1 /*
2 * Copyright (c) 1997, 2013, 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 char[] aChar = new char[65535];
80 StringBuffer xmlDeclStr = new StringBuffer();
81 while ((c = m_pushbackReader.read()) != -1) {
82 aChar[index] = (char)c;
83 xmlDeclStr.append((char)c);
84 index++;
85 if (c == '>') {
86 break;
87 }
88 }
89 int len = index;
90
91 String decl = xmlDeclStr.toString();
92 boolean utf16 = false;
93 boolean utf8 = false;
94
95 int xmlIndex = decl.indexOf(utf16Decl);
96 if (xmlIndex > -1) {
97 utf16 = true;
98 } else {
99 xmlIndex = decl.indexOf("<?xml");
100 if (xmlIndex > -1) {
101 utf8 = true;
102 }
103 }
104
105 // no XML decl
106 if (!utf16 && !utf8) {
107 m_pushbackReader.unread(aChar, 0, len);
108 return;
109 }
110 m_hasHeader = true;
111
112 if (utf16) {
113 xmlDecl = new String(decl.getBytes(), "utf-16");
114 xmlDecl = xmlDecl.substring(xmlDecl.indexOf("<"));
115 } else {
116 xmlDecl = decl;
117 }
118 // do we want to check that there are no other characters preceeding <?xml
119 if (xmlIndex != 0) {
120 throw new IOException("Unexpected characters before XML declaration");
121 }
122
123 int versionIndex = xmlDecl.indexOf("version");
124 if (versionIndex == -1) {
125 throw new IOException("Mandatory 'version' attribute Missing in XML declaration");
126 }
127
128 // now set
129 int encodingIndex = xmlDecl.indexOf("encoding");
130 if (encodingIndex == -1) {
131 return;
132 }
133
134 if (versionIndex > encodingIndex) {
135 throw new IOException("The 'version' attribute should preceed the 'encoding' attribute in an XML Declaration");
136 }
137
138 int stdAloneIndex = xmlDecl.indexOf("standalone");
139 if ((stdAloneIndex > -1) && ((stdAloneIndex < versionIndex) || (stdAloneIndex < encodingIndex))) {
140 throw new IOException("The 'standalone' attribute should be the last attribute in an XML Declaration");
141 }
142
143 int eqIndex = xmlDecl.indexOf("=", encodingIndex);
144 if (eqIndex == -1) {
145 throw new IOException("Missing '=' character after 'encoding' in XML declaration");
146 }
147
148 m_encoding = parseEncoding(xmlDecl, eqIndex);
149 if(m_encoding.startsWith("\"")){
150 m_encoding = m_encoding.substring(m_encoding.indexOf("\"")+1, m_encoding.lastIndexOf("\""));
151 } else if(m_encoding.startsWith("\'")){
152 m_encoding = m_encoding.substring(m_encoding.indexOf("\'")+1, m_encoding.lastIndexOf("\'"));
153 }
154 }
155
156 //--------------------------------------------------------------------
157
158 public void writeTo(Writer wr) throws IOException {
159 if (!m_hasHeader) return;
160 wr.write(xmlDecl.toString());
161 }
162
163 private String parseEncoding(String xmlDeclFinal, int eqIndex) throws IOException {
164 java.util.StringTokenizer strTok = new java.util.StringTokenizer(
165 xmlDeclFinal.substring(eqIndex + 1));
166 if (strTok.hasMoreTokens()) {
167 String encodingTok = strTok.nextToken();
168 int indexofQ = encodingTok.indexOf("?");
169 if (indexofQ > -1) {
170 return encodingTok.substring(0,indexofQ);
171 } else {
172 return encodingTok;
173 }
174 } else {
175 throw new IOException("Error parsing 'encoding' attribute in XML declaration");
176 }
177 }
178
179 }