Examples of cascading.tap.hadoop.Hfs

cascading.tap.hadoop.Hfs
ode> will denote Dfs, and file://... will denote Lfs.
Call {@link #setTemporaryDirectory(java.util.Map,String)} to use a different temporary file directory pathother than the current Hadoop default path.
By default Cascading on Hadoop will assume any source or sink Tap using the {@code file://} URI schemeintends to read files from the local client filesystem (for example when using the {@code Lfs} Tap) where the Hadoopjob jar is started, Tap so will force any MapReduce jobs reading or writing to {@code file://} resources to run inHadoop "standalone mode" so that the file can be read.
To change this behavior, {@link HfsProps#setLocalModeScheme(java.util.Map,String)} to set a different scheme value,or to "none" to disable entirely for the case the file to be read is available on every Hadoop processing node in the exact same path.
Hfs can optionally combine multiple small files (or a series of small "blocks") into larger "splits". This reduces the number of resulting map tasks created by Hadoop and can improve application performance.
This is enabled by calling {@link HfsProps#setUseCombinedInput(boolean)} to {@code true}. By default, merging or combining splits into large ones is disabled.

//    }


  @Test
  public void testMerge2()
    {
    Tap source1 = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge1" );
    Tap source2 = new Hfs( new SequenceFile( new Fields( "offset", "line" ) ), "foo/merge2" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe left = new Each( new Pipe( "left" ), new Fields( "line" ), new RegexFilter( ".*46.*" ) );
    Pipe right = new Each( new Pipe( "right" ), new Fields( "line" ), new RegexFilter( ".*192.*" ) );


    Pipe merge = new GroupBy( "merge", Pipe.pipes( left, right ), new Fields( "offset" ) );

View Full Code Here

   * Tests the case where the same source is split, then re-merged
   */
  @Test
  public void testMergeSameSourceSplit()
    {
    Tap source = new Hfs( new TextLine( new Fields( "offset", "line" ) ), "foo/merge1" );


    Tap sink = new Hfs( new TextLine(), "foo" );


    Pipe head = new Pipe( "source" );


    head = new Each( head, new Fields( "line" ), new ExpressionFilter( "line.length() != 0", String.class ) );

View Full Code Here

    }


  @Test
  public void testCoGroupAroundCoGroup() throws Exception
    {
    Tap source10 = new Hfs( new TextLine( new Fields( "num" ) ), "foo" );
    Tap source20 = new Hfs( new TextLine( new Fields( "num" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "source20", source20 );
    sources.put( "source101", source10 );
    sources.put( "source102", source10 );


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


    Pipe pipeNum20 = new Pipe( "source20" );
    Pipe pipeNum101 = new Pipe( "source101" );
    Pipe pipeNum102 = new Pipe( "source102" );

View Full Code Here

    }


  @Test
  public void testCoGroupAroundCoGroupOptimized() throws Exception
    {
    Tap source10 = new Hfs( new TextLine( new Fields( "num" ) ), "foo" );
    Tap source20 = new Hfs( new TextLine( new Fields( "num" ) ), "bar" );


    Map sources = new HashMap();


    sources.put( "source20", source20 );
    sources.put( "source101", source10 );
    sources.put( "source102", source10 );


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


    Pipe pipeNum20 = new Pipe( "source20" );
    Pipe pipeNum101 = new Pipe( "source101" );
    Pipe pipeNum102 = new Pipe( "source102" );

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

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cascading.tap.hadoop.Hfs

cascading.flow.hadoop.BuildJobsHadoopPlatformTest

cascading.flow.hadoop.FlowPlatformTest

cascading.flow.hadoop.MapReduceFlow

cascading.flow.hadoop.MapReduceFlowPlatformTest

cascading.flow.hadoop.planner.rule.scopeexpression.EquivalentTapsScopeExpression

cascading.flow.hadoop.util.HadoopMRUtil

cascading.flow.hadoop.util.HadoopUtil

cascading.lingual.platform.hadoop.HadoopDefaultFactory

cascading.lingual.platform.hadoop.HadoopPlatformBroker

cascading.lingual.platform.hadoop2.Hadoop2MR1DefaultFactory

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.