xmlpullparser.java

Wap Explorer 一个完整的在eclipse下可以运行的java工程。功能还不错

/* -*-             c-basic-offset: 4; indent-tabs-mode: nil; -*-  //------100-columns-wide------>|*/
// for license please see accompanying LICENSE.txt file (available also at http://www.xmlpull.org/)

package org.xmlpull.v1;

import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;

/**
 * XML Pull Parser is an interface that defines parsing functionlity provided
 * in <a href="http://www.xmlpull.org/">XMLPULL V1 API</a> (visit this website to
 * learn more about API and its implementations).
 *
 * <p>There are following different
 * kinds of parser depending on which features are set:<ul>
 * <li><b>non-validating</b> parser as defined in XML 1.0 spec when
 *   FEATURE_PROCESS_DOCDECL is set to true
 * <li><b>validating parser</b> as defined in XML 1.0 spec when
 *   FEATURE_VALIDATION is true (and that implies that FEATURE_PROCESS_DOCDECL is true)
 * <li>when FEATURE_PROCESS_DOCDECL is false (this is default and
 *   if different value is required necessary must be changed before parsing is started)
 *   then parser behaves like XML 1.0 compliant non-validating parser under condition that
 *  <em>no DOCDECL is present</em> in XML documents
 *   (internal entites can still be defined with defineEntityReplacementText()).
 *   This mode of operation is intened <b>for operation in constrained environments</b> such as J2ME.
 * </ul>
 *
 *
 * <p>There are two key methods: next() and nextToken(). While next() provides
 * access to high level parsing events, nextToken() allows access to lower
 * level tokens.
 *
 * <p>The current event state of the parser
 * can be determined by calling the
 * <a href="#getEventType()">getEventType()</a> method.
 * Initially, the parser is in the <a href="#START_DOCUMENT">START_DOCUMENT</a>
 * state.
 *
 * <p>The method <a href="#next()">next()</a> advances the parser to the
 * next event. The int value returned from next determines the current parser
 * state and is identical to the value returned from following calls to
 * getEventType ().
 *
 * <p>Th following event types are seen by next()<dl>
 * <dt><a href="#START_TAG">START_TAG</a><dd> An XML start tag was read.
 * <dt><a href="#TEXT">TEXT</a><dd> Text content was read;
 * the text content can be retreived using the getText() method.
 *  (when in validating mode next() will not report ignorable whitespaces, use nextToken() instead)
 * <dt><a href="#END_TAG">END_TAG</a><dd> An end tag was read
 * <dt><a href="#END_DOCUMENT">END_DOCUMENT</a><dd> No more events are available
 * </dl>
 *
 * <p>after first next() or nextToken() (or any other next*() method)
 * is called user application can obtain
 * XML version, standalone and encoding from XML declaration
 * in following ways:<ul>
 * <li><b>version</b>:
 *  getProperty(&quot;<a href="http://xmlpull.org/v1/doc/properties.html#xmldecl-version">http://xmlpull.org/v1/doc/properties.html#xmldecl-version</a>&quot;)
 *       returns String ("1.0") or null if XMLDecl was not read or if property is not supported
 * <li><b>standalone</b>:
 *  getProperty(&quot;<a href="http://xmlpull.org/v1/doc/features.html#xmldecl-standalone">http://xmlpull.org/v1/doc/features.html#xmldecl-standalone</a>&quot;)
 *       returns Boolean: null if there was no standalone declaration
 *  or if property is not supported
 *         otherwise returns Boolean(true) if standalon="yes" and Boolean(false) when standalone="no"
 * <li><b>encoding</b>: obtained from getInputEncoding()
 *       null if stream had unknown encoding (not set in setInputStream)
 *           and it was not declared in XMLDecl
 * </ul>
 *
 * A minimal example for using this API may look as follows:
 * <pre>
 * import java.io.IOException;
 * import java.io.StringReader;
 *
 * import org.xmlpull.v1.XmlPullParser;
 * import org.xmlpull.v1.<a href="XmlPullParserException.html">XmlPullParserException.html</a>;
 * import org.xmlpull.v1.<a href="XmlPullParserFactory.html">XmlPullParserFactory</a>;
 *
 * public class SimpleXmlPullApp
 * {
 *
 *     public static void main (String args[])
 *         throws XmlPullParserException, IOException
 *     {
 *         XmlPullParserFactory factory = XmlPullParserFactory.newInstance();
 *         factory.setNamespaceAware(true);
 *         XmlPullParser xpp = factory.newPullParser();
 *
 *         xpp.<a href="#setInput">setInput</a>( new StringReader ( "&lt;foo>Hello World!&lt;/foo>" ) );
 *         int eventType = xpp.getEventType();
 *         while (eventType != XmlPullParser.END_DOCUMENT) {
 *          if(eventType == XmlPullParser.START_DOCUMENT) {
 *              System.out.println("Start document");
 *          } else if(eventType == XmlPullParser.END_DOCUMENT) {
 *              System.out.println("End document");
 *          } else if(eventType == XmlPullParser.START_TAG) {
 *              System.out.println("Start tag "+xpp.<a href="#getName()">getName()</a>);
 *          } else if(eventType == XmlPullParser.END_TAG) {
 *              System.out.println("End tag "+xpp.getName());
 *          } else if(eventType == XmlPullParser.TEXT) {
 *              System.out.println("Text "+xpp.<a href="#getText()">getText()</a>);
 *          }
 *          eventType = xpp.next();
 *         }
 *     }
 * }
 * </pre>
 *
 * <p>The above example will generate the following output:
 * <pre>
 * Start document
 * Start tag foo
 * Text Hello World!
 * End tag foo
 * </pre>
 *
 * <p>For more details on API usage, please refer to the
 * quick Introduction available at <a href="http://www.xmlpull.org">http://www.xmlpull.org</a>
 *
 * @see XmlPullParserFactory
 * @see #defineEntityReplacementText
 * @see #getName
 * @see #getNamespace
 * @see #getText
 * @see #next
 * @see #nextToken
 * @see #setInput
 * @see #FEATURE_PROCESS_DOCDECL
 * @see #FEATURE_VALIDATION
 * @see #START_DOCUMENT
 * @see #START_TAG
 * @see #TEXT
 * @see #END_TAG
 * @see #END_DOCUMENT
 *
 * @author <a href="http://www-ai.cs.uni-dortmund.de/PERSONAL/haustein.html">Stefan Haustein</a>
 * @author <a href="http://www.extreme.indiana.edu/~aslom/">Aleksander Slominski</a>
 */

public interface XmlPullParser {

    /** This constant represents the default namespace (empty string "") */
    String NO_NAMESPACE = "";

    // ----------------------------------------------------------------------------
    // EVENT TYPES as reported by next()

    /**
     * Signalize that parser is at the very beginning of the document
     * and nothing was read yet.
     * This event type can only be observed by calling getEvent()
     * before the first call to next(), nextToken, or nextTag()</a>).
     *
     * @see #next
     * @see #nextToken
     */
    int START_DOCUMENT = 0;

    /**
     * Logical end of the xml document. Returned from getEventType, next()
     * and nextToken()
     * when the end of the input document has been reached.
     * <p><strong>NOTE:</strong> calling again
     * <a href="#next()">next()</a> or <a href="#nextToken()">nextToken()</a>
     * will result in exception being thrown.
     *
     * @see #next
     * @see #nextToken
     */
    int END_DOCUMENT = 1;

    /**
     * Returned from getEventType(),
     * <a href="#next()">next()</a>, <a href="#nextToken()">nextToken()</a> when
     * a start tag was read.
     * The name of start tag is available from getName(), its namespace and prefix are
     * available from getNamespace() and getPrefix()
     * if <a href='#FEATURE_PROCESS_NAMESPACES'>namespaces are enabled</a>.
     * See getAttribute* methods to retrieve element attributes.
     * See getNamespace* methods to retrieve newly declared namespaces.
     *
     * @see #next
     * @see #nextToken
     * @see #getName
     * @see #getPrefix
     * @see #getNamespace
     * @see #getAttributeCount
     * @see #getDepth
     * @see #getNamespaceCount
     * @see #getNamespace
     * @see #FEATURE_PROCESS_NAMESPACES
     */
    int START_TAG = 2;

    /**
     * Returned from getEventType(), <a href="#next()">next()</a>, or
     * <a href="#nextToken()">nextToken()</a> when an end tag was read.
     * The name of start tag is available from getName(), its
     * namespace and prefix are
     * available from getNamespace() and getPrefix().
     *
     * @see #next
     * @see #nextToken
     * @see #getName
     * @see #getPrefix
     * @see #getNamespace
     * @see #FEATURE_PROCESS_NAMESPACES
     */
    int END_TAG = 3;


    /**
     * Character data was read and will is available by calling getText().
     * <p><strong>Please note:</strong> <a href="#next()">next()</a> will
     * accumulate multiple
     * events into one TEXT event, skipping IGNORABLE_WHITESPACE,
     * PROCESSING_INSTRUCTION and COMMENT events,
     * In contrast, <a href="#nextToken()">nextToken()</a> will stop reading
     * text when any other event is observed.
     * Also, when the state was reached by calling next(), the text value will
     * be normalized, whereas getText() will
     * return unnormalized content in the case of nextToken(). This allows
     * an exact roundtrip without chnanging line ends when examining low
     * level events, whereas for high level applications the text is
     * normalized apropriately.
     *
     * @see #next
     * @see #nextToken
     * @see #getText
     */
    int TEXT = 4;

    // ----------------------------------------------------------------------------
    // additional events exposed by lower level nextToken()

    /**
     * A CDATA sections was just read;
     * this token is available only from calls to <a href="#nextToken()">nextToken()</a>.
     * A call to next() will accumulate various text events into a single event
     * of type TEXT. The text contained in the CDATA section is available
     * by callling getText().
     *
     * @see #nextToken
     * @see #getText
     */
    int CDSECT = 5;

    /**
     * An entity reference was just read;
     * this token is available from <a href="#nextToken()">nextToken()</a>
     * only. The entity name is available by calling getName(). If available,
     * the replacement text can be obtained by calling getTextt(); otherwise,
     * the user is responsibile for resolving the entity reference.
     * This event type is never returned from next(); next() will
     * accumulate the replacement text and other text
     * events to a single TEXT event.
     *
     * @see #nextToken
     * @see #getText
     */
    int ENTITY_REF = 6;

    /**
     * Ignorable whitespace was just read.
     * This token is available only from <a href="#nextToken()">nextToken()</a>).
     * For non-validating
     * parsers, this event is only reported by nextToken() when outside
     * the root element.
     * Validating parsers may be able to detect ignorable whitespace at
     * other locations.
     * The ignorable whitespace string is available by calling getText()
     *
     * <p><strong>NOTE:</strong> this is different from calling the
     *  isWhitespace() method, since text content
     *  may be whitespace but not ignorable.
     *
     * Ignorable whitespace is skipped by next() automatically; this event
     * type is never returned from next().
     *
     * @see #nextToken
     * @see #getText
     */
    int IGNORABLE_WHITESPACE = 7;

    /**
     * An XML processing instruction declaration was just read. This
     * event type is available only via <a href="#nextToken()">nextToken()</a>.
     * getText() will return text that is inside the processing instruction.
     * Calls to next() will skip processing instructions automatically.
     * @see #nextToken
     * @see #getText
     */
    int PROCESSING_INSTRUCTION = 8;

    /**
     * An XML comment was just read. This event type is this token is
     * available via <a href="#nextToken()">nextToken()</a> only;
     * calls to next() will skip comments automatically.
     * The content of the comment can be accessed using the getText()
     * method.
     *
     * @see #nextToken
     * @see #getText
     */
    int COMMENT = 9;

    /**
     * An XML document type declaration was just read. This token is
     * available from <a href="#nextToken()">nextToken()</a> only.
     * The unparsed text inside the doctype is available via
     * the getText() method.
     *
     * @see #nextToken
     * @see #getText
     */
    int DOCDECL = 10;

    /**
     * This array can be used to convert the event type integer constants
     * such as START_TAG or TEXT to
     * to a string. For example, the value of TYPES[START_TAG] is
     * the string "START_TAG".
     *
     * This array is intended for diagnostic output only. Relying
     * on the contents of the array may be dangerous since malicous
     * applications may alter the array, although it is final, due
     * to limitations of the Java language.
     */
    String [] TYPES = {
        "START_DOCUMENT",
            "END_DOCUMENT",
            "START_TAG",
            "END_TAG",
            "TEXT",
            "CDSECT",
            "ENTITY_REF",
            "IGNORABLE_WHITESPACE",
            "PROCESSING_INSTRUCTION",
            "COMMENT",
            "DOCDECL"
    };


    // ----------------------------------------------------------------------------
    // namespace related features

    /**
     * This feature determines whether the parser processes
     * namespaces. As for all features, the default value is false.
     * <p><strong>NOTE:</strong> The value can not be changed during
     * parsing an must be set before parsing.
     *
     * @see #getFeature
     * @see #setFeature
     */
    String FEATURE_PROCESS_NAMESPACES =
        "http://xmlpull.org/v1/doc/features.html#process-namespaces";

    /**
     * This feature determines whether namespace attributes are
     * exposed via the attribute access methods. Like all features,
     * the default value is false. This feature cannot be changed
     * during parsing.
     *
     * @see #getFeature
     * @see #setFeature
     */
    String FEATURE_REPORT_NAMESPACE_ATTRIBUTES =
        "http://xmlpull.org/v1/doc/features.html#report-namespace-prefixes";

    /**
     * This feature determines whether the document declaration