This is an automated email from the ASF dual-hosted git repository.
madhan pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/atlas.git
The following commit(s) were added to refs/heads/master by this push:
new 80b305f ATLAS-4188: Docker setup updated to run Atlas, Solr, Kafka,
HBase, HDFS, Zookeeper in separate containers
80b305f is described below
commit 80b305f827092f5e006d556aba3e02acee052c2d
Author: Madhan Neethiraj <[email protected]>
AuthorDate: Fri Mar 5 21:09:23 2021 -0800
ATLAS-4188: Docker setup updated to run Atlas, Solr, Kafka, HBase, HDFS,
Zookeeper in separate containers
---
dev-support/atlas-docker/.dockerignore | 1 +
dev-support/atlas-docker/.env | 5 +-
dev-support/atlas-docker/Dockerfile.atlas | 14 +-
dev-support/atlas-docker/Dockerfile.atlas-base | 10 +-
dev-support/atlas-docker/Dockerfile.atlas-hadoop | 43 ++
.../{Dockerfile.atlas => Dockerfile.atlas-hbase} | 32 +-
.../{Dockerfile.atlas => Dockerfile.atlas-kafka} | 28 +-
.../{scripts/atlas.sh => Dockerfile.atlas-solr} | 33 +-
.../{scripts/atlas.sh => Dockerfile.atlas-zk} | 28 +-
dev-support/atlas-docker/README.md | 44 +-
dev-support/atlas-docker/config/solr/currency.xml | 67 +++
.../atlas-docker/config/solr/lang/stopwords_en.txt | 54 ++
dev-support/atlas-docker/config/solr/protwords.txt | 21 +
dev-support/atlas-docker/config/solr/schema.xml | 534 +++++++++++++++++
.../atlas-docker/config/solr/solrconfig.xml | 630 +++++++++++++++++++++
dev-support/atlas-docker/config/solr/stopwords.txt | 14 +
dev-support/atlas-docker/config/solr/synonyms.txt | 29 +
.../atlas-docker/docker-compose.atlas-hadoop.yml | 31 +
.../atlas-docker/docker-compose.atlas-hbase.yml | 30 +
.../atlas-docker/docker-compose.atlas-kafka.yml | 27 +
dev-support/atlas-docker/docker-compose.atlas.yml | 33 +-
dev-support/atlas-docker/download-archives.sh | 49 ++
dev-support/atlas-docker/downloads/.gitignore | 1 +
.../scripts/{atlas.sh => atlas-hadoop-mkdir.sh} | 34 +-
.../atlas-docker/scripts/atlas-hadoop-setup.sh | 60 ++
dev-support/atlas-docker/scripts/atlas-hadoop.sh | 54 ++
.../scripts/{atlas.sh => atlas-hbase-setup.sh} | 31 +-
.../scripts/{atlas.sh => atlas-hbase.sh} | 28 +-
.../scripts/{atlas.sh => atlas-kafka-setup.sh} | 30 +-
.../scripts/{atlas.sh => atlas-kafka.sh} | 27 +-
.../atlas-docker/scripts/atlas-solr-create.sh | 6 +
dev-support/atlas-docker/scripts/atlas.sh | 11 +
dev-support/atlas-docker/scripts/hbase-site.xml | 52 ++
distro/pom.xml | 2 -
pom.xml | 2 +-
webapp/pom.xml | 18 +-
36 files changed, 1877 insertions(+), 236 deletions(-)
diff --git a/dev-support/atlas-docker/.dockerignore
b/dev-support/atlas-docker/.dockerignore
index d6a8480..fa4ce32 100644
--- a/dev-support/atlas-docker/.dockerignore
+++ b/dev-support/atlas-docker/.dockerignore
@@ -1,4 +1,5 @@
*
!config
!dist/apache-atlas-*-bin.tar.gz
+!downloads/*
!scripts/*
diff --git a/dev-support/atlas-docker/.env b/dev-support/atlas-docker/.env
index 19443ad..79d2b97 100644
--- a/dev-support/atlas-docker/.env
+++ b/dev-support/atlas-docker/.env
@@ -2,6 +2,9 @@ BUILD_HOST_SRC=true
SKIPTESTS=true
GIT_URL=https://github.com/apache/atlas.git
BRANCH=master
-PROFILE=dist,berkeley-solr
+PROFILE=dist,external-hbase-solr
ATLAS_VERSION=3.0.0-SNAPSHOT
+HADOOP_VERSION=3.3.0
+HBASE_VERSION=2.3.3
+KAFKA_VERSION=2.5.0
diff --git a/dev-support/atlas-docker/Dockerfile.atlas
b/dev-support/atlas-docker/Dockerfile.atlas
index 76e5c59..4bafe80 100644
--- a/dev-support/atlas-docker/Dockerfile.atlas
+++ b/dev-support/atlas-docker/Dockerfile.atlas
@@ -19,19 +19,21 @@ FROM atlas-base:latest
ARG ATLAS_VERSION
COPY ./scripts/atlas.sh ${ATLAS_SCRIPTS}/
-COPY ./dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz /tmp/
+COPY ./dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz /home/atlas/dist/
-RUN tar xfz /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz --directory=/opt/ &&
\
+RUN tar xfz /home/atlas/dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz
--directory=/opt/ && \
ln -s /opt/apache-atlas-${ATLAS_VERSION} ${ATLAS_HOME} && \
- rm -f /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz && \
- mkdir -p /var/run/atlas && \
- mkdir -p /var/log/atlas && \
- mkdir -p /home/atlas/data && \
+ rm -f /home/atlas/dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz && \
+ mkdir -p /var/run/atlas /var/log/atlas /home/atlas/data
${ATLAS_HOME}/hbase/conf && \
rm -rf ${ATLAS_HOME}/logs && \
ln -s /var/log/atlas ${ATLAS_HOME}/logs && \
ln -s /home/atlas/data ${ATLAS_HOME}/data && \
chown -R atlas:atlas ${ATLAS_HOME}/ /var/run/atlas/ /var/log/atlas/
+COPY ./scripts/hbase-site.xml ${ATLAS_HOME}/hbase/conf/
+
VOLUME /home/atlas/data
+EXPOSE 21000
+
ENTRYPOINT [ "/home/atlas/scripts/atlas.sh" ]
diff --git a/dev-support/atlas-docker/Dockerfile.atlas-base
b/dev-support/atlas-docker/Dockerfile.atlas-base
index 36e8f0f..e68daa6 100644
--- a/dev-support/atlas-docker/Dockerfile.atlas-base
+++ b/dev-support/atlas-docker/Dockerfile.atlas-base
@@ -17,9 +17,9 @@
FROM ubuntu:20.04
-# Install curl, wget, tzdata, Python, Java
+# Install tzdata, Python, Java
RUN apt-get update && \
- DEBIAN_FRONTEND="noninteractive" apt-get -y install curl wget tzdata \
+ DEBIAN_FRONTEND="noninteractive" apt-get -y install tzdata \
python python3 python3-pip openjdk-8-jdk bc iputils-ping ssh pdsh
# Set environment variables
@@ -33,6 +33,12 @@ ENV PATH
/usr/java/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bi
# setup groups, users, directories
RUN groupadd atlas && \
useradd -g atlas -ms /bin/bash atlas && \
+ groupadd hadoop && \
+ useradd -g hadoop -ms /bin/bash hdfs && \
+ useradd -g hadoop -ms /bin/bash yarn && \
+ useradd -g hadoop -ms /bin/bash hive && \
+ useradd -g hadoop -ms /bin/bash hbase && \
+ useradd -g hadoop -ms /bin/bash kafka && \
mkdir -p /home/atlas/dist && \
mkdir -p /home/atlas/scripts && \
chown -R atlas:atlas /home/atlas
diff --git a/dev-support/atlas-docker/Dockerfile.atlas-hadoop
b/dev-support/atlas-docker/Dockerfile.atlas-hadoop
new file mode 100644
index 0000000..26e766e
--- /dev/null
+++ b/dev-support/atlas-docker/Dockerfile.atlas-hadoop
@@ -0,0 +1,43 @@
+# 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.
+
+FROM atlas-base:latest
+
+ARG HADOOP_VERSION
+
+
+COPY ./downloads/hadoop-${HADOOP_VERSION}.tar.gz /home/atlas/dist/
+
+COPY ./scripts/atlas-hadoop-setup.sh /home/atlas/scripts/
+COPY ./scripts/atlas-hadoop.sh /home/atlas/scripts/
+COPY ./scripts/atlas-hadoop-mkdir.sh /home/atlas/scripts/
+
+RUN tar xvfz /home/atlas/dist/hadoop-${HADOOP_VERSION}.tar.gz
--directory=/opt/ && \
+ ln -s /opt/hadoop-${HADOOP_VERSION} /opt/hadoop && \
+ rm -f /home/atlas/dist/hadoop-${HADOOP_VERSION}.tar.gz
+
+ENV HADOOP_HOME /opt/hadoop
+ENV HADOOP_CONF_DIR /opt/hadoop/etc/hadoop
+ENV HADOOP_HDFS_HOME /opt/hadoop
+ENV HADOOP_MAPRED_HOME /opt/hadoop
+ENV HADOOP_COMMON_HOME /opt/hadoop
+ENV YARN_HOME /opt/hadoop
+ENV PATH
/usr/java/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/hadoop/bin
+
+EXPOSE 9000
+EXPOSE 8088
+
+ENTRYPOINT [ "/home/atlas/scripts/atlas-hadoop.sh" ]
diff --git a/dev-support/atlas-docker/Dockerfile.atlas
b/dev-support/atlas-docker/Dockerfile.atlas-hbase
similarity index 52%
copy from dev-support/atlas-docker/Dockerfile.atlas
copy to dev-support/atlas-docker/Dockerfile.atlas-hbase
index 76e5c59..1c5fa28 100644
--- a/dev-support/atlas-docker/Dockerfile.atlas
+++ b/dev-support/atlas-docker/Dockerfile.atlas-hbase
@@ -17,21 +17,25 @@
FROM atlas-base:latest
ARG ATLAS_VERSION
+ARG HBASE_VERSION
-COPY ./scripts/atlas.sh ${ATLAS_SCRIPTS}/
-COPY ./dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz /tmp/
-RUN tar xfz /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz --directory=/opt/ &&
\
- ln -s /opt/apache-atlas-${ATLAS_VERSION} ${ATLAS_HOME} && \
- rm -f /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz && \
- mkdir -p /var/run/atlas && \
- mkdir -p /var/log/atlas && \
- mkdir -p /home/atlas/data && \
- rm -rf ${ATLAS_HOME}/logs && \
- ln -s /var/log/atlas ${ATLAS_HOME}/logs && \
- ln -s /home/atlas/data ${ATLAS_HOME}/data && \
- chown -R atlas:atlas ${ATLAS_HOME}/ /var/run/atlas/ /var/log/atlas/
+COPY ./downloads/hbase-${HBASE_VERSION}-bin.tar.gz /home/atlas/dist/
-VOLUME /home/atlas/data
+COPY ./scripts/atlas-hbase-setup.sh /home/atlas/scripts/
+COPY ./scripts/atlas-hbase.sh /home/atlas/scripts/
+COPY ./scripts/hbase-site.xml /home/atlas/scripts/
-ENTRYPOINT [ "/home/atlas/scripts/atlas.sh" ]
+RUN tar xvfz /home/atlas/dist/hbase-${HBASE_VERSION}-bin.tar.gz
--directory=/opt/ && \
+ ln -s /opt/hbase-${HBASE_VERSION} /opt/hbase && \
+ rm -f /home/atlas/dist/hbase-${HBASE_VERSION}-bin.tar.gz
+
+ENV HBASE_HOME /opt/hbase
+ENV PATH
/usr/java/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/hbase/bin
+
+EXPOSE 16000
+EXPOSE 16010
+EXPOSE 16020
+EXPOSE 16030
+
+ENTRYPOINT [ "/home/atlas/scripts/atlas-hbase.sh" ]
diff --git a/dev-support/atlas-docker/Dockerfile.atlas
b/dev-support/atlas-docker/Dockerfile.atlas-kafka
similarity index 53%
copy from dev-support/atlas-docker/Dockerfile.atlas
copy to dev-support/atlas-docker/Dockerfile.atlas-kafka
index 76e5c59..e06d628 100644
--- a/dev-support/atlas-docker/Dockerfile.atlas
+++ b/dev-support/atlas-docker/Dockerfile.atlas-kafka
@@ -17,21 +17,21 @@
FROM atlas-base:latest
ARG ATLAS_VERSION
+ARG KAFKA_VERSION
-COPY ./scripts/atlas.sh ${ATLAS_SCRIPTS}/
-COPY ./dist/apache-atlas-${ATLAS_VERSION}-bin.tar.gz /tmp/
-RUN tar xfz /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz --directory=/opt/ &&
\
- ln -s /opt/apache-atlas-${ATLAS_VERSION} ${ATLAS_HOME} && \
- rm -f /tmp/apache-atlas-${ATLAS_VERSION}-bin.tar.gz && \
- mkdir -p /var/run/atlas && \
- mkdir -p /var/log/atlas && \
- mkdir -p /home/atlas/data && \
- rm -rf ${ATLAS_HOME}/logs && \
- ln -s /var/log/atlas ${ATLAS_HOME}/logs && \
- ln -s /home/atlas/data ${ATLAS_HOME}/data && \
- chown -R atlas:atlas ${ATLAS_HOME}/ /var/run/atlas/ /var/log/atlas/
+COPY ./downloads/kafka_2.12-${KAFKA_VERSION}.tgz /home/atlas/dist/
-VOLUME /home/atlas/data
+COPY ./scripts/atlas-kafka-setup.sh /home/atlas/scripts/
+COPY ./scripts/atlas-kafka.sh /home/atlas/scripts/
-ENTRYPOINT [ "/home/atlas/scripts/atlas.sh" ]
+RUN tar xvfz /home/atlas/dist/kafka_2.12-${KAFKA_VERSION}.tgz
--directory=/opt/ && \
+ ln -s /opt/kafka_2.12-${KAFKA_VERSION} /opt/kafka && \
+ rm -f /home/atlas/dist/kafka_2.12-${KAFKA_VERSION}.tgz
+
+ENV KAFKA_HOME /opt/kafka
+ENV PATH
/usr/java/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/opt/kafka/bin
+
+EXPOSE 9092
+
+ENTRYPOINT [ "/home/atlas/scripts/atlas-kafka.sh" ]
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/Dockerfile.atlas-solr
old mode 100755
new mode 100644
similarity index 56%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/Dockerfile.atlas-solr
index 7abb6f7..17c14bb
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/Dockerfile.atlas-solr
@@ -1,5 +1,3 @@
-#!/bin/bash
-
# 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
@@ -16,28 +14,19 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
-
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
-then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
-
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
+FROM solr:8
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
+USER 0
- chown -R atlas:atlas ${ATLAS_HOME}/
+# Copy Atlas collections config set
+RUN mkdir -p /opt/solr/server/solr/configsets/atlas/conf/lang
+COPY ./config/solr/*.* /opt/solr/server/solr/configsets/atlas/conf/
+COPY ./config/solr/lang/*.* /opt/solr/server/solr/configsets/atlas/conf/lang/
+RUN chown -R solr:solr /opt/solr/server/solr/configsets/atlas/
- touch ${ATLAS_HOME}/.setupDone
-fi
+# Copy script that creates Atlas collections
+COPY ./scripts/atlas-solr-create.sh /docker-entrypoint-initdb.d/
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
+EXPOSE 8983
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+USER solr
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/Dockerfile.atlas-zk
old mode 100755
new mode 100644
similarity index 56%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/Dockerfile.atlas-zk
index 7abb6f7..2855b50
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/Dockerfile.atlas-zk
@@ -1,5 +1,3 @@
-#!/bin/bash
-
# 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
@@ -16,28 +14,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
-
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
-then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
-
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
-
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
-
- chown -R atlas:atlas ${ATLAS_HOME}/
-
- touch ${ATLAS_HOME}/.setupDone
-fi
-
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
-
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+FROM zookeeper:3.5.9
diff --git a/dev-support/atlas-docker/README.md
b/dev-support/atlas-docker/README.md
index 37caa3a..6ba4058 100644
--- a/dev-support/atlas-docker/README.md
+++ b/dev-support/atlas-docker/README.md
@@ -23,54 +23,28 @@ Docker files in this folder create docker images and run
them to build Apache At
## Usage
-1. Ensure that you have recent version of Docker installed from
[docker.io](http://www.docker.io) (as of this writing: Engine 19.03, Compose
1.26.2).
+1. Ensure that you have recent version of Docker installed from
[docker.io](http://www.docker.io) (as of this writing: Engine 20.10.5, Compose
1.28.5).
+ Make sure to configure docker with at least 6gb of memory.
2. Set this folder as your working directory.
3. Update environment variables in .env file, if necessary
-4. Using docker-compose is the simpler way to build and deploy Apache Atlas in
containers.
+4. Execute following command to download necessary archives to setup
Atlas/HDFS/HBase/Kafka services:
+ ./download-archives.sh
- 4.1. Execute following command to build Apache Atlas:
+5. Build and deploy Apache Atlas in containers using docker-compose
+
+ 5.1. Execute following command to build Apache Atlas:
docker-compose -f docker-compose.atlas-base.yml -f
docker-compose.atlas-build.yml up
Time taken to complete the build might vary (upto an hour), depending on
status of ${HOME}/.m2 directory cache.
- 4.2. Execute following command to install and start Atlas in a container:
+ 5.2. Execute following command to install and start Atlas and dependent
services (Solr, HBase, Kafka) in containers:
- docker-compose -f docker-compose.atlas-base.yml -f
docker-compose.atlas.yml up -d
+ docker-compose -f docker-compose.atlas-base.yml -f
docker-compose.atlas.yml -f docker-compose.atlas-hadoop.yml -f
docker-compose.atlas-hbase.yml -f docker-compose.atlas-kafka.yml up -d
Apache Atlas will be installed at /opt/atlas/, and logs are at
/var/logs/atlas directory.
-5. Alternatively docker command can be used to build and deploy Apache Atlas.
-
- 5.1. Execute following command to build Docker image **atlas-base**:
-
- docker build -f Dockerfile.atlas-base -t atlas-base .
-
- This might take about 10 minutes to complete.
-
- 5.2. Execute following command to build Docker image **atlas-build**:
-
- docker build -f Dockerfile.atlas-build -t atlas-build .
-
- 5.3. Build Apache Atlas in a container with one of the following commands:
-
- docker run -it --rm -v ${HOME}/.m2:/home/atlas/.m2:delegated -v
$(pwd)/scripts:/home/atlas/scripts -v $(pwd)/../..:/home/atlas/src:delegated -v
$(pwd)/patches:/home/atlas/patches -v $(pwd)/dist:/home/atlas/dist --env-file
./.env atlas-build
-
- Time taken to complete the build might vary (upto an hour), depending on
status of ${HOME}/.m2 directory cache.
-
- 5.4. Execute following command to build Docker image **atlas**:
-
- docker build -f Dockerfile.atlas --build-arg
ATLAS_VERSION=3.0.0-SNAPSHOT -t atlas .
-
- This might take about 10 minutes to complete.
-
- 5.5. Execute following command to install and run Atlas services in a
container:
-
- docker run -it -d --name atlas --hostname atlas.example.com -p
21000:21000 -v $(pwd)/data:/home/atlas/data atlas
-
- This might take few minutes to complete.
-
6. Atlas Admin can be accessed at http://localhost:21000 (admin/atlasR0cks!)
diff --git a/dev-support/atlas-docker/config/solr/currency.xml
b/dev-support/atlas-docker/config/solr/currency.xml
new file mode 100644
index 0000000..3a9c58a
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/currency.xml
@@ -0,0 +1,67 @@
+<?xml version="1.0" ?>
+<!--
+ 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.
+-->
+
+<!-- Example exchange rates file for CurrencyField type named "currency" in
example schema -->
+
+<currencyConfig version="1.0">
+ <rates>
+ <!-- Updated from http://www.exchangerate.com/ at 2011-09-27 -->
+ <rate from="USD" to="ARS" rate="4.333871" comment="ARGENTINA Peso" />
+ <rate from="USD" to="AUD" rate="1.025768" comment="AUSTRALIA Dollar" />
+ <rate from="USD" to="EUR" rate="0.743676" comment="European Euro" />
+ <rate from="USD" to="BRL" rate="1.881093" comment="BRAZIL Real" />
+ <rate from="USD" to="CAD" rate="1.030815" comment="CANADA Dollar" />
+ <rate from="USD" to="CLP" rate="519.0996" comment="CHILE Peso" />
+ <rate from="USD" to="CNY" rate="6.387310" comment="CHINA Yuan" />
+ <rate from="USD" to="CZK" rate="18.47134" comment="CZECH REP. Koruna" />
+ <rate from="USD" to="DKK" rate="5.515436" comment="DENMARK Krone" />
+ <rate from="USD" to="HKD" rate="7.801922" comment="HONG KONG Dollar" />
+ <rate from="USD" to="HUF" rate="215.6169" comment="HUNGARY Forint" />
+ <rate from="USD" to="ISK" rate="118.1280" comment="ICELAND Krona" />
+ <rate from="USD" to="INR" rate="49.49088" comment="INDIA Rupee" />
+ <rate from="USD" to="XDR" rate="0.641358" comment="INTNL MON. FUND SDR" />
+ <rate from="USD" to="ILS" rate="3.709739" comment="ISRAEL Sheqel" />
+ <rate from="USD" to="JPY" rate="76.32419" comment="JAPAN Yen" />
+ <rate from="USD" to="KRW" rate="1169.173" comment="KOREA (SOUTH) Won" />
+ <rate from="USD" to="KWD" rate="0.275142" comment="KUWAIT Dinar" />
+ <rate from="USD" to="MXN" rate="13.85895" comment="MEXICO Peso" />
+ <rate from="USD" to="NZD" rate="1.285159" comment="NEW ZEALAND Dollar" />
+ <rate from="USD" to="NOK" rate="5.859035" comment="NORWAY Krone" />
+ <rate from="USD" to="PKR" rate="87.57007" comment="PAKISTAN Rupee" />
+ <rate from="USD" to="PEN" rate="2.730683" comment="PERU Sol" />
+ <rate from="USD" to="PHP" rate="43.62039" comment="PHILIPPINES Peso" />
+ <rate from="USD" to="PLN" rate="3.310139" comment="POLAND Zloty" />
+ <rate from="USD" to="RON" rate="3.100932" comment="ROMANIA Leu" />
+ <rate from="USD" to="RUB" rate="32.14663" comment="RUSSIA Ruble" />
+ <rate from="USD" to="SAR" rate="3.750465" comment="SAUDI ARABIA Riyal" />
+ <rate from="USD" to="SGD" rate="1.299352" comment="SINGAPORE Dollar" />
+ <rate from="USD" to="ZAR" rate="8.329761" comment="SOUTH AFRICA Rand" />
+ <rate from="USD" to="SEK" rate="6.883442" comment="SWEDEN Krona" />
+ <rate from="USD" to="CHF" rate="0.906035" comment="SWITZERLAND Franc" />
+ <rate from="USD" to="TWD" rate="30.40283" comment="TAIWAN Dollar" />
+ <rate from="USD" to="THB" rate="30.89487" comment="THAILAND Baht" />
+ <rate from="USD" to="AED" rate="3.672955" comment="U.A.E. Dirham" />
+ <rate from="USD" to="UAH" rate="7.988582" comment="UKRAINE Hryvnia" />
+ <rate from="USD" to="GBP" rate="0.647910" comment="UNITED KINGDOM Pound" />
+
+ <!-- Cross-rates for some common currencies -->
+ <rate from="EUR" to="GBP" rate="0.869914" />
+ <rate from="EUR" to="NOK" rate="7.800095" />
+ <rate from="GBP" to="NOK" rate="8.966508" />
+ </rates>
+</currencyConfig>
diff --git a/dev-support/atlas-docker/config/solr/lang/stopwords_en.txt
b/dev-support/atlas-docker/config/solr/lang/stopwords_en.txt
new file mode 100644
index 0000000..2c164c0
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/lang/stopwords_en.txt
@@ -0,0 +1,54 @@
+# 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.
+
+# a couple of test stopwords to test that the words are really being
+# configured from this file:
+stopworda
+stopwordb
+
+# Standard english stop words taken from Lucene's StopAnalyzer
+a
+an
+and
+are
+as
+at
+be
+but
+by
+for
+if
+in
+into
+is
+it
+no
+not
+of
+on
+or
+such
+that
+the
+their
+then
+there
+these
+they
+this
+to
+was
+will
+with
diff --git a/dev-support/atlas-docker/config/solr/protwords.txt
b/dev-support/atlas-docker/config/solr/protwords.txt
new file mode 100644
index 0000000..1dfc0ab
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/protwords.txt
@@ -0,0 +1,21 @@
+# 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.
+
+#-----------------------------------------------------------------------
+# Use a protected word file to protect against the stemmer reducing two
+# unrelated words to the same base word.
+
+# Some non-words that normally won't be encountered,
+# just to test that they won't be stemmed.
+dontstems
+zwhacky
+
diff --git a/dev-support/atlas-docker/config/solr/schema.xml
b/dev-support/atlas-docker/config/solr/schema.xml
new file mode 100644
index 0000000..7c2ad3c
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/schema.xml
@@ -0,0 +1,534 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ 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.
+-->
+
+<!--
+ This is the Solr schema file. This file should be named "schema.xml" and
+ should be in the conf directory under the solr home
+ (i.e. ./solr/conf/schema.xml by default)
+ or located where the classloader for the Solr webapp can find it.
+
+ This example schema is the recommended starting point for users.
+ It should be kept correct and concise, usable out-of-the-box.
+
+ For more information, on how to customize this file, please see
+ http://wiki.apache.org/solr/SchemaXml
+-->
+
+<schema name="titan-schema" version="1.5">
+ <!-- attribute "name" is the name of this schema and is only used for
display purposes.
+ version="x.y" is Solr's version number for the schema syntax and
+ semantics. It should not normally be changed by applications.
+
+ 1.0: multiValued attribute did not exist, all fields are multiValued
+ by nature
+ 1.1: multiValued attribute introduced, false by default
+ 1.2: omitTermFreqAndPositions attribute introduced, true by default
+ except for text fields.
+ 1.3: removed optional field compress feature
+ 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
+ behavior when a single string produces multiple tokens. Defaults
+ to off for version >= 1.4
+ 1.5: omitNorms defaults to true for primitive field types
+ (int, float, boolean, string...)
+ -->
+
+
+ <!-- Valid attributes for fields:
+ name: mandatory - the name for the field
+ type: mandatory - the name of a field type from the
+ <types> fieldType section
+ indexed: true if this field should be indexed (searchable or sortable)
+ stored: true if this field should be retrievable
+ docValues: true if this field should have doc values. Doc values are
+ useful for faceting, grouping, sorting and function queries. Although
not
+ required, doc values will make the index faster to load, more
+ NRT-friendly and more memory-efficient. They however come with some
+ limitations: they are currently only supported by StrField, UUIDField
+ and all Trie*Fields, and depending on the field type, they might
+ require the field to be single-valued, be required or have a default
+ value (check the documentation of the field type you're interested in
+ for more information)
+ multiValued: true if this field may contain multiple values per document
+ omitNorms: (expert) set to true to omit the norms associated with
+ this field (this disables length normalization and index-time
+ boosting for the field, and saves some memory). Only full-text
+ fields or fields that need an index-time boost need norms.
+ Norms are omitted for primitive (non-analyzed) types by default.
+ termVectors: [false] set to true to store the term vector for a
+ given field.
+ When using MoreLikeThis, fields used for similarity should be
+ stored for best performance.
+ termPositions: Store position information with the term vector.
+ This will increase storage costs.
+ termOffsets: Store offset information with the term vector. This
+ will increase storage costs.
+ required: The field is required. It will throw an error if the
+ value does not exist
+ default: a value that should be used if no value is specified
+ when adding a document.
+ -->
+
+ <!-- field names should consist of alphanumeric or underscore characters
only and
+ not start with a digit. This is not currently strictly enforced,
+ but other field names will not have first class support from all
components
+ and back compatibility is not guaranteed. Names with both leading and
+ trailing underscores (e.g. _version_) are reserved.
+ -->
+
+ <!-- If you remove this field, you must _also_ disable the update log in
solrconfig.xml
+ or Solr won't start. _version_ and update log are required for SolrCloud
+ -->
+ <field name="_version_" type="long" indexed="true" stored="true"/>
+
+ <!-- points to the root document of a block of nested documents. Required
for nested
+ document support, may be removed otherwise
+ -->
+ <field name="_root_" type="string" indexed="true" stored="false"/>
+
+ <!-- Only remove the "id" field if you have a very good reason to. While
not strictly
+ required, it is highly recommended. A <uniqueKey> is present in almost
all Solr
+ installations. See the <uniqueKey> declaration below where <uniqueKey> is
set to "id".
+ -->
+ <field name="id" type="string" indexed="true" stored="true" required="true"
multiValued="false" />
+
+ <!-- Dynamic field definitions allow using convention over configuration
+ for fields via the specification of patterns to match field names.
+ EXAMPLE: name="*_i" will match any field ending in _i (like myid_i,
z_i)
+ RESTRICTION: the glob-like pattern in the name attribute must have
+ a "*" only at the start or the end. -->
+
+ <dynamicField name="*_i" type="int" indexed="true" stored="true"/>
+ <dynamicField name="*_is" type="int" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_s" type="string" indexed="true" stored="true" />
+ <dynamicField name="*_ss" type="string" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
+ <dynamicField name="*_ls" type="long" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_t" type="text_general" indexed="true"
stored="true"/>
+ <dynamicField name="*_txt" type="text_general" indexed="true"
stored="true" multiValued="true"/>
+ <dynamicField name="*_en" type="text_en" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
+ <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
+ <dynamicField name="*_fs" type="float" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
+ <dynamicField name="*_ds" type="double" indexed="true" stored="true"
multiValued="true"/>
+
+ <!-- Type used to index the lat and lon components for the "location"
FieldType -->
+ <dynamicField name="*_coordinate" type="tdouble" indexed="true"
stored="false" />
+
+ <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
+ <dynamicField name="*_dts" type="date" indexed="true" stored="true"
multiValued="true"/>
+ <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
+
+ <!-- some trie-coded dynamic fields for faster range queries -->
+ <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
+ <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
+ <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
+ <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
+ <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
+
+ <dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
+
+ <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+ <dynamicField name="attr_*" type="text_general" indexed="true"
stored="true" multiValued="true"/>
+
+ <dynamicField name="random_*" type="random" />
+
+ <!-- uncomment the following to ignore any fields that don't already match
an existing
+ field name or dynamic field, rather than reporting them as an error.
+ alternately, change the type="ignored" to some other type e.g. "text"
if you want
+ unknown fields indexed and/or stored by default -->
+ <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+
+ <!-- Field to use to determine and enforce document uniqueness.
+ Unless this field is marked with required="false", it will be a required
field
+ -->
+ <uniqueKey>id</uniqueKey>
+
+ <!-- copyField commands copy one field to another at the time a document
+ is added to the index. It's used either to index the same field
differently,
+ or to add multiple fields to the same field for easier/faster
searching. -->
+
+ <!--
+ <copyField source="title" dest="text"/>
+ <copyField source="body" dest="text"/>
+ -->
+
+ <!-- field type definitions. The "name" attribute is
+ just a label to be used by field definitions. The "class"
+ attribute and any other attributes determine the real
+ behavior of the fieldType.
+ Class names starting with "solr" refer to java classes in a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim.
+ It supports doc values but in that case the field needs to be
+ single-valued and either required or have a default value.
+ -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+
+ <!-- sortMissingLast and sortMissingFirst attributes are optional
attributes are
+ currently supported on types that are sorted internally as strings
+ and on numeric types.
+ This includes "string","boolean", and, as of 3.5 (and 4.x),
+ int, float, long, date, double, including the "Trie" variants.
+ - If sortMissingLast="true", then a sort on this field will cause
documents
+ without the field to come after documents with the field,
+ regardless of the requested sort order (asc or desc).
+ - If sortMissingFirst="true", then a sort on this field will cause
documents
+ without the field to come before documents with the field,
+ regardless of the requested sort order.
+ - If sortMissingLast="false" and sortMissingFirst="false" (the default),
+ then default lucene sorting will be used which places docs without the
+ field first in an ascending sort and last in a descending sort.
+ -->
+
+ <!--
+ Default numeric field types. For faster range queries, consider the
tint/tfloat/tlong/tdouble types.
+
+ These fields support doc values, but they require the field to be
+ single-valued and either be required or have a default value.
+ -->
+ <fieldType name="int" class="solr.TrieIntField" precisionStep="0"
positionIncrementGap="0"/>
+ <fieldType name="float" class="solr.TrieFloatField" precisionStep="0"
positionIncrementGap="0"/>
+ <fieldType name="long" class="solr.TrieLongField" precisionStep="0"
positionIncrementGap="0"/>
+ <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0"
positionIncrementGap="0"/>
+
+ <!--
+ Numeric field types that index each value at various levels of precision
+ to accelerate range queries when the number of values between the range
+ endpoints is large. See the javadoc for NumericRangeQuery for internal
+ implementation details.
+
+ Smaller precisionStep values (specified in bits) will lead to more tokens
+ indexed per value, slightly larger index size, and faster range queries.
+ A precisionStep of 0 disables indexing at different precision levels.
+ -->
+ <fieldType name="tint" class="solr.TrieIntField" precisionStep="8"
positionIncrementGap="0"/>
+ <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8"
positionIncrementGap="0"/>
+ <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8"
positionIncrementGap="0"/>
+ <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8"
positionIncrementGap="0"/>
+
+ <!-- The format for this date field is of the form 1995-12-31T23:59:59Z,
and
+ is a more restricted form of the canonical representation of dateTime
+ http://www.w3.org/TR/xmlschema-2/#dateTime
+ The trailing "Z" designates UTC time and is mandatory.
+ Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+ All other components are mandatory.
+
+ Expressions can also be used to denote calculations that should be
+ performed relative to "NOW" to determine the value, ie...
+
+ NOW/HOUR
+ ... Round to the start of the current hour
+ NOW-1DAY
+ ... Exactly 1 day prior to now
+ NOW/DAY+6MONTHS+3DAYS
+ ... 6 months and 3 days in the future from the start of
+ the current day
+
+ Consult the TrieDateField javadocs for more information.
+
+ Note: For faster range queries, consider the tdate type
+ -->
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0"
positionIncrementGap="0"/>
+
+ <!-- A Trie based date field for faster date range queries and date
faceting. -->
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6"
positionIncrementGap="0"/>
+
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64
encoded Strings -->
+ <fieldType name="binary" class="solr.BinaryField"/>
+
+ <!-- The "RandomSortField" is not used to store or search any
+ data. You can declare fields of this type it in your schema
+ to generate pseudo-random orderings of your docs for sorting
+ or function purposes. The ordering is generated based on the field
+ name and the version of the index. As long as the index version
+ remains unchanged, and the same field name is reused,
+ the ordering of the docs will be consistent.
+ If you want different psuedo-random orderings of documents,
+ for the same version of the index, use a dynamicField and
+ change the field name in the request.
+ -->
+ <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+
+ <!-- solr.TextField allows the specification of custom text analyzers
+ specified as a tokenizer and a list of token filters. Different
+ analyzers may be specified for indexing and querying.
+
+ The optional positionIncrementGap puts space between multiple fields
of
+ this type on the same document, with the purpose of preventing false
phrase
+ matching across fields.
+
+ For more info on customizing your analyzer chain, please see
+ http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+ -->
+
+ <!-- One can also specify an existing Analyzer class that has a
+ default constructor via the class attribute on the analyzer element.
+ Example:
+ <fieldType name="text_greek" class="solr.TextField">
+ <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
+ </fieldType>
+ -->
+
+ <!-- A text field that only splits on whitespace for exact matching of
words -->
+ <fieldType name="text_ws" class="solr.TextField"
positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms. -->
+ <fieldType name="text_general" class="solr.TextField"
positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory"
synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from
protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <fieldType name="text_en" class="solr.TextField"
positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory"
synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer
instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer
instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <fieldType name="text_en_splitting" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer type="index">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory"
synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"
splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"
splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Less flexible matching, but less false matches. Probably not ideal
for product names,
+ but may be good for SKUs. Can insert dashes in the wrong place and
still match. -->
+ <fieldType name="text_en_splitting_tight" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0"
generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the
same position - sometimes
+ possible with WordDelimiterFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries. -->
+ <fieldType name="text_general_rev" class="solr.TextField"
positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- This is an example of using the KeywordTokenizer along
+ With various TokenFilterFactories to produce a sortable field
+ that does not include some properties of the source text
+ -->
+ <fieldType name="alphaOnlySort" class="solr.TextField"
sortMissingLast="true" omitNorms="true">
+ <analyzer>
+ <!-- KeywordTokenizer does no actual tokenizing, so the entire
+ input string is preserved as a single token
+ -->
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <!-- The LowerCase TokenFilter does what you expect, which can be
+ when you want your sorting to be case insensitive
+ -->
+ <filter class="solr.LowerCaseFilterFactory" />
+ <!-- The TrimFilter removes any leading or trailing whitespace -->
+ <filter class="solr.TrimFilterFactory" />
+ <!-- The PatternReplaceFilter gives you the flexibility to use
+ Java Regular expression to replace any sequence of characters
+ matching a pattern with an arbitrary replacement string,
+ which may include back references to portions of the original
+ string matched by the pattern.
+
+ See the Java Regular Expression documentation for more
+ information on pattern and replacement string syntax.
+
+
http://docs.oracle.com/javase/7/docs/api/java/util/regex/package-summary.html
+ -->
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-z])" replacement="" replace="all"
+ />
+ </analyzer>
+ </fieldType>
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <fieldType name="lowercase" class="solr.TextField"
positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
+ </analyzer>
+ </fieldType>
+
+ <!-- since fields of this type are by default not stored or indexed,
+ any data added to them will be ignored outright. -->
+ <fieldType name="ignored" stored="false" indexed="false"
multiValued="true" class="solr.StrField" />
+
+ <!-- This point type indexes the coordinates as separate fields (subFields)
+ If subFieldType is defined, it references a type, and a dynamic field
+ definition is created matching *___<typename>. Alternately, if
+ subFieldSuffix is defined, that is used to create the subFields.
+ Example: if subFieldType="double", then the coordinates would be
+ indexed in fields myloc_0___double,myloc_1___double.
+ Example: if subFieldSuffix="_d" then the coordinates would be indexed
+ in fields myloc_0_d,myloc_1_d
+ The subFields are an implementation detail of the fieldType, and end
+ users normally should not need to know about them.
+ -->
+ <fieldType name="point" class="solr.PointType" dimension="2"
subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search. If indexed, this fieldType
must not be multivalued. -->
+ <fieldType name="location" class="solr.LatLonType"
subFieldSuffix="_coordinate"/>
+
+ <!-- Spatial rectangle (bounding box) field. It supports most spatial
predicates, and has
+ special relevancy modes: score=overlapRatio|area|area2D (local-param to
the query). DocValues is recommended for
+ relevancy. -->
+ <fieldType name="bbox" class="solr.BBoxField"
+ geo="true" distanceUnits="kilometers" numberType="_bbox_coord"
/>
+ <fieldType name="_bbox_coord" class="solr.TrieDoubleField"
precisionStep="8" docValues="true" stored="false"/>
+
+ <!-- Money/currency field type. See
http://wiki.apache.org/solr/MoneyFieldType
+ Parameters:
+ defaultCurrency: Specifies the default currency if none specified.
Defaults to "USD"
+ precisionStep: Specifies the precisionStep for the TrieLong field
used for the amount
+ providerClass: Lets you plug in other exchange provider backend:
+ solr.FileExchangeRateProvider is the default and
takes one parameter:
+ currencyConfig: name of an xml file holding
exchange rates
+ solr.OpenExchangeRatesOrgProvider uses rates from
openexchangerates.org:
+ ratesFileLocation: URL or path to rates JSON file
(default latest.json on the web)
+ refreshInterval: Number of minutes between each
rates fetch (default: 1440, min: 60)
+ -->
+ <fieldType name="currency" class="solr.CurrencyField" precisionStep="8"
defaultCurrency="USD" currencyConfig="currency.xml" />
+
+ <!--Titan specific-->
+ <fieldType name="uuid"
+ class="solr.UUIDField"
+ indexed="true" />
+
+
+ <dynamicField name="*_uuid" type="uuid" indexed="true" stored="true"/>
+
+ <!-- TTL -->
+ <field name="ttl" type="string" indexed="true" stored="true" />
+ <field name="expire_at" type="date" indexed="true" stored="true" />
+ <field name="timestamp" type="date" indexed="true" stored="true" />
+</schema>
diff --git a/dev-support/atlas-docker/config/solr/solrconfig.xml
b/dev-support/atlas-docker/config/solr/solrconfig.xml
new file mode 100644
index 0000000..21d19ef
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/solrconfig.xml
@@ -0,0 +1,630 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ 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.
+-->
+
+<!--
+ For more details about configurations options that may appear in
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
+-->
+<config>
+ <!-- In all configuration below, a prefix of "solr." for class names
+ is an alias that causes solr to search appropriate packages,
+ including org.apache.solr.(search|update|request|core|analysis)
+
+ You may also specify a fully qualified Java classname if you
+ have your own custom plugins.
+ -->
+
+ <!-- Controls what version of Lucene various components of Solr
+ adhere to. Generally, you want to use the latest version to
+ get all bug fixes and improvements. It is highly recommended
+ that you fully re-index after changing this setting as it can
+ affect both how text is indexed and queried.
+ -->
+ <luceneMatchVersion>5.0.0</luceneMatchVersion>
+
+ <!-- Data Directory
+
+ Used to specify an alternate directory to hold all index data
+ other than the default ./data under the Solr home. If
+ replication is in use, this should match the replication
+ configuration.
+ -->
+ <dataDir>${solr.data.dir:}</dataDir>
+
+
+ <!-- The DirectoryFactory to use for indexes.
+
+ solr.StandardDirectoryFactory is filesystem
+ based and tries to pick the best implementation for the current
+ JVM and platform. solr.NRTCachingDirectoryFactory, the default,
+ wraps solr.StandardDirectoryFactory and caches small files in memory
+ for better NRT performance.
+
+ One can force a particular implementation via solr.MMapDirectoryFactory,
+ solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
+
+ solr.RAMDirectoryFactory is memory based, not
+ persistent, and doesn't work with replication.
+ -->
+ <directoryFactory name="DirectoryFactory"
+
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
+
+ <!-- These will be used if you are using the solr.HdfsDirectoryFactory,
+ otherwise they will be ignored. If you don't plan on using hdfs,
+ you can safely remove this section. -->
+ <!-- The root directory that collection data should be written to. -->
+ <str name="solr.hdfs.home">${solr.hdfs.home:}</str>
+ <!-- The hadoop configuration files to use for the hdfs client. -->
+ <str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
+ <!-- Enable/Disable the hdfs cache. -->
+ <str
name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str>
+ <!-- Enable/Disable using one global cache for all SolrCores.
+ The settings used will be from the first HdfsDirectoryFactory
created. -->
+ <str
name="solr.hdfs.blockcache.global">${solr.hdfs.blockcache.global:true}</str>
+
+ </directoryFactory>
+
+ <!-- The CodecFactory for defining the format of the inverted index.
+ The default implementation is SchemaCodecFactory, which is the official
Lucene
+ index format, but hooks into the schema to provide per-field
customization of
+ the postings lists and per-document values in the fieldType element
+ (postingsFormat/docValuesFormat). Note that most of the alternative
implementations
+ are experimental, so if you choose to customize the index format, it's
a good
+ idea to convert back to the official format e.g. via
IndexWriter.addIndexes(IndexReader)
+ before upgrading to a newer version to avoid unnecessary reindexing.
+ -->
+ <codecFactory class="solr.SchemaCodecFactory"/>
+
+
+ <!-- To enable dynamic schema REST APIs, use the following for
<schemaFactory>:
+
+ <schemaFactory class="ManagedIndexSchemaFactory">
+ <bool name="mutable">true</bool>
+ <str name="managedSchemaResourceName">managed-schema</str>
+ </schemaFactory>
+
+ When ManagedIndexSchemaFactory is specified, Solr will load the schema
from
+ he resource named in 'managedSchemaResourceName', rather than from
schema.xml.
+ Note that the managed schema resource CANNOT be named schema.xml. If
the managed
+ schema does not exist, Solr will create it after reading schema.xml,
then rename
+ 'schema.xml' to 'schema.xml.bak'.
+
+ Do NOT hand edit the managed schema - external modifications will be
ignored and
+ overwritten as a result of schema modification REST API calls.
+
+ When ManagedIndexSchemaFactory is specified with mutable = true, schema
+ modification REST API calls will be allowed; otherwise, error responses
will be
+ sent back for these requests.
+ <schemaFactory class="ClassicIndexSchemaFactory"/>
+ -->
+
+ <schemaFactory class="ManagedIndexSchemaFactory">
+ <bool name="mutable">true</bool>
+ <str name="managedSchemaResourceName">managed-schema</str>
+ </schemaFactory>
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Index Config - These settings control low-level behavior of indexing
+ Most example settings here show the default value, but are commented
+ out, to more easily see where customizations have been made.
+
+ Note: This replaces <indexDefaults> and <mainIndex> from older versions
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-->
+ <indexConfig>
+
+ <!-- LockFactory
+
+ This option specifies which Lucene LockFactory implementation
+ to use.
+
+ single = SingleInstanceLockFactory - suggested for a
+ read-only index or when there is no possibility of
+ another process trying to modify the index.
+ native = NativeFSLockFactory - uses OS native file locking.
+ Do not use when multiple solr webapps in the same
+ JVM are attempting to share a single index.
+ simple = SimpleFSLockFactory - uses a plain file for locking
+
+ Defaults: 'native' is default for Solr3.6 and later, otherwise
+ 'simple' is the default
+
+ More details on the nuances of each LockFactory...
+ http://wiki.apache.org/lucene-java/AvailableLockFactories
+ -->
+ <lockType>${solr.lock.type:native}</lockType>
+
+ <!-- Lucene Infostream
+
+ To aid in advanced debugging, Lucene provides an "InfoStream"
+ of detailed information when indexing.
+
+ Setting the value to true will instruct the underlying Lucene
+ IndexWriter to write its info stream to solr's log. By default,
+ this is enabled here, and controlled through log4j.properties.
+ -->
+ <infoStream>true</infoStream>
+ </indexConfig>
+
+
+ <!-- JMX
+
+ This example enables JMX if and only if an existing MBeanServer
+ is found, use this if you want to configure JMX through JVM
+ parameters. Remove this to disable exposing Solr configuration
+ and statistics to JMX.
+
+ For more details see http://wiki.apache.org/solr/SolrJmx
+ -->
+ <jmx />
+ <!-- If you want to connect to a particular server, specify the
+ agentId
+ -->
+ <!-- <jmx agentId="myAgent" /> -->
+ <!-- If you want to start a new MBeanServer, specify the serviceUrl -->
+ <!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
+ -->
+
+ <!-- The default high-performance update handler -->
+ <updateHandler class="solr.DirectUpdateHandler2">
+
+ <!-- Enables a transaction log, used for real-time get, durability, and
+ and solr cloud replica recovery. The log can grow as big as
+ uncommitted changes to the index, so use of a hard autoCommit
+ is recommended (see below).
+ "dir" - the target directory for transaction logs, defaults to the
+ solr data directory. -->
+ <updateLog>
+ <str name="dir">${solr.ulog.dir:}</str>
+ </updateLog>
+
+ <!-- AutoCommit
+
+ Perform a hard commit automatically under certain conditions.
+ Instead of enabling autoCommit, consider using "commitWithin"
+ when adding documents.
+
+ http://wiki.apache.org/solr/UpdateXmlMessages
+
+ maxDocs - Maximum number of documents to add since the last
+ commit before automatically triggering a new commit.
+
+ maxTime - Maximum amount of time in ms that is allowed to pass
+ since a document was added before automatically
+ triggering a new commit.
+ openSearcher - if false, the commit causes recent index changes
+ to be flushed to stable storage, but does not cause a new
+ searcher to be opened to make those changes visible.
+
+ If the updateLog is enabled, then it's highly recommended to
+ have some sort of hard autoCommit to limit the log size.
+ -->
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
+
+ <!-- softAutoCommit is like autoCommit except it causes a
+ 'soft' commit which only ensures that changes are visible
+ but does not ensure that data is synced to disk. This is
+ faster and more near-realtime friendly than a hard commit.
+ -->
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
+ </autoSoftCommit>
+
+ </updateHandler>
+
+ <!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Query section - these settings control query time things like caches
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-->
+ <query>
+ <!-- Max Boolean Clauses
+
+ Maximum number of clauses in each BooleanQuery, an exception
+ is thrown if exceeded.
+
+ ** WARNING **
+
+ This option actually modifies a global Lucene property that
+ will affect all SolrCores. If multiple solrconfig.xml files
+ disagree on this property, the value at any given moment will
+ be based on the last SolrCore to be initialized.
+
+ -->
+ <maxBooleanClauses>1024</maxBooleanClauses>
+
+
+ <!-- Solr Internal Query Caches
+
+ There are two implementations of cache available for Solr,
+ LRUCache, based on a synchronized LinkedHashMap, and
+ FastLRUCache, based on a ConcurrentHashMap.
+
+ FastLRUCache has faster gets and slower puts in single
+ threaded operation and thus is generally faster than LRUCache
+ when the hit ratio of the cache is high (> 75%), and may be
+ faster under other scenarios on multi-cpu systems.
+ -->
+
+ <!-- Filter Cache
+
+ Cache used by SolrIndexSearcher for filters (DocSets),
+ unordered sets of *all* documents that match a query. When a
+ new searcher is opened, its caches may be prepopulated or
+ "autowarmed" using data from caches in the old searcher.
+ autowarmCount is the number of items to prepopulate. For
+ LRUCache, the autowarmed items will be the most recently
+ accessed items.
+
+ Parameters:
+ class - the SolrCache implementation LRUCache or
+ (LRUCache or FastLRUCache)
+ size - the maximum number of entries in the cache
+ initialSize - the initial capacity (number of entries) of
+ the cache. (see java.util.HashMap)
+ autowarmCount - the number of entries to prepopulate from
+ and old cache.
+ -->
+ <filterCache class="solr.FastLRUCache"
+ size="2000"
+ initialSize="2000"
+ autowarmCount="1000"/>
+
+ <!-- Query Result Cache
+
+ Caches results of searches - ordered lists of document ids
+ (DocList) based on a query, a sort, and the range of documents
requested.
+ -->
+ <queryResultCache class="solr.FastLRUCache"
+ size="26000"
+ initialSize="26000"
+ autowarmCount="400"/>
+
+ <!-- Document Cache
+
+ Caches Lucene Document objects (the stored fields for each
+ document). Since Lucene internal document ids are transient,
+ this cache will not be autowarmed.
+ -->
+ <documentCache class="solr.FastLRUCache"
+ size="26000"
+ initialSize="26000"
+ autowarmCount="400"/>
+
+ <!-- custom cache currently used by block join -->
+ <cache name="perSegFilter"
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ regenerator="solr.NoOpRegenerator" />
+
+ <!-- Lazy Field Loading
+
+ If true, stored fields that are not requested will be loaded
+ lazily. This can result in a significant speed improvement
+ if the usual case is to not load all stored fields,
+ especially if the skipped fields are large compressed text
+ fields.
+ -->
+ <enableLazyFieldLoading>true</enableLazyFieldLoading>
+
+ <!-- Result Window Size
+
+ An optimization for use with the queryResultCache. When a search
+ is requested, a superset of the requested number of document ids
+ are collected. For example, if a search for a particular query
+ requests matching documents 10 through 19, and queryWindowSize is 50,
+ then documents 0 through 49 will be collected and cached. Any further
+ requests in that range can be satisfied via the cache.
+ -->
+ <queryResultWindowSize>20</queryResultWindowSize>
+
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
+
+ <!-- Use Cold Searcher
+
+ If a search request comes in and there is no current
+ registered searcher, then immediately register the still
+ warming searcher and use it. If "false" then all requests
+ will block until the first searcher is done warming.
+ -->
+ <useColdSearcher>false</useColdSearcher>
+
+ <!-- Max Warming Searchers
+
+ Maximum number of searchers that may be warming in the
+ background concurrently. An error is returned if this limit
+ is exceeded.
+
+ Recommend values of 1-2 for read-only slaves, higher for
+ masters w/o cache warming.
+ -->
+ <maxWarmingSearchers>2</maxWarmingSearchers>
+
+ </query>
+
+
+ <!-- Request Dispatcher
+
+ This section contains instructions for how the SolrDispatchFilter
+ should behave when processing requests for this SolrCore.
+
+ handleSelect is a legacy option that affects the behavior of requests
+ such as /select?qt=XXX
+
+ handleSelect="true" will cause the SolrDispatchFilter to process
+ the request and dispatch the query to a handler specified by the
+ "qt" param, assuming "/select" isn't already registered.
+
+ handleSelect="false" will cause the SolrDispatchFilter to
+ ignore "/select" requests, resulting in a 404 unless a handler
+ is explicitly registered with the name "/select"
+
+ handleSelect="true" is not recommended for new users, but is the default
+ for backwards compatibility
+ -->
+ <requestDispatcher handleSelect="false" >
+ <!-- Request Parsing
+
+ These settings indicate how Solr Requests may be parsed, and
+ what restrictions may be placed on the ContentStreams from
+ those requests
+
+ enableRemoteStreaming - enables use of the stream.file
+ and stream.url parameters for specifying remote streams.
+
+ multipartUploadLimitInKB - specifies the max size (in KiB) of
+ Multipart File Uploads that Solr will allow in a Request.
+
+ formdataUploadLimitInKB - specifies the max size (in KiB) of
+ form data (application/x-www-form-urlencoded) sent via
+ POST. You can use POST to pass request parameters not
+ fitting into the URL.
+
+ addHttpRequestToContext - if set to true, it will instruct
+ the requestParsers to include the original HttpServletRequest
+ object in the context map of the SolrQueryRequest under the
+ key "httpRequest". It will not be used by any of the existing
+ Solr components, but may be useful when developing custom
+ plugins.
+
+ *** WARNING ***
+ The settings below authorize Solr to fetch remote files, You
+ should make sure your system has some authentication before
+ using enableRemoteStreaming="true"
+
+ -->
+ <requestParsers enableRemoteStreaming="true"
+ multipartUploadLimitInKB="2048000"
+ formdataUploadLimitInKB="2048"
+ addHttpRequestToContext="false"/>
+
+ <!-- HTTP Caching
+
+ Set HTTP caching related parameters (for proxy caches and clients).
+
+ The options below instruct Solr not to output any HTTP Caching
+ related headers
+ -->
+ <httpCaching never304="true" />
+
+ </requestDispatcher>
+
+ <!-- Request Handlers
+
+ http://wiki.apache.org/solr/SolrRequestHandler
+
+ Incoming queries will be dispatched to a specific handler by name
+ based on the path specified in the request.
+
+ Legacy behavior: If the request path uses "/select" but no Request
+ Handler has that name, and if handleSelect="true" has been specified in
+ the requestDispatcher, then the Request Handler is dispatched based on
+ the qt parameter. Handlers without a leading '/' are accessed this way
+ like so: http://host/app/[core/]select?qt=name If no qt is
+ given, then the requestHandler that declares default="true" will be
+ used or the one named "standard".
+
+ If a Request Handler is declared with startup="lazy", then it will
+ not be initialized until the first request that uses it.
+
+ -->
+ <!-- SearchHandler
+
+ http://wiki.apache.org/solr/SearchHandler
+
+ For processing Search Queries, the primary Request Handler
+ provided with Solr is "SearchHandler" It delegates to a sequent
+ of SearchComponents (see below) and supports distributed
+ queries across multiple shards
+ -->
+ <requestHandler name="/select" class="solr.SearchHandler">
+ <!-- default values for query parameters can be specified, these
+ will be overridden by parameters in the request
+ -->
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ </lst>
+
+ </requestHandler>
+
+ <!-- A request handler that returns indented JSON by default -->
+ <requestHandler name="/query" class="solr.SearchHandler">
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
+ <str name="df">text</str>
+ </lst>
+ </requestHandler>
+
+
+ <!--
+ The export request handler is used to export full sorted result sets.
+ Do not change these defaults.
+ -->
+ <requestHandler name="/export" class="solr.SearchHandler">
+ <lst name="invariants">
+ <str name="rq">{!xport}</str>
+ <str name="wt">xsort</str>
+ <str name="distrib">false</str>
+ </lst>
+
+ <arr name="components">
+ <str>query</str>
+ </arr>
+ </requestHandler>
+
+
+ <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell">
+ <lst name="defaults">
+ <str name="df">text</str>
+ </lst>
+ </initParams>
+
+ <!-- Field Analysis Request Handler
+
+ RequestHandler that provides much the same functionality as
+ analysis.jsp. Provides the ability to specify multiple field
+ types and field names in the same request and outputs
+ index-time and query-time analysis for each of them.
+
+ Request parameters are:
+ analysis.fieldname - field name whose analyzers are to be used
+
+ analysis.fieldtype - field type whose analyzers are to be used
+ analysis.fieldvalue - text for index-time analysis
+ q (or analysis.q) - text for query time analysis
+ analysis.showmatch (true|false) - When set to true and when
+ query analysis is performed, the produced tokens of the
+ field value analysis will be marked as "matched" for every
+ token that is produces by the query analysis
+ -->
+ <requestHandler name="/analysis/field"
+ startup="lazy"
+ class="solr.FieldAnalysisRequestHandler" />
+
+
+ <!-- Document Analysis Handler
+
+ http://wiki.apache.org/solr/AnalysisRequestHandler
+
+ An analysis handler that provides a breakdown of the analysis
+ process of provided documents. This handler expects a (single)
+ content stream with the following format:
+
+ <docs>
+ <doc>
+ <field name="id">1</field>
+ <field name="name">The Name</field>
+ <field name="text">The Text Value</field>
+ </doc>
+ <doc>...</doc>
+ <doc>...</doc>
+ ...
+ </docs>
+
+ Note: Each document must contain a field which serves as the
+ unique key. This key is used in the returned response to associate
+ an analysis breakdown to the analyzed document.
+
+ Like the FieldAnalysisRequestHandler, this handler also supports
+ query analysis by sending either an "analysis.query" or "q"
+ request parameter that holds the query text to be analyzed. It
+ also supports the "analysis.showmatch" parameter which when set to
+ true, all field tokens that match the query tokens will be marked
+ as a "match".
+ -->
+ <requestHandler name="/analysis/document"
+ class="solr.DocumentAnalysisRequestHandler"
+ startup="lazy" />
+
+ <!-- Echo the request contents back to the client -->
+ <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <str name="echoHandler">true</str>
+ </lst>
+ </requestHandler>
+
+
+
+ <!-- Search Components
+
+ Search components are registered to SolrCore and used by
+ instances of SearchHandler (which can access them by name)
+
+ By default, the following components are available:
+
+ <searchComponent name="query" class="solr.QueryComponent" />
+ <searchComponent name="facet" class="solr.FacetComponent" />
+ <searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
+ <searchComponent name="highlight" class="solr.HighlightComponent" />
+ <searchComponent name="stats" class="solr.StatsComponent" />
+ <searchComponent name="debug" class="solr.DebugComponent" />
+
+ -->
+
+ <!-- Terms Component
+
+ http://wiki.apache.org/solr/TermsComponent
+
+ A component to return terms and document frequency of those
+ terms
+ -->
+ <searchComponent name="terms" class="solr.TermsComponent"/>
+
+ <!-- A request handler for demonstrating the terms component -->
+ <requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
+ <lst name="defaults">
+ <bool name="terms">true</bool>
+ <bool name="distrib">false</bool>
+ </lst>
+ <arr name="components">
+ <str>terms</str>
+ </arr>
+ </requestHandler>
+
+ <!-- Legacy config for the admin interface -->
+ <admin>
+ <defaultQuery>*:*</defaultQuery>
+ </admin>
+
+
+ <!--Titan specific-->
+ <updateRequestProcessorChain default="true">
+ <processor class="solr.TimestampUpdateProcessorFactory">
+ <str name="fieldName">timestamp</str>
+ </processor>
+ <processor class="solr.processor.DocExpirationUpdateProcessorFactory">
+ <int name="autoDeletePeriodSeconds">5</int>
+ <str name="ttlFieldName">ttl</str>
+ <str name="expirationFieldName">expire_at</str>
+ </processor>
+ <processor class="solr.FirstFieldValueUpdateProcessorFactory">
+ <str name="fieldName">expire_at_dt</str>
+ </processor>
+ <processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.RunUpdateProcessorFactory"/>
+ </updateRequestProcessorChain>
+</config>
diff --git a/dev-support/atlas-docker/config/solr/stopwords.txt
b/dev-support/atlas-docker/config/solr/stopwords.txt
new file mode 100644
index 0000000..ae1e83e
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/stopwords.txt
@@ -0,0 +1,14 @@
+# 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.
diff --git a/dev-support/atlas-docker/config/solr/synonyms.txt
b/dev-support/atlas-docker/config/solr/synonyms.txt
new file mode 100644
index 0000000..7f72128
--- /dev/null
+++ b/dev-support/atlas-docker/config/solr/synonyms.txt
@@ -0,0 +1,29 @@
+# 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.
+
+#-----------------------------------------------------------------------
+#some test synonym mappings unlikely to appear in real input text
+aaafoo => aaabar
+bbbfoo => bbbfoo bbbbar
+cccfoo => cccbar cccbaz
+fooaaa,baraaa,bazaaa
+
+# Some synonym groups specific to this example
+GB,gib,gigabyte,gigabytes
+MB,mib,megabyte,megabytes
+Television, Televisions, TV, TVs
+#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#after us won't split it into two words.
+
+# Synonym mappings can be used for spelling correction too
+pixima => pixma
+
diff --git a/dev-support/atlas-docker/docker-compose.atlas-hadoop.yml
b/dev-support/atlas-docker/docker-compose.atlas-hadoop.yml
new file mode 100644
index 0000000..b172e54
--- /dev/null
+++ b/dev-support/atlas-docker/docker-compose.atlas-hadoop.yml
@@ -0,0 +1,31 @@
+version: '3'
+services:
+ atlas-hadoop:
+ build:
+ context: .
+ dockerfile: Dockerfile.atlas-hadoop
+ args:
+ - HADOOP_VERSION=${HADOOP_VERSION}
+ image: atlas-hadoop
+ container_name: atlas-hadoop
+ hostname: atlas-hadoop.example.com
+ stdin_open: true
+ tty: true
+ networks:
+ - atlas
+ ports:
+ - "9000:9000"
+ - "8088:8088"
+ depends_on:
+ - atlas-base
+ healthcheck:
+ test: "hdfs dfs -ls /"
+ interval: 1m30s
+ timeout: 10s
+ retries: 30
+ start_period: 40s
+ environment:
+ - HADOOP_VERSION
+
+networks:
+ atlas:
diff --git a/dev-support/atlas-docker/docker-compose.atlas-hbase.yml
b/dev-support/atlas-docker/docker-compose.atlas-hbase.yml
new file mode 100644
index 0000000..7157889
--- /dev/null
+++ b/dev-support/atlas-docker/docker-compose.atlas-hbase.yml
@@ -0,0 +1,30 @@
+version: '3'
+services:
+ atlas-hbase:
+ build:
+ context: .
+ dockerfile: Dockerfile.atlas-hbase
+ args:
+ - HBASE_VERSION=${HBASE_VERSION}
+ image: atlas-hbase
+ container_name: atlas-hbase
+ hostname: atlas-hbase.example.com
+ stdin_open: true
+ tty: true
+ networks:
+ - atlas
+ ports:
+ - "16000:16000"
+ - "16010:16010"
+ - "16020:16020"
+ - "16030:16030"
+ depends_on:
+ atlas-hadoop:
+ condition: service_healthy
+ atlas-zk:
+ condition: service_started
+ environment:
+ - HBASE_VERSION
+
+networks:
+ atlas:
diff --git a/dev-support/atlas-docker/docker-compose.atlas-kafka.yml
b/dev-support/atlas-docker/docker-compose.atlas-kafka.yml
new file mode 100644
index 0000000..1f70521
--- /dev/null
+++ b/dev-support/atlas-docker/docker-compose.atlas-kafka.yml
@@ -0,0 +1,27 @@
+version: '3'
+services:
+ atlas-kafka:
+ build:
+ context: .
+ dockerfile: Dockerfile.atlas-kafka
+ args:
+ - KAFKA_VERSION=${KAFKA_VERSION}
+ - ATLAS_VERSION=${ATLAS_VERSION}
+ image: atlas-kafka
+ container_name: atlas-kafka
+ hostname: atlas-kafka.example.com
+ stdin_open: true
+ tty: true
+ networks:
+ - atlas
+ ports:
+ - "9092:9092"
+ depends_on:
+ atlas-zk:
+ condition: service_started
+ environment:
+ - KAFKA_VERSION
+ - ATLAS_VERSION
+
+networks:
+ atlas:
diff --git a/dev-support/atlas-docker/docker-compose.atlas.yml
b/dev-support/atlas-docker/docker-compose.atlas.yml
index cfaf0d7..561c475 100644
--- a/dev-support/atlas-docker/docker-compose.atlas.yml
+++ b/dev-support/atlas-docker/docker-compose.atlas.yml
@@ -18,11 +18,42 @@ services:
ports:
- "21000:21000"
depends_on:
- - atlas-base
+ atlas-hbase:
+ condition: service_started
+ atlas-kafka:
+ condition: service_started
+ atlas-solr:
+ condition: service_started
+ atlas-zk:
+ condition: service_started
environment:
- ATLAS_VERSION
command:
- /home/atlas/scripts/atlas.sh
+ atlas-zk:
+ build:
+ context: .
+ dockerfile: Dockerfile.atlas-zk
+ image: atlas-zk
+ container_name: atlas-zk
+ hostname: atlas-zk.example.com
+ networks:
+ - atlas
+ ports:
+ - "2181:2181"
+
+ atlas-solr:
+ build:
+ context: .
+ dockerfile: Dockerfile.atlas-solr
+ image: atlas-solr
+ container_name: atlas-solr
+ hostname: atlas-solr.example.com
+ networks:
+ - atlas
+ ports:
+ - "8983:8983"
+
networks:
atlas:
diff --git a/dev-support/atlas-docker/download-archives.sh
b/dev-support/atlas-docker/download-archives.sh
new file mode 100755
index 0000000..dc6d22c
--- /dev/null
+++ b/dev-support/atlas-docker/download-archives.sh
@@ -0,0 +1,49 @@
+#!/bin/bash
+
+# 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.
+
+#
+# Downloads HDFS/Hive/HBase/Kafka/.. archives to a local cache directory.
+# The downloaded archives will be used while building docker images that
+# run these services
+#
+
+
+#
+# source .env file to get versions to download
+#
+source .env
+
+
+downloadIfNotPresent() {
+ local fileName=$1
+ local urlBase=$2
+
+ if [ ! -f "downloads/${fileName}" ]
+ then
+ echo "downloading ${urlBase}/${fileName}.."
+
+ curl -L ${urlBase}/${fileName} --output downloads/${fileName}
+ else
+ echo "file already in cache: ${fileName}"
+ fi
+}
+
+downloadIfNotPresent hadoop-${HADOOP_VERSION}.tar.gz
https://archive.apache.org/dist/hadoop/common/hadoop-${HADOOP_VERSION}
+downloadIfNotPresent hbase-${HBASE_VERSION}-bin.tar.gz
https://archive.apache.org/dist/hbase/${HBASE_VERSION}
+downloadIfNotPresent kafka_2.12-${KAFKA_VERSION}.tgz
https://archive.apache.org/dist/kafka/${KAFKA_VERSION}
+
diff --git a/dev-support/atlas-docker/downloads/.gitignore
b/dev-support/atlas-docker/downloads/.gitignore
new file mode 100644
index 0000000..72e8ffc
--- /dev/null
+++ b/dev-support/atlas-docker/downloads/.gitignore
@@ -0,0 +1 @@
+*
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas-hadoop-mkdir.sh
similarity index 57%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/scripts/atlas-hadoop-mkdir.sh
index 7abb6f7..2334ded 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas-hadoop-mkdir.sh
@@ -16,28 +16,12 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
-
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
-then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
-
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
-
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
-
- chown -R atlas:atlas ${ATLAS_HOME}/
-
- touch ${ATLAS_HOME}/.setupDone
-fi
-
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
-
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+# setup directories for HBase
+${HADOOP_HOME}/bin/hdfs dfs -mkdir /hbase
+${HADOOP_HOME}/bin/hdfs dfs -chown hbase:hadoop /hbase
+
+# setup directories for Hive
+${HADOOP_HOME}/bin/hdfs dfs -mkdir -p /user/hive/warehouse
+${HADOOP_HOME}/bin/hdfs dfs -mkdir -p /tmp/hive
+${HADOOP_HOME}/bin/hdfs dfs -chown -R hive:hadoop /tmp/hive /user/hive
+${HADOOP_HOME}/bin/hdfs dfs -chmod 777 /tmp/hive
diff --git a/dev-support/atlas-docker/scripts/atlas-hadoop-setup.sh
b/dev-support/atlas-docker/scripts/atlas-hadoop-setup.sh
new file mode 100755
index 0000000..d299feb
--- /dev/null
+++ b/dev-support/atlas-docker/scripts/atlas-hadoop-setup.sh
@@ -0,0 +1,60 @@
+#!/bin/bash
+
+# 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.
+
+echo "export JAVA_HOME=${JAVA_HOME}" >> ${HADOOP_HOME}/etc/hadoop/hadoop-env.sh
+
+cat <<EOF > /etc/ssh/ssh_config
+Host *
+ StrictHostKeyChecking no
+ UserKnownHostsFile=/dev/null
+EOF
+
+cat <<EOF > ${HADOOP_HOME}/etc/hadoop/core-site.xml
+<configuration>
+ <property>
+ <name>fs.defaultFS</name>
+ <value>hdfs://atlas-hadoop:9000</value>
+ </property>
+</configuration>
+EOF
+
+cat <<EOF > ${HADOOP_HOME}/etc/hadoop/hdfs-site.xml
+<configuration>
+ <property>
+ <name>dfs.replication</name>
+ <value>1</value>
+ </property>
+</configuration>
+EOF
+
+cat <<EOF > ${HADOOP_HOME}/etc/hadoop/yarn-site.xml
+<configuration>
+ <property>
+ <name>yarn.nodemanager.aux-services</name>
+ <value>mapreduce_shuffle</value>
+ </property>
+ <property>
+ <name>yarn.nodemanager.env-whitelist</name>
+
<value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_MAPRED_HOME</value>
+ </property>
+</configuration>
+EOF
+
+mkdir -p /opt/hadoop/logs
+chown -R hdfs:hadoop /opt/hadoop/
+chmod g+w /opt/hadoop/logs
diff --git a/dev-support/atlas-docker/scripts/atlas-hadoop.sh
b/dev-support/atlas-docker/scripts/atlas-hadoop.sh
new file mode 100755
index 0000000..b33fc16
--- /dev/null
+++ b/dev-support/atlas-docker/scripts/atlas-hadoop.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+
+# 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.
+
+service ssh start
+
+CREATE_HDFS_DIR=false
+
+if [ ! -e ${HADOOP_HOME}/.setupDone ]
+then
+ su -c "ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa" hdfs
+ su -c "cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys" hdfs
+ su -c "chmod 0600 ~/.ssh/authorized_keys" hdfs
+
+ su -c "ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa" yarn
+ su -c "cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys" yarn
+ su -c "chmod 0600 ~/.ssh/authorized_keys" yarn
+
+ echo "ssh" > /etc/pdsh/rcmd_default
+
+ ${ATLAS_SCRIPTS}/atlas-hadoop-setup.sh
+
+ su -c "${HADOOP_HOME}/bin/hdfs namenode -format" hdfs
+
+ CREATE_HDFS_DIR=true
+ touch ${HADOOP_HOME}/.setupDone
+fi
+
+su -c "${HADOOP_HOME}/sbin/start-dfs.sh" hdfs
+su -c "${HADOOP_HOME}/sbin/start-yarn.sh" yarn
+
+if [ "${CREATE_HDFS_DIR}" == "true" ]
+then
+ su -c "${ATLAS_SCRIPTS}/atlas-hadoop-mkdir.sh" hdfs
+fi
+
+NAMENODE_PID=`ps -ef | grep -v grep | grep -i
"org.apache.hadoop.hdfs.server.namenode.NameNode" | awk '{print $2}'`
+
+# prevent the container from exiting
+tail --pid=$NAMENODE_PID -f /dev/null
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas-hbase-setup.sh
similarity index 57%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/scripts/atlas-hbase-setup.sh
index 7abb6f7..c576989 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas-hbase-setup.sh
@@ -16,28 +16,13 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
+echo "export JAVA_HOME=${JAVA_HOME}" >> ${HBASE_HOME}/conf/hbase-env.sh
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
-then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
+cat <<EOF > /etc/ssh/ssh_config
+Host *
+ StrictHostKeyChecking no
+ UserKnownHostsFile=/dev/null
+EOF
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
-
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
-
- chown -R atlas:atlas ${ATLAS_HOME}/
-
- touch ${ATLAS_HOME}/.setupDone
-fi
-
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
-
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+cp ${ATLAS_SCRIPTS}/hbase-site.xml /opt/hbase/conf/hbase-site.xml
+chown -R hbase:hadoop /opt/hbase/
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas-hbase.sh
similarity index 60%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/scripts/atlas-hbase.sh
index 7abb6f7..81b382b 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas-hbase.sh
@@ -16,28 +16,24 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
+service ssh start
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
+if [ ! -e ${HBASE_HOME}/.setupDone ]
then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
-
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
+ su -c "ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa" hbase
+ su -c "cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys" hbase
+ su -c "chmod 0600 ~/.ssh/authorized_keys" hbase
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
+ echo "ssh" > /etc/pdsh/rcmd_default
- chown -R atlas:atlas ${ATLAS_HOME}/
+ ${ATLAS_SCRIPTS}/atlas-hbase-setup.sh
- touch ${ATLAS_HOME}/.setupDone
+ touch ${HBASE_HOME}/.setupDone
fi
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
+su -c "${HBASE_HOME}/bin/start-hbase.sh" hbase
+
+HBASE_MASTER_PID=`ps -ef | grep -v grep | grep -i
"org.apache.hadoop.hbase.master.HMaster" | awk '{print $2}'`
# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+tail --pid=$HBASE_MASTER_PID -f /dev/null
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas-kafka-setup.sh
similarity index 57%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/scripts/atlas-kafka-setup.sh
index 7abb6f7..2946aeb 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas-kafka-setup.sh
@@ -16,28 +16,12 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
+cat <<EOF > /etc/ssh/ssh_config
+Host *
+ StrictHostKeyChecking no
+ UserKnownHostsFile=/dev/null
+EOF
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
-then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
+sed -i 's/localhost:2181/atlas-zk.example.com:2181/'
/opt/kafka/config/server.properties
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
-
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
-
- chown -R atlas:atlas ${ATLAS_HOME}/
-
- touch ${ATLAS_HOME}/.setupDone
-fi
-
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
-
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+chown -R kafka:hadoop /opt/kafka/
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas-kafka.sh
similarity index 58%
copy from dev-support/atlas-docker/scripts/atlas.sh
copy to dev-support/atlas-docker/scripts/atlas-kafka.sh
index 7abb6f7..6c0fad0 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas-kafka.sh
@@ -16,28 +16,19 @@
# See the License for the specific language governing permissions and
# limitations under the License.
-set -x
+service ssh start
-if [ ! -e ${ATLAS_HOME}/.setupDone ]
+if [ ! -e ${KAFKA_HOME}/.setupDone ]
then
- SETUP_ATLAS=true
-else
- SETUP_ATLAS=false
-fi
-
-if [ "${SETUP_ATLAS}" == "true" ]
-then
- encryptedPwd=$(${ATLAS_HOME}/bin/cputil.py -g -u admin -p atlasR0cks! -s)
+ su -c "ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa" kafka
+ su -c "cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys" kafka
+ su -c "chmod 0600 ~/.ssh/authorized_keys" kafka
- echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
+ echo "ssh" > /etc/pdsh/rcmd_default
- chown -R atlas:atlas ${ATLAS_HOME}/
+ ${ATLAS_SCRIPTS}/atlas-kafka-setup.sh
- touch ${ATLAS_HOME}/.setupDone
+ touch ${KAFKA_HOME}/.setupDone
fi
-su -c "cd ${ATLAS_HOME}/bin && ./atlas_start.py" atlas
-ATLAS_PID=`ps -ef | grep -v grep | grep -i "org.apache.atlas.Atlas" | awk
'{print $2}'`
-
-# prevent the container from exiting
-tail --pid=$ATLAS_PID -f /dev/null
+su -c "cd ${KAFKA_HOME} && CLASSPATH=${KAFKA_HOME}/config
./bin/kafka-server-start.sh config/server.properties" kafka
diff --git a/dev-support/atlas-docker/scripts/atlas-solr-create.sh
b/dev-support/atlas-docker/scripts/atlas-solr-create.sh
new file mode 100755
index 0000000..8b1d75d
--- /dev/null
+++ b/dev-support/atlas-docker/scripts/atlas-solr-create.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+
+# Create Solr collections used by Atlas
+precreate-core vertex_index /opt/solr/server/solr/configsets/atlas/
+precreate-core edge_index /opt/solr/server/solr/configsets/atlas/
+precreate-core fulltext_index /opt/solr/server/solr/configsets/atlas/
diff --git a/dev-support/atlas-docker/scripts/atlas.sh
b/dev-support/atlas-docker/scripts/atlas.sh
index 7abb6f7..57d8021 100755
--- a/dev-support/atlas-docker/scripts/atlas.sh
+++ b/dev-support/atlas-docker/scripts/atlas.sh
@@ -31,6 +31,17 @@ then
echo "admin=ADMIN::${encryptedPwd}" >
${ATLAS_HOME}/conf/users-credentials.properties
+ sed -i
"s/atlas.graph.storage.hostname=.*$/atlas.graph.storage.hostname=atlas-zk.example.com:2181/"
/opt/atlas/conf/atlas-application.properties
+ sed -i
"s/atlas.audit.hbase.zookeeper.quorum=.*$/atlas.audit.hbase.zookeeper.quorum=atlas-zk.example.com:2181/"
/opt/atlas/conf/atlas-application.properties
+
+ sed -i "s/^atlas.graph.index.search.solr.mode=cloud/#
atlas.graph.index.search.solr.mode=cloud/"
/opt/atlas/conf/atlas-application.properties
+ sed -i "s/^#
*atlas.graph.index.search.solr.mode=http/atlas.graph.index.search.solr.mode=http/"
/opt/atlas/conf/atlas-application.properties
+ sed -i
"s/^.*atlas.graph.index.search.solr.http-urls=.*$/atlas.graph.index.search.solr.http-urls=http:\/\/atlas-solr.example.com:8983\/solr/"
/opt/atlas/conf/atlas-application.properties
+
+ sed -i
"s/atlas.notification.embedded=.*$/atlas.notification.embedded=false/"
/opt/atlas/conf/atlas-application.properties
+ sed -i
"s/atlas.kafka.zookeeper.connect=.*$/atlas.kafka.zookeeper.connect=atlas-zk.example.com:2181/"
/opt/atlas/conf/atlas-application.properties
+ sed -i
"s/atlas.kafka.bootstrap.servers=.*$/atlas.kafka.bootstrap.servers=atlas-kafka.example.com:9092/"
/opt/atlas/conf/atlas-application.properties
+
chown -R atlas:atlas ${ATLAS_HOME}/
touch ${ATLAS_HOME}/.setupDone
diff --git a/dev-support/atlas-docker/scripts/hbase-site.xml
b/dev-support/atlas-docker/scripts/hbase-site.xml
new file mode 100644
index 0000000..dd8828f
--- /dev/null
+++ b/dev-support/atlas-docker/scripts/hbase-site.xml
@@ -0,0 +1,52 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><!--
+/*
+ * 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.
+ */
+--><configuration>
+ <!--
+ The following properties are set for running HBase as a single process on a
+ developer workstation. With this configuration, HBase is running in
+ "stand-alone" mode and without a distributed file system. In this mode, and
+ without further configuration, HBase and ZooKeeper data are stored on the
+ local filesystem, in a path under the value configured for `hbase.tmp.dir`.
+ This value is overridden from its default value of `/tmp` because many
+ systems clean `/tmp` on a regular basis. Instead, it points to a path
within
+ this HBase installation directory.
+
+ Running against the `LocalFileSystem`, as opposed to a distributed
+ filesystem, runs the risk of data integrity issues and data loss. Normally
+ HBase will refuse to run in such an environment. Setting
+ `hbase.unsafe.stream.capability.enforce` to `false` overrides this
behavior,
+ permitting operation. This configuration is for the developer workstation
+ only and __should not be used in production!__
+
+ See also https://hbase.apache.org/book.html#standalone_dist
+ -->
+ <property>
+ <name>hbase.cluster.distributed</name>
+ <value>true</value>
+ </property>
+ <property>
+ <name>hbase.rootdir</name>
+ <value>hdfs://atlas-hadoop.example.com:9000/hbase</value>
+ </property>
+ <property>
+ <name>hbase.zookeeper.quorum</name>
+ <value>atlas-zk.example.com</value>
+ </property>
+</configuration>
diff --git a/distro/pom.xml b/distro/pom.xml
index c00de39..d84f5e7 100644
--- a/distro/pom.xml
+++ b/distro/pom.xml
@@ -65,7 +65,6 @@ atlas.graph.index.search.solr.wait-searcher=true
#for distributed mode, specify zookeeper quorum here
atlas.graph.storage.hostname=
atlas.graph.storage.hbase.regions-per-server=1
-atlas.graph.storage.lock.wait-time=10000
#In order to use Cassandra as a backend, comment out the hbase specific
properties above, and uncomment the
#the following properties
@@ -333,7 +332,6 @@ atlas.graph.index.search.solr.wait-searcher=true
#for distributed mode, specify zookeeper quorum here
atlas.graph.storage.hostname=localhost
atlas.graph.storage.hbase.regions-per-server=1
-atlas.graph.storage.lock.wait-time=10000
</graph.storage.properties>
<hbase.dir>${project.build.directory}/hbase</hbase.dir>
<hbase.embedded>true</hbase.embedded>
diff --git a/pom.xml b/pom.xml
index df4dec5..092ba09 100644
--- a/pom.xml
+++ b/pom.xml
@@ -698,7 +698,7 @@
<guava.version>25.1-jre</guava.version>
<guice.version>4.1.0</guice.version>
<hadoop.hdfs-client.version>${hadoop.version}</hadoop.hdfs-client.version>
- <hadoop.version>3.1.1</hadoop.version>
+ <hadoop.version>3.3.0</hadoop.version>
<hbase.version>2.3.3</hbase.version>
<hive.version>3.1.0</hive.version>
<hppc.version>0.8.1</hppc.version>
diff --git a/webapp/pom.xml b/webapp/pom.xml
index 7d61735..ccbcc31 100755
--- a/webapp/pom.xml
+++ b/webapp/pom.xml
@@ -98,12 +98,6 @@
<dependency>
<groupId>org.apache.atlas</groupId>
<artifactId>atlas-common</artifactId>
- <exclusions>
- <exclusion>
- <groupId>com.fasterxml.jackson.core</groupId>
- <artifactId>*</artifactId>
- </exclusion>
- </exclusions>
</dependency>
<dependency>
@@ -494,6 +488,12 @@
<groupId>org.keycloak</groupId>
<artifactId>keycloak-spring-security-adapter</artifactId>
<version>${keycloak.version}</version>
+ <exclusions>
+ <exclusion>
+ <groupId>com.fasterxml.jackson.core</groupId>
+ <artifactId>jackson-core</artifactId>
+ </exclusion>
+ </exclusions>
</dependency>
<dependency>
@@ -519,6 +519,12 @@
<artifactId>log4j-api</artifactId>
<version>${log4j2.version}</version>
</dependency>
+
+ <dependency>
+ <groupId>com.fasterxml.jackson.core</groupId>
+ <artifactId>jackson-core</artifactId>
+ <version>${jackson.version}</version>
+ </dependency>
</dependencies>
<build>
