Cascading Demo

gistfile1.java

Scheme sourceScheme = new TextLine( new Fields( "line" ) );
Tap source = new Hfs( sourceScheme, inputPath );

Scheme sinkScheme = new TextLine( new Fields( "word", "count" ) );
Tap sink = new Hfs( sinkScheme, outputPath, SinkMode.REPLACE );

Pipe assembly = new Pipe( "wordcount" );

String regex = "(?<!\\pL)(?=\\pL)[^ ]*(?<=\\pL)(?!\\pL)";
Function function = new RegexGenerator( new Fields( "word" ), regex );
assembly = new Each( assembly, new Fields( "line" ), function );

assembly = new GroupBy( assembly, new Fields( "word" ) );

Aggregator count = new Count( new Fields( "count" ) );
assembly = new Every( assembly, count );

Properties properties = new Properties();
FlowConnector.setApplicationJarClass( properties, Main.class );

FlowConnector flowConnector = new FlowConnector( properties );
Flow flow = flowConnector.connect( "word-count", source, sink, assembly );
flow.complete();