How to use

HuffmanCodec

in

it.unimi.dsi.compression

/**
 * This verifies that a code book constructed from a given set of
 * frequencies may be reconstructed from the cord word bit lengths, given in
 * a non-decreasing order, together with the symbols in a correlated array.
 * 
 * @param frequency
 */
public void doRoundTripTest(final int[] frequency) {
  
  final DecoderInputs decoderInputs = new DecoderInputs();
  
  final HuffmanCodec codec = new HuffmanCodec(frequency, decoderInputs);
  if (log.isDebugEnabled()) {
    log.debug(printCodeBook(codec.codeWords()) + "\nlength[]="
        + Arrays.toString(decoderInputs.getLengths()) + "\nsymbol[]="
        + Arrays.toString(decoderInputs.getSymbols()));
  }
  
  final CanonicalFast64CodeWordDecoder actualDecoder = new CanonicalFast64CodeWordDecoder(
      decoderInputs.getLengths(), decoderInputs.getSymbols());
  for (int i = 0; i < frequency.length; i++) {
    final BooleanIterator coded = codec.coder().encode(i/*symbol*/);
    
    assertEquals(i, actualDecoder.decode(coded));
    
  }
}

/**
 * @param shortestCodeWord
 * @param lengths
 * @param
 */
private void doCoderRoundTripTest(final BitVector[] expected,
    final BitVector shortestCodeWord, final int[] length,
    final int[] symbol) {
  final PrefixCoder newCoder = HuffmanCodec.newCoder(shortestCodeWord,
      length, symbol);
  final BitVector[] actual = newCoder.codeWords();
  assertEquals("codeWord[]", expected, actual);
  if (log.isDebugEnabled()) {
       log.debug("\nexpected: " + Arrays.toString(expected)
        + "\nactual  : " + Arrays.toString(actual));
    
  }
  
}
 

/** Creates a new Huffman codec using the given vector of frequencies.
 *
 * @param frequency a vector of nonnnegative frequencies.
 */
public HuffmanCodec(final int[] frequency) {
  this(intArray2LongArray(frequency));
}

  : getSumCodedValueBitLengths(setup.codec().codeWords(),
      raba, (Byte2Symbol) setup);
      : new long[size + 1]);
  final long sumCodedValueBitLengths2 = writeCodedValues(setup
      .codec().coder(), raba, (Byte2Symbol) setup,
      codedValueOffset, obs);
  assert sumCodedValueBitLengths == sumCodedValueBitLengths2 : "sumCodedValueBitLengths="
return new CodedRabaImpl(slice, setup.codec().decoder(),
    decoderInputsBitLength);

codec = new HuffmanCodec(packedFrequency, decoderInputs);
          + printCodeBook(codec.codeWords(), this/* Symbol2Byte */));

/**
 * Unit test for processing an {@link IRaba} representing B+Tree values
 * suitable to setup the data for compression.
 * 
 * @throws IOException 
 * 
 * @todo test w/ nulls.
 */
public void test_valueRabaSetup() throws IOException {
  final int n = 3;
  final byte[][] a = new byte[n][];
  a[0] = new byte[]{2,3};
  a[1] = new byte[]{3,5};
  a[2] = new byte[]{'m','i','k','e'};
  
  final IRaba raba = new ReadOnlyValuesRaba(a);
  final RabaCodingSetup setup = new RabaCodingSetup(raba);
  
  // verify that we can re-create the decoder.
  doDecoderInputRoundTripTest(setup.getSymbolCount(), setup
      .decoderInputs());
  // verify that we can re-create the coder.
  doCoderRoundTripTest(setup.codec().codeWords(), setup.decoderInputs()
      .getShortestCodeWord(), setup.decoderInputs().getLengths(),
      setup.decoderInputs().getSymbols());
}

  : getSumCodedValueBitLengths(setup.codec().codeWords(),
      raba, (Byte2Symbol) setup);
      : new long[size + 1]);
  final long sumCodedValueBitLengths2 = writeCodedValues(setup
      .codec().coder(), raba, (Byte2Symbol) setup,
      codedValueOffset, obs);
  assert sumCodedValueBitLengths == sumCodedValueBitLengths2 : "sumCodedValueBitLengths="
return new CodedRabaImpl(slice, setup.codec().decoder(),
    decoderInputsBitLength);

codec = new HuffmanCodec(packedFrequency, decoderInputs);
          + printCodeBook(codec.codeWords(), this/* Symbol2Byte */));

/**
 * Unit test for processing an {@link IRaba} representing B+Tree values
 * suitable to setup the data for compression.
 * 
 * @throws IOException 
 * 
 * @todo test w/ nulls.
 */
public void test_valueRabaSetup() throws IOException {
  final int n = 3;
  final byte[][] a = new byte[n][];
  a[0] = new byte[]{2,3};
  a[1] = new byte[]{3,5};
  a[2] = new byte[]{'m','i','k','e'};
  
  final IRaba raba = new ReadOnlyValuesRaba(a);
  final RabaCodingSetup setup = new RabaCodingSetup(raba);
  
  // verify that we can re-create the decoder.
  doDecoderInputRoundTripTest(setup.getSymbolCount(), setup
      .decoderInputs());
  // verify that we can re-create the coder.
  doCoderRoundTripTest(setup.codec().codeWords(), setup.decoderInputs()
      .getShortestCodeWord(), setup.decoderInputs().getLengths(),
      setup.decoderInputs().getSymbols());
}

/**
 * This verifies that a code book constructed from a given set of
 * frequencies may be reconstructed from the cord word bit lengths, given in
 * a non-decreasing order, together with the symbols in a correlated array.
 * 
 * @param frequency
 */
public void doRoundTripTest(final int[] frequency) {
  
  final DecoderInputs decoderInputs = new DecoderInputs();
  
  final HuffmanCodec codec = new HuffmanCodec(frequency, decoderInputs);
  if (log.isDebugEnabled()) {
    log.debug(printCodeBook(codec.codeWords()) + "\nlength[]="
        + Arrays.toString(decoderInputs.getLengths()) + "\nsymbol[]="
        + Arrays.toString(decoderInputs.getSymbols()));
  }
  
  final CanonicalFast64CodeWordDecoder actualDecoder = new CanonicalFast64CodeWordDecoder(
      decoderInputs.getLengths(), decoderInputs.getSymbols());
  for (int i = 0; i < frequency.length; i++) {
    final BooleanIterator coded = codec.coder().encode(i/*symbol*/);
    
    assertEquals(i, actualDecoder.decode(coded));
    
  }
}

/**
 * @param shortestCodeWord
 * @param lengths
 * @param
 */
private void doCoderRoundTripTest(final BitVector[] expected,
    final BitVector shortestCodeWord, final int[] length,
    final int[] symbol) {
  final PrefixCoder newCoder = HuffmanCodec.newCoder(shortestCodeWord,
      length, symbol);
  final BitVector[] actual = newCoder.codeWords();
  assertEquals("codeWord[]", expected, actual);
  if (log.isDebugEnabled()) {
       log.debug("\nexpected: " + Arrays.toString(expected)
        + "\nactual  : " + Arrays.toString(actual));
    
  }
  
}
 

/**
 * Unit test for processing an {@link IRaba} representing B+Tree keys
 * suitable to setup the data for compression.
 * 
 * @throws IOException 
 */
public void test_keyRabaSetup() throws IOException {
  final int n = 8;
  final byte[][] a = new byte[n][];
  a[0] = new byte[]{1,2};
  a[1] = new byte[]{1,2,3};
  a[2] = new byte[]{1,3};
  a[3] = new byte[]{1,3,1};
  a[4] = new byte[]{1,3,3};
  a[5] = new byte[]{1,3,7};
  a[6] = new byte[]{1,5};
  a[7] = new byte[]{1,6,0};
  
  final IRaba raba = new ReadOnlyKeysRaba(a);
  final AbstractCodingSetup setup = new RabaCodingSetup(raba);
  doDecoderInputRoundTripTest(setup.getSymbolCount(), setup
      .decoderInputs());
  // verify that we can re-create the coder.
  doCoderRoundTripTest(setup.codec().codeWords(), setup.decoderInputs()
      .getShortestCodeWord(), setup.decoderInputs().getLengths(),
      setup.decoderInputs().getSymbols());
}

final HuffmanCodec codec = new HuffmanCodec(frequency, decoderInputs);
final PrefixCoder expected = codec.coder();
final PrefixCoder actual = new Fast64CodeWordCoder(codec.codeWords());
  log.debug(printCodeBook(codec.codeWords()));

/**
 * (Re-)constructs the canonical huffman code from the shortest code word,
 * the non-decreasing bit lengths of each code word, and the permutation of
 * the symbols corresponding to those bit lengths. This information is
 * necessary and sufficient to reconstruct a canonical huffman code.
 * 
 * @param decoderInputs
 *            This contains the necessary and sufficient information to
 *            recreate the {@link PrefixCoder}.
 * 
 * @return A new {@link PrefixCoder} instance for the corresponding
 *         canonical huffman code.
 */
static public PrefixCoder newCoder(final DecoderInputs decoderInputs) {
  return newCoder(decoderInputs.getShortestCodeWord(), decoderInputs
      .getLengths(), decoderInputs.getSymbols());
}

/**
 * Unit test for processing an {@link IRaba} representing B+Tree keys
 * suitable to setup the data for compression.
 * 
 * @throws IOException 
 */
public void test_keyRabaSetup() throws IOException {
  final int n = 8;
  final byte[][] a = new byte[n][];
  a[0] = new byte[]{1,2};
  a[1] = new byte[]{1,2,3};
  a[2] = new byte[]{1,3};
  a[3] = new byte[]{1,3,1};
  a[4] = new byte[]{1,3,3};
  a[5] = new byte[]{1,3,7};
  a[6] = new byte[]{1,5};
  a[7] = new byte[]{1,6,0};
  
  final IRaba raba = new ReadOnlyKeysRaba(a);
  final AbstractCodingSetup setup = new RabaCodingSetup(raba);
  doDecoderInputRoundTripTest(setup.getSymbolCount(), setup
      .decoderInputs());
  // verify that we can re-create the coder.
  doCoderRoundTripTest(setup.codec().codeWords(), setup.decoderInputs()
      .getShortestCodeWord(), setup.decoderInputs().getLengths(),
      setup.decoderInputs().getSymbols());
}

final HuffmanCodec codec = new HuffmanCodec(frequency, decoderInputs);
final PrefixCoder expected = codec.coder();
final PrefixCoder actual = new Fast64CodeWordCoder(codec.codeWords());
  log.debug(printCodeBook(codec.codeWords()));

/**
 * (Re-)constructs the canonical huffman code from the shortest code word,
 * the non-decreasing bit lengths of each code word, and the permutation of
 * the symbols corresponding to those bit lengths. This information is
 * necessary and sufficient to reconstruct a canonical huffman code.
 * 
 * @param decoderInputs
 *            This contains the necessary and sufficient information to
 *            recreate the {@link PrefixCoder}.
 * 
 * @return A new {@link PrefixCoder} instance for the corresponding
 *         canonical huffman code.
 */
static public PrefixCoder newCoder(final DecoderInputs decoderInputs) {
  return newCoder(decoderInputs.getShortestCodeWord(), decoderInputs
      .getLengths(), decoderInputs.getSymbols());
}