HADOOP-9264. Port change to use Java untar API on Windows from branch-1-win to trunk. Contributed by Chris Nauroth.

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1441172 13f79535-47bb-0310-9956-ffa450edef68

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

@@ -325,6 +325,9 @@ Trunk (Unreleased)
     HADOOP-9249. hadoop-maven-plugins version-info goal causes build failure
     when running with Clover. (Chris Nauroth via suresh)
 
+    HADOOP-9264. Port change to use Java untar API on Windows from 
+    branch-1-win to trunk. (Chris Nauroth via suresh)
+
   OPTIMIZATIONS
 
     HADOOP-7761. Improve the performance of raw comparisons. (todd)

hadoop-common-project/hadoop-common/pom.xml

@@ -241,6 +241,11 @@
       <type>test-jar</type>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.apache.commons</groupId>
+      <artifactId>commons-compress</artifactId>
+      <version>1.4</version>
+    </dependency>
   </dependencies>
 
   <build>
@@ -381,6 +386,23 @@
               </target>
             </configuration>
           </execution>
+          <execution>
+            <id>copy-test-tarballs</id>
+            <phase>process-test-resources</phase>
+            <goals>
+              <goal>run</goal>
+            </goals>
+            <configuration>
+              <target>
+                <copy toDir="${test.cache.data}">
+                  <fileset dir="${basedir}/src/test/java/org/apache/hadoop/fs">
+                    <include name="test-untar.tar"/>
+                    <include name="test-untar.tgz"/>
+                  </fileset>
+                </copy>
+              </target>
+            </configuration>
+          </execution>
           <execution>
             <phase>pre-site</phase>
             <goals>
@@ -485,6 +507,7 @@
             <exclude>src/test/all-tests</exclude>
             <exclude>src/test/resources/kdc/ldif/users.ldif</exclude>
             <exclude>src/main/native/src/org/apache/hadoop/io/compress/lz4/lz4.c</exclude>
+            <exclude>src/test/java/org/apache/hadoop/fs/test-untar.tgz</exclude>
           </excludes>
         </configuration>
       </plugin>

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

@@ -21,9 +21,12 @@ package org.apache.hadoop.fs;
 import java.io.*;
 import java.util.Arrays;
 import java.util.Enumeration;
+import java.util.zip.GZIPInputStream;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipFile;
 
+import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
+import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
 import org.apache.hadoop.classification.InterfaceAudience;
 import org.apache.hadoop.classification.InterfaceStability;
 import org.apache.hadoop.conf.Configuration;
@@ -630,8 +633,22 @@ public class FileUtil {
       }
     }
 
-    StringBuilder untarCommand = new StringBuilder();
     boolean gzipped = inFile.toString().endsWith("gz");
+    if(Shell.WINDOWS) {
+      // Tar is not native to Windows. Use simple Java based implementation for 
+      // tests and simple tar archives
+      unTarUsingJava(inFile, untarDir, gzipped);
+    }
+    else {
+      // spawn tar utility to untar archive for full fledged unix behavior such 
+      // as resolving symlinks in tar archives
+      unTarUsingTar(inFile, untarDir, gzipped);
+    }
+  }
+  
+  private static void unTarUsingTar(File inFile, File untarDir,
+      boolean gzipped) throws IOException {
+    StringBuffer untarCommand = new StringBuffer();
     if (gzipped) {
       untarCommand.append(" gzip -dc '");
       untarCommand.append(FileUtil.makeShellPath(inFile));
@@ -657,6 +674,61 @@ public class FileUtil {
     }
   }
   
+  private static void unTarUsingJava(File inFile, File untarDir,
+      boolean gzipped) throws IOException {
+    InputStream inputStream = null;
+    if (gzipped) {
+      inputStream = new BufferedInputStream(new GZIPInputStream(
+          new FileInputStream(inFile)));
+    } else {
+      inputStream = new BufferedInputStream(new FileInputStream(inFile));
+    }
+
+    TarArchiveInputStream tis = new TarArchiveInputStream(inputStream);
+
+    for (TarArchiveEntry entry = tis.getNextTarEntry(); entry != null;) {
+      unpackEntries(tis, entry, untarDir);
+      entry = tis.getNextTarEntry();
+    }
+  }
+  
+  private static void unpackEntries(TarArchiveInputStream tis,
+      TarArchiveEntry entry, File outputDir) throws IOException {
+    if (entry.isDirectory()) {
+      File subDir = new File(outputDir, entry.getName());
+      if (!subDir.mkdir() && !subDir.isDirectory()) {
+        throw new IOException("Mkdirs failed to create tar internal dir "
+            + outputDir);
+      }
+
+      for (TarArchiveEntry e : entry.getDirectoryEntries()) {
+        unpackEntries(tis, e, subDir);
+      }
+
+      return;
+    }
+
+    File outputFile = new File(outputDir, entry.getName());
+    if (!outputDir.exists()) {
+      if (!outputDir.mkdirs()) {
+        throw new IOException("Mkdirs failed to create tar internal dir "
+            + outputDir);
+      }
+    }
+
+    int count;
+    byte data[] = new byte[2048];
+    BufferedOutputStream outputStream = new BufferedOutputStream(
+        new FileOutputStream(outputFile));
+
+    while ((count = tis.read(data)) != -1) {
+      outputStream.write(data, 0, count);
+    }
+
+    outputStream.flush();
+    outputStream.close();
+  }
+  
   /**
    * Class for creating hardlinks.
    * Supports Unix, Cygwin, WindXP.

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

@@ -546,4 +546,44 @@ public class TestFileUtil {
     long expected = 2 * (3 + System.getProperty("line.separator").length());
     Assert.assertEquals(expected, du);
   }
+
+  private void doUntarAndVerify(File tarFile, File untarDir) 
+                                 throws IOException {
+    if (untarDir.exists() && !FileUtil.fullyDelete(untarDir)) {
+      throw new IOException("Could not delete directory '" + untarDir + "'");
+    }
+    FileUtil.unTar(tarFile, untarDir);
+
+    String parentDir = untarDir.getCanonicalPath() + Path.SEPARATOR + "name";
+    File testFile = new File(parentDir + Path.SEPARATOR + "version");
+    Assert.assertTrue(testFile.exists());
+    Assert.assertTrue(testFile.length() == 0);
+    String imageDir = parentDir + Path.SEPARATOR + "image";
+    testFile = new File(imageDir + Path.SEPARATOR + "fsimage");
+    Assert.assertTrue(testFile.exists());
+    Assert.assertTrue(testFile.length() == 157);
+    String currentDir = parentDir + Path.SEPARATOR + "current";
+    testFile = new File(currentDir + Path.SEPARATOR + "fsimage");
+    Assert.assertTrue(testFile.exists());
+    Assert.assertTrue(testFile.length() == 4331);
+    testFile = new File(currentDir + Path.SEPARATOR + "edits");
+    Assert.assertTrue(testFile.exists());
+    Assert.assertTrue(testFile.length() == 1033);
+    testFile = new File(currentDir + Path.SEPARATOR + "fstime");
+    Assert.assertTrue(testFile.exists());
+    Assert.assertTrue(testFile.length() == 8);
+  }
+
+  @Test
+  public void testUntar() throws IOException {
+    String tarGzFileName = System.getProperty("test.cache.data",
+        "build/test/cache") + "/test-untar.tgz";
+    String tarFileName = System.getProperty("test.cache.data",
+        "build/test/cache") + "/test-untar.tar";
+    String dataDir = System.getProperty("test.build.data", "build/test/data");
+    File untarDir = new File(dataDir, "untarDir");
+
+    doUntarAndVerify(new File(tarGzFileName), untarDir);
+    doUntarAndVerify(new File(tarFileName), untarDir);
+  }
 }