Merge pull request #5 from datastax/feature/log4j-vulnerability-fix

Resolved log4j vulnerability

Author: pravinbhat

.idea/runConfigurations.xml

@@ -44,8 +44,10 @@ Note: Above command also generates a log file `logfile_name.txt` to avoid log ou
 - Validation job will report differences as “ERRORS” in the log file as shown below
 
 ```
-22/02/16 12:41:15 ERROR DiffJobSession: Data is missing in Astra: e7cd5752-bc0d-4157-a80f-7523add8dbcd
-22/02/16 12:41:15 ERROR DiffJobSession: Data difference found -  Key: 1 Data:  (Index: 3 Source: [val-A, val-B] Astra: [val-A, val-B, val-C] )
+22/09/27 11:21:24 ERROR DiffJobSession: Data mismatch found -  Key: ek-1 %% mn1 %% c1 %% true Data:  (Index: 4 Source: 30 Astra: 20 )
+22/09/27 11:21:24 ERROR DiffJobSession: Corrected mismatch data in Astra: ek-1 %% mn1 %% c1 %% true
+22/09/27 11:21:24 ERROR DiffJobSession: Data is missing in Astra: ek-2 %% mn2 %% c2 %% true
+22/09/27 11:21:24 ERROR DiffJobSession: Corrected missing data in Astra: ek-2 %% mn2 %% c2 %% true
 ```
 
 - Please grep for all `ERROR` from the output log files to get the list of missing and mismatched records.

README.md

@@ -3,7 +3,7 @@
 
   <groupId>datastax.astra.migrate</groupId>
   <artifactId>cassandra-data-migrator</artifactId>
-  <version>1.2</version>
+  <version>1.3</version>
   <packaging>jar</packaging>
 
   <properties>
@@ -32,6 +32,12 @@
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.main.version}</artifactId>
       <version>${spark.version}</version>
+      <exclusions>
+        <exclusion>
+          <groupId>log4j</groupId>
+          <artifactId>log4j</artifactId>
+        </exclusion>
+      </exclusions>
     </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
@@ -42,13 +48,39 @@
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-hive_${scala.main.version}</artifactId>
       <version>${spark.version}</version>
+      <exclusions>
+        <exclusion>
+          <groupId>log4j</groupId>
+          <artifactId>log4j</artifactId>
+        </exclusion>
+        <exclusion>
+          <groupId>log4j</groupId>
+          <artifactId>apache-log4j-extras</artifactId>
+        </exclusion>
+      </exclusions>
     </dependency>
     <dependency>
       <groupId>com.datastax.spark</groupId>
       <artifactId>spark-cassandra-connector_${scala.main.version}</artifactId>
       <version>${connector.version}</version>
     </dependency>
 
+    <dependency>
+      <groupId>org.apache.logging.log4j</groupId>
+      <artifactId>log4j-api</artifactId>
+      <version>2.19.0</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.logging.log4j</groupId>
+      <artifactId>log4j-core</artifactId>
+      <version>2.19.0</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.logging.log4j</groupId>
+      <artifactId>log4j-to-slf4j</artifactId>
+      <version>2.19.0</version>
+    </dependency>
+
     <!-- Test Dependencies -->
     <dependency>
       <groupId>org.scalatest</groupId>

pom.xml

@@ -5,8 +5,9 @@
 import com.datastax.oss.driver.api.core.cql.PreparedStatement;
 import com.datastax.oss.driver.api.core.cql.Row;
 import com.datastax.oss.driver.shaded.guava.common.util.concurrent.RateLimiter;
-import org.apache.log4j.Logger;
 import org.apache.spark.SparkConf;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.util.ArrayList;
 import java.util.List;
@@ -15,7 +16,7 @@
 
 public abstract class AbstractJobSession {
 
-    public static Logger logger = Logger.getLogger(AbstractJobSession.class);
+    public Logger logger = LoggerFactory.getLogger(this.getClass().getName());
 
     protected PreparedStatement sourceSelectStatement;
     protected String sourceSelectCondition;

src/main/java/datastax/astra/migrate/AbstractJobSession.java

@@ -2,8 +2,9 @@
 
 import com.datastax.oss.driver.api.core.CqlSession;
 import com.datastax.oss.driver.api.core.cql.*;
-import org.apache.log4j.Logger;
 import org.apache.spark.SparkConf;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.math.BigInteger;
 import java.util.ArrayList;
@@ -15,7 +16,7 @@
 
 public class CopyJobSession extends AbstractJobSession {
 
-    public static Logger logger = Logger.getLogger(CopyJobSession.class);
+    public Logger logger = LoggerFactory.getLogger(this.getClass().getName());
     private static CopyJobSession copyJobSession;
 
     protected PreparedStatement astraInsertStatement;

src/main/java/datastax/astra/migrate/CopyJobSession.java

@@ -4,20 +4,19 @@
 import com.datastax.oss.driver.api.core.CqlSession;
 import com.datastax.oss.driver.api.core.cql.ResultSet;
 import com.datastax.oss.driver.api.core.cql.Row;
-import org.apache.log4j.Logger;
 import org.apache.spark.SparkConf;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.math.BigInteger;
-import java.util.ArrayList;
-import java.util.List;
 import java.util.concurrent.ForkJoinPool;
 import java.util.concurrent.atomic.AtomicLong;
 import java.util.stream.IntStream;
 import java.util.stream.StreamSupport;
 
 public class DiffJobSession extends CopyJobSession {
 
-    public static Logger logger = Logger.getLogger(DiffJobSession.class);
+    public Logger logger = LoggerFactory.getLogger(this.getClass().getName());
     private static DiffJobSession diffJobSession;
 
     private AtomicLong readCounter = new AtomicLong(0);

src/main/java/datastax/astra/migrate/DiffJobSession.java

@@ -1,6 +1,7 @@
 package datastax.astra.migrate;
 
-import org.apache.log4j.Logger;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.Serializable;
 import java.math.BigInteger;
@@ -11,7 +12,7 @@
 
 public class SplitPartitions {
 
-    public static Logger logger = Logger.getLogger(SplitPartitions.class);
+    public static Logger logger = LoggerFactory.getLogger(SplitPartitions.class.getName());
     public final static Long MIN_PARTITION = Long.MIN_VALUE;
     public final static Long MAX_PARTITION  = Long.MAX_VALUE;
 

src/main/java/datastax/astra/migrate/SplitPartitions.java

@@ -1,15 +1,15 @@
 package datastax.astra.migrate
 
 import com.datastax.spark.connector.cql.CassandraConnector
-import org.apache.log4j.Logger
 import org.apache.spark.sql.SparkSession
+import org.slf4j.LoggerFactory
 
 import java.math.BigInteger
 import java.lang.Long
 
 class AbstractJob extends App {
 
-  val abstractLogger = Logger.getLogger(this.getClass.getName)
+  val abstractLogger = LoggerFactory.getLogger(this.getClass.getName)
   val spark = SparkSession.builder
     .appName("Datastax Data Validation")
     .getOrCreate()

src/main/scala/datastax/astra/migrate/AbstractJob.scala

@@ -1,13 +1,13 @@
 package datastax.astra.migrate
 
 import com.datastax.spark.connector.cql.CassandraConnector
-import org.apache.log4j.Logger
+import org.slf4j.LoggerFactory
 
 import scala.collection.JavaConversions._
 
 object DiffData extends AbstractJob {
 
-  val logger = Logger.getLogger(this.getClass.getName)
+  val logger = LoggerFactory.getLogger(this.getClass.getName)
   logger.info("Started Data Validation App")
 
   diffTable(sourceConnection, destinationConnection)