Examples of cascading.scheme.hadoop.TextLine

cascading.scheme.hadoop.TextLine
A TextLine is a type of {@link cascading.scheme.Scheme} for plain text files. Files are broken intolines. Either line-feed or carriage-return are used to signal end of line.
By default, this scheme returns a {@link Tuple} with two fields, "offset" and "line".
Many of the constructors take both "sourceFields" and "sinkFields". sourceFields denote the field names to be used instead of the names "offset" and "line". sinkFields is a selector and is by default {@link Fields#ALL}. Any available field names can be given if only a subset of the incoming fields should be used.
If a {@link Fields} instance is passed on the constructor as sourceFields having only one field, the return tupleswill simply be the "line" value using the given field name.
Note that TextLine will concatenate all the Tuple values for the selected fields with a TAB delimiter before writing out the line.
Note sink compression is {@link Compress#DISABLE} by default. If {@code null} is passed to the constructorfor the compression value, it will remain disabled.
If any of the input files end with ".zip", an error will be thrown. *
By default, all text is encoded/decoded as UTF-8. This can be changed via the {@code charsetName} constructorargument.

    {
    getPlatform().copyFromLocal( inputFileApache );


    Fields sourceFields = new Fields( "offset", "line" ).applyTypes( Coercions.BIG_DECIMAL, String.class );


    Tap source = new Hfs( new TextLine( sourceFields ), inputFileApache );


    Pipe pipe = new Pipe( "test" );


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

View Full Code Here

    }


  @Test
  public void testCoGroupAroundCoGroupAroundCoGroup() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "lower", sourceLower );
    sources.put( "upper1", sourceUpper );
    sources.put( "upper2", sourceUpper );


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


    // using null pos so all fields are written
    Tap sink = new Hfs( new TextLine(), "output", true );


    Pipe pipeLower = new Each( "lower", new Fields( "line" ), splitter );
    Pipe pipeUpper1 = new Each( "upper1", new Fields( "line" ), splitter );
    Pipe pipeUpper2 = new Each( "upper2", new Fields( "line" ), splitter );

View Full Code Here

    }


  @Test
  public void testCoGroupWithResultGroupFieldsDefault() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "bar" );


    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(), "/complex/cogroup/", true );


    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( pipeLower, new Fields( "num" ), pipeUpper, new Fields( "num" ), new Fields( "num1", "lhs", "num2", "rhs" ) );

View Full Code Here

    }


  @Test
  public void testCoGroupWithResultGroupFields() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "bar" );


    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(), "/complex/cogroup/", true );


    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( pipeLower, new Fields( "num" ), pipeUpper, new Fields( "num" ), new Fields( "num1", "lhs", "num2", "rhs" ), new Fields( "somenum", "somenum2" ) );

View Full Code Here

    }


  @Test
  public void testDirectCoGroup() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "num", "char" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );
    sources.put( "lower2", sourceLower );
    sources.put( "upper1", sourceUpper );
    sources.put( "upper2", sourceUpper );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

   * @throws Exception
   */
  @Test
  public void testMultipleCoGroupSimilarSources() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "num", "char" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );
    sources.put( "upper1", sourceUpper );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

   * @throws Exception
   */
  @Test
  public void testMultipleCoGroupSplitSources() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "num", "char" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );
    sources.put( "upper1", sourceUpper );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

   * @throws Exception
   */
  @Test
  public void testSplitEachOnGroup() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

    }


  @Test
  public void testSplitEveryOnGroup() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

    }


  @Test
  public void testSplitOutput() throws Exception
    {
    Tap sourceLower = new Hfs( new TextLine( new Fields( "num", "char" ) ), "foo" );


    Map sources = new HashMap();


    sources.put( "lower1", sourceLower );


    // using null pos so all fields are written
    Tap sink1 = new Hfs( new TextLine(), "output1", true );
    Tap sink2 = new Hfs( new TextLine(), "output2", true );


    Map sinks = new HashMap();


    sinks.put( "output1", sink1 );
    sinks.put( "output2", sink2 );

View Full Code Here

0 1 2 3 4 5 6 7 8

TOP

Related Classes of cascading.scheme.hadoop.TextLine

cascading.flow.hadoop.BuildJobsHadoopPlatformTest

cascading.flow.hadoop.FlowPlatformTest

cascading.flow.hadoop.MapReduceFlowPlatformTest

cascading.flow.hadoop.util.HadoopMRUtil

cascading.flow.hadoop.util.HadoopUtil

cascading.lingual.platform.hadoop.HadoopPlatformBroker

cascading.lingual.platform.hadoop2.Hadoop2MR1PlatformBroker

cascading.platform.hadoop.BaseHadoopPlatform

cascading.tap.hadoop.HadoopMR1TapPlatformTest

cascading.tap.hadoop.HadoopTapPlatformTest

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.