使用批量优先级运行查询

使用批量优先级运行查询作业。

深入探索

如需查看包含此代码示例的详细文档,请参阅以下内容:

代码示例

Go

试用此示例之前,请按照 BigQuery 快速入门:使用客户端库中的 Go 设置说明进行操作。 如需了解详情,请参阅 BigQuery Go API 参考文档

如需向 BigQuery 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为客户端库设置身份验证

import (
	"context"
	"fmt"
	"io"
	"time"

	"cloud.google.com/go/bigquery"
)

// queryBatch demonstrates issuing a query job using batch priority.
func queryBatch(w io.Writer, projectID, dstDatasetID, dstTableID string) error {
	// projectID := "my-project-id"
	// dstDatasetID := "mydataset"
	// dstTableID := "mytable"
	ctx := context.Background()
	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		return fmt.Errorf("bigquery.NewClient: %w", err)
	}
	defer client.Close()

	// Build an aggregate table.
	q := client.Query(`
		SELECT
  			corpus,
  			SUM(word_count) as total_words,
  			COUNT(1) as unique_words
		FROM ` + "`bigquery-public-data.samples.shakespeare`" + `
		GROUP BY corpus;`)
	q.Priority = bigquery.BatchPriority
	q.QueryConfig.Dst = client.Dataset(dstDatasetID).Table(dstTableID)

	// Start the job.
	job, err := q.Run(ctx)
	if err != nil {
		return err
	}
	// Job is started and will progress without interaction.
	// To simulate other work being done, sleep a few seconds.
	time.Sleep(5 * time.Second)
	status, err := job.Status(ctx)
	if err != nil {
		return err
	}

	state := "Unknown"
	switch status.State {
	case bigquery.Pending:
		state = "Pending"
	case bigquery.Running:
		state = "Running"
	case bigquery.Done:
		state = "Done"
	}
	// You can continue to monitor job progress until it reaches
	// the Done state by polling periodically.  In this example,
	// we print the latest status.
	fmt.Fprintf(w, "Job %s in Location %s currently in state: %s\n", job.ID(), job.Location(), state)

	return nil

}

Java

试用此示例之前,请按照 BigQuery 快速入门:使用客户端库中的 Java 设置说明进行操作。 如需了解详情,请参阅 BigQuery Java API 参考文档

如需向 BigQuery 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为客户端库设置身份验证

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.TableResult;

// Sample to query batch in a table
public class QueryBatch {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "MY_PROJECT_ID";
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    String query =
        "SELECT corpus"
            + " FROM `"
            + projectId
            + "."
            + datasetName
            + "."
            + tableName
            + " GROUP BY corpus;";
    queryBatch(query);
  }

  public static void queryBatch(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 =
          QueryJobConfiguration.newBuilder(query)
              // Run at batch priority, which won't count toward concurrent rate limit.
              .setPriority(QueryJobConfiguration.Priority.BATCH)
              .build();

      TableResult results = bigquery.query(queryConfig);

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

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

Node.js

试用此示例之前,请按照 BigQuery 快速入门:使用客户端库中的 Node.js 设置说明进行操作。 如需了解详情,请参阅 BigQuery Node.js API 参考文档

如需向 BigQuery 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为客户端库设置身份验证

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

async function queryBatch() {
  // Runs a query at batch priority.

  // Create query job configuration. For all options, see
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#jobconfigurationquery
  const queryJobConfig = {
    query: `SELECT corpus
            FROM \`bigquery-public-data.samples.shakespeare\` 
            LIMIT 10`,
    useLegacySql: false,
    priority: 'BATCH',
  };

  // Create job configuration. For all options, see
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#jobconfiguration
  const jobConfig = {
    // Specify a job configuration to set optional job resource properties.
    configuration: {
      query: queryJobConfig,
    },
  };

  // Make API request.
  const [job] = await bigquery.createJob(jobConfig);

  const jobId = job.metadata.id;
  const state = job.metadata.status.state;
  console.log(`Job ${jobId} is currently in state ${state}`);
}

Python

试用此示例之前,请按照 BigQuery 快速入门:使用客户端库中的 Python 设置说明进行操作。 如需了解详情,请参阅 BigQuery Python API 参考文档

如需向 BigQuery 进行身份验证,请设置应用默认凭据。 如需了解详情,请参阅为客户端库设置身份验证

from google.cloud import bigquery

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

job_config = bigquery.QueryJobConfig(
    # Run at batch priority, which won't count toward concurrent rate limit.
    priority=bigquery.QueryPriority.BATCH
)

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.

# Check on the progress by getting the job's updated state. Once the state
# is `DONE`, the results are ready.
query_job = typing.cast(
    "bigquery.QueryJob",
    client.get_job(
        query_job.job_id, location=query_job.location
    ),  # Make an API request.
)

print("Job {} is currently in state {}".format(query_job.job_id, query_job.state))

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例,请参阅 Google Cloud 示例浏览器