hadoop-common-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From acmur...@apache.org
Subject svn commit: r709303 - in /hadoop/core/trunk: CHANGES.txt src/mapred/org/apache/hadoop/mapred/JobHistory.java src/test/org/apache/hadoop/mapred/TestJobName.java
Date Fri, 31 Oct 2008 00:08:13 GMT
Author: acmurthy
Date: Thu Oct 30 17:08:13 2008
New Revision: 709303

URL: http://svn.apache.org/viewvc?rev=709303&view=rev
Log:
HADOOP-4498. Ensure that JobHistory correctly escapes the job name so that regex patterns
work. Contributed by Chris Wensel.

Added:
    hadoop/core/trunk/src/test/org/apache/hadoop/mapred/TestJobName.java
Modified:
    hadoop/core/trunk/CHANGES.txt
    hadoop/core/trunk/src/mapred/org/apache/hadoop/mapred/JobHistory.java

Modified: hadoop/core/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/hadoop/core/trunk/CHANGES.txt?rev=709303&r1=709302&r2=709303&view=diff
==============================================================================
--- hadoop/core/trunk/CHANGES.txt (original)
+++ hadoop/core/trunk/CHANGES.txt Thu Oct 30 17:08:13 2008
@@ -1041,6 +1041,9 @@
 
     HADOOP-4499. DFSClient should invoke checksumOk only once. (Raghu Angadi)
 
+    HADOOP-4498. Ensure that JobHistory correctly escapes the job name so that
+    regex patterns work. (Chris Wensel via acmurthy)
+
 Release 0.18.2 - Unreleased
 
   BUG FIXES

Modified: hadoop/core/trunk/src/mapred/org/apache/hadoop/mapred/JobHistory.java
URL: http://svn.apache.org/viewvc/hadoop/core/trunk/src/mapred/org/apache/hadoop/mapred/JobHistory.java?rev=709303&r1=709302&r2=709303&view=diff
==============================================================================
--- hadoop/core/trunk/src/mapred/org/apache/hadoop/mapred/JobHistory.java (original)
+++ hadoop/core/trunk/src/mapred/org/apache/hadoop/mapred/JobHistory.java Thu Oct 30 17:08:13
2008
@@ -610,6 +610,10 @@
       return jobName;
     }
     
+    private static String escapeRegexChars( String string ) {
+      return "\\Q"+string.replaceAll("\\\\E", "\\\\E\\\\\\\\E\\\\Q")+"\\E";
+    }
+
     /**
      * Recover the job history filename from the history folder. 
      * Uses the following pattern
@@ -628,6 +632,8 @@
         return null;
       }
       
+      jobName = escapeRegexChars( jobName );
+
       // Make the pattern matching the job's history file
       final Pattern historyFilePattern = 
         Pattern.compile(jobtrackerHostname + "_" + "[0-9]+" + "_" 

Added: hadoop/core/trunk/src/test/org/apache/hadoop/mapred/TestJobName.java
URL: http://svn.apache.org/viewvc/hadoop/core/trunk/src/test/org/apache/hadoop/mapred/TestJobName.java?rev=709303&view=auto
==============================================================================
--- hadoop/core/trunk/src/test/org/apache/hadoop/mapred/TestJobName.java (added)
+++ hadoop/core/trunk/src/test/org/apache/hadoop/mapred/TestJobName.java Thu Oct 30 17:08:13
2008
@@ -0,0 +1,107 @@
+/**
+ * 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.mapred;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.OutputStream;
+import java.io.OutputStreamWriter;
+import java.io.Writer;
+import java.util.Iterator;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.fs.FileUtil;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.serializer.JavaSerializationComparator;
+import org.apache.hadoop.mapred.lib.IdentityMapper;
+
+public class TestJobName extends ClusterMapReduceTestCase {
+
+  public void testComplexName() throws Exception {
+    OutputStream os = getFileSystem().create(new Path(getInputDir(),
+        "text.txt"));
+    Writer wr = new OutputStreamWriter(os);
+    wr.write("b a\n");
+    wr.close();
+
+    JobConf conf = createJobConf();
+    conf.setJobName("[name][some other value that gets truncated internally that this test
attempts to aggravate]");
+
+    conf.setInputFormat(TextInputFormat.class);
+
+    conf.setOutputKeyClass(LongWritable.class);
+    conf.setOutputValueClass(Text.class);
+
+    conf.setMapperClass(IdentityMapper.class);
+
+    FileInputFormat.setInputPaths(conf, getInputDir());
+
+    FileOutputFormat.setOutputPath(conf, getOutputDir());
+
+    JobClient.runJob(conf);
+
+    Path[] outputFiles = FileUtil.stat2Paths(
+                           getFileSystem().listStatus(getOutputDir(),
+                           new OutputLogFilter()));
+    assertEquals(1, outputFiles.length);
+    InputStream is = getFileSystem().open(outputFiles[0]);
+    BufferedReader reader = new BufferedReader(new InputStreamReader(is));
+    assertEquals("0\tb a", reader.readLine());
+    assertNull(reader.readLine());
+    reader.close();
+  }
+
+  public void testComplexNameWithRegex() throws Exception {
+    OutputStream os = getFileSystem().create(new Path(getInputDir(),
+        "text.txt"));
+    Writer wr = new OutputStreamWriter(os);
+    wr.write("b a\n");
+    wr.close();
+
+    JobConf conf = createJobConf();
+    conf.setJobName("name \\Evalue]");
+
+    conf.setInputFormat(TextInputFormat.class);
+
+    conf.setOutputKeyClass(LongWritable.class);
+    conf.setOutputValueClass(Text.class);
+
+    conf.setMapperClass(IdentityMapper.class);
+
+    FileInputFormat.setInputPaths(conf, getInputDir());
+
+    FileOutputFormat.setOutputPath(conf, getOutputDir());
+
+    JobClient.runJob(conf);
+
+    Path[] outputFiles = FileUtil.stat2Paths(
+                           getFileSystem().listStatus(getOutputDir(),
+                           new OutputLogFilter()));
+    assertEquals(1, outputFiles.length);
+    InputStream is = getFileSystem().open(outputFiles[0]);
+    BufferedReader reader = new BufferedReader(new InputStreamReader(is));
+    assertEquals("0\tb a", reader.readLine());
+    assertNull(reader.readLine());
+    reader.close();
+  }
+
+}
\ No newline at end of file



Mime
View raw message