dict		API documentation		The XML C parser and toolkit of Gnome	entities

Table of Contents

int	xmlDelEncodingAlias	(const char * alias)

const char *	xmlGetEncodingAlias	(const char * alias)

int	xmlUTF8Strloc	(const xmlChar * utf, 
				 const xmlChar * utfchar)

void	xmlCleanupCharEncodingHandlers	(void)

xmlCharEncodingHandlerPtr	xmlFindCharEncodingHandler	(const char * name)

int	xmlCharEncCloseFunc	(xmlCharEncodingHandler * handler)

int	xmlUTF8Size	(const xmlChar * utf)

xmlCharEncoding	xmlParseCharEncoding	(const char * name)

xmlChar *	xmlUTF8Strpos	(const xmlChar * utf, 
				 int pos)

Structure xmlCharEncodingHandler
struct _xmlCharEncodingHandler {
    char *	name
    xmlCharEncodingInputFunc	input
    xmlCharEncodingOutputFunc	output
    iconv_t	iconv_in
    iconv_t	iconv_out
}

const char *	xmlGetCharEncodingName	(xmlCharEncoding enc)

int	xmlCheckUTF8	(const unsigned char * utf)

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

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

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

Typedef xmlCharEncodingHandler * xmlCharEncodingHandlerPtr

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

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.

xmlCharEncodingHandlerPtr	xmlGetCharEncodingHandler	(xmlCharEncoding enc)

xmlChar *	xmlUTF8Strsub	(const xmlChar * utf, 
				 int start, 
				 int len)

int	xmlGetUTF8Char	(const unsigned char * utf, 
				 int * len)

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

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

void	xmlInitCharEncodingHandlers	(void)

void	xmlRegisterCharEncodingHandler	(xmlCharEncodingHandlerPtr handler)

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

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
}

int	xmlUTF8Strsize	(const xmlChar * utf, 
				 int len)

int	xmlUTF8Charcmp	(const xmlChar * utf1, 
				 const xmlChar * utf2)

int	xmlUTF8Strlen	(const xmlChar * utf)

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 an other encoding. Note: a first call designed to produce heading info is called with in = NULL. If stateful this should also initialize the encoder state.

xmlChar *	xmlUTF8Strndup	(const xmlChar * utf, 
				 int len)

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

void	xmlCleanupEncodingAliases	(void)

Description

Function: xmlDelEncodingAlias

int	xmlDelEncodingAlias	(const char * alias)

Unregisters an encoding alias @alias

Function: xmlGetEncodingAlias

const char *	xmlGetEncodingAlias	(const char * alias)

Lookup an encoding name for the given alias.

Function: xmlUTF8Strloc

int	xmlUTF8Strloc	(const xmlChar * utf, 
				 const xmlChar * utfchar)

a function to provide relative location of a UTF8 char

Function: xmlCleanupCharEncodingHandlers

void	xmlCleanupCharEncodingHandlers	(void)

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

Function: xmlFindCharEncodingHandler

xmlCharEncodingHandlerPtr	xmlFindCharEncodingHandler	(const char * name)

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

Function: xmlCharEncCloseFunc

int	xmlCharEncCloseFunc	(xmlCharEncodingHandler * handler)

Generic front-end for encoding handler close function

Function: xmlUTF8Size

int	xmlUTF8Size	(const xmlChar * utf)

calulates the internal size of a UTF8 character

Function: xmlParseCharEncoding

xmlCharEncoding	xmlParseCharEncoding	(const char * name)

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

Function: xmlUTF8Strpos

xmlChar *	xmlUTF8Strpos	(const xmlChar * utf, 
				 int pos)

a function to provide the equivalent of fetching a character from a string array

Function: 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

Function: xmlCheckUTF8

int	xmlCheckUTF8	(const unsigned char * utf)

Checks @utf for being valid utf-8. @utf is assumed to be null-terminated. This function is not super-strict, as it will allow longer utf-8 sequences than necessary. Note that Java is capable of producing these sequences if provoked. Also note, this routine checks for the 4-byte maximum size, but does not check for 0x10ffff maximum value.

Function: 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.

Function: xmlCharEncInFunc

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

Generic front-end for the encoding handler input function

Function: xmlAddEncodingAlias

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

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

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.

Function: xmlGetCharEncodingHandler

xmlCharEncodingHandlerPtr	xmlGetCharEncodingHandler	(xmlCharEncoding enc)

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

Function: xmlUTF8Strsub

xmlChar *	xmlUTF8Strsub	(const xmlChar * utf, 
				 int start, 
				 int len)

Note: positions are given in units of UTF-8 chars

Function: xmlGetUTF8Char

int	xmlGetUTF8Char	(const unsigned char * utf, 
				 int * len)

Read one UTF8 Char from @utf

Function: 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.

Function: xmlNewCharEncodingHandler

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

Create and registers an xmlCharEncodingHandler.

Function: 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.

Function: xmlRegisterCharEncodingHandler

void	xmlRegisterCharEncodingHandler	(xmlCharEncodingHandlerPtr handler)

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

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.

Function: xmlUTF8Strsize

int	xmlUTF8Strsize	(const xmlChar * utf, 
				 int len)

storage size of an UTF8 string

Function: xmlUTF8Charcmp

int	xmlUTF8Charcmp	(const xmlChar * utf1, 
				 const xmlChar * utf2)

compares the two UCS4 values

Function: xmlUTF8Strlen

int	xmlUTF8Strlen	(const xmlChar * utf)

compute the length of an UTF8 string, it doesn't do a full UTF8 checking of the content of the string.

Function: xmlUTF8Strndup

xmlChar *	xmlUTF8Strndup	(const xmlChar * utf, 
				 int len)

a strndup for array of UTF8's

Function: xmlDetectCharEncoding

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

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

Function: xmlCleanupEncodingAliases

void	xmlCleanupEncodingAliases	(void)

Unregisters all aliases

Daniel Veillard