This API is used to convert codepage or character encoded data to and * from UTF-16. You can open a converter with {@link ucnv_open()}. With that * converter, you can get its properties, set options, convert your data and * close the converter.
* *Since many software programs recogize different converter names for * different types of converters, there are other functions in this API to * iterate over the converter aliases. The functions {@link ucnv_getAvailableName()}, * {@link ucnv_getAlias()} and {@link ucnv_getStandardName()} are some of the * more frequently used alias functions to get this information.
* *More information about this API can be found in our * User's * Guide.
*/ #ifndef UCNV_H #define UCNV_H /** Forward declaring the UConverter structure. @stable */ struct UConverter; /** @stable */ typedef struct UConverter UConverter; #include "unicode/utypes.h" #include "unicode/ucnv_err.h" #include "unicode/uenum.h" U_CDECL_BEGIN /** Maximum length of a converter name including the terminating NULL */ #define UCNV_MAX_CONVERTER_NAME_LENGTH 60 /** Maximum length of a converter name including path and terminating NULL */ #define UCNV_MAX_FULL_FILE_NAME_LENGTH (600+UCNV_MAX_CONVERTER_NAME_LENGTH) /** Shift in for EBDCDIC_STATEFUL and iso2022 states */ #define UCNV_SI 0x0F /** Shift out for EBDCDIC_STATEFUL and iso2022 states */ #define UCNV_SO 0x0E /** * Enum for specifying basic types of converters * @see ucnv_getType * @stable */ typedef enum { UCNV_UNSUPPORTED_CONVERTER = -1, UCNV_SBCS = 0, UCNV_DBCS = 1, UCNV_MBCS = 2, UCNV_LATIN_1 = 3, UCNV_UTF8 = 4, UCNV_UTF16_BigEndian = 5, UCNV_UTF16_LittleEndian = 6, UCNV_UTF32_BigEndian = 7, UCNV_UTF32_LittleEndian = 8, UCNV_EBCDIC_STATEFUL = 9, UCNV_ISO_2022 = 10, UCNV_LMBCS_1 = 11, UCNV_LMBCS_2, UCNV_LMBCS_3, UCNV_LMBCS_4, UCNV_LMBCS_5, UCNV_LMBCS_6, UCNV_LMBCS_8, UCNV_LMBCS_11, UCNV_LMBCS_16, UCNV_LMBCS_17, UCNV_LMBCS_18, UCNV_LMBCS_19, UCNV_LMBCS_LAST = UCNV_LMBCS_19, UCNV_HZ, UCNV_SCSU, UCNV_ISCII, UCNV_US_ASCII, UCNV_UTF7, UCNV_BOCU1, UCNV_UTF16, UCNV_UTF32, UCNV_CESU8, /* Number of converter types for which we have conversion routines. */ UCNV_NUMBER_OF_SUPPORTED_CONVERTER_TYPES } UConverterType; /** * Enum for specifying which platform a converter ID refers to. * The use of platform/CCSID is not recommended. See ucnv_openCCSID(). * * @see ucnv_getPlatform * @see ucnv_openCCSID * @see ucnv_getCCSID * @stable */ typedef enum { UCNV_UNKNOWN = -1, UCNV_IBM = 0 } UConverterPlatform; /** * Function pointer for error callback in the codepage to unicode direction. * Called when an error has occured in conversion to unicode, or on open/close of the callback (see reason). * @param context Pointer to the callback's private data * @param args Information about the conversion in progress * @param codePoints Points to 'length' bytes of the concerned codepage sequence * @param length Size (in bytes) of the concerned codepage sequence * @param reason Defines the reason the callback was invoked * @see ucnv_setToUCallBack * @see UConverterToUnicodeArgs * @stable */ typedef void (U_EXPORT2 *UConverterToUCallback) ( const void* context, UConverterToUnicodeArgs *args, const char *codePoints, int32_t length, UConverterCallbackReason reason, UErrorCode *); /** * Function pointer for error callback in the unicode to codepage direction. * Called when an error has occured in conversion from unicode, or on open/close of the callback (see reason). * @param context Pointer to the callback's private data * @param args Information about the conversion in progress * @param codeUnits Points to 'length' UChars of the concerned Unicode sequence * @param length Size (in bytes) of the concerned codepage sequence * @param codePoint Single UChar32 (UTF-32) containing the concerend Unicode codepoint. * @param reason Defines the reason the callback was invoked * @see ucnv_setFromUCallBack * @stable */ typedef void (U_EXPORT2 *UConverterFromUCallback) ( const void* context, UConverterFromUnicodeArgs *args, const UChar* codeUnits, int32_t length, UChar32 codePoint, UConverterCallbackReason reason, UErrorCode *); U_CDECL_END /** * Character that separates converter names from options and options from each other. * @see ucnv_open * @stable */ #define UCNV_OPTION_SEP_CHAR ',' /** * String version of UCNV_OPTION_SEP_CHAR. * @see ucnv_open * @stable */ #define UCNV_OPTION_SEP_STRING "," /** * Character that separates a converter option from its value. * @see ucnv_open * @stable */ #define UCNV_VALUE_SEP_CHAR '=' /** * String version of UCNV_VALUE_SEP_CHAR. * @see ucnv_open * @stable */ #define UCNV_VALUE_SEP_STRING "=" /** * Converter option for specifying a locale. * For example, ucnv_open("SCSU,locale=ja", &errorCode); * See convrtrs.txt. * * @see ucnv_open * @stable */ #define UCNV_LOCALE_OPTION_STRING ",locale=" /** * Converter option for specifying a version selector (0..9) for some converters. * For example, ucnv_open("UTF-7,version=1", &errorCode); * See convrtrs.txt. * * @see ucnv_open * @draft ICU 2.4 */ #define UCNV_VERSION_OPTION_STRING ",version=" /** * Converter option for EBCDIC SBCS or mixed-SBCS/DBCS (stateful) codepages. * Swaps Unicode mappings for EBCDIC LF and NL codes, as used on * S/390 (z/OS) Unix System Services (Open Edition). * For example, ucnv_open("ibm-1047,swaplfnl", &errorCode); * See convrtrs.txt. * * @see ucnv_open * @draft ICU 2.4 */ #define UCNV_SWAP_LFNL_OPTION_STRING ",swaplfnl" /** * Do a fuzzy compare of a two converter/alias names. The comparison * is case-insensitive. It also ignores the characters '-', '_', and * ' ' (dash, underscore, and space). Thus the strings "UTF-8", * "utf_8", and "Utf 8" are exactly equivalent. * * @param name1 a converter name or alias, zero-terminated * @param name2 a converter name or alias, zero-terminated * @return 0 if the names match, or a negative value if the name1 * lexically precedes name2, or a positive value if the name1 * lexically follows name2. * @stable */ U_CAPI int U_EXPORT2 ucnv_compareNames(const char *name1, const char *name2); /** * Creates a UConverter object with the names specified as a C string. * The actual name will be resolved with the alias file * using a case-insensitive string comparison that ignores * the delimiters '-', '_', and ' ' (dash, underscore, and space). * E.g., the names "UTF8", "utf-8", and "Utf 8" are all equivalent. * IfNULL is passed for the converter name, it will create one with the
* getDefaultName return value.
*
* A converter name for ICU 1.5 and above may contain options * like a locale specification to control the specific behavior of * the newly instantiated converter. * The meaning of the options depends on the particular converter. * If an option is not defined for or recognized by a given converter, then it is ignored.
* *Options are appended to the converter name string, with a
* UCNV_OPTION_SEP_CHAR between the name and the first option and
* also between adjacent options.
Creates a UConverter object specified from a packageName and a converterName.
* *The packageName and converterName must point to an ICU udata object, as defined by
* udata_open( packageName, "cnv", converterName, err) or equivalent.
* Typically, packageName will refer to a (.dat) file, or to a package registered with
* udata_setAppData().
The name will NOT be looked up in the alias mechanism, nor will the converter be * stored in the converter cache or the alias table. The only way to open further converters * is call this function multiple times, or use the ucnv_safeClone() function to clone a * 'master' converter.
* *Example Use:
* cnv = ucnv_openPackage("myapp", "myconverter", &err);
*
U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is
* still data to be written to the target.
* @see ucnv_fromUChars
* @see ucnv_convert
* @see ucnv_getMinCharSize
* @see ucnv_setToUCallBack
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_fromUnicode (UConverter * converter,
char **target,
const char *targetLimit,
const UChar ** source,
const UChar * sourceLimit,
int32_t* offsets,
UBool flush,
UErrorCode * err);
/**
* Converts a buffer of codepage bytes into an array of unicode UChars
* 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 byte of source consumed.
*
* Target similarly starts out pointer at the first available UChar in the output
* buffer, and ends up pointing after the last UChar written to the output.
* It does NOT necessarily keep UChar sequences together.
*
* 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.
*
* This is a stateful 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
* the next empty chunk of target in case of a
* U_BUFFER_OVERFLOW_ERROR, and updating the source pointers
* with the next chunk of source when a successful error status is
* returned, until there are no more chunks of source data.
* @param converter the Unicode converter
* @param target I/O parameter. Input : Points to the beginning of the buffer to copy
* UChars into. Output : points to after the last UChar copied.
* @param targetLimit the pointer just after the end of the target buffer
* @param source I/O parameter, pointer to pointer to the source codepage buffer.
* @param sourceLimit the pointer to the byte after the end of the source buffer
* @param offsets if NULL is passed, nothing will happen to it, otherwise it needs to have the same number
* of allocated cells as target. Will fill in offsets from target to source pointer
* e.g: offsets[3] is equal to 6, it means that the target[3] was a result of transcoding source[6]
* For output data carried across calls, and other data without a specific source character
* (such as from escape sequences or callbacks) -1 will be placed for offsets.
* @param flush set to TRUE if the current source buffer is the last available
* chunk of the source, FALSE otherwise. Note that if a failing status is returned,
* this function may have to be called multiple times with flush set to TRUE until
* the source buffer is consumed.
* @param err the error status. U_ILLEGAL_ARGUMENT_ERROR will be set if the
* converter is NULL.
* U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is
* still data to be written to the target.
* @see ucnv_fromUChars
* @see ucnv_convert
* @see ucnv_getMinCharSize
* @see ucnv_setFromUCallBack
* @see ucnv_getNextUChar
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_toUnicode (UConverter * converter,
UChar ** target,
const UChar * targetLimit,
const char **source,
const char *sourceLimit,
int32_t* offsets,
UBool flush,
UErrorCode * err);
/**
* Convert the Unicode string into a codepage string using an existing UConverter.
* The output string is NUL-terminated if possible.
*
* This function is a more convenient but less powerful version of ucnv_fromUnicode().
* It is only useful for whole strings, not for streaming conversion.
*
* The maximum output buffer capacity required (barring output from callbacks) will be
* srcLength*ucnv_getMaxCharSize(cnv).
*
* @param cnv the converter object to be used (ucnv_resetFromUnicode() will be called)
* @param src the input Unicode string
* @param srcLength the input string length, or -1 if NUL-terminated
* @param dest destination string buffer, can be NULL if destCapacity==0
* @param destCapacity the number of chars available at dest
* @param errorCode normal ICU error code;
* common error codes that may be set by this function include
* U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING,
* U_ILLEGAL_ARGUMENT_ERROR, and conversion errors
* @return the length of the output string, not counting the terminating NUL;
* if the length is greater than destCapacity, then the string will not fit
* and a buffer of the indicated length would need to be passed in
* @see ucnv_fromUnicode
* @see ucnv_convert
* @draft ICU 2.0 (new NUL-termination semantics)
*/
U_CAPI int32_t U_EXPORT2
ucnv_fromUChars(UConverter *cnv,
char *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert the codepage string into a Unicode string using an existing UConverter.
* The output string is NUL-terminated if possible.
*
* This function is a more convenient but less powerful version of ucnv_toUnicode().
* It is only useful for whole strings, not for streaming conversion.
*
* The maximum output buffer capacity required (barring output from callbacks) will be
* 2*srcLength (each char may be converted into a surrogate pair).
*
* @param cnv the converter object to be used (ucnv_resetToUnicode() will be called)
* @param src the input codepage string
* @param srcLength the input string length, or -1 if NUL-terminated
* @param dest destination string buffer, can be NULL if destCapacity==0
* @param destCapacity the number of UChars available at dest
* @param errorCode normal ICU error code;
* common error codes that may be set by this function include
* U_BUFFER_OVERFLOW_ERROR, U_STRING_NOT_TERMINATED_WARNING,
* U_ILLEGAL_ARGUMENT_ERROR, and conversion errors
* @return the length of the output string, not counting the terminating NUL;
* if the length is greater than destCapacity, then the string will not fit
* and a buffer of the indicated length would need to be passed in
* @see ucnv_toUnicode
* @see ucnv_convert
* @draft ICU 2.0 (new NUL-termination semantics)
*/
U_CAPI int32_t U_EXPORT2
ucnv_toUChars(UConverter *cnv,
UChar *dest, int32_t destCapacity,
const char *src, int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Will convert a codepage buffer into unicode one character at a time.
* This function was written to be efficient when transcoding small * amounts of data at a time. * In that case it will be more efficient than \Ref{ucnv_toUnicode}. * When converting large buffers use \Ref{ucnv_toUnicode}.
* *Handling of surrogate pairs and supplementary-plane code points:
* There are two different kinds of codepages that provide mappings for surrogate characters:
*
U_INDEX_OUTOFBOUNDS_ERROR will be set if the input
* is empty or does not convert to any output (e.g.: pure state-change
* codes SI/SO, escape sequences for ISO 2022,
* or if the callback did not output anything, ...).
* This function will not set a U_BUFFER_OVERFLOW_ERROR because
* the "buffer" is the return code. However, there might be subsequent output
* stored in the converter object
* that will be returned in following calls to this function.
* @return a UChar32 resulting from the partial conversion of source
* @see ucnv_toUnicode
* @see ucnv_toUChars
* @see ucnv_convert
* @stable
*/
U_CAPI UChar32 U_EXPORT2
ucnv_getNextUChar (UConverter * converter,
const char **source,
const char * sourceLimit,
UErrorCode * err);
/**
* Will convert a sequence of bytes from one codepage to another.
* This is NOT AN EFFICIENT way to transcode.
* use \Ref{ucnv_toUnicode} and \Ref{ucnv_fromUnicode} for efficiency.
* @param toConverterName The name of the converter that will be used
* in conversion from unicode into the output buffer
* @param fromConverterName: The name of the converter that will be used
* in conversion from the source buffer into intermediate unicode.
* @param target Pointer to the output buffer
* @param targetCapacity capacity of the target, in bytes
* @param source Pointer to the input buffer
* @param sourceLength capacity of the source, in bytes
* @param err error status.
* U_BUFFER_OVERFLOW_ERROR will be set if the target is full and there is still input left in the source.
* @return will be filled in with the number of bytes needed in target
* @see ucnv_fromUnicode
* @see ucnv_toUnicode
* @see ucnv_fromUChars
* @see ucnv_toUChars
* @see ucnv_getNextUChar
* @stable
*/
U_CAPI int32_t U_EXPORT2
ucnv_convert (const char *toConverterName,
const char *fromConverterName,
char *target,
int32_t targetCapacity,
const char *source,
int32_t sourceLength,
UErrorCode * err);
/**
* Frees up memory occupied by unused, cached converter shared data.
*
* @return the number of cached converters successfully deleted
* @see ucnv_close
* @stable
*/
U_CAPI int32_t U_EXPORT2
ucnv_flushCache (void);
/**
* returns the number of available converters, as per the alias file.
*
* @return the number of available converters
* @see ucnv_getAvailableName
* @stable
*/
U_CAPI int32_t U_EXPORT2
ucnv_countAvailable (void);
/**
* Gets the name of the specified converter from a list of all converters
* contaied in the alias file.
* @param n the index to a converter available on the system (in the range [0..ucnv_countAvaiable()])
* @return a pointer a string (library owned), or NULL if the index is out of bounds.
* @see ucnv_countAvailable
* @stable
*/
U_CAPI const char* U_EXPORT2
ucnv_getAvailableName (int32_t n);
/**
* Gives the number of aliases for a given converter or alias name.
* If the alias is ambiguous, then the preferred converter is used
* and the status is set to U_AMBIGUOUS_ALIAS_WARNING.
* This method only enumerates the listed entries in the alias file.
* @param alias alias name
* @param pErrorCode error status
* @return number of names on alias list for given alias
* @stable
*/
U_CAPI uint16_t U_EXPORT2
ucnv_countAliases(const char *alias, UErrorCode *pErrorCode);
/**
* Gives the name of the alias at given index of alias list.
* This method only enumerates the listed entries in the alias file.
* If the alias is ambiguous, then the preferred converter is used
* and the status is set to U_AMBIGUOUS_ALIAS_WARNING.
* @param alias alias name
* @param n index in alias list
* @param pErrorCode result of operation
* @return returns the name of the alias at given index
* @see ucnv_countAliases
* @stable
*/
U_CAPI const char * U_EXPORT2
ucnv_getAlias(const char *alias, uint16_t n, UErrorCode *pErrorCode);
/**
* Fill-up the list of alias names for the given alias.
* This method only enumerates the listed entries in the alias file.
* If the alias is ambiguous, then the preferred converter is used
* and the status is set to U_AMBIGUOUS_ALIAS_WARNING.
* @param alias alias name
* @param aliases fill-in list, aliases is a pointer to an array of
* ucnv_countAliases() string-pointers
* (const char *) that will be filled in.
* The strings themselves are owned by the library.
* @param pErrorCode result of operation
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_getAliases(const char *alias, const char **aliases, UErrorCode *pErrorCode);
/**
* Return a new UEnumeration object for enumerating all the
* alias names for a given converter that are recognized by a standard.
* This method only enumerates the listed entries in the alias file.
* The convrtrs.txt file can be modified to change the results of
* this function.
* The first result in this list is the same result given by
* ucnv_getStandardName, which is the default alias for
* the specified standard name. The returned object must be closed with
* uenum_close when you are done with the object.
*
* @param convName original converter name
* @param standard name of the standard governing the names; MIME and IANA
* are such standards
* @param pErrorCode The error code
* @return A UEnumeration object for getting all aliases that are recognized
* by a standard. If any of the parameters are invalid, NULL
* is returned.
* @see ucnv_getStandardName
* @see uenum_close
* @see uenum_next
* @draft ICU 2.2
*/
U_CAPI UEnumeration *
ucnv_openStandardNames(const char *convName,
const char *standard,
UErrorCode *pErrorCode);
/**
* Gives the number of standards associated to converter names.
* @return number of standards
* @stable
*/
U_CAPI uint16_t U_EXPORT2
ucnv_countStandards(void);
/**
* Gives the name of the standard at given index of standard list.
* @param n index in standard list
* @param pErrorCode result of operation
* @return returns the name of the standard at given index. Owned by the library.
* @stable
*/
U_CAPI const char * U_EXPORT2
ucnv_getStandard(uint16_t n, UErrorCode *pErrorCode);
/**
* Returns a standard name for a given converter name.
*
* @param name original converter name
* @param standard name of the standard governing the names; MIME and IANA
* are such standards
* @return returns the standard converter name;
* if a standard converter name cannot be determined,
* then NULL is returned. Owned by the library.
* @stable
*/
U_CAPI const char * U_EXPORT2
ucnv_getStandardName(const char *name, const char *standard, UErrorCode *pErrorCode);
/**
* returns the current default converter name.
*
* @return returns the current default converter name;
* if a default converter name cannot be determined,
* then NULL is returned.
* Storage owned by the library
* @see ucnv_setDefaultName
* @stable
*/
U_CAPI const char * U_EXPORT2
ucnv_getDefaultName (void);
/**
* sets the current default converter name. Caller must own the storage for 'name'
* and preserve it indefinitely.
* @param name the converter name to be the default (must exist).
* @see ucnv_getDefaultName
* @system SYSTEM API
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_setDefaultName (const char *name);
/**
* Fixes the backslash character mismapping. For example, in SJIS, the backslash
* character in the ASCII portion is also used to represent the yen currency sign.
* When mapping from Unicode character 0x005C, it's unclear whether to map the
* character back to yen or backslash in SJIS. This function will take the input
* buffer and replace all the yen sign characters with backslash. This is necessary
* when the user tries to open a file with the input buffer on Windows.
* This function will test the converter to see whether such mapping is
* required. You can sometimes avoid using this function by using the correct version
* of Shift-JIS.
*
* @param cnv The converter representing the target codepage.
* @param source the input buffer to be fixed
* @param sourceLen the length of the input buffer
* @see ucnv_isAmbiguous
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_fixFileSeparator(const UConverter *cnv, UChar* source, int32_t sourceLen);
/**
* Determines if the converter contains ambiguous mappings of the same
* character or not.
* @param cnv the converter to be tested
* @return TRUE if the converter contains ambiguous mapping of the same
* character, FALSE otherwise.
* @stable
*/
U_CAPI UBool U_EXPORT2
ucnv_isAmbiguous(const UConverter *cnv);
/**
* Sets the converter to use fallback mapping or not.
* @param cnv The converter to set the fallback mapping usage on.
* @param usesFallback TRUE if the user wants the converter to take advantage of the fallback
* mapping, FALSE otherwise.
* @stable
*/
U_CAPI void U_EXPORT2
ucnv_setFallback(UConverter *cnv, UBool usesFallback);
/**
* Determines if the converter uses fallback mappings or not.
* @param cnv The converter to be tested
* @return TRUE if the converter uses fallback, FALSE otherwise.
* @stable
*/
U_CAPI UBool U_EXPORT2
ucnv_usesFallback(const UConverter *cnv);
/**
* Detects Unicode signatures in the given byte stream. The signature bytes are not consumed,
* instead the number of bytes that make up the signature is returned. The conversion APIs
* donot discard signature bytes, so if the caller wishes to discard them, the caller should
* explicity add code to do that after calling this function.
* * Usage: * @code * UErrorCode err = U_ZERO_ERROR; * char input[] = { '\xEF','\xBB', '\xBF','\x41','\x42','\x43' }; * char* source = input; * int32_t signatureLength = 0; * char* encoding = ucnv_detectUnicodeSignatures(source,sizeof(input),&signatureLength,&err); * UConverter* conv = NULL; * if(encoding!=NULL && U_SUCCESS(err)){ * // should signature be discarded ? * if (discardSignature){ * source += signatureLength; * } * conv = ucnv_open(encoding, &err); * .... do the conversion .... * } * * @endcode * * @param source The source string in which the signature should be detected. * @param sourceLength Length of the input string, or -1 if NUL-terminated. * @param signatureLength A pointer to int8_t to receive the number of bytes that make up the signature * of the detected UTF. 0 if not detected. * @param pErrorCode A pointer to receive information about any errors that may occur during detection. * Must be a valid pointer to an error code value, which must not indicate a failure * before the function call. * @return The name of the encoding detected. NULL if encoding is not detected. */ U_CAPI const char* U_EXPORT2 ucnv_detectUnicodeSignature( const char* source, int32_t sourceLength, int32_t* signatureLength, UErrorCode* pErrorCode); #endif /*_UCNV*/