HDFS-2023. Backport of NPE for File.list and File.listFiles.

Merged ports of HADOOP-7322, HDFS-1934, HADOOP-7342, and HDFS-2019.
(Bharath Mundlapudi via mattf)


git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/branches/branch-0.20-security-204@1137291 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -142,6 +142,10 @@ Release 0.20.204.0 - unreleased
 
     HADOOP-7398. Suppress warnings about use of HADOOP_HOME. (omalley)
 
+    HDFS-2023. Backport of NPE for File.list and File.listFiles.
+    Merged ports of HADOOP-7322, HDFS-1934, HADOOP-7342, and HDFS-2019.
+    (Bharath Mundlapudi via mattf)
+
     MAPREDUCE-2415. Distribute the user task logs on to multiple disks.
     (Bharath Mundlapudi via omalley)
 

src/core/org/apache/hadoop/fs/FileUtil.java

@@ -288,7 +288,7 @@ public class FileUtil {
       if (!dstFS.mkdirs(dst)) {
         return false;
       }
-      File contents[] = src.listFiles();
+      File contents[] = listFiles(src);
       for (int i = 0; i < contents.length; i++) {
         copy(contents[i], dstFS, new Path(dst, contents[i].getName()),
              deleteSource, conf);
@@ -444,8 +444,10 @@ public class FileUtil {
     } else {
       size = dir.length();
       File[] allFiles = dir.listFiles();
-      for (int i = 0; i < allFiles.length; i++) {
-        size = size + getDU(allFiles[i]);
+      if(allFiles != null) {
+        for (int i = 0; i < allFiles.length; i++) {
+           size = size + getDU(allFiles[i]);
+        }
       }
       return size;
     }
@@ -653,4 +655,42 @@ public class FileUtil {
       }
     }
   }
+
+  /**
+   * A wrapper for {@link File#listFiles()}. This java.io API returns null 
+   * when a dir is not a directory or for any I/O error. Instead of having
+   * null check everywhere File#listFiles() is used, we will add utility API
+   * to get around this problem. For the majority of cases where we prefer 
+   * an IOException to be thrown.
+   * @param dir directory for which listing should be performed
+   * @return list of files or empty list
+   * @exception IOException for invalid directory or for a bad disk.
+   */
+  public static File[] listFiles(File dir) throws IOException {
+    File[] files = dir.listFiles();
+    if(files == null) {
+      throw new IOException("Invalid directory or I/O error occurred for dir: "
+                + dir.toString());
+    }
+    return files;
+  }
+  
+  /**
+   * A wrapper for {@link File#list()}. This java.io API returns null 
+   * when a dir is not a directory or for any I/O error. Instead of having
+   * null check everywhere File#list() is used, we will add utility API
+   * to get around this problem. For the majority of cases where we prefer 
+   * an IOException to be thrown.
+   * @param dir directory for which listing should be performed
+   * @return list of file names or empty string list
+   * @exception IOException for invalid directory or for a bad disk.
+   */
+  public static String[] list(File dir) throws IOException {
+    String[] fileNames = dir.list();
+    if(fileNames == null) {
+      throw new IOException("Invalid directory or I/O error occurred for dir: "
+                + dir.toString());
+    }
+    return fileNames;
+  }  
 }

src/core/org/apache/hadoop/fs/RawLocalFileSystem.java

@@ -271,7 +271,7 @@ public class RawLocalFileSystem extends FileSystem {
     if (f.isFile()) {
       return f.delete();
     } else if ((!recursive) && f.isDirectory() && 
-        (f.listFiles().length != 0)) {
+        (FileUtil.listFiles(f).length != 0)) {
       throw new IOException("Directory " + f.toString() + " is not empty");
     }
     return FileUtil.fullyDelete(f);

src/core/org/apache/hadoop/util/ProcfsBasedProcessTree.java

@@ -33,6 +33,7 @@ import java.util.LinkedList;
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.fs.FileUtil;
 
 /**
  * A Proc file-system based ProcessTree. Works only on Linux.
@@ -268,16 +269,18 @@ public class ProcfsBasedProcessTree extends ProcessTree {
     String[] processDirs = (new File(procfsDir)).list();
     List<Integer> processList = new ArrayList<Integer>();
 
-    for (String dir : processDirs) {
-      try {
-        int pd = Integer.parseInt(dir);
-        if ((new File(procfsDir, dir)).isDirectory()) {
-          processList.add(Integer.valueOf(pd));
+    if (processDirs != null) {
+      for (String dir : processDirs) {
+        try {
+          int pd = Integer.parseInt(dir);
+          if ((new File(procfsDir, dir)).isDirectory()) {
+            processList.add(Integer.valueOf(pd));
+          }
+        } catch (NumberFormatException n) {
+          // skip this directory
+        } catch (SecurityException s) {
+          // skip this process
         }
-      } catch (NumberFormatException n) {
-        // skip this directory
-      } catch (SecurityException s) {
-        // skip this process
       }
     }
     return processList;

src/hdfs/org/apache/hadoop/hdfs/server/datanode/FSDataset.java

@@ -82,7 +82,7 @@ public class FSDataset implements FSConstants, FSDatasetInterface {
                                 dir.toString());
         }
       } else {
-        File[] files = dir.listFiles();
+        File[] files = FileUtil.listFiles(dir);
         int numChildren = 0;
         for (int idx = 0; idx < files.length; idx++) {
           if (files[idx].isDirectory()) {
@@ -202,10 +202,14 @@ public class FSDataset implements FSConstants, FSDatasetInterface {
       }
 
       File blockFiles[] = dir.listFiles();
-      for (int i = 0; i < blockFiles.length; i++) {
-        if (Block.isBlockFilename(blockFiles[i])) {
-          long genStamp = getGenerationStampFromFile(blockFiles, blockFiles[i]);
-          blockSet.add(new Block(blockFiles[i], blockFiles[i].length(), genStamp));
+      if (blockFiles != null) {
+        for (int i = 0; i < blockFiles.length; i++) {
+          if (Block.isBlockFilename(blockFiles[i])) {
+            long genStamp = getGenerationStampFromFile(blockFiles,
+                blockFiles[i]);
+            blockSet.add(new Block(blockFiles[i], blockFiles[i].length(),
+                genStamp));
+          }
         }
       }
     }
@@ -218,11 +222,14 @@ public class FSDataset implements FSConstants, FSDatasetInterface {
       }
 
       File blockFiles[] = dir.listFiles();
-      for (int i = 0; i < blockFiles.length; i++) {
-        if (Block.isBlockFilename(blockFiles[i])) {
-          long genStamp = getGenerationStampFromFile(blockFiles, blockFiles[i]);
-          volumeMap.put(new Block(blockFiles[i], blockFiles[i].length(), genStamp), 
-                        new DatanodeBlockInfo(volume, blockFiles[i]));
+      if (blockFiles != null) {
+        for (int i = 0; i < blockFiles.length; i++) {
+          if (Block.isBlockFilename(blockFiles[i])) {
+            long genStamp = getGenerationStampFromFile(blockFiles,
+                blockFiles[i]);
+            volumeMap.put(new Block(blockFiles[i], blockFiles[i].length(),
+                genStamp), new DatanodeBlockInfo(volume, blockFiles[i]));
+          }
         }
       }
     }
@@ -469,10 +476,7 @@ public class FSDataset implements FSConstants, FSDatasetInterface {
      */
     private void recoverDetachedBlocks(File dataDir, File dir) 
                                            throws IOException {
-      File contents[] = dir.listFiles();
-      if (contents == null) {
-        return;
-      }
+      File contents[] = FileUtil.listFiles(dir);
       for (int i = 0; i < contents.length; i++) {
         if (!contents[i].isFile()) {
           throw new IOException ("Found " + contents[i] + " in " + dir +

src/test/org/apache/hadoop/fs/TestFileUtil.java

@@ -249,4 +249,58 @@ public class TestFileUtil {
     boolean ret = FileUtil.fullyDeleteContents(new MyFile(del));
     validateAndSetWritablePermissions(ret);
   }
+  
+  @Test
+  public void testListFiles() throws IOException {
+    setupDirs();
+    //Test existing files case 
+    File[] files = FileUtil.listFiles(tmp);
+    Assert.assertEquals(1, files.length);
+
+    //Test existing directory with no files case 
+    File newDir = new File(tmp.getPath(),"test");
+    newDir.mkdir();
+    Assert.assertTrue("Failed to create test dir", newDir.exists());
+    files = FileUtil.listFiles(newDir);
+    Assert.assertEquals(0, files.length);
+    newDir.delete();
+    Assert.assertFalse("Failed to delete test dir", newDir.exists());
+    
+    //Test non-existing directory case, this throws 
+    //IOException
+    try {
+      files = FileUtil.listFiles(newDir);
+      Assert.fail("IOException expected on listFiles() for non-existent dir "
+          + newDir.toString());
+    } catch(IOException ioe) {
+      //Expected an IOException
+    }
+  }
+
+  @Test
+  public void testListAPI() throws IOException {
+    setupDirs();
+    //Test existing files case 
+    String[] files = FileUtil.list(tmp);
+    Assert.assertEquals(1, files.length);
+
+    //Test existing directory with no files case 
+    File newDir = new File(tmp.getPath(),"test");
+    newDir.mkdir();
+    Assert.assertTrue("Failed to create test dir", newDir.exists());
+    files = FileUtil.list(newDir);
+    Assert.assertEquals(0, files.length);
+    newDir.delete();
+    Assert.assertFalse("Failed to delete test dir", newDir.exists());
+    
+    //Test non-existing directory case, this throws 
+    //IOException
+    try {
+      files = FileUtil.list(newDir);
+      Assert.fail("IOException expected on list() for non-existent dir "
+          + newDir.toString());
+    } catch(IOException ioe) {
+      //Expected an IOException
+    }
+  }
 }