xml11serializer.java
来自「JAVA 所有包」· Java 代码 · 共 539 行 · 第 1/2 页
JAVA
539 行
/* * Copyright 1999-2002,2004,2005 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. */// Sep 14, 2000:// Fixed problem with namespace handling. Contributed by// David Blondeau <blondeau@intalio.com>// Sep 14, 2000:// Fixed serializer to report IO exception directly, instead at// the end of document processing.// Reported by Patrick Higgins <phiggins@transzap.com>// Aug 21, 2000:// Fixed bug in startDocument not calling prepare.// Reported by Mikael Staldal <d96-mst-ingen-reklam@d.kth.se>// Aug 21, 2000:// Added ability to omit DOCTYPE declaration.package com.sun.org.apache.xml.internal.serialize;import java.io.IOException;import java.io.OutputStream;import java.io.Writer;import com.sun.org.apache.xerces.internal.dom.DOMMessageFormatter;import com.sun.org.apache.xerces.internal.impl.Constants;import com.sun.org.apache.xerces.internal.util.NamespaceSupport;import com.sun.org.apache.xerces.internal.util.SymbolTable;import com.sun.org.apache.xerces.internal.util.XML11Char;import com.sun.org.apache.xerces.internal.util.XMLChar;import org.xml.sax.SAXException;import org.w3c.dom.DOMError;/** * Implements an XML serializer supporting both DOM and SAX pretty * serializing. For usage instructions see {@link Serializer}. * <p> * If an output stream is used, the encoding is taken from the * output format (defaults to <tt>UTF-8</tt>). If a writer is * used, make sure the writer uses the same encoding (if applies) * as specified in the output format. * <p> * The serializer supports both DOM and SAX. SAX serializing is done by firing * SAX events and using the serializer as a document handler. DOM serializing is done * by calling {@link #serialize(Document)} or by using DOM Level 3 * {@link org.w3c.dom.ls.DOMSerializer} and * serializing with {@link org.w3c.dom.ls.DOMSerializer#write}, * {@link org.w3c.dom.ls.DOMSerializer#writeToString}. * <p> * If an I/O exception occurs while serializing, the serializer * will not throw an exception directly, but only throw it * at the end of serializing (either DOM or SAX's {@link * org.xml.sax.DocumentHandler#endDocument}. * <p> * For elements that are not specified as whitespace preserving, * the serializer will potentially break long text lines at space * boundaries, indent lines, and serialize elements on separate * lines. Line terminators will be regarded as spaces, and * spaces at beginning of line will be stripped. * @author <a href="mailto:arkin@intalio.com">Assaf Arkin</a> * @author <a href="mailto:rahul.srivastava@sun.com">Rahul Srivastava</a> * @author Elena Litani IBM * @version $Revision: 1.2.6.1 $ $Date: 2005/09/09 07:26:18 $ * @see Serializer */public class XML11Serializerextends XMLSerializer { // // constants // protected static final boolean DEBUG = false; // // data // // // DOM Level 3 implementation: variables intialized in DOMSerializerImpl // /** stores namespaces in scope */ protected NamespaceSupport fNSBinder; /** stores all namespace bindings on the current element */ protected NamespaceSupport fLocalNSBinder; /** symbol table for serialization */ protected SymbolTable fSymbolTable; // is node dom level 1 node? protected boolean fDOML1 = false; // counter for new prefix names protected int fNamespaceCounter = 1; protected final static String PREFIX = "NS"; /** * Controls whether namespace fixup should be performed during * the serialization. * NOTE: if this field is set to true the following * fields need to be initialized: fNSBinder, fLocalNSBinder, fSymbolTable, * XMLSymbols.EMPTY_STRING, fXmlSymbol, fXmlnsSymbol, fNamespaceCounter. */ protected boolean fNamespaces = false; private boolean fPreserveSpace; /** * Constructs a new serializer. The serializer cannot be used without * calling {@link #setOutputCharStream} or {@link #setOutputByteStream} * first. */ public XML11Serializer() { super( ); _format.setVersion("1.1"); } /** * Constructs a new serializer. The serializer cannot be used without * calling {@link #setOutputCharStream} or {@link #setOutputByteStream} * first. */ public XML11Serializer( OutputFormat format ) { super( format ); _format.setVersion("1.1"); } /** * Constructs a new serializer that writes to the specified writer * using the specified output format. If <tt>format</tt> is null, * will use a default output format. * * @param writer The writer to use * @param format The output format to use, null for the default */ public XML11Serializer( Writer writer, OutputFormat format ) { super( writer, format ); _format.setVersion("1.1"); } /** * Constructs a new serializer that writes to the specified output * stream using the specified output format. If <tt>format</tt> * is null, will use a default output format. * * @param output The output stream to use * @param format The output format to use, null for the default */ public XML11Serializer( OutputStream output, OutputFormat format ) { super( output, format != null ? format : new OutputFormat( Method.XML, null, false ) ); _format.setVersion("1.1"); } //-----------------------------------------// // SAX content handler serializing methods // //-----------------------------------------// public void characters( char[] chars, int start, int length ) throws SAXException { ElementState state; try { state = content(); // Check if text should be print as CDATA section or unescaped // based on elements listed in the output format (the element // state) or whether we are inside a CDATA section or entity. if ( state.inCData || state.doCData ) { int saveIndent; // Print a CDATA section. The text is not escaped, but ']]>' // appearing in the code must be identified and dealt with. // The contents of a text node is considered space preserving. if ( ! state.inCData ) { _printer.printText( "<![CDATA[" ); state.inCData = true; } saveIndent = _printer.getNextIndent(); _printer.setNextIndent( 0 ); char ch; final int end = start + length; for ( int index = start; index < end; ++index ) { ch = chars[index]; if ( ch == ']' && index + 2 < end && chars[ index + 1 ] == ']' && chars[ index + 2 ] == '>' ) { _printer.printText("]]]]><![CDATA[>"); index +=2; continue; } if (!XML11Char.isXML11Valid(ch)) { // check if it is surrogate if (++index < end) { surrogates(ch, chars[index]); } else { fatalError("The character '"+(char)ch+"' is an invalid XML character"); } continue; } else { if ( _encodingInfo.isPrintable((char)ch) && XML11Char.isXML11ValidLiteral(ch)) { _printer.printText((char)ch); } else { // The character is not printable -- split CDATA section _printer.printText("]]>&#x"); _printer.printText(Integer.toHexString(ch)); _printer.printText(";<![CDATA["); } } } _printer.setNextIndent( saveIndent ); } else { int saveIndent; if ( state.preserveSpace ) { // If preserving space then hold of indentation so no // excessive spaces are printed at line breaks, escape // the text content without replacing spaces and print // the text breaking only at line breaks. saveIndent = _printer.getNextIndent(); _printer.setNextIndent( 0 ); printText( chars, start, length, true, state.unescaped ); _printer.setNextIndent( saveIndent ); } else { printText( chars, start, length, false, state.unescaped ); } } } catch ( IOException except ) { throw new SAXException( except ); } } // // overwrite printing functions to make sure serializer prints out valid XML // protected void printEscaped( String source ) throws IOException { int length = source.length(); for ( int i = 0 ; i < length ; ++i ) { int ch = source.charAt(i); if (!XML11Char.isXML11Valid(ch)) { if (++i <length) { surrogates(ch, source.charAt(i)); } else { fatalError("The character '"+(char)ch+"' is an invalid XML character");
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?