Add Apache Atlas version 2.2.0

Dockerfile

@@ -1,59 +1,87 @@
-FROM scratch
-FROM ubuntu:18.04
+FROM ubuntu:20.04 as build
 LABEL maintainer="[email protected]"
-ARG VERSION=2.1.0
+
+ARG VERSION=2.2.0
+ARG DEBIAN_FRONTEND=noninteractive
+ENV TZ=Etc/UTC
+ENV MAVEN_OPTS="-Xms2g -Xmx2g"
+ENV JAVA_HOME="/usr/lib/jvm/java-8-openjdk-amd64"
+
+RUN mkdir -p /tmp/atlas-src \
+    && mkdir -p /apache-atlas \
+    && mkdir -p /gremlin
+
+COPY pom.xml.patch /tmp/atlas-src/
 
 RUN apt-get update \
     && apt-get -y upgrade \
     && apt-get -y install apt-utils \
     && apt-get -y install \
         maven \
         wget \
-        git \
         python \
         openjdk-8-jdk-headless \
         patch \
-	unzip \
+        unzip \
     && cd /tmp \
-    && wget http://mirror.linux-ia64.org/apache/atlas/${VERSION}/apache-atlas-${VERSION}-sources.tar.gz \
-    && mkdir -p /opt/gremlin \
-    && mkdir -p /tmp/atlas-src \
+    && wget https://archive.apache.org/dist/atlas/${VERSION}/apache-atlas-${VERSION}-sources.tar.gz \
     && tar --strip 1 -xzvf apache-atlas-${VERSION}-sources.tar.gz -C /tmp/atlas-src \
     && rm apache-atlas-${VERSION}-sources.tar.gz \
     && cd /tmp/atlas-src \
     && sed -i 's/http:\/\/repo1.maven.org\/maven2/https:\/\/repo1.maven.org\/maven2/g' pom.xml \
-    && export MAVEN_OPTS="-Xms2g -Xmx2g" \
-    && export JAVA_HOME="/usr/lib/jvm/java-8-openjdk-amd64" \
-    && mvn clean -Dmaven.repo.local=/tmp/.mvn-repo -Dhttps.protocols=TLSv1.2 -DskipTests package -Pdist,embedded-hbase-solr \
-    && tar -xzvf /tmp/atlas-src/distro/target/apache-atlas-${VERSION}-server.tar.gz -C /opt \
+    && patch -b -f < pom.xml.patch \
+    && mvn clean \
+        -Dmaven.repo.local=/tmp/atlas-src/.mvn-repo \
+        -Dhttps.protocols=TLSv1.2 \
+        -DskipTests \
+        -Drat.skip=true \
+        package -Pdist,embedded-hbase-solr \
+    && tar --strip 1 -xzvf /tmp/atlas-src/distro/target/apache-atlas-${VERSION}-server.tar.gz -C /apache-atlas \
     && rm -Rf /tmp/atlas-src \
-    && rm -Rf /tmp/.mvn-repo \
     && apt-get -y --purge remove \
         maven \
         git \
-    && apt-get -y remove openjdk-11-jre-headless \
+        unzip \
     && apt-get -y autoremove \
     && apt-get -y clean
 
-VOLUME ["/opt/apache-atlas-${VERSION}/conf", "/opt/apache-atlas-${VERSION}/logs"]
+FROM ubuntu:20.04
+LABEL maintainer="[email protected]"
+ARG VERSION=2.2.0
+ENV JAVA_HOME="/usr/lib/jvm/java-8-openjdk-amd64"
 
-COPY atlas_start.py.patch atlas_config.py.patch /opt/apache-atlas-${VERSION}/bin/
+COPY --from=build /apache-atlas /apache-atlas
 
-RUN cd /opt/apache-atlas-${VERSION}/bin \
-    && patch -b -f < atlas_start.py.patch \
-    && patch -b -f < atlas_config.py.patch
+RUN apt-get update \
+    && apt-get -y upgrade \
+    && apt-get -y install apt-utils \
+    && apt-get -y install \
+        maven \
+        wget \
+        python \
+        openjdk-8-jdk-headless \
+        patch
 
-COPY conf/hbase/hbase-site.xml.template /opt/apache-atlas-${VERSION}/conf/hbase/hbase-site.xml.template
-COPY conf/atlas-env.sh /opt/apache-atlas-${VERSION}/conf/atlas-env.sh
+COPY conf/hbase/hbase-site.xml.template /apache-atlas/conf/hbase/hbase-site.xml.template
+COPY atlas_start.py.patch atlas_config.py.patch /apache-atlas/bin/
+COPY conf/atlas-env.sh /apache-atlas/conf/atlas-env.sh
+COPY conf/gremlin /gremlin/
 
-COPY conf/gremlin /opt/gremlin/
+WORKDIR /apache-atlas/bin
+RUN patch -b -f < atlas_start.py.patch \
+    && patch -b -f < atlas_config.py.patch
 
-RUN cd /opt/apache-atlas-${VERSION} \
-    && ./bin/atlas_start.py -setup || true
+WORKDIR /apache-atlas/conf
+RUN sed -i 's/\${atlas.log.dir}/\/apache-atlas\/logs/g' atlas-log4j.xml \
+    && sed -i 's/\${atlas.log.file}/application.log/g' atlas-log4j.xml
 
-RUN cd /opt/apache-atlas-${VERSION} \
-    && ./bin/atlas_start.py & \
-    touch /opt/apache-atlas-${VERSION}/logs/application.log \
-    && tail -f /opt/apache-atlas-${VERSION}/logs/application.log | sed '/AtlasAuthenticationFilter.init(filterConfig=null)/ q' \
+WORKDIR /apache-atlas/bin
+RUN ./atlas_start.py -setup || true
+RUN ./atlas_start.py & \
+    touch /apache-atlas/logs/application.log \
+    && tail -f /apache-atlas/logs/application.log | sed '/Defaulting to local host name/ q' \
     && sleep 10 \
-    && /opt/apache-atlas-${VERSION}/bin/atlas_stop.py
+    && ./atlas_stop.py \
+    && truncate -s0 /apache-atlas/logs/application.log
+
+ENTRYPOINT ["/bin/bash", "-c", "/apache-atlas/bin/atlas_start.py; tail -fF /apache-atlas/logs/application.log"]

README.md

@@ -1,32 +1,26 @@
-[![Atlas version](https://img.shields.io/badge/Atlas-2.1.0-brightgreen.svg)](https://github.com/sburn/docker-apache-atlas)
+[![Atlas version](https://img.shields.io/badge/Atlas-2.2.0-brightgreen.svg)](https://github.com/sburn/docker-apache-atlas)
 [![License: Apache 2.0](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0.html)
 [![Docker Pulls](https://img.shields.io/docker/pulls/sburn/apache-atlas.svg)](https://hub.docker.com/repository/docker/sburn/apache-atlas)
 
 Apache Atlas Docker image
 =======================================
 
-This `Apache Atlas` is built from the 2.1.0-release source tarball and patched to be run in a Docker container.
+This `Apache Atlas` is built from the 2.2.0-release source tarball and patched to be run in a Docker container.
 
 Atlas is built with `embedded HBase + Solr` and it is pre-initialized, so you can use it right after image download without additional steps.
 
 If you want to use external Atlas backends, set them up according to [the documentation](https://atlas.apache.org/#/Configuration).
 
 Basic usage
 -----------
-1. Pull the latest release image:
 
-```bash
-docker pull sburn/apache-atlas
-```
-
-2. Start Apache Atlas in a container exposing Web-UI port 21000:
+1. Start Apache Atlas in a container exposing Web-UI port 21000:
 
 ```bash
 docker run -d \
     -p 21000:21000 \
     --name atlas \
-    sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    sburn/apache-atlas
 ```
 
 Please, take into account that the first startup of Atlas may take up to few mins depending on host machine performance before web-interface become available at `http://localhost:21000/`
@@ -39,7 +33,7 @@ Usage options
 Gracefully stop Atlas:
 
 ```bash
-docker exec -ti atlas /opt/apache-atlas-2.1.0/bin/atlas_stop.py
+docker exec -ti atlas /apache-atlas/bin/atlas_stop.py
 ```
 
 Check Atlas startup script output:
@@ -48,16 +42,16 @@ Check Atlas startup script output:
 docker logs atlas
 ```
 
-Check interactively Atlas application.log (useful at the first run and for debugging during workload):
+Check Atlas application.log (useful at the first run and for debugging during workload):
 
 ```bash
-docker exec -ti atlas tail -f /opt/apache-atlas-2.1.0/logs/application.log
+docker exec -ti atlas tail -f /apache-atlas/logs/application.log
 ```
 
 Run the example (this will add sample types and instances along with traits):
 
 ```bash
-docker exec -ti atlas /opt/apache-atlas-2.1.0/bin/quick_start.py
+docker exec -ti atlas /apache-atlas/bin/quick_start.py
 ```
 
 Start Atlas overriding settings by environment variables 
@@ -74,39 +68,37 @@ docker run --detach \
     -XX:+PrintHeapAtGC -XX:+PrintGCTimeStamps" \
     -p 21000:21000 \
     --name atlas \
-    sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    sburn/apache-atlas
 ```
 
-Start Atlas exposing logs directory on the host to view them directly:
+Explore logs: start Atlas exposing logs directory on the host
 
 ```bash
 docker run --detach \
-    -v ${PWD}/atlas-logs:/opt/apache-atlas-2.1.0/logs \
+    -v ${PWD}/atlas-logs:/apache-atlas/logs \
     -p 21000:21000 \
     --name atlas \
-    sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    sburn/apache-atlas
 ```
 
-Start Atlas exposing conf directory on the host to place and edit configuration files directly:
+Custom configuration: start Atlas exposing conf directory on the host
 
 ```bash
 docker run --detach \
-    -v ${PWD}/pre-conf:/opt/apache-atlas-2.1.0/conf \
+    -v ${PWD}/pre-conf:/apache-atlas/conf \
     -p 21000:21000 \
     --name atlas \
-    sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    sburn/apache-atlas
 ```
-Start Atlas with data directory mounted on the host to provide its persistency:
+
+Data parsistency: start Atlas with data directory mounted on the host
+
 ```bash
 docker run --detach \
-    -v ${PWD}/data:/opt/apache-atlas-2.1.0/data \
+    -v ${PWD}/data:/apache-atlas/data \
     -p 21000:21000 \
     --name atlas \
-    sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    sburn/apache-atlas
 ```
 
 Tinkerpop Gremlin support
@@ -118,15 +110,15 @@ Image contains build-in extras for those who want to play with Janusgraph, and A
 
 2. Install `gremlin-server` and `gremlin-console` into the container by running included automation script:
 ```bash
-docker exec -ti atlas /opt/gremlin/install-gremlin.sh
+docker exec -ti atlas /gremlin/install-gremlin.sh
 ```
 3. Start `gremlin-server` in the same container:
 ```bash
-docker exec -d atlas /opt/gremlin/start-gremlin-server.sh
+docker exec -d atlas /gremlin/start-gremlin-server.sh
 ```
 4. Finally, run `gremlin-console` interactively:
 ```bash
-docker exec -ti atlas /opt/gremlin/run-gremlin-console.sh
+docker exec -ti atlas /gremlin/run-gremlin-console.sh
 ```
 Gremlin-console usage example:
 ```bash
@@ -161,6 +153,7 @@ The following environment variables are available for configuration:
 | ATLAS_PID_DIR | <none> | Where pid files are stored. Defatult is logs directory under the base install location
 | ATLAS_EXPANDED_WEBAPP_DIR | <none> | Where do you want to expand the war file. By Default it is in /server/webapp dir under the base install dir.
 
+For additional infomation about configurable options check official Apache Atlas documentation.
 
 Bug Tracker
 -----------

atlas_config.py.patch

@@ -33,7 +33,7 @@
 +	    break
 +
 +        if not os.path.exists(pid_file):
-+            sys.stdout.write('\nApache Atlas startup failed!\nCheck logs: /opt/apache-atlas-2.1.0/logs/application.log')
++            sys.stdout.write('\nApache Atlas startup failed!\nCheck logs: /apache-atlas/logs/application.log')
 +            sys.stdout.flush()
 +	    exit()
 +	    break

atlas_start.py.patch

@@ -1,41 +1,32 @@
---- atlas_start.py.orig	2019-05-03 08:22:00.000000000 +0300
-+++ atlas_start.py	2020-01-16 01:37:16.147611498 +0300
-@@ -18,6 +18,9 @@
- import os
- import sys
- import traceback
-+import os.path
-+import time
-+from time import sleep
-
- import atlas_config as mc
-
-@@ -114,6 +117,9 @@
-         mc.configure_hbase(atlas_home)
+--- atlas_start.py.orig 2022-12-14 14:49:45.000000000 +0000
++++ atlas_start.py  2022-12-15 15:37:31.143089911 +0000
+@@ -117,6 +117,9 @@
          mc.run_hbase_action(mc.hbaseBinDir(atlas_home), "start", hbase_conf_dir, logdir)
-         print "hbase started."
+
+         print("Local HBase started!")
 +        if is_setup:
 +            print ("Sleeping 60s due too setup (init run)...")
 +            sleep(60)
 
      #solr setup
      if mc.is_solr_local(confdir):
-@@ -128,6 +134,9 @@
+@@ -135,6 +138,9 @@
+         mc.run_solr(mc.solrBinDir(atlas_home), "start", mc.get_solr_zk_url(confdir), mc.solrPort(), logdir, True, mc.solrHomeDir(atlas_home))
 
-         mc.run_solr(mc.solrBinDir(atlas_home), "start", mc.get_solr_zk_url(confdir), mc.solrPort(), logdir)
-         print "solr started."
+         print("Local Solr started!")
 +        if is_setup:
 +            print ("Sleeping 60s due too setup (init run)...")
 +            sleep(60)
 
-         print "setting up solr collections..."
-         mc.create_solr_collection(mc.solrBinDir(atlas_home), mc.solrConfDir(atlas_home), "vertex_index", logdir)
-@@ -145,8 +154,27 @@
+         print("\nCreating Solr collections for Atlas using config: " + mc.solrConfDir(atlas_home))
+
+@@ -155,8 +161,22 @@
          web_app_path = mc.convertCygwinPath(web_app_path)
      if not is_setup:
          start_atlas_server(atlas_classpath, atlas_pid_file, jvm_logdir, jvm_opts_list, web_app_path)
 -        mc.wait_for_startup(confdir, 300)
--        print "Apache Atlas Server started!!!\n"
+-        print("Apache Atlas Server started!!!\n")
++
 +        mc.wait_for_startup(confdir, 600)
 +        print ("Apache Atlas Server process started!\n")
 +
@@ -48,14 +39,8 @@
 +        except:
 +            pid = None
 +        if not pid:
-+            sys.stderr.write("No PID file found! Server is not running?\nCheck logs: /opt/apache-atlas-2.1.0/logs/application.log\n\n")
++            sys.stderr.write("No PID file found! Server is not running?\nCheck logs: /apache-atlas/logs/application.log\n\n")
 +            return
-+
-+
-+        while os.path.exists(atlas_pid_file):
-+            time.sleep(1)
-+
-+        print ("Apache Atlas stopped!\n")
 +
      else:
          process = mc.java("org.apache.atlas.web.setup.AtlasSetup", [], atlas_classpath, jvm_opts_list, jvm_logdir)

conf/hbase/hbase-site.xml.template

@@ -41,4 +41,8 @@
     <name>hbase.regionserver.port</name>
     <value>61520</value>
   </property>
+  <property>
+    <name>hbase.unsafe.stream.capability.enforce</name>
+    <value>false</value>
+  </property>
 </configuration>

pom.xml.patch

@@ -0,0 +1,14 @@
+--- pom.xml.orig     2022-12-14 10:46:31.615039877 +0000
++++ pom.xml    2022-12-14 10:33:21.019600529 +0000
+@@ -834,6 +834,11 @@
+             <name>Typesafe Repository</name>
+             <url>http://repo.typesafe.com/typesafe/releases/</url>
+         </repository>
++        <repository>
++            <id>maven-restlet</id>
++            <name>Public online Restlet repository</name>
++            <url>https://maven.restlet.talend.com</url>
++        </repository>
+     </repositories>
+
+     <dependencyManagement>

start.sh

@@ -4,4 +4,4 @@ docker run --detach \
     -p 21000:21000 \
     --name atlas \
     sburn/apache-atlas \
-    /opt/apache-atlas-2.1.0/bin/atlas_start.py
+    /apache-atlas/bin/atlas_start.py

stop.sh

@@ -1,3 +1,3 @@
 #!/bin/sh
 
-docker exec -ti atlas /opt/apache-atlas-2.1.0/bin/atlas_stop.py
+docker exec -ti atlas /apache-atlas/bin/atlas_stop.py