Quickstart: Query with the BigQuery API

Create a simple app with BigQuery.

Documentation pages that include this code sample

Code Sample

C#

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


using System;
using Google.Cloud.BigQuery.V2;

namespace GoogleCloudSamples
{
    public class Program
    {
        public static void Main(string[] args)
        {
            string projectId = "YOUR-PROJECT-ID";
            var client = BigQueryClient.Create(projectId);
            string query = @"SELECT
                CONCAT(
                    'https://stackoverflow.com/questions/',
                    CAST(id as STRING)) as url, view_count
                FROM `bigquery-public-data.stackoverflow.posts_questions`
                WHERE tags like '%google-bigquery%'
                ORDER BY view_count DESC
                LIMIT 10";
            var result = client.ExecuteQuery(query, parameters: null);
            Console.Write("\nQuery Results:\n------------\n");
            foreach (var row in result)
            {
                Console.WriteLine($"{row["url"]}: {row["view_count"]} views");
            }
        }
    }
}

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"
	"log"
	"os"

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


func main() {
	projectID := os.Getenv("GOOGLE_CLOUD_PROJECT")
	if projectID == "" {
		fmt.Println("GOOGLE_CLOUD_PROJECT environment variable must be set.")
		os.Exit(1)
	}

	ctx := context.Background()

	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		log.Fatalf("bigquery.NewClient: %v", err)
	}
	defer client.Close()

	rows, err := query(ctx, client)
	if err != nil {
		log.Fatal(err)
	}
	if err := printResults(os.Stdout, rows); err != nil {
		log.Fatal(err)
	}
}

// query returns a row iterator suitable for reading query results.
func query(ctx context.Context, client *bigquery.Client) (*bigquery.RowIterator, error) {

	query := client.Query(
		`SELECT
			CONCAT(
				'https://stackoverflow.com/questions/',
				CAST(id as STRING)) as url,
			view_count
		FROM ` + "`bigquery-public-data.stackoverflow.posts_questions`" + `
		WHERE tags like '%google-bigquery%'
		ORDER BY view_count DESC
		LIMIT 10;`)
	return query.Read(ctx)
}

type StackOverflowRow struct {
	URL       string `bigquery:"url"`
	ViewCount int64  `bigquery:"view_count"`
}

// printResults prints results from a query to the Stack Overflow public dataset.
func printResults(w io.Writer, iter *bigquery.RowIterator) error {
	for {
		var row StackOverflowRow
		err := iter.Next(&row)
		if err == iterator.Done {
			return nil
		}
		if err != nil {
			return fmt.Errorf("error iterating through results: %v", err)
		}

		fmt.Fprintf(w, "url: %s views: %d\n", row.URL, row.ViewCount)
	}
}

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.BigQueryOptions;
import com.google.cloud.bigquery.FieldValueList;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobId;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.QueryJobConfiguration;
import com.google.cloud.bigquery.TableResult;
import java.util.UUID;


public class SimpleApp {
  public static void main(String... args) throws Exception {
    BigQuery bigquery = BigQueryOptions.getDefaultInstance().getService();
    QueryJobConfiguration queryConfig =
        QueryJobConfiguration.newBuilder(
                "SELECT commit, author, repo_name "
                    + "FROM `bigquery-public-data.github_repos.commits` "
                    + "WHERE subject like '%bigquery%' "
                    + "ORDER BY subject DESC LIMIT 10")
            // Use standard SQL syntax for queries.
            // See: https://cloud.google.com/bigquery/sql-reference/
            .setUseLegacySql(false)
            .build();

    // Create a job ID so that we can safely retry.
    JobId jobId = JobId.of(UUID.randomUUID().toString());
    Job queryJob = bigquery.create(JobInfo.newBuilder(queryConfig).setJobId(jobId).build());

    // Wait for the query to complete.
    queryJob = queryJob.waitFor();

    // Check for errors
    if (queryJob == null) {
      throw new RuntimeException("Job no longer exists");
    } else if (queryJob.getStatus().getError() != null) {
      // You can also look at queryJob.getStatus().getExecutionErrors() for all
      // errors, not just the latest one.
      throw new RuntimeException(queryJob.getStatus().getError().toString());
    }

    // Get the results.
    TableResult result = queryJob.getQueryResults();

    // Print all pages of the results.
    for (FieldValueList row : result.iterateAll()) {
      // String type
      String commit = row.get("commit").getStringValue();
      // Record type
      FieldValueList author = row.get("author").getRecordValue();
      String name = author.get("name").getStringValue();
      String email = author.get("email").getStringValue();
      // String Repeated type
      String repoName = row.get("repo_name").getRecordValue().get(0).getStringValue();
      System.out.printf(
          "Repo name: %s Author name: %s email: %s commit: %s\n", repoName, name, email, commit);
    }
  }
}

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');

async function queryStackOverflow() {
  // Queries a public Stack Overflow dataset.

  // Create a client
  const bigqueryClient = new BigQuery();

  // The SQL query to run
  const sqlQuery = `SELECT
    CONCAT(
      'https://stackoverflow.com/questions/',
      CAST(id as STRING)) as url,
    view_count
    FROM \`bigquery-public-data.stackoverflow.posts_questions\`
    WHERE tags like '%google-bigquery%'
    ORDER BY view_count DESC
    LIMIT 10`;

  const options = {
    query: sqlQuery,
    // Location must match that of the dataset(s) referenced in the query.
    location: 'US',
  };

  // Run the query
  const [rows] = await bigqueryClient.query(options);

  console.log('Query Results:');
  rows.forEach(row => {
    const url = row['url'];
    const viewCount = row['view_count'];
    console.log(`url: ${url}, ${viewCount} views`);
  });
}
queryStackOverflow();

PHP

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

require __DIR__ . '/vendor/autoload.php';

use Google\Cloud\BigQuery\BigQueryClient;


// get the project ID as the first argument
if (2 != count($argv)) {
    die("Usage: php stackoverflow.php YOUR_PROJECT_ID\n");
}

$projectId = $argv[1];

$bigQuery = new BigQueryClient([
    'projectId' => $projectId,
]);
$query = <<<ENDSQL
SELECT
  CONCAT(
    'https://stackoverflow.com/questions/',
    CAST(id as STRING)) as url,
  view_count
FROM `bigquery-public-data.stackoverflow.posts_questions`
WHERE tags like '%google-bigquery%'
ORDER BY view_count DESC
LIMIT 10;
ENDSQL;
$queryJobConfig = $bigQuery->query($query);
$queryResults = $bigQuery->runQuery($queryJobConfig);

if ($queryResults->isComplete()) {
    $i = 0;
    $rows = $queryResults->rows();
    foreach ($rows as $row) {
        printf('--- Row %s ---' . PHP_EOL, ++$i);
        printf('url: %s, %s views' . PHP_EOL, $row['url'], $row['view_count']);
    }
    printf('Found %s row(s)' . PHP_EOL, $i);
} else {
    throw new Exception('The query failed to complete');
}

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



def query_stackoverflow():
    client = bigquery.Client()
    query_job = client.query(
        """
        SELECT
          CONCAT(
            'https://stackoverflow.com/questions/',
            CAST(id as STRING)) as url,
          view_count
        FROM `bigquery-public-data.stackoverflow.posts_questions`
        WHERE tags like '%google-bigquery%'
        ORDER BY view_count DESC
        LIMIT 10"""
    )

    results = query_job.result()  # Waits for job to complete.

    for row in results:
        print("{} : {} views".format(row.url, row.view_count))


if __name__ == "__main__":
    query_stackoverflow()