1 /* 2 * Copyright 2001-2004 The Apache Software Foundation. 3 * 4 * Licensed under the Apache License, Version 2.0 (the "License"); 5 * you may not use this file except in compliance with the License. 6 * You may obtain a copy of the License at 7 * 8 * http://www.apache.org/licenses/LICENSE-2.0 9 * 10 * Unless required by applicable law or agreed to in writing, software 11 * distributed under the License is distributed on an "AS IS" BASIS, 12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 * See the License for the specific language governing permissions and 14 * limitations under the License. 15 */ 16 17 package org.apache.commons.codec.net; 18 19 import java.io.UnsupportedEncodingException; 20 21 import org.apache.commons.codec.DecoderException; 22 import org.apache.commons.codec.EncoderException; 23 24 /** 25 * <p> 26 * Implements methods common to all codecs defined in RFC 1522. 27 * </p> 28 * 29 * <p> 30 * <a href="http://www.ietf.org/rfc/rfc1522.txt">RFC 1522</a> 31 * describes techniques to allow the encoding of non-ASCII text in 32 * various portions of a RFC 822 [2] message header, in a manner which 33 * is unlikely to confuse existing message handling software. 34 * </p> 35 36 * @see <a href="http://www.ietf.org/rfc/rfc1522.txt"> 37 * MIME (Multipurpose Internet Mail Extensions) Part Two: 38 * Message Header Extensions for Non-ASCII Text</a> 39 * </p> 40 * 41 * @author Apache Software Foundation 42 * @since 1.3 43 * @version $Id: RFC1522Codec.java,v 1.2 2004/04/09 22:21:43 ggregory Exp $ 44 */ 45 abstract class RFC1522Codec { 46 47 /** 48 * Applies an RFC 1522 compliant encoding scheme to the given string of text with the 49 * given charset. This method constructs the "encoded-word" header common to all the 50 * RFC 1522 codecs and then invokes {@link #doEncoding(byte [])} method of a concrete 51 * class to perform the specific enconding. 52 * 53 * @param text a string to encode 54 * @param charset a charset to be used 55 * 56 * @return RFC 1522 compliant "encoded-word" 57 * 58 * @throws EncoderException thrown if there is an error conidition during the Encoding 59 * process. 60 * @throws UnsupportedEncodingException thrown if charset is not supported 61 * 62 * @see <a href="http://java.sun.com/j2se/1.3/docs/api/java/lang/package-summary.html#charenc">JRE character 63 * encoding names</a> 64 */ encodeText(final String text, final String charset)65 protected String encodeText(final String text, final String charset) 66 throws EncoderException, UnsupportedEncodingException 67 { 68 if (text == null) { 69 return null; 70 } 71 StringBuffer buffer = new StringBuffer(); 72 buffer.append("=?"); 73 buffer.append(charset); 74 buffer.append('?'); 75 buffer.append(getEncoding()); 76 buffer.append('?'); 77 byte [] rawdata = doEncoding(text.getBytes(charset)); 78 buffer.append(new String(rawdata, StringEncodings.US_ASCII)); 79 buffer.append("?="); 80 return buffer.toString(); 81 } 82 83 /** 84 * Applies an RFC 1522 compliant decoding scheme to the given string of text. This method 85 * processes the "encoded-word" header common to all the RFC 1522 codecs and then invokes 86 * {@link #doEncoding(byte [])} method of a concrete class to perform the specific deconding. 87 * 88 * @param text a string to decode 89 * 90 * @throws DecoderException thrown if there is an error conidition during the Decoding 91 * process. 92 * @throws UnsupportedEncodingException thrown if charset specified in the "encoded-word" 93 * header is not supported 94 */ decodeText(final String text)95 protected String decodeText(final String text) 96 throws DecoderException, UnsupportedEncodingException 97 { 98 if (text == null) { 99 return null; 100 } 101 if ((!text.startsWith("=?")) || (!text.endsWith("?="))) { 102 throw new DecoderException("RFC 1522 violation: malformed encoded content"); 103 } 104 int termnator = text.length() - 2; 105 int from = 2; 106 int to = text.indexOf("?", from); 107 if ((to == -1) || (to == termnator)) { 108 throw new DecoderException("RFC 1522 violation: charset token not found"); 109 } 110 String charset = text.substring(from, to); 111 if (charset.equals("")) { 112 throw new DecoderException("RFC 1522 violation: charset not specified"); 113 } 114 from = to + 1; 115 to = text.indexOf("?", from); 116 if ((to == -1) || (to == termnator)) { 117 throw new DecoderException("RFC 1522 violation: encoding token not found"); 118 } 119 String encoding = text.substring(from, to); 120 if (!getEncoding().equalsIgnoreCase(encoding)) { 121 throw new DecoderException("This codec cannot decode " + 122 encoding + " encoded content"); 123 } 124 from = to + 1; 125 to = text.indexOf("?", from); 126 byte[] data = text.substring(from, to).getBytes(StringEncodings.US_ASCII); 127 data = doDecoding(data); 128 return new String(data, charset); 129 } 130 131 /** 132 * Returns the codec name (referred to as encoding in the RFC 1522) 133 * 134 * @return name of the codec 135 */ getEncoding()136 protected abstract String getEncoding(); 137 138 /** 139 * Encodes an array of bytes using the defined encoding scheme 140 * 141 * @param bytes Data to be encoded 142 * 143 * @return A byte array containing the encoded data 144 * 145 * @throws EncoderException thrown if the Encoder encounters a failure condition 146 * during the encoding process. 147 */ doEncoding(byte[] bytes)148 protected abstract byte[] doEncoding(byte[] bytes) throws EncoderException; 149 150 /** 151 * Decodes an array of bytes using the defined encoding scheme 152 * 153 * @param bytes Data to be decoded 154 * 155 * @return a byte array that contains decoded data 156 * 157 * @throws DecoderException A decoder exception is thrown if a Decoder encounters a 158 * failure condition during the decode process. 159 */ doDecoding(byte[] bytes)160 protected abstract byte[] doDecoding(byte[] bytes) throws DecoderException; 161 } 162