xincludetextreader.java

来自「JAVA 所有包」· Java 代码 · 共 514 行 · 第 1/2 页

/*
 * Copyright 2003-2005 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.
 */
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.Iterator;
import java.util.Locale;
import java.util.Map;

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.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.util.EncodingMap;
import com.sun.org.apache.xerces.internal.util.HTTPInputSource;
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.xni.XMLString;
import com.sun.org.apache.xerces.internal.xni.parser.XMLInputSource;

/**
 * This class is used for reading resources requested in <include> elements,
 * when the parse attribute of the <include> 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 Ankit Pasricha, IBM
 * @author Arun Yadav, Sun Microsystems Inc.
 *
 * @version $Id: XIncludeTextReader.java,v 1.3 2005/09/26 13:03:04 sunithareddy Exp $
 *
 * @see XIncludeHandler
 */
public class XIncludeTextReader {

    private Reader fReader;
    private XIncludeHandler fHandler;
    private XMLInputSource fSource;
    private XMLErrorReporter fErrorReporter;
    private XMLString fTempString = new XMLString();
 
    /**
     * Construct the XIncludeReader using the XMLInputSource and XIncludeHandler.
     *
     * @param source The XMLInputSource to use.
     * @param handler The XIncludeHandler to use.
     * @param bufferSize The size of this text reader's buffer.
     */
    public XIncludeTextReader(XMLInputSource source, XIncludeHandler handler, int bufferSize)
        throws IOException {
        fHandler = handler;
        fSource = source;
        fTempString = new XMLString(new char[bufferSize + 1], 0, 0);
    }
    
    /**
     * 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;
    }

    /**
     * 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, fTempString.ch.length);
                }
            }
            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 request properties to the request.
                if (urlCon instanceof HttpURLConnection && source instanceof HTTPInputSource) {
                    final HttpURLConnection urlConnection = (HttpURLConnection) urlCon;
                    final HTTPInputSource httpInputSource = (HTTPInputSource) source;
                    
                    // set request properties
                    Iterator propIter = httpInputSource.getHTTPRequestProperties();
                    while (propIter.hasNext()) {
                        Map.Entry entry = (Map.Entry) propIter.next();
                        urlConnection.setRequestProperty((String) entry.getKey(), (String) entry.getValue());
                    }
                    
                    // set preference for redirection
                    boolean followRedirects = httpInputSource.getFollowHTTPRedirects();
                    if (!followRedirects) {
                        XMLEntityManager.setInstanceFollowRedirects(urlConnection, followRedirects);
                    }
                }
                
                // 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);
            
            // eat the Byte Order Mark
            encoding = consumeBOM(stream, encoding);
            
            // If the document is UTF-8 or US-ASCII use 
            // the Xerces readers for these encodings. For
            // US-ASCII consult the encoding map since
            // this encoding has many aliases.
            if (encoding.equals("UTF-8")) {
                return new UTF8Reader(stream, 
                    fTempString.ch.length, 
                    fErrorReporter.getMessageFormatter(XMLMessageFormatter.XML_DOMAIN), 
                    fErrorReporter.getLocale() );
            }
            
            // Try to use a Java reader.
            String javaEncoding = EncodingMap.getIANA2JavaMapping(encoding);
            
            // If the specified encoding wasn't a recognized IANA encoding throw an IOException.
            // The XIncludeHandler will report this as a ResourceError and then will
            // attempt to include a fallback if there is one.
            if (javaEncoding == null) {
                MessageFormatter aFormatter = 
                    fErrorReporter.getMessageFormatter(XMLMessageFormatter.XML_DOMAIN);
                Locale aLocale = fErrorReporter.getLocale();
                throw new IOException( aFormatter.formatMessage( aLocale, 
                    "EncodingDeclInvalid", 
                    new Object[] {encoding} ) );
            }
            else if (javaEncoding.equals("ASCII")) {
                return new ASCIIReader(stream,
                    fTempString.ch.length,
                    fErrorReporter.getMessageFormatter(XMLMessageFormatter.XML_DOMAIN), 
                    fErrorReporter.getLocale() );
            }
            
            return new InputStreamReader(stream, javaEncoding);
        }