Merge pull request #60 from scalyr/log4JUpdate

Address Log4J Arbitrary Code Execution Exploit

Author: Kami

.circleci/config.yml

@@ -6,15 +6,15 @@ version: 2.1
 parameters:
   scalyr_sink_version: # scalyr_sink_version needs to be updated on every new version release.
     type: string
-    default: "1.3"
+    default: "1.4"
 
 jobs: # a collection of steps
   build: # runs not using Workflows must have a `build` job as entry point
 
     working_directory: ~/circleci-kafka-connect-scalyr # directory where steps will run
 
     docker: # run the steps with Docker
-      - image: circleci/openjdk:8-jdk-stretch # ...with this image as the primary container; this is where all `steps` will run
+      - image: cimg/openjdk:11.0 # ...with this image as the primary container; this is where all `steps` will run
 
     steps: # a collection of executable commands
 
@@ -39,14 +39,6 @@ jobs: # a collection of steps
 
       - setup_remote_docker
 
-      - run: # Python dependencies for System Test
-          name: Python Dependencies
-          command: |
-            set -x
-            sudo apt update
-            sudo apt install python-pip
-            pip install requests
-
       - run:
           name: System Test
           command: |
@@ -61,10 +53,10 @@ jobs: # a collection of steps
             .circleci/configure_scalyr_connector.sh
 
             # Verify logs are in Scalyr
-            python .circleci/verify_scalyr_events.py dataset=\'accesslog\'
-            python .circleci/verify_scalyr_events.py app=\'customApp\'
-            python .circleci/verify_scalyr_events.py tag=\'fluentd-apache\'
-            python .circleci/verify_scalyr_events.py tag=\'fluentbit-cpu\' 50
+            python3 .circleci/verify_scalyr_events.py dataset=\'accesslog\'
+            python3 .circleci/verify_scalyr_events.py app=\'customApp\'
+            python3 .circleci/verify_scalyr_events.py tag=\'fluentd-apache\'
+            python3 .circleci/verify_scalyr_events.py tag=\'fluentbit-cpu\' 50
 
       - store_test_results: # uploads the test metadata from the `target/surefire-reports` directory so that it can show up in the CircleCI dashboard. 
           # Upload test results for display in Test Summary: https://circleci.com/docs/2.0/collect-test-data/

.circleci/verify_scalyr_events.py

@@ -1,4 +1,5 @@
-# Copyright 2014-2020 Scalyr Inc.
+#!/usr/bin/env python3
+# Copyright 2014-2021 Scalyr Inc.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -106,10 +107,10 @@ def check_scalyr_events(additional_filter, expected_num_events):
 
   print("Query returned {0} Scalyr events".format(matches))
   if not has_expected_session_attrs:
-    print "Session attributes incorrect!"
+    print("Session attributes incorrect!")
 
   if not has_expected_event_attrs:
-    print "Event attributes incorrect!"
+    print("Event attributes incorrect!")
 
   return matches == expected_num_events and has_expected_session_attrs and has_expected_event_attrs
 

CHANGELOG.md

@@ -1,22 +1,30 @@
 # Kafka Connect Scalyr Sink Connector Changes by Release
 
+## 1.4
+
+* Address Log4J Arbitrary Code Execution exploit by upgrading to log4j v2.15.0. For more information on the vulnerability
+  see upstream log4j CVE https://nvd.nist.gov/vuln/detail/CVE-2021-44228.
+
+## 1.3
+
+Features
+* Regular expression support for custom application event mapping `matcher.value`.
+* `matchAll` support for custom application event mapping matcher.
+
+## 1.2
+
+* Allow not specifying application attribute fields in custom application event mappings when `send_entire_record` is `true`.
+* Change default `batch_send_size_bytes` to 5 MB.
+
+## 1.1
+Performance improvements for JSON serialization.
+
 ## 1.0
+
 Initial Release
 
 Features:
 * Supports Elastic Filebeat log messages with automatic conversion of Filebeat log messages to Scalyr log events.
 * Supports custom application log messages using user defined conversion of message fields to Scalyr log event attributes.
 * Supports Fluentd and Fluent Bit using custom application event mappings.
 * Exactly once delivery using the topic, partition, and offset to uniquely identify events and prevent duplicate delivery.
-
-## 1.1
-Performance improvements for JSON serialization.
-
-## 1.2
-* Allow not specifying application attribute fields in custom application event mappings when `send_entire_record` is `true`.
-* Change default `batch_send_size_bytes` to 5 MB.
-
-## 1.3
-Features
-* Regular expression support for custom application event mapping `matcher.value`.
-* `matchAll` support for custom application event mapping matcher.

docker-compose.yml

@@ -8,14 +8,14 @@
 version: '3'
 services:
   zookeeper:
-    image: confluentinc/cp-zookeeper:5.4.3
+    image: confluentinc/cp-zookeeper:6.1.0
     container_name: zookeeper
     environment:
       ZOOKEEPER_CLIENT_PORT: 2181
       ZOOKEEPER_TICK_TIME: 2000
 
   kafka:
-    image: confluentinc/cp-kafka:5.4.3
+    image: confluentinc/cp-kafka:6.1.0
     container_name: kafka
     depends_on:
       - zookeeper
@@ -30,14 +30,14 @@ services:
       KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
 
   kafka-setup:
-    image: confluentinc/cp-kafka:5.4.3
+    image: confluentinc/cp-kafka:6.1.0
     depends_on:
       - kafka
     command: "bash -c 'echo Waiting for Kafka to be ready... && \
                        cub kafka-ready -z zookeeper:2181 1 30 && \
-                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --topic connect-config-storage && \
-                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --topic connect-offset-storage && \
-                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --topic connect-status-storage && \
+                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --config cleanup.policy=compact --topic connect-config-storage && \
+                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --config cleanup.policy=compact --topic connect-offset-storage && \
+                       kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --config cleanup.policy=compact --topic connect-status-storage && \
                        kafka-topics --create --if-not-exists --zookeeper zookeeper:2181 --partitions 1 --replication-factor 1 --topic logs'"
     environment:
       KAFKA_BROKER_ID: 1

pom.xml

@@ -4,14 +4,14 @@
 
     <groupId>com.scalyr.integrations.kafka</groupId>
     <artifactId>kafka-connect-scalyr-sink</artifactId>
-    <version>1.3</version>
+    <version>1.4</version>
     <packaging>jar</packaging>
 
     <name>kafka-connect-scalyr-sink</name>
 
     <properties>
         <kafka.version>2.4.1</kafka.version>
-        <junit.version>4.13.1</junit.version>
+        <junit.version>4.13.2</junit.version>
         <sonar.projectKey>scalyr_kafka-connect-scalyr</sonar.projectKey>
         <sonar.organization>scalyr</sonar.organization>
         <sonar.host.url>https://sonarcloud.io</sonar.host.url>
@@ -44,7 +44,7 @@
         <dependency>
             <groupId>com.google.guava</groupId>
             <artifactId>guava</artifactId>
-            <version>29.0-jre</version>
+            <version>31.0.1-jre</version>
         </dependency>
         <dependency>
             <groupId>com.github.luben</groupId>
@@ -76,21 +76,22 @@
             <scope>test</scope>
         </dependency>
         <dependency>
-           <groupId>org.slf4j</groupId>
-           <artifactId>slf4j-api</artifactId>
-           <version>1.7.32</version>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-core</artifactId>
+            <version>2.15.0</version>
         </dependency>
         <dependency>
-           <groupId>org.slf4j</groupId>
-           <artifactId>slf4j-log4j12</artifactId>
-           <version>1.7.32</version>
+            <groupId>org.apache.logging.log4j</groupId>
+            <artifactId>log4j-slf4j-impl</artifactId>
+            <version>2.15.0</version>
         </dependency>
     </dependencies>
     <build>
         <plugins>
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-jar-plugin</artifactId>
+                <version>3.2.0</version>
                 <configuration>
                     <archive>
                         <manifest>
@@ -106,13 +107,13 @@
                 <version>2.5.1</version>
                 <inherited>true</inherited>
                 <configuration>
-                    <source>8</source>
-                    <target>8</target>
+                    <source>11</source>
+                    <target>11</target>
                 </configuration>
             </plugin>
             <plugin>
                 <artifactId>maven-assembly-plugin</artifactId>
-                <version>2.5.3</version>
+                <version>3.3.0</version>
                 <configuration>
                     <descriptors>
                         <descriptor>src/main/assembly/package.xml</descriptor>

src/test/SystemTest/docker/kafka-connect/Dockerfile

@@ -1,5 +1,4 @@
 # Create Kafka Connect image with Scalyr Sink Connector
-#FROM confluentinc/cp-kafka-connect-base:latest # latest build doesn't even start correctly without our connector
-FROM confluentinc/cp-kafka-connect:5.5.1-1-ubi8
+FROM confluentinc/cp-kafka-connect:6.1.0-1-ubi8
 RUN mkdir -p /etc/kafka-connect/jars/kafka-connect-scalyr-sink
 COPY target/kafka-connect-scalyr-sink-latest-package/share/java/kafka-connect-scalyr-sink /etc/kafka-connect/jars/kafka-connect-scalyr-sink

src/test/java/com/scalyr/integrations/kafka/AddEventsClientTest.java

@@ -26,8 +26,8 @@
 import okhttp3.mockwebserver.MockResponse;
 import okhttp3.mockwebserver.MockWebServer;
 import okhttp3.mockwebserver.RecordedRequest;
-import org.apache.log4j.Level;
-import org.apache.log4j.LogManager;
+import org.apache.logging.log4j.Level;
+import org.apache.logging.log4j.core.config.Configurator;
 import org.asynchttpclient.AsyncHttpClient;
 import org.junit.After;
 import org.junit.Before;
@@ -47,6 +47,7 @@
 import java.util.UUID;
 import java.util.concurrent.CompletableFuture;
 import java.util.concurrent.TimeUnit;
+
 import java.util.stream.Collectors;
 import java.util.stream.IntStream;
 import java.util.stream.Stream;
@@ -103,7 +104,7 @@ public void setup() {
     this.deflateCompressor = CompressorFactory.getCompressor(CompressorFactory.DEFLATE, 3);
 
     // We disable payload logging so we don't get very large raw payload messages in the log output
-    LogManager.getLogger("com.scalyr.integrations.kafka.eventpayload").setLevel(Level.OFF);
+    Configurator.setLevel("com.scalyr.integrations.kafka.eventpayload", Level.OFF);
   }
 
   @After