From 37ce4e2a398bb0bd83eedb0e4b961d7463de8569 Mon Sep 17 00:00:00 2001
From: nruest <ruestn@gmail.com>
Date: Fri, 17 Jan 2020 10:07:32 -0500
Subject: [PATCH] Fix for #19.

- Adds work around for au shaded tika issue
- Update Spark to 2.4.4
- Update to aut-0.18.1
- README updates
- See also: https://github.com/archivesunleashed/aut/issues/407
- See also: https://github.com/archivesunleashed/aut/releases/tag/aut-0.18.1
---
 Dockerfile | 11 +++++++++--
 README.md  | 14 ++++++--------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index b1084c8..7d71d8b 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -8,7 +8,7 @@ LABEL website="https://archivesunleashed.org/"
 
 ## Build variables
 #########################
-ARG SPARK_VERSION=2.4.3
+ARG SPARK_VERSION=2.4.4
 
 # Git and Wget
 RUN apk add --update \
@@ -18,6 +18,13 @@ RUN apk add --update \
 # Sample resources
 RUN git clone https://github.com/archivesunleashed/aut-resources.git /aut-resources
 
+# Build aut (workaround for https://github.com/archivesunleashed/docker-aut/issues/19)
+
+RUN git clone https://github.com/archivesunleashed/aut.git /aut \
+    && cd /aut \
+    && git checkout 59b60621500246f48051466005d6a5dc59f74369 \
+    && mvn clean install
+
 # Spark shell
 RUN mkdir /spark \
     && cd /tmp \
@@ -25,4 +32,4 @@ RUN mkdir /spark \
     && tar -xf "/tmp/spark-$SPARK_VERSION-bin-hadoop2.7.tgz" -C /spark --strip-components=1 \
     && rm "/tmp/spark-$SPARK_VERSION-bin-hadoop2.7.tgz"
 
-CMD /spark/bin/spark-shell --packages "io.archivesunleashed:aut:0.18.0"
+CMD /spark/bin/spark-shell --packages "io.archivesunleashed:aut:0.18.1"
diff --git a/README.md b/README.md
index 5ce96e4..2b5874e 100644
--- a/README.md
+++ b/README.md
@@ -38,27 +38,25 @@ If you want to mount your own data:
 You can add any Spark flags to the build if you need too.
 
 ```
-$ docker run --rm -it archivesunleashed/docker-aut:0.18.0 /spark/bin/spark-shell --packages "io.archivesunleashed:aut:0.18.0" --conf spark.network.timeout=100000000 --conf spark.executor.heartbeatInterval=6000s
+$ docker run --rm -it archivesunleashed/docker-aut:0.18.0 /spark/bin/spark-shell --packages "io.archivesunleashed:aut:0.18.1" --conf spark.network.timeout=100000000 --conf spark.executor.heartbeatInterval=6000s
 ```
 
 Once the build finishes, you should see:
 
 ```bash
 $ docker run --rm -it aut
+
+Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
 Setting default log level to "WARN".
 To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
-2017-12-08 00:28:03,803 [main] WARN  NativeCodeLoader - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
-2017-12-08 00:28:10,965 [main] WARN  ObjectStore - Version information not found in metastore. hive.metastore.schema.verification is not enabled so recording the schema version 1.2.0
-2017-12-08 00:28:11,130 [main] WARN  ObjectStore - Failed to get database default, returning NoSuchObjectException
-2017-12-08 00:28:12,068 [main] WARN  ObjectStore - Failed to get database global_temp, returning NoSuchObjectException
-Spark context Web UI available at http://172.17.0.2:4040
-Spark context available as 'sc' (master = local[*], app id = local-1512692884451).
+Spark context Web UI available at http://fee0a4330af9:4040
+Spark context available as 'sc' (master = local[*], app id = local-1579273425545).
 Spark session available as 'spark'.
 Welcome to
       ____              __
      / __/__  ___ _____/ /__
     _\ \/ _ \/ _ `/ __/  '_/
-   /___/ .__/\_,_/_/ /_/\_\   version 2.4.3
+   /___/ .__/\_,_/_/ /_/\_\   version 2.4.4
       /_/
          
 Using Scala version 2.11.12 (OpenJDK 64-Bit Server VM, Java 1.8.0_212)