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 *      http://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.binary;
019
020import java.nio.ByteBuffer;
021import java.nio.charset.Charset;
022import java.nio.charset.StandardCharsets;
023
024import org.apache.commons.codec.BinaryDecoder;
025import org.apache.commons.codec.BinaryEncoder;
026import org.apache.commons.codec.CharEncoding;
027import org.apache.commons.codec.DecoderException;
028import org.apache.commons.codec.EncoderException;
029
030/**
031 * Converts hexadecimal Strings. The Charset used for certain operation can be set, the default is set in
032 * {@link #DEFAULT_CHARSET_NAME}
033 *
034 * This class is thread-safe.
035 *
036 * @since 1.1
037 */
038public class Hex implements BinaryEncoder, BinaryDecoder {
039
040    /**
041     * Default charset is {@link StandardCharsets#UTF_8}.
042     *
043     * @since 1.7
044     */
045    public static final Charset DEFAULT_CHARSET = StandardCharsets.UTF_8;
046
047    /**
048     * Default charset name is {@link CharEncoding#UTF_8}.
049     *
050     * @since 1.4
051     */
052    public static final String DEFAULT_CHARSET_NAME = CharEncoding.UTF_8;
053
054    /**
055     * Used to build output as hex.
056     */
057    private static final char[] DIGITS_LOWER = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'a', 'b', 'c', 'd',
058            'e', 'f' };
059
060    /**
061     * Used to build output as hex.
062     */
063    private static final char[] DIGITS_UPPER = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D',
064            'E', 'F' };
065
066    private final Charset charset;
067
068    /**
069     * Converts an array of characters representing hexadecimal values into an array of bytes of those same values. The
070     * returned array will be half the length of the passed array, as it takes two characters to represent any given
071     * byte. An exception is thrown if the passed char array has an odd number of elements.
072     *
073     * @param data An array of characters containing hexadecimal digits
074     * @return A byte array containing binary data decoded from the supplied char array.
075     * @throws DecoderException Thrown if an odd number of characters or illegal characters are supplied
076     */
077    public static byte[] decodeHex(final char[] data) throws DecoderException {
078        final byte[] out = new byte[data.length >> 1];
079        decodeHex(data, out, 0);
080        return out;
081    }
082
083    /**
084     * Converts an array of characters representing hexadecimal values into an array of bytes of those same values. The
085     * returned array will be half the length of the passed array, as it takes two characters to represent any given
086     * byte. An exception is thrown if the passed char array has an odd number of elements.
087     *
088     * @param data An array of characters containing hexadecimal digits
089     * @param out A byte array to contain the binary data decoded from the supplied char array.
090     * @param outOffset The position within {@code out} to start writing the decoded bytes.
091     * @return the number of bytes written to {@code out}.
092     * @throws DecoderException Thrown if an odd number of characters or illegal characters are supplied
093     * @since 1.15
094     */
095    public static int decodeHex(final char[] data, final byte[] out, final int outOffset) throws DecoderException {
096        final int len = data.length;
097
098        if ((len & 0x01) != 0) {
099            throw new DecoderException("Odd number of characters.");
100        }
101
102        final int outLen = len >> 1;
103        if (out.length - outOffset < outLen) {
104            throw new DecoderException("Output array is not large enough to accommodate decoded data.");
105        }
106
107        // two characters form the hex value.
108        for (int i = outOffset, j = 0; j < len; i++) {
109            int f = toDigit(data[j], j) << 4;
110            j++;
111            f = f | toDigit(data[j], j);
112            j++;
113            out[i] = (byte) (f & 0xFF);
114        }
115
116        return outLen;
117    }
118
119    /**
120     * Converts a String representing hexadecimal values into an array of bytes of those same values. The returned array
121     * will be half the length of the passed String, as it takes two characters to represent any given byte. An
122     * exception is thrown if the passed String has an odd number of elements.
123     *
124     * @param data A String containing hexadecimal digits
125     * @return A byte array containing binary data decoded from the supplied char array.
126     * @throws DecoderException Thrown if an odd number of characters or illegal characters are supplied
127     * @since 1.11
128     */
129    public static byte[] decodeHex(final String data) throws DecoderException {
130        return decodeHex(data.toCharArray());
131    }
132
133    /**
134     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
135     * The returned array will be double the length of the passed array, as it takes two characters to represent any
136     * given byte.
137     *
138     * @param data a byte[] to convert to hex characters
139     * @return A char[] containing lower-case hexadecimal characters
140     */
141    public static char[] encodeHex(final byte[] data) {
142        return encodeHex(data, true);
143    }
144
145    /**
146     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
147     * The returned array will be double the length of the passed array, as it takes two characters to represent any
148     * given byte.
149     *
150     * @param data        a byte[] to convert to Hex characters
151     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
152     * @return A char[] containing hexadecimal characters in the selected case
153     * @since 1.4
154     */
155    public static char[] encodeHex(final byte[] data, final boolean toLowerCase) {
156        return encodeHex(data, toLowerCase ? DIGITS_LOWER : DIGITS_UPPER);
157    }
158
159    /**
160     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
161     * The returned array will be double the length of the passed array, as it takes two characters to represent any
162     * given byte.
163     *
164     * @param data     a byte[] to convert to hex characters
165     * @param toDigits the output alphabet (must contain at least 16 chars)
166     * @return A char[] containing the appropriate characters from the alphabet For best results, this should be either
167     *         upper- or lower-case hex.
168     * @since 1.4
169     */
170    protected static char[] encodeHex(final byte[] data, final char[] toDigits) {
171        final int dataLength = data.length;
172        final char[] out = new char[dataLength << 1];
173        encodeHex(data, 0, dataLength, toDigits, out, 0);
174        return out;
175    }
176
177    /**
178     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
179     *
180     * @param data a byte[] to convert to hex characters
181     * @param dataOffset the position in {@code data} to start encoding from
182     * @param dataLen the number of bytes from {@code dataOffset} to encode
183     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
184     * @return A char[] containing the appropriate characters from the alphabet For best results, this should be either
185     *         upper- or lower-case hex.
186     * @since 1.15
187     */
188    public static char[] encodeHex(final byte[] data, final int dataOffset, final int dataLen,
189            final boolean toLowerCase) {
190        final char[] out = new char[dataLen << 1];
191        encodeHex(data, dataOffset, dataLen, toLowerCase ? DIGITS_LOWER : DIGITS_UPPER, out, 0);
192        return out;
193    }
194
195    /**
196     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
197     *
198     * @param data a byte[] to convert to hex characters
199     * @param dataOffset the position in {@code data} to start encoding from
200     * @param dataLen the number of bytes from {@code dataOffset} to encode
201     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
202     * @param out a char[] which will hold the resultant appropriate characters from the alphabet.
203     * @param outOffset the position within {@code out} at which to start writing the encoded characters.
204     * @since 1.15
205     */
206    public static void encodeHex(final byte[] data, final int dataOffset, final int dataLen,
207            final boolean toLowerCase, final char[] out, final int outOffset) {
208        encodeHex(data, dataOffset, dataLen, toLowerCase ? DIGITS_LOWER : DIGITS_UPPER, out, outOffset);
209    }
210
211    /**
212     * Converts an array of bytes into an array of characters representing the hexadecimal values of each byte in order.
213     *
214     * @param data a byte[] to convert to hex characters
215     * @param dataOffset the position in {@code data} to start encoding from
216     * @param dataLen the number of bytes from {@code dataOffset} to encode
217     * @param toDigits the output alphabet (must contain at least 16 chars)
218     * @param out a char[] which will hold the resultant appropriate characters from the alphabet.
219     * @param outOffset the position within {@code out} at which to start writing the encoded characters.
220     */
221    private static void encodeHex(final byte[] data, final int dataOffset, final int dataLen, final char[] toDigits,
222            final char[] out, final int outOffset) {
223        // two characters form the hex value.
224        for (int i = dataOffset, j = outOffset; i < dataOffset + dataLen; i++) {
225            out[j++] = toDigits[(0xF0 & data[i]) >>> 4];
226            out[j++] = toDigits[0x0F & data[i]];
227        }
228    }
229
230    /**
231     * Converts a byte buffer into an array of characters representing the hexadecimal values of each byte in order. The
232     * returned array will be double the length of the passed array, as it takes two characters to represent any given
233     * byte.
234     *
235     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
236     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
237     *
238     * @param data a byte buffer to convert to hex characters
239     * @return A char[] containing lower-case hexadecimal characters
240     * @since 1.11
241     */
242    public static char[] encodeHex(final ByteBuffer data) {
243        return encodeHex(data, true);
244    }
245
246    /**
247     * Converts a byte buffer into an array of characters representing the hexadecimal values of each byte in order. The
248     * returned array will be double the length of the passed array, as it takes two characters to represent any given
249     * byte.
250     *
251     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
252     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
253     *
254     * @param data        a byte buffer to convert to hex characters
255     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
256     * @return A char[] containing hexadecimal characters in the selected case
257     * @since 1.11
258     */
259    public static char[] encodeHex(final ByteBuffer data, final boolean toLowerCase) {
260        return encodeHex(data, toLowerCase ? DIGITS_LOWER : DIGITS_UPPER);
261    }
262
263    /**
264     * Converts a byte buffer into an array of characters representing the hexadecimal values of each byte in order. The
265     * returned array will be double the length of the passed array, as it takes two characters to represent any given
266     * byte.
267     *
268     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
269     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
270     *
271     * @param byteBuffer a byte buffer to convert to hex characters
272     * @param toDigits   the output alphabet (must be at least 16 characters)
273     * @return A char[] containing the appropriate characters from the alphabet For best results, this should be either
274     *         upper- or lower-case hex.
275     * @since 1.11
276     */
277    protected static char[] encodeHex(final ByteBuffer byteBuffer, final char[] toDigits) {
278        return encodeHex(toByteArray(byteBuffer), toDigits);
279    }
280
281    /**
282     * Converts an array of bytes into a String representing the hexadecimal values of each byte in order. The returned
283     * String will be double the length of the passed array, as it takes two characters to represent any given byte.
284     *
285     * @param data a byte[] to convert to hex characters
286     * @return A String containing lower-case hexadecimal characters
287     * @since 1.4
288     */
289    public static String encodeHexString(final byte[] data) {
290        return new String(encodeHex(data));
291    }
292
293    /**
294     * Converts an array of bytes into a String representing the hexadecimal values of each byte in order. The returned
295     * String will be double the length of the passed array, as it takes two characters to represent any given byte.
296     *
297     * @param data        a byte[] to convert to hex characters
298     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
299     * @return A String containing lower-case hexadecimal characters
300     * @since 1.11
301     */
302    public static String encodeHexString(final byte[] data, final boolean toLowerCase) {
303        return new String(encodeHex(data, toLowerCase));
304    }
305
306    /**
307     * Converts a byte buffer into a String representing the hexadecimal values of each byte in order. The returned
308     * String will be double the length of the passed array, as it takes two characters to represent any given byte.
309     *
310     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
311     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
312     *
313     * @param data a byte buffer to convert to hex characters
314     * @return A String containing lower-case hexadecimal characters
315     * @since 1.11
316     */
317    public static String encodeHexString(final ByteBuffer data) {
318        return new String(encodeHex(data));
319    }
320
321    /**
322     * Converts a byte buffer into a String representing the hexadecimal values of each byte in order. The returned
323     * String will be double the length of the passed array, as it takes two characters to represent any given byte.
324     *
325     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
326     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
327     *
328     * @param data        a byte buffer to convert to hex characters
329     * @param toLowerCase {@code true} converts to lowercase, {@code false} to uppercase
330     * @return A String containing lower-case hexadecimal characters
331     * @since 1.11
332     */
333    public static String encodeHexString(final ByteBuffer data, final boolean toLowerCase) {
334        return new String(encodeHex(data, toLowerCase));
335    }
336
337    /**
338     * Convert the byte buffer to a byte array. All bytes identified by
339     * {@link ByteBuffer#remaining()} will be used.
340     *
341     * @param byteBuffer the byte buffer
342     * @return the byte[]
343     */
344    private static byte[] toByteArray(final ByteBuffer byteBuffer) {
345        final int remaining = byteBuffer.remaining();
346        // Use the underlying buffer if possible
347        if (byteBuffer.hasArray()) {
348            final byte[] byteArray = byteBuffer.array();
349            if (remaining == byteArray.length) {
350                byteBuffer.position(remaining);
351                return byteArray;
352            }
353        }
354        // Copy the bytes
355        final byte[] byteArray = new byte[remaining];
356        byteBuffer.get(byteArray);
357        return byteArray;
358    }
359
360    /**
361     * Converts a hexadecimal character to an integer.
362     *
363     * @param ch    A character to convert to an integer digit
364     * @param index The index of the character in the source
365     * @return An integer
366     * @throws DecoderException Thrown if ch is an illegal hex character
367     */
368    protected static int toDigit(final char ch, final int index) throws DecoderException {
369        final int digit = Character.digit(ch, 16);
370        if (digit == -1) {
371            throw new DecoderException("Illegal hexadecimal character " + ch + " at index " + index);
372        }
373        return digit;
374    }
375
376    /**
377     * Creates a new codec with the default charset name {@link #DEFAULT_CHARSET}
378     */
379    public Hex() {
380        // use default encoding
381        this.charset = DEFAULT_CHARSET;
382    }
383
384    /**
385     * Creates a new codec with the given Charset.
386     *
387     * @param charset the charset.
388     * @since 1.7
389     */
390    public Hex(final Charset charset) {
391        this.charset = charset;
392    }
393
394    /**
395     * Creates a new codec with the given charset name.
396     *
397     * @param charsetName the charset name.
398     * @throws java.nio.charset.UnsupportedCharsetException If the named charset is unavailable
399     * @since 1.4
400     * @since 1.7 throws UnsupportedCharsetException if the named charset is unavailable
401     */
402    public Hex(final String charsetName) {
403        this(Charset.forName(charsetName));
404    }
405
406    /**
407     * Converts an array of character bytes representing hexadecimal values into an array of bytes of those same values.
408     * The returned array will be half the length of the passed array, as it takes two characters to represent any given
409     * byte. An exception is thrown if the passed char array has an odd number of elements.
410     *
411     * @param array An array of character bytes containing hexadecimal digits
412     * @return A byte array containing binary data decoded from the supplied byte array (representing characters).
413     * @throws DecoderException Thrown if an odd number of characters is supplied to this function
414     * @see #decodeHex(char[])
415     */
416    @Override
417    public byte[] decode(final byte[] array) throws DecoderException {
418        return decodeHex(new String(array, getCharset()).toCharArray());
419    }
420
421    /**
422     * Converts a buffer of character bytes representing hexadecimal values into an array of bytes of those same values.
423     * The returned array will be half the length of the passed array, as it takes two characters to represent any given
424     * byte. An exception is thrown if the passed char array has an odd number of elements.
425     *
426     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
427     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
428     *
429     * @param buffer An array of character bytes containing hexadecimal digits
430     * @return A byte array containing binary data decoded from the supplied byte array (representing characters).
431     * @throws DecoderException Thrown if an odd number of characters is supplied to this function
432     * @see #decodeHex(char[])
433     * @since 1.11
434     */
435    public byte[] decode(final ByteBuffer buffer) throws DecoderException {
436        return decodeHex(new String(toByteArray(buffer), getCharset()).toCharArray());
437    }
438
439    /**
440     * Converts a String or an array of character bytes representing hexadecimal values into an array of bytes of those
441     * same values. The returned array will be half the length of the passed String or array, as it takes two characters
442     * to represent any given byte. An exception is thrown if the passed char array has an odd number of elements.
443     *
444     * @param object A String, ByteBuffer, byte[], or an array of character bytes containing hexadecimal digits
445     * @return A byte array containing binary data decoded from the supplied byte array (representing characters).
446     * @throws DecoderException Thrown if an odd number of characters is supplied to this function or the object is not
447     *                          a String or char[]
448     * @see #decodeHex(char[])
449     */
450    @Override
451    public Object decode(final Object object) throws DecoderException {
452        if (object instanceof String) {
453            return decode(((String) object).toCharArray());
454        }
455        if (object instanceof byte[]) {
456            return decode((byte[]) object);
457        }
458        if (object instanceof ByteBuffer) {
459            return decode((ByteBuffer) object);
460        }
461        try {
462            return decodeHex((char[]) object);
463        } catch (final ClassCastException e) {
464            throw new DecoderException(e.getMessage(), e);
465        }
466    }
467
468    /**
469     * Converts an array of bytes into an array of bytes for the characters representing the hexadecimal values of each
470     * byte in order. The returned array will be double the length of the passed array, as it takes two characters to
471     * represent any given byte.
472     * <p>
473     * The conversion from hexadecimal characters to the returned bytes is performed with the charset named by
474     * {@link #getCharset()}.
475     * </p>
476     *
477     * @param array a byte[] to convert to hex characters
478     * @return A byte[] containing the bytes of the lower-case hexadecimal characters
479     * @since 1.7 No longer throws IllegalStateException if the charsetName is invalid.
480     * @see #encodeHex(byte[])
481     */
482    @Override
483    public byte[] encode(final byte[] array) {
484        return encodeHexString(array).getBytes(this.getCharset());
485    }
486
487    /**
488     * Converts byte buffer into an array of bytes for the characters representing the hexadecimal values of each byte
489     * in order. The returned array will be double the length of the passed array, as it takes two characters to
490     * represent any given byte.
491     *
492     * <p>The conversion from hexadecimal characters to the returned bytes is performed with the charset named by
493     * {@link #getCharset()}.</p>
494     *
495     * <p>All bytes identified by {@link ByteBuffer#remaining()} will be used; after this method
496     * the value {@link ByteBuffer#remaining() remaining()} will be zero.</p>
497     *
498     * @param array a byte buffer to convert to hex characters
499     * @return A byte[] containing the bytes of the lower-case hexadecimal characters
500     * @see #encodeHex(byte[])
501     * @since 1.11
502     */
503    public byte[] encode(final ByteBuffer array) {
504        return encodeHexString(array).getBytes(this.getCharset());
505    }
506
507    /**
508     * Converts a String or an array of bytes into an array of characters representing the hexadecimal values of each
509     * byte in order. The returned array will be double the length of the passed String or array, as it takes two
510     * characters to represent any given byte.
511     * <p>
512     * The conversion from hexadecimal characters to bytes to be encoded to performed with the charset named by
513     * {@link #getCharset()}.
514     * </p>
515     *
516     * @param object a String, ByteBuffer, or byte[] to convert to hex characters
517     * @return A char[] containing lower-case hexadecimal characters
518     * @throws EncoderException Thrown if the given object is not a String or byte[]
519     * @see #encodeHex(byte[])
520     */
521    @Override
522    public Object encode(final Object object) throws EncoderException {
523        final byte[] byteArray;
524        if (object instanceof String) {
525            byteArray = ((String) object).getBytes(this.getCharset());
526        } else if (object instanceof ByteBuffer) {
527            byteArray = toByteArray((ByteBuffer) object);
528        } else {
529            try {
530                byteArray = (byte[]) object;
531            } catch (final ClassCastException e) {
532                throw new EncoderException(e.getMessage(), e);
533            }
534        }
535        return encodeHex(byteArray);
536    }
537
538    /**
539     * Gets the charset.
540     *
541     * @return the charset.
542     * @since 1.7
543     */
544    public Charset getCharset() {
545        return this.charset;
546    }
547
548    /**
549     * Gets the charset name.
550     *
551     * @return the charset name.
552     * @since 1.4
553     */
554    public String getCharsetName() {
555        return this.charset.name();
556    }
557
558    /**
559     * Returns a string representation of the object, which includes the charset name.
560     *
561     * @return a string representation of the object.
562     */
563    @Override
564    public String toString() {
565        return super.toString() + "[charsetName=" + this.charset + "]";
566    }
567}