Development/Tutorials/Programming Tutorial KDE 4/How to write an XML parser

A parser is used to distinguish between formal language and bulk data of a given grammar. See http://en.wikipedia.org/wiki/Parser for more information. There are two ways to write a parser: to split up the content of a file into an object as known from object-oriented programming (the DOM approach) or to trigger a function everytime a reader occurs a given syntax tag (the QXML approach).

The QXML approach

parser.h: <highlightSyntax language="cpp"> /*

parser.h - demonstration of a parser in C++

• /

1. ifndef PARSER_H
2. define PARSER_H

1. include <qstring.h>
2. include <QtXml/QXmlDefaultHandler>
3. include <QtXml/QXmlAttributes>

class Parser : public QXmlDefaultHandler { public:

 Parser();

 /** given by the framework from qxml. Called when parsing the xml-document starts.          */
 bool startDocument();

 /** given by the framework from qxml. Called when the reader occurs an open tag (e.g. \<b\> ) */
 bool startElement( const QString&, const QString&, const QString& qName, const QXmlAttributes& att );

};

1. endif

</highlightSyntax>

parser.cpp: <highlightSyntax language="cpp"> /*

parser.cpp - demonstration of a parser in C++

• /

1. include "parser.h"
2. include <kdebug.h>

 Parser::Parser()
 {
 }
 
 bool Parser::startDocument()
 {
   kDebug() << "Searching document for tags" << endl;
   return true;
 }
 
 bool Parser::startElement( const QString&, const QString&, const QString& qName, const QXmlAttributes& att )
 {
   kDebug() << "Found Element " << qName << endl;
   return true;
}

</highlightSyntax>

hello.cpp: <highlightSyntax language="cpp"> /* hello.cpp compile it with g++ -I. -I/home/kde-devel/kde/include -I/home/kde-devel/qt-unstable/include/Qt -I/home/kde-devel/qt-unstable/include I/home/kde-devel/qt-unstable/include/QtXml parser.h parser.cpp hello.cpp -L/home/kde-devel/kde/lib -L/home/kde-devel/qt-unstable/lib -lQtCore_debug -lQtXml_debug -lkdeui

• /

1. include <qstring.h>
2. include <QXmlInputSource>
3. include <qfile.h>
4. include <parser.h>

int main() {

 Parser* handler=new Parser();
 QXmlInputSource* source=new QXmlInputSource(new QFile("hello.htm"));
 QXmlSimpleReader reader;
 reader.setContentHandler( handler );
 reader.parse( source );

} </highlightSyntax>

The DOM approach

<highlightSyntax language="cpp"> /*

  dom.cpp
  A demonstration how to use the dom parsing framework.
  Prints the first subnode of an html file, i.e. typically "head" or "body".
  compile it like this:
  g++ -I. -I/opt/kde3/include -I/usr/lib/qt3/include dom.cpp -L/opt/kde3/lib \

-L/usr/lib/qt3/lib -lqt-mt -lkdeui

• /

1. include <qdom.h>
2. include <qfile.h>
3. include <kdebug.h>

int main() {

 QDomDocument doc( "myDocument" );
 QFile qf("hello.htm");
 doc.setContent( &qf );
 QDomElement docElement = doc.documentElement(); 
 QDomNode node;
 node = docElement.firstChild();
 kdDebug() << node.nodeName() << endl;

} </highlightSyntax>