1 /* 2 * Copyright (c) 2015, 2017, Oracle and/or its affiliates. All rights reserved. 3 */ 4 /* 5 * Licensed to the Apache Software Foundation (ASF) under one or more 6 * contributor license agreements. See the NOTICE file distributed with 7 * this work for additional information regarding copyright ownership. 8 * The ASF licenses this file to You under the Apache License, Version 2.0 9 * (the "License"); you may not use this file except in compliance with 10 * the License. You may obtain a copy of the License at 11 * 12 * http://www.apache.org/licenses/LICENSE-2.0 13 * 14 * Unless required by applicable law or agreed to in writing, software 15 * distributed under the License is distributed on an "AS IS" BASIS, 16 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 17 * See the License for the specific language governing permissions and 18 * limitations under the License. 19 */ 20 21 22 package com.sun.org.apache.xml.internal.serialize; 23 24 25 import com.sun.org.apache.xerces.internal.util.EncodingMap; 26 import java.io.UnsupportedEncodingException; 27 import java.util.Locale; 28 import java.util.Map; 29 import java.util.concurrent.ConcurrentHashMap; 30 31 32 /** 33 * Provides information about encodings. Depends on the Java runtime 34 * to provides writers for the different encodings, but can be used 35 * to override encoding names and provide the last printable character 36 * for each encoding. 37 * 38 * @author <a href="mailto:arkin@intalio.com">Assaf Arkin</a> 39 * 40 * @deprecated As of JDK 9, Xerces 2.9.0, Xerces DOM L3 Serializer implementation 41 * is replaced by that of Xalan. Main class 42 * {@link com.sun.org.apache.xml.internal.serialize.DOMSerializerImpl} is replaced 43 * by {@link com.sun.org.apache.xml.internal.serializer.dom3.LSSerializerImpl}. 44 * 45 * @LastModified: Oct 2017 46 */ 47 @Deprecated 48 class Encodings 49 { 50 51 52 /** 53 * The last printable character for unknown encodings. 54 */ 55 static final int DEFAULT_LAST_PRINTABLE = 0x7F; 56 57 // last printable character for Unicode-compatible encodings 58 static final int LAST_PRINTABLE_UNICODE = 0xffff; 59 // unicode-compliant encodings; can express plane 0 60 static final String[] UNICODE_ENCODINGS = { 61 "Unicode", "UnicodeBig", "UnicodeLittle", "GB2312", "UTF8", "UTF-16", 62 }; 63 // default (Java) encoding if none supplied: 64 static final String DEFAULT_ENCODING = "UTF8"; 65 66 // note that the size of this Map 67 // is bounded by the number of encodings recognized by EncodingMap; 68 // therefore it poses no static mutability risk. 69 private static final Map<String, EncodingInfo> _encodings = new ConcurrentHashMap<>(); 70 71 /** 72 * @param encoding a MIME charset name, or null. 73 */ 74 static EncodingInfo getEncodingInfo(String encoding, boolean allowJavaNames) throws UnsupportedEncodingException { 75 EncodingInfo eInfo = null; 76 if (encoding == null) { 77 if((eInfo = _encodings.get(DEFAULT_ENCODING)) != null) 78 return eInfo; 79 eInfo = new EncodingInfo(EncodingMap.getJava2IANAMapping(DEFAULT_ENCODING), DEFAULT_ENCODING, LAST_PRINTABLE_UNICODE); 80 _encodings.put(DEFAULT_ENCODING, eInfo); 81 return eInfo; 82 } 83 // need to convert it to upper case: 84 encoding = encoding.toUpperCase(Locale.ENGLISH); 85 String jName = EncodingMap.getIANA2JavaMapping(encoding); 86 if(jName == null) { 87 // see if the encoding passed in is a Java encoding name. 88 if(allowJavaNames ) { 89 EncodingInfo.testJavaEncodingName(encoding); 90 if((eInfo = _encodings.get(encoding)) != null) 91 return eInfo; 92 // is it known to be unicode-compliant? 93 int i=0; 94 for(; i<UNICODE_ENCODINGS.length; i++) { 95 if(UNICODE_ENCODINGS[i].equalsIgnoreCase(encoding)) { 96 eInfo = new EncodingInfo(EncodingMap.getJava2IANAMapping(encoding), encoding, LAST_PRINTABLE_UNICODE); 97 break; 98 } 99 } 100 if(i == UNICODE_ENCODINGS.length) { 101 eInfo = new EncodingInfo(EncodingMap.getJava2IANAMapping(encoding), encoding, DEFAULT_LAST_PRINTABLE); 102 } 103 _encodings.put(encoding, eInfo); 104 return eInfo; 105 } else { 106 throw new UnsupportedEncodingException(encoding); 107 } 108 } 109 if ((eInfo = _encodings.get(jName)) != null) 110 return eInfo; 111 // have to create one... 112 // is it known to be unicode-compliant? 113 int i=0; 114 for(; i<UNICODE_ENCODINGS.length; i++) { 115 if(UNICODE_ENCODINGS[i].equalsIgnoreCase(jName)) { 116 eInfo = new EncodingInfo(encoding, jName, LAST_PRINTABLE_UNICODE); 117 break; 118 } 119 } 120 if(i == UNICODE_ENCODINGS.length) { 121 eInfo = new EncodingInfo(encoding, jName, DEFAULT_LAST_PRINTABLE); 122 } 123 _encodings.put(jName, eInfo); 124 return eInfo; 125 } 126 127 static final String JIS_DANGER_CHARS 128 = "\\\u007e\u007f\u00a2\u00a3\u00a5\u00ac" 129 +"\u2014\u2015\u2016\u2026\u203e\u203e\u2225\u222f\u301c" 130 +"\uff3c\uff5e\uffe0\uffe1\uffe2\uffe3"; 131 132 }