1 /*
2 * Copyright (c) 1998, 2018, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package javax.swing.text.html.parser;
27
28 import javax.swing.text.SimpleAttributeSet;
29 import javax.swing.text.html.HTMLEditorKit;
30 import javax.swing.text.html.HTML;
31 import javax.swing.text.ChangedCharSetException;
32
33 import java.util.*;
34 import java.io.*;
35 import java.net.*;
36
37 /**
38 * A Parser for HTML Documents (actually, you can specify a DTD, but
39 * you should really only use this class with the html dtd in swing).
40 * Reads an InputStream of HTML and
41 * invokes the appropriate methods in the ParserCallback class. This
42 * is the default parser used by HTMLEditorKit to parse HTML url's.
43 * <p>This will message the callback for all valid tags, as well as
44 * tags that are implied but not explicitly specified. For example, the
45 * html string (<p>blah) only has a p tag defined. The callback
46 * will see the following methods:
47 * <ol><li><i>handleStartTag(html, ...)</i></li>
48 * <li><i>handleStartTag(head, ...)</i></li>
49 * <li><i>handleEndTag(head)</i></li>
50 * <li><i>handleStartTag(body, ...)</i></li>
51 * <li><i>handleStartTag(p, ...)</i></li>
52 * <li><i>handleText(...)</i></li>
53 * <li><i>handleEndTag(p)</i></li>
54 * <li><i>handleEndTag(body)</i></li>
55 * <li><i>handleEndTag(html)</i></li>
56 * </ol>
57 * The items in <i>italic</i> are implied, that is, although they were not
58 * explicitly specified, to be correct html they should have been present
59 * (head isn't necessary, but it is still generated). For tags that
60 * are implied, the AttributeSet argument will have a value of
61 * <code>Boolean.TRUE</code> for the key
62 * <code>HTMLEditorKit.ParserCallback.IMPLIED</code>.
63 * <p>HTML.Attributes defines a type safe enumeration of html attributes.
64 * If an attribute key of a tag is defined in HTML.Attribute, the
65 * HTML.Attribute will be used as the key, otherwise a String will be used.
66 * For example <p foo=bar class=neat> has two attributes. foo is
67 * not defined in HTML.Attribute, where as class is, therefore the
68 * AttributeSet will have two values in it, HTML.Attribute.CLASS with
69 * a String value of 'neat' and the String key 'foo' with a String value of
70 * 'bar'.
71 * <p>The position argument will indicate the start of the tag, comment
72 * or text. Similar to arrays, the first character in the stream has a
73 * position of 0. For tags that are
74 * implied the position will indicate
75 * the location of the next encountered tag. In the first example,
76 * the implied start body and html tags will have the same position as the
77 * p tag, and the implied end p, html and body tags will all have the same
78 * position.
79 * <p>As html skips whitespace the position for text will be the position
80 * of the first valid character, eg in the string '\n\n\nblah'
81 * the text 'blah' will have a position of 3, the newlines are skipped.
82 * <p>
83 * For attributes that do not have a value, eg in the html
84 * string <code><foo blah></code> the attribute <code>blah</code>
85 * does not have a value, there are two possible values that will be
86 * placed in the AttributeSet's value:
87 * <ul>
88 * <li>If the DTD does not contain an definition for the element, or the
89 * definition does not have an explicit value then the value in the
90 * AttributeSet will be <code>HTML.NULL_ATTRIBUTE_VALUE</code>.
91 * <li>If the DTD contains an explicit value, as in:
92 * <code><!ATTLIST OPTION selected (selected) #IMPLIED></code>
93 * this value from the dtd (in this case selected) will be used.
94 * </ul>
95 * <p>
96 * Once the stream has been parsed, the callback is notified of the most
97 * likely end of line string. The end of line string will be one of
98 * \n, \r or \r\n, which ever is encountered the most in parsing the
99 * stream.
100 *
101 * @author Sunita Mani
102 */
103 public class DocumentParser extends javax.swing.text.html.parser.Parser {
104
105 private int inbody;
106 private int intitle;
107 private int inhead;
108 private int instyle;
109 private int inscript;
110 private boolean seentitle;
111 private HTMLEditorKit.ParserCallback callback = null;
112 private boolean ignoreCharSet = false;
113 private static final boolean debugFlag = false;
114
115 /**
116 * Creates document parser with the specified {@code dtd}.
117 *
118 * @param dtd the dtd.
119 */
120 public DocumentParser(DTD dtd) {
121 super(dtd);
122 }
123
124 /**
125 * Parse an HTML stream, given a DTD.
126 *
127 * @param in the reader to read the source from
128 * @param callback the callback
129 * @param ignoreCharSet if {@code true} the charset is ignored
130 * @throws IOException if an I/O error occurs
131 */
132 public void parse(Reader in, HTMLEditorKit.ParserCallback callback, boolean ignoreCharSet) throws IOException {
133 this.ignoreCharSet = ignoreCharSet;
134 this.callback = callback;
135 parse(in);
136 // end of line
137 callback.handleEndOfLineString(getEndOfLineString());
138 }
139
140 /**
141 * Handle Start Tag.
142 */
143 protected void handleStartTag(TagElement tag) {
144
145 Element elem = tag.getElement();
146 if (elem == dtd.body) {
147 inbody++;
148 } else if (elem == dtd.html) {
149 } else if (elem == dtd.head) {
150 inhead++;
151 } else if (elem == dtd.title) {
152 intitle++;
153 } else if (elem == dtd.style) {
154 instyle++;
155 } else if (elem == dtd.script) {
156 inscript++;
157 }
158 if (debugFlag) {
159 if (tag.fictional()) {
160 debug("Start Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
161 } else {
162 debug("Start Tag: " + tag.getHTMLTag() + " attributes: " +
163 getAttributes() + " pos: " + getCurrentPos());
164 }
165 }
166 if (tag.fictional()) {
167 SimpleAttributeSet attrs = new SimpleAttributeSet();
168 attrs.addAttribute(HTMLEditorKit.ParserCallback.IMPLIED,
169 Boolean.TRUE);
170 callback.handleStartTag(tag.getHTMLTag(), attrs,
171 getBlockStartPosition());
172 } else {
173 callback.handleStartTag(tag.getHTMLTag(), getAttributes(),
174 getBlockStartPosition());
175 flushAttributes();
176 }
177 }
178
179
180 protected void handleComment(char[] text) {
181 if (debugFlag) {
182 debug("comment: ->" + new String(text) + "<-"
183 + " pos: " + getCurrentPos());
184 }
185 callback.handleComment(text, getBlockStartPosition());
186 }
187
188 /**
189 * Handle Empty Tag.
190 */
191 protected void handleEmptyTag(TagElement tag) throws ChangedCharSetException {
192
193 Element elem = tag.getElement();
194 if (elem == dtd.meta && !ignoreCharSet) {
195 SimpleAttributeSet atts = getAttributes();
196 if (atts != null) {
197 String content = (String)atts.getAttribute(HTML.Attribute.CONTENT);
198 if (content != null) {
199 if ("content-type".equalsIgnoreCase((String)atts.getAttribute(HTML.Attribute.HTTPEQUIV))) {
200 if (!content.equalsIgnoreCase("text/html") &&
201 !content.equalsIgnoreCase("text/plain")) {
202 throw new ChangedCharSetException(content, false);
203 }
204 } else if ("charset" .equalsIgnoreCase((String)atts.getAttribute(HTML.Attribute.HTTPEQUIV))) {
205 throw new ChangedCharSetException(content, true);
206 }
207 }
208 }
209 }
210 if (inbody != 0 || elem == dtd.meta || elem == dtd.base || elem == dtd.isindex || elem == dtd.style || elem == dtd.link) {
211 if (debugFlag) {
212 if (tag.fictional()) {
213 debug("Empty Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
214 } else {
215 debug("Empty Tag: " + tag.getHTMLTag() + " attributes: "
216 + getAttributes() + " pos: " + getCurrentPos());
217 }
218 }
219 if (tag.fictional()) {
220 SimpleAttributeSet attrs = new SimpleAttributeSet();
221 attrs.addAttribute(HTMLEditorKit.ParserCallback.IMPLIED,
222 Boolean.TRUE);
223 callback.handleSimpleTag(tag.getHTMLTag(), attrs,
224 getBlockStartPosition());
225 } else {
226 callback.handleSimpleTag(tag.getHTMLTag(), getAttributes(),
227 getBlockStartPosition());
228 flushAttributes();
229 }
230 }
231 }
232
233 /**
234 * Handle End Tag.
235 */
236 protected void handleEndTag(TagElement tag) {
237 Element elem = tag.getElement();
238 if (elem == dtd.body) {
239 inbody--;
240 } else if (elem == dtd.title) {
241 intitle--;
242 seentitle = true;
243 } else if (elem == dtd.head) {
244 inhead--;
245 } else if (elem == dtd.style) {
246 instyle--;
247 } else if (elem == dtd.script) {
248 inscript--;
249 }
250 if (debugFlag) {
251 debug("End Tag: " + tag.getHTMLTag() + " pos: " + getCurrentPos());
252 }
253 callback.handleEndTag(tag.getHTMLTag(), getBlockStartPosition());
254
255 }
256
257 /**
258 * Handle Text.
259 */
260 protected void handleText(char[] data) {
261 if (data != null) {
262 if (inscript != 0) {
263 callback.handleComment(data, getBlockStartPosition());
264 return;
265 }
266 if (inbody != 0 || ((instyle != 0) ||
267 ((intitle != 0) && !seentitle))) {
268 if (debugFlag) {
269 debug("text: ->" + new String(data) + "<-" + " pos: " + getCurrentPos());
270 }
271 callback.handleText(data, getBlockStartPosition());
272 }
273 }
274 }
275
276 /*
277 * Error handling.
278 */
279 protected void handleError(int ln, String errorMsg) {
280 if (debugFlag) {
281 debug("Error: ->" + errorMsg + "<-" + " pos: " + getCurrentPos());
282 }
283 /* PENDING: need to improve the error string. */
284 callback.handleError(errorMsg, getCurrentPos());
285 }
286
287
288 /*
289 * debug messages
290 */
291 private void debug(String msg) {
292 System.out.println(msg);
293 }
294 }