From ad35ab94d2102c6ff897f3ea75e723f6de56f83b Mon Sep 17 00:00:00 2001 From: Ayush Shah Date: Mon, 18 Oct 2021 17:39:46 +0000 Subject: [PATCH] GitBook: [#199] Added Bigquery Usage Documentation --- docs/SUMMARY.md | 1 + .../connectors/database-services/README.md | 4 + .../database-services/bigquery-usage.md | 125 ++++++++++++++++++ 3 files changed, 130 insertions(+) create mode 100644 docs/install/metadata-ingestion/connectors/database-services/bigquery-usage.md diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md index 3ed90cbbf7e..90436a0b1de 100644 --- a/docs/SUMMARY.md +++ b/docs/SUMMARY.md @@ -75,6 +75,7 @@ * [Database Services](install/metadata-ingestion/connectors/database-services/README.md) * [Athena](install/metadata-ingestion/connectors/database-services/athena.md) * [BigQuery](install/metadata-ingestion/connectors/database-services/bigquery.md) + * [BigQuery Usage](install/metadata-ingestion/connectors/database-services/bigquery-usage.md) * [ElasticSearch](install/metadata-ingestion/connectors/database-services/elastic-search.md) * [MsSQL](install/metadata-ingestion/connectors/database-services/mssql.md) * [MySQL](install/metadata-ingestion/connectors/database-services/mysql.md) diff --git a/docs/install/metadata-ingestion/connectors/database-services/README.md b/docs/install/metadata-ingestion/connectors/database-services/README.md index 9fef2ec989a..a6d47b48c65 100644 --- a/docs/install/metadata-ingestion/connectors/database-services/README.md +++ b/docs/install/metadata-ingestion/connectors/database-services/README.md @@ -10,6 +10,10 @@ OpenMetadata supports connectors to some popular data sources. We will continue [bigquery.md](bigquery.md) {% endcontent-ref %} +{% content-ref url="bigquery-usage.md" %} +[bigquery-usage.md](bigquery-usage.md) +{% endcontent-ref %} + {% content-ref url="elastic-search.md" %} [elastic-search.md](elastic-search.md) {% endcontent-ref %} diff --git a/docs/install/metadata-ingestion/connectors/database-services/bigquery-usage.md b/docs/install/metadata-ingestion/connectors/database-services/bigquery-usage.md new file mode 100644 index 00000000000..0df45f420e0 --- /dev/null +++ b/docs/install/metadata-ingestion/connectors/database-services/bigquery-usage.md @@ -0,0 +1,125 @@ +--- +description: This guide will help install BigQuery Usage connector and run manually +--- + +# BigQuery Usage + +{% hint style="info" %} +**Prerequisites** + +OpenMetadata is built using Java, DropWizard, Jetty, and MySQL. + +1. Python 3.7 or above +{% endhint %} + +### Install from PyPI + +{% tabs %} +{% tab title="Install Using PyPI" %} +```bash +pip install 'openmetadata-ingestion[bigquery-usage]' +``` +{% endtab %} +{% endtabs %} + +## Run Manually + +```bash +metadata ingest -c ./examples/workflows/bigquery_usage.json +``` + +### Configuration + +{% code title="bigquery-creds.json (boilerplate)" %} +```javascript +{ + "type": "service_account", + "project_id": "project_id", + "private_key_id": "private_key_id", + "private_key": "", + "client_email": "gcpuser@project_id.iam.gserviceaccount.com", + "client_id": "", + "auth_uri": "https://accounts.google.com/o/oauth2/auth", + "token_uri": "https://oauth2.googleapis.com/token", + "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs", + "client_x509_cert_url": "" +} +``` +{% endcode %} + +{% code title="bigquery_usage.json" %} +```javascript +{ + "source": { + "type": "bigquery-usage", + "config": { + "project_id": "project_id", + "host_port": "https://bigquery.googleapis.com", + "username": "gcpuser@project_id.iam.gserviceaccount.com", + "service_name": "gcp_bigquery", + "duration": 2, + "options": { + "credentials_path": "examples/creds/bigquery-cred.json" + } + } + }, +``` +{% endcode %} + +1. **username** - pass the Bigquery username. +2. **password** - the password for the Bigquery username. +3. **service_name** - Service Name for this Bigquery cluster. If you added the Bigquery cluster through OpenMetadata UI, make sure the service name matches the same. +4. **filter_pattern** - It contains includes, excludes options to choose which pattern of datasets you want to ingest into OpenMetadata. +5. **database -** Database name from where data is to be fetched. + +### Publish to OpenMetadata + +Below is the configuration to publish Bigquery data into the OpenMetadata service. + +Add optionally`query-parser` processor, `table-usage` stage and `metadata-usage` bulk_sink along with `metadata-server` config + +{% code title="bigquery_usage.json" %} +```javascript +{ + "source": { + "type": "bigquery-usage", + "config": { + "project_id": "project_id", + "host_port": "https://bigquery.googleapis.com", + "username": "gcpuser@project_id.iam.gserviceaccount.com", + "service_name": "gcp_bigquery", + "duration": 2, + "options": { + "credentials_path": "examples/creds/bigquery-cred.json" + } + } + }, + "processor": { + "type": "query-parser", + "config": { + "filter": "" + } + }, + "stage": { + "type": "table-usage", + "config": { + "filename": "/tmp/bigquery_usage" + } + }, + "bulk_sink": { + "type": "metadata-usage", + "config": { + "filename": "/tmp/bigquery_usage" + } + }, + "metadata_server": { + "type": "metadata-server", + "config": { + "api_endpoint": "http://localhost:8585/api", + "auth_provider_type": "no-auth" + } + } +} + +``` +{% endcode %}