svn commit: r1074055 - in /hadoop/mapreduce/trunk: ./ src/java/org/apache/hadoop/mapreduce/lib/input/ src/test/mapred/org/apache/hadoop/mapreduce/lib/input/

[to...@apache.org]

Author: todd
Date: Thu Feb 24 07:07:29 2011
New Revision: 1074055

URL: http://svn.apache.org/viewvc?rev=1074055&view=rev
Log:
MAPREDUCE-2254. Allow setting of end-of-record delimiter for TextInputFormat. Contributed by Ahmed Radwan.

Added:
    hadoop/mapreduce/trunk/src/test/mapred/org/apache/hadoop/mapreduce/lib/input/TestLineRecordReader.java
Modified:
    hadoop/mapreduce/trunk/CHANGES.txt
    hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java
    hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/TextInputFormat.java

Modified: hadoop/mapreduce/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/hadoop/mapreduce/trunk/CHANGES.txt?rev=1074055&r1=1074054&r2=1074055&view=diff
==============================================================================
--- hadoop/mapreduce/trunk/CHANGES.txt (original)
+++ hadoop/mapreduce/trunk/CHANGES.txt Thu Feb 24 07:07:29 2011
@@ -32,6 +32,9 @@ Trunk (unreleased changes)
     MAPREDUCE-2334. Update BlockPlacementPolicyRaid for the new method
     in BlockPlacementPolicy.  (szetszwo)
 
+    MAPREDUCE-2254. Allow setting of end-of-record delimiter for
+    TextInputFormat (Ahmed Radwan via todd)
+
   OPTIMIZATIONS
     
     MAPREDUCE-2026. Make JobTracker.getJobCounters() and

Modified: hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java
URL: http://svn.apache.org/viewvc/hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java?rev=1074055&r1=1074054&r2=1074055&view=diff
==============================================================================
--- hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java (original)
+++ hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/LineRecordReader.java Thu Feb 24 07:07:29 2011
@@ -66,6 +66,14 @@ public class LineRecordReader extends Re
   private Counter inputByteCounter;
   private CompressionCodec codec;
   private Decompressor decompressor;
+  private byte[] recordDelimiterBytes;
+
+  public LineRecordReader() {
+  }
+
+  public LineRecordReader(byte[] recordDelimiter) {
+    this.recordDelimiterBytes = recordDelimiter;
+  }
 
   public void initialize(InputSplit genericSplit,
                          TaskAttemptContext context) throws IOException {
@@ -90,17 +98,33 @@ public class LineRecordReader extends Re
           ((SplittableCompressionCodec)codec).createInputStream(
             fileIn, decompressor, start, end,
             SplittableCompressionCodec.READ_MODE.BYBLOCK);
-        in = new LineReader(cIn, job);
+        if (null == this.recordDelimiterBytes){
+          in = new LineReader(cIn, job);
+        } else {
+          in = new LineReader(cIn, job, this.recordDelimiterBytes);
+        }
+
         start = cIn.getAdjustedStart();
         end = cIn.getAdjustedEnd();
         filePosition = cIn;
       } else {
-        in = new LineReader(codec.createInputStream(fileIn, decompressor), job);
+        if (null == this.recordDelimiterBytes) {
+          in = new LineReader(codec.createInputStream(fileIn, decompressor),
+              job);
+        } else {
+          in = new LineReader(codec.createInputStream(fileIn,
+              decompressor), job, this.recordDelimiterBytes);
+        }
         filePosition = fileIn;
       }
     } else {
       fileIn.seek(start);
-      in = new LineReader(fileIn, job);
+      if (null == this.recordDelimiterBytes){
+        in = new LineReader(fileIn, job);
+      } else {
+        in = new LineReader(fileIn, job, this.recordDelimiterBytes);
+      }
+
       filePosition = fileIn;
     }
     // If this is not the first split, we always throw away first record

Modified: hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/TextInputFormat.java
URL: http://svn.apache.org/viewvc/hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/TextInputFormat.java?rev=1074055&r1=1074054&r2=1074055&view=diff
==============================================================================
--- hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/TextInputFormat.java (original)
+++ hadoop/mapreduce/trunk/src/java/org/apache/hadoop/mapreduce/lib/input/TextInputFormat.java Thu Feb 24 07:07:29 2011
@@ -43,7 +43,12 @@ public class TextInputFormat extends Fil
   public RecordReader<LongWritable, Text> 
     createRecordReader(InputSplit split,
                        TaskAttemptContext context) {
-    return new LineRecordReader();
+    String delimiter = context.getConfiguration().get(
+        "textinputformat.record.delimiter");
+    byte[] recordDelimiterBytes = null;
+    if (null != delimiter)
+      recordDelimiterBytes = delimiter.getBytes();
+    return new LineRecordReader(recordDelimiterBytes);
   }
 
   @Override

Added: hadoop/mapreduce/trunk/src/test/mapred/org/apache/hadoop/mapreduce/lib/input/TestLineRecordReader.java
URL: http://svn.apache.org/viewvc/hadoop/mapreduce/trunk/src/test/mapred/org/apache/hadoop/mapreduce/lib/input/TestLineRecordReader.java?rev=1074055&view=auto
==============================================================================
--- hadoop/mapreduce/trunk/src/test/mapred/org/apache/hadoop/mapreduce/lib/input/TestLineRecordReader.java (added)
+++ hadoop/mapreduce/trunk/src/test/mapred/org/apache/hadoop/mapreduce/lib/input/TestLineRecordReader.java Thu Feb 24 07:07:29 2011
@@ -0,0 +1,140 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.mapreduce.lib.input;
+
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.io.OutputStreamWriter;
+import java.io.Reader;
+import java.io.Writer;
+
+import junit.framework.TestCase;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.Mapper;
+import org.apache.hadoop.mapreduce.Reducer;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.apache.tools.ant.util.FileUtils;
+import org.junit.Test;
+
+public class TestLineRecordReader extends TestCase {
+
+  private static Path workDir = new Path(new Path(System.getProperty(
+      "test.build.data", "."), "data"), "TestTextInputFormat");
+  private static Path inputDir = new Path(workDir, "input");
+  private static Path outputDir = new Path(workDir, "output");
+
+  /**
+   * Writes the input test file
+   *
+   * @param conf
+   * @throws IOException
+   */
+  public void createInputFile(Configuration conf) throws IOException {
+    FileSystem localFs = FileSystem.getLocal(conf);
+    Path file = new Path(inputDir, "test.txt");
+    Writer writer = new OutputStreamWriter(localFs.create(file));
+    writer.write("abc\ndef\t\nghi\njkl");
+    writer.close();
+  }
+
+  /**
+   * Reads the output file into a string
+   *
+   * @param conf
+   * @return
+   * @throws IOException
+   */
+  public String readOutputFile(Configuration conf) throws IOException {
+    FileSystem localFs = FileSystem.getLocal(conf);
+    Path file = new Path(outputDir, "part-r-00000");
+    Reader reader = new InputStreamReader(localFs.open(file));
+    String r = FileUtils.readFully(reader);
+    reader.close();
+    return r;
+  }
+
+  /**
+   * Creates and runs an MR job
+   *
+   * @param conf
+   * @throws IOException
+   * @throws InterruptedException
+   * @throws ClassNotFoundException
+   */
+  public void createAndRunJob(Configuration conf) throws IOException,
+      InterruptedException, ClassNotFoundException {
+    Job job = Job.getInstance(conf);
+    job.setJarByClass(TestLineRecordReader.class);
+    job.setMapperClass(Mapper.class);
+    job.setReducerClass(Reducer.class);
+    FileInputFormat.addInputPath(job, inputDir);
+    FileOutputFormat.setOutputPath(job, outputDir);
+    job.waitForCompletion(true);
+  }
+
+  /**
+   * Test the case when a custom record delimiter is specified using the
+   * textinputformat.record.delimiter configuration property
+   *
+   * @throws IOException
+   * @throws InterruptedException
+   * @throws ClassNotFoundException
+   */
+  @Test
+  public void testCustomRecordDelimiters() throws IOException,
+      InterruptedException, ClassNotFoundException {
+    Configuration conf = new Configuration();
+    conf.set("textinputformat.record.delimiter", "\t\n");
+    FileSystem localFs = FileSystem.getLocal(conf);
+    // cleanup
+    localFs.delete(workDir, true);
+    // creating input test file
+    createInputFile(conf);
+    createAndRunJob(conf);
+    String expected = "0\tabc\ndef\n9\tghi\njkl\n";
+    this.assertEquals(expected, readOutputFile(conf));
+  }
+
+  /**
+   * Test the default behavior when the textinputformat.record.delimiter
+   * configuration property is not specified
+   *
+   * @throws IOException
+   * @throws InterruptedException
+   * @throws ClassNotFoundException
+   */
+  @Test
+  public void testDefaultRecordDelimiters() throws IOException,
+      InterruptedException, ClassNotFoundException {
+    Configuration conf = new Configuration();
+    FileSystem localFs = FileSystem.getLocal(conf);
+    // cleanup
+    localFs.delete(workDir, true);
+    // creating input test file
+    createInputFile(conf);
+    createAndRunJob(conf);
+    String expected = "0\tabc\n4\tdef\t\n9\tghi\n13\tjkl\n";
+    this.assertEquals(expected, readOutputFile(conf));
+  }
+
+}