Examples of cascading.operation.regex.RegexFilter

cascading.operation.regex.RegexFilter
Class RegexFilter will apply the regex patternString against every input Tuple value and filter the Tuple stream accordingly.
By default, Tuples that match the given pattern are kept, and Tuples that do not match are filtered out. This can be changed by setting removeMatch to true.
Also, by default, the whole Tuple is matched against the given patternString (tab delimited). If matchEachElement is set to true, the pattern is applied to each Tuple value individually.
This operation uses {@link java.util.regex.Matcher} internally, specifically the method {@link java.util.regex.Matcher#find()}. @see java.util.regex.Matcher @see java.util.regex.Pattern


    pipe = new GroupBy( pipe, new Fields( "ip" ) );


    pipe = new Every( pipe, new Fields( "ip" ), new Count(), new Fields( "ip", "count" ) );


    pipe = new Each( pipe, new Fields( "ip" ), new RegexFilter( "^68.*" ) );


    Pipe left = new Each( pipe, new Fields( "ip" ), new RegexFilter( ".*46.*" ) );


    left = new Pipe( "left", left );


    Pipe right = new Each( pipe, new Fields( "ip" ), new RegexFilter( ".*192.*" ) );


    right = new Pipe( "right", right );


    Map sources = new HashMap();
    sources.put( "split", source );

View Full Code Here

    Tap source1 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge1" );
    Tap source2 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge2" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe left = new Each( new Pipe( "left" ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right" ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Pipe merge = new GroupBy( "merge", Pipe.pipes( left, right ), new Fields( "offset" ) );


    Map sources = new HashMap();
    sources.put( "left", source1 );

View Full Code Here

    Tap source1 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge" );
    Tap source2 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe left = new Each( new Pipe( "left" ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right" ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );
    right = new Each( right, new Fields( "line" ), new RegexFilter( ".*192.*" ) );
    right = new Each( right, new Fields( "line" ), new RegexFilter( ".*192.*" ) );
    right = new Each( right, new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Pipe merge = new GroupBy( "merge", Pipe.pipes( left, right ), new Fields( "offset" ) );


    Map sources = new HashMap();
    sources.put( "left", source1 );

View Full Code Here

    Tap source1 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge1" );
    Tap source2 = new Hfs( new SequenceFile( new Fields( "offset", "line" ) ), "foo/merge2" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe left = new Each( new Pipe( "left" ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right" ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Pipe merge = new GroupBy( "merge", Pipe.pipes( left, right ), new Fields( "offset" ) );


    Map sources = new HashMap();
    sources.put( "left", source1 );

View Full Code Here


    Pipe head = new Pipe( "source" );


    head = new Each( head, new Fields( "line" ), new ExpressionFilter( "line.length() != 0", String.class ) );


    Pipe left = new Each( new Pipe( "left", head ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right", head ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Pipe merge = new GroupBy( "merge", Pipe.pipes( left, right ), new Fields( "offset" ) );


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

View Full Code Here

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


    Pipe splice = new CoGroup( "both", pipeLower, new Fields( "num" ), pipeUpper, new Fields( "num" ), new Fields( "num", "lower", "num2", "upper" ) );


    splice = new Each( splice, new Fields( "num" ), new RegexFilter( ".*" ) );


    Pipe left = splice;


    if( before )
      left = new Pipe( "left", left );


    left = new Each( left, new Fields( "num" ), new RegexFilter( ".*" ) );


    if( !before )
      left = new Pipe( "left", left );


    Pipe right = left;


    if( before )
      right = new Pipe( "right", right );


    right = new Each( right, new Fields( "num" ), new RegexFilter( ".*" ) );


    if( !before )
      right = new Pipe( "right", right );


    FlowConnector flowConnector = getPlatform().getFlowConnector();

View Full Code Here

    Tap source1 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge1" );
    Tap source2 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge2" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe left = new Each( new Pipe( "left" ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right" ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Fields[] fields = Fields.fields( new Fields( "offset" ), new Fields( "offset" ) );
    Pipe merge = new HashJoin( "join", Pipe.pipes( left, right ), fields, Fields.size( 4 ), new InnerJoin() );


    merge = new Every( merge, new MaxValue() );

View Full Code Here

    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );
    Tap sink = getPlatform().getTextFile( getOutputPath( "splitsourcemerged" ), SinkMode.REPLACE );


    Pipe pipe = new Pipe( "split" );


    pipe = new Each( pipe, new Fields( "line" ), new RegexFilter( "^68.*" ) );


    Pipe left = new Each( new Pipe( "left", pipe ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right", pipe ), new Fields( "line" ), new RegexFilter( ".*102.*" ) );


    Pipe merged = new Merge( "merged", left, right );


    merged = new Each( merged, new Fields( "line" ), new Identity() );

View Full Code Here

    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );
    Tap sink = getPlatform().getTextFile( getOutputPath( "splitsourcemergedcomplex" ), SinkMode.REPLACE );


    Pipe pipe = new Pipe( "split" );


    pipe = new Each( pipe, new Fields( "line" ), new RegexFilter( "^68.*" ) );


    Pipe left = new Each( new Pipe( "left", pipe ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right", pipe ), new Fields( "line" ), new RegexFilter( ".*102.*" ) );


    Pipe merged = new Merge( "merged-first", left, right );


    merged = new Each( merged, new Fields( "line" ), new Identity() );


    left = new Each( new Pipe( "left", merged ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    right = new Each( new Pipe( "right", merged ), new Fields( "line" ), new RegexFilter( ".*102.*" ) );


    merged = new Merge( "merged-second", left, right );


    merged = new Each( merged, new Fields( "line" ), new Identity() );

View Full Code Here

    // skip the first line
    pipe = new Each( pipe, new Fields( 0 ), new ExpressionFilter( "$0 == 0", Long.class ) );


    pipe = new Each( pipe, new Fields( 1 ), new Identity() );


    pipe = new Each( pipe, Fields.ALL, new RegexFilter( "a|b|c" ) );


    pipe = new GroupBy( pipe, new Fields( 0 ) );


    Aggregator counter = new Count();

View Full Code Here

0 1 2 3 4 5

TOP

Related Classes of cascading.operation.regex.RegexFilter

cascading.assembly.CrossTab

cascading.BasicPipesPlatformTest

cascading.CoGroupFieldedPipesPlatformTest

cascading.DistanceUseCasePlatformTest

cascading.FieldedPipesPlatformTest

cascading.flow.hadoop.BuildJobsHadoopPlatformTest

cascading.flow.iso.graph.LoneGroupAssertionGraph

cascading.function.FunctionPlatformTest

cascading.JoinFieldedPipesPlatformTest

cascading.MergePipesPlatformTest

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.