lib/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-07-20 16:43:05 +03:00
Code Activity
Files
c758c229b4f9669ff61a7ce1af3e4f74b11e2cb0
libxml2/doc/html/libxml-encoding.html
Daniel Veillard c758c229b4 rebuilt the API and docs. Daniel 
* doc/libxml2-api.xml doc/html/*: rebuilt the API and docs.
Daniel
2003-08-04 20:42:34 +00:00

432 lines
43 KiB
HTML
Raw Blame History

<html><head><meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"><title>encoding</title><meta name="generator" content="DocBook XSL Stylesheets V1.58.1"><style xmlns="http://www.w3.org/TR/xhtml1/transitional" type="text/css">
.synopsis, .classsynopsis {
background: #eeeeee;
border: solid 1px #aaaaaa;
padding: 0.5em;
}
.programlisting {
background: #eeeeff;
border: solid 1px #aaaaff;
padding: 0.5em;
}
.variablelist {
padding: 4px;
margin-left: 3em;
}
.navigation {
background: #ffeeee;
border: solid 1px #ffaaaa;
margin-top: 0.5em;
margin-bottom: 0.5em;
}
.navigation a {
color: #770000;
}
.navigation a:visited {
color: #550000;
}
.navigation .title {
font-size: 200%;
}
</style><link rel="home" href="index.html" title="Gnome XML Library Reference Manual"><link rel="up" href="libxml-lib.html" title="Libxml Library Reference"><link rel="previous" href="libxml-parserInternals.html" title="parserInternals"><link rel="next" href="libxml-hash.html" title="hash"></head><body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF"><table xmlns="http://www.w3.org/TR/xhtml1/transitional" class="navigation" width="100%" summary="Navigation header" cellpadding="2" cellspacing="2"><tr valign="middle"><td><a accesskey="p" href="libxml-parserInternals.html"><img src="left.png" width="24" height="24" border="0" alt="Prev"></img></a></td><td><a accesskey="u" href="libxml-lib.html"><img src="up.png" width="24" height="24" border="0" alt="Up"></img></a></td><td><a accesskey="h" href="index.html"><img src="home.png" width="24" height="24" border="0" alt="Home"></img></a></td><th width="100%" align="center">Gnome XML Library Reference Manual</th><td><a accesskey="n" href="libxml-hash.html"><img src="right.png" width="24" height="24" border="0" alt="Next"></img></a></td></tr></table><div class="refentry" lang="en"><a name="libxml-encoding"></a><div class="titlepage"></div><div class="refnamediv"><h2>encoding</h2><p>encoding &#8212; </p></div><div class="refsynopsisdiv"><h2>Synopsis</h2><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);
<a href="libxml-encoding.html#xmlCharEncodingHandlerPtr">xmlCharEncodingHandlerPtr</a> <a href="libxml-encoding.html#xmlNewCharEncodingHandler">xmlNewCharEncodingHandler</a>
(const char *name,
<a href="libxml-encoding.html#xmlCharEncodingInputFunc">xmlCharEncodingInputFunc</a> input,
<a href="libxml-encoding.html#xmlCharEncodingOutputFunc">xmlCharEncodingOutputFunc</a> output);
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#xmlGetUTF8Char">xmlGetUTF8Char</a> (unsigned char *utf,
int *len);
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);
int <a href="libxml-encoding.html#xmlUTF8Size">xmlUTF8Size</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf);
int <a href="libxml-encoding.html#xmlUTF8Charcmp">xmlUTF8Charcmp</a> (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf1,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf2);
</pre></div><div class="refsect1" lang="en"><h2>Description</h2><p>
</p></div><div class="refsect1" lang="en"><h2>Details</h2><div class="refsect2" lang="en"><h3><a name="xmlCharEncoding"></a>enum xmlCharEncoding</h3><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><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 xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncodingInputFunc"></a>xmlCharEncodingInputFunc ()</h3><pre class="programlisting">int (*xmlCharEncodingInputFunc) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> a pointer to an array of bytes to store the UTF-8 result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> a pointer to an array of chars in the original encoding
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the number of byte written, or -1 by lack of space, or -2
if the transcoding failed.
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictiable.
The value of <i><tt>outlen</tt></i> after return is the number of octets consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncodingOutputFunc"></a>xmlCharEncodingOutputFunc ()</h3><pre class="programlisting">int (*xmlCharEncodingOutputFunc) (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> a pointer to an array of bytes to store the result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> a pointer to an array of UTF-8 chars
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the number of byte written, or -1 by lack of space, or -2
if the transcoding failed.
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictiable.
The value of <i><tt>outlen</tt></i> after return is the number of ocetes consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncodingHandler"></a>struct xmlCharEncodingHandler</h3><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><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncodingHandlerPtr"></a>xmlCharEncodingHandlerPtr</h3><pre class="programlisting">typedef xmlCharEncodingHandler *xmlCharEncodingHandlerPtr;
</pre><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlInitCharEncodingHandlers"></a>xmlInitCharEncodingHandlers ()</h3><pre class="programlisting">void xmlInitCharEncodingHandlers (void);</pre><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 xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCleanupCharEncodingHandlers"></a>xmlCleanupCharEncodingHandlers ()</h3><pre class="programlisting">void xmlCleanupCharEncodingHandlers (void);</pre><p>
Cleanup the memory allocated for the char encoding support, it
unregisters all the encoding handlers and the aliases.</p><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlRegisterCharEncodingHandler"></a>xmlRegisterCharEncodingHandler ()</h3><pre class="programlisting">void xmlRegisterCharEncodingHandler (<a href="libxml-encoding.html#xmlCharEncodingHandlerPtr">xmlCharEncodingHandlerPtr</a> handler);</pre><p>
Register the char encoding handler, surprising, isn't it ?</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>handler</tt></i><EFBFBD>:</span></td><td> the xmlCharEncodingHandlerPtr handler block
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlGetCharEncodingHandler"></a>xmlGetCharEncodingHandler ()</h3><pre class="programlisting"><a href="libxml-encoding.html#xmlCharEncodingHandlerPtr">xmlCharEncodingHandlerPtr</a> xmlGetCharEncodingHandler
(<a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);</pre><p>
Search in the registered set the handler able to read/write that encoding.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>enc</tt></i><EFBFBD>:</span></td><td> an xmlCharEncoding value.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the handler or NULL if not found
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlFindCharEncodingHandler"></a>xmlFindCharEncodingHandler ()</h3><pre class="programlisting"><a href="libxml-encoding.html#xmlCharEncodingHandlerPtr">xmlCharEncodingHandlerPtr</a> xmlFindCharEncodingHandler
(const char *name);</pre><p>
Search in the registered set the handler able to read/write that encoding.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i><EFBFBD>:</span></td><td> a string describing the char encoding.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the handler or NULL if not found
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlNewCharEncodingHandler"></a>xmlNewCharEncodingHandler ()</h3><pre class="programlisting"><a href="libxml-encoding.html#xmlCharEncodingHandlerPtr">xmlCharEncodingHandlerPtr</a> xmlNewCharEncodingHandler
(const char *name,
<a href="libxml-encoding.html#xmlCharEncodingInputFunc">xmlCharEncodingInputFunc</a> input,
<a href="libxml-encoding.html#xmlCharEncodingOutputFunc">xmlCharEncodingOutputFunc</a> output);</pre><p>
Create and registers an xmlCharEncodingHandler.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i><EFBFBD>:</span></td><td> the encoding name, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><i><tt>input</tt></i><EFBFBD>:</span></td><td> the xmlCharEncodingInputFunc to read that encoding
</td></tr><tr><td><span class="term"><i><tt>output</tt></i><EFBFBD>:</span></td><td> the xmlCharEncodingOutputFunc to write that encoding
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the xmlCharEncodingHandlerPtr created (or NULL in case of error).
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlAddEncodingAlias"></a>xmlAddEncodingAlias ()</h3><pre class="programlisting">int xmlAddEncodingAlias (const char *name,
const char *alias);</pre><p>
Registers and alias <i><tt>alias</tt></i> for an encoding named <i><tt>name</tt></i>. Existing alias
will be overwritten.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i><EFBFBD>:</span></td><td> the encoding name as parsed, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><i><tt>alias</tt></i><EFBFBD>:</span></td><td> the alias name as parsed, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 in case of success, -1 in case of error
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlDelEncodingAlias"></a>xmlDelEncodingAlias ()</h3><pre class="programlisting">int xmlDelEncodingAlias (const char *alias);</pre><p>
Unregisters an encoding alias <i><tt>alias</tt></i></p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>alias</tt></i><EFBFBD>:</span></td><td> the alias name as parsed, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 in case of success, -1 in case of error
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlGetEncodingAlias"></a>xmlGetEncodingAlias ()</h3><pre class="programlisting">const char* xmlGetEncodingAlias (const char *alias);</pre><p>
Lookup an encoding name for the given alias.</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>alias</tt></i><EFBFBD>:</span></td><td> the alias name as parsed, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>NULL if not found the original name otherwise
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCleanupEncodingAliases"></a>xmlCleanupEncodingAliases ()</h3><pre class="programlisting">void xmlCleanupEncodingAliases (void);</pre><p>
Unregisters all aliases</p><p>
</p></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlParseCharEncoding"></a>xmlParseCharEncoding ()</h3><pre class="programlisting"><a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> xmlParseCharEncoding (const char *name);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>name</tt></i><EFBFBD>:</span></td><td> the encoding name as parsed, in UTF-8 format (ASCII actually)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>one of the XML_CHAR_ENCODING_... values or XML_CHAR_ENCODING_NONE
if not recognized.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlGetCharEncodingName"></a>xmlGetCharEncodingName ()</h3><pre class="programlisting">const char* xmlGetCharEncodingName (<a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> enc);</pre><p>
The &quot;canonical&quot; name for XML encoding.
C.f. http://www.w3.org/TR/REC-xml<GTKDOCLINK xmlns="http://www.w3.org/TR/xhtml1/transitional" HREF="charencoding">charencoding</GTKDOCLINK>
Section 4.3.3 Character Encoding in Entities</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>enc</tt></i><EFBFBD>:</span></td><td> the encoding
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the canonical name for the given encoding
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlDetectCharEncoding"></a>xmlDetectCharEncoding ()</h3><pre class="programlisting"><a href="libxml-encoding.html#xmlCharEncoding">xmlCharEncoding</a> xmlDetectCharEncoding (unsigned char *in,
int len);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> a pointer to the first bytes of the XML entity, must be at least
4 bytes long.
</td></tr><tr><td><span class="term"><i><tt>len</tt></i><EFBFBD>:</span></td><td> pointer to the length of the buffer
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>one of the XML_CHAR_ENCODING_... values.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncOutFunc"></a>xmlCharEncOutFunc ()</h3><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><p>
Generic front-end for the encoding handler output function
a first call with <i><tt>in</tt></i> == 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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>handler</tt></i><EFBFBD>:</span></td><td> char enconding transformation data structure
</td></tr><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the output.
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the input
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>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></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncInFunc"></a>xmlCharEncInFunc ()</h3><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><p>
Generic front-end for the encoding handler input function</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>handler</tt></i><EFBFBD>:</span></td><td> char encoding transformation data structure
</td></tr><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the output.
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the input
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>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></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncFirstLine"></a>xmlCharEncFirstLine ()</h3><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><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>handler</tt></i><EFBFBD>:</span></td><td> char enconding transformation data structure
</td></tr><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the output.
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> an xmlBuffer for the input
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>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></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCharEncCloseFunc"></a>xmlCharEncCloseFunc ()</h3><pre class="programlisting">int xmlCharEncCloseFunc (<a href="libxml-encoding.html#xmlCharEncodingHandler">xmlCharEncodingHandler</a> *handler);</pre><p>
Generic front-end for encoding handler close function</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>handler</tt></i><EFBFBD>:</span></td><td> char enconding transformation data structure
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 if success, or -1 in case of error
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="UTF8Toisolat1"></a>UTF8Toisolat1 ()</h3><pre class="programlisting">int UTF8Toisolat1 (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> a pointer to an array of bytes to store the result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> a pointer to an array of UTF-8 chars
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 if success, -2 if the transcoding fails, or -1 otherwise
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <i><tt>outlen</tt></i> after return is the number of ocetes consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="isolat1ToUTF8"></a>isolat1ToUTF8 ()</h3><pre class="programlisting">int isolat1ToUTF8 (unsigned char *out,
int *outlen,
unsigned char *in,
int *inlen);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>out</tt></i><EFBFBD>:</span></td><td> a pointer to an array of bytes to store the result
</td></tr><tr><td><span class="term"><i><tt>outlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>out</tt></i>
</td></tr><tr><td><span class="term"><i><tt>in</tt></i><EFBFBD>:</span></td><td> a pointer to an array of ISO Latin 1 chars
</td></tr><tr><td><span class="term"><i><tt>inlen</tt></i><EFBFBD>:</span></td><td> the length of <i><tt>in</tt></i>
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>0 if success, or -1 otherwise
The value of <i><tt>inlen</tt></i> after return is the number of octets consumed
as the return value is positive, else unpredictable.
The value of <i><tt>outlen</tt></i> after return is the number of ocetes consumed.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlGetUTF8Char"></a>xmlGetUTF8Char ()</h3><pre class="programlisting">int xmlGetUTF8Char (unsigned char *utf,
int *len);</pre><p>
Read one UTF8 Char from <i><tt>utf</tt></i></p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> a sequence of UTF-8 encoded bytes
</td></tr><tr><td><span class="term"><i><tt>len</tt></i><EFBFBD>:</span></td><td> a pointer to <i><tt>bytes</tt></i> len
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the char value or -1 in case of error and update <i><tt>len</tt></i> with the
number of bytes used
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlCheckUTF8"></a>xmlCheckUTF8 ()</h3><pre class="programlisting">int xmlCheckUTF8 (unsigned char *utf);</pre><p>
Checks <i><tt>utf</tt></i> for being valid utf-8. <i><tt>utf</tt></i> 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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> Pointer to putative utf-8 encoded string.
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td> true if <i><tt>utf</tt></i> is valid.
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strsize"></a>xmlUTF8Strsize ()</h3><pre class="programlisting">int xmlUTF8Strsize (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf,
int len);</pre><p>
storage size of an UTF8 string</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> a sequence of UTF-8 encoded bytes
</td></tr><tr><td><span class="term"><i><tt>len</tt></i><EFBFBD>:</span></td><td> the number of characters in the array
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the storage size of
the first 'len' characters of ARRAY
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strndup"></a>xmlUTF8Strndup ()</h3><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><p>
a strndup for array of UTF8's</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> the input UTF8 *
</td></tr><tr><td><span class="term"><i><tt>len</tt></i><EFBFBD>:</span></td><td> the len of <i><tt>utf</tt></i> (in chars)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>a new UTF8 * or NULL
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strpos"></a>xmlUTF8Strpos ()</h3><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><p>
a function to provide the equivalent of fetching a
character from a string array</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> the input UTF8 *
</td></tr><tr><td><span class="term"><i><tt>pos</tt></i><EFBFBD>:</span></td><td> the position of the desired UTF8 char (in chars)
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>a pointer to the UTF8 character or NULL
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strloc"></a>xmlUTF8Strloc ()</h3><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><p>
a function to provide relative location of a UTF8 char</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> the input UTF8 *
</td></tr><tr><td><span class="term"><i><tt>utfchar</tt></i><EFBFBD>:</span></td><td> the UTF8 character to be found
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the relative character position of the desired char
or -1 if not found
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strsub"></a>xmlUTF8Strsub ()</h3><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><p>
Note: positions are given in units of UTF-8 chars</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> a sequence of UTF-8 encoded bytes
</td></tr><tr><td><span class="term"><i><tt>start</tt></i><EFBFBD>:</span></td><td> relative pos of first char
</td></tr><tr><td><span class="term"><i><tt>len</tt></i><EFBFBD>:</span></td><td> total number to copy
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>a pointer to a newly created string
or NULL if any problem
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Strlen"></a>xmlUTF8Strlen ()</h3><pre class="programlisting">int xmlUTF8Strlen (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf);</pre><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="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> a sequence of UTF-8 encoded bytes
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the number of characters in the string or -1 in case of error
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Size"></a>xmlUTF8Size ()</h3><pre class="programlisting">int xmlUTF8Size (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf);</pre><p>
</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf</tt></i><EFBFBD>:</span></td><td> pointer to the UTF8 character
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>the numbers of bytes in the character, -1 on format error
</td></tr></tbody></table></div></div><hr xmlns="http://www.w3.org/TR/xhtml1/transitional"></hr><div class="refsect2" lang="en"><h3><a name="xmlUTF8Charcmp"></a>xmlUTF8Charcmp ()</h3><pre class="programlisting">int xmlUTF8Charcmp (const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf1,
const <a href="libxml-tree.html#xmlChar">xmlChar</a> *utf2);</pre><p>
</p><p>
</p><div class="variablelist"><table border="0"><col align="left" valign="top"><tbody><tr><td><span class="term"><i><tt>utf1</tt></i><EFBFBD>:</span></td><td> pointer to first UTF8 char
</td></tr><tr><td><span class="term"><i><tt>utf2</tt></i><EFBFBD>:</span></td><td> pointer to second UTF8 char
</td></tr><tr><td><span class="term"><span class="emphasis"><em>Returns</em></span> :</span></td><td>result of comparing the two UCS4 values
as with xmlStrncmp
</td></tr></tbody></table></div></div></div></div><table xmlns="http://www.w3.org/TR/xhtml1/transitional" class="navigation" width="100%" summary="Navigation footer" cellpadding="2" cellspacing="0"><tr valign="middle"><td align="left"><a accesskey="p" href="libxml-parserInternals.html"><b>&lt;&lt;<EFBFBD>parserInternals</b></a></td><td align="right"><a accesskey="n" href="libxml-hash.html"><b>hash<EFBFBD>&gt;&gt;</b></a></td></tr></table></body></html>
View Git Blame Copy Permalink