Structure uconv_t

struct _uconv_t {
    UConverter *	uconv	: for conversion between an encoding and UTF-16
    UConverter *	utf8	: for conversion between UTF-8 and UTF-16
} uconv_t;

Enum xmlCharEncoding

enum xmlCharEncoding {
    XML_CHAR_ENCODING_ERROR = -1 /* No char encoding detected */
    XML_CHAR_ENCODING_NONE = 0 /* No char encoding detected */
    XML_CHAR_ENCODING_UTF8 = 1 /* UTF-8 */
    XML_CHAR_ENCODING_UTF16LE = 2 /* UTF-16 little endian */
    XML_CHAR_ENCODING_UTF16BE = 3 /* UTF-16 big endian */
    XML_CHAR_ENCODING_UCS4LE = 4 /* UCS-4 little endian */
    XML_CHAR_ENCODING_UCS4BE = 5 /* UCS-4 big endian */
    XML_CHAR_ENCODING_EBCDIC = 6 /* EBCDIC uh! */
    XML_CHAR_ENCODING_UCS4_2143 = 7 /* UCS-4 unusual ordering */
    XML_CHAR_ENCODING_UCS4_3412 = 8 /* UCS-4 unusual ordering */
    XML_CHAR_ENCODING_UCS2 = 9 /* UCS-2 */
    XML_CHAR_ENCODING_8859_1 = 10 /* ISO-8859-1 ISO Latin 1 */
    XML_CHAR_ENCODING_8859_2 = 11 /* ISO-8859-2 ISO Latin 2 */
    XML_CHAR_ENCODING_8859_3 = 12 /* ISO-8859-3 */
    XML_CHAR_ENCODING_8859_4 = 13 /* ISO-8859-4 */
    XML_CHAR_ENCODING_8859_5 = 14 /* ISO-8859-5 */
    XML_CHAR_ENCODING_8859_6 = 15 /* ISO-8859-6 */
    XML_CHAR_ENCODING_8859_7 = 16 /* ISO-8859-7 */
    XML_CHAR_ENCODING_8859_8 = 17 /* ISO-8859-8 */
    XML_CHAR_ENCODING_8859_9 = 18 /* ISO-8859-9 */
    XML_CHAR_ENCODING_2022_JP = 19 /* ISO-2022-JP */
    XML_CHAR_ENCODING_SHIFT_JIS = 20 /* Shift_JIS */
    XML_CHAR_ENCODING_EUC_JP = 21 /* EUC-JP */
    XML_CHAR_ENCODING_ASCII = 22 /*  pure ASCII */
};

Structure xmlCharEncodingHandler

struct _xmlCharEncodingHandler {
    char *	name
    xmlCharEncodingInputFunc	input
    xmlCharEncodingOutputFunc	output
    iconv_t	iconv_in
    iconv_t	iconv_out
    uconv_t *	uconv_in
    uconv_t *	uconv_out
} xmlCharEncodingHandler;

Typedef xmlCharEncodingHandlerPtr

xmlCharEncodingHandler * xmlCharEncodingHandlerPtr;

Function type xmlCharEncodingInputFunc

int	xmlCharEncodingInputFunc	(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen)

Take a block of chars in the original encoding and try to convert it to an UTF-8 block of chars out.

Function type xmlCharEncodingOutputFunc

int	xmlCharEncodingOutputFunc	(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen)

Take a block of UTF-8 chars in and try to convert it to another encoding. Note: a first call designed to produce heading info is called with in = NULL. If stateful this should also initialize the encoder state.

UTF8Toisolat1 ()

int	UTF8Toisolat1			(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen)

Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1 block of chars out.

isolat1ToUTF8 ()

int	isolat1ToUTF8			(unsigned char * out, 
					 int * outlen, 
					 const unsigned char * in, 
					 int * inlen)

Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8 block of chars out.

xmlAddEncodingAlias ()

int	xmlAddEncodingAlias		(const char * name, 
					 const char * alias)

Registers an alias @alias for an encoding named @name. Existing alias will be overwritten.

xmlCharEncCloseFunc ()

int	xmlCharEncCloseFunc		(xmlCharEncodingHandler * handler)

Generic front-end for encoding handler close function

xmlCharEncFirstLine ()

int	xmlCharEncFirstLine		(xmlCharEncodingHandler * handler, 
					 xmlBufferPtr out, 
					 xmlBufferPtr in)

Front-end for the encoding handler input function, but handle only the very first line, i.e. limit itself to 45 chars.

xmlCharEncInFunc ()

int	xmlCharEncInFunc		(xmlCharEncodingHandler * handler, 
					 xmlBufferPtr out, 
					 xmlBufferPtr in)

Generic front-end for the encoding handler input function

xmlCharEncOutFunc ()

int	xmlCharEncOutFunc		(xmlCharEncodingHandler * handler, 
					 xmlBufferPtr out, 
					 xmlBufferPtr in)

Generic front-end for the encoding handler output function a first call with @in == NULL has to be made firs to initiate the output in case of non-stateless encoding needing to initiate their state or the output (like the BOM in UTF16). In case of UTF8 sequence conversion errors for the given encoder, the content will be automatically remapped to a CharRef sequence.

xmlCleanupCharEncodingHandlers ()

void	xmlCleanupCharEncodingHandlers	(void)

Cleanup the memory allocated for the char encoding support, it unregisters all the encoding handlers and the aliases.

xmlCleanupEncodingAliases ()

void	xmlCleanupEncodingAliases	(void)

Unregisters all aliases

xmlDelEncodingAlias ()

int	xmlDelEncodingAlias		(const char * alias)

Unregisters an encoding alias @alias

xmlDetectCharEncoding ()

xmlCharEncoding	xmlDetectCharEncoding	(const unsigned char * in, 
					 int len)

Guess the encoding of the entity using the first bytes of the entity content according to the non-normative appendix F of the XML-1.0 recommendation.

xmlFindCharEncodingHandler ()

xmlCharEncodingHandlerPtr	xmlFindCharEncodingHandler	(const char * name)

Search in the registered set the handler able to read/write that encoding.

xmlGetCharEncodingHandler ()

xmlCharEncodingHandlerPtr	xmlGetCharEncodingHandler	(xmlCharEncoding enc)

Search in the registered set the handler able to read/write that encoding.

xmlGetCharEncodingName ()

const char *	xmlGetCharEncodingName	(xmlCharEncoding enc)

The "canonical" name for XML encoding. C.f. http://www.w3.org/TR/REC-xml#charencoding Section 4.3.3 Character Encoding in Entities

xmlGetEncodingAlias ()

const char *	xmlGetEncodingAlias	(const char * alias)

Lookup an encoding name for the given alias.

xmlInitCharEncodingHandlers ()

void	xmlInitCharEncodingHandlers	(void)

Initialize the char encoding support, it registers the default encoding supported. NOTE: while public, this function usually doesn't need to be called in normal processing.

xmlNewCharEncodingHandler ()

xmlCharEncodingHandlerPtr	xmlNewCharEncodingHandler	(const char * name, 
							 xmlCharEncodingInputFunc input, 
							 xmlCharEncodingOutputFunc output)

Create and registers an xmlCharEncodingHandler.

xmlParseCharEncoding ()

xmlCharEncoding	xmlParseCharEncoding	(const char * name)

Compare the string to the encoding schemes already known. Note that the comparison is case insensitive accordingly to the section [XML] 4.3.3 Character Encoding in Entities.

xmlRegisterCharEncodingHandler ()

void	xmlRegisterCharEncodingHandler	(xmlCharEncodingHandlerPtr handler)

Register the char encoding handler, surprising, isn't it ?