<HTML
><HEAD
><TITLE
>encoding</TITLE
><META
NAME="GENERATOR"
CONTENT="Modular DocBook HTML Stylesheet Version 1.64
"><LINK
REL="HOME"
TITLE="Gnome XML Library Reference Manual"
HREF="book1.html"><LINK
REL="UP"
TITLE="Libxml Library Reference"
HREF="libxml-lib.html"><LINK
REL="PREVIOUS"
TITLE="parserInternals"
HREF="libxml-parserinternals.html"><LINK
REL="NEXT"
TITLE="hash"
HREF="libxml-hash.html"></HEAD
><BODY
CLASS="REFENTRY"
BGCOLOR="#FFFFFF"
TEXT="#000000"
LINK="#0000FF"
VLINK="#840084"
ALINK="#0000FF"
><DIV
CLASS="NAVHEADER"
><TABLE
WIDTH="100%"
BORDER="0"
BGCOLOR="#000000"
CELLPADDING="1"
CELLSPACING="0"
><TR
><TH
COLSPAN="4"
ALIGN="center"
><FONT
COLOR="#FFFFFF"
SIZE="5"
>Gnome XML Library Reference Manual</FONT
></TH
></TR
><TR
><TD
WIDTH="25%"
BGCOLOR="#C00000"
ALIGN="left"
><A
HREF="libxml-parserinternals.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><<< Previous Page</B
></FONT
></A
></TD
><TD
WIDTH="25%"
BGCOLOR="#0000C0"
ALIGN="center"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><A
HREF="book1.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Home</B
></FONT
></A
></B
></FONT
></TD
><TD
WIDTH="25%"
BGCOLOR="#00C000"
ALIGN="center"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><A
HREF="libxml-lib.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Up</B
></FONT
></A
></B
></FONT
></TD
><TD
WIDTH="25%"
BGCOLOR="#C00000"
ALIGN="right"
><A
HREF="libxml-hash.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Next Page >>></B
></FONT
></A
></TD
></TR
></TABLE
></DIV
><H1
><A
NAME="LIBXML-ENCODING"
>encoding</A
></H1
><DIV
CLASS="REFNAMEDIV"
><A
NAME="AEN23858"
></A
><H2
>Name</H2
>encoding -- </DIV
><DIV
CLASS="REFSYNOPSISDIV"
><A
NAME="AEN23861"
></A
><H2
>Synopsis</H2
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="SYNOPSIS"
>
enum <A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
>;
int (<A
HREF="libxml-encoding.html#XMLCHARENCODINGINPUTFUNC"
>*xmlCharEncodingInputFunc</A
>) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);
int (<A
HREF="libxml-encoding.html#XMLCHARENCODINGOUTPUTFUNC"
>*xmlCharEncodingOutputFunc</A
>) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);
struct <A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
>;
typedef <A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
>;
void <A
HREF="libxml-encoding.html#XMLINITCHARENCODINGHANDLERS"
>xmlInitCharEncodingHandlers</A
> (void);
void <A
HREF="libxml-encoding.html#XMLCLEANUPCHARENCODINGHANDLERS"
>xmlCleanupCharEncodingHandlers</A
> (void);
void <A
HREF="libxml-encoding.html#XMLREGISTERCHARENCODINGHANDLER"
>xmlRegisterCharEncodingHandler</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> handler);
<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> <A
HREF="libxml-encoding.html#XMLGETCHARENCODINGHANDLER"
>xmlGetCharEncodingHandler</A
>
(<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> enc);
<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> <A
HREF="libxml-encoding.html#XMLFINDCHARENCODINGHANDLER"
>xmlFindCharEncodingHandler</A
>
(const char *name);
int <A
HREF="libxml-encoding.html#XMLADDENCODINGALIAS"
>xmlAddEncodingAlias</A
> (const char *name,
const char *alias);
int <A
HREF="libxml-encoding.html#XMLDELENCODINGALIAS"
>xmlDelEncodingAlias</A
> (const char *alias);
const char* <A
HREF="libxml-encoding.html#XMLGETENCODINGALIAS"
>xmlGetEncodingAlias</A
> (const char *alias);
void <A
HREF="libxml-encoding.html#XMLCLEANUPENCODINGALIASES"
>xmlCleanupEncodingAliases</A
> (void);
<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> <A
HREF="libxml-encoding.html#XMLPARSECHARENCODING"
>xmlParseCharEncoding</A
> (const char *name);
const char* <A
HREF="libxml-encoding.html#XMLGETCHARENCODINGNAME"
>xmlGetCharEncodingName</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> enc);
<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> <A
HREF="libxml-encoding.html#XMLDETECTCHARENCODING"
>xmlDetectCharEncoding</A
> (unsigned char *in,
int len);
int <A
HREF="libxml-encoding.html#XMLCHARENCOUTFUNC"
>xmlCharEncOutFunc</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);
int <A
HREF="libxml-encoding.html#XMLCHARENCINFUNC"
>xmlCharEncInFunc</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);
int <A
HREF="libxml-encoding.html#XMLCHARENCFIRSTLINE"
>xmlCharEncFirstLine</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);
int <A
HREF="libxml-encoding.html#XMLCHARENCCLOSEFUNC"
>xmlCharEncCloseFunc</A
> (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler);
int <A
HREF="libxml-encoding.html#UTF8TOISOLAT1"
>UTF8Toisolat1</A
> (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);
int <A
HREF="libxml-encoding.html#ISOLAT1TOUTF8"
>isolat1ToUTF8</A
> (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);
int <A
HREF="libxml-encoding.html#XMLCHECKUTF8"
>xmlCheckUTF8</A
> (unsigned char *utf);
int <A
HREF="libxml-encoding.html#XMLUTF8STRSIZE"
>xmlUTF8Strsize</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int len);
<A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* <A
HREF="libxml-encoding.html#XMLUTF8STRNDUP"
>xmlUTF8Strndup</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int len);
<A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* <A
HREF="libxml-encoding.html#XMLUTF8STRPOS"
>xmlUTF8Strpos</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int pos);
int <A
HREF="libxml-encoding.html#XMLUTF8STRLOC"
>xmlUTF8Strloc</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utfchar);
<A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* <A
HREF="libxml-encoding.html#XMLUTF8STRSUB"
>xmlUTF8Strsub</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int start,
int len);
int <A
HREF="libxml-encoding.html#XMLUTF8STRLEN"
>xmlUTF8Strlen</A
> (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf);</PRE
></TD
></TR
></TABLE
></DIV
><DIV
CLASS="REFSECT1"
><A
NAME="AEN23921"
></A
><H2
>Description</H2
><P
></P
></DIV
><DIV
CLASS="REFSECT1"
><A
NAME="AEN23924"
></A
><H2
>Details</H2
><DIV
CLASS="REFSECT2"
><A
NAME="AEN23926"
></A
><H3
><A
NAME="XMLCHARENCODING"
></A
>enum xmlCharEncoding</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>typedef enum {
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 */
} xmlCharEncoding;</PRE
></TD
></TR
></TABLE
><P
>Predefined values for some standard encodings
Libxml don't do beforehand translation on UTF8, ISOLatinX
It also support UTF16 (LE and BE) by default.</P
><P
>Anything else would have to be translated to UTF8 before being
given to the parser itself. The BOM for UTF16 and the encoding
declaration are looked at and a converter is looked for at that
point. If not found the parser stops here as asked by the XML REC
Converter can be registered by the user using xmlRegisterCharEncodingHandler
but the current form doesn't allow stateful transcoding (a serious
problem agreed !). If iconv has been found it will be used
automatically and allow stateful transcoding, the simplest is then
to be sure to enable icon and to provide iconv libs for the encoding
support needed.</P
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN23933"
></A
><H3
><A
NAME="XMLCHARENCODINGINPUTFUNC"
></A
>xmlCharEncodingInputFunc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int (*xmlCharEncodingInputFunc) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</PRE
></TD
></TR
></TABLE
><P
>Take a block of chars in the original encoding and try to convert
it to an UTF-8 block of chars out.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN23939"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of bytes to store the UTF-8 result</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>out</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of chars in the original encoding</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>in</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the number of byte written, or -1 by lack of space, or -2
if the transcoding failed.
The value of <TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> after return is the number of octets consumed
as the return value is positive, else unpredictiable.
The value of <TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> after return is the number of octets consumed.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN23968"
></A
><H3
><A
NAME="XMLCHARENCODINGOUTPUTFUNC"
></A
>xmlCharEncodingOutputFunc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int (*xmlCharEncodingOutputFunc) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</PRE
></TD
></TR
></TABLE
><P
>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</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN23974"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of bytes to store the result</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>out</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of UTF-8 chars</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>in</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the number of byte written, or -1 by lack of space, or -2
if the transcoding failed.
The value of <TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> after return is the number of octets consumed
as the return value is positive, else unpredictiable.
The value of <TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> after return is the number of ocetes consumed.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24003"
></A
><H3
><A
NAME="XMLCHARENCODINGHANDLER"
></A
>struct xmlCharEncodingHandler</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>struct xmlCharEncodingHandler {
char *name;
xmlCharEncodingInputFunc input;
xmlCharEncodingOutputFunc output;
#ifdef LIBXML_ICONV_ENABLED
iconv_t iconv_in;
iconv_t iconv_out;
#endif /* LIBXML_ICONV_ENABLED */
};</PRE
></TD
></TR
></TABLE
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24008"
></A
><H3
><A
NAME="XMLCHARENCODINGHANDLERPTR"
></A
>xmlCharEncodingHandlerPtr</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>typedef xmlCharEncodingHandler *xmlCharEncodingHandlerPtr;</PRE
></TD
></TR
></TABLE
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24013"
></A
><H3
><A
NAME="XMLINITCHARENCODINGHANDLERS"
></A
>xmlInitCharEncodingHandlers ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>void xmlInitCharEncodingHandlers (void);</PRE
></TD
></TR
></TABLE
><P
>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.</P
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24019"
></A
><H3
><A
NAME="XMLCLEANUPCHARENCODINGHANDLERS"
></A
>xmlCleanupCharEncodingHandlers ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>void xmlCleanupCharEncodingHandlers (void);</PRE
></TD
></TR
></TABLE
><P
>Cleanup the memory allocated for the char encoding support, it
unregisters all the encoding handlers and the aliases.</P
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24025"
></A
><H3
><A
NAME="XMLREGISTERCHARENCODINGHANDLER"
></A
>xmlRegisterCharEncodingHandler ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>void xmlRegisterCharEncodingHandler (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> handler);</PRE
></TD
></TR
></TABLE
><P
>Register the char encoding handler, surprising, isn't it ?</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24032"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>handler</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the xmlCharEncodingHandlerPtr handler block</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24041"
></A
><H3
><A
NAME="XMLGETCHARENCODINGHANDLER"
></A
>xmlGetCharEncodingHandler ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> xmlGetCharEncodingHandler
(<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> enc);</PRE
></TD
></TR
></TABLE
><P
>Search in the registered set the handler able to read/write that encoding.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24049"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>enc</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlCharEncoding value.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the handler or NULL if not found</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24062"
></A
><H3
><A
NAME="XMLFINDCHARENCODINGHANDLER"
></A
>xmlFindCharEncodingHandler ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLERPTR"
>xmlCharEncodingHandlerPtr</A
> xmlFindCharEncodingHandler
(const char *name);</PRE
></TD
></TR
></TABLE
><P
>Search in the registered set the handler able to read/write that encoding.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24069"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>name</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a string describing the char encoding.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the handler or NULL if not found</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24082"
></A
><H3
><A
NAME="XMLADDENCODINGALIAS"
></A
>xmlAddEncodingAlias ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlAddEncodingAlias (const char *name,
const char *alias);</PRE
></TD
></TR
></TABLE
><P
>Registers and alias <TT
CLASS="PARAMETER"
><I
>alias</I
></TT
> for an encoding named <TT
CLASS="PARAMETER"
><I
>name</I
></TT
>. Existing alias
will be overwritten.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24090"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>name</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the encoding name as parsed, in UTF-8 format (ASCII actually)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>alias</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the alias name as parsed, in UTF-8 format (ASCII actually)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>0 in case of success, -1 in case of error</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24107"
></A
><H3
><A
NAME="XMLDELENCODINGALIAS"
></A
>xmlDelEncodingAlias ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlDelEncodingAlias (const char *alias);</PRE
></TD
></TR
></TABLE
><P
>Unregisters an encoding alias <TT
CLASS="PARAMETER"
><I
>alias</I
></TT
></P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24114"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>alias</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the alias name as parsed, in UTF-8 format (ASCII actually)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>0 in case of success, -1 in case of error</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24127"
></A
><H3
><A
NAME="XMLGETENCODINGALIAS"
></A
>xmlGetEncodingAlias ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>const char* xmlGetEncodingAlias (const char *alias);</PRE
></TD
></TR
></TABLE
><P
>Lookup an encoding name for the given alias.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24133"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>alias</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the alias name as parsed, in UTF-8 format (ASCII actually)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>NULL if not found the original name otherwise</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24146"
></A
><H3
><A
NAME="XMLCLEANUPENCODINGALIASES"
></A
>xmlCleanupEncodingAliases ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>void xmlCleanupEncodingAliases (void);</PRE
></TD
></TR
></TABLE
><P
>Unregisters all aliases</P
><P
></P
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24152"
></A
><H3
><A
NAME="XMLPARSECHARENCODING"
></A
>xmlParseCharEncoding ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> xmlParseCharEncoding (const char *name);</PRE
></TD
></TR
></TABLE
><P
>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.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24159"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>name</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the encoding name as parsed, in UTF-8 format (ASCII actually)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>one of the XML_CHAR_ENCODING_... values or XML_CHAR_ENCODING_NONE
if not recognized.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24172"
></A
><H3
><A
NAME="XMLGETCHARENCODINGNAME"
></A
>xmlGetCharEncodingName ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>const char* xmlGetCharEncodingName (<A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> enc);</PRE
></TD
></TR
></TABLE
><P
>The "canonical" name for XML encoding.
C.f. http://www.w3.org/TR/REC-xml<GTKDOCLINK
HREF="CHARENCODING"
>charencoding</GTKDOCLINK
>
Section 4.3.3 Character Encoding in Entities</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24180"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>enc</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the encoding</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the canonical name for the given encoding</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24193"
></A
><H3
><A
NAME="XMLDETECTCHARENCODING"
></A
>xmlDetectCharEncoding ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-encoding.html#XMLCHARENCODING"
>xmlCharEncoding</A
> xmlDetectCharEncoding (unsigned char *in,
int len);</PRE
></TD
></TR
></TABLE
><P
>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.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24200"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to the first bytes of the XML entity, must be at least
4 bytes long.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>len</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> pointer to the length of the buffer</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>one of the XML_CHAR_ENCODING_... values.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24217"
></A
><H3
><A
NAME="XMLCHARENCOUTFUNC"
></A
>xmlCharEncOutFunc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlCharEncOutFunc (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);</PRE
></TD
></TR
></TABLE
><P
>Generic front-end for the encoding handler output function
a first call with <TT
CLASS="PARAMETER"
><I
>in</I
></TT
> == 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.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24227"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>handler</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> char enconding transformation data structure</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the output.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the input</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>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</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24248"
></A
><H3
><A
NAME="XMLCHARENCINFUNC"
></A
>xmlCharEncInFunc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlCharEncInFunc (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);</PRE
></TD
></TR
></TABLE
><P
>Generic front-end for the encoding handler input function</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24257"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>handler</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> char encoding transformation data structure</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the output.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the input</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>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</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24278"
></A
><H3
><A
NAME="XMLCHARENCFIRSTLINE"
></A
>xmlCharEncFirstLine ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlCharEncFirstLine (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> out,
<A
HREF="libxml-tree.html#XMLBUFFERPTR"
>xmlBufferPtr</A
> in);</PRE
></TD
></TR
></TABLE
><P
>Front-end for the encoding handler input function, but handle only
the very first line, i.e. limit itself to 45 chars.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24287"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>handler</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> char enconding transformation data structure</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the output.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> an xmlBuffer for the input</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>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</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24308"
></A
><H3
><A
NAME="XMLCHARENCCLOSEFUNC"
></A
>xmlCharEncCloseFunc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlCharEncCloseFunc (<A
HREF="libxml-encoding.html#XMLCHARENCODINGHANDLER"
>xmlCharEncodingHandler</A
> *handler);</PRE
></TD
></TR
></TABLE
><P
>Generic front-end for encoding handler close function</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24315"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>handler</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> char enconding transformation data structure</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>0 if success, or -1 in case of error</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24328"
></A
><H3
><A
NAME="UTF8TOISOLAT1"
></A
>UTF8Toisolat1 ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int UTF8Toisolat1 (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</PRE
></TD
></TR
></TABLE
><P
>Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
block of chars out.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24334"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of bytes to store the result</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>out</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of UTF-8 chars</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>in</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>0 if success, -2 if the transcoding fails, or -1 otherwise
The value of <TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> after return is the number of ocetes consumed.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24363"
></A
><H3
><A
NAME="ISOLAT1TOUTF8"
></A
>isolat1ToUTF8 ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int isolat1ToUTF8 (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</PRE
></TD
></TR
></TABLE
><P
>Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
block of chars out.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24369"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>out</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of bytes to store the result</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>out</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>in</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a pointer to an array of ISO Latin 1 chars</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the length of <TT
CLASS="PARAMETER"
><I
>in</I
></TT
></TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>0 if success, or -1 otherwise
The value of <TT
CLASS="PARAMETER"
><I
>inlen</I
></TT
> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <TT
CLASS="PARAMETER"
><I
>outlen</I
></TT
> after return is the number of ocetes consumed.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24398"
></A
><H3
><A
NAME="XMLCHECKUTF8"
></A
>xmlCheckUTF8 ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlCheckUTF8 (unsigned char *utf);</PRE
></TD
></TR
></TABLE
><P
>Checks <TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> for being valid utf-8. <TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> 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.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24406"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> Pointer to putative utf-8 encoded string.</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> true if <TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> is valid.</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24420"
></A
><H3
><A
NAME="XMLUTF8STRSIZE"
></A
>xmlUTF8Strsize ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlUTF8Strsize (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int len);</PRE
></TD
></TR
></TABLE
><P
>storage size of an UTF8 string</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24427"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a sequence of UTF-8 encoded bytes</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>len</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the number of characters in the array</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the storage size of
the first 'len' characters of ARRAY </TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24444"
></A
><H3
><A
NAME="XMLUTF8STRNDUP"
></A
>xmlUTF8Strndup ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* xmlUTF8Strndup (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int len);</PRE
></TD
></TR
></TABLE
><P
>a strndup for array of UTF8's</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24452"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the input UTF8 *</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>len</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the len of <TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> (in chars)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>a new UTF8 * or NULL</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24470"
></A
><H3
><A
NAME="XMLUTF8STRPOS"
></A
>xmlUTF8Strpos ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* xmlUTF8Strpos (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int pos);</PRE
></TD
></TR
></TABLE
><P
>a function to provide the equivalent of fetching a
character from a string array</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24478"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the input UTF8 *</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>pos</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the position of the desired UTF8 char (in chars)</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>a pointer to the UTF8 character or NULL</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24495"
></A
><H3
><A
NAME="XMLUTF8STRLOC"
></A
>xmlUTF8Strloc ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlUTF8Strloc (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utfchar);</PRE
></TD
></TR
></TABLE
><P
>a function to provide relative location of a UTF8 char</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24503"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the input UTF8 *</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utfchar</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> the UTF8 character to be found</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the relative character position of the desired char
or -1 if not found</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24520"
></A
><H3
><A
NAME="XMLUTF8STRSUB"
></A
>xmlUTF8Strsub ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
><A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
>* xmlUTF8Strsub (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf,
int start,
int len);</PRE
></TD
></TR
></TABLE
><P
>Note: positions are given in units of UTF-8 chars</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24528"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a sequence of UTF-8 encoded bytes</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>start</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> relative pos of first char</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>len</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> total number to copy</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>a pointer to a newly created string
or NULL if any problem</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
><HR><DIV
CLASS="REFSECT2"
><A
NAME="AEN24549"
></A
><H3
><A
NAME="XMLUTF8STRLEN"
></A
>xmlUTF8Strlen ()</H3
><TABLE
BORDER="0"
BGCOLOR="#D6E8FF"
WIDTH="100%"
CELLPADDING="6"
><TR
><TD
><PRE
CLASS="PROGRAMLISTING"
>int xmlUTF8Strlen (const <A
HREF="libxml-tree.html#XMLCHAR"
>xmlChar</A
> *utf);</PRE
></TD
></TR
></TABLE
><P
>compute the length of an UTF8 string, it doesn't do a full UTF8
checking of the content of the string.</P
><P
></P
><DIV
CLASS="INFORMALTABLE"
><A
NAME="AEN24556"
></A
><P
></P
><TABLE
BORDER="0"
WIDTH="100%"
BGCOLOR="#FFD0D0"
CELLSPACING="0"
CELLPADDING="4"
CLASS="CALSTABLE"
><TBODY
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><TT
CLASS="PARAMETER"
><I
>utf</I
></TT
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
> a sequence of UTF-8 encoded bytes</TD
></TR
><TR
><TD
WIDTH="20%"
ALIGN="RIGHT"
VALIGN="TOP"
><I
CLASS="EMPHASIS"
>Returns</I
> :</TD
><TD
WIDTH="80%"
ALIGN="LEFT"
VALIGN="TOP"
>the number of characters in the string or -1 in case of error</TD
></TR
></TBODY
></TABLE
><P
></P
></DIV
></DIV
></DIV
><DIV
CLASS="NAVFOOTER"
><BR
CLEAR="all"><BR><TABLE
WIDTH="100%"
BORDER="0"
BGCOLOR="#000000"
CELLPADDING="1"
CELLSPACING="0"
><TR
><TD
WIDTH="25%"
BGCOLOR="#C00000"
ALIGN="left"
><A
HREF="libxml-parserinternals.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><<< Previous Page</B
></FONT
></A
></TD
><TD
WIDTH="25%"
BGCOLOR="#0000C0"
ALIGN="center"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><A
HREF="book1.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Home</B
></FONT
></A
></B
></FONT
></TD
><TD
WIDTH="25%"
BGCOLOR="#00C000"
ALIGN="center"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
><A
HREF="libxml-lib.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Up</B
></FONT
></A
></B
></FONT
></TD
><TD
WIDTH="25%"
BGCOLOR="#C00000"
ALIGN="right"
><A
HREF="libxml-hash.html"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>Next Page >>></B
></FONT
></A
></TD
></TR
><TR
><TD
COLSPAN="2"
ALIGN="left"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>parserInternals</B
></FONT
></TD
><TD
COLSPAN="2"
ALIGN="right"
><FONT
COLOR="#FFFFFF"
SIZE="3"
><B
>hash</B
></FONT
></TD
></TR
></TABLE
></DIV
></BODY
></HTML
>