-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'develop' of https://github.com/ebi-gene-expression-grou…
…p/atlas-web-bulk into chore/add_back_experiment_design
- Loading branch information
Showing
10 changed files
with
264 additions
and
64 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
FROM ubuntu:jammy | ||
|
||
# Update package list and install necessary tools | ||
# Python 3 is required by index-bioentities but comes as part of Ubuntu | ||
RUN apt-get update && \ | ||
apt-get install -y --no-install-recommends \ | ||
git openjdk-11-jdk jq rsync curl | ||
|
||
# Clean up APT cache and temporary files | ||
RUN apt-get clean && \ | ||
rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* | ||
|
||
# Create the necessary directory | ||
RUN mkdir -p /root/bioentity-properties-jsonl | ||
RUN mkdir -p /root/experiments-jsonl | ||
|
||
# Clone the necessary repositories | ||
WORKDIR /root | ||
RUN git clone --depth 1 --recurse-submodules https://github.com/ebi-gene-expression-group/index-bioentities.git | ||
RUN git clone --depth 1 --recurse-submodules https://github.com/ebi-gene-expression-group/atlas-web-bulk.git | ||
RUN git clone --depth 1 --recurse-submodules https://github.com/ebi-gene-expression-group/solr-bulk.git | ||
|
||
ENTRYPOINT ["/bin/bash", "-c"] |
92 changes: 92 additions & 0 deletions
92
docker/prepare-dev-environment/solr-analytics/docker-compose.yml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,92 @@ | ||
version: "3.6" | ||
|
||
services: | ||
solr-populator: | ||
build: | ||
context: ${DOCKERFILE_PATH} | ||
no_cache: true | ||
networks: | ||
- atlas-test-net | ||
ports: | ||
- "8089:8089" | ||
depends_on: | ||
- gxa-postgres | ||
- gxa-solrcloud-0 | ||
- gxa-solrcloud-1 | ||
volumes: | ||
- gradle-wrapper-dists:/root/.gradle/wrapper/dists | ||
- gradle-ro-dep-cache:/gradle-ro-dep-cache:ro | ||
- atlas-data-bioentity-properties:/atlas-data/bioentity_properties | ||
- atlas-data-exp:/atlas-data/exp | ||
- atlas-data-expdesign:/atlas-data/expdesign | ||
secrets: | ||
- solrcloud.pem | ||
environment: | ||
JAVA_TOOL_OPTIONS: "-Dfile.encoding=UTF8" | ||
JAVA_OPTS: "-Dsolr.httpclient.builder.factory=org.apache.solr.client.solrj.impl.PreemptiveBasicAuthClientBuilderFactory -Dbasicauth=${SOLR_USER}:${SOLR_PASSWORD}" | ||
GRADLE_RO_DEP_CACHE: /gradle-ro-dep-cache | ||
ZK_HOSTS: "${PROJECT_NAME}-${SOLR_CLOUD_ZK_CONTAINER_1_NAME}:2181,${PROJECT_NAME}-${SOLR_CLOUD_ZK_CONTAINER_2_NAME}:2181,${PROJECT_NAME}-${SOLR_CLOUD_ZK_CONTAINER_3_NAME}:2181" | ||
SOLR_HOST: "http://${PROJECT_NAME}-${SOLR_CLOUD_CONTAINER_1_NAME}:8983/solr" | ||
SOLR_NUM_SHARDS: 2 | ||
NUM_DOCS_PER_BATCH: 20000 | ||
SOLR_COLLECTION_BIOENTITIES: bioentities | ||
SOLR_COLLECTION_BIOENTITIES_SCHEMA_VERSION: 1 | ||
SOLR_COLLECTION_BULK_ANALYTICS: bulk-analytics | ||
SOLR_COLLECTION_BULK_ANALYTICS_SCHEMA_VERSION: 1 | ||
working_dir: /root | ||
command: | ||
- | | ||
cd /root/atlas-web-bulk | ||
./gradlew -PdataFilesLocation=/root \ | ||
-PexperimentFilesLocation=/atlas-data/exp \ | ||
-PexperimentDesignLocation=/atlas-data/expdesign \ | ||
-PjdbcUrl=jdbc:postgresql://${POSTGRES_HOST}:5432/${POSTGRES_DB} \ | ||
-PjdbcUsername=${POSTGRES_USER} \ | ||
-PjdbcPassword=${POSTGRES_PASSWORD} \ | ||
-PzkHosts=$${ZK_HOSTS} \ | ||
-PsolrHosts=$${SOLR_HOST} \ | ||
-PsolrUser=${SOLR_USER} \ | ||
-PsolrPassword=${SOLR_PASSWORD} \ | ||
:cli:bootRun --args="bulk-analytics-json --output=/root/experiments-jsonl -e $(echo ${EXP_IDS} ${PRIVATE_EXP_IDS} | sed -e "s/ /,/g")" | ||
cd /root/solr-bulk/bin | ||
export SOLR_HOST="${PROJECT_NAME}-${SOLR_CLOUD_CONTAINER_1_NAME}:8983" | ||
./create-bulk-analytics-collection.sh | ||
echo "bulk-analytics collection has been created" | ||
./create-bulk-analytics-schema.sh | ||
echo "bulk-analytics schema has been created" | ||
cd /root/index-bioentities/bin | ||
export SOLR_COLLECTION=$${SOLR_COLLECTION_BULK_ANALYTICS} | ||
export SCHEMA_VERSION=$${SOLR_COLLECTION_BULK_ANALYTICS_SCHEMA_VERSION} | ||
export SOLR_HOSTS="${PROJECT_NAME}-${SOLR_CLOUD_CONTAINER_1_NAME}:8983" | ||
export SOLR_PROCESSORS=dedupe | ||
for FILE in `ls /root/experiments-jsonl/*.jsonl` | ||
do | ||
INPUT_JSONL=$${FILE} ./solr-jsonl-chunk-loader.sh >> /dev/stdout 2>&1 | ||
done | ||
secrets: | ||
solrcloud.pem: | ||
file: ${SOLR_PRIVATE_KEY:-/dev/null} | ||
|
||
volumes: | ||
gradle-wrapper-dists: | ||
external: true | ||
name: ${PROJECT_NAME}_${GRADLE_WRAPPER_DISTS_VOL_NAME} | ||
gradle-ro-dep-cache: | ||
external: true | ||
name: ${PROJECT_NAME}_${GRADLE_RO_DEP_CACHE_VOL_NAME} | ||
atlas-data-bioentity-properties: | ||
external: true | ||
name: ${PROJECT_NAME}_${ATLAS_DATA_BIOENTITY_PROPERTIES_VOL_NAME} | ||
atlas-data-exp: | ||
external: true | ||
name: ${PROJECT_NAME}_${ATLAS_DATA_EXP_VOL_NAME} | ||
atlas-data-expdesign: | ||
external: true | ||
name: ${PROJECT_NAME}_${ATLAS_DATA_EXPDESIGN_VOL_NAME} | ||
|
||
networks: | ||
atlas-test-net: | ||
name: atlas-test-net |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.