1 /* DocumentParser.java -- A parser for HTML documents. 2 Copyright (C) 2005 Free Software Foundation, Inc. 3 4 This file is part of GNU Classpath. 5 6 GNU Classpath 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, or (at your option) 9 any later version. 10 11 GNU Classpath is distributed in the hope that it will be useful, but 12 WITHOUT ANY WARRANTY; without even the implied warranty of 13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 14 General Public License for more details. 15 16 You should have received a copy of the GNU General Public License 17 along with GNU Classpath; see the file COPYING. If not, write to the 18 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 19 02110-1301 USA. 20 21 Linking this library statically or dynamically with other modules is 22 making a combined work based on this library. Thus, the terms and 23 conditions of the GNU General Public License cover the whole 24 combination. 25 26 As a special exception, the copyright holders of this library give you 27 permission to link this library with independent modules to produce an 28 executable, regardless of the license terms of these independent 29 modules, and to copy and distribute the resulting executable under 30 terms of your choice, provided that you also meet, for each linked 31 independent module, the terms and conditions of the license of that 32 module. An independent module is a module which is not derived from 33 or based on this library. If you modify this library, you may extend 34 this exception to your version of the library, but you are not 35 obligated to do so. If you do not wish to do so, delete this 36 exception statement from your version. */ 37 38 39 package javax.swing.text.html.parser; 40 41 import gnu.javax.swing.text.html.parser.htmlAttributeSet; 42 import javax.swing.text.html.parser.Parser; 43 44 import java.io.IOException; 45 import java.io.Reader; 46 47 import javax.swing.text.BadLocationException; 48 import javax.swing.text.html.HTMLEditorKit; 49 50 /** 51 * <p>A simple error-tolerant HTML parser that uses a DTD document 52 * to access data on the possible tokens, arguments and syntax.</p> 53 * <p> The parser reads an HTML content from a Reader and calls various 54 * notifying methods (which should be overridden in a subclass) 55 * when tags or data are encountered.</p> 56 * <p>Some HTML elements need no opening or closing tags. The 57 * task of this parser is to invoke the tag handling methods also when 58 * the tags are not explicitly specified and must be supposed using 59 * information, stored in the DTD. 60 * For example, parsing the document 61 * <p><table><tr><td>a<td>b<td>c</tr> <br> 62 * will invoke exactly the handling methods exactly in the same order 63 * (and with the same parameters) as if parsing the document: <br> 64 * <em><html><head></head><body><table>< 65 * tbody></em><tr><td>a<em></td></em><td>b<em> 66 * </td></em><td>c<em></td></tr></em>< 67 * <em>/tbody></table></body></html></em></p> 68 * (supposed tags are given in italics). The parser also supports 69 * obsolete elements of HTML syntax.<p> 70 * </p> 71 * In this implementation, DocumentParser is directly derived from its 72 * ancestor without changes of functionality. 73 * @author Audrius Meskauskas, Lithuania (AudriusA@Bioinformatics.org) 74 */ 75 public class DocumentParser 76 extends Parser 77 implements DTDConstants 78 { 79 /** 80 * The enclosed working parser class. 81 */ 82 private class gnuParser 83 extends gnu.javax.swing.text.html.parser.support.Parser 84 { gnuParser(DTD d)85 private gnuParser(DTD d) 86 { 87 super(d); 88 } 89 handleComment(char[] comment)90 protected final void handleComment(char[] comment) 91 { 92 parser.handleComment(comment); 93 callBack.handleComment(comment, hTag.where.startPosition); 94 } 95 handleEmptyTag(TagElement tag)96 protected final void handleEmptyTag(TagElement tag) 97 throws javax.swing.text.ChangedCharSetException 98 { 99 parser.handleEmptyTag(tag); 100 callBack.handleSimpleTag(tag.getHTMLTag(), getAttributes(), 101 hTag.where.startPosition 102 ); 103 } 104 handleEndTag(TagElement tag)105 protected final void handleEndTag(TagElement tag) 106 { 107 parser.handleEndTag(tag); 108 callBack.handleEndTag(tag.getHTMLTag(), hTag.where.startPosition); 109 } 110 handleError(int line, String message)111 protected final void handleError(int line, String message) 112 { 113 parser.handleError(line, message); 114 callBack.handleError(message, hTag.where.startPosition); 115 } 116 handleStartTag(TagElement tag)117 protected final void handleStartTag(TagElement tag) 118 { 119 parser.handleStartTag(tag); 120 htmlAttributeSet attributes = gnu.getAttributes(); 121 122 if (tag.fictional()) 123 attributes.addAttribute(HTMLEditorKit.ParserCallback.IMPLIED, 124 Boolean.TRUE 125 ); 126 127 callBack.handleStartTag(tag.getHTMLTag(), attributes, 128 hTag.where.startPosition 129 ); 130 } 131 handleText(char[] text)132 protected final void handleText(char[] text) 133 { 134 parser.handleText(text); 135 callBack.handleText(text, hTag.where.startPosition); 136 } 137 getDTD()138 DTD getDTD() 139 { 140 return dtd; 141 } 142 } 143 144 /** 145 * This field is used to access the identically named 146 * methods of the outer class. 147 * This is package-private to avoid an accessor method. 148 */ 149 DocumentParser parser = this; 150 151 /** 152 * The callback. 153 * This is package-private to avoid an accessor method. 154 */ 155 HTMLEditorKit.ParserCallback callBack; 156 157 /** 158 * The reference to the working class of HTML parser that is 159 * actually used to parse the document. 160 * This is package-private to avoid an accessor method. 161 */ 162 gnuParser gnu; 163 164 /** 165 * Creates a new parser that uses the given DTD to access data on the 166 * possible tokens, arguments and syntax. There is no single - step way 167 * to get a default DTD; you must either refer to the implementation - 168 * specific packages, write your own DTD or obtain the working instance 169 * of parser in other way, for example, by calling 170 * {@link javax.swing.text.html.HTMLEditorKit#getParser()}. 171 * 172 * @param a_dtd a DTD to use. 173 */ DocumentParser(DTD a_dtd)174 public DocumentParser(DTD a_dtd) 175 { 176 super(a_dtd); 177 gnu = new gnuParser(a_dtd); 178 } 179 180 /** 181 * Parses the HTML document, calling methods of the provided 182 * callback. This method must be multithread - safe. 183 * @param reader The reader to read the HTML document from 184 * @param aCallback The callback that is notifyed about the presence 185 * of HTML elements in the document. 186 * @param ignoreCharSet If thrue, any charset changes during parsing 187 * are ignored. 188 * @throws java.io.IOException 189 */ parse(Reader reader, HTMLEditorKit.ParserCallback aCallback, boolean ignoreCharSet )190 public void parse(Reader reader, HTMLEditorKit.ParserCallback aCallback, 191 boolean ignoreCharSet 192 ) 193 throws IOException 194 { 195 callBack = aCallback; 196 gnu.parse(reader); 197 198 callBack.handleEndOfLineString(gnu.getEndOfLineSequence()); 199 try 200 { 201 callBack.flush(); 202 } 203 catch (BadLocationException ex) 204 { 205 // Convert this into the supported type of exception. 206 throw new IOException(ex.getMessage()); 207 } 208 } 209 210 /** 211 * Handle HTML comment. The default method returns without action. 212 * @param comment the comment being handled 213 */ handleComment(char[] comment)214 protected void handleComment(char[] comment) 215 { 216 // This default implementation does nothing. 217 } 218 219 /** 220 * Handle the tag with no content, like <br>. The method is 221 * called for the elements that, in accordance with the current DTD, 222 * has an empty content. 223 * @param tag the tag being handled. 224 * @throws javax.swing.text.ChangedCharSetException 225 */ handleEmptyTag(TagElement tag)226 protected void handleEmptyTag(TagElement tag) 227 throws javax.swing.text.ChangedCharSetException 228 { 229 // This default implementation does nothing. 230 } 231 232 /** 233 * The method is called when the HTML closing tag ((like </table>) 234 * is found or if the parser concludes that the one should be present 235 * in the current position. 236 * @param tag The tag being handled 237 */ handleEndTag(TagElement tag)238 protected void handleEndTag(TagElement tag) 239 { 240 // This default implementation does nothing. 241 } 242 243 /* Handle error that has occured in the given line. */ handleError(int line, String message)244 protected void handleError(int line, String message) 245 { 246 // This default implementation does nothing. 247 } 248 249 /** 250 * The method is called when the HTML opening tag ((like <table>) 251 * is found or if the parser concludes that the one should be present 252 * in the current position. 253 * @param tag The tag being handled 254 */ handleStartTag(TagElement tag)255 protected void handleStartTag(TagElement tag) 256 { 257 // This default implementation does nothing. 258 } 259 260 /** 261 * Handle the text section. 262 * @param text a section text. 263 */ handleText(char[] text)264 protected void handleText(char[] text) 265 { 266 // This default implementation does nothing. 267 } 268 } 269