Package cascading.operation.regex

Examples of cascading.operation.regex.RegexSplitter


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

    Pipe pipe = new Pipe( "test" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexSplitter( Fields.UNKNOWN ) );

    pipe = new Each( pipe, new Debug() );

    pipe = new Each( pipe, new Fields( 2 ), new Identity( new Fields( "label" ) ) );
View Full Code Here


    Tap source = getPlatform().getTextFile( inputFileCritics );
    Tap sink = getPlatform().getTextFile( getOutputPath( "varwidth" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

    pipe = new Each( pipe, new Fields( "line" ), new RegexSplitter( Fields.UNKNOWN ) );

    pipe = new Each( pipe, AssertionLevel.STRICT, new AssertSizeMoreThan( 3 ) );

    pipe = new Each( pipe, new Fields( 0, 1, -1 ), new Identity( new Fields( "name", "second", "last" ) ) );
View Full Code Here

    Tap sink = getPlatform().getTextFile( getOutputPath( "ungrouped-unknown-nondeterministic" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

    // emits Fields.UNKNOWN
    pipe = new Each( pipe, new Fields( 1 ), new RegexSplitter( "\t" ), Fields.ALL );

    // accepts Fields.UNKNOWN
    pipe = new Each( pipe, new UnGroup( Fields.size( 2 ), new Fields( 0 ), Fields.fields( new Fields( 1 ), new Fields( 2 ) ) ) );

    Flow flow = getPlatform().getFlowConnector().connect( source, sink, pipe );
View Full Code Here

    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 = new Hfs( new SequenceFile( Fields.ALL ), getOutputPath( "writablekeyvalue" ), SinkMode.REPLACE );

    Pipe pipeLower = new Each( new Pipe( "lower" ), new Fields( "line" ), splitter );
View Full Code Here

    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 = new Hfs( new TextLine( new Fields( "line" ) ), getOutputPath( "byteswritablekeyvalue" ), SinkMode.REPLACE );

    Pipe pipeLower = new Each( new Pipe( "lower" ), new Fields( "line" ), splitter );
View Full Code Here

    Map sources = new HashMap();

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

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

    Tap sink = new Hfs( new SequenceFile( Fields.ALL ), getOutputPath( "customerwritable" ), SinkMode.REPLACE );

    Pipe pipeLower = new Each( new Pipe( "lower" ), new Fields( "line" ), splitter );
    pipeLower = new Each( pipeLower, new InsertTestText( new Fields( "group" ), "inserted text as bytes", false ), Fields.ALL );
View Full Code Here

    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
    Fields fields = new Fields( "num", "char", "group", "value", "num2", "char2", "group2", "value2" );
    Tap sink = new Hfs( new SequenceFile( fields ), getOutputPath( "/rawbyteskeyvalue/" + useDefaultComparator + "/" + secondarySortOnValue + "/" + ignoreSerializationToken + "/" + compositeGrouping ), SinkMode.REPLACE );
View Full Code Here


    Map sinks = new HashMap();
    sinks.put( "sink", new NonTap( "sink", new Fields( "offset", "line" ) ) );

    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 pipeLhs = new Each( new Pipe( "lhs" ), new Fields( "line" ), splitter );
View Full Code Here

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

    Pipe pipe = new Pipe( "test" );

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

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

    pipe = new Every( pipe, new TestBuffer( new Fields( "next" ), 2, true, true, "next" ) );
View Full Code Here

    Tap source = getPlatform().getTextFile( inputFileLhs );
    Tap sink = getPlatform().getTextFile( new Fields( "line" ), getOutputPath( "simple2" ), SinkMode.REPLACE );

    Pipe pipe = new Pipe( "test" );

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

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

    pipe = new Every( pipe, new Fields( "lower" ), new TestBuffer( new Fields( "next" ), 1, true, "next" ), Fields.RESULTS );
View Full Code Here

TOP

Related Classes of cascading.operation.regex.RegexSplitter

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.