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.

  // test is not executed, just guarantees flow is run locally


  @Test
  public void testLocalModeSink() throws Exception
    {
    Tap source = new Hfs( new TextLine(), "input/path" );
    Tap sink = new Lfs( new TextLine(), "output/path", SinkMode.REPLACE );


    Pipe pipe = new Pipe( "test" );


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

View Full Code Here

  public void testHfsBracketAsterisk() throws Exception
    {
    getPlatform().copyFromLocal( inputFileLower );
    getPlatform().copyFromLocal( inputFileUpper );


    Hfs sourceExists = new Hfs( new TextLine( new Fields( "offset", "line" ) ), InputData.inputPath + "{*}" );


    assertTrue( sourceExists.resourceExists( getPlatform().getFlowProcess() ) );


    TupleEntryIterator iterator = sourceExists.openForRead( getPlatform().getFlowProcess() );
    assertTrue( iterator.hasNext() );
    iterator.close();


    try
      {
      Hfs sourceNotExists = new Hfs( new TextLine( new Fields( "offset", "line" ) ), InputData.inputPath + "/blah/" );
      iterator = sourceNotExists.openForRead( getPlatform().getFlowProcess() );
      fail();
      }
    catch( IOException exception )
      {

View Full Code Here

    getPlatform().copyFromLocal( inputFileLower );
    getPlatform().copyFromLocal( inputFileUpper );


    Configuration jobConf = ( (BaseHadoopPlatform) getPlatform() ).getConfiguration();


    Hfs tap = new Hfs( new TextLine( new Fields( "offset", "line" ) ), getOutputPath( "multifiles" ) );


    tap.deleteResource( getPlatform().getFlowProcess() );


    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 2, true ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 2, false ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 1, true ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 1, false ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 0, true ) );
    assertEqualsSize( "missing", 0, tap.getChildIdentifiers( jobConf, 0, false ) );


    tap.createResource( getPlatform().getFlowProcess() );


    assertEqualsSize( "no children", 0, tap.getChildIdentifiers( jobConf ) );
    assertEqualsSize( "no children", 0, tap.getChildIdentifiers( jobConf, 2, true ) );
    assertEqualsSize( "no children", 0, tap.getChildIdentifiers( jobConf, 2, false ) );
    assertEqualsSize( "no children", 0, tap.getChildIdentifiers( jobConf, 1, true ) );
    assertEqualsSize( "no children", 0, tap.getChildIdentifiers( jobConf, 1, false ) );
    assertEqualsSize( "no children", 1, tap.getChildIdentifiers( jobConf, 0, true ) );
    assertEqualsSize( "no children", 1, tap.getChildIdentifiers( jobConf, 0, false ) );


    writeFileTo( "multifiles/A" );
    writeFileTo( "multifiles/B" );


    assertEqualsSize( "children", 2, tap.getChildIdentifiers( jobConf ) );
    assertEqualsSize( "children", 2, tap.getChildIdentifiers( jobConf, 2, true ) );
    assertEqualsSize( "children", 2, tap.getChildIdentifiers( jobConf, 2, false ) );
    assertEqualsSize( "children", 2, tap.getChildIdentifiers( jobConf, 1, true ) );
    assertEqualsSize( "children", 2, tap.getChildIdentifiers( jobConf, 1, false ) );
    assertEqualsSize( "children", 1, tap.getChildIdentifiers( jobConf, 0, true ) );
    assertEqualsSize( "children", 1, tap.getChildIdentifiers( jobConf, 0, false ) );


    tap = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "/" );


    assertEqualsSize( "root", -1, tap.getChildIdentifiers( jobConf ) );
    assertEqualsSize( "root", -1, tap.getChildIdentifiers( jobConf, 2, true ) );
    assertEqualsSize( "root", -1, tap.getChildIdentifiers( jobConf, 2, false ) );
    assertEqualsSize( "root", -1, tap.getChildIdentifiers( jobConf, 1, true ) );
    assertEqualsSize( "root", -1, tap.getChildIdentifiers( jobConf, 1, false ) );
    assertEqualsSize( "root", 1, tap.getChildIdentifiers( jobConf, 0, true ) );
    assertEqualsSize( "root", 1, tap.getChildIdentifiers( jobConf, 0, false ) );


    tap = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "./" );


    assertEqualsSize( "current", -1, tap.getChildIdentifiers( jobConf ) );
    assertEqualsSize( "current", -1, tap.getChildIdentifiers( jobConf, 2, true ) );
    assertEqualsSize( "current", -1, tap.getChildIdentifiers( jobConf, 2, false ) );
    assertEqualsSize( "current", -1, tap.getChildIdentifiers( jobConf, 1, true ) );

View Full Code Here

  public void testNotLocalMode() throws Exception
    {
    if( !getPlatform().isUseCluster() )
      return;


    Tap source = new Hfs( new TextLine(), "input/path" );
    Tap sink = new Hfs( new TextLine(), "output/path", true );


    Pipe pipe = new Pipe( "test" );


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

View Full Code Here

    assertEquals( expected, actual.length );
    }


  private void writeFileTo( String path ) throws IOException
    {
    Hfs tap = new Hfs( new TextLine( new Fields( "offset", "line" ) ), getOutputPath( path ) );


    TupleEntryCollector collector = tap.openForWrite( getPlatform().getFlowProcess() );


    collector.add( new Tuple( 1, "1" ) );

View Full Code Here

      return;


    getPlatform().copyFromLocal( inputFileLower );
    getPlatform().copyFromLocal( inputFileUpper );


    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileLower );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileUpper );


    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(), getOutputPath( "stopped" ), true );


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


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

View Full Code Here

  @Test
  public void testFailedSerialization() throws Exception
    {
    getPlatform().copyFromLocal( inputFileLower );


    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileLower );


    Map sources = new HashMap();


    sources.put( "lower", sourceLower );


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


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


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


    pipeLower = new Each( pipeLower, new Fields( "num" ), new BadFilter() );

View Full Code Here

  @Test
  public void testStartStopRace() throws Exception
    {
    getPlatform().copyFromLocal( inputFileLower );


    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileLower );


    Map sources = new HashMap();


    sources.put( "lower", sourceLower );


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


    // using null pos so all fields are written
    Tap sink = new Hfs( new TextLine(), getOutputPath( "startstop" ), SinkMode.REPLACE );


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


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

View Full Code Here

  private void failingListenerTest( FailingFlowListener.OnFail onFail ) throws Exception
    {
    getPlatform().copyFromLocal( inputFileLower );
    getPlatform().copyFromLocal( inputFileUpper );


    Tap sourceLower = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileLower );
    Tap sourceUpper = new Hfs( new TextLine( new Fields( "offset", "line" ) ), inputFileUpper );


    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(), getOutputPath( onFail + "/stopped" ), true );


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


    if( onFail == FailingFlowListener.OnFail.THROWABLE )
      {

View Full Code Here

    }


  @Test
  public void testFlowID() throws Exception
    {
    Tap source = new Lfs( new TextLine(), "input/path" );
    Tap sink = new Hfs( new TextLine(), "output/path", true );


    Pipe pipe = new Pipe( "test" );


    Map<Object, Object> props = getProperties();
    Flow flow1 = getPlatform().getFlowConnector( props ).connect( source, sink, pipe );

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.