Examples of org.apache.pig.data.DataBag$BagDelimiterTuple

org.apache.pig.data.DataBag
A collection of Tuples. A DataBag may or may not fit into memory. DataBag extends spillable, which means that it registers with a memory manager. By default, it attempts to keep all of its contents in memory. If it is asked by the memory manager to spill to disk (by a call to spill()), it takes whatever it has in memory, opens a spill file, and writes the contents out. This may happen multiple times. The bag tracks all of the files it's spilled to. DataBag provides an Iterator interface, that allows callers to read through the contents. The iterators are aware of the data spilling. They have to be able to handle reading from files, as well as the fact that data they were reading from memory may have been spilled to disk underneath them. The DataBag interface assumes that all data is written before any is read. That is, a DataBag cannot be used as a queue. If data is written after data is read, the results are undefined. This condition is not checked on each add or read, for reasons of speed. Caveat emptor. Since spills are asynchronous (the memory manager requesting a spill runs in a separate thread), all operations dealing with the mContents Collection (which is the collection of tuples contained in the bag) have to be synchronized. This means that reading from a DataBag is currently serialized. This is ok for the moment because pig execution is currently single threaded. A ReadWriteLock was experimented with, but it was found to be about 10x slower than using the synchronize keyword. If pig changes its execution model to be multithreaded, we may need to return to this issue, as synchronizing reads will most likely defeat the purpose of multi-threading execution. DataBag come in several types, default, sorted, and distinct. The type must be chosen up front, there is no way to convert a bag on the fly.

        //(chuck,{(kick,3)})
        it = pig.openIterator("cc_rows");
        if (it.hasNext()) {
            Tuple t = it.next();
            Assert.assertEquals(t.get(0), "chuck");           
            DataBag columns = (DataBag) t.get(1);
            Iterator<Tuple> iter = columns.iterator();
            if(iter.hasNext())
            {
                Tuple column = iter.next();
                Assert.assertEquals(column.get(0), "kick");
                Assert.assertEquals(column.get(1), 3L);

View Full Code Here

        innerTuple.append("k");


        input.append(innerTuple);
        result = rbsc.exec(input);
        assertEquals("a b c d e f g h i j k", result);
        DataBag db = new DefaultDataBag();
        Tuple dbTuple = new DefaultTuple();
        dbTuple.append("l");
        dbTuple.append("m");
        db.add(dbTuple);
        innerTuple.append(db);
        result = rbsc.exec(input);
        assertEquals("a b c d e f g h i j k l m", result);
    }

View Full Code Here


        input.append(innerTuple);
        rbsc = new RangeBasedStringConcat("0,9", " ");
        result = rbsc.exec(input);
        assertEquals("a j k", result);
        DataBag db = new DefaultDataBag();
        Tuple dbTuple = new DefaultTuple();
        dbTuple.append("l");
        dbTuple.append("m");
        db.add(dbTuple);
        innerTuple.append(db);
        rbsc = new RangeBasedStringConcat("0,9,10", " ");
        result = rbsc.exec(input);
        assertEquals("a j k l m", result);
    }

View Full Code Here

        this.context = context;
    }


    public Tuple exec(Tuple input) throws IOException {
        Tuple row = TupleFactory.getInstance().newTuple(2);
        DataBag columns = BagFactory.getInstance().newDefaultBag();
        UDFContext context = UDFContext.getUDFContext();
        Properties property = context.getUDFProperties(ToCassandraBag.class);
        String fieldString = property.getProperty(getSchemaKey());
        String [] fieldnames = INPUT_DELIM.split(fieldString);
        if (log.isDebugEnabled()) {
            log.debug("Tuple: " + input.toDelimitedString(",") + " Fields: " + fieldString);
        }


        // IT IS ALWAYS ASSUMED THAT THE OBJECT AT INDEX 0 IS THE ROW KEY
        if(input.get(0)==null)
            throw new IOException("The object at index 0 is the row key, its value can't be null!");
        if (input.size() != fieldnames.length){
            throw new IOException("There is a mismatch between the number of inputs (" + input.size() + " and fieldnames (" + fieldnames.length + ")");
        }
        for (int i=1; i<input.size(); i++) {
            if (input.get(i) instanceof DataBag) {
                columns.addAll((DataBag) input.get(i));
            } else {
                columns.add(getColumnDef(fieldnames[i], input.get(i)));
            }
        }


        row.set(0, input.get(0));
        row.set(1, columns);

View Full Code Here

            throw new IOException("Invalid input. Please pass in both a list of column names and the columns themselves.");
        if (input.isNull(0) || input.isNull(1))
            return null;


        String columnSelector = input.get(0).toString();
        DataBag cassandraBag  = (DataBag)input.get(1);
        String[] selections   = DELIM_PATTERN.split(columnSelector);
        Tuple output          = TupleFactory.getInstance().newTuple(selections.length);


        for (int i = 0; i < selections.length; i++) {
            String selection = selections[i];
            if (selection.endsWith(GREEDY_OPERATOR)) {
                String namePrefix  = selection.substring(0,selection.length()-1);
                DataBag columnsBag = BagFactory.getInstance().newDefaultBag();


                // Find all columns in the input bag that begin with 'namePrefix'
                // and add them to the 'columnsBag'
                for (Tuple cassandraColumn : cassandraBag) {
                    String name = cassandraColumn.get(0).toString();
                    if (name.startsWith(namePrefix)) {
                        columnsBag.add(cassandraColumn);
                    }
                }


                // Sometimes this bag will have no columns in it, this _is_ the desired behavior.
                output.set(i, columnsBag);

View Full Code Here

    private static String INPUT_DELIM = "[\\s,]+";
    private static char OUTPUT_DELIM = ',';


    public Tuple exec(Tuple input) throws IOException {
        Tuple row = TupleFactory.getInstance().newTuple(2);
        DataBag columns = BagFactory.getInstance().newDefaultBag();
        UDFContext context = UDFContext.getUDFContext();
        Properties property = context.getUDFProperties(DeleteColumns.class);
        String fieldString = property.getProperty(UDFCONTEXT_SCHEMA_KEY);
        String [] fieldnames = fieldString.split(INPUT_DELIM);


        // IT IS ALWAYS ASSUMED THAT THE OBJECT AT INDEX 0 IS THE ROW KEY


        for (int i=1; i<input.size(); i++) {
            if (input.get(i) instanceof DataBag) {
                for (Tuple cassandraColumn : (DataBag) input.get(i)) {
                    String name = cassandraColumn.get(0).toString();
                    columns.add(getColumnDef(name, null));
                }
            } else {
                columns.add(getColumnDef(fieldnames[i], null));
            }
        }


        row.set(0, input.get(0));
        row.set(1, columns);

View Full Code Here

                Tuple tmp = (Tuple) o;
                if (tmp.size() > 0){
                    processTuple(tmp, builder);
                }
            } else if (o instanceof DataBag){
                DataBag db = (DataBag) o;
                for (Tuple tuple : db) {
                    processTuple(tuple, builder);
                }
            } else {
                String s = o.toString();

View Full Code Here

    public void testSortFRJoin() throws IOException{
      pigServer.registerQuery("A = LOAD '" + INPUT_FILE + "' as (x:int,y:int);");
      pigServer.registerQuery("B = LOAD '" + INPUT_FILE + "' as (x:int,y:int);");
      pigServer.registerQuery("D = ORDER A by y;");
      pigServer.registerQuery("E = ORDER B by y;");
      DataBag dbfrj = BagFactory.getInstance().newDefaultBag(), dbshj = BagFactory.getInstance().newDefaultBag();
      {
          pigServer.registerQuery("C = join D by $0, E by $0 using \"replicated\";");
          Iterator<Tuple> iter = pigServer.openIterator("C");
          
          while(iter.hasNext()) {
              dbfrj.add(iter.next());
          }
      }
      {
          pigServer.registerQuery("C = join D by $0, E by $0;");
          Iterator<Tuple> iter = pigServer.openIterator("C");
          
          while(iter.hasNext()) {
              dbshj.add(iter.next());
          }
      }
      Assert.assertEquals(dbfrj.size(), dbshj.size());
      Assert.assertEquals(true, TestHelper.compareBags(dbfrj, dbshj));        
    }

View Full Code Here

    public void testDistinctFRJoin() throws IOException{
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE + "' as (x:int,y:int);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE + "' as (x:int,y:int);");
        pigServer.registerQuery("D = distinct A ;");
        pigServer.registerQuery("E = distinct B ;");
        DataBag dbfrj = BagFactory.getInstance().newDefaultBag(), dbshj = BagFactory.getInstance().newDefaultBag();
        {
            pigServer.registerQuery("C = join D by $0, E by $0 using \"replicated\";");
            Iterator<Tuple> iter = pigServer.openIterator("C");
            
            while(iter.hasNext()) {
                dbfrj.add(iter.next());
            }
        }
        {
            pigServer.registerQuery("C = join D by $0, E by $0;");
            Iterator<Tuple> iter = pigServer.openIterator("C");
            
            while(iter.hasNext()) {
                dbshj.add(iter.next());
            }
        }
        Assert.assertEquals(dbfrj.size(), dbshj.size());
        Assert.assertEquals(true, TestHelper.compareBags(dbfrj, dbshj));        
      }

View Full Code Here

    @Test
    public void testUDFFRJ() throws IOException {
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE + "' as (x:chararray,y:int);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE + "' as (x:chararray,y:int);");
        
        DataBag dbfrj = BagFactory.getInstance().newDefaultBag(), dbshj = BagFactory.getInstance().newDefaultBag();
        {
            String fSpec = FRJoin.class.getName()+ "('" + INPUT_FILE + "')";
            pigServer.registerFunction("FRJ", new FuncSpec(fSpec));
            pigServer.registerQuery("C = foreach A generate *, flatten(FRJ(*));");
            Iterator<Tuple> iter = pigServer.openIterator("C");
            
            while(iter.hasNext()) {
                dbfrj.add(iter.next());
            }
        }
        {
            pigServer.registerQuery("C = join A by $0, B by $0;");
            Iterator<Tuple> iter = pigServer.openIterator("C");
            
            while(iter.hasNext()) {
                dbshj.add(iter.next());
            }
        }
        Assert.assertTrue(dbfrj.size()>0 && dbshj.size()>0);
        Assert.assertEquals(true, TestHelper.compareBags(dbfrj, dbshj));
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.pig.data.DataBag$BagDelimiterTuple

com.inadco.hbl.piggybank.AggregationFromMeasureBag

com.mongodb.hadoop.pig.JSONPigReplaceTest

com.mongodb.hadoop.pig.MongoLoaderTest

com.mozilla.pig.eval.json.JsonMap

com.twitter.elephantbird.pig.piggybank.Fixtures

com.twitter.elephantbird.pig.util.ProtobufToPig

datafu.pig.linkanalysis.PageRank

org.apache.cassandra.pig.CqlTableTest

org.apache.cassandra.pig.ThriftColumnFamilyTest

org.apache.hadoop.zebra.io.TestColumnGroupSplits

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.