Examples of RegexSplitter

cascading.operation.regex.RegexSplitter
Class RegexSplitter will split an incoming argument value by the given regex delimiter patternString.

Examples of cascading.operation.regex.RegexSplitter


//    uniques = new Each( uniques, new Debug( true ) );


    Pipe fielded = new Pipe( "fielded" );


    fielded = new Each( fielded, new Fields( "line" ), new RegexSplitter( "\\s" ) );


//    fielded = new Each( fielded, new Debug( true ) );


    Pipe inner = new CoGroup( "inner", fielded, new Fields( 0 ), uniques, new Fields( "word" ), new InnerJoin() );
    Pipe outer = new CoGroup( "outer", fielded, new Fields( 0 ), uniques, new Fields( "word" ), new OuterJoin() );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter


  private Flow secondFlow( Tap source, String path )
    {
    Pipe pipe = new Pipe( "second" );


    pipe = new Each( pipe, new RegexSplitter( new Fields( "first", "second", "third", "fourth" ), "\\." ) );


    Tap sink = getPlatform().getTabDelimitedFile( new Fields( "first", "second", "third", "fourth" ), getOutputPath( path + "/second" ), SinkMode.REPLACE );


    return getPlatform().getFlowConnector().connect( source, sink, pipe );
    }

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter


  private Flow secondFlow( Tap source, String path )
    {
    Pipe pipe = new Pipe( "second" );


    pipe = new Each( pipe, new RegexSplitter( new Fields( "first", "second", "third", "fourth" ), "\\." ) );


    Tap sink = getPlatform().getTabDelimitedFile( new Fields( "first", "second", "third", "fourth" ), getOutputPath( path ), SinkMode.REPLACE );


    return getPlatform().getFlowConnector().connect( source, sink, pipe );
    }

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter


    Tap source = getPlatform().getTextFile( new Fields( "line" ), inputFileApache );


    Pipe pipe = new Pipe( "test" );


    pipe = new Each( pipe, new RegexSplitter( "\\s+" ), new Fields( 1 ) );


    Tap sink = getPlatform().getTextFile( new Fields( "line" ), getOutputPath( "nogroup" ), SinkMode.REPLACE );


    Flow flow = getPlatform().getFlowConnector().connect( source, sink, pipe );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter

    Map sources = new HashMap();


    sources.put( "lower", sourceLower );
    sources.put( "upper", sourceUpper );


    Function splitter = new RegexSplitter( new Fields( "num", "char" ), " " );


    // using null pos so all fields are written
    Tap sink = getPlatform().getTextFile( new Fields( "line" ), getOutputPath( "simplemerge" ), SinkMode.REPLACE );


    Pipe pipeLower = new Each( new Pipe( "lower" ), new Fields( "line" ), splitter );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter

    sources.put( "upper", sourceUpper );
    sources.put( "offset", sourceLowerOffset );


    Tap sink = getPlatform().getDelimitedFile( Fields.ALL, "\t", getOutputPath( "simplemergethree" ), SinkMode.REPLACE );


    Function splitter = new RegexSplitter( new Fields( "num", "char" ), " " );


    Pipe pipeLower = new Each( new Pipe( "lower" ), new Fields( "line" ), splitter );
    Pipe pipeUpper = new Each( new Pipe( "upper" ), new Fields( "line" ), splitter );
    Pipe pipeOffset = new Each( new Pipe( "offset" ), new Fields( "line" ), splitter );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter


    sources.put( "split", sourceLower );


    Tap sink = getPlatform().getTextFile( getOutputPath( "samemergethreechaingroup" ), SinkMode.REPLACE );


    Function splitter = new RegexSplitter( new Fields( "num", "char" ), " " );


    Pipe pipe = new Pipe( "split" );


    Pipe pipeLower = new Each( new Pipe( "lower", pipe ), new Fields( "line" ), splitter );
    Pipe pipeUpper = new Each( new Pipe( "upper", pipe ), new Fields( "line" ), splitter );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter

    Tap source = getPlatform().getTextFile( inputFileJoined );
    Tap sink = getPlatform().getTextFile( getOutputPath( "ungrouped" ), SinkMode.REPLACE );


    Pipe pipe = new Pipe( "test" );


    pipe = new Each( pipe, new Fields( "line" ), new RegexSplitter( new Fields( "num", "lower", "upper" ) ) );


    pipe = new Each( pipe, new UnGroup( new Fields( "num", "char" ), new Fields( "num" ), Fields.fields( new Fields( "lower" ), new Fields( "upper" ) ) ) );


    Flow flow = getPlatform().getFlowConnector().connect( source, sink, pipe );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter

    Tap source = getPlatform().getTextFile( inputFileJoined );
    Tap sink = getPlatform().getTextFile( getOutputPath( "ungroupedanon" ), SinkMode.REPLACE );


    Pipe pipe = new Pipe( "test" );


    pipe = new Each( pipe, new Fields( "line" ), new RegexSplitter( new Fields( "num", "lower", "upper" ) ) );


    pipe = new Each( pipe, new UnGroup( new Fields( "num" ), Fields.fields( new Fields( "lower" ), new Fields( "upper" ) ) ) );


    Flow flow = getPlatform().getFlowConnector().connect( source, sink, pipe );

View Full Code Here

Examples of cascading.operation.regex.RegexSplitter


  private Flow secondFlow( String name, Tap source )
    {
    Pipe pipe = new Pipe( name );


    pipe = new Each( pipe, new RegexSplitter( new Fields( "first", "second", "third", "fourth" ), "\\." ) );
    pipe = new Each( pipe, new FieldJoiner( new Fields( "mangled" ), "-" ) );


    Tap sink = getPlatform().getTabDelimitedFile( new Fields( "mangled" ), getOutputPath( name ), SinkMode.REPLACE );


    return getPlatform().getFlowConnector().connect( source, sink, pipe );

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.