Package cascading.operation.regex

Examples of cascading.operation.regex.RegexSplitter

1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
//    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
65
66
67
68
69
70
71
72
73
74
75
  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
90
91
92
93
94
95
96
97
98
99
100
  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
156
157
158
159
160
161
162
163
164
165
166
    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
203
204
205
206
207
208
209
210
211
212
213
    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
255
256
257
258
259
260
261
262
263
264
265
    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
301
302
303
304
305
306
307
308
309
310
311
    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
335
336
337
338
339
340
341
342
343
344
345
    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
356
357
358
359
360
361
362
363
364
365
366
    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
61
62
63
64
65
66
67
68
69
70
71
  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
TOP

Related Classes of cascading.operation.regex.RegexSplitter

  • cascading.BasicPipesPlatformTest
  • cascading.BufferPipesPlatformTest
  • cascading.cascade.CascadePlatformTest
  • cascading.cascade.hadoop.RiffleCascadePlatformTest
  • cascading.cascade.ParallelCascadePlatformTest
  • cascading.CoGroupFieldedPipesPlatformTest
  • cascading.DistanceUseCasePlatformTest
  • cascading.FieldedPipesPlatformTest
  • cascading.flow.hadoop.BuildJobsHadoopPlatformTest
  • cascading.flow.hadoop.FlowPlatformTest
    • 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.