Example usage for org.apache.cassandra.hadoop.cql3 CqlConfigHelper setOutputCql

Introduction

In this page you can find the example usage for org.apache.cassandra.hadoop.cql3 CqlConfigHelper setOutputCql.

Prototype

public static void setOutputCql(Configuration conf, String cql) 

Source Link

Document

Set the CQL prepared statement for the output of this job.

Usage

From source file:com.dse.pig.udfs.CqlStorage.java

License:Apache License

/** set store configuration settings */
public void setStoreLocation(String location, Job job) throws IOException {
    conf = job.getConfiguration();/*  w  w  w .j  ava  2s .  c o  m*/
    setLocationFromUri(location);

    if (username != null && password != null)
        ConfigHelper.setOutputKeyspaceUserNameAndPassword(conf, username, password);
    if (splitSize > 0)
        ConfigHelper.setInputSplitSize(conf, splitSize);
    if (partitionerClass != null)
        ConfigHelper.setOutputPartitioner(conf, partitionerClass);
    if (rpcPort != null) {
        ConfigHelper.setOutputRpcPort(conf, rpcPort);
        ConfigHelper.setInputRpcPort(conf, rpcPort);
    }
    if (initHostAddress != null) {
        ConfigHelper.setOutputInitialAddress(conf, initHostAddress);
        ConfigHelper.setInputInitialAddress(conf, initHostAddress);
    }

    ConfigHelper.setOutputColumnFamily(conf, keyspace, column_family);
    CqlConfigHelper.setOutputCql(conf, outputQuery);

    setConnectionInformation();

    if (ConfigHelper.getOutputRpcPort(conf) == 0)
        throw new IOException("PIG_OUTPUT_RPC_PORT or PIG_RPC_PORT environment variable not set");
    if (ConfigHelper.getOutputInitialAddress(conf) == null)
        throw new IOException("PIG_OUTPUT_INITIAL_ADDRESS or PIG_INITIAL_ADDRESS environment variable not set");
    if (ConfigHelper.getOutputPartitioner(conf) == null)
        throw new IOException("PIG_OUTPUT_PARTITIONER or PIG_PARTITIONER environment variable not set");

    initSchema(storeSignature);
}

---

From source file:net.orpiske.tcs.wc.main.Main.java

License:Apache License

/**
 * Setup the output to dump the M/R result to word_cloud table on
 * Cassandra/*from   w ww.j a v  a  2s . co m*/
 * @param configuration
 */
private void outputConfiguration(Configuration configuration) {
    ConfigHelper.setOutputInitialAddress(configuration, DB_HOST);
    ConfigHelper.setOutputColumnFamily(configuration, KEYSPACE, OUTPUT_TABLE);
    ConfigHelper.setOutputPartitioner(configuration, PARTITIONER);

    String query = "UPDATE " + KEYSPACE + "." + OUTPUT_TABLE
            + " SET hash = ?, domain = ?, word = ?, occurrences = ?, reference_date = ? ";
    CqlConfigHelper.setOutputCql(configuration, query);
}

---

From source file:org.wikimedia.analytics.refinery.cassandra.CassandraXSVLoader.java

License:Apache License

/**
 * Runs the map-reduce job// www .j a va 2s.  c o m
 */
public int run(String[] args) throws Exception {

    // Configuration from Tool
    Configuration conf = getConf();

    // Checking configuration parameters
    if (!checkConfParameters()) {
        logger.error("Problem with configuration, aborting.");
        System.exit(1);
    }

    //Build cql query
    String cqlQuery = makeCqlQuery();
    logger.info("CQL Query to be run: " + cqlQuery);

    // Parameters ok -> job configuration and launch
    Job job = new Job(conf, "CassandraXSVLoader");
    job.setJarByClass(CassandraXSVLoader.class);

    // Identity Mapper - Nothing to get done at map time
    job.setMapperClass(Mapper.class);
    FileInputFormat.addInputPath(job, new Path(conf.get(INPUT_PATH_PROP)));

    // reducer to cassandra
    job.setReducerClass(ReducerToCassandra.class);

    job.setMapOutputKeyClass(LongWritable.class);
    job.setMapOutputValueClass(Text.class);
    job.setOutputKeyClass(Map.class);
    job.setOutputValueClass(List.class);

    // Use cassandra cql output format
    // This is where the actual connection and data push
    // to cassandra is made
    job.setOutputFormatClass(CqlOutputFormat.class);

    ConfigHelper.setOutputColumnFamily(job.getConfiguration(), quoteIdentifier(conf.get(OUTPUT_KEYSPACE_PROP)),
            quoteIdentifier(conf.get(OUTPUT_COLUMN_FAMILY_PROP)));

    CqlConfigHelper.setOutputCql(job.getConfiguration(), cqlQuery);
    ConfigHelper.setOutputPartitioner(job.getConfiguration(), "Murmur3Partitioner");

    ConfigHelper.setOutputInitialAddress(job.getConfiguration(), conf.get(CASSANDRA_HOST_PROP));

    CqlConfigHelper.setUserNameAndPassword(job.getConfiguration(), conf.get(CASSANDRA_USER_PROP),
            conf.get(CASSANDRA_PASSWD_PROP));

    // If batch size parameters are set, use them
    if ((conf.getInt(CASSANDRA_NODES, 0) > 0) && (conf.getInt(BATCH_SIZE_PROP, 0) > 0)) {
        conf.setInt(ColumnFamilyOutputFormat.BATCH_THRESHOLD, conf.getInt(BATCH_SIZE_PROP, 0));
        conf.setInt(ColumnFamilyOutputFormat.QUEUE_SIZE,
                conf.getInt(BATCH_SIZE_PROP, 0) * conf.getInt(CASSANDRA_NODES, 0) + 1);
    }

    job.waitForCompletion(true);
    return 0;
}

---