Source code

001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      https://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018package org.apache.commons.codec.net;
019
020import java.io.UnsupportedEncodingException;
021import java.nio.charset.Charset;
022import java.nio.charset.StandardCharsets;
023import java.nio.charset.UnsupportedCharsetException;
024import java.util.BitSet;
025
026import org.apache.commons.codec.DecoderException;
027import org.apache.commons.codec.EncoderException;
028import org.apache.commons.codec.StringDecoder;
029import org.apache.commons.codec.StringEncoder;
030
031/**
032 * Similar to the Quoted-Printable content-transfer-encoding defined in
033 * <a href="https://www.ietf.org/rfc/rfc1521.txt">RFC 1521</a> and designed to allow text containing mostly ASCII
034 * characters to be decipherable on an ASCII terminal without decoding.
035 * <p>
036 * <a href="https://www.ietf.org/rfc/rfc1522.txt">RFC 1522</a> describes techniques to allow the encoding of non-ASCII
037 * text in various portions of a RFC 822 [2] message header, in a manner which is unlikely to confuse existing message
038 * handling software.
039 * </p>
040 * <p>
041 * This class is conditionally thread-safe.
042 * The instance field for encoding blanks is mutable {@link #setEncodeBlanks(boolean)}
043 * but is not volatile, and accesses are not synchronized.
044 * If an instance of the class is shared between threads, the caller needs to ensure that suitable synchronization
045 * is used to ensure safe publication of the value between threads, and must not invoke
046 * {@link #setEncodeBlanks(boolean)} after initial setup.
047 * </p>
048 *
049 * @see <a href="https://www.ietf.org/rfc/rfc1522.txt">MIME (Multipurpose Internet Mail Extensions) Part Two: Message
050 *          Header Extensions for Non-ASCII Text</a>
051 *
052 * @since 1.3
053 */
054public class QCodec extends RFC1522Codec implements StringEncoder, StringDecoder {
055
056    /**
057     * BitSet of printable characters as defined in RFC 1522.
058     */
059    private static final BitSet PRINTABLE_CHARS = new BitSet(256);
060
061    // Static initializer for printable chars collection
062    static {
063        // alpha characters
064        PRINTABLE_CHARS.set(' ');
065        PRINTABLE_CHARS.set('!');
066        PRINTABLE_CHARS.set('"');
067        PRINTABLE_CHARS.set('#');
068        PRINTABLE_CHARS.set('$');
069        PRINTABLE_CHARS.set('%');
070        PRINTABLE_CHARS.set('&');
071        PRINTABLE_CHARS.set('\'');
072        PRINTABLE_CHARS.set('(');
073        PRINTABLE_CHARS.set(')');
074        PRINTABLE_CHARS.set('*');
075        PRINTABLE_CHARS.set('+');
076        PRINTABLE_CHARS.set(',');
077        PRINTABLE_CHARS.set('-');
078        PRINTABLE_CHARS.set('.');
079        PRINTABLE_CHARS.set('/');
080        for (int i = '0'; i <= '9'; i++) {
081            PRINTABLE_CHARS.set(i);
082        }
083        PRINTABLE_CHARS.set(':');
084        PRINTABLE_CHARS.set(';');
085        PRINTABLE_CHARS.set('<');
086        PRINTABLE_CHARS.set('>');
087        PRINTABLE_CHARS.set('@');
088        for (int i = 'A'; i <= 'Z'; i++) {
089            PRINTABLE_CHARS.set(i);
090        }
091        PRINTABLE_CHARS.set('[');
092        PRINTABLE_CHARS.set('\\');
093        PRINTABLE_CHARS.set(']');
094        PRINTABLE_CHARS.set('^');
095        PRINTABLE_CHARS.set('`');
096        for (int i = 'a'; i <= 'z'; i++) {
097            PRINTABLE_CHARS.set(i);
098        }
099        PRINTABLE_CHARS.set('{');
100        PRINTABLE_CHARS.set('|');
101        PRINTABLE_CHARS.set('}');
102        PRINTABLE_CHARS.set('~');
103    }
104    private static final byte SPACE = 32;
105
106    private static final byte UNDERSCORE = 95;
107
108    private boolean encodeBlanks;
109
110    /**
111     * Default constructor.
112     */
113    public QCodec() {
114        this(StandardCharsets.UTF_8);
115    }
116
117    /**
118     * Constructor which allows for the selection of a default Charset.
119     *
120     * @param charset
121     *            the default string Charset to use.
122     *
123     * @see Charset
124     * @since 1.7
125     */
126    public QCodec(final Charset charset) {
127        super(charset);
128    }
129
130    /**
131     * Constructor which allows for the selection of a default Charset.
132     *
133     * @param charsetName
134     *            the Charset to use.
135     * @throws java.nio.charset.UnsupportedCharsetException
136     *             If the named Charset is unavailable.
137     * @since 1.7 throws UnsupportedCharsetException if the named Charset is unavailable
138     * @see Charset
139     */
140    public QCodec(final String charsetName) {
141        this(Charset.forName(charsetName));
142    }
143
144    /**
145     * Decodes a quoted-printable object into its original form. Escaped characters are converted back to their original
146     * representation.
147     *
148     * @param obj
149     *            quoted-printable object to convert into its original form.
150     * @return original object.
151     * @throws DecoderException
152     *             Thrown if the argument is not a {@code String}. Thrown if a failure condition is encountered
153     *             during the decode process.
154     */
155    @Override
156    public Object decode(final Object obj) throws DecoderException {
157        if (obj == null) {
158            return null;
159        }
160        if (obj instanceof String) {
161            return decode((String) obj);
162        }
163        throw new DecoderException("Objects of type " + obj.getClass().getName() + " cannot be decoded using Q codec");
164    }
165
166    /**
167     * Decodes a quoted-printable string into its original form. Escaped characters are converted back to their original
168     * representation.
169     *
170     * @param str
171     *            quoted-printable string to convert into its original form.
172     * @return original string.
173     * @throws DecoderException
174     *             A decoder exception is thrown if a failure condition is encountered during the decode process.
175     */
176    @Override
177    public String decode(final String str) throws DecoderException {
178        try {
179            return decodeText(str);
180        } catch (final UnsupportedEncodingException e) {
181            throw new DecoderException(e.getMessage(), e);
182        }
183    }
184
185    @Override
186    protected byte[] doDecoding(final byte[] bytes) throws DecoderException {
187        if (bytes == null) {
188            return null;
189        }
190        boolean hasUnderscores = false;
191        for (final byte b : bytes) {
192            if (b == UNDERSCORE) {
193                hasUnderscores = true;
194                break;
195            }
196        }
197        if (hasUnderscores) {
198            final byte[] tmp = new byte[bytes.length];
199            for (int i = 0; i < bytes.length; i++) {
200                final byte b = bytes[i];
201                if (b != UNDERSCORE) {
202                    tmp[i] = b;
203                } else {
204                    tmp[i] = SPACE;
205                }
206            }
207            return QuotedPrintableCodec.decodeQuotedPrintable(tmp);
208        }
209        return QuotedPrintableCodec.decodeQuotedPrintable(bytes);
210    }
211
212    @Override
213    protected byte[] doEncoding(final byte[] bytes) {
214        if (bytes == null) {
215            return null;
216        }
217        final byte[] data = QuotedPrintableCodec.encodeQuotedPrintable(PRINTABLE_CHARS, bytes);
218        if (this.encodeBlanks) {
219            for (int i = 0; i < data.length; i++) {
220                if (data[i] == SPACE) {
221                    data[i] = UNDERSCORE;
222                }
223            }
224        }
225        return data;
226    }
227
228    /**
229     * Encodes an object into its quoted-printable form using the default Charset. Unsafe characters are escaped.
230     *
231     * @param obj
232     *            object to convert to quoted-printable form.
233     * @return quoted-printable object.
234     * @throws EncoderException
235     *             thrown if a failure condition is encountered during the encoding process.
236     */
237    @Override
238    public Object encode(final Object obj) throws EncoderException {
239        if (obj == null) {
240            return null;
241        }
242        if (obj instanceof String) {
243            return encode((String) obj);
244        }
245        throw new EncoderException("Objects of type " + obj.getClass().getName() + " cannot be encoded using Q codec");
246    }
247
248    /**
249     * Encodes a string into its quoted-printable form using the default Charset. Unsafe characters are escaped.
250     *
251     * @param sourceStr
252     *            string to convert to quoted-printable form.
253     * @return quoted-printable string.
254     * @throws EncoderException
255     *             thrown if a failure condition is encountered during the encoding process.
256     */
257    @Override
258    public String encode(final String sourceStr) throws EncoderException {
259        return encode(sourceStr, getCharset());
260    }
261
262    /**
263     * Encodes a string into its quoted-printable form using the specified Charset. Unsafe characters are escaped.
264     *
265     * @param sourceStr
266     *            string to convert to quoted-printable form.
267     * @param sourceCharset
268     *            the Charset for sourceStr.
269     * @return quoted-printable string.
270     * @throws EncoderException
271     *             thrown if a failure condition is encountered during the encoding process.
272     * @since 1.7
273     */
274    public String encode(final String sourceStr, final Charset sourceCharset) throws EncoderException {
275        return encodeText(sourceStr, sourceCharset);
276    }
277
278    /**
279     * Encodes a string into its quoted-printable form using the specified Charset. Unsafe characters are escaped.
280     *
281     * @param sourceStr
282     *            string to convert to quoted-printable form.
283     * @param sourceCharset
284     *            the Charset for sourceStr.
285     * @return quoted-printable string.
286     * @throws EncoderException
287     *             thrown if a failure condition is encountered during the encoding process.
288     */
289    public String encode(final String sourceStr, final String sourceCharset) throws EncoderException {
290        try {
291            return encodeText(sourceStr, sourceCharset);
292        } catch (final UnsupportedCharsetException e) {
293            throw new EncoderException(e.getMessage(), e);
294        }
295    }
296
297    @Override
298    protected String getEncoding() {
299        return "Q";
300    }
301
302    /**
303     * Tests if optional transformation of SPACE characters is to be used
304     *
305     * @return {@code true} if SPACE characters are to be transformed, {@code false} otherwise.
306     */
307    public boolean isEncodeBlanks() {
308        return this.encodeBlanks;
309    }
310
311    /**
312     * Defines whether optional transformation of SPACE characters is to be used
313     *
314     * @param b
315     *            {@code true} if SPACE characters are to be transformed, {@code false} otherwise.
316     */
317    public void setEncodeBlanks(final boolean b) {
318        this.encodeBlanks = b;
319    }
320}