HADOOP-18136. Verify FileUtils.unTar() handling of missing .tar files.

Contributed by Steve Loughran

Change-Id: Id6f3f2b0eeeb186a757d8b6ee5a0584cb4114469

Author: steveloughran

hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileUtil.java

@@ -886,10 +886,13 @@ private static void unTarUsingTar(InputStream inputStream, File untarDir,
   private static void unTarUsingTar(File inFile, File untarDir,
       boolean gzipped) throws IOException {
     StringBuffer untarCommand = new StringBuffer();
+    // not using canonical path here; this postpones relative path
+    // resolution until bash is executed.
+    final String source = "'" + FileUtil.makeSecureShellPath(inFile) + "'";
     if (gzipped) {
-      untarCommand.append(" gzip -dc '");
-      untarCommand.append(FileUtil.makeSecureShellPath(inFile));
-      untarCommand.append("' | (");
+      untarCommand.append(" gzip -dc ")
+          .append(source)
+          .append(" | (");
     }
     untarCommand.append("cd '");
     untarCommand.append(FileUtil.makeSecureShellPath(untarDir));
@@ -899,15 +902,17 @@ private static void unTarUsingTar(File inFile, File untarDir,
     if (gzipped) {
       untarCommand.append(" -)");
     } else {
-      untarCommand.append(FileUtil.makeSecureShellPath(inFile));
+      untarCommand.append(source);
     }
+    LOG.debug("executing [{}]", untarCommand);
     String[] shellCmd = { "bash", "-c", untarCommand.toString() };
     ShellCommandExecutor shexec = new ShellCommandExecutor(shellCmd);
     shexec.execute();
     int exitcode = shexec.getExitCode();
     if (exitcode != 0) {
       throw new IOException("Error untarring file " + inFile +
-                  ". Tar process exited with exit code " + exitcode);
+          ". Tar process exited with exit code " + exitcode
+          + " from command " + untarCommand);
     }
   }
 

hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/TestFileUtil.java

@@ -17,6 +17,7 @@
  */
 package org.apache.hadoop.fs;
 
+import static org.apache.hadoop.test.LambdaTestUtils.intercept;
 import static org.apache.hadoop.test.PlatformAssumptions.assumeNotWindows;
 import static org.junit.Assert.assertArrayEquals;
 import static org.junit.Assert.assertEquals;
@@ -1164,6 +1165,38 @@ public void testUntar() throws IOException {
     doUntarAndVerify(new File(tarFileName), untarDir);
   }
 
+  /**
+   * Verify we can't unTar a file which isn't there.
+   * This will test different codepaths on Windows from unix,
+   * but both MUST throw an IOE of some kind.
+   */
+  @Test(timeout = 30000)
+  public void testUntarMissingFile() throws Throwable {
+    File dataDir = GenericTestUtils.getTestDir();
+    File tarFile = new File(dataDir, "missing; true");
+    File untarDir = new File(dataDir, "untarDir");
+    intercept(IOException.class, () ->
+        FileUtil.unTar(tarFile, untarDir));
+  }
+
+  /**
+   * Verify we can't unTar a file which isn't there
+   * through the java untar code.
+   * This is how {@code FileUtil.unTar(File, File}
+   * will behave on Windows,
+   */
+  @Test(timeout = 30000)
+  public void testUntarMissingFileThroughJava() throws Throwable {
+    File dataDir = GenericTestUtils.getTestDir();
+    File tarFile = new File(dataDir, "missing; true");
+    File untarDir = new File(dataDir, "untarDir");
+    // java8 on unix throws java.nio.file.NoSuchFileException here;
+    // leaving as an IOE intercept in case windows throws something
+    // else.
+    intercept(IOException.class, () ->
+        FileUtil.unTarUsingJava(tarFile, untarDir, false));
+  }
+
   @Test (timeout = 30000)
   public void testCreateJarWithClassPath() throws Exception {
     // setup test directory for files