Examples of org.apache.pig.data.DataBag

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.

    @Test
    public void testSkewedJoinMapKey() throws IOException{
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE4 + "' as (m:[]);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE4 + "' as (n:[]);");
        try {
            DataBag dbfrj = BagFactory.getInstance().newDefaultBag();
            {
                pigServer.registerQuery("C = join A by (chararray)m#'a100', B by (chararray)n#'a100' using \"skewed\" parallel 20;");
                Iterator<Tuple> iter = pigServer.openIterator("C");
                
                while(iter.hasNext()) {
                    dbfrj.add(iter.next());
                }
            }
        }catch(Exception e) {
      System.out.println(e.getMessage());
      e.printStackTrace();

View Full Code Here

    @Test 
    public void testSkewedJoinNullKeys() throws IOException {
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE5 + "' as (id,name);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE5 + "' as (id,name);");
        try {
            DataBag dbfrj = BagFactory.getInstance().newDefaultBag();
            {
                pigServer.registerQuery("C = join A by id, B by id using \"skewed\";");
                Iterator<Tuple> iter = pigServer.openIterator("C");
                
                while(iter.hasNext()) {
                    dbfrj.add(iter.next());
                }
            }
        } catch(Exception e) {
      System.out.println(e.getMessage());
      e.printStackTrace();

View Full Code Here

    @Test 
    public void testSkewedJoinOuter() throws IOException {
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE5 + "' as (id,name);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE5 + "' as (id,name);");
        try {
            DataBag dbfrj = BagFactory.getInstance().newDefaultBag();
            {
                pigServer.registerQuery("C = join A by id left, B by id using \"skewed\";");
                Iterator<Tuple> iter = pigServer.openIterator("C");
                
                while(iter.hasNext()) {
                    dbfrj.add(iter.next());
                }
            }
            {
                pigServer.registerQuery("C = join A by id right, B by id using \"skewed\";");
                Iterator<Tuple> iter = pigServer.openIterator("C");
                
                while(iter.hasNext()) {
                    dbfrj.add(iter.next());
                }
            }
            {
                pigServer.registerQuery("C = join A by id full, B by id using \"skewed\";");
                Iterator<Tuple> iter = pigServer.openIterator("C");
                
                while(iter.hasNext()) {
                    dbfrj.add(iter.next());
                }
            }
        } catch(Exception e) {
            System.out.println(e.getMessage());
            e.printStackTrace();

View Full Code Here


        pigServer.registerQuery("C = FILTER A by id == 400;");
        pigServer.registerQuery("D = FILTER B by id == 400;");


        
        DataBag dbfrj = BagFactory.getInstance().newDefaultBag(), dbrj = BagFactory.getInstance().newDefaultBag();
        {
            pigServer.registerQuery("E = join C by id, D by id using \"skewed\";");
            Iterator<Tuple> iter = pigServer.openIterator("E");
                
            while(iter.hasNext()) {
                dbfrj.add(iter.next());
            }
        }
        {
          pigServer.registerQuery("E = join C by id, D by id;");
          Iterator<Tuple> iter = pigServer.openIterator("E");
        
          while(iter.hasNext()) {
            dbrj.add(iter.next());
          }
        }
        Assert.assertEquals(dbfrj.size(), dbrj.size());
        Assert.assertEquals(true, TestHelper.compareBags(dbfrj, dbrj));       
       
    }

View Full Code Here

    public void testSkewedJoinManyReducers() throws IOException {
        pigServer.getPigContext().getProperties().setProperty("pig.skewedjoin.reduce.maxtuple", "2");
        pigServer.registerQuery("A = LOAD '" + INPUT_FILE6 + "' as (id,name);");
        pigServer.registerQuery("B = LOAD '" + INPUT_FILE7 + "' as (id,name);");
           
        DataBag dbfrj = BagFactory.getInstance().newDefaultBag(), dbrj = BagFactory.getInstance().newDefaultBag();
        {
            pigServer.registerQuery("E = join A by id, B by id using \"skewed\" parallel 300;");
            Iterator<Tuple> iter = pigServer.openIterator("E");
                
            while(iter.hasNext()) {
                dbfrj.add(iter.next());
            }
        }
        {
            pigServer.registerQuery("E = join A by id, B by id;");
            Iterator<Tuple> iter = pigServer.openIterator("E");
        
            while(iter.hasNext()) {
                dbrj.add(iter.next());
            }
        }
        Assert.assertEquals(dbfrj.size(), dbrj.size());
        Assert.assertEquals(true, TestHelper.compareBags(dbfrj, dbrj));       
       
    }

View Full Code Here

    @Test
    public void testSkewedJoinUDF() throws IOException {
        PartitionSkewedKeys udf = new PartitionSkewedKeys(new String[]{"0.1", "2", "1.txt"});
        Tuple t = TupleFactory.getInstance().newTuple();
        t.append(3);    // use 3 reducers
        DataBag db = new DefaultDataBag();
        Tuple sample;
        for (int i=0;i<=3;i++) {
            sample = TupleFactory.getInstance().newTuple();
            if (i!=3)
                sample.append("1");
            else
                sample.append("2");
            sample.append((long)200);
            if (i!=3)
                sample.append((long)0);
            else
                sample.append((long)30);
            db.add(sample);
        }
        t.append(db);
        Map<String, Object> output = udf.exec(t);
        DataBag parList = (DataBag)output.get(PartitionSkewedKeys.PARTITION_LIST);
        for (Tuple par : parList) {
            if (par.get(0).equals("1")) {
                par.get(1).equals(0);
                par.get(2).equals(2);
            }

View Full Code Here

    public  void testBytesToBag() throws IOException
    {
        ResourceFieldSchema fs = GenRandomData.getFullTupTextDataBagFieldSchema();
        
        for (int i = 0; i < MAX; i++) {
            DataBag b = GenRandomData.genRandFullTupTextDataBag(r,5,100);
            DataBag convertedBag = ps.getLoadCaster().bytesToBag(b.toString().getBytes(), fs);
            assertTrue(TestHelper.bagEquals(b, convertedBag));
        }
        
    }

View Full Code Here

        assertTrue(DataType.equalByteArrays(t.toString().getBytes(), ((Utf8StorageConverter)ps.getLoadCaster()).toBytes(t)));
    }
        
    @Test
    public void testBagToBytes() throws IOException {
        DataBag b = GenRandomData.genRandFullTupTextDataBag(r,5,100);
        assertTrue(DataType.equalByteArrays(b.toString().getBytes(), ((Utf8StorageConverter)ps.getLoadCaster()).toBytes(b)));
    }

View Full Code Here

        assertTrue(DataType.equalByteArrays(DataType.mapToString(m).getBytes(), ((Utf8StorageConverter)ps.getLoadCaster()).toBytes(m)));
    }
    
    @Test
    public void testBytesToBagWithConversion() throws IOException {
        DataBag b = GenRandomData.genFloatDataBag(r,5,100);
        ResourceFieldSchema fs = GenRandomData.getFloatDataBagFieldSchema(5);
        DataBag convertedBag = ps.getLoadCaster().bytesToBag(b.toString().getBytes(), fs);
        
        Iterator<Tuple> iter1 = b.iterator();
        Iterator<Tuple> iter2 = convertedBag.iterator();
        for (int i=0;i<100;i++) {
            Tuple t1 = (Tuple)iter1.next();
            assertTrue(iter2.hasNext());
            Tuple t2 = (Tuple)iter2.next();
            for (int j=0;j<5;j++) {

View Full Code Here

        assertTrue(t==null);
        
        s = "{(a,b}";
        schema = Utils.getSchemaFromString("b:bag{t:tuple(a:chararray, b:chararray)}");
        rfs = new ResourceSchema(schema).getFields()[0];
        DataBag b = ps.getLoadCaster().bytesToBag(s.getBytes(), rfs);
        assertTrue(b==null);
        
        s = "{(a,b)";
        schema = Utils.getSchemaFromString("b:bag{t:tuple(a:chararray, b:chararray)}");
        rfs = new ResourceSchema(schema).getFields()[0];

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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

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.