Merge pull request #60 from data-catering/datahub

Add in support for datahub and confluent schema registry

README.md

@@ -120,50 +120,51 @@ POSTGRES_USER=my-user POSTGRES_PASSWORD=my-password ./run.sh postgres
 
 ## Services
 
-| Service Type                | Service       | Supported |
-|-----------------------------|---------------|-----------|
-| Change Data Capture         | debezium      | ✅         |
-| Database                    | cassandra     | ✅         |
-| Database                    | cockroachdb   | ✅         |
-| Database                    | elasticsearch | ✅         |
-| Database                    | mariadb       | ✅         |
-| Database                    | mongodb       | ✅         |
-| Database                    | mssql         | ✅         |
-| Database                    | mysql         | ✅         |
-| Database                    | neo4j         | ✅         |
-| Database                    | opensearch    | ✅         |
-| Database                    | postgres      | ✅         |
-| Database                    | spanner       | ✅         |
-| Database                    | sqlite        | ✅         |
-| Data Catalog                | amundsen      | ✅         |
-| Data Catalog                | marquez       | ✅         |
-| Data Catalog                | polaris       | ✅         |
-| Data Catalog                | unitycatalog  | ✅         |
-| Data Catalog                | datahub       | ❌         |
-| Data Catalog                | openmetadata  | ❌         |
-| Distributed Coordination    | zookeeper     | ✅         |
-| Distributed Data Processing | flink         | ✅         |
-| HTTP                        | httpbin       | ✅         |
-| Identity Management         | keycloak      | ✅         |
-| Job Orchestrator            | airflow       | ✅         |
-| Job Orchestrator            | dagster       | ✅         |
-| Job Orchestrator            | mage-ai       | ✅         |
-| Job Orchestrator            | prefect       | ✅         |
-| Messaging                   | activemq      | ✅         |
-| Messaging                   | kafka         | ✅         |
-| Messaging                   | rabbitmq      | ✅         |
-| Messaging                   | solace        | ✅         |
-| Notebook                    | jupyter       | ✅         |
-| Object Storage              | minio         | ✅         |
-| Query Engine                | duckdb        | ✅         |
-| Query Engine                | flight-sql    | ✅         |
-| Query Engine                | presto        | ✅         |
-| Query Engine                | trino         | ✅         |
-| Real-time OLAP              | clickhouse    | ✅         |
-| Real-time OLAP              | doris         | ✅         |
-| Real-time OLAP              | druid         | ✅         |
-| Real-time OLAP              | pinot         | ✅         |
-| Test Data Management        | data-caterer  | ✅         |
-| Workflow                    | maestro       | ✅         | 
-| Workflow                    | temporal      | ✅         | 
+| Service Type                | Service                   | Supported |
+|-----------------------------|---------------------------|-----------|
+| Change Data Capture         | debezium                  | ✅         |
+| Database                    | cassandra                 | ✅         |
+| Database                    | cockroachdb               | ✅         |
+| Database                    | elasticsearch             | ✅         |
+| Database                    | mariadb                   | ✅         |
+| Database                    | mongodb                   | ✅         |
+| Database                    | mssql                     | ✅         |
+| Database                    | mysql                     | ✅         |
+| Database                    | neo4j                     | ✅         |
+| Database                    | opensearch                | ✅         |
+| Database                    | postgres                  | ✅         |
+| Database                    | spanner                   | ✅         |
+| Database                    | sqlite                    | ✅         |
+| Data Catalog                | amundsen                  | ✅         |
+| Data Catalog                | datahub                   | ✅         |
+| Data Catalog                | marquez                   | ✅         |
+| Data Catalog                | polaris                   | ✅         |
+| Data Catalog                | unitycatalog              | ✅         |
+| Data Catalog                | openmetadata              | ❌         |
+| Distributed Coordination    | zookeeper                 | ✅         |
+| Distributed Data Processing | flink                     | ✅         |
+| HTTP                        | httpbin                   | ✅         |
+| Identity Management         | keycloak                  | ✅         |
+| Job Orchestrator            | airflow                   | ✅         |
+| Job Orchestrator            | dagster                   | ✅         |
+| Job Orchestrator            | mage-ai                   | ✅         |
+| Job Orchestrator            | prefect                   | ✅         |
+| Messaging                   | activemq                  | ✅         |
+| Messaging                   | kafka                     | ✅         |
+| Messaging                   | rabbitmq                  | ✅         |
+| Messaging                   | solace                    | ✅         |
+| Notebook                    | jupyter                   | ✅         |
+| Object Storage              | minio                     | ✅         |
+| Query Engine                | duckdb                    | ✅         |
+| Query Engine                | flight-sql                | ✅         |
+| Query Engine                | presto                    | ✅         |
+| Query Engine                | trino                     | ✅         |
+| Real-time OLAP              | clickhouse                | ✅         |
+| Real-time OLAP              | doris                     | ✅         |
+| Real-time OLAP              | druid                     | ✅         |
+| Real-time OLAP              | pinot                     | ✅         |
+| Schema Registry             | confluent-schema-registry | ✅         |
+| Test Data Management        | data-caterer              | ✅         |
+| Workflow                    | maestro                   | ✅         | 
+| Workflow                    | temporal                  | ✅         | 
 

data/confluent-schema-registry/env/docker.env

@@ -0,0 +1,11 @@
+SCHEMA_REGISTRY_HOST_NAME=schema-registry
+SCHEMA_REGISTRY_KAFKASTORE_SECURITY_PROTOCOL=PLAINTEXT
+SCHEMA_REGISTRY_KAFKASTORE_BOOTSTRAP_SERVERS=kafka:29092
+
+# Uncomment to customize the Schema Registry kafka store connection
+# ZOOKEEPER_SASL_ENABLED=false
+# KAFKA_OPTS=-Xms1g -Xmx1g
+# SCHEMA_REGISTRY_JMX_OPTS=-Dcom.sun.management.jmxremote -Dcom.sun.management.jmxremote.authenticate=false -Dcom.sun.management.jmxremote.ssl=false
+
+# Uncomment to use schema registry < v5.4.0
+# SCHEMA_REGISTRY_KAFKASTORE_CONNECTION_URL=zookeeper:2181

data/datahub-actions/env/docker.env

@@ -0,0 +1,38 @@
+DATAHUB_GMS_PROTOCOL=http
+DATAHUB_GMS_HOST=datahub-gms
+DATAHUB_GMS_PORT=8080
+
+KAFKA_BOOTSTRAP_SERVER=broker:29092
+SCHEMA_REGISTRY_URL=http://schema-registry:8081
+# SCHEMA_REGISTRY_URL=http://datahub-gms:8080/schema-registry/api/
+METADATA_AUDIT_EVENT_NAME=MetadataAuditEvent_v4
+METADATA_CHANGE_LOG_VERSIONED_TOPIC_NAME=MetadataChangeLog_Versioned_v1
+
+# System Auth --
+DATAHUB_SYSTEM_CLIENT_ID=__datahub_system
+DATAHUB_SYSTEM_CLIENT_SECRET=JohnSnowKnowsNothing
+
+# Kafka Authentication
+KAFKA_PROPERTIES_SECURITY_PROTOCOL=PLAINTEXT
+
+# Uncomment the following if your Kafka deployment requires SSL.
+# KAFKA_PROPERTIES_SSL_KEYSTORE_LOCATION=/mnt/certs/keystore
+# KAFKA_PROPERTIES_SSL_TRUSTSTORE_LOCATION=/mnt/certs/truststore
+# KAFKA_PROPERTIES_SSL_KEYSTORE_PASSWORD=keystore_password
+# KAFKA_PROPERTIES_SSL_KEY_PASSWORD=keystore_password
+# KAFKA_PROPERTIES_SSL_TRUSTSTORE_PASSWORD=truststore_password
+
+# The following env vars are meant to be passed through from the Host System
+# to configure the Slack and Teams Actions
+# _ENABLED flags need to be set to "true" case sensitive for the action to be enabled
+DATAHUB_ACTIONS_SLACK_ENABLED
+DATAHUB_ACTIONS_SLACK_DATAHUB_BASE_URL
+DATAHUB_ACTIONS_SLACK_BOT_TOKEN
+DATAHUB_ACTIONS_SLACK_SIGNING_SECRET
+DATAHUB_ACTIONS_SLACK_CHANNEL
+DATAHUB_ACTIONS_SLACK_SUPPRESS_SYSTEM_ACTIVITY
+
+DATAHUB_ACTIONS_TEAMS_ENABLED
+DATAHUB_ACTIONS_TEAMS_DATAHUB_BASE_URL
+DATAHUB_ACTIONS_TEAMS_WEBHOOK_URL
+DATAHUB_ACTIONS_TEAMS_SUPPRESS_SYSTEM_ACTIVITY

data/datahub-frontend/env/docker.env

@@ -0,0 +1,71 @@
+DATAHUB_GMS_HOST=datahub-gms
+DATAHUB_GMS_PORT=8080
+DATAHUB_SECRET=YouKnowNothing
+DATAHUB_APP_VERSION=1.0
+DATAHUB_PLAY_MEM_BUFFER_SIZE=10MB
+JAVA_OPTS=-Xms512m -Xmx512m -Dhttp.port=9002 -Dconfig.file=datahub-frontend/conf/application.conf -Djava.security.auth.login.config=datahub-frontend/conf/jaas.conf -Dlogback.configurationFile=datahub-frontend/conf/logback.xml -Dlogback.debug=false -Dpidfile.path=/dev/null
+
+# Uncomment and set these to support SSL connection to GMS
+# NOTE: Currently GMS itself does not offer SSL support, these settings are intended for when there is a proxy in front
+#       of GMS that handles SSL, such as an EC2 Load Balancer.
+#DATAHUB_GMS_USE_SSL=true
+#DATAHUB_GMS_SSL_PROTOCOL=
+
+# Uncomment and set custom SSL truststore settings
+# SSL_TRUSTSTORE_FILE=datahub-frontend/conf/truststore.jks
+# SSL_TRUSTSTORE_TYPE=jks
+# SSL_TRUSTSTORE_PASSWORD=MyTruststorePassword
+
+# Uncomment to enable Metadata Service Authentication
+# METADATA_SERVICE_AUTH_ENABLED=true
+
+# Uncomment & populate these configs to enable OIDC SSO in React application.
+# Required OIDC configs
+# AUTH_OIDC_ENABLED=true
+# AUTH_OIDC_CLIENT_ID=1030786188615-rr9ics9gl8n4acngj9opqbf2mruflqpr.apps.googleusercontent.com
+# AUTH_OIDC_CLIENT_SECRET=acEdaGcnfd7KxvsXRFDD7FNF
+# AUTH_OIDC_DISCOVERY_URI=https://accounts.google.com/.well-known/openid-configuration
+# AUTH_OIDC_BASE_URL=http://localhost:9001
+# Optional OIDC configs
+# AUTH_OIDC_USER_NAME_CLAIM=email
+# AUTH_OIDC_USER_NAME_CLAIM_REGEX=([^@]+)
+# AUTH_OIDC_SCOPE=
+# Optional Provisioning Configs
+# AUTH_OIDC_JIT_PROVISIONING_ENABLED=true
+# AUTH_OIDC_PRE_PROVISIONING_REQUIRED=false
+# AUTH_OIDC_EXTRACT_GROUPS_ENABLED=false
+# AUTH_OIDC_GROUPS_CLAIM=groups
+
+# Uncomment to disable JAAS username / password authentication (enabled by default)
+# AUTH_JAAS_ENABLED=false
+
+# Uncomment to disable persistence of client-side analytics events
+# DATAHUB_ANALYTICS_ENABLED=false
+
+# Required Kafka Producer Configs
+KAFKA_BOOTSTRAP_SERVER=kafka:29092
+DATAHUB_TRACKING_TOPIC=DataHubUsageEvent_v1
+
+# Required Elastic Client Configuration (Analytics)
+ELASTIC_CLIENT_HOST=elasticsearch
+ELASTIC_CLIENT_PORT=9200
+
+# Optional Elastic Client Configurations
+# ELASTIC_CLIENT_THREAD_COUNT=2
+# ELASTIC_CLIENT_CONNECTION_REQUEST_TIMEOUT=50
+
+# To support SSL connections to Elastic, uncomment and set the following
+# ELASTIC_CLIENT_USE_SSL=true
+# ELASTIC_CLIENT_SSL_PROTOCOL=TLSv1.2
+# ELASTIC_CLIENT_SSL_SECURE_RANDOM_IMPLEMENTATION=
+# ELASTIC_CLIENT_SSL_TRUST_STORE_FILE=
+# ELASTIC_CLIENT_SSL_TRUST_STORE_TYPE=
+# ELASTIC_CLIENT_SSL_TRUST_STORE_PASSWORD=
+# ELASTIC_CLIENT_SSL_KEY_STORE_FILE=
+# ELASTIC_CLIENT_SSL_KEY_STORE_TYPE=
+# ELASTIC_CLIENT_SSL_KEY_STORE_PASSWORD=
+
+# To use simple username/password authentication to Elasticsearch over HTTPS
+# set ELASTIC_CLIENT_USE_SSL=true and uncomment:
+# ELASTIC_CLIENT_USERNAME=
+# ELASTIC_CLIENT_PASSWORD=

data/datahub-gms/env/docker.env

@@ -0,0 +1,55 @@
+DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID=generic-duhe-consumer-job-client-gms
+EBEAN_DATASOURCE_USERNAME=datahub
+EBEAN_DATASOURCE_PASSWORD=datahub
+EBEAN_DATASOURCE_HOST=mysql:3306
+EBEAN_DATASOURCE_URL=jdbc:mysql://mysql:3306/datahub?verifyServerCertificate=false&useSSL=true&useUnicode=yes&characterEncoding=UTF-8
+EBEAN_DATASOURCE_DRIVER=com.mysql.jdbc.Driver
+KAFKA_BOOTSTRAP_SERVER=kafka:29092
+KAFKA_SCHEMAREGISTRY_URL=http://schema-registry:8081
+# KAFKA_SCHEMAREGISTRY_URL=http://datahub-gms:8080/schema-registry/api/
+ELASTICSEARCH_HOST=elasticsearch
+ELASTICSEARCH_PORT=9200
+ELASTICSEARCH_INDEX_BUILDER_SETTINGS_REINDEX=true
+ELASTICSEARCH_INDEX_BUILDER_MAPPINGS_REINDEX=true
+ES_BULK_REFRESH_POLICY=WAIT_UNTIL
+GRAPH_SERVICE_DIFF_MODE_ENABLED=true
+GRAPH_SERVICE_IMPL=elasticsearch
+JAVA_OPTS=-Xms1g -Xmx1g
+ENTITY_REGISTRY_CONFIG_PATH=/datahub/datahub-gms/resources/entity-registry.yml
+
+MAE_CONSUMER_ENABLED=true
+MCE_CONSUMER_ENABLED=true
+PE_CONSUMER_ENABLED=true
+UI_INGESTION_ENABLED=true
+ENTITY_SERVICE_ENABLE_RETENTION=true
+
+ELASTIC_ID_HASH_ALGO=MD5
+
+# Uncomment to disable persistence of client-side analytics events
+# DATAHUB_ANALYTICS_ENABLED=false
+
+# Uncomment to configure kafka topic names
+# Make sure these names are consistent across the whole deployment
+# METADATA_AUDIT_EVENT_NAME=MetadataAuditEvent_v4
+# METADATA_CHANGE_EVENT_NAME=MetadataChangeEvent_v4
+# FAILED_METADATA_CHANGE_EVENT_NAME=FailedMetadataChangeEvent_v4
+
+# Uncomment and set these to support SSL connection to Elasticsearch
+# ELASTICSEARCH_USE_SSL=true
+# ELASTICSEARCH_SSL_PROTOCOL=TLSv1.2
+# ELASTICSEARCH_SSL_SECURE_RANDOM_IMPL=
+# ELASTICSEARCH_SSL_TRUSTSTORE_FILE=
+# ELASTICSEARCH_SSL_TRUSTSTORE_TYPE=
+# ELASTICSEARCH_SSL_TRUSTSTORE_PASSWORD=
+# ELASTICSEARCH_SSL_KEYSTORE_FILE=
+# ELASTICSEARCH_SSL_KEYSTORE_TYPE=
+# ELASTICSEARCH_SSL_KEYSTORE_PASSWORD=
+
+# To use simple username/password authentication to Elasticsearch over HTTPS
+# set ELASTICSEARCH_USE_SSL=true and uncomment:
+# ELASTICSEARCH_USERNAME=
+# ELASTICSEARCH_PASSWORD=
+
+# Uncomment to run a one-time upgrade to migrate legacy default browse path format to latest format
+# More details can be found at https://datahubproject.io/docs/advanced/browse-paths-upgrade
+# UPGRADE_DEFAULT_BROWSE_PATHS_ENABLED=true

data/datahub-upgrade/env/docker-without-neo4j.env

@@ -0,0 +1,55 @@
+DATAHUB_UPGRADE_HISTORY_KAFKA_CONSUMER_GROUP_ID=generic-duhe-consumer-job-client-gms
+EBEAN_DATASOURCE_USERNAME=datahub
+EBEAN_DATASOURCE_PASSWORD=datahub
+EBEAN_DATASOURCE_HOST=mysql:3306
+EBEAN_DATASOURCE_URL=jdbc:mysql://mysql:3306/datahub?verifyServerCertificate=false&useSSL=true&useUnicode=yes&characterEncoding=UTF-8
+EBEAN_DATASOURCE_DRIVER=com.mysql.jdbc.Driver
+KAFKA_BOOTSTRAP_SERVER=kafka:29092
+KAFKA_SCHEMAREGISTRY_URL=http://schema-registry:8081
+# KAFKA_SCHEMAREGISTRY_URL=http://datahub-gms:8080/schema-registry/api/
+ELASTICSEARCH_HOST=elasticsearch
+ELASTICSEARCH_PORT=9200
+ELASTICSEARCH_INDEX_BUILDER_SETTINGS_REINDEX=true
+ELASTICSEARCH_INDEX_BUILDER_MAPPINGS_REINDEX=true
+ES_BULK_REFRESH_POLICY=WAIT_UNTIL
+GRAPH_SERVICE_DIFF_MODE_ENABLED=true
+GRAPH_SERVICE_IMPL=elasticsearch
+JAVA_OPTS=-Xms1g -Xmx1g
+ENTITY_REGISTRY_CONFIG_PATH=/datahub/datahub-gms/resources/entity-registry.yml
+
+MAE_CONSUMER_ENABLED=true
+MCE_CONSUMER_ENABLED=true
+PE_CONSUMER_ENABLED=true
+UI_INGESTION_ENABLED=true
+ENTITY_SERVICE_ENABLE_RETENTION=true
+
+ELASTIC_ID_HASH_ALGO=MD5
+
+# Uncomment to disable persistence of client-side analytics events
+# DATAHUB_ANALYTICS_ENABLED=false
+
+# Uncomment to configure kafka topic names
+# Make sure these names are consistent across the whole deployment
+# METADATA_AUDIT_EVENT_NAME=MetadataAuditEvent_v4
+# METADATA_CHANGE_EVENT_NAME=MetadataChangeEvent_v4
+# FAILED_METADATA_CHANGE_EVENT_NAME=FailedMetadataChangeEvent_v4
+
+# Uncomment and set these to support SSL connection to Elasticsearch
+# ELASTICSEARCH_USE_SSL=true
+# ELASTICSEARCH_SSL_PROTOCOL=TLSv1.2
+# ELASTICSEARCH_SSL_SECURE_RANDOM_IMPL=
+# ELASTICSEARCH_SSL_TRUSTSTORE_FILE=
+# ELASTICSEARCH_SSL_TRUSTSTORE_TYPE=
+# ELASTICSEARCH_SSL_TRUSTSTORE_PASSWORD=
+# ELASTICSEARCH_SSL_KEYSTORE_FILE=
+# ELASTICSEARCH_SSL_KEYSTORE_TYPE=
+# ELASTICSEARCH_SSL_KEYSTORE_PASSWORD=
+
+# To use simple username/password authentication to Elasticsearch over HTTPS
+# set ELASTICSEARCH_USE_SSL=true and uncomment:
+# ELASTICSEARCH_USERNAME=
+# ELASTICSEARCH_PASSWORD=
+
+# Uncomment to run a one-time upgrade to migrate legacy default browse path format to latest format
+# More details can be found at https://datahubproject.io/docs/advanced/browse-paths-upgrade
+# UPGRADE_DEFAULT_BROWSE_PATHS_ENABLED=true

data/mysql/data/datahub.sql

@@ -0,0 +1,43 @@
+-- create datahub database
+CREATE DATABASE IF NOT EXISTS `datahub` CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;
+USE `datahub`;
+
+-- create metadata aspect table
+create table if not exists metadata_aspect_v2
+(
+    urn            varchar(500) not null,
+    aspect         varchar(200) not null,
+    version        bigint(20) not null,
+    metadata       longtext     not null,
+    systemmetadata longtext,
+    createdon      datetime(6)  not null,
+    createdby      varchar(255) not null,
+    createdfor     varchar(255),
+    constraint pk_metadata_aspect_v2 primary key (urn, aspect, version),
+    INDEX          timeIndex(createdon)
+) CHARACTER SET utf8mb4 COLLATE utf8mb4_bin;
+
+-- create default records for datahub user if not exists
+DROP TABLE if exists temp_metadata_aspect_v2;
+CREATE TABLE temp_metadata_aspect_v2 LIKE metadata_aspect_v2;
+INSERT INTO temp_metadata_aspect_v2 (urn, aspect, version, metadata, createdon, createdby)
+VALUES ('urn:li:corpuser:datahub',
+        'corpUserInfo',
+        0,
+        '{"displayName":"Data Hub","active":true,"fullName":"Data Hub","email":"[email protected]"}',
+        now(),
+        'urn:li:corpuser:__datahub_system'),
+       ('urn:li:corpuser:datahub',
+        'corpUserEditableInfo',
+        0,
+        '{"skills":[],"teams":[],"pictureLink":"https://raw.githubusercontent.com/datahub-project/datahub/master/datahub-web-react/src/images/default_avatar.png"}',
+        now(),
+        'urn:li:corpuser:__datahub_system');
+-- only add default records if metadata_aspect is empty
+INSERT INTO metadata_aspect_v2
+SELECT *
+FROM temp_metadata_aspect_v2
+WHERE NOT EXISTS (SELECT * from metadata_aspect_v2);
+DROP TABLE temp_metadata_aspect_v2;
+
+DROP TABLE IF EXISTS metadata_index;