tostream.java

来自「JAVA 所有包」· Java 代码 · 共 2,016 行 · 第 1/5 页

/*
 * Copyright 2001-2004 The Apache Software Foundation.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
/*
 * $Id: ToStream.java,v 1.4 2005/11/10 06:43:26 suresh_emailid Exp $
 */
package com.sun.org.apache.xml.internal.serializer;

import java.io.IOException;
import java.io.OutputStream;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
import java.util.Properties;
import java.util.StringTokenizer;
import java.util.Vector;

import javax.xml.transform.ErrorListener;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerException;

import com.sun.org.apache.xml.internal.serializer.utils.MsgKey;
import com.sun.org.apache.xml.internal.serializer.utils.Utils;
import com.sun.org.apache.xml.internal.serializer.utils.WrappedRuntimeException;
import org.w3c.dom.Node;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;

//import com.sun.media.sound.IESecurity;

/**
 * This abstract class is a base class for other stream 
 * serializers (xml, html, text ...) that write output to a stream.
 * 
 * @xsl.usage internal
 */
abstract public class ToStream extends SerializerBase
{

    private static final String COMMENT_BEGIN = "<!--";
    private static final String COMMENT_END = "-->";

    /** Stack to keep track of disabling output escaping. */
    protected BoolStack m_disableOutputEscapingStates = new BoolStack();


    /**
     * The encoding information associated with this serializer.
     * Although initially there is no encoding,
     * there is a dummy EncodingInfo object that will say
     * that every character is in the encoding. This is useful
     * for a serializer that is in temporary output state and has
     * no associated encoding. A serializer in final output state
     * will have an encoding, and will worry about whether 
     * single chars or surrogate pairs of high/low chars form
     * characters in the output encoding. 
     */
    EncodingInfo m_encodingInfo = new EncodingInfo(null,null);
    
    /**
     * Method reference to the sun.io.CharToByteConverter#canConvert method
     * for this encoding.  Invalid if m_charToByteConverter is null.
     */
    java.lang.reflect.Method m_canConvertMeth;



    /**
     * Boolean that tells if we already tried to get the converter.
     */
    boolean m_triedToGetConverter = false;


    /**
     * Opaque reference to the sun.io.CharToByteConverter for this
     * encoding.
     */
    Object m_charToByteConverter = null;
 
 
    /**
     * Stack to keep track of whether or not we need to
     * preserve whitespace.
     * 
     * Used to push/pop values used for the field m_ispreserve, but
     * m_ispreserve is only relevant if m_doIndent is true.
     * If m_doIndent is false this field has no impact.
     * 
     */
    protected BoolStack m_preserves = new BoolStack();

    /**
     * State flag to tell if preservation of whitespace
     * is important. 
     * 
     * Used only in shouldIndent() but only if m_doIndent is true.
     * If m_doIndent is false this flag has no impact.
     * 
     */
    protected boolean m_ispreserve = false;

    /**
     * State flag that tells if the previous node processed
     * was text, so we can tell if we should preserve whitespace.
     * 
     * Used in endDocument() and shouldIndent() but
     * only if m_doIndent is true. 
     * If m_doIndent is false this flag has no impact.
     */
    protected boolean m_isprevtext = false;

    /**
     * The maximum character size before we have to resort
     * to escaping.
     */
    protected int m_maxCharacter = Encodings.getLastPrintable();


    /**
     * The system line separator for writing out line breaks.
     * The default value is from the system property,
     * but this value can be set through the xsl:output
     * extension attribute xalan:line-separator.
     */
    protected char[] m_lineSep =
        System.getProperty("line.separator").toCharArray();
        
    /**
     * True if the the system line separator is to be used.
     */    
    protected boolean m_lineSepUse = true;    

    /**
     * The length of the line seperator, since the write is done
     * one character at a time.
     */
    protected int m_lineSepLen = m_lineSep.length;

    /**
     * Map that tells which characters should have special treatment, and it
     *  provides character to entity name lookup.
     */
    protected CharInfo m_charInfo;

    /** True if we control the buffer, and we should flush the output on endDocument. */
    boolean m_shouldFlush = true;

    /**
     * Add space before '/>' for XHTML.
     */
    protected boolean m_spaceBeforeClose = false;

    /**
     * Flag to signal that a newline should be added.
     * 
     * Used only in indent() which is called only if m_doIndent is true.
     * If m_doIndent is false this flag has no impact.
     */
    boolean m_startNewLine;

    /**
     * Tells if we're in an internal document type subset.
     */
    protected boolean m_inDoctype = false;

    /**
       * Flag to quickly tell if the encoding is UTF8.
       */
    boolean m_isUTF8 = false;

    /** The xsl:output properties. */
    protected Properties m_format;

    /**
     * remembers if we are in between the startCDATA() and endCDATA() callbacks
     */
    protected boolean m_cdataStartCalled = false;
    
    /**
     * If this flag is true DTD entity references are not left as-is,
     * which is exiting older behavior.
     */
    private boolean m_expandDTDEntities = true;
  

    /**
     * Default constructor
     */
    public ToStream()
    {
    }

    /**
     * This helper method to writes out "]]>" when closing a CDATA section.
     *
     * @throws org.xml.sax.SAXException
     */
    protected void closeCDATA() throws org.xml.sax.SAXException
    {
        try
        {
            m_writer.write(CDATA_DELIMITER_CLOSE);
            // write out a CDATA section closing "]]>"
            m_cdataTagOpen = false; // Remember that we have done so.
        }
        catch (IOException e)
        {
            throw new SAXException(e);
        }
    }

    /**
     * Serializes the DOM node. Throws an exception only if an I/O
     * exception occured while serializing.
     *
     * @param node Node to serialize.
     * @throws IOException An I/O exception occured while serializing
     */
    public void serialize(Node node) throws IOException
    {

        try
        {
            TreeWalker walker =
                new TreeWalker(this);

            walker.traverse(node);
        }
        catch (org.xml.sax.SAXException se)
        {
            throw new WrappedRuntimeException(se);
        }
    }

    /**
     * Return true if the character is the high member of a surrogate pair.
     *
     * NEEDSDOC @param c
     *
     * NEEDSDOC ($objectName$) @return
     */
    static final boolean isUTF16Surrogate(char c)
    {
        return (c & 0xFC00) == 0xD800;
    }

    /**
     * Taken from XSLTC 
     */
    private boolean m_escaping = true;

    /**
     * Flush the formatter's result stream.
     *
     * @throws org.xml.sax.SAXException
     */
    protected final void flushWriter() throws org.xml.sax.SAXException
    {
        final java.io.Writer writer = m_writer;
        if (null != writer)
        {
            try
            {
                if (writer instanceof WriterToUTF8Buffered)
                {
                    if (m_shouldFlush)
                         ((WriterToUTF8Buffered) writer).flush();
                    else
                         ((WriterToUTF8Buffered) writer).flushBuffer();
                }
                if (writer instanceof WriterToASCI)
                {
                    if (m_shouldFlush)
                        writer.flush();
                }
                else
                {
                    // Flush always. 
                    // Not a great thing if the writer was created 
                    // by this class, but don't have a choice.
                    writer.flush();
                }
            }
            catch (IOException ioe)
            {
                throw new org.xml.sax.SAXException(ioe);
            }
        }
    }

    /**
     * Get the output stream where the events will be serialized to.
     *
     * @return reference to the result stream, or null of only a writer was
     * set.
     */
    public OutputStream getOutputStream()
    {

        if (m_writer instanceof WriterToUTF8Buffered)
            return ((WriterToUTF8Buffered) m_writer).getOutputStream();
        if (m_writer instanceof WriterToASCI)
            return ((WriterToASCI) m_writer).getOutputStream();
        else
            return null;
    }

    // Implement DeclHandler

    /**
     *   Report an element type declaration.
     *  
     *   <p>The content model will consist of the string "EMPTY", the
     *   string "ANY", or a parenthesised group, optionally followed
     *   by an occurrence indicator.  The model will be normalized so
     *   that all whitespace is removed,and will include the enclosing
     *   parentheses.</p>
     *  
     *   @param name The element type name.
     *   @param model The content model as a normalized string.
     *   @exception SAXException The application may raise an exception.
     */
    public void elementDecl(String name, String model) throws SAXException
    {
        // Do not inline external DTD
        if (m_inExternalDTD)
            return;
        try
        {
            final java.io.Writer writer = m_writer;
            DTDprolog();

            writer.write("<!ELEMENT ");
            writer.write(name);
            writer.write(' ');
            writer.write(model);
            writer.write('>');
            writer.write(m_lineSep, 0, m_lineSepLen);
        }
        catch (IOException e)
        {
            throw new SAXException(e);
        }

    }

    /**
     * Report an internal entity declaration.
     *
     * <p>Only the effective (first) declaration for each entity
     * will be reported.</p>
     *
     * @param name The name of the entity.  If it is a parameter
     *        entity, the name will begin with '%'.
     * @param value The replacement text of the entity.
     * @exception SAXException The application may raise an exception.
     * @see #externalEntityDecl
     * @see org.xml.sax.DTDHandler#unparsedEntityDecl
     */
    public void internalEntityDecl(String name, String value)
        throws SAXException
    {
        // Do not inline external DTD
        if (m_inExternalDTD)
            return;
        try
        {
            DTDprolog();
            outputEntityDecl(name, value);
        }
        catch (IOException e)
        {
            throw new SAXException(e);
        }

    }

    /**
     * Output the doc type declaration.
     *
     * @param name non-null reference to document type name.
     * NEEDSDOC @param value
     *
     * @throws org.xml.sax.SAXException
     */
    void outputEntityDecl(String name, String value) throws IOException
    {
        final java.io.Writer writer = m_writer;
        writer.write("<!ENTITY ");
        writer.write(name);
        writer.write(" \"");