Read from a query

Use the BigQueryIO connector to read from a query result.

Explore further

For detailed documentation that includes this code sample, see the following:

• Read from BigQuery to Dataflow

Code sample

Java

To authenticate to Dataflow, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.api.services.bigquery.model.TableRow;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.TypedRead;
import org.apache.beam.sdk.options.PipelineOptions;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.TypeDescriptor;

public class BigQueryReadFromQuery {
  public static void main(String[] args) {
    // The SQL query to run inside BigQuery.
    final String queryString =
        "SELECT repo_name as repo, COUNT(*) as count "
            + "FROM `bigquery-public-data.github_repos.sample_commits` "
            + "GROUP BY repo_name";

    // Parse the pipeline options passed into the application.
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation().create();

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        // Read the query results into TableRow objects.
        .apply(BigQueryIO.readTableRows()
            .fromQuery(queryString)
            .usingStandardSql()
            .withMethod(TypedRead.Method.DIRECT_READ))
        // The output from the previous step is a PCollection<TableRow>.
        .apply(MapElements
            .into(TypeDescriptor.of(TableRow.class))
            .via((TableRow row) -> {
              System.out.printf("Repo: %s, commits: %s%n", row.get("repo"), row.get("count"));
              return row;
            }));
    pipeline.run().waitUntilFinish();
  }
}

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.