File: SAXmyHtmlHandler.java

package info (click to toggle)
libitext-java 2.1.7-16
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 11,788 kB
  • sloc: java: 94,213; xml: 947; makefile: 6
file content (276 lines) | stat: -rw-r--r-- 10,490 bytes parent folder | download | duplicates (7)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
/*
 * $Id: SAXmyHtmlHandler.java 3373 2008-05-12 16:21:24Z xlv $
 *
 * Copyright 2001, 2002 by Bruno Lowagie.
 *
 * The contents of this file are subject to the Mozilla Public License Version 1.1
 * (the "License"); you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at http://www.mozilla.org/MPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the License.
 *
 * The Original Code is 'iText, a free JAVA-PDF library'.
 *
 * The Initial Developer of the Original Code is Bruno Lowagie. Portions created by
 * the Initial Developer are Copyright (C) 1999, 2000, 2001, 2002 by Bruno Lowagie.
 * All Rights Reserved.
 * Co-Developer of the code is Paulo Soares. Portions created by the Co-Developer
 * are Copyright (C) 2000, 2001, 2002 by Paulo Soares. All Rights Reserved.
 *
 * Contributor(s): all the names of the contributors are added in the source code
 * where applicable.
 *
 * Alternatively, the contents of this file may be used under the terms of the
 * LGPL license (the "GNU LIBRARY GENERAL PUBLIC LICENSE"), in which case the
 * provisions of LGPL are applicable instead of those above.  If you wish to
 * allow use of your version of this file only under the terms of the LGPL
 * License and not to allow others to use your version of this file under
 * the MPL, indicate your decision by deleting the provisions above and
 * replace them with the notice and other provisions required by the LGPL.
 * If you do not delete the provisions above, a recipient may use your version
 * of this file under either the MPL or the GNU LIBRARY GENERAL PUBLIC LICENSE.
 *
 * This library is free software; you can redistribute it and/or modify it
 * under the terms of the MPL as stated above or under the terms of the GNU
 * Library General Public License as published by the Free Software Foundation;
 * either version 2 of the License, or any later version.
 *
 * This library is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU Library general Public License for more
 * details.
 *
 * If you didn't download this code from the following link, you should check if
 * you aren't using an obsolete version:
 * http://www.lowagie.com/iText/
 */

package com.lowagie.text.html;

import java.util.HashMap;
import java.util.Properties;

import org.xml.sax.Attributes;

import com.lowagie.text.DocListener;
import com.lowagie.text.DocumentException;
import com.lowagie.text.Element;
import com.lowagie.text.ElementTags;
import com.lowagie.text.ExceptionConverter;
import com.lowagie.text.pdf.BaseFont;
import com.lowagie.text.xml.SAXiTextHandler;
import com.lowagie.text.xml.XmlPeer;

/**
 * The <CODE>Tags</CODE>-class maps several XHTML-tags to iText-objects.
 */

public class SAXmyHtmlHandler extends SAXiTextHandler // SAXmyHandler
{

    /** These are the properties of the body section. */
    private Properties bodyAttributes = new Properties();

    /** This is the status of the table border. */
    private boolean tableBorder = false;

    /**
     * Constructs a new SAXiTextHandler that will translate all the events
     * triggered by the parser to actions on the <CODE>Document</CODE>-object.
     * 
     * @param document
     *            this is the document on which events must be triggered
     */

    public SAXmyHtmlHandler(DocListener document) {
        super(document, new HtmlTagMap());
    }
    /**
     * Constructs a new SAXiTextHandler that will translate all the events
     * triggered by the parser to actions on the <CODE>Document</CODE>-object.
     * 
     * @param document
     *            this is the document on which events must be triggered
     * @param bf
     */

    public SAXmyHtmlHandler(DocListener document, BaseFont bf) {
        super(document, new HtmlTagMap(), bf);
    }

    /**
     * Constructs a new SAXiTextHandler that will translate all the events
     * triggered by the parser to actions on the <CODE>Document</CODE>-object.
     * 
     * @param document
     *            this is the document on which events must be triggered
     * @param htmlTags
     *            a tagmap translating HTML tags to iText tags
     */

    public SAXmyHtmlHandler(DocListener document, HashMap htmlTags) {
        super(document, htmlTags);
    }

    /**
     * This method gets called when a start tag is encountered.
     * 
     * @param uri
     *            the Uniform Resource Identifier
     * @param lname
     *            the local name (without prefix), or the empty string if
     *            Namespace processing is not being performed.
     * @param name
     *            the name of the tag that is encountered
     * @param attrs
     *            the list of attributes
     */

    public void startElement(String uri, String lname, String name,
            Attributes attrs) {
        // System.err.println("Start: " + name);

        // super.handleStartingTags is replaced with handleStartingTags
        // suggestion by Vu Ngoc Tan/Hop
    	name = name.toLowerCase();
        if (HtmlTagMap.isHtml(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isHead(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isTitle(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isMeta(name)) {
            // we look if we can change the body attributes
            String meta = null;
            String content = null;
            if (attrs != null) {
                for (int i = 0; i < attrs.getLength(); i++) {
                    String attribute = attrs.getQName(i);
                    if (attribute.equalsIgnoreCase(HtmlTags.CONTENT))
                        content = attrs.getValue(i);
                    else if (attribute.equalsIgnoreCase(HtmlTags.NAME))
                        meta = attrs.getValue(i);
                }
            }
            if (meta != null && content != null) {
                bodyAttributes.put(meta, content);
            }
            return;
        }
        if (HtmlTagMap.isLink(name)) {
            // we do nothing for the moment, in a later version we could extract
            // the style sheet
            return;
        }
        if (HtmlTagMap.isBody(name)) {
            // maybe we could extract some info about the document: color,
            // margins,...
            // but that's for a later version...
            XmlPeer peer = new XmlPeer(ElementTags.ITEXT, name);
            peer.addAlias(ElementTags.TOP, HtmlTags.TOPMARGIN);
            peer.addAlias(ElementTags.BOTTOM, HtmlTags.BOTTOMMARGIN);
            peer.addAlias(ElementTags.RIGHT, HtmlTags.RIGHTMARGIN);
            peer.addAlias(ElementTags.LEFT, HtmlTags.LEFTMARGIN);
            bodyAttributes.putAll(peer.getAttributes(attrs));
            handleStartingTags(peer.getTag(), bodyAttributes);
            return;
        }
        if (myTags.containsKey(name)) {
            XmlPeer peer = (XmlPeer) myTags.get(name);
            if (ElementTags.TABLE.equals(peer.getTag()) || ElementTags.CELL.equals(peer.getTag())) {
                Properties p = peer.getAttributes(attrs);
                String value;
                if (ElementTags.TABLE.equals(peer.getTag())
                        && (value = p.getProperty(ElementTags.BORDERWIDTH)) != null) {
                    if (Float.parseFloat(value + "f") > 0) {
                        tableBorder = true;
                    }
                }
                if (tableBorder) {
                    p.put(ElementTags.LEFT, String.valueOf(true));
                    p.put(ElementTags.RIGHT, String.valueOf(true));
                    p.put(ElementTags.TOP, String.valueOf(true));
                    p.put(ElementTags.BOTTOM, String.valueOf(true));
                }
                handleStartingTags(peer.getTag(), p);
                return;
            }
            handleStartingTags(peer.getTag(), peer.getAttributes(attrs));
            return;
        }
        Properties attributes = new Properties();
        if (attrs != null) {
            for (int i = 0; i < attrs.getLength(); i++) {
                String attribute = attrs.getQName(i).toLowerCase();
                attributes.setProperty(attribute, attrs.getValue(i).toLowerCase());
            }
        }
        handleStartingTags(name, attributes);
    }

    /**
     * This method gets called when an end tag is encountered.
     * 
     * @param uri
     *            the Uniform Resource Identifier
     * @param lname
     *            the local name (without prefix), or the empty string if
     *            Namespace processing is not being performed.
     * @param name
     *            the name of the tag that ends
     */

    public void endElement(String uri, String lname, String name) {
        // System.err.println("End: " + name);
    	name = name.toLowerCase();
        if (ElementTags.PARAGRAPH.equals(name)) {
            try {
                document.add((Element) stack.pop());
                return;
            } catch (DocumentException e) {
                throw new ExceptionConverter(e);
            }
        }
        if (HtmlTagMap.isHead(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isTitle(name)) {
            if (currentChunk != null) {
                bodyAttributes.put(ElementTags.TITLE, currentChunk.getContent());
            }
            return;
        }
        if (HtmlTagMap.isMeta(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isLink(name)) {
            // we do nothing
            return;
        }
        if (HtmlTagMap.isBody(name)) {
            // we do nothing
            return;
        }
        if (myTags.containsKey(name)) {
            XmlPeer peer = (XmlPeer) myTags.get(name);
            if (ElementTags.TABLE.equals(peer.getTag())) {
                tableBorder = false;
            }
            super.handleEndingTags(peer.getTag());
            return;
        }
        // super.handleEndingTags is replaced with handleEndingTags
        // suggestion by Ken Auer
        handleEndingTags(name);
    }
}