[ 
https://issues.apache.org/jira/browse/HADOOP-18258?focusedWorklogId=783821&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-783821
 ]

ASF GitHub Bot logged work on HADOOP-18258:
-------------------------------------------

                Author: ASF GitHub Bot
            Created on: 22/Jun/22 11:38
            Start Date: 22/Jun/22 11:38
    Worklog Time Spent: 10m 
      Work Description: sravanigadey commented on code in PR #4383:
URL: https://github.com/apache/hadoop/pull/4383#discussion_r903630927


##########
hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/audit/AuditTool.java:
##########
@@ -0,0 +1,308 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ *  or more contributor license agreements.  See the NOTICE file
+ *  distributed with this work for additional information
+ *  regarding copyright ownership.  The ASF licenses this file
+ *  to you under the Apache License, Version 2.0 (the
+ *  "License"); you may not use this file except in compliance
+ *  with the License.  You may obtain a copy of the License at
+ *
+ *       http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing, software
+ *  distributed under the License is distributed on an "AS IS" BASIS,
+ *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ *  See the License for the specific language governing permissions and
+ *  limitations under the License.
+ */
+
+package org.apache.hadoop.fs.s3a.audit;
+
+import java.io.Closeable;
+import java.io.EOFException;
+import java.io.File;
+import java.io.IOException;
+import java.io.PrintWriter;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import org.apache.commons.io.FileUtils;
+import org.apache.hadoop.classification.VisibleForTesting;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.FilterFileSystem;
+import org.apache.hadoop.fs.LocatedFileStatus;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.RemoteIterator;
+import org.apache.hadoop.fs.s3a.S3AFileSystem;
+import org.apache.hadoop.util.ExitUtil;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
+
+import static 
org.apache.hadoop.service.launcher.LauncherExitCodes.EXIT_COMMAND_ARGUMENT_ERROR;
+import static 
org.apache.hadoop.service.launcher.LauncherExitCodes.EXIT_SERVICE_UNAVAILABLE;
+import static 
org.apache.hadoop.service.launcher.LauncherExitCodes.EXIT_SUCCESS;
+
+/**
+ * AuditTool is a Command Line Interface.
+ * i.e, it's functionality is to parse the merged audit log file.
+ * and generate avro file.
+ */
+public class AuditTool extends Configured implements Tool, Closeable {
+
+  private static final Logger LOG = LoggerFactory.getLogger(AuditTool.class);
+
+  private final String entryPoint = "s3audit";
+
+  private PrintWriter out;
+
+  // Exit codes
+  private static final int SUCCESS = EXIT_SUCCESS;
+  private static final int INVALID_ARGUMENT = EXIT_COMMAND_ARGUMENT_ERROR;
+
+  /**
+   * Error String when the wrong FS is used for binding: {@value}.
+   **/
+  @VisibleForTesting
+  public static final String WRONG_FILESYSTEM = "Wrong filesystem for ";
+
+  private final String usage = entryPoint + "  s3a://BUCKET\n";
+
+  public AuditTool() {
+  }
+
+  /**
+   * Tells us the usage of the AuditTool by commands.
+   *
+   * @return the string USAGE
+   */
+  public String getUsage() {
+    return usage;
+  }
+
+  /**
+   * This run method in AuditTool takes S3 bucket path.
+   * which contains audit log files from command line arguments.
+   * and merge the audit log files present in that path into single file in.
+   * local system.
+   *
+   * @param args command specific arguments.
+   * @return SUCCESS i.e, '0', which is an exit code.
+   * @throws Exception on any failure.
+   */
+  @Override
+  public int run(String[] args) throws Exception {
+    List<String> argv = new ArrayList<>(Arrays.asList(args));
+    if (argv.isEmpty()) {
+      errorln(getUsage());
+      throw invalidArgs("No bucket specified");
+    }
+    //Path of audit log files in s3 bucket
+    Path s3LogsPath = new Path(argv.get(0));
+
+    //Setting the file system
+    URI fsURI = toUri(String.valueOf(s3LogsPath));
+    S3AFileSystem s3AFileSystem =
+        bindFilesystem(FileSystem.newInstance(fsURI, getConf()));
+    RemoteIterator<LocatedFileStatus> listOfS3LogFiles =
+        s3AFileSystem.listFiles(s3LogsPath, true);
+
+    //Merging local audit files into a single file
+    File s3aLogsDirectory = new File(s3LogsPath.getName());
+    boolean s3aLogsDirectoryCreation = false;
+    if (!s3aLogsDirectory.exists()) {
+      s3aLogsDirectoryCreation = s3aLogsDirectory.mkdir();
+    }
+    if(s3aLogsDirectoryCreation) {
+      while (listOfS3LogFiles.hasNext()) {
+        Path s3LogFilePath = listOfS3LogFiles.next().getPath();
+        File s3LogLocalFilePath =

Review Comment:
   modified file name to s3LogLocalFile





Issue Time Tracking
-------------------

    Worklog Id:     (was: 783821)
    Time Spent: 6h 10m  (was: 6h)

> Merging of S3A Audit Logs
> -------------------------
>
>                 Key: HADOOP-18258
>                 URL: https://issues.apache.org/jira/browse/HADOOP-18258
>             Project: Hadoop Common
>          Issue Type: Sub-task
>          Components: fs/s3
>            Reporter: Sravani Gadey
>            Assignee: Sravani Gadey
>            Priority: Major
>              Labels: pull-request-available
>          Time Spent: 6h 10m
>  Remaining Estimate: 0h
>
> Merging audit log files containing huge number of audit logs collected from a 
> job like Hive or Spark job containing various S3 requests like list, head, 
> get and put requests.



--
This message was sent by Atlassian Jira
(v8.20.7#820007)

---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org

Reply via email to