1 /* 2 * Copyright (c) 1997, 2012, Oracle and/or its affiliates. All rights reserved. 3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. 4 * 5 * This code is free software; you can redistribute it and/or modify it 6 * under the terms of the GNU General Public License version 2 only, as 7 * published by the Free Software Foundation. Oracle designates this 8 * particular file as subject to the "Classpath" exception as provided 9 * by Oracle in the LICENSE file that accompanied this code. 10 * 11 * This code is distributed in the hope that it will be useful, but WITHOUT 12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License 14 * version 2 for more details (a copy is included in the LICENSE file that 15 * accompanied this code). 16 * 17 * You should have received a copy of the GNU General Public License version 18 * 2 along with this work; if not, write to the Free Software Foundation, 19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. 20 * 21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA 22 * or visit www.oracle.com if you need additional information or have any 23 * questions. 24 */ 25 26 package com.sun.xml.internal.messaging.saaj.util; 27 28 import java.io.*; 29 30 import javax.xml.transform.TransformerException; 31 32 /* 33 * Class that parses the very first construct in the document i.e. 34 * <?xml ... ?> 35 * 36 * @author Panos Kougiouris (panos@acm.org) 37 * @version 38 */ 39 40 public class XMLDeclarationParser { 41 private String m_encoding; 42 private PushbackReader m_pushbackReader; 43 private boolean m_hasHeader; // preserve the case where no XML Header exists 44 private String xmlDecl = null; 45 static String gt16 = null; 46 static String utf16Decl = null; 47 static { 48 try { 49 gt16 = new String(">".getBytes("utf-16")); 50 utf16Decl = new String("<?xml".getBytes("utf-16")); 51 } catch (Exception e) {} 52 } 53 54 //--------------------------------------------------------------------- 55 56 public XMLDeclarationParser(PushbackReader pr) 57 { 58 m_pushbackReader = pr; 59 m_encoding = "utf-8"; 60 m_hasHeader = false; 61 } 62 63 //--------------------------------------------------------------------- 64 public String getEncoding() 65 { 66 return m_encoding; 67 } 68 69 public String getXmlDeclaration() { 70 return xmlDecl; 71 } 72 73 //--------------------------------------------------------------------- 74 75 public void parse() throws TransformerException, IOException 76 { 77 int c = 0; 78 int index = 0; 79 StringBuilder xmlDeclStr = new StringBuilder(); 80 while ((c = m_pushbackReader.read()) != -1) { 81 xmlDeclStr.append((char)c); 82 index++; 83 if (c == '>') { 84 break; 85 } 86 } 87 int len = index; 88 89 String decl = xmlDeclStr.toString(); 90 boolean utf16 = false; 91 boolean utf8 = false; 92 93 int xmlIndex = decl.indexOf(utf16Decl); 94 if (xmlIndex > -1) { 95 utf16 = true; 96 } else { 97 xmlIndex = decl.indexOf("<?xml"); 98 if (xmlIndex > -1) { 99 utf8 = true; 100 } 101 } 102 103 // no XML decl 104 if (!utf16 && !utf8) { 105 m_pushbackReader.unread(decl.toCharArray(), 0, len); 106 return; 107 } 108 m_hasHeader = true; 109 110 if (utf16) { 111 xmlDecl = new String(decl.getBytes(), "utf-16"); 112 xmlDecl = xmlDecl.substring(xmlDecl.indexOf("<")); 113 } else { 114 xmlDecl = decl; 115 } 116 // do we want to check that there are no other characters preceeding <?xml 117 if (xmlIndex != 0) { 118 throw new IOException("Unexpected characters before XML declaration"); 119 } 120 121 int versionIndex = xmlDecl.indexOf("version"); 122 if (versionIndex == -1) { 123 throw new IOException("Mandatory 'version' attribute Missing in XML declaration"); 124 } 125 126 // now set 127 int encodingIndex = xmlDecl.indexOf("encoding"); 128 if (encodingIndex == -1) { 129 return; 130 } 131 132 if (versionIndex > encodingIndex) { 133 throw new IOException("The 'version' attribute should preceed the 'encoding' attribute in an XML Declaration"); 134 } 135 136 int stdAloneIndex = xmlDecl.indexOf("standalone"); 137 if ((stdAloneIndex > -1) && ((stdAloneIndex < versionIndex) || (stdAloneIndex < encodingIndex))) { 138 throw new IOException("The 'standalone' attribute should be the last attribute in an XML Declaration"); 139 } 140 141 int eqIndex = xmlDecl.indexOf("=", encodingIndex); 142 if (eqIndex == -1) { 143 throw new IOException("Missing '=' character after 'encoding' in XML declaration"); 144 } 145 146 m_encoding = parseEncoding(xmlDecl, eqIndex); 147 if(m_encoding.startsWith("\"")){ 148 m_encoding = m_encoding.substring(m_encoding.indexOf("\"")+1, m_encoding.lastIndexOf("\"")); 149 } else if(m_encoding.startsWith("\'")){ 150 m_encoding = m_encoding.substring(m_encoding.indexOf("\'")+1, m_encoding.lastIndexOf("\'")); 151 } 152 } 153 154 //-------------------------------------------------------------------- 155 156 public void writeTo(Writer wr) throws IOException { 157 if (!m_hasHeader) return; 158 wr.write(xmlDecl.toString()); 159 } 160 161 private String parseEncoding(String xmlDeclFinal, int eqIndex) throws IOException { 162 java.util.StringTokenizer strTok = new java.util.StringTokenizer( 163 xmlDeclFinal.substring(eqIndex + 1)); 164 if (strTok.hasMoreTokens()) { 165 String encodingTok = strTok.nextToken(); 166 int indexofQ = encodingTok.indexOf("?"); 167 if (indexofQ > -1) { 168 return encodingTok.substring(0,indexofQ); 169 } else { 170 return encodingTok; 171 } 172 } else { 173 throw new IOException("Error parsing 'encoding' attribute in XML declaration"); 174 } 175 } 176 177 }