path: root/Doc/libxmllib.tex

\section{Standard Module \sectcode{xmllib}}
% Author: Sjoerd Mullender
\label{module-xmllib}
\stmodindex{xmllib}
\index{XML}

This module defines a class \code{XMLParser} which serves as the basis 
for parsing text files formatted in XML (eXtended Markup Language).

The \code{XMLParser} class must be instantiated without arguments.  It 
has the following interface methods:

\renewcommand{\indexsubitem}{(XMLParser method)}

\begin{funcdesc}{reset}{}
Reset the instance.  Loses all unprocessed data.  This is called
implicitly at the instantiation time.
\end{funcdesc}

\begin{funcdesc}{setnomoretags}{}
Stop processing tags.  Treat all following input as literal input
(CDATA).
\end{funcdesc}

\begin{funcdesc}{setliteral}{}
Enter literal mode (CDATA mode).
\end{funcdesc}

\begin{funcdesc}{feed}{data}
Feed some text to the parser.  It is processed insofar as it consists
of complete elements; incomplete data is buffered until more data is
fed or \code{close()} is called.
\end{funcdesc}

\begin{funcdesc}{close}{}
Force processing of all buffered data as if it were followed by an
end-of-file mark.  This method may be redefined by a derived class to
define additional processing at the end of the input, but the
redefined version should always call \code{XMLParser.close()}.
\end{funcdesc}

\begin{funcdesc}{translate_references}{data}
Translate all entity and character references in \code{data} and
returns the translated string.
\end{funcdesc}

\begin{funcdesc}{handle_xml}{encoding\, standalone}
This method is called when the \code{<?xml ...?>} tag is processed.
The arguments are the values of the encoding and standalone attributes 
in the tag.  Both encoding and standalone are optional.  The values
passed to \code{handle_xml} default to \code{None} and the string
\code{'no'} respectively.
\end{funcdesc}

\begin{funcdesc}{handle_doctype}{tag\, data}
This method is called when the \code{<!DOCTYPE...>} tag is processed.
The arguments are the name of the root element and the uninterpreted
contents of the tag, starting after the white space after the name of
the root element.
\end{funcdesc}

\begin{funcdesc}{handle_starttag}{tag\, method\, attributes}
This method is called to handle start tags for which a
\code{start_\var{tag}()} method has been defined.  The \code{tag}
argument is the name of the tag, and the \code{method} argument is the
bound method which should be used to support semantic interpretation
of the start tag.  The \var{attributes} argument is a dictionary of
attributes, the key being the \var{name} and the value being the
\var{value} of the attribute found inside the tag's \code{<>} brackets.
Character and entity references in the \var{value} have
been interpreted.  For instance, for the tag
\code{<A HREF="http://www.cwi.nl/">}, this method would be called as
\code{handle_starttag('A', self.start_A, \{'HREF': 'http://www.cwi.nl/'\})}.
The base implementation simply calls \code{method} with \code{attributes}
as the only argument.
\end{funcdesc}

\begin{funcdesc}{handle_endtag}{tag\, method}
This method is called to handle endtags for which an
\code{end_\var{tag}()} method has been defined.  The \code{tag}
argument is the name of the tag, and the
\code{method} argument is the bound method which should be used to
support semantic interpretation of the end tag.  If no
\code{end_\var{tag}()} method is defined for the closing element, this
handler is not called.  The base implementation simply calls
\code{method}.
\end{funcdesc}

\begin{funcdesc}{handle_data}{data}
This method is called to process arbitrary data.  It is intended to be
overridden by a derived class; the base class implementation does
nothing.
\end{funcdesc}

\begin{funcdesc}{handle_charref}{ref}
This method is called to process a character reference of the form
``\code{\&\#\var{ref};}''.  \var{ref} can either be a decimal number,
or a hexadecimal number when preceded by \code{x}.
In the base implementation, \var{ref} must be a number in the
range 0-255.  It translates the character to \ASCII{} and calls the
method \code{handle_data()} with the character as argument.  If
\var{ref} is invalid or out of range, the method
\code{unknown_charref(\var{ref})} is called to handle the error.  A
subclass must override this method to provide support for character
references outside of the \ASCII{} range.
\end{funcdesc}

\begin{funcdesc}{handle_entityref}{ref}
This method is called to process a general entity reference of the form
``\code{\&\var{ref};}'' where \var{ref} is an general entity
reference.  It looks for \var{ref} in the instance (or class)
variable \code{entitydefs} which should be a mapping from entity names
to corresponding translations.
If a translation is found, it calls the method \code{handle_data()}
with the translation; otherwise, it calls the method
\code{unknown_entityref(\var{ref})}.  The default \code{entitydefs}
defines translations for \code{\&amp;}, \code{\&apos}, \code{\&gt;},
\code{\&lt;}, and \code{\&quot;}.
\end{funcdesc}

\begin{funcdesc}{handle_comment}{comment}
This method is called when a comment is encountered.  The
\code{comment} argument is a string containing the text between the
``\code{<!--}'' and ``\code{-->}'' delimiters, but not the delimiters
themselves.  For example, the comment ``\code{<!--text-->}'' will
cause this method to be called with the argument \code{'text'}.  The
default method does nothing.
\end{funcdesc}

\begin{funcdesc}{handle_cdata}{data}
This method is called when a CDATA element is encountered.  The
\code{data} argument is a string containing the text between the
``\code{<![CDATA[}'' and ``\code{]]>}'' delimiters, but not the delimiters
themselves.  For example, the entity ``\code{<![CDATA[text]]>}'' will
cause this method to be called with the argument \code{'text'}.  The
default method does nothing.
\end{funcdesc}

\begin{funcdesc}{handle_proc}{name\, data}
This method is called when a processing instruction (PI) is encountered.  The
\code{name} is the PI target, and the \code{data} argument is a
string containing the text between the PI target and the closing delimiter,
but not the delimiter itself.  For example, the instruction
``\code{<?XML text?>}'' will cause this method to be called with the
arguments \code{'XML'} and \code{'text'}.  The default method does
nothing.  Note that if a document starts with a \code{<?xml ...?>}
tag, \code{handle_xml} is called to handle it.
\end{funcdesc}

\begin{funcdesc}{handle_special}{data}
This method is called when a declaration is encountered.  The
\code{data} argument is a string containing the text between the
``\code{<!}'' and ``\code{>}'' delimiters, but not the delimiters
themselves.  For example, the entity ``\code{<!ENTITY text>}'' will
cause this method to be called with the argument \code{'ENTITY text'}.  The
default method does nothing.  Note that \code{<!DOCTYPE ...>} is
handled separately if it is located at the start of the document.
\end{funcdesc}

\begin{funcdesc}{syntax_error}{message}
This method is called when a syntax error is encountered.  The
\code{message} is a description of what was wrong.  The default method 
raises a \code{RuntimeError} exception.  If this method is overridden, 
it is permissable for it to return.  This method is only called when
the error can be recovered from.  Unrecoverable errors raise a
\code{RuntimeError} without first calling \code{syntax_error}.
\end{funcdesc}

\begin{funcdesc}{unknown_starttag}{tag\, attributes}
This method is called to process an unknown start tag.  It is intended
to be overridden by a derived class; the base class implementation
does nothing.
\end{funcdesc}

\begin{funcdesc}{unknown_endtag}{tag}
This method is called to process an unknown end tag.  It is intended
to be overridden by a derived class; the base class implementation
does nothing.
\end{funcdesc}

\begin{funcdesc}{unknown_charref}{ref}
This method is called to process unresolvable numeric character
references.  It is intended to be overridden by a derived class; the
base class implementation does nothing.
\end{funcdesc}

\begin{funcdesc}{unknown_entityref}{ref}
This method is called to process an unknown entity reference.  It is
intended to be overridden by a derived class; the base class
implementation does nothing.
\end{funcdesc}

Apart from overriding or extending the methods listed above, derived
classes may also define methods and variables of the following form to
define processing of specific tags.  Tag names in the input stream are
case dependent; the \var{tag} occurring in method names must be in the
correct case:

\begin{funcdesc}{start_\var{tag}}{attributes}
This method is called to process an opening tag \var{tag}.  The
\var{attributes} argument has the same meaning as described for
\code{handle_starttag()} above.  In fact, the base implementation of
\code{handle_starttag} calls this method.
\end{funcdesc}

\begin{funcdesc}{end_\var{tag}}{}
This method is called to process a closing tag \var{tag}.
\end{funcdesc}

\begin{datadesc}{\var{tag}_attributes}
If a class or instance variable \code{\var{tag}_attributes} exists, it 
should be a list or a dictionary.  If a list, the elements of the list 
are the valid attributes for the element \var{tag}; if a dictionary,
the keys are the valid attributes for the element \var{tag}, and the
values the default values of the attributes, or \code{None} if there
is no default.
In addition to the attributes that were present in the tag, the
attribute dictionary that is passed to \code{handle_starttag} and
\code{unknown_starttag} contains values for all attributes that have a
default value.
\end{datadesc}