HADOOP-11429. Findbugs warnings in hadoop extras. Contributed by Varun Saxena.

hadoop-common-project/hadoop-common/CHANGES.txt

@@ -641,6 +641,9 @@ Release 2.7.0 - UNRELEASED
     HADOOP-11431. clean up redundant maven-site-plugin configuration.
     (Herve Boutemy via wheat9)
 
+    HADOOP-11429. Findbugs warnings in hadoop extras.
+    (Varun Saxena via wheat9)
+
 Release 2.6.0 - 2014-11-18
 
   INCOMPATIBLE CHANGES

hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/DistCh.java

@@ -238,11 +238,10 @@ public class DistCh extends DistTool {
 
       Text key = new Text();
       FileOperation value = new FileOperation();
-      SequenceFile.Reader in = null;
       long prev = 0L;
       int count = 0; //count src
-      try {
-        for(in = new SequenceFile.Reader(fs, srcs, job); in.next(key, value); ) {
+      try (SequenceFile.Reader in = new SequenceFile.Reader(fs, srcs, job)) {
+        for ( ; in.next(key, value); ) {
           long curr = in.getPosition();
           long delta = curr - prev;
           if (++count > targetcount) {
@@ -252,9 +251,6 @@ public class DistCh extends DistTool {
           }
         }
       }
-      finally {
-        in.close();
-      }
       long remaining = fs.getFileStatus(srcs).getLen() - prev;
       if (remaining != 0) {
         splits.add(new FileSplit(srcs, prev, remaining, (String[])null));
@@ -449,10 +445,8 @@ public class DistCh extends DistTool {
     Path opList = new Path(jobdir, "_" + OP_LIST_LABEL);
     jobconf.set(OP_LIST_LABEL, opList.toString());
     int opCount = 0, synCount = 0;
-    SequenceFile.Writer opWriter = null;
-    try {
-      opWriter = SequenceFile.createWriter(fs, jobconf, opList, Text.class,
-          FileOperation.class, SequenceFile.CompressionType.NONE);
+    try (SequenceFile.Writer opWriter = SequenceFile.createWriter(fs, jobconf, opList, Text.class,
+            FileOperation.class, SequenceFile.CompressionType.NONE)) {
       for(FileOperation op : ops) {
         FileStatus srcstat = fs.getFileStatus(op.src); 
         if (srcstat.isDirectory() && op.isDifferent(srcstat)) {
@@ -479,8 +473,6 @@ public class DistCh extends DistTool {
           }
         }
       }
-    } finally {
-      opWriter.close();
     }
 
     checkDuplication(fs, opList, new Path(jobdir, "_sorted"), jobconf);
@@ -496,9 +488,7 @@ public class DistCh extends DistTool {
     SequenceFile.Sorter sorter = new SequenceFile.Sorter(fs,
         new Text.Comparator(), Text.class, FileOperation.class, conf);
     sorter.sort(file, sorted);
-    SequenceFile.Reader in = null;
-    try {
-      in = new SequenceFile.Reader(fs, sorted, conf);
+    try (SequenceFile.Reader in = new SequenceFile.Reader(fs, sorted, conf)) {
       FileOperation curop = new FileOperation();
       Text prevsrc = null, cursrc = new Text(); 
       for(; in.next(cursrc, curop); ) {
@@ -512,9 +502,6 @@ public class DistCh extends DistTool {
         curop = new FileOperation();
       }
     }
-    finally {
-      in.close();
-    }
   } 
 
   public static void main(String[] args) throws Exception {

hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/DistCpV1.java

@@ -24,6 +24,7 @@ import java.io.DataOutput;
 import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.io.InputStreamReader;
+import java.nio.charset.Charset;
 import java.util.ArrayList;
 import java.util.EnumSet;
 import java.util.HashSet;
@@ -697,16 +698,13 @@ public class DistCpV1 implements Tool {
       throws IOException {
     List<Path> result = new ArrayList<Path>();
     FileSystem fs = srcList.getFileSystem(conf);
-    BufferedReader input = null;
-    try {
-      input = new BufferedReader(new InputStreamReader(fs.open(srcList)));
+    try (BufferedReader input = new BufferedReader(new InputStreamReader(fs.open(srcList),
+            Charset.forName("UTF-8")))) {
       String line = input.readLine();
       while (line != null) {
         result.add(new Path(line));
         line = input.readLine();
       }
-    } finally {
-      checkAndClose(input);
     }
     return result;
   }
@@ -957,7 +955,7 @@ public class DistCpV1 implements Tool {
             throw new IllegalArgumentException("num_maps not specified in -m");
           }
           try {
-            conf.setInt(MAX_MAPS_LABEL, Integer.valueOf(args[idx]));
+            conf.setInt(MAX_MAPS_LABEL, Integer.parseInt(args[idx]));
           } catch (NumberFormatException e) {
             throw new IllegalArgumentException("Invalid argument to -m: " +
                                                args[idx]);

hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/DistTool.java

@@ -23,6 +23,7 @@ import java.io.DataOutput;
 import java.io.FileNotFoundException;
 import java.io.IOException;
 import java.io.InputStreamReader;
+import java.nio.charset.Charset;
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Random;
@@ -96,14 +97,11 @@ abstract class DistTool implements org.apache.hadoop.util.Tool {
       ) throws IOException {
     List<String> result = new ArrayList<String>();
     FileSystem fs = inputfile.getFileSystem(conf);
-    BufferedReader input = null;
-    try {
-      input = new BufferedReader(new InputStreamReader(fs.open(inputfile)));
+    try (BufferedReader input = new BufferedReader(new InputStreamReader(fs.open(inputfile),
+            Charset.forName("UTF-8")))) {
       for(String line; (line = input.readLine()) != null;) {
         result.add(line);
       }
-    } finally {
-      input.close();
     }
     return result;
   }

hadoop-tools/hadoop-extras/src/main/java/org/apache/hadoop/tools/Logalyzer.java

@@ -21,6 +21,7 @@ package org.apache.hadoop.tools;
 import java.io.ByteArrayInputStream;
 import java.io.DataInputStream;
 import java.io.IOException;
+import java.nio.charset.Charset;
 import java.util.Random;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
@@ -155,15 +156,15 @@ public class Logalyzer {
         
         //Compare column-wise according to *sortSpec*
         for(int i=0; i < sortSpec.length; ++i) {
-          int column = (Integer.valueOf(sortSpec[i]).intValue());
+          int column = Integer.parseInt(sortSpec[i]);
           String c1 = logColumns1[column]; 
           String c2 = logColumns2[column];
           
           //Compare columns
           int comparision = super.compareBytes(
-                                               c1.getBytes(), 0, c1.length(),
-                                               c2.getBytes(), 0, c2.length()
-                                               );
+                                  c1.getBytes(Charset.forName("UTF-8")), 0, c1.length(),
+                                  c2.getBytes(Charset.forName("UTF-8")), 0, c2.length()
+                                  );
           
           //They differ!
           if (comparision != 0) {