001package org.apache.maven.doxia.module.xhtml;
002
003/*
004 * Licensed to the Apache Software Foundation (ASF) under one
005 * or more contributor license agreements.  See the NOTICE file
006 * distributed with this work for additional information
007 * regarding copyright ownership.  The ASF licenses this file
008 * to you under the Apache License, Version 2.0 (the
009 * "License"); you may not use this file except in compliance
010 * with the License.  You may obtain a copy of the License at
011 *
012 *   http://www.apache.org/licenses/LICENSE-2.0
013 *
014 * Unless required by applicable law or agreed to in writing,
015 * software distributed under the License is distributed on an
016 * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
017 * KIND, either express or implied.  See the License for the
018 * specific language governing permissions and limitations
019 * under the License.
020 */
021
022import javax.swing.text.html.HTML.Attribute;
023
024import org.apache.maven.doxia.macro.MacroExecutionException;
025import org.apache.maven.doxia.parser.Parser;
026import org.apache.maven.doxia.parser.XhtmlBaseParser;
027import org.apache.maven.doxia.sink.Sink;
028import org.apache.maven.doxia.sink.SinkEventAttributeSet;
029
030import org.codehaus.plexus.component.annotations.Component;
031import org.codehaus.plexus.util.xml.pull.XmlPullParser;
032import org.codehaus.plexus.util.xml.pull.XmlPullParserException;
033
034/**
035 * Parse an xhtml model and emit events into a Doxia Sink.
036 *
037 * @author <a href="mailto:jason@maven.org">Jason van Zyl</a>
038 * @version $Id$
039 * @since 1.0
040 */
041@Component( role = Parser.class, hint = "xhtml" )
042public class XhtmlParser
043    extends XhtmlBaseParser
044    implements XhtmlMarkup
045{
046    /** For boxed verbatim. */
047    private boolean boxed;
048
049    /** Empty elements don't write a closing tag. */
050    private boolean isEmptyElement;
051
052    /** {@inheritDoc} */
053    protected void handleStartTag( XmlPullParser parser, Sink sink )
054        throws XmlPullParserException, MacroExecutionException
055    {
056        isEmptyElement = parser.isEmptyElementTag();
057
058        SinkEventAttributeSet attribs = getAttributesFromParser( parser );
059
060        if ( parser.getName().equals( HTML.toString() ) )
061        {
062            //Do nothing
063            return;
064        }
065        else if ( parser.getName().equals( HEAD.toString() ) )
066        {
067            sink.head( attribs );
068        }
069        else if ( parser.getName().equals( TITLE.toString() ) )
070        {
071            sink.title( attribs );
072        }
073        else if ( parser.getName().equals( META.toString() ) )
074        {
075            String name = parser.getAttributeValue( null, Attribute.NAME.toString() );
076            String content = parser.getAttributeValue( null, Attribute.CONTENT.toString() );
077
078            if ( "author".equals( name ) )
079            {
080                sink.author( null );
081
082                sink.text( content );
083
084                sink.author_();
085            }
086            else if ( "date".equals( name ) )
087            {
088                sink.date( null );
089
090                sink.text( content );
091
092                sink.date_();
093            }
094            else
095            {
096                sink.unknown( "meta", new Object[] { Integer.valueOf( TAG_TYPE_SIMPLE ) }, attribs );
097            }
098        }
099        /*
100         * The ADDRESS element may be used by authors to supply contact information
101         * for a model or a major part of a model such as a form. This element
102         *  often appears at the beginning or end of a model.
103         */
104        else if ( parser.getName().equals( ADDRESS.toString() ) )
105        {
106            sink.author( attribs );
107        }
108        else if ( parser.getName().equals( BODY.toString() ) )
109        {
110            sink.body( attribs );
111        }
112        else if ( parser.getName().equals( DIV.toString() ) )
113        {
114            String divclass = parser.getAttributeValue( null, Attribute.CLASS.toString() );
115
116            if ( "source".equals( divclass ) )
117            {
118                this.boxed = true;
119            }
120
121            baseStartTag( parser, sink ); // pick up other divs
122        }
123        /*
124         * The PRE element tells visual user agents that the enclosed text is
125         * "preformatted". When handling preformatted text, visual user agents:
126         * - May leave white space intact.
127         * - May render text with a fixed-pitch font.
128         * - May disable automatic word wrap.
129         * - Must not disable bidirectional processing.
130         * Non-visual user agents are not required to respect extra white space
131         * in the content of a PRE element.
132         */
133        else if ( parser.getName().equals( PRE.toString() ) )
134        {
135            if ( boxed )
136            {
137                attribs.addAttributes( SinkEventAttributeSet.BOXED );
138            }
139
140            verbatim();
141
142            sink.verbatim( attribs );
143        }
144        else if ( !baseStartTag( parser, sink ) )
145        {
146            if ( isEmptyElement )
147            {
148                handleUnknown( parser, sink, TAG_TYPE_SIMPLE );
149            }
150            else
151            {
152                handleUnknown( parser, sink, TAG_TYPE_START );
153            }
154
155            if ( getLog().isDebugEnabled() )
156            {
157                String position = "[" + parser.getLineNumber() + ":"
158                    + parser.getColumnNumber() + "]";
159                String tag = "<" + parser.getName() + ">";
160
161                getLog().debug( "Unrecognized xhtml tag: " + tag + " at " + position );
162            }
163        }
164    }
165
166    /** {@inheritDoc} */
167    protected void handleEndTag( XmlPullParser parser, Sink sink )
168        throws XmlPullParserException, MacroExecutionException
169    {
170        if ( parser.getName().equals( HTML.toString() ) )
171        {
172            //Do nothing
173            return;
174        }
175        else if ( parser.getName().equals( HEAD.toString() ) )
176        {
177            sink.head_();
178        }
179        else if ( parser.getName().equals( TITLE.toString() ) )
180        {
181            sink.title_();
182        }
183        else if ( parser.getName().equals( BODY.toString() ) )
184        {
185            consecutiveSections( 0, sink );
186
187            sink.body_();
188        }
189        else if ( parser.getName().equals( ADDRESS.toString() ) )
190        {
191            sink.author_();
192        }
193        else if ( parser.getName().equals( DIV.toString() ) )
194        {
195            this.boxed = false;
196            baseEndTag( parser, sink );
197        }
198        else if ( !baseEndTag( parser, sink ) )
199        {
200            if ( !isEmptyElement )
201            {
202                handleUnknown( parser, sink, TAG_TYPE_END );
203            }
204        }
205
206        isEmptyElement = false;
207    }
208
209    /** {@inheritDoc} */
210    protected void init()
211    {
212        super.init();
213
214        this.boxed = false;
215        this.isEmptyElement = false;
216    }
217}