array of size 256 to be filled in
 * @param err error status, <TT>U_ILLEGAL_ARGUMENT_ERROR</TT> if the 
 * converter is not a type which can return starters.
 * @see ucnv_getType
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ucnv_getStarters(const UConverter* converter, 
                 UBool starters[256],
                 UErrorCode* err);


/**
 * Selectors for Unicode sets that can be returned by ucnv_getUnicodeSet().
 * @see ucnv_getUnicodeSet
 * @stable ICU 2.6
 */
typedef enum UConverterUnicodeSet {
    /** Select the set of roundtrippable Unicode code points. @stable ICU 2.6 */
    UCNV_ROUNDTRIP_SET,
    /** Number of UConverterUnicodeSet selectors. @stable ICU 2.6 */
    UCNV_SET_COUNT
} UConverterUnicodeSet;


/**
 * Returns the set of Unicode code points that can be converted by an ICU converter.
 *
 * The current implementation returns only one kind of set (UCNV_ROUNDTRIP_SET):
 * The set of all Unicode code points that can be roundtrip-converted
 * (converted without any data loss) with the converter.
 * This set will not include code points that have fallback mappings
 * or are only the result of reverse fallback mappings.
 * See UTR #22 "Character Mapping Markup Language"
 * at http://www.unicode.org/reports/tr22/
 *
 * This is useful for example for
 * - checking that a string or document can be roundtrip-converted with a converter,
 *   without/before actually performing the conversion
 * - testing if a converter can be used for text for typical text for a certain locale,
 *   by comparing its roundtrip set with the set of ExemplarCharacters from
 *   ICU's locale data or other sources
 *
 * In the future, there may be more UConverterUnicodeSet choices to select
 * sets with different properties.
 *
 * @param cnv The converter for which a set is requested.
 * @param setFillIn A valid USet *. It will be cleared by this function before
 *            the converter's specific set is filled into the USet.
 * @param whichSet A UConverterUnicodeSet selector;
 *              currently UCNV_ROUNDTRIP_SET is the only supported value.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 *
 * @see UConverterUnicodeSet
 * @see uset_open
 * @see uset_close
 * @stable ICU 2.6
 */
U_STABLE void U_EXPORT2
ucnv_getUnicodeSet(const UConverter *cnv,
                   USet *setFillIn,
                   UConverterUnicodeSet whichSet,
                   UErrorCode *pErrorCode);

/**
 * Gets the current calback function used by the converter when an illegal
 *  or invalid codepage sequence is found. 
 * Context pointers are always owned by the caller.
 *
 * @param converter the unicode converter
 * @param action fillin: returns the callback function pointer
 * @param context fillin: returns the callback's private void* context
 * @see ucnv_setToUCallBack
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ucnv_getToUCallBack (const UConverter * converter,
                     UConverterToUCallback *action,
                     const void **context);

/**
 * Gets the current callback function used by the converter when illegal 
 * or invalid Unicode sequence is found.
 * Context pointers are always owned by the caller.
 *
 * @param converter the unicode converter
 * @param action fillin: returns the callback function pointer
 * @param context fillin: returns the callback's private void* context
 * @see ucnv_setFromUCallBack
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ucnv_getFromUCallBack (const UConverter * converter,
                       UConverterFromUCallback *action,
                       const void **context);

/**
 * Changes the callback function used by the converter when
 * an illegal or invalid sequence is found.
 * Context pointers are always owned by the caller.
 * Predefined actions and contexts can be found in the ucnv_err.h header.
 *
 * @param converter the unicode converter
 * @param newAction the new callback function
 * @param newContext the new toUnicode callback context pointer. This can be NULL.
 * @param oldAction fillin: returns the old callback function pointer. This can be NULL.
 * @param oldContext fillin: returns the old callback's private void* context. This can be NULL.
 * @param err The error code status
 * @see ucnv_getToUCallBack
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ucnv_setToUCallBack (UConverter * converter,
                     UConverterToUCallback newAction,
                     const void* newContext,
                     UConverterToUCallback *oldAction,
                     const void** oldContext,
                     UErrorCode * err);

/**
 * Changes the current callback function used by the converter when
 * an illegal or invalid sequence is found.
 * Context pointers are always owned by the caller.
 * Predefined actions and contexts can be found in the ucnv_err.h header.
 *
 * @param converter the unicode converter
 * @param newAction the new callback function
 * @param newContext the new fromUnicode callback context pointer. This can be NULL.
 * @param oldAction fillin: returns the old callback function pointer. This can be NULL.
 * @param oldContext fillin: returns the old callback's private void* context. This can be NULL.
 * @param err The error code status
 * @see ucnv_getFromUCallBack
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ucnv_setFromUCallBack (UConverter * converter,
                       UConverterFromUCallback newAction,
                       const void *newContext,
                       UConverterFromUCallback *oldAction,
                       const void **oldContext,
                       UErrorCode * err);

/**
 * Converts an array of unicode characters to an array of codepage
 * characters. This function is optimized for converting a continuous
 * stream of data in buffer-sized chunks, where the entire source and
 * target does not fit in available buffers.
 * 
 * The source pointer is an in/out parameter. It starts out pointing where the 
 * conversion is to begin, and ends up pointing after the last UChar consumed. 
 * 
 * Target similarly starts out pointer at the first available byte in the output
 * buffer, and ends up pointing after the last byte written to the output.
 * 
 * The converter always attempts to consume the entire source buffer, unless 
 * (1.) the target buffer is full, or (2.) a failing error is returned from the
 * current callback function.  When a successful error status has been
 * returned, it means that all of the source buffer has been
 *  consumed. At that point, the caller should reset the source and
 *  sourceLimit pointers to point to the next chunk.
 * 
 * At the end of the stream (flush==TRUE), the input is completely consumed
 * when *source==sourceLimit and no error code is set.
 * The converter object is then automatically reset by this function.
 * (This means that a converter need not be reset explicitly between data
 * streams if it finishes the previous stream without errors.)
 * 
 * This is a <I>stateful</I> conversion. Additionally, even when all source data has
 * been consumed, some data may be in the converters' internal state.
 * Call this function repeatedly, updating the target pointers with