interface for the encoding conversion functions needed for XML basic encoding and iconv() support. Related specs are rfc2044 (UTF-8 and UTF-16) F. Yergeau Alis Technologies [ISO-10646] UTF-8 and UTF-16 in Annexes [ISO-8859-1] ISO Latin-1 characters codes. [UNICODE] The Unicode Consortium, "The Unicode Standard -- Worldwide Character Encoding -- Version 1.0", Addison- Wesley, Volume 1, 1991, Volume 2, 1992. UTF-8 is described in Unicode Technical Report #4. [US-ASCII] Coded Character Set--7-bit American Standard Code for Information Interchange, ANSI X3.4-1986. Table of ContentsEnum xmlCharEncoding
Structure xmlCharEncodingHandler struct _xmlCharEncodingHandler
Typedef xmlCharEncodingHandler * xmlCharEncodingHandlerPtr
int UTF8Toisolat1 (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
int isolat1ToUTF8 (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
int xmlAddEncodingAlias (const char * name, const char * alias)
int xmlCharEncCloseFunc (xmlCharEncodingHandler * handler)
int xmlCharEncFirstLine (xmlCharEncodingHandler * handler, xmlBufferPtr out, xmlBufferPtr in)
int xmlCharEncInFunc (xmlCharEncodingHandler * handler, xmlBufferPtr out, xmlBufferPtr in)
int xmlCharEncOutFunc (xmlCharEncodingHandler * handler, xmlBufferPtr out, xmlBufferPtr in)
Function type: xmlCharEncodingInputFunc
int xmlCharEncodingInputFunc (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
Function type: xmlCharEncodingOutputFunc
int xmlCharEncodingOutputFunc (unsigned char * out, int * outlen, const unsigned char * in, int * inlen)
int xmlCheckUTF8 (const unsigned char * utf)
void xmlCleanupCharEncodingHandlers (void)
void xmlCleanupEncodingAliases (void)
int xmlDelEncodingAlias (const char * alias)
xmlCharEncoding xmlDetectCharEncoding (const unsigned char * in, int len)
xmlCharEncodingHandlerPtr xmlFindCharEncodingHandler (const char * name)
xmlCharEncodingHandlerPtr xmlGetCharEncodingHandler (xmlCharEncoding enc)
const char * xmlGetCharEncodingName (xmlCharEncoding enc)
const char * xmlGetEncodingAlias (const char * alias)
int xmlGetUTF8Char (const unsigned char * utf, int * len)
void xmlInitCharEncodingHandlers (void)
xmlCharEncodingHandlerPtr xmlNewCharEncodingHandler (const char * name, xmlCharEncodingInputFunc input, xmlCharEncodingOutputFunc output)
xmlCharEncoding xmlParseCharEncoding (const char * name)
void xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler)
int xmlUTF8Charcmp (const xmlChar * utf1, const xmlChar * utf2)
int xmlUTF8Size (const xmlChar * utf)
int xmlUTF8Strlen (const xmlChar * utf)
int xmlUTF8Strloc (const xmlChar * utf, const xmlChar * utfchar)
xmlChar * xmlUTF8Strndup (const xmlChar * utf, int len)
xmlChar * xmlUTF8Strpos (const xmlChar * utf, int pos)
int xmlUTF8Strsize (const xmlChar * utf, int len)
xmlChar * xmlUTF8Strsub (const xmlChar * utf, int start, int len)
Description
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
} Function: UTF8Toisolat1int 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.
out: | a pointer to an array of bytes to store the result | outlen: | the length of @out | in: | a pointer to an array of UTF-8 chars | inlen: | the length of @in | Returns: | 0 if success, -2 if the transcoding fails, or -1 otherwise The value of @inlen after return is the number of octets consumed if the return value is positive, else unpredictable. The value of @outlen after return is the number of octets consumed. |
Function: isolat1ToUTF8int 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.
out: | a pointer to an array of bytes to store the result | outlen: | the length of @out | in: | a pointer to an array of ISO Latin 1 chars | inlen: | the length of @in | Returns: | 0 if success, or -1 otherwise The value of @inlen after return is the number of octets consumed if the return value is positive, else unpredictable. The value of @outlen after return is the number of octets consumed. |
Function: xmlAddEncodingAliasint xmlAddEncodingAlias (const char * name, const char * alias)
Registers an alias @alias for an encoding named @name. Existing alias will be overwritten.
name: | the encoding name as parsed, in UTF-8 format (ASCII actually) | alias: | the alias name as parsed, in UTF-8 format (ASCII actually) | Returns: | 0 in case of success, -1 in case of error |
Function: xmlCharEncCloseFuncint xmlCharEncCloseFunc (xmlCharEncodingHandler * handler)
Generic front-end for encoding handler close function
handler: | char enconding transformation data structure | Returns: | 0 if success, or -1 in case of error |
Function: xmlCharEncFirstLineint 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.
handler: | char enconding transformation data structure | out: | an xmlBuffer for the output. | in: | an xmlBuffer for the input | Returns: | the number of byte written if success, or -1 general error -2 if the transcoding fails (for *in is not valid utf8 string or the result of transformation can't fit into the encoding we want), or |
Function: xmlCharEncInFuncint xmlCharEncInFunc (xmlCharEncodingHandler * handler, xmlBufferPtr out, xmlBufferPtr in)
Generic front-end for the encoding handler input function
handler: | char encoding transformation data structure | out: | an xmlBuffer for the output. | in: | an xmlBuffer for the input | Returns: | the number of byte written if success, or -1 general error -2 if the transcoding fails (for *in is not valid utf8 string or the result of transformation can't fit into the encoding we want), or |
Function: xmlCharEncOutFuncint 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.
handler: | char enconding transformation data structure | out: | an xmlBuffer for the output. | in: | an xmlBuffer for the input | Returns: | the number of byte written if success, or -1 general error -2 if the transcoding fails (for *in is not valid utf8 string or the result of transformation can't fit into the encoding we want), or |
Function type: xmlCharEncodingInputFuncFunction 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. out: | a pointer to an array of bytes to store the UTF-8 result | outlen: | the length of @out | in: | a pointer to an array of chars in the original encoding | inlen: | the length of @in | Returns: | the number of bytes written, -1 if lack of space, or -2 if the transcoding failed. The value of @inlen after return is the number of octets consumed if the return value is positive, else unpredictiable. The value of @outlen after return is the number of octets consumed. |
Function type: xmlCharEncodingOutputFuncFunction 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. out: | a pointer to an array of bytes to store the result | outlen: | the length of @out | in: | a pointer to an array of UTF-8 chars | inlen: | the length of @in | Returns: | the number of bytes written, -1 if lack of space, or -2 if the transcoding failed. The value of @inlen after return is the number of octets consumed if the return value is positive, else unpredictiable. The value of @outlen after return is the number of ocetes consumed. |
Function: xmlCheckUTF8int 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.
utf: | Pointer to putative UTF-8 encoded string. | Returns: | value: true if @utf is valid. |
Function: xmlCleanupCharEncodingHandlersvoid xmlCleanupCharEncodingHandlers (void)
Cleanup the memory allocated for the char encoding support, it unregisters all the encoding handlers and the aliases.
Function: xmlCleanupEncodingAliasesvoid xmlCleanupEncodingAliases (void)
Unregisters all aliases
Function: xmlDelEncodingAliasint xmlDelEncodingAlias (const char * alias)
Unregisters an encoding alias @alias
alias: | the alias name as parsed, in UTF-8 format (ASCII actually) | Returns: | 0 in case of success, -1 in case of error |
Function: xmlDetectCharEncodingxmlCharEncoding 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.
in: | a pointer to the first bytes of the XML entity, must be at least 2 bytes long (at least 4 if encoding is UTF4 variant). | len: | pointer to the length of the buffer | Returns: | one of the XML_CHAR_ENCODING_... values. |
Function: xmlFindCharEncodingHandlerxmlCharEncodingHandlerPtr xmlFindCharEncodingHandler (const char * name)
Search in the registered set the handler able to read/write that encoding.
name: | a string describing the char encoding. | Returns: | the handler or NULL if not found |
Function: xmlGetCharEncodingHandlerxmlCharEncodingHandlerPtr xmlGetCharEncodingHandler (xmlCharEncoding enc)
Search in the registered set the handler able to read/write that encoding.
Function: xmlGetCharEncodingNameconst 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
enc: | the encoding | Returns: | the canonical name for the given encoding |
Function: xmlGetEncodingAliasconst char * xmlGetEncodingAlias (const char * alias)
Lookup an encoding name for the given alias.
alias: | the alias name as parsed, in UTF-8 format (ASCII actually) | Returns: | NULL if not found, otherwise the original name |
Function: xmlGetUTF8Charint xmlGetUTF8Char (const unsigned char * utf, int * len)
Read one UTF8 Char from @utf
utf: | a sequence of UTF-8 encoded bytes | len: | a pointer to @bytes len | Returns: | the char value or -1 in case of error, and updates *len with the number of bytes consumed |
Function: xmlInitCharEncodingHandlersvoid 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: xmlNewCharEncodingHandlerxmlCharEncodingHandlerPtr xmlNewCharEncodingHandler (const char * name, xmlCharEncodingInputFunc input, xmlCharEncodingOutputFunc output)
Create and registers an xmlCharEncodingHandler.
Function: xmlParseCharEncodingxmlCharEncoding 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.
name: | the encoding name as parsed, in UTF-8 format (ASCII actually) | Returns: | one of the XML_CHAR_ENCODING_... values or XML_CHAR_ENCODING_NONE if not recognized. |
Function: xmlRegisterCharEncodingHandlervoid xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler)
Register the char encoding handler, surprising, isn't it ?
Function: xmlUTF8Charcmpint xmlUTF8Charcmp (const xmlChar * utf1, const xmlChar * utf2)
compares the two UCS4 values
utf1: | pointer to first UTF8 char | utf2: | pointer to second UTF8 char | Returns: | result of the compare as with xmlStrncmp |
Function: xmlUTF8Sizeint xmlUTF8Size (const xmlChar * utf)
calculates the internal size of a UTF8 character
utf: | pointer to the UTF8 character | Returns: | the numbers of bytes in the character, -1 on format error |
Function: xmlUTF8Strlenint 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.
utf: | a sequence of UTF-8 encoded bytes | Returns: | the number of characters in the string or -1 in case of error |
Function: xmlUTF8Strlocint xmlUTF8Strloc (const xmlChar * utf, const xmlChar * utfchar)
a function to provide the relative location of a UTF8 char
utf: | the input UTF8 * | utfchar: | the UTF8 character to be found | Returns: | the relative character position of the desired char or -1 if not found |
Function: xmlUTF8StrndupxmlChar * xmlUTF8Strndup (const xmlChar * utf, int len)
a strndup for array of UTF8's
utf: | the input UTF8 * | len: | the len of @utf (in chars) | Returns: | a new UTF8 * or NULL |
Function: xmlUTF8StrposxmlChar * xmlUTF8Strpos (const xmlChar * utf, int pos)
a function to provide the equivalent of fetching a character from a string array
utf: | the input UTF8 * | pos: | the position of the desired UTF8 char (in chars) | Returns: | a pointer to the UTF8 character or NULL |
Function: xmlUTF8Strsizeint xmlUTF8Strsize (const xmlChar * utf, int len)
storage size of an UTF8 string
utf: | a sequence of UTF-8 encoded bytes | len: | the number of characters in the array | Returns: | the storage size of the first 'len' characters of ARRAY |
Function: xmlUTF8StrsubxmlChar * xmlUTF8Strsub (const xmlChar * utf, int start, int len)
Create a substring from a given UTF-8 string Note: positions are given in units of UTF-8 chars
utf: | a sequence of UTF-8 encoded bytes | start: | relative pos of first char | len: | total number to copy | Returns: | a pointer to a newly created string or NULL if any problem |
Daniel Veillard |