HDFS-12221. Replace xcerces in XmlEditsVisitor. (Ajay Kumar via lei)

hadoop-client-modules/hadoop-client-minicluster/pom.xml

@@ -628,12 +628,6 @@
                         <exclude>**/*.class</exclude>
                       </excludes>
                     </filter>
-                    <filter>
-                      <artifact>xerces:xercesImpl</artifact>
-                      <excludes>
-                        <exclude>**/*</exclude>
-                      </excludes>
-                    </filter>
                     <filter>
                       <artifact>org.apache.hadoop:hadoop-mapreduce-client-jobclient:*</artifact>
                       <excludes>

hadoop-client-modules/hadoop-client-runtime/pom.xml

@@ -174,13 +174,6 @@
                         <exclude>org/apache/jasper/compiler/Localizer.class</exclude>
                       </excludes>
                     </filter>
-                    <!-- We only have xerces as a dependency for XML output for the fsimage edits, we don't need anything specific to it for javax xml support -->
-                    <filter>
-                      <artifact>xerces:xercesImpl</artifact>
-                      <excludes>
-                        <exclude>META-INF/services/*</exclude>
-                      </excludes>
-                    </filter>
                     <!-- We rely on jersey for our web interfaces. We want to use its java services stuff only internal to jersey -->
                     <filter>
                       <artifact>com.sun.jersey:*</artifact>

hadoop-hdfs-project/hadoop-hdfs/pom.xml

@@ -173,11 +173,6 @@ http://maven.apache.org/xsd/maven-4.0.0.xsd">
       <artifactId>netty-all</artifactId>
       <scope>compile</scope>
     </dependency>
-    <dependency>
-      <groupId>xerces</groupId>
-      <artifactId>xercesImpl</artifactId>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.htrace</groupId>
       <artifactId>htrace-core4</artifactId>

hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java

@@ -20,17 +20,21 @@ package org.apache.hadoop.hdfs.tools.offlineEditsViewer;
 import java.io.IOException;
 import java.io.OutputStream;
 
+import javax.xml.transform.OutputKeys;
+import javax.xml.transform.TransformerConfigurationException;
+import javax.xml.transform.sax.SAXTransformerFactory;
+import javax.xml.transform.sax.TransformerHandler;
+import javax.xml.transform.stream.StreamResult;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.SAXException;
+import org.xml.sax.helpers.AttributesImpl;
+
 import org.apache.hadoop.hdfs.util.XMLUtils;
 import org.apache.hadoop.hdfs.server.namenode.FSEditLogOp;
 
 import org.apache.hadoop.classification.InterfaceAudience;
 import org.apache.hadoop.classification.InterfaceStability;
-import org.xml.sax.ContentHandler;
-import org.xml.sax.SAXException;
-import org.xml.sax.helpers.AttributesImpl;
 
-import org.apache.xml.serialize.OutputFormat;
-import org.apache.xml.serialize.XMLSerializer;
 
 /**
  * An XmlEditsVisitor walks over an EditLog structure and writes out
@@ -41,26 +45,37 @@ import org.apache.xml.serialize.XMLSerializer;
 public class XmlEditsVisitor implements OfflineEditsVisitor {
   private final OutputStream out;
   private ContentHandler contentHandler;
+  private final SAXTransformerFactory factory;
+  private final static String XML_INDENTATION_PROP ="{http://xml.apache.org/" +
+          "xslt}indent-amount";
+  private final static String XML_INDENTATION_NUM ="2";
 
   /**
    * Create a processor that writes to the file named and may or may not
    * also output to the screen, as specified.
    *
-   * @param filename Name of file to write output to
-   * @param printToScreen Mirror output to screen?
+   * @param out output stream to write
+   * @throws IOException on any error
    */
   public XmlEditsVisitor(OutputStream out)
       throws IOException {
     this.out = out;
-    OutputFormat outFormat = new OutputFormat("XML", "UTF-8", true);
-    outFormat.setIndenting(true);
-    outFormat.setIndent(2);
-    outFormat.setDoctype(null, null);
-    XMLSerializer serializer = new XMLSerializer(out, outFormat);
-    contentHandler = serializer.asContentHandler();
+    factory =(SAXTransformerFactory)SAXTransformerFactory.newInstance();
     try {
+      TransformerHandler handler = factory.newTransformerHandler();
+      handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
+      handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "UTF-8");
+      handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
+      handler.getTransformer().setOutputProperty(XML_INDENTATION_PROP,
+              XML_INDENTATION_NUM);
+      handler.getTransformer().setOutputProperty(OutputKeys.STANDALONE, "yes");
+      handler.setResult(new StreamResult(out));
+      contentHandler = handler;
+      
       contentHandler.startDocument();
       contentHandler.startElement("", "", "EDITS", new AttributesImpl());
+    } catch (TransformerConfigurationException e) {
+      throw new IOException("SAXTransformer error: " + e.getMessage());
     } catch (SAXException e) {
       throw new IOException("SAX error: " + e.getMessage());
     }

hadoop-hdfs-project/hadoop-hdfs/src/test/resources/editsStored.xml

@@ -1,6 +1,6 @@
-<?xml version="1.0" encoding="UTF-8"?>
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 <EDITS>
-  <EDITS_VERSION>-63</EDITS_VERSION>
+  <EDITS_VERSION>-64</EDITS_VERSION>
   <RECORD>
     <OPCODE>OP_START_LOG_SEGMENT</OPCODE>
     <DATA>
@@ -63,8 +63,8 @@
       <MTIME>1422406380369</MTIME>
       <ATIME>1422406380345</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <PERMISSION_STATUS>
         <USERNAME>xyao</USERNAME>
@@ -96,8 +96,8 @@
       <MTIME>1422406380376</MTIME>
       <ATIME>1422406380345</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <PERMISSION_STATUS>
         <USERNAME>xyao</USERNAME>
@@ -238,8 +238,8 @@
       <MTIME>1422406380425</MTIME>
       <ATIME>1422406380423</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <PERMISSION_STATUS>
         <USERNAME>xyao</USERNAME>
@@ -360,7 +360,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1001</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -393,7 +393,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1002</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -426,7 +426,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1003</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -441,8 +441,8 @@
       <MTIME>1422406380534</MTIME>
       <ATIME>1422406380446</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <BLOCK>
         <BLOCK_ID>1073741825</BLOCK_ID>
@@ -513,7 +513,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1004</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -546,7 +546,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1005</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -579,7 +579,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1006</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -594,8 +594,8 @@
       <MTIME>1422406380558</MTIME>
       <ATIME>1422406380537</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <BLOCK>
         <BLOCK_ID>1073741828</BLOCK_ID>
@@ -666,7 +666,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1007</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -699,7 +699,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1008</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -732,7 +732,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1009</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -747,8 +747,8 @@
       <MTIME>1422406380579</MTIME>
       <ATIME>1422406380560</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <BLOCK>
         <BLOCK_ID>1073741831</BLOCK_ID>
@@ -834,7 +834,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1010</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -867,7 +867,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1011</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -882,8 +882,8 @@
       <MTIME>1422406380599</MTIME>
       <ATIME>1422406380586</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <BLOCK>
         <BLOCK_ID>1073741834</BLOCK_ID>
@@ -979,7 +979,7 @@
         <NUM_BYTES>0</NUM_BYTES>
         <GENSTAMP>1012</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -993,7 +993,7 @@
         <NUM_BYTES>11</NUM_BYTES>
         <GENSTAMP>1012</GENSTAMP>
       </BLOCK>
-      <RPC_CLIENTID></RPC_CLIENTID>
+      <RPC_CLIENTID/>
       <RPC_CALLID>-2</RPC_CALLID>
     </DATA>
   </RECORD>
@@ -1024,8 +1024,8 @@
       <MTIME>1422406383261</MTIME>
       <ATIME>1422406380608</ATIME>
       <BLOCKSIZE>512</BLOCKSIZE>
-      <CLIENT_NAME></CLIENT_NAME>
-      <CLIENT_MACHINE></CLIENT_MACHINE>
+      <CLIENT_NAME/>
+      <CLIENT_MACHINE/>
       <OVERWRITE>false</OVERWRITE>
       <BLOCK>
         <BLOCK_ID>1073741836</BLOCK_ID>

hadoop-mapreduce-project/hadoop-mapreduce-client/pom.xml

@@ -238,14 +238,6 @@
                       <outputDirectory>${project.build.directory}</outputDirectory>
                       <destFileName>hadoop-annotations.jar</destFileName>
                     </artifactItem>
-                    <artifactItem>
-                      <groupId>xerces</groupId>
-                      <artifactId>xercesImpl</artifactId>
-                      <version>${xerces.version.jdiff}</version>
-                      <overWrite>false</overWrite>
-                      <outputDirectory>${project.build.directory}</outputDirectory>
-                      <destFileName>xerces.jar</destFileName>
-                    </artifactItem>
                   </artifactItems>
                 </configuration>
               </execution>
@@ -283,7 +275,7 @@
                            sourceFiles="${dev-support.relative.dir}/jdiff/Null.java"
                            maxmemory="${jdiff.javadoc.maxmemory}">
                     <doclet name="org.apache.hadoop.classification.tools.IncludePublicAnnotationsJDiffDoclet"
-                            path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar:${project.build.directory}/xerces.jar">
+                            path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar">
                       <param name="-oldapi" value="${project.name} ${jdiff.stable.api}"/>
                       <param name="-newapi" value="${project.name} ${project.version}"/>
                       <param name="-oldapidir" value="${basedir}/${dev-support.relative.dir}/jdiff"/>

hadoop-project-dist/pom.xml

@@ -194,14 +194,6 @@
                       <outputDirectory>${project.build.directory}</outputDirectory>
                       <destFileName>hadoop-annotations.jar</destFileName>
                     </artifactItem>
-                    <artifactItem>
-                      <groupId>xerces</groupId>
-                      <artifactId>xercesImpl</artifactId>
-                      <version>${xerces.jdiff.version}</version>
-                      <overWrite>false</overWrite>
-                      <outputDirectory>${project.build.directory}</outputDirectory>
-                      <destFileName>xerces.jar</destFileName>
-                    </artifactItem>
                   </artifactItems>
                 </configuration>
               </execution>
@@ -267,7 +259,7 @@
                              sourceFiles="${basedir}/dev-support/jdiff/Null.java"
                              maxmemory="${jdiff.javadoc.maxmemory}">
                       <doclet name="org.apache.hadoop.classification.tools.IncludePublicAnnotationsJDiffDoclet"
-                              path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar:${project.build.directory}/xerces.jar">
+                              path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar">
                         <param name="-oldapi" value="${project.name} ${jdiff.stable.api}"/>
                         <param name="-newapi" value="${project.name} ${project.version}"/>
                         <param name="-oldapidir" value="${basedir}/dev-support/jdiff"/>

hadoop-project/pom.xml

@@ -45,8 +45,6 @@
     <!-- These 2 versions are defined here because they are used -->
     <!-- JDIFF generation from embedded ant in the antrun plugin -->
     <jdiff.version>1.0.9</jdiff.version>
-    <!-- Version number for xerces used by JDiff -->
-    <xerces.jdiff.version>2.11.0</xerces.jdiff.version>
 
     <kafka.version>0.8.2.1</kafka.version>
     <hbase.version>1.2.6</hbase.version>
@@ -1155,12 +1153,6 @@
         </exclusions>
      </dependency>
 
-     <dependency>
-       <groupId>xerces</groupId>
-       <artifactId>xercesImpl</artifactId>
-       <version>2.9.1</version>
-     </dependency>
-
      <dependency>
        <groupId>org.apache.curator</groupId>
        <artifactId>curator-recipes</artifactId>

hadoop-yarn-project/hadoop-yarn/pom.xml

@@ -155,14 +155,6 @@
                       <outputDirectory>${project.build.directory}</outputDirectory>
                       <destFileName>hadoop-annotations.jar</destFileName>
                     </artifactItem>
-                    <artifactItem>
-                      <groupId>xerces</groupId>
-                      <artifactId>xercesImpl</artifactId>
-                      <version>${xerces.version.jdiff}</version>
-                      <overWrite>false</overWrite>
-                      <outputDirectory>${project.build.directory}</outputDirectory>
-                      <destFileName>xerces.jar</destFileName>
-                    </artifactItem>
                   </artifactItems>
                 </configuration>
               </execution>
@@ -201,7 +193,7 @@
                       sourceFiles="${dev-support.relative.dir}/jdiff/Null.java"
                              maxmemory="${jdiff.javadoc.maxmemory}">
                       <doclet name="org.apache.hadoop.classification.tools.IncludePublicAnnotationsJDiffDoclet"
-                              path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar:${project.build.directory}/xerces.jar">
+                              path="${project.build.directory}/hadoop-annotations.jar:${project.build.directory}/jdiff.jar">
                         <param name="-oldapi" value="${project.name} ${jdiff.stable.api}"/>
                         <param name="-newapi" value="${project.name} ${project.version}"/>
                         <param name="-oldapidir" value="${basedir}/${dev-support.relative.dir}/jdiff"/>