Package org.apache.pig.impl.io

Examples of org.apache.pig.impl.io.ReadToEndLoader


     * 2) Opening an input stream to the specified file and
     * 3) Binding to the input stream at the specified offset.
     * @throws IOException
     */
    public void setUp() throws IOException{
        loader = new ReadToEndLoader((LoadFunc)
                PigContext.instantiateFuncFromSpec(lFile.getFuncSpec()),
                ConfigurationUtil.toConfiguration(pc.getProperties()),
                lFile.getFileName(),0);
    }
View Full Code Here


                    conf.set("pig.tmpfilecompression.codec", configuration.get("pig.tmpfilecompression.codec"));
            }
            }
            conf.set(MapRedUtil.FILE_SYSTEM_NAME, "file:///");
           
            ReadToEndLoader loader = new ReadToEndLoader(Utils.getTmpFileStorageObject(conf),
                    conf, quantilesFile, 0);
            DataBag quantilesList;
            Tuple t = loader.getNext();
            if (t != null) {
                // the Quantiles file has a tuple as under:
                // (numQuantiles, bag of samples)
                // numQuantiles here is the reduce parallelism
                Map<String, Object> quantileMap = (Map<String, Object>) t.get(0);
View Full Code Here

    public void testLFPig() throws Exception {
        Util.createInputFile(cluster, "input.txt", new String[]
            {"this:is:delimited:by:a:colon\n"});
        int arity1 = 6;
        LoadFunc lf = new PigStorage(":");
        LoadFunc p1 = new ReadToEndLoader(lf, ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f1 = p1.getNext();
        assertTrue(f1.size() == arity1);
        Util.deleteFile(cluster, "input.txt");

        int LOOP_COUNT = 100;
        String[] input = new String[LOOP_COUNT * LOOP_COUNT];
        int n = 0;
        for (int i = 0; i < LOOP_COUNT; i++) {
            for (int j = 0; j < LOOP_COUNT; j++) {
                input[n++] = (i + "\t" + i + "\t" + j % 2);
            }
        }
        Util.createInputFile(cluster, "input.txt", input);

        LoadFunc p15 = new ReadToEndLoader(new PigStorage(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);

        int count = 0;
        while (true) {
            Tuple f15 = p15.getNext();
            if (f15 == null)
                break;
            count++;
            assertEquals(3, f15.size());
        }
        assertEquals(LOOP_COUNT * LOOP_COUNT, count);
        Util.deleteFile(cluster, "input.txt");

        String input2 = ":this:has:a:leading:colon\n";
        int arity2 = 6;
        Util.createInputFile(cluster, "input.txt", new String[] {input2});
        LoadFunc p2 = new ReadToEndLoader(new PigStorage(":"), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f2 = p2.getNext();
        assertTrue(f2.size() == arity2);
        Util.deleteFile(cluster, "input.txt");

        String input3 = "this:has:a:trailing:colon:\n";
        int arity3 = 6;
        Util.createInputFile(cluster, "input.txt", new String[] {input2});
        LoadFunc p3 = new ReadToEndLoader(new PigStorage(":"), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f3 = p3.getNext();
        assertTrue(f3.size() == arity3);
        Util.deleteFile(cluster, "input.txt");
    }
View Full Code Here

        Util.createInputFile(cluster,
                "testLFTest-input1.txt",
                new String[] {input1});
        // check that loading the top level dir still reading the file a couple
        // of subdirs below
        LoadFunc text1 = new ReadToEndLoader(new TextLoader(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "testLFTest-input1.txt", 0);
        Tuple f1 = text1.getNext();
        Tuple f2 = text1.getNext();
        Util.deleteFile(cluster, "testLFTest-input1.txt");
        assertTrue(expected1.equals(f1.get(0).toString()) &&
            expected2.equals(f2.get(0).toString()));
        Util.createInputFile(cluster, "testLFTest-input2.txt", new String[] {});
        LoadFunc text2 = new ReadToEndLoader(new TextLoader(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "testLFTest-input2.txt", 0);
        Tuple f3 = text2.getNext();
        Util.deleteFile(cluster, "testLFTest-input2.txt");
        assertTrue(f3 == null);
    }
View Full Code Here

        String query = "a = load 'testSFPig-input.txt';" +
            "store a into '" + outputLocation + "';";
        mrPigServer.setBatchOn();
        Util.registerMultiLineQuery(mrPigServer, query);
        mrPigServer.executeBatch();
        LoadFunc lfunc = new ReadToEndLoader(new PigStorage(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), outputLocation, 0);
        Tuple f2 = lfunc.getNext();
        Util.deleteFile(cluster, "testSFPig-input.txt");

        Util.deleteFile(cluster, outputLocation);
        assertEquals(f1, f2);
    }
View Full Code Here

     * 2) Opening an input stream to the specified file and
     * 3) Binding to the input stream at the specified offset.
     * @throws IOException
     */
    public void setUp() throws IOException{
        loader = new ReadToEndLoader((LoadFunc)
                PigContext.instantiateFuncFromSpec(lFile.getFuncSpec()),
                ConfigurationUtil.toConfiguration(pc.getProperties()),
                lFile.getFileName(),0, signature);
    }
View Full Code Here

    public void testLFPig() throws Exception {
        Util.createInputFile(cluster, "input.txt", new String[]
            {"this:is:delimited:by:a:colon\n"});
        int arity1 = 6;
        LoadFunc lf = new PigStorage(":");
        LoadFunc p1 = new ReadToEndLoader(lf, ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f1 = p1.getNext();
        assertTrue(f1.size() == arity1);
        Util.deleteFile(cluster, "input.txt");

        int LOOP_COUNT = 100;
        String[] input = new String[LOOP_COUNT * LOOP_COUNT];
        int n = 0;
        for (int i = 0; i < LOOP_COUNT; i++) {
            for (int j = 0; j < LOOP_COUNT; j++) {
                input[n++] = (i + "\t" + i + "\t" + j % 2);
            }
        }
        Util.createInputFile(cluster, "input.txt", input);

        LoadFunc p15 = new ReadToEndLoader(new PigStorage(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);

        int count = 0;
        while (true) {
            Tuple f15 = p15.getNext();
            if (f15 == null)
                break;
            count++;
            assertEquals(3, f15.size());
        }
        assertEquals(LOOP_COUNT * LOOP_COUNT, count);
        Util.deleteFile(cluster, "input.txt");

        String input2 = ":this:has:a:leading:colon\n";
        int arity2 = 6;
        Util.createInputFile(cluster, "input.txt", new String[] {input2});
        LoadFunc p2 = new ReadToEndLoader(new PigStorage(":"), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f2 = p2.getNext();
        assertTrue(f2.size() == arity2);
        Util.deleteFile(cluster, "input.txt");

        String input3 = "this:has:a:trailing:colon:\n";
        int arity3 = 6;
        Util.createInputFile(cluster, "input.txt", new String[] {input2});
        LoadFunc p3 = new ReadToEndLoader(new PigStorage(":"), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "input.txt", 0);
        Tuple f3 = p3.getNext();
        assertTrue(f3.size() == arity3);
        Util.deleteFile(cluster, "input.txt");
    }
View Full Code Here

        Util.createInputFile(cluster,
                "testLFTest-input1.txt",
                new String[] {input1});
        // check that loading the top level dir still reading the file a couple
        // of subdirs below
        LoadFunc text1 = new ReadToEndLoader(new TextLoader(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "testLFTest-input1.txt", 0);
        Tuple f1 = text1.getNext();
        Tuple f2 = text1.getNext();
        Util.deleteFile(cluster, "testLFTest-input1.txt");
        assertTrue(expected1.equals(f1.get(0).toString()) &&
            expected2.equals(f2.get(0).toString()));
        Util.createInputFile(cluster, "testLFTest-input2.txt", new String[] {});
        LoadFunc text2 = new ReadToEndLoader(new TextLoader(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), "testLFTest-input2.txt", 0);
        Tuple f3 = text2.getNext();
        Util.deleteFile(cluster, "testLFTest-input2.txt");
        assertTrue(f3 == null);
    }
View Full Code Here

        String query = "a = load 'testSFPig-input.txt';" +
            "store a into '" + outputLocation + "';";
        mrPigServer.setBatchOn();
        Util.registerMultiLineQuery(mrPigServer, query);
        mrPigServer.executeBatch();
        LoadFunc lfunc = new ReadToEndLoader(new PigStorage(), ConfigurationUtil.
            toConfiguration(cluster.getProperties()), outputLocation, 0);
        Tuple f2 = lfunc.getNext();
        Util.deleteFile(cluster, "testSFPig-input.txt");

        Util.deleteFile(cluster, outputLocation);
        assertEquals(f1, f2);
    }
View Full Code Here

                if (configuration.get("pig.tmpfilecompression.codec")!=null)
                    conf.set("pig.tmpfilecompression.codec", configuration.get("pig.tmpfilecompression.codec"));
            }
            conf.set(MapRedUtil.FILE_SYSTEM_NAME, "file:///");
           
            ReadToEndLoader loader = new ReadToEndLoader(Utils.getTmpFileStorageObject(conf),
                    conf, quantilesFile, 0);
            DataBag quantilesList;
            Tuple t = loader.getNext();
            if(t!=null)
            {
                // the Quantiles file has a tuple as under:
                // (numQuantiles, bag of samples)
                // numQuantiles here is the reduce parallelism
View Full Code Here

TOP

Related Classes of org.apache.pig.impl.io.ReadToEndLoader

Copyright © 2018 www.massapicom. All rights reserved.
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.