|
0
|
1 /*--
|
|
|
2
|
|
|
3 $Id: SAXHandler.java,v 1.73 2007/11/10 05:29:00 jhunter Exp $
|
|
|
4
|
|
|
5 Copyright (C) 2000-2007 Jason Hunter & Brett McLaughlin.
|
|
|
6 All rights reserved.
|
|
|
7
|
|
|
8 Redistribution and use in source and binary forms, with or without
|
|
|
9 modification, are permitted provided that the following conditions
|
|
|
10 are met:
|
|
|
11
|
|
|
12 1. Redistributions of source code must retain the above copyright
|
|
|
13 notice, this list of conditions, and the following disclaimer.
|
|
|
14
|
|
|
15 2. Redistributions in binary form must reproduce the above copyright
|
|
|
16 notice, this list of conditions, and the disclaimer that follows
|
|
|
17 these conditions in the documentation and/or other materials
|
|
|
18 provided with the distribution.
|
|
|
19
|
|
|
20 3. The name "JDOM" must not be used to endorse or promote products
|
|
|
21 derived from this software without prior written permission. For
|
|
|
22 written permission, please contact <request_AT_jdom_DOT_org>.
|
|
|
23
|
|
|
24 4. Products derived from this software may not be called "JDOM", nor
|
|
|
25 may "JDOM" appear in their name, without prior written permission
|
|
|
26 from the JDOM Project Management <request_AT_jdom_DOT_org>.
|
|
|
27
|
|
|
28 In addition, we request (but do not require) that you include in the
|
|
|
29 end-user documentation provided with the redistribution and/or in the
|
|
|
30 software itself an acknowledgement equivalent to the following:
|
|
|
31 "This product includes software developed by the
|
|
|
32 JDOM Project (http://www.jdom.org/)."
|
|
|
33 Alternatively, the acknowledgment may be graphical using the logos
|
|
|
34 available at http://www.jdom.org/images/logos.
|
|
|
35
|
|
|
36 THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
|
|
|
37 WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
|
|
38 OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
|
39 DISCLAIMED. IN NO EVENT SHALL THE JDOM AUTHORS OR THE PROJECT
|
|
|
40 CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
|
41 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
|
42 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
|
|
|
43 USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
|
|
44 ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
|
45 OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
|
|
|
46 OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
|
47 SUCH DAMAGE.
|
|
|
48
|
|
|
49 This software consists of voluntary contributions made by many
|
|
|
50 individuals on behalf of the JDOM Project and was originally
|
|
|
51 created by Jason Hunter <jhunter_AT_jdom_DOT_org> and
|
|
|
52 Brett McLaughlin <brett_AT_jdom_DOT_org>. For more information
|
|
|
53 on the JDOM Project, please see <http://www.jdom.org/>.
|
|
|
54
|
|
|
55 */
|
|
|
56
|
|
|
57 package org.jdom.input;
|
|
|
58
|
|
|
59 import java.util.*;
|
|
|
60
|
|
|
61 import org.jdom.*;
|
|
|
62 import org.xml.sax.*;
|
|
|
63 import org.xml.sax.ext.*;
|
|
|
64 import org.xml.sax.helpers.*;
|
|
|
65
|
|
|
66 /**
|
|
|
67 * A support class for {@link SAXBuilder}.
|
|
|
68 *
|
|
|
69 * @version $Revision: 1.73 $, $Date: 2007/11/10 05:29:00 $
|
|
|
70 * @author Brett McLaughlin
|
|
|
71 * @author Jason Hunter
|
|
|
72 * @author Philip Nelson
|
|
|
73 * @author Bradley S. Huffman
|
|
|
74 * @author phil@triloggroup.com
|
|
|
75 */
|
|
|
76 public class SAXHandler extends DefaultHandler implements LexicalHandler,
|
|
|
77 DeclHandler,
|
|
|
78 DTDHandler {
|
|
|
79
|
|
|
80 private static final String CVS_ID =
|
|
|
81 "@(#) $RCSfile: SAXHandler.java,v $ $Revision: 1.73 $ $Date: 2007/11/10 05:29:00 $ $Name: jdom_1_1_1 $";
|
|
|
82
|
|
|
83 /** Hash table to map SAX attribute type names to JDOM attribute types. */
|
|
|
84 private static final Map attrNameToTypeMap = new HashMap(13);
|
|
|
85
|
|
|
86 /** <code>Document</code> object being built */
|
|
|
87 private Document document;
|
|
|
88
|
|
|
89 /** <code>Element</code> object being built */
|
|
|
90 private Element currentElement;
|
|
|
91
|
|
|
92 /** Indicator of where in the document we are */
|
|
|
93 private boolean atRoot;
|
|
|
94
|
|
|
95 /** Indicator of whether we are in the DocType. Note that the DTD consists
|
|
|
96 * of both the internal subset (inside the <!DOCTYPE> tag) and the
|
|
|
97 * external subset (in a separate .dtd file). */
|
|
|
98 private boolean inDTD = false;
|
|
|
99
|
|
|
100 /** Indicator of whether we are in the internal subset */
|
|
|
101 private boolean inInternalSubset = false;
|
|
|
102
|
|
|
103 /** Indicator of whether we previously were in a CDATA */
|
|
|
104 private boolean previousCDATA = false;
|
|
|
105
|
|
|
106 /** Indicator of whether we are in a CDATA */
|
|
|
107 private boolean inCDATA = false;
|
|
|
108
|
|
|
109 /** Indicator of whether we should expand entities */
|
|
|
110 private boolean expand = true;
|
|
|
111
|
|
|
112 /** Indicator of whether we are actively suppressing (non-expanding) a
|
|
|
113 current entity */
|
|
|
114 private boolean suppress = false;
|
|
|
115
|
|
|
116 /** How many nested entities we're currently within */
|
|
|
117 private int entityDepth = 0; // XXX may not be necessary anymore?
|
|
|
118
|
|
|
119 /** Temporary holder for namespaces that have been declared with
|
|
|
120 * startPrefixMapping, but are not yet available on the element */
|
|
|
121 private List declaredNamespaces;
|
|
|
122
|
|
|
123 /** Temporary holder for the internal subset */
|
|
|
124 private StringBuffer internalSubset = new StringBuffer();
|
|
|
125
|
|
|
126 /** Temporary holder for Text and CDATA */
|
|
|
127 private TextBuffer textBuffer = new TextBuffer();
|
|
|
128
|
|
|
129 /** The external entities defined in this document */
|
|
|
130 private Map externalEntities;
|
|
|
131
|
|
|
132 /** The JDOMFactory used for JDOM object creation */
|
|
|
133 private JDOMFactory factory;
|
|
|
134
|
|
|
135 /** Whether to ignore ignorable whitespace */
|
|
|
136 private boolean ignoringWhite = false;
|
|
|
137
|
|
|
138 /** Whether to ignore text containing all whitespace */
|
|
|
139 private boolean ignoringBoundaryWhite = false;
|
|
|
140
|
|
|
141 /** The SAX Locator object provided by the parser */
|
|
|
142 private Locator locator;
|
|
|
143
|
|
|
144 /**
|
|
|
145 * Class initializer: Populate a table to translate SAX attribute
|
|
|
146 * type names into JDOM attribute type value (integer).
|
|
|
147 * <p>
|
|
|
148 * <b>Note that all the mappings defined below are compliant with
|
|
|
149 * the SAX 2.0 specification exception for "ENUMERATION" with is
|
|
|
150 * specific to Crimson 1.1.X and Xerces 2.0.0-betaX which report
|
|
|
151 * attributes of enumerated types with a type "ENUMERATION"
|
|
|
152 * instead of the expected "NMTOKEN".
|
|
|
153 * </p>
|
|
|
154 * <p>
|
|
|
155 * Note also that Xerces 1.4.X is not SAX 2.0 compliant either
|
|
|
156 * but handling its case requires
|
|
|
157 * {@link #getAttributeType specific code}.
|
|
|
158 * </p>
|
|
|
159 */
|
|
|
160 static {
|
|
|
161 attrNameToTypeMap.put("CDATA",
|
|
|
162 new Integer(Attribute.CDATA_TYPE));
|
|
|
163 attrNameToTypeMap.put("ID",
|
|
|
164 new Integer(Attribute.ID_TYPE));
|
|
|
165 attrNameToTypeMap.put("IDREF",
|
|
|
166 new Integer(Attribute.IDREF_TYPE));
|
|
|
167 attrNameToTypeMap.put("IDREFS",
|
|
|
168 new Integer(Attribute.IDREFS_TYPE));
|
|
|
169 attrNameToTypeMap.put("ENTITY",
|
|
|
170 new Integer(Attribute.ENTITY_TYPE));
|
|
|
171 attrNameToTypeMap.put("ENTITIES",
|
|
|
172 new Integer(Attribute.ENTITIES_TYPE));
|
|
|
173 attrNameToTypeMap.put("NMTOKEN",
|
|
|
174 new Integer(Attribute.NMTOKEN_TYPE));
|
|
|
175 attrNameToTypeMap.put("NMTOKENS",
|
|
|
176 new Integer(Attribute.NMTOKENS_TYPE));
|
|
|
177 attrNameToTypeMap.put("NOTATION",
|
|
|
178 new Integer(Attribute.NOTATION_TYPE));
|
|
|
179 attrNameToTypeMap.put("ENUMERATION",
|
|
|
180 new Integer(Attribute.ENUMERATED_TYPE));
|
|
|
181 }
|
|
|
182
|
|
|
183 /**
|
|
|
184 * This will create a new <code>SAXHandler</code> that listens to SAX
|
|
|
185 * events and creates a JDOM Document. The objects will be constructed
|
|
|
186 * using the default factory.
|
|
|
187 */
|
|
|
188 public SAXHandler() {
|
|
|
189 this(null);
|
|
|
190 }
|
|
|
191
|
|
|
192 /**
|
|
|
193 * This will create a new <code>SAXHandler</code> that listens to SAX
|
|
|
194 * events and creates a JDOM Document. The objects will be constructed
|
|
|
195 * using the provided factory.
|
|
|
196 *
|
|
|
197 * @param factory <code>JDOMFactory</code> to be used for constructing
|
|
|
198 * objects
|
|
|
199 */
|
|
|
200 public SAXHandler(JDOMFactory factory) {
|
|
|
201 if (factory != null) {
|
|
|
202 this.factory = factory;
|
|
|
203 } else {
|
|
|
204 this.factory = new DefaultJDOMFactory();
|
|
|
205 }
|
|
|
206
|
|
|
207 atRoot = true;
|
|
|
208 declaredNamespaces = new ArrayList();
|
|
|
209 externalEntities = new HashMap();
|
|
|
210
|
|
|
211 document = this.factory.document(null);
|
|
|
212 }
|
|
|
213
|
|
|
214 /**
|
|
|
215 * Pushes an element onto the tree under construction. Allows subclasses
|
|
|
216 * to put content under a dummy root element which is useful for building
|
|
|
217 * content that would otherwise be a non-well formed document.
|
|
|
218 *
|
|
|
219 * @param element root element under which content will be built
|
|
|
220 */
|
|
|
221 protected void pushElement(Element element) {
|
|
|
222 if (atRoot) {
|
|
|
223 document.setRootElement(element); // XXX should we use a factory call?
|
|
|
224 atRoot = false;
|
|
|
225 }
|
|
|
226 else {
|
|
|
227 factory.addContent(currentElement, element);
|
|
|
228 }
|
|
|
229 currentElement = element;
|
|
|
230 }
|
|
|
231
|
|
|
232 /**
|
|
|
233 * Returns the document. Should be called after parsing is complete.
|
|
|
234 *
|
|
|
235 * @return <code>Document</code> - Document that was built
|
|
|
236 */
|
|
|
237 public Document getDocument() {
|
|
|
238 return document;
|
|
|
239 }
|
|
|
240
|
|
|
241 /**
|
|
|
242 * Returns the factory used for constructing objects.
|
|
|
243 *
|
|
|
244 * @return <code>JDOMFactory</code> - the factory used for
|
|
|
245 * constructing objects.
|
|
|
246 *
|
|
|
247 * @see #SAXHandler(org.jdom.JDOMFactory)
|
|
|
248 */
|
|
|
249 public JDOMFactory getFactory() {
|
|
|
250 return factory;
|
|
|
251 }
|
|
|
252
|
|
|
253 /**
|
|
|
254 * This sets whether or not to expand entities during the build.
|
|
|
255 * A true means to expand entities as normal content. A false means to
|
|
|
256 * leave entities unexpanded as <code>EntityRef</code> objects. The
|
|
|
257 * default is true.
|
|
|
258 *
|
|
|
259 * @param expand <code>boolean</code> indicating whether entity expansion
|
|
|
260 * should occur.
|
|
|
261 */
|
|
|
262 public void setExpandEntities(boolean expand) {
|
|
|
263 this.expand = expand;
|
|
|
264 }
|
|
|
265
|
|
|
266 /**
|
|
|
267 * Returns whether or not entities will be expanded during the
|
|
|
268 * build.
|
|
|
269 *
|
|
|
270 * @return <code>boolean</code> - whether entity expansion
|
|
|
271 * will occur during build.
|
|
|
272 *
|
|
|
273 * @see #setExpandEntities
|
|
|
274 */
|
|
|
275 public boolean getExpandEntities() {
|
|
|
276 return expand;
|
|
|
277 }
|
|
|
278
|
|
|
279 /**
|
|
|
280 * Specifies whether or not the parser should elminate whitespace in
|
|
|
281 * element content (sometimes known as "ignorable whitespace") when
|
|
|
282 * building the document. Only whitespace which is contained within
|
|
|
283 * element content that has an element only content model will be
|
|
|
284 * eliminated (see XML Rec 3.2.1). For this setting to take effect
|
|
|
285 * requires that validation be turned on. The default value of this
|
|
|
286 * setting is <code>false</code>.
|
|
|
287 *
|
|
|
288 * @param ignoringWhite Whether to ignore ignorable whitespace
|
|
|
289 */
|
|
|
290 public void setIgnoringElementContentWhitespace(boolean ignoringWhite) {
|
|
|
291 this.ignoringWhite = ignoringWhite;
|
|
|
292 }
|
|
|
293
|
|
|
294 /**
|
|
|
295 * Specifies whether or not the parser should elminate text() nodes
|
|
|
296 * containing only whitespace when building the document. See
|
|
|
297 * {@link SAXBuilder#setIgnoringBoundaryWhitespace(boolean)}.
|
|
|
298 *
|
|
|
299 * @param ignoringBoundaryWhite Whether to ignore only whitespace content
|
|
|
300 */
|
|
|
301 public void setIgnoringBoundaryWhitespace(boolean ignoringBoundaryWhite) {
|
|
|
302 this.ignoringBoundaryWhite = ignoringBoundaryWhite;
|
|
|
303 }
|
|
|
304
|
|
|
305 /**
|
|
|
306 * Returns whether or not the parser will elminate element content
|
|
|
307 * containing only whitespace.
|
|
|
308 *
|
|
|
309 * @return <code>boolean</code> - whether only whitespace content will
|
|
|
310 * be ignored during build.
|
|
|
311 *
|
|
|
312 * @see #setIgnoringBoundaryWhitespace
|
|
|
313 */
|
|
|
314 public boolean getIgnoringBoundaryWhitespace() {
|
|
|
315 return ignoringBoundaryWhite;
|
|
|
316 }
|
|
|
317
|
|
|
318 /**
|
|
|
319 * Returns whether or not the parser will elminate whitespace in
|
|
|
320 * element content (sometimes known as "ignorable whitespace") when
|
|
|
321 * building the document.
|
|
|
322 *
|
|
|
323 * @return <code>boolean</code> - whether ignorable whitespace will
|
|
|
324 * be ignored during build.
|
|
|
325 *
|
|
|
326 * @see #setIgnoringElementContentWhitespace
|
|
|
327 */
|
|
|
328 public boolean getIgnoringElementContentWhitespace() {
|
|
|
329 return ignoringWhite;
|
|
|
330 }
|
|
|
331
|
|
|
332 public void startDocument() {
|
|
|
333 if (locator != null) {
|
|
|
334 document.setBaseURI(locator.getSystemId());
|
|
|
335 }
|
|
|
336 }
|
|
|
337
|
|
|
338 /**
|
|
|
339 * This is called when the parser encounters an external entity
|
|
|
340 * declaration.
|
|
|
341 *
|
|
|
342 * @param name entity name
|
|
|
343 * @param publicID public id
|
|
|
344 * @param systemID system id
|
|
|
345 * @throws SAXException when things go wrong
|
|
|
346 */
|
|
|
347 public void externalEntityDecl(String name,
|
|
|
348 String publicID, String systemID)
|
|
|
349 throws SAXException {
|
|
|
350 // Store the public and system ids for the name
|
|
|
351 externalEntities.put(name, new String[]{publicID, systemID});
|
|
|
352
|
|
|
353 if (!inInternalSubset) return;
|
|
|
354
|
|
|
355 internalSubset.append(" <!ENTITY ")
|
|
|
356 .append(name);
|
|
|
357 appendExternalId(publicID, systemID);
|
|
|
358 internalSubset.append(">\n");
|
|
|
359 }
|
|
|
360
|
|
|
361 /**
|
|
|
362 * This handles an attribute declaration in the internal subset.
|
|
|
363 *
|
|
|
364 * @param eName <code>String</code> element name of attribute
|
|
|
365 * @param aName <code>String</code> attribute name
|
|
|
366 * @param type <code>String</code> attribute type
|
|
|
367 * @param valueDefault <code>String</code> default value of attribute
|
|
|
368 * @param value <code>String</code> value of attribute
|
|
|
369 * @throws SAXException
|
|
|
370 */
|
|
|
371 public void attributeDecl(String eName, String aName, String type,
|
|
|
372 String valueDefault, String value)
|
|
|
373 throws SAXException {
|
|
|
374
|
|
|
375 if (!inInternalSubset) return;
|
|
|
376
|
|
|
377 internalSubset.append(" <!ATTLIST ")
|
|
|
378 .append(eName)
|
|
|
379 .append(' ')
|
|
|
380 .append(aName)
|
|
|
381 .append(' ')
|
|
|
382 .append(type)
|
|
|
383 .append(' ');
|
|
|
384 if (valueDefault != null) {
|
|
|
385 internalSubset.append(valueDefault);
|
|
|
386 } else {
|
|
|
387 internalSubset.append('\"')
|
|
|
388 .append(value)
|
|
|
389 .append('\"');
|
|
|
390 }
|
|
|
391 if ((valueDefault != null) && (valueDefault.equals("#FIXED"))) {
|
|
|
392 internalSubset.append(" \"")
|
|
|
393 .append(value)
|
|
|
394 .append('\"');
|
|
|
395 }
|
|
|
396 internalSubset.append(">\n");
|
|
|
397 }
|
|
|
398
|
|
|
399 /**
|
|
|
400 * Handle an element declaration in a DTD.
|
|
|
401 *
|
|
|
402 * @param name <code>String</code> name of element
|
|
|
403 * @param model <code>String</code> model of the element in DTD syntax
|
|
|
404 * @throws SAXException
|
|
|
405 */
|
|
|
406 public void elementDecl(String name, String model) throws SAXException {
|
|
|
407 // Skip elements that come from the external subset
|
|
|
408 if (!inInternalSubset) return;
|
|
|
409
|
|
|
410 internalSubset.append(" <!ELEMENT ")
|
|
|
411 .append(name)
|
|
|
412 .append(' ')
|
|
|
413 .append(model)
|
|
|
414 .append(">\n");
|
|
|
415 }
|
|
|
416
|
|
|
417 /**
|
|
|
418 * Handle an internal entity declaration in a DTD.
|
|
|
419 *
|
|
|
420 * @param name <code>String</code> name of entity
|
|
|
421 * @param value <code>String</code> value of the entity
|
|
|
422 * @throws SAXException
|
|
|
423 */
|
|
|
424 public void internalEntityDecl(String name, String value)
|
|
|
425 throws SAXException {
|
|
|
426
|
|
|
427 // Skip entities that come from the external subset
|
|
|
428 if (!inInternalSubset) return;
|
|
|
429
|
|
|
430 internalSubset.append(" <!ENTITY ");
|
|
|
431 if (name.startsWith("%")) {
|
|
|
432 internalSubset.append("% ").append(name.substring(1));
|
|
|
433 } else {
|
|
|
434 internalSubset.append(name);
|
|
|
435 }
|
|
|
436 internalSubset.append(" \"")
|
|
|
437 .append(value)
|
|
|
438 .append("\">\n");
|
|
|
439 }
|
|
|
440
|
|
|
441 /**
|
|
|
442 * This will indicate that a processing instruction has been encountered.
|
|
|
443 * (The XML declaration is not a processing instruction and will not
|
|
|
444 * be reported.)
|
|
|
445 *
|
|
|
446 * @param target <code>String</code> target of PI
|
|
|
447 * @param data <code>String</code> containing all data sent to the PI.
|
|
|
448 * This typically looks like one or more attribute value
|
|
|
449 * pairs.
|
|
|
450 * @throws SAXException when things go wrong
|
|
|
451 */
|
|
|
452 public void processingInstruction(String target, String data)
|
|
|
453 throws SAXException {
|
|
|
454
|
|
|
455 if (suppress) return;
|
|
|
456
|
|
|
457 flushCharacters();
|
|
|
458
|
|
|
459 if (atRoot) {
|
|
|
460 factory.addContent(document, factory.processingInstruction(target, data));
|
|
|
461 } else {
|
|
|
462 factory.addContent(getCurrentElement(),
|
|
|
463 factory.processingInstruction(target, data));
|
|
|
464 }
|
|
|
465 }
|
|
|
466
|
|
|
467 /**
|
|
|
468 * This indicates that an unresolvable entity reference has been
|
|
|
469 * encountered, normally because the external DTD subset has not been
|
|
|
470 * read.
|
|
|
471 *
|
|
|
472 * @param name <code>String</code> name of entity
|
|
|
473 * @throws SAXException when things go wrong
|
|
|
474 */
|
|
|
475 public void skippedEntity(String name)
|
|
|
476 throws SAXException {
|
|
|
477
|
|
|
478 // We don't handle parameter entity references.
|
|
|
479 if (name.startsWith("%")) return;
|
|
|
480
|
|
|
481 flushCharacters();
|
|
|
482
|
|
|
483 factory.addContent(getCurrentElement(), factory.entityRef(name));
|
|
|
484 }
|
|
|
485
|
|
|
486 /**
|
|
|
487 * This will add the prefix mapping to the JDOM
|
|
|
488 * <code>Document</code> object.
|
|
|
489 *
|
|
|
490 * @param prefix <code>String</code> namespace prefix.
|
|
|
491 * @param uri <code>String</code> namespace URI.
|
|
|
492 */
|
|
|
493 public void startPrefixMapping(String prefix, String uri)
|
|
|
494 throws SAXException {
|
|
|
495
|
|
|
496 if (suppress) return;
|
|
|
497
|
|
|
498 Namespace ns = Namespace.getNamespace(prefix, uri);
|
|
|
499 declaredNamespaces.add(ns);
|
|
|
500 }
|
|
|
501
|
|
|
502 /**
|
|
|
503 * This reports the occurrence of an actual element. It will include
|
|
|
504 * the element's attributes, with the exception of XML vocabulary
|
|
|
505 * specific attributes, such as
|
|
|
506 * <code>xmlns:[namespace prefix]</code> and
|
|
|
507 * <code>xsi:schemaLocation</code>.
|
|
|
508 *
|
|
|
509 * @param namespaceURI <code>String</code> namespace URI this element
|
|
|
510 * is associated with, or an empty
|
|
|
511 * <code>String</code>
|
|
|
512 * @param localName <code>String</code> name of element (with no
|
|
|
513 * namespace prefix, if one is present)
|
|
|
514 * @param qName <code>String</code> XML 1.0 version of element name:
|
|
|
515 * [namespace prefix]:[localName]
|
|
|
516 * @param atts <code>Attributes</code> list for this element
|
|
|
517 * @throws SAXException when things go wrong
|
|
|
518 */
|
|
|
519 public void startElement(String namespaceURI, String localName,
|
|
|
520 String qName, Attributes atts)
|
|
|
521 throws SAXException {
|
|
|
522 if (suppress) return;
|
|
|
523
|
|
|
524 Element element = null;
|
|
|
525
|
|
|
526 if ((namespaceURI != null) && (!namespaceURI.equals(""))) {
|
|
|
527 String prefix = "";
|
|
|
528
|
|
|
529 // Determine any prefix on the Element
|
|
|
530 if (!qName.equals(localName)) {
|
|
|
531 int split = qName.indexOf(":");
|
|
|
532 prefix = qName.substring(0, split);
|
|
|
533 }
|
|
|
534 Namespace elementNamespace =
|
|
|
535 Namespace.getNamespace(prefix, namespaceURI);
|
|
|
536 element = factory.element(localName, elementNamespace);
|
|
|
537 } else {
|
|
|
538 element = factory.element(localName);
|
|
|
539 }
|
|
|
540
|
|
|
541 // Take leftover declared namespaces and add them to this element's
|
|
|
542 // map of namespaces
|
|
|
543 if (declaredNamespaces.size() > 0) {
|
|
|
544 transferNamespaces(element);
|
|
|
545 }
|
|
|
546
|
|
|
547 // Handle attributes
|
|
|
548 for (int i=0, len=atts.getLength(); i<len; i++) {
|
|
|
549 Attribute attribute = null;
|
|
|
550
|
|
|
551 String attLocalName = atts.getLocalName(i);
|
|
|
552 String attQName = atts.getQName(i);
|
|
|
553 int attType = getAttributeType(atts.getType(i));
|
|
|
554
|
|
|
555 // Bypass any xmlns attributes which might appear, as we got
|
|
|
556 // them already in startPrefixMapping().
|
|
|
557 // This is sometimes necessary when SAXHandler is used with
|
|
|
558 // another source than SAXBuilder, as with JDOMResult.
|
|
|
559 if (attQName.startsWith("xmlns:") || attQName.equals("xmlns")) {
|
|
|
560 continue;
|
|
|
561 }
|
|
|
562
|
|
|
563 // First clause per http://markmail.org/message/2p245ggcjst27xe6
|
|
|
564 // patch from Mattias Jiderhamn
|
|
|
565 if ("".equals(attLocalName) && attQName.indexOf(":") == -1) {
|
|
|
566 attribute = factory.attribute(attQName, atts.getValue(i), attType);
|
|
|
567 } else if (!attQName.equals(attLocalName)) {
|
|
|
568 String attPrefix = attQName.substring(0, attQName.indexOf(":"));
|
|
|
569 Namespace attNs = Namespace.getNamespace(attPrefix,
|
|
|
570 atts.getURI(i));
|
|
|
571
|
|
|
572 attribute = factory.attribute(attLocalName, atts.getValue(i),
|
|
|
573 attType, attNs);
|
|
|
574 } else {
|
|
|
575 attribute = factory.attribute(attLocalName, atts.getValue(i),
|
|
|
576 attType);
|
|
|
577 }
|
|
|
578 factory.setAttribute(element, attribute);
|
|
|
579 }
|
|
|
580
|
|
|
581 flushCharacters();
|
|
|
582
|
|
|
583 if (atRoot) {
|
|
|
584 document.setRootElement(element); // XXX should we use a factory call?
|
|
|
585 atRoot = false;
|
|
|
586 } else {
|
|
|
587 factory.addContent(getCurrentElement(), element);
|
|
|
588 }
|
|
|
589 currentElement = element;
|
|
|
590 }
|
|
|
591
|
|
|
592 /**
|
|
|
593 * This will take the supplied <code>{@link Element}</code> and
|
|
|
594 * transfer its namespaces to the global namespace storage.
|
|
|
595 *
|
|
|
596 * @param element <code>Element</code> to read namespaces from.
|
|
|
597 */
|
|
|
598 private void transferNamespaces(Element element) {
|
|
|
599 Iterator i = declaredNamespaces.iterator();
|
|
|
600 while (i.hasNext()) {
|
|
|
601 Namespace ns = (Namespace)i.next();
|
|
|
602 if (ns != element.getNamespace()) {
|
|
|
603 element.addNamespaceDeclaration(ns);
|
|
|
604 }
|
|
|
605 }
|
|
|
606 declaredNamespaces.clear();
|
|
|
607 }
|
|
|
608
|
|
|
609 /**
|
|
|
610 * This will report character data (within an element).
|
|
|
611 *
|
|
|
612 * @param ch <code>char[]</code> character array with character data
|
|
|
613 * @param start <code>int</code> index in array where data starts.
|
|
|
614 * @param length <code>int</code> length of data.
|
|
|
615 * @throws SAXException
|
|
|
616 */
|
|
|
617 public void characters(char[] ch, int start, int length)
|
|
|
618 throws SAXException {
|
|
|
619
|
|
|
620 if (suppress || (length == 0))
|
|
|
621 return;
|
|
|
622
|
|
|
623 if (previousCDATA != inCDATA) {
|
|
|
624 flushCharacters();
|
|
|
625 }
|
|
|
626
|
|
|
627 textBuffer.append(ch, start, length);
|
|
|
628 }
|
|
|
629
|
|
|
630 /**
|
|
|
631 * Capture ignorable whitespace as text. If
|
|
|
632 * setIgnoringElementContentWhitespace(true) has been called then this
|
|
|
633 * method does nothing.
|
|
|
634 *
|
|
|
635 * @param ch <code>[]</code> - char array of ignorable whitespace
|
|
|
636 * @param start <code>int</code> - starting position within array
|
|
|
637 * @param length <code>int</code> - length of whitespace after start
|
|
|
638 * @throws SAXException when things go wrong
|
|
|
639 */
|
|
|
640 public void ignorableWhitespace(char[] ch, int start, int length)
|
|
|
641 throws SAXException {
|
|
|
642 if (!ignoringWhite) {
|
|
|
643 characters(ch, start, length);
|
|
|
644 }
|
|
|
645 }
|
|
|
646
|
|
|
647 /**
|
|
|
648 * This will flush any characters from SAX character calls we've
|
|
|
649 * been buffering.
|
|
|
650 *
|
|
|
651 * @throws SAXException when things go wrong
|
|
|
652 */
|
|
|
653 protected void flushCharacters() throws SAXException {
|
|
|
654 if (ignoringBoundaryWhite) {
|
|
|
655 if (!textBuffer.isAllWhitespace()) {
|
|
|
656 flushCharacters(textBuffer.toString());
|
|
|
657 }
|
|
|
658 }
|
|
|
659 else {
|
|
|
660 flushCharacters(textBuffer.toString());
|
|
|
661 }
|
|
|
662 textBuffer.clear();
|
|
|
663 }
|
|
|
664
|
|
|
665 /**
|
|
|
666 * Flush the given string into the document. This is a protected method
|
|
|
667 * so subclassers can control text handling without knowledge of the
|
|
|
668 * internals of this class.
|
|
|
669 *
|
|
|
670 * @param data string to flush
|
|
|
671 */
|
|
|
672 protected void flushCharacters(String data) throws SAXException {
|
|
|
673 if (data.length() == 0) {
|
|
|
674 previousCDATA = inCDATA;
|
|
|
675 return;
|
|
|
676 }
|
|
|
677
|
|
|
678 /**
|
|
|
679 * This is commented out because of some problems with
|
|
|
680 * the inline DTDs that Xerces seems to have.
|
|
|
681 if (!inDTD) {
|
|
|
682 if (inEntity) {
|
|
|
683 getCurrentElement().setContent(factory.text(data));
|
|
|
684 } else {
|
|
|
685 getCurrentElement().addContent(factory.text(data));
|
|
|
686 }
|
|
|
687 */
|
|
|
688
|
|
|
689 if (previousCDATA) {
|
|
|
690 factory.addContent(getCurrentElement(), factory.cdata(data));
|
|
|
691 }
|
|
|
692 else {
|
|
|
693 factory.addContent(getCurrentElement(), factory.text(data));
|
|
|
694 }
|
|
|
695
|
|
|
696 previousCDATA = inCDATA;
|
|
|
697 }
|
|
|
698
|
|
|
699 /**
|
|
|
700 * Indicates the end of an element
|
|
|
701 * (<code></[element name]></code>) is reached. Note that
|
|
|
702 * the parser does not distinguish between empty
|
|
|
703 * elements and non-empty elements, so this will occur uniformly.
|
|
|
704 *
|
|
|
705 * @param namespaceURI <code>String</code> URI of namespace this
|
|
|
706 * element is associated with
|
|
|
707 * @param localName <code>String</code> name of element without prefix
|
|
|
708 * @param qName <code>String</code> name of element in XML 1.0 form
|
|
|
709 * @throws SAXException when things go wrong
|
|
|
710 */
|
|
|
711 public void endElement(String namespaceURI, String localName,
|
|
|
712 String qName) throws SAXException {
|
|
|
713
|
|
|
714 if (suppress) return;
|
|
|
715
|
|
|
716 flushCharacters();
|
|
|
717
|
|
|
718 if (!atRoot) {
|
|
|
719 Parent p = currentElement.getParent();
|
|
|
720 if (p instanceof Document) {
|
|
|
721 atRoot = true;
|
|
|
722 }
|
|
|
723 else {
|
|
|
724 currentElement = (Element) p;
|
|
|
725 }
|
|
|
726 }
|
|
|
727 else {
|
|
|
728 throw new SAXException(
|
|
|
729 "Ill-formed XML document (missing opening tag for " +
|
|
|
730 localName + ")");
|
|
|
731 }
|
|
|
732 }
|
|
|
733
|
|
|
734 /**
|
|
|
735 * This will signify that a DTD is being parsed, and can be
|
|
|
736 * used to ensure that comments and other lexical structures
|
|
|
737 * in the DTD are not added to the JDOM <code>Document</code>
|
|
|
738 * object.
|
|
|
739 *
|
|
|
740 * @param name <code>String</code> name of element listed in DTD
|
|
|
741 * @param publicID <code>String</code> public ID of DTD
|
|
|
742 * @param systemID <code>String</code> system ID of DTD
|
|
|
743 */
|
|
|
744 public void startDTD(String name, String publicID, String systemID)
|
|
|
745 throws SAXException {
|
|
|
746
|
|
|
747 flushCharacters(); // Is this needed here?
|
|
|
748
|
|
|
749 factory.addContent(document, factory.docType(name, publicID, systemID));
|
|
|
750 inDTD = true;
|
|
|
751 inInternalSubset = true;
|
|
|
752 }
|
|
|
753
|
|
|
754 /**
|
|
|
755 * This signifies that the reading of the DTD is complete.
|
|
|
756 *
|
|
|
757 * @throws SAXException
|
|
|
758 */
|
|
|
759 public void endDTD() throws SAXException {
|
|
|
760
|
|
|
761 document.getDocType().setInternalSubset(internalSubset.toString());
|
|
|
762 inDTD = false;
|
|
|
763 inInternalSubset = false;
|
|
|
764 }
|
|
|
765
|
|
|
766 public void startEntity(String name) throws SAXException {
|
|
|
767 entityDepth++;
|
|
|
768
|
|
|
769 if (expand || entityDepth > 1) {
|
|
|
770 // Short cut out if we're expanding or if we're nested
|
|
|
771 return;
|
|
|
772 }
|
|
|
773
|
|
|
774 // A "[dtd]" entity indicates the beginning of the external subset
|
|
|
775 if (name.equals("[dtd]")) {
|
|
|
776 inInternalSubset = false;
|
|
|
777 return;
|
|
|
778 }
|
|
|
779
|
|
|
780 // Ignore DTD references, and translate the standard 5
|
|
|
781 if ((!inDTD) &&
|
|
|
782 (!name.equals("amp")) &&
|
|
|
783 (!name.equals("lt")) &&
|
|
|
784 (!name.equals("gt")) &&
|
|
|
785 (!name.equals("apos")) &&
|
|
|
786 (!name.equals("quot"))) {
|
|
|
787
|
|
|
788 if (!expand) {
|
|
|
789 String pub = null;
|
|
|
790 String sys = null;
|
|
|
791 String[] ids = (String[]) externalEntities.get(name);
|
|
|
792 if (ids != null) {
|
|
|
793 pub = ids[0]; // may be null, that's OK
|
|
|
794 sys = ids[1]; // may be null, that's OK
|
|
|
795 }
|
|
|
796 /**
|
|
|
797 * if no current element, this entity belongs to an attribute
|
|
|
798 * in these cases, it is an error on the part of the parser
|
|
|
799 * to call startEntity but this will help in some cases.
|
|
|
800 * See org/xml/sax/ext/LexicalHandler.html#startEntity(java.lang.String)
|
|
|
801 * for more information
|
|
|
802 */
|
|
|
803 if (!atRoot) {
|
|
|
804 flushCharacters();
|
|
|
805 EntityRef entity = factory.entityRef(name, pub, sys);
|
|
|
806
|
|
|
807 // no way to tell if the entity was from an attribute or element so just assume element
|
|
|
808 factory.addContent(getCurrentElement(), entity);
|
|
|
809 }
|
|
|
810 suppress = true;
|
|
|
811 }
|
|
|
812 }
|
|
|
813 }
|
|
|
814
|
|
|
815 public void endEntity(String name) throws SAXException {
|
|
|
816 entityDepth--;
|
|
|
817 if (entityDepth == 0) {
|
|
|
818 // No way are we suppressing if not in an entity,
|
|
|
819 // regardless of the "expand" value
|
|
|
820 suppress = false;
|
|
|
821 }
|
|
|
822 if (name.equals("[dtd]")) {
|
|
|
823 inInternalSubset = true;
|
|
|
824 }
|
|
|
825 }
|
|
|
826
|
|
|
827 /**
|
|
|
828 * Report a CDATA section
|
|
|
829 *
|
|
|
830 * @throws SAXException
|
|
|
831 */
|
|
|
832 public void startCDATA() throws SAXException {
|
|
|
833 if (suppress) return;
|
|
|
834
|
|
|
835 inCDATA = true;
|
|
|
836 }
|
|
|
837
|
|
|
838 /**
|
|
|
839 * Report a CDATA section
|
|
|
840 */
|
|
|
841 public void endCDATA() throws SAXException {
|
|
|
842 if (suppress) return;
|
|
|
843
|
|
|
844 previousCDATA = true;
|
|
|
845 inCDATA = false;
|
|
|
846 }
|
|
|
847
|
|
|
848 /**
|
|
|
849 * This reports that a comments is parsed. If not in the
|
|
|
850 * DTD, this comment is added to the current JDOM
|
|
|
851 * <code>Element</code>, or the <code>Document</code> itself
|
|
|
852 * if at that level.
|
|
|
853 *
|
|
|
854 * @param ch <code>ch[]</code> array of comment characters.
|
|
|
855 * @param start <code>int</code> index to start reading from.
|
|
|
856 * @param length <code>int</code> length of data.
|
|
|
857 * @throws SAXException
|
|
|
858 */
|
|
|
859 public void comment(char[] ch, int start, int length)
|
|
|
860 throws SAXException {
|
|
|
861
|
|
|
862 if (suppress) return;
|
|
|
863
|
|
|
864 flushCharacters();
|
|
|
865
|
|
|
866 String commentText = new String(ch, start, length);
|
|
|
867 if (inDTD && inInternalSubset && (expand == false)) {
|
|
|
868 internalSubset.append(" <!--")
|
|
|
869 .append(commentText)
|
|
|
870 .append("-->\n");
|
|
|
871 return;
|
|
|
872 }
|
|
|
873 if ((!inDTD) && (!commentText.equals(""))) {
|
|
|
874 if (atRoot) {
|
|
|
875 factory.addContent(document, factory.comment(commentText));
|
|
|
876 } else {
|
|
|
877 factory.addContent(getCurrentElement(), factory.comment(commentText));
|
|
|
878 }
|
|
|
879 }
|
|
|
880 }
|
|
|
881
|
|
|
882 /**
|
|
|
883 * Handle the declaration of a Notation in a DTD
|
|
|
884 *
|
|
|
885 * @param name name of the notation
|
|
|
886 * @param publicID the public ID of the notation
|
|
|
887 * @param systemID the system ID of the notation
|
|
|
888 */
|
|
|
889 public void notationDecl(String name, String publicID, String systemID)
|
|
|
890 throws SAXException {
|
|
|
891
|
|
|
892 if (!inInternalSubset) return;
|
|
|
893
|
|
|
894 internalSubset.append(" <!NOTATION ")
|
|
|
895 .append(name);
|
|
|
896 appendExternalId(publicID, systemID);
|
|
|
897 internalSubset.append(">\n");
|
|
|
898 }
|
|
|
899
|
|
|
900 /**
|
|
|
901 * Handler for unparsed entity declarations in the DTD
|
|
|
902 *
|
|
|
903 * @param name <code>String</code> of the unparsed entity decl
|
|
|
904 * @param publicID <code>String</code> of the unparsed entity decl
|
|
|
905 * @param systemID <code>String</code> of the unparsed entity decl
|
|
|
906 * @param notationName <code>String</code> of the unparsed entity decl
|
|
|
907 */
|
|
|
908 public void unparsedEntityDecl(String name, String publicID,
|
|
|
909 String systemID, String notationName)
|
|
|
910 throws SAXException {
|
|
|
911
|
|
|
912 if (!inInternalSubset) return;
|
|
|
913
|
|
|
914 internalSubset.append(" <!ENTITY ")
|
|
|
915 .append(name);
|
|
|
916 appendExternalId(publicID, systemID);
|
|
|
917 internalSubset.append(" NDATA ")
|
|
|
918 .append(notationName);
|
|
|
919 internalSubset.append(">\n");
|
|
|
920 }
|
|
|
921
|
|
|
922 /**
|
|
|
923 * Appends an external ID to the internal subset buffer. Either publicID
|
|
|
924 * or systemID may be null, but not both.
|
|
|
925 *
|
|
|
926 * @param publicID the public ID
|
|
|
927 * @param systemID the system ID
|
|
|
928 */
|
|
|
929 private void appendExternalId(String publicID, String systemID) {
|
|
|
930 if (publicID != null) {
|
|
|
931 internalSubset.append(" PUBLIC \"")
|
|
|
932 .append(publicID)
|
|
|
933 .append('\"');
|
|
|
934 }
|
|
|
935 if (systemID != null) {
|
|
|
936 if (publicID == null) {
|
|
|
937 internalSubset.append(" SYSTEM ");
|
|
|
938 }
|
|
|
939 else {
|
|
|
940 internalSubset.append(' ');
|
|
|
941 }
|
|
|
942 internalSubset.append('\"')
|
|
|
943 .append(systemID)
|
|
|
944 .append('\"');
|
|
|
945 }
|
|
|
946 }
|
|
|
947
|
|
|
948 /**
|
|
|
949 * Returns the being-parsed element.
|
|
|
950 *
|
|
|
951 * @return <code>Element</code> - element being built.
|
|
|
952 * @throws SAXException
|
|
|
953 */
|
|
|
954 public Element getCurrentElement() throws SAXException {
|
|
|
955 if (currentElement == null) {
|
|
|
956 throw new SAXException(
|
|
|
957 "Ill-formed XML document (multiple root elements detected)");
|
|
|
958 }
|
|
|
959 return currentElement;
|
|
|
960 }
|
|
|
961
|
|
|
962 /**
|
|
|
963 * Returns the the JDOM Attribute type value from the SAX 2.0
|
|
|
964 * attribute type string provided by the parser.
|
|
|
965 *
|
|
|
966 * @param typeName <code>String</code> the SAX 2.0 attribute
|
|
|
967 * type string.
|
|
|
968 *
|
|
|
969 * @return <code>int</code> the JDOM attribute type.
|
|
|
970 *
|
|
|
971 * @see Attribute#setAttributeType
|
|
|
972 * @see Attributes#getType
|
|
|
973 */
|
|
|
974 private static int getAttributeType(String typeName) {
|
|
|
975 Integer type = (Integer)(attrNameToTypeMap.get(typeName));
|
|
|
976 if (type == null) {
|
|
|
977 if (typeName != null && typeName.length() > 0 &&
|
|
|
978 typeName.charAt(0) == '(') {
|
|
|
979 // Xerces 1.4.X reports attributes of enumerated type with
|
|
|
980 // a type string equals to the enumeration definition, i.e.
|
|
|
981 // starting with a parenthesis.
|
|
|
982 return Attribute.ENUMERATED_TYPE;
|
|
|
983 }
|
|
|
984 else {
|
|
|
985 return Attribute.UNDECLARED_TYPE;
|
|
|
986 }
|
|
|
987 } else {
|
|
|
988 return type.intValue();
|
|
|
989 }
|
|
|
990 }
|
|
|
991
|
|
|
992 /**
|
|
|
993 * Receives an object for locating the origin of SAX document
|
|
|
994 * events. This method is invoked by the SAX parser.
|
|
|
995 * <p>
|
|
|
996 * {@link org.jdom.JDOMFactory} implementations can use the
|
|
|
997 * {@link #getDocumentLocator} method to get access to the
|
|
|
998 * {@link Locator} during parse.
|
|
|
999 * </p>
|
|
|
1000 *
|
|
|
1001 * @param locator <code>Locator</code> an object that can return
|
|
|
1002 * the location of any SAX document event.
|
|
|
1003 */
|
|
|
1004 public void setDocumentLocator(Locator locator) {
|
|
|
1005 this.locator = locator;
|
|
|
1006 }
|
|
|
1007
|
|
|
1008 /**
|
|
|
1009 * Provides access to the {@link Locator} object provided by the
|
|
|
1010 * SAX parser.
|
|
|
1011 *
|
|
|
1012 * @return <code>Locator</code> an object that can return
|
|
|
1013 * the location of any SAX document event.
|
|
|
1014 */
|
|
|
1015 public Locator getDocumentLocator() {
|
|
|
1016 return locator;
|
|
|
1017 }
|
|
|
1018 }
|
