Example usage for com.google.common.hash Hashing murmur3

Introduction

In this page you can find the example usage for com.google.common.hash Hashing murmur3_128.

Prototype

public static HashFunction murmur3_128(int seed)

Source Link

Document

Returns a hash function implementing the <a href="http://smhasher.googlecode.com/svn/trunk/MurmurHash3.cpp"> 128-bit murmur3 algorithm, x64 variant</a> (little-endian variant), using the given seed value.

Usage

From source file:com.github.mgunlogson.cuckoofilter4j.SerializableSaltedHasher.java

private static HashFunction configureHash(Algorithm alg, long seedNSalt, long addlSipSeed) {
    switch (alg) {
    case xxHash64:
        return new xxHashFunction(seedNSalt);
    case Murmur3_128:
        return Hashing.murmur3_128((int) seedNSalt);
    case Murmur3_32:
        return Hashing.murmur3_32((int) seedNSalt);
    case sha256:/*  ww w . j ava 2  s. c o  m*/
        return Hashing.sha1();
    case sipHash24:
        return Hashing.sipHash24(seedNSalt, addlSipSeed);
    default:
        throw new IllegalArgumentException("Invalid Enum Hashing Algorithm???");
    }
}

From source file:org.apache.flink.migration.streaming.api.graph.StreamGraphHasherV1.java

@Override
public Map<Integer, byte[]> traverseStreamGraphAndGenerateHashes(StreamGraph streamGraph) {
    // The hash function used to generate the hash
    final HashFunction hashFunction = Hashing.murmur3_128(0);
    final Map<Integer, byte[]> hashes = new HashMap<>();

    Set<Integer> visited = new HashSet<>();
    Queue<StreamNode> remaining = new ArrayDeque<>();

    // We need to make the source order deterministic. The source IDs are
    // not returned in the same order, which means that submitting the same
    // program twice might result in different traversal, which breaks the
    // deterministic hash assignment.
    List<Integer> sources = new ArrayList<>();
    for (Integer sourceNodeId : streamGraph.getSourceIDs()) {
        sources.add(sourceNodeId);// w w  w  . j av a2  s.co m
    }
    Collections.sort(sources);

    //
    // Traverse the graph in a breadth-first manner. Keep in mind that
    // the graph is not a tree and multiple paths to nodes can exist.
    //

    // Start with source nodes
    for (Integer sourceNodeId : sources) {
        remaining.add(streamGraph.getStreamNode(sourceNodeId));
        visited.add(sourceNodeId);
    }

    StreamNode currentNode;
    while ((currentNode = remaining.poll()) != null) {
        // Generate the hash code. Because multiple path exist to each
        // node, we might not have all required inputs available to
        // generate the hash code.
        if (generateNodeHash(currentNode, hashFunction, hashes, streamGraph.isChainingEnabled())) {
            // Add the child nodes
            for (StreamEdge outEdge : currentNode.getOutEdges()) {
                StreamNode child = outEdge.getTargetVertex();

                if (!visited.contains(child.getId())) {
                    remaining.add(child);
                    visited.add(child.getId());
                }
            }
        } else {
            // We will revisit this later.
            visited.remove(currentNode.getId());
        }
    }

    return hashes;
}

From source file:com.scurrilous.circe.guava.GuavaHashProvider.java

@Override
protected Hash get(HashParameters params, EnumSet<HashSupport> required) {
    if (params instanceof SipHash24Parameters) {
        final SipHash24Parameters sipParams = (SipHash24Parameters) params;
        return new HasherLongHash(Hashing.sipHash24(sipParams.seedLow(), sipParams.seedHigh()),
                params.algorithm());/*  w ww. j  a  va  2  s.  c  o  m*/
    }
    if (params instanceof MurmurHash3Parameters) {
        final MurmurHash3Parameters murmurParams = (MurmurHash3Parameters) params;
        final int seed = murmurParams.seed();
        switch (murmurParams.variant()) {
        case X86_32:
            return new HasherIntHash(Hashing.murmur3_32(seed), params.algorithm());
        case X64_128:
            return new HasherHash(Hashing.murmur3_128(seed), params.algorithm());
        default:
            throw new UnsupportedOperationException();
        }
    }
    throw new UnsupportedOperationException();
}

From source file:org.knime.ext.textprocessing.nodes.transformation.documentvectorhashing.Murmur3_128bitHashingFunction.java

/**
 * {@inheritDoc}/*from w ww  .  j  a  v  a2  s . com*/
 */
@Override
public int hash(final String term, final int seed) {
    HashFunction hash = Hashing.murmur3_128(seed);
    HashCode hashCode = hash.hashString(term, Charsets.UTF_8);
    return hashCode.asInt();
}

From source file:org.apache.flink.streaming.runtime.partitioner.PartialPartitioner.java

@Override
public int[] selectChannels(SerializationDelegate<StreamRecord<T>> record, int numChannels) {
    if (!initializedStats) {
        this.targetChannelStats = new long[numChannels];
        this.initializedStats = true;
        h = new HashFunction[this.workersPerKey];
        for (int i = 0; i < this.workersPerKey; i++) {
            currentPrime = getNextPrime(currentPrime);
            h[i] = Hashing.murmur3_128(currentPrime);
        }/*  w  w  w  .  j a v  a 2  s. com*/
    }
    int[] choices;
    Object key;
    try {
        key = keySelector.getKey(record.getInstance().getValue());
        int counter = 0;
        choices = new int[this.workersPerKey];
        if (this.workersPerKey == numChannels) {
            while (counter < this.workersPerKey) {
                choices[counter] = counter;
                counter++;
            }
        } else {
            while (counter < this.workersPerKey) {
                choices[counter] = (int) (Math.abs(h[counter].hashBytes(serialize(key)).asLong())
                        % numChannels);
                counter++;
            }
        }
    } catch (Exception e) {
        throw new RuntimeException("Could not extract key from " + record.getInstance().getValue(), e);
    }
    int selected = selectMinWorker(targetChannelStats, choices);
    targetChannelStats[selected]++;

    returnArray[0] = selected;
    return returnArray;
}

From source file:org.apache.flink.streaming.api.graph.StreamGraphHasherV2.java

/**
 * Returns a map with a hash for each {@link StreamNode} of the {@link
 * StreamGraph}. The hash is used as the {@link JobVertexID} in order to
 * identify nodes across job submissions if they didn't change.
 *
 * <p>// w ww  . j av  a 2s  .com
 * <p>The complete {@link StreamGraph} is traversed. The hash is either
 * computed from the transformation's user-specified id (see
 * {@link StreamTransformation#getUid()}) or generated in a deterministic way.
 *
 * <p>
 * <p>The generated hash is deterministic with respect to:
 * <ul>
 * <li>node-local properties (like parallelism, UDF, node ID),
 * <li>chained output nodes, and
 * <li>input nodes hashes
 * </ul>
 *
 * @return A map from {@link StreamNode#id} to hash as 16-byte array.
 */
@Override
public Map<Integer, byte[]> traverseStreamGraphAndGenerateHashes(StreamGraph streamGraph) {
    // The hash function used to generate the hash
    final HashFunction hashFunction = Hashing.murmur3_128(0);
    final Map<Integer, byte[]> hashes = new HashMap<>();

    Set<Integer> visited = new HashSet<>();
    Queue<StreamNode> remaining = new ArrayDeque<>();

    // We need to make the source order deterministic. The source IDs are
    // not returned in the same order, which means that submitting the same
    // program twice might result in different traversal, which breaks the
    // deterministic hash assignment.
    List<Integer> sources = new ArrayList<>();
    for (Integer sourceNodeId : streamGraph.getSourceIDs()) {
        sources.add(sourceNodeId);
    }
    Collections.sort(sources);

    //
    // Traverse the graph in a breadth-first manner. Keep in mind that
    // the graph is not a tree and multiple paths to nodes can exist.
    //

    // Start with source nodes
    for (Integer sourceNodeId : sources) {
        remaining.add(streamGraph.getStreamNode(sourceNodeId));
        visited.add(sourceNodeId);
    }

    StreamNode currentNode;
    while ((currentNode = remaining.poll()) != null) {
        // Generate the hash code. Because multiple path exist to each
        // node, we might not have all required inputs available to
        // generate the hash code.
        if (generateNodeHash(currentNode, hashFunction, hashes, streamGraph.isChainingEnabled())) {
            // Add the child nodes
            for (StreamEdge outEdge : currentNode.getOutEdges()) {
                StreamNode child = outEdge.getTargetVertex();

                if (!visited.contains(child.getId())) {
                    remaining.add(child);
                    visited.add(child.getId());
                }
            }
        } else {
            // We will revisit this later.
            visited.remove(currentNode.getId());
        }
    }

    return hashes;
}

From source file:edu.umd.marbl.mhap.sketch.HashUtils.java

public final static long[][] computeNGramHashesExact(final String seq, final int nGramSize, final int numWords,
        final int seed) {
    HashFunction hf = Hashing.murmur3_128(seed);

    long[][] hashes = new long[seq.length() - nGramSize + 1][numWords];
    for (int iter = 0; iter < hashes.length; iter++) {
        String subStr = seq.substring(iter, iter + nGramSize);

        for (int word = 0; word < numWords; word++) {
            HashCode hc = hf.newHasher().putUnencodedChars(subStr).putInt(word).hash();
            hashes[iter][word] = hc.asLong();
        }/* w  w w . ja  va  2 s .  co m*/
    }

    return hashes;
}