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


    Pipe pipe = new Pipe( "test" );


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

View Full Code Here

    collector.close();


    Pipe inPipe = new Pipe("in");
    Pipe p = new Each(inPipe, new Fields("value"), new ExpandProto(Example.Person.class), new Fields("id", "name", "email", "position"));


    Hfs sink = new Hfs(new TextLine(), "/tmp/output");
    new HadoopFlowConnector().connect(inTap, sink, p).complete();


    TupleEntryIterator iter = sink.openForRead(new HadoopFlowProcess());
    List<Tuple> results = new ArrayList<Tuple>();
    while (iter.hasNext()) {

View Full Code Here

  public void testLeftJoinLargeLHS() throws Exception {
    Map<String, Tap> sources = new HashMap<String, Tap>();
    sources.put("lhs", this.lhsStore);
    sources.put("rhs", this.rhsStore);


    Tap sink = new Hfs(new TextLine(), getTestRoot() + "/output");


    Pipe lhsPipe = new Pipe("lhs");
    Pipe rhsPipe = new Pipe("rhs");


    Pipe joined = new BloomJoin(lhsPipe, new Fields("key"), rhsPipe, new Fields("key"), new Fields("key", "key2", "lhs-value", "key-copy", "key2-copy", "rhs-value"), new LeftJoin());

View Full Code Here

  public void testRightJoinLargeRHS() throws Exception {
    Map<String, Tap> sources = new HashMap<String, Tap>();
    sources.put("lhs", this.lhsStore);
    sources.put("rhs", this.rhsStore);


    Tap sink = new Hfs(new TextLine(), getTestRoot() + "/output");


    Pipe lhsPipe = new Pipe("lhs");
    Pipe rhsPipe = new Pipe("rhs");


    Pipe joined = new BloomJoin(rhsPipe, new Fields("key"), lhsPipe, new Fields("key"), new Fields("key", "key2", "lhs-value", "key-copy", "key2-copy", "rhs-value"), new RightJoin(), BloomAssembly.CoGroupOrder.LARGE_RHS);

View Full Code Here


  @Test
  public void testBlackHoleWarning() throws IOException {


    FileSystemHelper.safeMkdirs(FileSystemHelper.getFS(), new Path(getTestRoot() + "/input"));
    Tap input = new Hfs(new TextLine(), getTestRoot() + "/input");
    Tap output = new Hfs(new TextLine(), getTestRoot() + "/output", SinkMode.REPLACE);
    Pipe removeAll = new Pipe("remove all");
    removeAll = new Each(removeAll, new RemoveAll());


    Flow flow = CascadingUtil.get().getFlowConnector().connect(input, output, removeAll);
    flow.complete();

View Full Code Here

    }


  @Override
  public FileType getFileTypeFor( String identifier )
    {
    return new Hfs( new TextLine(), identifier, SinkMode.KEEP );
    }

View Full Code Here

    }


  @Override
  public FileType getFileTypeFor( String identifier )
    {
    return new Hfs( new TextLine(), identifier, SinkMode.KEEP );
    }

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.