xmlwriter.java

解决如何把XML应用到JAVA里问题

/*
 * Copyright 2001-2005 (C) MetaStuff, Ltd. All Rights Reserved.
 *
 * This software is open source.
 * See the bottom of this file for the licence.
 */

package org.dom4j.io;

import java.io.BufferedWriter;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.StringTokenizer;

import org.dom4j.Attribute;
import org.dom4j.CDATA;
import org.dom4j.Comment;
import org.dom4j.Document;
import org.dom4j.DocumentType;
import org.dom4j.Element;
import org.dom4j.Entity;
import org.dom4j.Namespace;
import org.dom4j.Node;
import org.dom4j.ProcessingInstruction;
import org.dom4j.Text;
import org.dom4j.tree.NamespaceStack;

import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXNotRecognizedException;
import org.xml.sax.SAXNotSupportedException;
import org.xml.sax.XMLReader;
import org.xml.sax.ext.LexicalHandler;
import org.xml.sax.helpers.XMLFilterImpl;

/**
 * <p>
 * <code>XMLWriter</code> takes a DOM4J tree and formats it to a stream as
 * XML. It can also take SAX events too so can be used by SAX clients as this
 * object implements the {@link org.xml.sax.ContentHandler}and {@link
 * LexicalHandler} interfaces. as well. This formatter performs typical document
 * formatting. The XML declaration and processing instructions are always on
 * their own lines. An {@link OutputFormat}object can be used to define how
 * whitespace is handled when printing and allows various configuration options,
 * such as to allow suppression of the XML declaration, the encoding declaration
 * or whether empty documents are collapsed.
 * </p>
 * 
 * <p>
 * There are <code>write(...)</code> methods to print any of the standard
 * DOM4J classes, including <code>Document</code> and <code>Element</code>,
 * to either a <code>Writer</code> or an <code>OutputStream</code>.
 * Warning: using your own <code>Writer</code> may cause the writer's
 * preferred character encoding to be ignored. If you use encodings other than
 * UTF8, we recommend using the method that takes an OutputStream instead.
 * </p>
 * 
 * @author <a href="mailto:[e-mail]">James Strachan </a>
 * @author Joseph Bowbeer
 * @version $Revision: 1.83.2.2 $
 */
public class XMLWriter extends XMLFilterImpl implements LexicalHandler {
    private static final String PAD_TEXT = " ";

    protected static final String[] LEXICAL_HANDLER_NAMES = {
            "http://xml.org/sax/properties/lexical-handler",
            "http://xml.org/sax/handlers/LexicalHandler"};

    protected static final OutputFormat DEFAULT_FORMAT = new OutputFormat();

    /** Should entityRefs by resolved when writing ? */
    private boolean resolveEntityRefs = true;

    /**
     * Stores the last type of node written so algorithms can refer to the
     * previous node type
     */
    protected int lastOutputNodeType;

    /**
     * Stores if the last written element node was a closing tag or an opening
     * tag.
     */
    private boolean lastElementClosed = false;

    /** Stores the xml:space attribute value of preserve for whitespace flag */
    protected boolean preserve = false;

    /** The Writer used to output to */
    protected Writer writer;

    /** The Stack of namespaceStack written so far */
    private NamespaceStack namespaceStack = new NamespaceStack();

    /** The format used by this writer */
    private OutputFormat format;

    /** whether we should escape text */
    private boolean escapeText = true;

    /**
     * The initial number of indentations (so you can print a whole document
     * indented, if you like)
     */
    private int indentLevel = 0;

    /** buffer used when escaping strings */
    private StringBuffer buffer = new StringBuffer();

    /**
     * whether we have added characters before from the same chunk of characters
     */
    private boolean charsAdded = false;

    private char lastChar;

    /** Whether a flush should occur after writing a document */
    private boolean autoFlush;

    /** Lexical handler we should delegate to */
    private LexicalHandler lexicalHandler;

    /**
     * Whether comments should appear inside DTD declarations - defaults to
     * false
     */
    private boolean showCommentsInDTDs;

    /** Is the writer curerntly inside a DTD definition? */
    private boolean inDTD;

    /** The namespaces used for the current element when consuming SAX events */
    private Map namespacesMap;

    /**
     * what is the maximum allowed character code such as 127 in US-ASCII (7
     * bit) or 255 in ISO- (8 bit) or -1 to not escape any characters (other
     * than the special XML characters like &lt; &gt; &amp;)
     */
    private int maximumAllowedCharacter;

    public XMLWriter(Writer writer) {
        this(writer, DEFAULT_FORMAT);
    }

    public XMLWriter(Writer writer, OutputFormat format) {
        this.writer = writer;
        this.format = format;
        namespaceStack.push(Namespace.NO_NAMESPACE);
    }

    public XMLWriter() {
        this.format = DEFAULT_FORMAT;
        this.writer = new BufferedWriter(new OutputStreamWriter(System.out));
        this.autoFlush = true;
        namespaceStack.push(Namespace.NO_NAMESPACE);
    }

    public XMLWriter(OutputStream out) throws UnsupportedEncodingException {
        this.format = DEFAULT_FORMAT;
        this.writer = createWriter(out, format.getEncoding());
        this.autoFlush = true;
        namespaceStack.push(Namespace.NO_NAMESPACE);
    }

    public XMLWriter(OutputStream out, OutputFormat format)
            throws UnsupportedEncodingException {
        this.format = format;
        this.writer = createWriter(out, format.getEncoding());
        this.autoFlush = true;
        namespaceStack.push(Namespace.NO_NAMESPACE);
    }

    public XMLWriter(OutputFormat format) throws UnsupportedEncodingException {
        this.format = format;
        this.writer = createWriter(System.out, format.getEncoding());
        this.autoFlush = true;
        namespaceStack.push(Namespace.NO_NAMESPACE);
    }

    public void setWriter(Writer writer) {
        this.writer = writer;
        this.autoFlush = false;
    }

    public void setOutputStream(OutputStream out)
            throws UnsupportedEncodingException {
        this.writer = createWriter(out, format.getEncoding());
        this.autoFlush = true;
    }

    /**
     * DOCUMENT ME!
     * 
     * @return true if text thats output should be escaped. This is enabled by
     *         default. It could be disabled if the output format is textual,
     *         like in XSLT where we can have xml, html or text output.
     */
    public boolean isEscapeText() {
        return escapeText;
    }

    /**
     * Sets whether text output should be escaped or not. This is enabled by
     * default. It could be disabled if the output format is textual, like in
     * XSLT where we can have xml, html or text output.
     * 
     * @param escapeText
     *            DOCUMENT ME!
     */
    public void setEscapeText(boolean escapeText) {
        this.escapeText = escapeText;
    }

    /**
     * Set the initial indentation level. This can be used to output a document
     * (or, more likely, an element) starting at a given indent level, so it's
     * not always flush against the left margin. Default: 0
     * 
     * @param indentLevel
     *            the number of indents to start with
     */
    public void setIndentLevel(int indentLevel) {
        this.indentLevel = indentLevel;
    }

    /**
     * Returns the maximum allowed character code that should be allowed
     * unescaped which defaults to 127 in US-ASCII (7 bit) or 255 in ISO- (8
     * bit).
     * 
     * @return DOCUMENT ME!
     */
    public int getMaximumAllowedCharacter() {
        if (maximumAllowedCharacter == 0) {
            maximumAllowedCharacter = defaultMaximumAllowedCharacter();
        }

        return maximumAllowedCharacter;
    }

    /**
     * Sets the maximum allowed character code that should be allowed unescaped
     * such as 127 in US-ASCII (7 bit) or 255 in ISO- (8 bit) or -1 to not
     * escape any characters (other than the special XML characters like &lt;
     * &gt; &amp;) If this is not explicitly set then it is defaulted from the
     * encoding.
     * 
     * @param maximumAllowedCharacter
     *            The maximumAllowedCharacter to set
     */
    public void setMaximumAllowedCharacter(int maximumAllowedCharacter) {
        this.maximumAllowedCharacter = maximumAllowedCharacter;
    }

    /**
     * Flushes the underlying Writer
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void flush() throws IOException {
        writer.flush();
    }

    /**
     * Closes the underlying Writer
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void close() throws IOException {
        writer.close();
    }

    /**
     * Writes the new line text to the underlying Writer
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void println() throws IOException {
        writer.write(format.getLineSeparator());
    }

    /**
     * Writes the given {@link Attribute}.
     * 
     * @param attribute
     *            <code>Attribute</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(Attribute attribute) throws IOException {
        writeAttribute(attribute);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * <p>
     * This will print the <code>Document</code> to the current Writer.
     * </p>
     * 
     * <p>
     * Warning: using your own Writer may cause the writer's preferred character
     * encoding to be ignored. If you use encodings other than UTF8, we
     * recommend using the method that takes an OutputStream instead.
     * </p>
     * 
     * <p>
     * Note: as with all Writers, you may need to flush() yours after this
     * method returns.
     * </p>
     * 
     * @param doc
     *            <code>Document</code> to format.
     * 
     * @throws IOException
     *             if there's any problem writing.
     */
    public void write(Document doc) throws IOException {
        writeDeclaration();

        if (doc.getDocType() != null) {
            indent();
            writeDocType(doc.getDocType());
        }

        for (int i = 0, size = doc.nodeCount(); i < size; i++) {
            Node node = doc.node(i);
            writeNode(node);
        }

        writePrintln();

        if (autoFlush) {
            flush();
        }
    }

    /**
     * <p>
     * Writes the <code>{@link Element}</code>, including its <code>{@link
     * Attribute}</code>
     * s, and its value, and all its content (child nodes) to the current
     * Writer.
     * </p>
     * 
     * @param element
     *            <code>Element</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(Element element) throws IOException {
        writeElement(element);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link CDATA}.
     * 
     * @param cdata
     *            <code>CDATA</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(CDATA cdata) throws IOException {
        writeCDATA(cdata.getText());

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link Comment}.
     * 
     * @param comment
     *            <code>Comment</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(Comment comment) throws IOException {
        writeComment(comment.getText());

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link DocumentType}.
     * 
     * @param docType
     *            <code>DocumentType</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(DocumentType docType) throws IOException {
        writeDocType(docType);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link Entity}.
     * 
     * @param entity
     *            <code>Entity</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(Entity entity) throws IOException {
        writeEntity(entity);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link Namespace}.
     * 
     * @param namespace
     *            <code>Namespace</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(Namespace namespace) throws IOException {
        writeNamespace(namespace);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * Writes the given {@link ProcessingInstruction}.
     * 
     * @param processingInstruction
     *            <code>ProcessingInstruction</code> to output.
     * 
     * @throws IOException
     *             DOCUMENT ME!
     */
    public void write(ProcessingInstruction processingInstruction)
            throws IOException {
        writeProcessingInstruction(processingInstruction);

        if (autoFlush) {
            flush();
        }
    }

    /**
     * <p>
     * Print out a {@link String}, Perfoms the necessary entity escaping and
     * whitespace stripping.
     * </p>
     *