001: // ContentHandler.java - handle main document content.
002: // http://www.saxproject.org
003: // Written by David Megginson
004: // NO WARRANTY! This class is in the public domain.
005:
006: // $Id: ContentHandler.java,v 1.1.1.1 2002/05/03 23:29:40 yuvalo Exp $
007:
008: package org.xml.sax;
009:
010: /**
011: * Receive notification of the logical content of a document.
012: *
013: * <blockquote>
014: * <em>This module, both source code and documentation, is in the
015: * Public Domain, and comes with <strong>NO WARRANTY</strong>.</em>
016: * See <a href='http://www.saxproject.org'>http://www.saxproject.org</a>
017: * for further information.
018: * </blockquote>
019: *
020: * <p>This is the main interface that most SAX applications
021: * implement: if the application needs to be informed of basic parsing
022: * events, it implements this interface and registers an instance with
023: * the SAX parser using the {@link org.xml.sax.XMLReader#setContentHandler
024: * setContentHandler} method. The parser uses the instance to report
025: * basic document-related events like the start and end of elements
026: * and character data.</p>
027: *
028: * <p>The order of events in this interface is very important, and
029: * mirrors the order of information in the document itself. For
030: * example, all of an element's content (character data, processing
031: * instructions, and/or subelements) will appear, in order, between
032: * the startElement event and the corresponding endElement event.</p>
033: *
034: * <p>This interface is similar to the now-deprecated SAX 1.0
035: * DocumentHandler interface, but it adds support for Namespaces
036: * and for reporting skipped entities (in non-validating XML
037: * processors).</p>
038: *
039: * <p>Implementors should note that there is also a Java class
040: * {@link java.net.ContentHandler ContentHandler} in the java.net
041: * package; that means that it's probably a bad idea to do</p>
042: *
043: * <blockquote>
044: * import java.net.*;
045: * import org.xml.sax.*;
046: * </blockquote>
047: *
048: * <p>In fact, "import ...*" is usually a sign of sloppy programming
049: * anyway, so the user should consider this a feature rather than a
050: * bug.</p>
051: *
052: * @since SAX 2.0
053: * @author David Megginson
054: * @version 2.0.1 (sax2r2)
055: * @see org.xml.sax.XMLReader
056: * @see org.xml.sax.DTDHandler
057: * @see org.xml.sax.ErrorHandler
058: */
059: public interface ContentHandler {
060:
061: /**
062: * Receive an object for locating the origin of SAX document events.
063: *
064: * <p>SAX parsers are strongly encouraged (though not absolutely
065: * required) to supply a locator: if it does so, it must supply
066: * the locator to the application by invoking this method before
067: * invoking any of the other methods in the ContentHandler
068: * interface.</p>
069: *
070: * <p>The locator allows the application to determine the end
071: * position of any document-related event, even if the parser is
072: * not reporting an error. Typically, the application will
073: * use this information for reporting its own errors (such as
074: * character content that does not match an application's
075: * business rules). The information returned by the locator
076: * is probably not sufficient for use with a search engine.</p>
077: *
078: * <p>Note that the locator will return correct information only
079: * during the invocation of the events in this interface. The
080: * application should not attempt to use it at any other time.</p>
081: *
082: * @param locator An object that can return the location of
083: * any SAX document event.
084: * @see org.xml.sax.Locator
085: */
086: public void setDocumentLocator(Locator locator);
087:
088: /**
089: * Receive notification of the beginning of a document.
090: *
091: * <p>The SAX parser will invoke this method only once, before any
092: * other event callbacks (except for {@link #setDocumentLocator
093: * setDocumentLocator}).</p>
094: *
095: * @exception org.xml.sax.SAXException Any SAX exception, possibly
096: * wrapping another exception.
097: * @see #endDocument
098: */
099: public void startDocument() throws SAXException;
100:
101: /**
102: * Receive notification of the end of a document.
103: *
104: * <p>The SAX parser will invoke this method only once, and it will
105: * be the last method invoked during the parse. The parser shall
106: * not invoke this method until it has either abandoned parsing
107: * (because of an unrecoverable error) or reached the end of
108: * input.</p>
109: *
110: * @exception org.xml.sax.SAXException Any SAX exception, possibly
111: * wrapping another exception.
112: * @see #startDocument
113: */
114: public void endDocument() throws SAXException;
115:
116: /**
117: * Begin the scope of a prefix-URI Namespace mapping.
118: *
119: * <p>The information from this event is not necessary for
120: * normal Namespace processing: the SAX XML reader will
121: * automatically replace prefixes for element and attribute
122: * names when the <code>http://xml.org/sax/features/namespaces</code>
123: * feature is <var>true</var> (the default).</p>
124: *
125: * <p>There are cases, however, when applications need to
126: * use prefixes in character data or in attribute values,
127: * where they cannot safely be expanded automatically; the
128: * start/endPrefixMapping event supplies the information
129: * to the application to expand prefixes in those contexts
130: * itself, if necessary.</p>
131: *
132: * <p>Note that start/endPrefixMapping events are not
133: * guaranteed to be properly nested relative to each other:
134: * all startPrefixMapping events will occur immediately before the
135: * corresponding {@link #startElement startElement} event,
136: * and all {@link #endPrefixMapping endPrefixMapping}
137: * events will occur immediately after the corresponding
138: * {@link #endElement endElement} event,
139: * but their order is not otherwise
140: * guaranteed.</p>
141: *
142: * <p>There should never be start/endPrefixMapping events for the
143: * "xml" prefix, since it is predeclared and immutable.</p>
144: *
145: * @param prefix The Namespace prefix being declared.
146: * An empty string is used for the default element namespace,
147: * which has no prefix.
148: * @param uri The Namespace URI the prefix is mapped to.
149: * @exception org.xml.sax.SAXException The client may throw
150: * an exception during processing.
151: * @see #endPrefixMapping
152: * @see #startElement
153: */
154: public void startPrefixMapping(String prefix, String uri)
155: throws SAXException;
156:
157: /**
158: * End the scope of a prefix-URI mapping.
159: *
160: * <p>See {@link #startPrefixMapping startPrefixMapping} for
161: * details. These events will always occur immediately after the
162: * corresponding {@link #endElement endElement} event, but the order of
163: * {@link #endPrefixMapping endPrefixMapping} events is not otherwise
164: * guaranteed.</p>
165: *
166: * @param prefix The prefix that was being mapping.
167: * This is the empty string when a default mapping scope ends.
168: * @exception org.xml.sax.SAXException The client may throw
169: * an exception during processing.
170: * @see #startPrefixMapping
171: * @see #endElement
172: */
173: public void endPrefixMapping(String prefix) throws SAXException;
174:
175: /**
176: * Receive notification of the beginning of an element.
177: *
178: * <p>The Parser will invoke this method at the beginning of every
179: * element in the XML document; there will be a corresponding
180: * {@link #endElement endElement} event for every startElement event
181: * (even when the element is empty). All of the element's content will be
182: * reported, in order, before the corresponding endElement
183: * event.</p>
184: *
185: * <p>This event allows up to three name components for each
186: * element:</p>
187: *
188: * <ol>
189: * <li>the Namespace URI;</li>
190: * <li>the local name; and</li>
191: * <li>the qualified (prefixed) name.</li>
192: * </ol>
193: *
194: * <p>Any or all of these may be provided, depending on the
195: * values of the <var>http://xml.org/sax/features/namespaces</var>
196: * and the <var>http://xml.org/sax/features/namespace-prefixes</var>
197: * properties:</p>
198: *
199: * <ul>
200: * <li>the Namespace URI and local name are required when
201: * the namespaces property is <var>true</var> (the default), and are
202: * optional when the namespaces property is <var>false</var> (if one is
203: * specified, both must be);</li>
204: * <li>the qualified name is required when the namespace-prefixes property
205: * is <var>true</var>, and is optional when the namespace-prefixes property
206: * is <var>false</var> (the default).</li>
207: * </ul>
208: *
209: * <p>Note that the attribute list provided will contain only
210: * attributes with explicit values (specified or defaulted):
211: * #IMPLIED attributes will be omitted. The attribute list
212: * will contain attributes used for Namespace declarations
213: * (xmlns* attributes) only if the
214: * <code>http://xml.org/sax/features/namespace-prefixes</code>
215: * property is true (it is false by default, and support for a
216: * true value is optional).</p>
217: *
218: * <p>Like {@link #characters characters()}, attribute values may have
219: * characters that need more than one <code>char</code> value. </p>
220: *
221: * @param uri The Namespace URI, or the empty string if the
222: * element has no Namespace URI or if Namespace
223: * processing is not being performed.
224: * @param localName The local name (without prefix), or the
225: * empty string if Namespace processing is not being
226: * performed.
227: * @param qName The qualified name (with prefix), or the
228: * empty string if qualified names are not available.
229: * @param atts The attributes attached to the element. If
230: * there are no attributes, it shall be an empty
231: * Attributes object.
232: * @exception org.xml.sax.SAXException Any SAX exception, possibly
233: * wrapping another exception.
234: * @see #endElement
235: * @see org.xml.sax.Attributes
236: */
237: public void startElement(String uri, String localName,
238: String qName, Attributes atts) throws SAXException;
239:
240: /**
241: * Receive notification of the end of an element.
242: *
243: * <p>The SAX parser will invoke this method at the end of every
244: * element in the XML document; there will be a corresponding
245: * {@link #startElement startElement} event for every endElement
246: * event (even when the element is empty).</p>
247: *
248: * <p>For information on the names, see startElement.</p>
249: *
250: * @param uri The Namespace URI, or the empty string if the
251: * element has no Namespace URI or if Namespace
252: * processing is not being performed.
253: * @param localName The local name (without prefix), or the
254: * empty string if Namespace processing is not being
255: * performed.
256: * @param qName The qualified XML 1.0 name (with prefix), or the
257: * empty string if qualified names are not available.
258: * @exception org.xml.sax.SAXException Any SAX exception, possibly
259: * wrapping another exception.
260: */
261: public void endElement(String uri, String localName, String qName)
262: throws SAXException;
263:
264: /**
265: * Receive notification of character data.
266: *
267: * <p>The Parser will call this method to report each chunk of
268: * character data. SAX parsers may return all contiguous character
269: * data in a single chunk, or they may split it into several
270: * chunks; however, all of the characters in any single event
271: * must come from the same external entity so that the Locator
272: * provides useful information.</p>
273: *
274: * <p>The application must not attempt to read from the array
275: * outside of the specified range.</p>
276: *
277: * <p>Individual characters may consist of more than one Java
278: * <code>char</code> value. There are two important cases where this
279: * happens, because characters can't be represented in just sixteen bits.
280: * In one case, characters are represented in a <em>Surrogate Pair</em>,
281: * using two special Unicode values. Such characters are in the so-called
282: * "Astral Planes", with a code point above U+FFFF. A second case involves
283: * composite characters, such as a base character combining with one or
284: * more accent characters. </p>
285: *
286: * <p> Your code should not assume that algorithms using
287: * <code>char</code>-at-a-time idioms will be working in character
288: * units; in some cases they will split characters. This is relevant
289: * wherever XML permits arbitrary characters, such as attribute values,
290: * processing instruction data, and comments as well as in data reported
291: * from this method. It's also generally relevant whenever Java code
292: * manipulates internationalized text; the issue isn't unique to XML.</p>
293: *
294: * <p>Note that some parsers will report whitespace in element
295: * content using the {@link #ignorableWhitespace ignorableWhitespace}
296: * method rather than this one (validating parsers <em>must</em>
297: * do so).</p>
298: *
299: * @param ch The characters from the XML document.
300: * @param start The start position in the array.
301: * @param length The number of characters to read from the array.
302: * @exception org.xml.sax.SAXException Any SAX exception, possibly
303: * wrapping another exception.
304: * @see #ignorableWhitespace
305: * @see org.xml.sax.Locator
306: */
307: public void characters(char ch[], int start, int length)
308: throws SAXException;
309:
310: /**
311: * Receive notification of ignorable whitespace in element content.
312: *
313: * <p>Validating Parsers must use this method to report each chunk
314: * of whitespace in element content (see the W3C XML 1.0 recommendation,
315: * section 2.10): non-validating parsers may also use this method
316: * if they are capable of parsing and using content models.</p>
317: *
318: * <p>SAX parsers may return all contiguous whitespace in a single
319: * chunk, or they may split it into several chunks; however, all of
320: * the characters in any single event must come from the same
321: * external entity, so that the Locator provides useful
322: * information.</p>
323: *
324: * <p>The application must not attempt to read from the array
325: * outside of the specified range.</p>
326: *
327: * @param ch The characters from the XML document.
328: * @param start The start position in the array.
329: * @param length The number of characters to read from the array.
330: * @exception org.xml.sax.SAXException Any SAX exception, possibly
331: * wrapping another exception.
332: * @see #characters
333: */
334: public void ignorableWhitespace(char ch[], int start, int length)
335: throws SAXException;
336:
337: /**
338: * Receive notification of a processing instruction.
339: *
340: * <p>The Parser will invoke this method once for each processing
341: * instruction found: note that processing instructions may occur
342: * before or after the main document element.</p>
343: *
344: * <p>A SAX parser must never report an XML declaration (XML 1.0,
345: * section 2.8) or a text declaration (XML 1.0, section 4.3.1)
346: * using this method.</p>
347: *
348: * <p>Like {@link #characters characters()}, processing instruction
349: * data may have characters that need more than one <code>char</code>
350: * value. </p>
351: *
352: * @param target The processing instruction target.
353: * @param data The processing instruction data, or null if
354: * none was supplied. The data does not include any
355: * whitespace separating it from the target.
356: * @exception org.xml.sax.SAXException Any SAX exception, possibly
357: * wrapping another exception.
358: */
359: public void processingInstruction(String target, String data)
360: throws SAXException;
361:
362: /**
363: * Receive notification of a skipped entity.
364: * This is not called for entity references within markup constructs
365: * such as element start tags or markup declarations. (The XML
366: * recommendation requires reporting skipped external entities.
367: * SAX also reports internal entity expansion/non-expansion, except
368: * within markup constructs.)
369: *
370: * <p>The Parser will invoke this method each time the entity is
371: * skipped. Non-validating processors may skip entities if they
372: * have not seen the declarations (because, for example, the
373: * entity was declared in an external DTD subset). All processors
374: * may skip external entities, depending on the values of the
375: * <code>http://xml.org/sax/features/external-general-entities</code>
376: * and the
377: * <code>http://xml.org/sax/features/external-parameter-entities</code>
378: * properties.</p>
379: *
380: * @param name The name of the skipped entity. If it is a
381: * parameter entity, the name will begin with '%', and if
382: * it is the external DTD subset, it will be the string
383: * "[dtd]".
384: * @exception org.xml.sax.SAXException Any SAX exception, possibly
385: * wrapping another exception.
386: */
387: public void skippedEntity(String name) throws SAXException;
388: }
389:
390: // end of ContentHandler.java
|