xincludetextreader.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 524 行 · 第 1/2 页

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 2001-2004 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation and was
 * originally based on software copyright (c) 2003, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

package com.sun.org.apache.xerces.internal.xinclude;

import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;
import java.util.Locale;

import com.sun.org.apache.xerces.internal.impl.io.ASCIIReader;
import com.sun.org.apache.xerces.internal.impl.io.UTF8Reader;
import com.sun.org.apache.xerces.internal.impl.msg.XMLMessageFormatter;
import com.sun.org.apache.xerces.internal.impl.XMLEntityManager;
import com.sun.org.apache.xerces.internal.impl.XMLErrorReporter;
import com.sun.org.apache.xerces.internal.util.EncodingMap;
import com.sun.org.apache.xerces.internal.util.MessageFormatter;
import com.sun.org.apache.xerces.internal.util.XMLChar;
import com.sun.org.apache.xerces.internal.util.XMLStringBuffer;
import com.sun.org.apache.xerces.internal.xni.parser.XMLInputSource;

/**
 * This class is used for reading resources requested in &lt;include&gt; elements,
 * when the parse attribute of the &lt;include&gt; element is "text".  Using this
 * class will open the location, detect the encoding, and discard the byte order
 * mark, if applicable.
 * 
 * REVISIT:
 * Much of the code in this class is taken from XMLEntityManager.  It would be nice
 * if this code could be shared in some way.  However, since XMLEntityManager is used
 * for reading files as XML, and this needs to read files as text, there would need
 * to be some refactoring done.
 * 
 * @author Michael Glavassevich, IBM
 * @author Peter McCracken, IBM
 * @author Arun Yadav, Sun Microsystems Inc.
 *
 * @version $Id: XIncludeTextReader.java,v 1.10 2004/04/15 04:51:56 mrglavas Exp $
 *
 * @see XIncludeHandler
 */
public class XIncludeTextReader {

    private Reader fReader;
    private XIncludeHandler fHandler;
    private XMLInputSource fSource;
    private XMLErrorReporter fErrorReporter;
    
    // Content negotation parameters
    private String fAccept;
    private String fAcceptLanguage;
 
    /**
     * Construct the XIncludeReader using the XMLInputSource and XIncludeHandler.
     *
     * @param source The XMLInputSource to use.
     * @param handler The XIncludeHandler to use.
     */
    public XIncludeTextReader(XMLInputSource source, XIncludeHandler handler)
        throws IOException {
        fHandler = handler;
        fSource = source;
    }
    
    /**
     * Sets the XMLErrorReporter used for reporting errors while
     * reading the text include.
     *
     * @param errorReporter the XMLErrorReporter to be used for
     * reporting errors.
     */
    public void setErrorReporter(XMLErrorReporter errorReporter) {
        fErrorReporter = errorReporter;
    }
    
    /**
     * Sets content negotation parameters to be attached to an HTTP request.
     * 
     * @param accept the Accept HTTP request property
     * @param acceptLanguage the Accept-Language HTTP request property
     */
    public void setHttpProperties(String accept, String acceptLanguage) {
        fAccept = accept;
        fAcceptLanguage = acceptLanguage;
    }

    /**
     * Return the Reader for given XMLInputSource.
     *
     * @param source The XMLInputSource to use.
     */
    protected Reader getReader(XMLInputSource source) throws IOException {
        if (source.getCharacterStream() != null) {
            return source.getCharacterStream();
        }
        else {
            InputStream stream = null;

            String encoding = source.getEncoding();
            if (encoding == null) {
                encoding = "UTF-8";
            }
            if (source.getByteStream() != null) {
                stream = source.getByteStream();
                // Wrap the InputStream so that it is possible to rewind it.
                if (!(stream instanceof BufferedInputStream)) {
                    stream = new BufferedInputStream(stream);
                }
            }
            else {
                String expandedSystemId = XMLEntityManager.expandSystemId(source.getSystemId(), source.getBaseSystemId(), false);

                URL url = new URL(expandedSystemId);
                URLConnection urlCon = url.openConnection();
				
                // If this is an HTTP connection attach any 
                // content negotation parameters to the request.
                if (urlCon instanceof HttpURLConnection) {
                    if( fAccept != null && fAccept.length() > 0) {
                        urlCon.setRequestProperty(XIncludeHandler.HTTP_ACCEPT, fAccept);
                    }
                    if( fAcceptLanguage != null && fAcceptLanguage.length() > 0) {
                        urlCon.setRequestProperty(XIncludeHandler.HTTP_ACCEPT_LANGUAGE, fAcceptLanguage);
                    }
                }
                
                // Wrap the InputStream so that it is possible to rewind it.
                stream = new BufferedInputStream(urlCon.getInputStream());
                
                // content type will be string like "text/xml; charset=UTF-8" or "text/xml"
                String rawContentType = urlCon.getContentType();
                
                // text/xml and application/xml offer only one optional parameter
                int index = (rawContentType != null) ? rawContentType.indexOf(';') : -1;

                String contentType = null;
                String charset = null;
                if (index != -1) {
                    // this should be something like "text/xml"
                    contentType = rawContentType.substring(0, index).trim();

                    // this should be something like "charset=UTF-8", but we want to
                    // strip it down to just "UTF-8"
                    charset = rawContentType.substring(index + 1).trim();
                    if (charset.startsWith("charset=")) {
                        // 8 is the length of "charset="
                        charset = charset.substring(8).trim();
                        // strip quotes, if present
                        if ((charset.charAt(0) == '"'
                            && charset.charAt(charset.length() - 1) == '"')
                            || (charset.charAt(0) == '\''
                                && charset.charAt(charset.length() - 1)
                                    == '\'')) {
                            charset =
                                charset.substring(1, charset.length() - 1);
                        }
                    }
                    else {
                        charset = null;
                    }
                }
                else {
                    contentType = rawContentType.trim();
                }

                String detectedEncoding = null;
                /**  The encoding of such a resource is determined by:
                    1 external encoding information, if available, otherwise
                         -- the most common type of external information is the "charset" parameter of a MIME package
                    2 if the media type of the resource is text/xml, application/xml, or matches the conventions text/*+xml or application/*+xml as described in XML Media Types [IETF RFC 3023], the encoding is recognized as specified in XML 1.0, otherwise
                    3 the value of the encoding attribute if one exists, otherwise
                    4 UTF-8.
                 **/
                if (contentType.equals("text/xml")) {
                    if (charset != null) {
                        detectedEncoding = charset;
                    }
                    else {
                        // see RFC2376 or 3023, section 3.1
                        detectedEncoding = "US-ASCII";
                    }
                }
                else if (contentType.equals("application/xml")) {
                    if (charset != null) {
                        detectedEncoding = charset;
                    }
                    else {
                        // see RFC2376 or 3023, section 3.2
                        detectedEncoding = getEncodingName(stream);
                    }
                }
                else if (contentType.endsWith("+xml")) {
                    detectedEncoding = getEncodingName(stream);
                }

                if (detectedEncoding != null) {
                    encoding = detectedEncoding;
                }
                // else 3 or 4.
            }
            
            encoding = encoding.toUpperCase(Locale.ENGLISH);