fixing html whitelist bug
[mir.git] / source / mircoders / producer / PDFPreFormattingProducerNode.java
1 /*
2  * Copyright (C) 2001, 2002 The Mir-coders group
3  *
4  * This file is part of Mir.
5  *
6  * Mir is free software; you can redistribute it and/or modify
7  * it under the terms of the GNU General Public License as published by
8  * the Free Software Foundation; either version 2 of the License, or
9  * (at your option) any later version.
10  *
11  * Mir is distributed in the hope that it will be useful,
12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
14  * GNU General Public License for more details.
15  *
16  * You should have received a copy of the GNU General Public License
17  * along with Mir; if not, write to the Free Software
18  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
19  *
20  * In addition, as a special exception, The Mir-coders gives permission to link
21  * the code of this program with  any library licensed under the Apache Software License,
22  * The Sun (tm) Java Advanced Imaging library (JAI), The Sun JIMI library
23  * (or with modified versions of the above that use the same license as the above),
24  * and distribute linked combinations including the two.  You must obey the
25  * GNU General Public License in all respects for all of the code used other than
26  * the above mentioned libraries.  If you modify this file, you may extend this
27  * exception to your version of the file, but you are not obligated to do so.
28  * If you do not wish to do so, delete this exception statement from your version.
29  */
30
31 package mircoders.producer;
32
33 import java.io.PrintWriter;
34 import java.util.ArrayList;
35 import java.util.HashMap;
36 import java.util.Iterator;
37 import java.util.List;
38 import java.util.Map;
39
40 import mir.entity.Entity;
41 import mir.entity.EntityBrowser;
42 import mir.entity.adapter.EntityAdapter;
43 import mir.log.LoggerToWriterAdapter;
44 import mir.log.LoggerWrapper;
45 import mir.misc.StringUtil;
46 import mir.producer.ProducerFailure;
47 import mir.producer.ProducerNode;
48 import mir.util.CachingRewindableIterator;
49 import mir.util.HTMLRoutines;
50 import mir.util.ParameterExpander;
51 import mircoders.entity.EntityContent;
52 import mircoders.entity.EntityImages;
53 import mircoders.storage.DatabaseImages;
54
55
56 public class PDFPreFormattingProducerNode implements ProducerNode {
57   private String contentKey;
58   private int numLinesBetweenImages;
59   private float contentAreaWidthCM;
60   private float characterWidthCM;
61   private float pixelWidthCM;
62   private float lineHeightCM;
63
64   public PDFPreFormattingProducerNode(String aContentKey,String someNumLinesBetweenImages,String aContentAreaWidthCM,String aCharacterWidthCM,String aPixelWidthCM,String aLineHeightCM) {
65     contentKey = aContentKey;
66     numLinesBetweenImages=(new Integer(someNumLinesBetweenImages)).intValue();
67     contentAreaWidthCM=(new Float(aContentAreaWidthCM)).floatValue();
68     characterWidthCM=(new Float(aCharacterWidthCM)).floatValue();
69     pixelWidthCM=(new Float(aPixelWidthCM)).floatValue();
70     lineHeightCM=(new Float(aLineHeightCM)).floatValue();
71
72     //    float characterWidthCM = 0.17F;
73     //float contentAreaWidthCM = 16;
74     //float pixelWidthCM = .03F;
75     //float lineHeightCM = .5F;
76   }
77
78   public void produce(Map aValueMap, String aVerb, LoggerWrapper aLogger) throws ProducerFailure {
79     Object data;
80     Entity entity;
81
82     try {
83       data = ParameterExpander.findValueForKey( aValueMap, contentKey );
84
85       if (! (data instanceof EntityAdapter)) {
86         throw new ProducerFailure("PDFPreFormattingProducerNode: value of '"+contentKey+"' is not an EntityAdapter, but an " + data.getClass().getName(), null);
87       }
88
89       entity = ((EntityAdapter) data).getEntity();
90       if (! (entity instanceof EntityContent)) {
91         throw new ProducerFailure("PDFPreFormattingProducerNode: value of '"+contentKey+"' is not a content EntityAdapter, but a " + entity.getClass().getName() + " adapter", null);
92       }
93
94       int currentPosition = 0;
95
96       //int numLinesBetweenImages=3;
97
98
99
100
101       int numCharsInAnImagelessRow = (new Float(numLinesBetweenImages * (contentAreaWidthCM/characterWidthCM))).intValue();
102
103       boolean outOfText = false;
104
105       ArrayList brokenUpContent = new ArrayList();
106
107
108       List extraTables = new ArrayList();
109       extraTables.add("content_x_media cxm");
110       Iterator images = new EntityBrowser(
111         DatabaseImages.getInstance(), "i", extraTables,
112           "cxm.content_id="+entity.getId()+"and cxm.media_id=i.id",
113           "i.id desc", 30, -1, 0);
114
115       String theContent = ((EntityContent) entity).getFieldValue("content_data");
116       //remove pesky characters
117       theContent = HTMLRoutines.encodeXML(theContent);
118       //put in the <BR> tags so we can turn them to empty blocks
119       theContent = StringUtil.convertNewline2Break(theContent);
120
121       if (images == null){
122           Map row = new HashMap();
123           row.put("text",theContent);
124           row.put("hasImage","0");
125           brokenUpContent.add(row);
126       }
127       if (images != null){
128           //need to add checks for out of content!
129           Map row0 = new HashMap();
130           if (numCharsInAnImagelessRow>(theContent).length()){
131               row0.put("text",theContent);
132               outOfText = true;
133           }
134           else {
135               //break on words so we don't split html entities
136               int lastSpaceAt = theContent.lastIndexOf(" ",numCharsInAnImagelessRow);
137               row0.put("text",theContent.substring(0,lastSpaceAt));
138               currentPosition=lastSpaceAt;
139           }
140           row0.put("hasImage","0");
141           brokenUpContent.add(row0);
142           aLogger.debug("CP1 is "+ currentPosition);
143           while(images.hasNext()){
144               Map row1 = new HashMap();
145               Map row2 = new HashMap();
146               EntityImages currentImage=(EntityImages) images.next();
147               float img_width=(new Float(currentImage.getFieldValue("img_width"))).floatValue();
148               float img_height=(new Float(currentImage.getFieldValue("img_height"))).floatValue();
149
150               //oversize images must be shrunk
151               if (img_width>250){
152                   img_height=(new Float((new Float(img_height*(250.0F/img_width))).intValue())).floatValue();
153                   img_width=250.0F;
154               }
155
156
157               //calculate how much text goes in the column(use 8 pixels to pad the column)
158               float text_widthCM = contentAreaWidthCM-((img_width+8)*pixelWidthCM);
159               float number_of_lines = img_height*pixelWidthCM/lineHeightCM; //don't worry we will make it an int
160               //add one line for image description
161               int text_amount= (new Float((text_widthCM/characterWidthCM)*(number_of_lines+1))).intValue();
162
163               row1.put("text_widthCM",Float.toString(text_widthCM));
164
165               row1.put("img_title",currentImage.getFieldValue("title"));
166
167               row1.put("img_width",Float.toString(img_width));
168               row1.put("img_height",Float.toString(img_height));
169
170               aLogger.debug("img_width " +Float.toString(img_width));
171               aLogger.debug("img_height "+Float.toString(img_height));
172
173               row1.put("img_src",currentImage.getFieldValue("publish_path"));
174               row1.put("hasImage","1");
175               if (! outOfText){
176                   try {
177                       int lastSpaceAt = theContent.lastIndexOf(" ",currentPosition+text_amount);
178                       row1.put("text",theContent.substring(currentPosition,lastSpaceAt));
179                       currentPosition=lastSpaceAt;
180                   }
181                   catch (IndexOutOfBoundsException e){
182                       row1.put("text",theContent.substring(currentPosition));
183                       outOfText = true;
184                           }
185               }
186               aLogger.debug("CP2 is "+ currentPosition);
187               brokenUpContent.add(row1);
188
189               if (! outOfText){
190                   try {
191                       int lastSpaceAt = theContent.lastIndexOf(" ",currentPosition+numCharsInAnImagelessRow);
192                       row2.put("text",theContent.substring(currentPosition,lastSpaceAt));
193                       currentPosition=lastSpaceAt;
194                   }
195                   catch (IndexOutOfBoundsException e){
196                       row2.put("text",theContent.substring(currentPosition));
197                       outOfText = true;
198                           }
199               }
200               row2.put("hasImage","0");
201               brokenUpContent.add(row2);
202
203               aLogger.debug("CP3 is "+ currentPosition);
204           }
205           Map row3 = new HashMap();
206           if (! outOfText){
207               row3.put("text",theContent.substring(currentPosition));
208               row3.put("hasImage","0");
209               brokenUpContent.add(row3);
210           }
211
212       }
213
214
215
216
217
218       ParameterExpander.setValueForKey(
219                                        aValueMap,
220                                        "data.formatted_content",
221                                        new CachingRewindableIterator(brokenUpContent.iterator())
222                                        );
223
224
225     }
226     catch (Throwable t) {
227       aLogger.error("Error while formatting content for PDF: " + t.getMessage());
228       t.printStackTrace(new PrintWriter(new LoggerToWriterAdapter(aLogger, LoggerWrapper.DEBUG_MESSAGE)));
229     }
230   }
231 }
232
233
234
235