Enable large results

Query enables large result sets using legacy SQL.

Documentation pages that include this code sample

Code Sample

Go

Before trying this sample, follow the Go setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Go API reference documentation.

import (
	"context"
	"fmt"
	"io"

	"cloud.google.com/go/bigquery"
	"google.golang.org/api/iterator"
)

// queryLegacyLargeResults demonstrates issuing a legacy SQL query and writing a large result set
// into a destination table.
func queryLegacyLargeResults(w io.Writer, projectID, datasetID, tableID string) error {
	// projectID := "my-project-id"
	// datasetID := "destinationdataset"
	// tableID := "destinationtable"
	ctx := context.Background()
	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		return fmt.Errorf("bigquery.NewClient: %v", err)
	}
	defer client.Close()

	q := client.Query(
		"SELECT corpus FROM [bigquery-public-data:samples.shakespeare] GROUP BY corpus;")
	q.UseLegacySQL = true
	q.AllowLargeResults = true
	q.QueryConfig.Dst = client.Dataset(datasetID).Table(tableID)
	// Run the query and print results when the query job is completed.
	job, err := q.Run(ctx)
	if err != nil {
		return err
	}
	status, err := job.Wait(ctx)
	if err != nil {
		return err
	}
	if err := status.Err(); err != nil {
		return err
	}
	it, err := job.Read(ctx)
	for {
		var row []bigquery.Value
		err := it.Next(&row)
		if err == iterator.Done {
			break
		}
		if err != nil {
			return err
		}
		fmt.Fprintln(w, row)
	}
	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Java API reference documentation.

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TableResult;

// Sample to run query with large results and save the results to a table.
public class QueryLargeResults {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String destinationDataset = "MY_DESTINATION_DATASET_NAME";
    String destinationTable = "MY_DESTINATION_TABLE_NAME";
    String query = "SELECT corpus FROM [bigquery-public-data:samples.shakespeare] GROUP BY corpus;";
    queryLargeResults(destinationDataset, destinationTable, query);
  }

  public static void queryLargeResults(
      String destinationDataset, String destinationTable, String query) {
    try {
      // Initialize client that will be used to send requests. This client only needs to be created
      // once, and can be reused for multiple requests.
      BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();

      QueryJobConfiguration queryConfig =
          // To use legacy SQL syntax, set useLegacySql to true.
          QueryJobConfiguration.newBuilder(query)
              .setUseLegacySql(true)
              // Save the results of the query to a permanent table.
              .setDestinationTable(TableId.of(destinationDataset, destinationTable))
              // Allow results larger than the maximum response size.
              // If true, a destination table must be set.
              .setAllowLargeResults(true)
              .build();

      TableResult results = bigquery.query(queryConfig);

      results
          .iterateAll()
          .forEach(row -> row.forEach(val -> System.out.printf("%s,", val.toString())));

      System.out.println("Query large results performed successfully.");
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Query not performed \n" + e.toString());
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Node.js API reference documentation.

// Import the Google Cloud client library
const {BigQuery} = require('@google-cloud/bigquery');
const bigquery = new BigQuery();

async function queryLegacyLargeResults() {
  // Query enables large result sets.

  /**
   * TODO(developer): Uncomment the following lines before running the sample
   */
  // const projectId = "my_project"
  // const datasetId = "my_dataset";
  // const tableId = "my_table";

  const query =
    'SELECT word FROM [bigquery-public-data:samples.shakespeare] LIMIT 10;';

  // For all options, see https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs/query
  const options = {
    query: query,
    // Location must match that of the dataset(s) referenced
    // in the query and of the destination table.
    useLegacySql: true,
    allowLargeResult: true,
    destinationTable: {
      projectId: projectId,
      datasetId: datasetId,
      tableId: tableId,
    },
  };

  const [job] = await bigquery.createQueryJob(options);
  console.log(`Job ${job.id} started.`);

  // Wait for the query to finish
  const [rows] = await job.getQueryResults();

  // Print the results
  console.log('Rows:');
  rows.forEach(row => console.log(row));
}

Python

Before trying this sample, follow the Python setup instructions in the BigQuery Quickstart Using Client Libraries. For more information, see the BigQuery Python API reference documentation.

from google.cloud import bigquery

# Construct a BigQuery client object.
client = bigquery.Client()

# TODO(developer): Set table_id to the ID of the destination table.
# table_id = "your-project.your_dataset.your_table_name"

# Set the destination table and use_legacy_sql to True to use
# legacy SQL syntax.
job_config = bigquery.QueryJobConfig(
    allow_large_results=True, destination=table_id, use_legacy_sql=True
)

sql = """
    SELECT corpus
    FROM [bigquery-public-data:samples.shakespeare]
    GROUP BY corpus;
"""

# Start the query, passing in the extra configuration.
query_job = client.query(sql, job_config=job_config)  # Make an API request.
query_job.result()  # Wait for the job to complete.

print("Query results loaded to the table {}".format(table_id))