1 /*
2 * Copyright (c) 2000, 2005, 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 // ContentHandler.java - handle main document content.
27 // http://www.saxproject.org
28 // Written by David Megginson
29 // NO WARRANTY! This class is in the public domain.
30 // $Id: ContentHandler.java,v 1.2 2004/11/03 22:44:51 jsuttor Exp $
31
32 package org.xml.sax;
33
34
35 /**
36 * Receive notification of the logical content of a document.
37 *
38 * <blockquote>
39 * <em>This module, both source code and documentation, is in the
40 * Public Domain, and comes with <strong>NO WARRANTY</strong>.</em>
41 * See <a href='http://www.saxproject.org'>http://www.saxproject.org</a>
42 * for further information.
43 * </blockquote>
44 *
45 * <p>This is the main interface that most SAX applications
46 * implement: if the application needs to be informed of basic parsing
47 * events, it implements this interface and registers an instance with
48 * the SAX parser using the {@link org.xml.sax.XMLReader#setContentHandler
49 * setContentHandler} method. The parser uses the instance to report
50 * basic document-related events like the start and end of elements
51 * and character data.</p>
52 *
53 * <p>The order of events in this interface is very important, and
54 * mirrors the order of information in the document itself. For
55 * example, all of an element's content (character data, processing
56 * instructions, and/or subelements) will appear, in order, between
57 * the startElement event and the corresponding endElement event.</p>
58 *
59 * <p>This interface is similar to the now-deprecated SAX 1.0
60 * DocumentHandler interface, but it adds support for Namespaces
61 * and for reporting skipped entities (in non-validating XML
62 * processors).</p>
63 *
64 * <p>Implementors should note that there is also a
65 * <code>ContentHandler</code> class in the <code>java.net</code>
66 * package; that means that it's probably a bad idea to do</p>
67 *
68 * <pre>import java.net.*;
69 * import org.xml.sax.*;
70 * </pre>
71 *
72 * <p>In fact, "import ...*" is usually a sign of sloppy programming
73 * anyway, so the user should consider this a feature rather than a
74 * bug.</p>
75 *
76 * @since SAX 2.0
77 * @author David Megginson
78 * @see org.xml.sax.XMLReader
79 * @see org.xml.sax.DTDHandler
80 * @see org.xml.sax.ErrorHandler
81 */
82 public interface ContentHandler
83 {
84
85 /**
86 * Receive an object for locating the origin of SAX document events.
87 *
88 * <p>SAX parsers are strongly encouraged (though not absolutely
89 * required) to supply a locator: if it does so, it must supply
90 * the locator to the application by invoking this method before
91 * invoking any of the other methods in the ContentHandler
92 * interface.</p>
93 *
94 * <p>The locator allows the application to determine the end
95 * position of any document-related event, even if the parser is
96 * not reporting an error. Typically, the application will
97 * use this information for reporting its own errors (such as
98 * character content that does not match an application's
99 * business rules). The information returned by the locator
100 * is probably not sufficient for use with a search engine.</p>
101 *
102 * <p>Note that the locator will return correct information only
103 * during the invocation SAX event callbacks after
104 * {@link #startDocument startDocument} returns and before
105 * {@link #endDocument endDocument} is called. The
106 * application should not attempt to use it at any other time.</p>
107 *
108 * @param locator an object that can return the location of
109 * any SAX document event
110 * @see org.xml.sax.Locator
111 */
112 public void setDocumentLocator (Locator locator);
113
114
115 /**
116 * Receive notification of the beginning of a document.
117 *
118 * <p>The SAX parser will invoke this method only once, before any
119 * other event callbacks (except for {@link #setDocumentLocator
120 * setDocumentLocator}).</p>
121 *
122 * @throws org.xml.sax.SAXException any SAX exception, possibly
123 * wrapping another exception
124 * @see #endDocument
125 */
126 public void startDocument ()
127 throws SAXException;
128
129
130 /**
131 * Receive notification of the end of a document.
132 *
133 * <p><strong>There is an apparent contradiction between the
134 * documentation for this method and the documentation for {@link
135 * org.xml.sax.ErrorHandler#fatalError}. Until this ambiguity is
136 * resolved in a future major release, clients should make no
137 * assumptions about whether endDocument() will or will not be
138 * invoked when the parser has reported a fatalError() or thrown
139 * an exception.</strong></p>
140 *
141 * <p>The SAX parser will invoke this method only once, and it will
142 * be the last method invoked during the parse. The parser shall
143 * not invoke this method until it has either abandoned parsing
144 * (because of an unrecoverable error) or reached the end of
145 * input.</p>
146 *
147 * @throws org.xml.sax.SAXException any SAX exception, possibly
148 * wrapping another exception
149 * @see #startDocument
150 */
151 public void endDocument()
152 throws SAXException;
153
154
155 /**
156 * Begin the scope of a prefix-URI Namespace mapping.
157 *
158 * <p>The information from this event is not necessary for
159 * normal Namespace processing: the SAX XML reader will
160 * automatically replace prefixes for element and attribute
161 * names when the <code>http://xml.org/sax/features/namespaces</code>
162 * feature is <var>true</var> (the default).</p>
163 *
164 * <p>There are cases, however, when applications need to
165 * use prefixes in character data or in attribute values,
166 * where they cannot safely be expanded automatically; the
167 * start/endPrefixMapping event supplies the information
168 * to the application to expand prefixes in those contexts
169 * itself, if necessary.</p>
170 *
171 * <p>Note that start/endPrefixMapping events are not
172 * guaranteed to be properly nested relative to each other:
173 * all startPrefixMapping events will occur immediately before the
174 * corresponding {@link #startElement startElement} event,
175 * and all {@link #endPrefixMapping endPrefixMapping}
176 * events will occur immediately after the corresponding
177 * {@link #endElement endElement} event,
178 * but their order is not otherwise
179 * guaranteed.</p>
180 *
181 * <p>There should never be start/endPrefixMapping events for the
182 * "xml" prefix, since it is predeclared and immutable.</p>
183 *
184 * @param prefix the Namespace prefix being declared.
185 * An empty string is used for the default element namespace,
186 * which has no prefix.
187 * @param uri the Namespace URI the prefix is mapped to
188 * @throws org.xml.sax.SAXException the client may throw
189 * an exception during processing
190 * @see #endPrefixMapping
191 * @see #startElement
192 */
193 public void startPrefixMapping (String prefix, String uri)
194 throws SAXException;
195
196
197 /**
198 * End the scope of a prefix-URI mapping.
199 *
200 * <p>See {@link #startPrefixMapping startPrefixMapping} for
201 * details. These events will always occur immediately after the
202 * corresponding {@link #endElement endElement} event, but the order of
203 * {@link #endPrefixMapping endPrefixMapping} events is not otherwise
204 * guaranteed.</p>
205 *
206 * @param prefix the prefix that was being mapped.
207 * This is the empty string when a default mapping scope ends.
208 * @throws org.xml.sax.SAXException the client may throw
209 * an exception during processing
210 * @see #startPrefixMapping
211 * @see #endElement
212 */
213 public void endPrefixMapping (String prefix)
214 throws SAXException;
215
216
217 /**
218 * Receive notification of the beginning of an element.
219 *
220 * <p>The Parser will invoke this method at the beginning of every
221 * element in the XML document; there will be a corresponding
222 * {@link #endElement endElement} event for every startElement event
223 * (even when the element is empty). All of the element's content will be
224 * reported, in order, before the corresponding endElement
225 * event.</p>
226 *
227 * <p>This event allows up to three name components for each
228 * element:</p>
229 *
230 * <ol>
231 * <li>the Namespace URI;</li>
232 * <li>the local name; and</li>
233 * <li>the qualified (prefixed) name.</li>
234 * </ol>
235 *
236 * <p>Any or all of these may be provided, depending on the
237 * values of the <var>http://xml.org/sax/features/namespaces</var>
238 * and the <var>http://xml.org/sax/features/namespace-prefixes</var>
239 * properties:</p>
240 *
241 * <ul>
242 * <li>the Namespace URI and local name are required when
243 * the namespaces property is <var>true</var> (the default), and are
244 * optional when the namespaces property is <var>false</var> (if one is
245 * specified, both must be);</li>
246 * <li>the qualified name is required when the namespace-prefixes property
247 * is <var>true</var>, and is optional when the namespace-prefixes property
248 * is <var>false</var> (the default).</li>
249 * </ul>
250 *
251 * <p>Note that the attribute list provided will contain only
252 * attributes with explicit values (specified or defaulted):
253 * #IMPLIED attributes will be omitted. The attribute list
254 * will contain attributes used for Namespace declarations
255 * (xmlns* attributes) only if the
256 * <code>http://xml.org/sax/features/namespace-prefixes</code>
257 * property is true (it is false by default, and support for a
258 * true value is optional).</p>
259 *
260 * <p>Like {@link #characters characters()}, attribute values may have
261 * characters that need more than one <code>char</code> value. </p>
262 *
263 * @param uri the Namespace URI, or the empty string if the
264 * element has no Namespace URI or if Namespace
265 * processing is not being performed
266 * @param localName the local name (without prefix), or the
267 * empty string if Namespace processing is not being
268 * performed
269 * @param qName the qualified name (with prefix), or the
270 * empty string if qualified names are not available
271 * @param atts the attributes attached to the element. If
272 * there are no attributes, it shall be an empty
273 * Attributes object. The value of this object after
274 * startElement returns is undefined
275 * @throws org.xml.sax.SAXException any SAX exception, possibly
276 * wrapping another exception
277 * @see #endElement
278 * @see org.xml.sax.Attributes
279 * @see org.xml.sax.helpers.AttributesImpl
280 */
281 public void startElement (String uri, String localName,
282 String qName, Attributes atts)
283 throws SAXException;
284
285
286 /**
287 * Receive notification of the end of an element.
288 *
289 * <p>The SAX parser will invoke this method at the end of every
290 * element in the XML document; there will be a corresponding
291 * {@link #startElement startElement} event for every endElement
292 * event (even when the element is empty).</p>
293 *
294 * <p>For information on the names, see startElement.</p>
295 *
296 * @param uri the Namespace URI, or the empty string if the
297 * element has no Namespace URI or if Namespace
298 * processing is not being performed
299 * @param localName the local name (without prefix), or the
300 * empty string if Namespace processing is not being
301 * performed
302 * @param qName the qualified XML name (with prefix), or the
303 * empty string if qualified names are not available
304 * @throws org.xml.sax.SAXException any SAX exception, possibly
305 * wrapping another exception
306 */
307 public void endElement (String uri, String localName,
308 String qName)
309 throws SAXException;
310
311
312 /**
313 * Receive notification of character data.
314 *
315 * <p>The Parser will call this method to report each chunk of
316 * character data. SAX parsers may return all contiguous character
317 * data in a single chunk, or they may split it into several
318 * chunks; however, all of the characters in any single event
319 * must come from the same external entity so that the Locator
320 * provides useful information.</p>
321 *
322 * <p>The application must not attempt to read from the array
323 * outside of the specified range.</p>
324 *
325 * <p>Individual characters may consist of more than one Java
326 * <code>char</code> value. There are two important cases where this
327 * happens, because characters can't be represented in just sixteen bits.
328 * In one case, characters are represented in a <em>Surrogate Pair</em>,
329 * using two special Unicode values. Such characters are in the so-called
330 * "Astral Planes", with a code point above U+FFFF. A second case involves
331 * composite characters, such as a base character combining with one or
332 * more accent characters. </p>
333 *
334 * <p> Your code should not assume that algorithms using
335 * <code>char</code>-at-a-time idioms will be working in character
336 * units; in some cases they will split characters. This is relevant
337 * wherever XML permits arbitrary characters, such as attribute values,
338 * processing instruction data, and comments as well as in data reported
339 * from this method. It's also generally relevant whenever Java code
340 * manipulates internationalized text; the issue isn't unique to XML.</p>
341 *
342 * <p>Note that some parsers will report whitespace in element
343 * content using the {@link #ignorableWhitespace ignorableWhitespace}
344 * method rather than this one (validating parsers <em>must</em>
345 * do so).</p>
346 *
347 * @param ch the characters from the XML document
348 * @param start the start position in the array
349 * @param length the number of characters to read from the array
350 * @throws org.xml.sax.SAXException any SAX exception, possibly
351 * wrapping another exception
352 * @see #ignorableWhitespace
353 * @see org.xml.sax.Locator
354 */
355 public void characters (char ch[], int start, int length)
356 throws SAXException;
357
358
359 /**
360 * Receive notification of ignorable whitespace in element content.
361 *
362 * <p>Validating Parsers must use this method to report each chunk
363 * of whitespace in element content (see the W3C XML 1.0
364 * recommendation, section 2.10): non-validating parsers may also
365 * use this method if they are capable of parsing and using
366 * content models.</p>
367 *
368 * <p>SAX parsers may return all contiguous whitespace in a single
369 * chunk, or they may split it into several chunks; however, all of
370 * the characters in any single event must come from the same
371 * external entity, so that the Locator provides useful
372 * information.</p>
373 *
374 * <p>The application must not attempt to read from the array
375 * outside of the specified range.</p>
376 *
377 * @param ch the characters from the XML document
378 * @param start the start position in the array
379 * @param length the number of characters to read from the array
380 * @throws org.xml.sax.SAXException any SAX exception, possibly
381 * wrapping another exception
382 * @see #characters
383 */
384 public void ignorableWhitespace (char ch[], int start, int length)
385 throws SAXException;
386
387
388 /**
389 * Receive notification of a processing instruction.
390 *
391 * <p>The Parser will invoke this method once for each processing
392 * instruction found: note that processing instructions may occur
393 * before or after the main document element.</p>
394 *
395 * <p>A SAX parser must never report an XML declaration (XML 1.0,
396 * section 2.8) or a text declaration (XML 1.0, section 4.3.1)
397 * using this method.</p>
398 *
399 * <p>Like {@link #characters characters()}, processing instruction
400 * data may have characters that need more than one <code>char</code>
401 * value. </p>
402 *
403 * @param target the processing instruction target
404 * @param data the processing instruction data, or null if
405 * none was supplied. The data does not include any
406 * whitespace separating it from the target
407 * @throws org.xml.sax.SAXException any SAX exception, possibly
408 * wrapping another exception
409 */
410 public void processingInstruction (String target, String data)
411 throws SAXException;
412
413
414 /**
415 * Receive notification of a skipped entity.
416 * This is not called for entity references within markup constructs
417 * such as element start tags or markup declarations. (The XML
418 * recommendation requires reporting skipped external entities.
419 * SAX also reports internal entity expansion/non-expansion, except
420 * within markup constructs.)
421 *
422 * <p>The Parser will invoke this method each time the entity is
423 * skipped. Non-validating processors may skip entities if they
424 * have not seen the declarations (because, for example, the
425 * entity was declared in an external DTD subset). All processors
426 * may skip external entities, depending on the values of the
427 * <code>http://xml.org/sax/features/external-general-entities</code>
428 * and the
429 * <code>http://xml.org/sax/features/external-parameter-entities</code>
430 * properties.</p>
431 *
432 * @param name the name of the skipped entity. If it is a
433 * parameter entity, the name will begin with '%', and if
434 * it is the external DTD subset, it will be the string
435 * "[dtd]"
436 * @throws org.xml.sax.SAXException any SAX exception, possibly
437 * wrapping another exception
438 */
439 public void skippedEntity (String name)
440 throws SAXException;
441 }
442
443 // end of ContentHandler.java