Package cascading.operation.regex

Examples of cascading.operation.regex.RegexParser

492
493
494
495
496
497
498
499
500
501
502
    Pipe pipe = new Pipe( "test" );

    String regex = "^([^ ]*) +[^ ]* +[^ ]* +\\[([^]]*)\\] +\\\"([^ ]*) ([^ ]*) [^ ]*\\\" ([^ ]*) ([^ ]*).*$";
    Fields fieldDeclaration = new Fields( "ip", "time", "method", "event", "status", "size" );
    int[] groups = {1, 2, 3, 4, 5, 6};
    RegexParser function = new RegexParser( fieldDeclaration, regex, groups );
    pipe = new Each( pipe, new Fields( "line" ), function );

    pipe = new Each( pipe, new Fields( "method" ), new RegexFilter( "^fobar" ) ); // intentionally filtering all

    pipe = new GroupBy( pipe, new Fields( "method" ) );
View Full Code Here
697
698
699
700
701
702
703
704
705
706
707
    Tap sink1 = getPlatform().getTextFile( getOutputPath( "splitcomp1" ), SinkMode.REPLACE );
    Tap sink2 = getPlatform().getTextFile( getOutputPath( "splitcomp2" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "split" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );

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

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

View Full Code Here
756
757
758
759
760
761
762
763
764
765
766
    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );

    Pipe pipe = new Pipe( "test" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );

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

    pipe = new Every( pipe, new TestAggregator( new Fields( "count1" ), new Fields( "ip" ), new Tuple( "first1" ), new Tuple( "first2" ) ) );
    pipe = new Every( pipe, new TestAggregator( new Fields( "count2" ), new Fields( "ip" ), new Tuple( "second" ), new Tuple( "second2" ), new Tuple( "second3" ) ) );
View Full Code Here
780
781
782
783
784
785
786
787
788
789
790
    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );
    Tap sink = getPlatform().getTextFile( new Fields( "offset", "line" ), new Fields( "offset", "line" ), getOutputPath( "replace" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

    Function parser = new RegexParser( new Fields( 0 ), "^[^ ]*" );
    pipe = new Each( pipe, new Fields( "line" ), parser, Fields.REPLACE );
    pipe = new Each( pipe, new Fields( "line" ), new Identity( Fields.ARGS ), Fields.REPLACE );
    pipe = new Each( pipe, new Fields( "line" ), new Identity( new Fields( "line" ) ), Fields.REPLACE );

    pipe = new Each( pipe, new Debug( true ) );
View Full Code Here
802
803
804
805
806
807
808
809
810
811
812
    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );
    Tap sink = getPlatform().getTextFile( new Fields( "offset", "line" ), new Fields( "count", "ipaddress" ), getOutputPath( "swap" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

    Function parser = new RegexParser( new Fields( "ip" ), "^[^ ]*" );
    pipe = new Each( pipe, new Fields( "line" ), parser, Fields.SWAP );
    pipe = new GroupBy( pipe, new Fields( "ip" ) );
    pipe = new Every( pipe, new Fields( "ip" ), new Count( new Fields( "count" ) ) );
    pipe = new Each( pipe, new Fields( "ip" ), new Identity( new Fields( "ipaddress" ) ), Fields.SWAP );

View Full Code Here
823
824
825
826
827
828
829
830
831
832
833
    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );
    Tap sink = getPlatform().getTextFile( new Fields( "offset", "line" ), new Fields( "count", "ip" ), getOutputPath( "none" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

    Function parser = new RegexParser( new Fields( "ip" ), "^[^ ]*" );
    pipe = new Each( pipe, new Fields( "line" ), parser, Fields.ALL );
    pipe = new Each( pipe, new Fields( "line" ), new NoOp(), Fields.SWAP ); // declares Fields.NONE
    pipe = new GroupBy( pipe, new Fields( "ip" ) );
    pipe = new Every( pipe, new Fields( "ip" ), new Count( new Fields( "count" ) ) );
    pipe = new Each( pipe, Fields.NONE, new Insert( new Fields( "ipaddress" ), "1.2.3.4" ), Fields.ALL );
View Full Code Here
882
883
884
885
886
887
888
889
890
891
892
    Tap source = getPlatform().getTextFile( new Fields( "offset", "line" ), inputFileApache );

    Pipe pipe = new Pipe( "test" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );

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

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

View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
    {
    getPlatform().copyFromLocal( inputFileApache );

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

    Pipe pipe = new Each( new Pipe( "first" ), new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );
    pipe = new GroupBy( pipe, new Fields( "ip" ) );

    pipe = new Each( new Pipe( "second", pipe ), new Fields( "ip" ), new RegexFilter( "7" ) );
    pipe = new GroupBy( pipe, new Fields( "ip" ) );

View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
    {
    Tap source = getPlatform().getTextFile( "foosource" );

    Pipe pipe = new Pipe( "test" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );

    // always fail
    pipe = new Each( pipe, new Fields( "ip" ), new TestFunction( new Fields( "test" ), null ), Fields.ALL );

    pipe = new GroupBy( pipe, new Fields( "ip" ) );
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
    Tap source = getPlatform().getTextFile( "foosource" );

    Pipe pipe = new Pipe( "map" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexParser( new Fields( "ip" ), "^[^ ]*" ), new Fields( "ip" ) );

    // always fail
    pipe = new Each( pipe, new Fields( "ip" ), new TestFunction( new Fields( "test" ), null ), Fields.ALL );

    pipe = new GroupBy( "reduce", pipe, new Fields( "ip" ) );
View Full Code Here
TOP

Related Classes of cascading.operation.regex.RegexParser

  • bixo.examples.webmining.DemoWebMiningWorkflow
  • cascading.BasicPipesPlatformTest
  • cascading.BasicTrapPlatformTest
  • cascading.FieldedPipesPlatformTest
  • cascading.flow.AssemblyPlannerPlatformTest
  • cascading.flow.FlowStrategiesPlatformTest
  • cascading.flow.hadoop.BuildJobsHadoopPlatformTest
  • cascading.flow.SubAssemblyPlatformTest$TestAssembly
  • cascading.operation.assertion.BuildAssertionsPlatformTest
  • cascading.operation.debug.BuildDebugPlatformTest
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.