ceteri

bash-3.2$ pwd
/Users/ceteri/src/concur/pattern
bash-3.2$ java -version
java version "1.6.0_43"
Java(TM) SE Runtime Environment (build 1.6.0_43-b01-447-11M4203)
Java HotSpot(TM) 64-Bit Server VM (build 20.14-b01-447, mixed mode)
bash-3.2$ hadoop version
Warning: $HADOOP_HOME is deprecated.

Hadoop 1.0.3

ceteri

bash-3.2$ lein repl
Listening for transport dt_socket at address: 51539
nREPL server started on port 51542
REPL-y 0.1.0-beta10
Clojure 1.4.0
    Exit: Control+D or (exit) or (quit)
Commands: (user/help)
    Docs: (doc function-name-here)
          (find-doc "part-of-name-here")
  Source: (source function-name-here)

ceteri

import com.twitter.scalding._

class Example3(args : Args) extends Job(args) {
  Tsv(args("doc"), ('doc_id, 'text), skipHeader = true)
    .read
    .flatMap('text -> 'token) { text : String => text.split("[ \\[\\]\\(\\),.]") }
    .mapTo('token -> 'token) { token : String => scrub(token) }
    .filter('token) { token : String => token.length > 0 }
    .groupBy('token) { _.size('count) }
    .write(Tsv(args("wc"), writeHeader = true))

ccsevers

package cascading.avro.examples;

import java.util.Properties;

import cascading.flow.Flow;
import cascading.flow.FlowDef;
import cascading.flow.hadoop.HadoopFlowConnector;
import cascading.operation.aggregator.Count;
import cascading.operation.regex.RegexFilter;
import cascading.operation.regex.RegexSplitGenerator;

ceteri

bash-3.2$ java -version
java version "1.6.0_33"
Java(TM) SE Runtime Environment (build 1.6.0_33-b03-424-11M3720)
Java HotSpot(TM) 64-Bit Server VM (build 20.8-b03-424, mixed mode)
bash-3.2$ hadoop -version
Warning: $HADOOP_HOME is deprecated.

java version "1.6.0_33"
Java(TM) SE Runtime Environment (build 1.6.0_33-b03-424-11M3720)
Java HotSpot(TM) 64-Bit Server VM (build 20.8-b03-424, mixed mode)

ceteri

public class
  Main
  {
  public static void
  main( String[] args )
    {
    String docPath = args[ 0 ];
    String wcPath = args[ 1 ];
    String stopPath = args[ 2 ];
    String tfidfPath = args[ 3 ];

ceteri

public class
  Main
  {
  public static void
  main( String[] args )
    {
    String docPath = args[ 0 ];
    String wcPath = args[ 1 ];
    String stopPath = args[ 2 ];
    String tfidfPath = args[ 3 ];

ceteri

public class
  Main
  {
  public static void
  main( String[] args )
    {
    String docPath = args[ 0 ];
    String wcPath = args[ 1 ];
    String stopPath = args[ 2 ];

ceteri

public class
  Main
  {
  public static void
  main( String[] args )
    {
    String docPath = args[ 0 ];
    String wcPath = args[ 1 ];

    Properties properties = new Properties();

ceteri

public class
  Main
  {
  public static void
  main( String[] args )
    {
    String docPath = args[ 0 ];
    String wcPath = args[ 1 ];

    Properties properties = new Properties();