Examples of org.apache.hadoop.io.Text

org.apache.hadoop.io.Text
This class stores text using standard UTF8 encoding. It provides methods to serialize, deserialize, and compare texts at byte level. The type of length is integer and is serialized using zero-compressed format.
In addition, it provides methods for string traversal without converting the byte array to a string.
Also includes utilities for serializing/deserialing a string, coding/decoding a string, checking if a byte array contains valid UTF8 code, calculating the length of an encoded string.

public class TestNGramReducer {
  
  @Test(expected = IOException.class)
  public final void testReducerForNullValues() throws IOException, InterruptedException {
    ArrayList<Text> values = new ArrayList<Text>();
    values.add(new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    values.add(new Text("This is not a bookdelimiterBetweenKeyAndValuevalue2"));
    Reducer.Context context = mock(Reducer.Context.class);
    NGramReducer reducer = new NGramReducer();
    reducer.reduce(null, values, context);
  }

View Full Code Here

  }
  
  @Test
  public void testReducerValidValues() throws IOException, InterruptedException {
    ArrayList<Text> values = new ArrayList<Text>();
    values.add(new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    values.add(new Text("This is not a bookdelimiterBetweenKeyAndValuevalue2"));
    Reducer.Context context = mock(Reducer.Context.class);
    NGramReducer reducer = new NGramReducer();
    reducer.reduce(new Text("This is"), values, context);
    ValuePair valuePair = new ValuePair();
    valuePair.setValue1(new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    valuePair.setValue2(new Text("This is not a bookdelimiterBetweenKeyAndValuevalue2"));
    verify(context).write(valuePair, new IntWritable(1));    
  }

View Full Code Here

  
  @Test(expected = IOException.class)
  public final void testMapperForNullValues() throws IOException, InterruptedException {
    Mapper.Context context = mock(Mapper.Context.class);
    NGramMapper mapper = new NGramMapper();
    mapper.map(null, new Text("value1"), context);  
  }

View Full Code Here

  
  @Test
  public final void testMapperForValidValues() throws IOException, InterruptedException {
    Mapper.Context context = mock(Mapper.Context.class);
    NGramMapper mapper = new NGramMapper();
    mapper.map(new Text("This is a book"), new Text("value1"), context);
    verify(context).write(new Text("a book"), new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    verify(context).write(new Text("This is"), new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    verify(context).write(new Text("is a"), new Text("This is a bookdelimiterBetweenKeyAndValuevalue1"));
    }

View Full Code Here

    this.value2 = value2;
  }


  @Override
  public void readFields(DataInput in) throws IOException {
    value1 = new Text();
    value1.readFields(in);


    value2 = new Text();
    value2.readFields(in);
  }

View Full Code Here

    HashSet<String> nGramList = new HashSet<String>();
    int gramSize = 2;
    nGramList = getNGrams(key, gramSize);
    for (String nGrams : nGramList) {
      String value = key.toString() + "delimiterBetweenKeyAndValue" + val.toString();
      context.write(new Text(nGrams), new Text(value));
      logger.info("Key and Value in NGram Mapper is: " + new Text(nGrams)
          + ", " + new Text(value));
    }
  }

View Full Code Here


    ArrayList<Text> value = new ArrayList<Text>();
    
    Iterator<Text> iterator = values.iterator();
    while (iterator.hasNext()) {
      Text valueInIterator = iterator.next();
      logger.info("Value in NGram Reducer is: " + valueInIterator);
      value.add(new Text(valueInIterator));
    }


    for (Text valueInList : value) {
      logger.info("Value added in list is: " + valueInList);
    }

View Full Code Here

    return student;
  }
  
  @Test
  public void testMergeByCustomObjectKeyWithSequenceFileInputFormat() throws Exception {    
    Student student1 = setStudent(new Text("Sam"),new Text("US"),new IntWritable(1),
        new LongWritable(9999999998l),new DoubleWritable(99.12));        
    Student student2 = setStudent(new Text("John"),new Text("AUS"),new IntWritable(2),
        new LongWritable(9999999999l),new DoubleWritable(90.12));        
    Student student3 = setStudent(new Text("Mary"),new Text("UK"),new IntWritable(3),
        new LongWritable(9999999988l),new DoubleWritable(69.12));    
    Student student4 = setStudent(new Text("Kelvin"),new Text("UK"),new IntWritable(4),
        new LongWritable(9999998888l),new DoubleWritable(59.12));
  
    HashMap<Student, Text> inputData1 = new HashMap<Student, Text>();
    inputData1.put(student1, new Text("Macon Kent,6269 Aenean St.,1-247-399-1051,08253"));
    inputData1.put(student2, new Text("Dale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510"));
    inputData1.put(student3, new Text("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"));
    createSequenceFileInHdfs(inputData1, "/input1", "testFile1.seq");
    
    HashMap<Student, Text> inputData2 = new HashMap<Student, Text>();
    inputData2.put(student2, new Text("Austin Farley,4794 Donec Ave,1-230-823-8164,13508"));
    inputData2.put(student3, new Text("Macaulay Jackson,5435 Dui. Avenue,1-770-395-6446,31584"));
    inputData2.put(student4, new Text("Timon Leonard,716 Ac Ave,1-857-935-3882,62240"));
    createSequenceFileInHdfs(inputData2, "/input2", "testFile2.seq");
  


    String[] args = new String[] {
        "-newPath",  "/input1",

View Full Code Here


  
  @Test
  public void testMergeByIntWritableKeyWithSequenceFileInputFormat() throws Exception {
    HashMap<IntWritable, Text> inputData1 = new HashMap<IntWritable, Text>();
    inputData1.put(new IntWritable(1), new Text("Macon Kent,6269 Aenean St.,1-247-399-1051,08253"));
    inputData1.put(new IntWritable(2), new Text("Dale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510"));
    inputData1.put(new IntWritable(3), new Text("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"));
    createSequenceFileInHdfs(inputData1, "/input1", "testFile1.seq");
    
    HashMap<IntWritable, Text> inputData2 = new HashMap<IntWritable, Text>();
    inputData2.put(new IntWritable(1), new Text("Macaulay Jackson,5435 Dui. Avenue,1-770-395-6446,31584"));
    inputData2.put(new IntWritable(2), new Text("Timon Leonard,716 Ac Ave,1-857-935-3882,62240"));
    inputData2.put(new IntWritable(4), new Text("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"));
    createSequenceFileInHdfs(inputData2, "/input2", "testFile2.seq");
  


    String[] args = new String[] {
        "-newPath",  "/input1",

View Full Code Here

  } 
  
  @Test
  public void testMergeByLongWritableKeyWithSequenceFileInputFormat() throws Exception {
    HashMap<LongWritable, Text> inputData1 = new HashMap<LongWritable, Text>();
    inputData1.put(new LongWritable(1), new Text("Macon Kent,6269 Aenean St.,1-247-399-1051,08253"));
    inputData1.put(new LongWritable(2), new Text("Dale Zamora,521-7792 Mauris Rd.,1-214-625-6970,90510"));
    inputData1.put(new LongWritable(3), new Text("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"));
    createSequenceFileInHdfs(inputData1, "/input1", "testFile1.seq");
    
    HashMap<LongWritable, Text> inputData2 = new HashMap<LongWritable, Text>();
    inputData2.put(new LongWritable(1), new Text("Macaulay Jackson,5435 Dui. Avenue,1-770-395-6446,31584"));
    inputData2.put(new LongWritable(2), new Text("Timon Leonard,716 Ac Ave,1-857-935-3882,62240"));
    inputData2.put(new LongWritable(4), new Text("Charles Wood,525-9709 In Rd.,1-370-528-4758,62714"));
    createSequenceFileInHdfs(inputData2, "/input2", "testFile2.seq");
  


    String[] args = new String[] {
        "-newPath",  "/input1",

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.hadoop.io.Text

azkaban.common.web.JsonSequenceFileViewer

bbejeck.mapred.aggregation.AverageTemperatureCombiningMapperTest

bbejeck.mapred.aggregation.AverageTemperatureMapperTest

bbejeck.mapred.aggregation.AverageTemperatureMapReduceTest

bbejeck.mapred.coocurrance.PairsOccurrenceMapperTest

bbejeck.mapred.coocurrance.StripesOccurrenceMapperTest

bbejeck.mapred.coocurrance.WordPair

cellmate.accumulo.writer.dbtransformers.AccumuloDBItemTransformers

co.nubetech.hiho.dedup.DelimitedLineRecordReader

co.nubetech.hiho.dedup.HihoTuple

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.