加载 CSV 文件并自动检测架构

加载 Cloud Storage 中的 CSV 文件并自动检测架构。

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：

使用架构自动检测功能

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。

import (
	"context"
	"fmt"

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

// importCSVAutodetectSchema demonstrates loading data from CSV data in Cloud Storage
// and using schema autodetection to identify the available columns.
func importCSVAutodetectSchema(projectID, datasetID, tableID string) error {
	// projectID := "my-project-id"
	// datasetID := "mydataset"
	// tableID := "mytable"
	ctx := context.Background()
	client, err := bigquery.NewClient(ctx, projectID)
	if err != nil {
		return fmt.Errorf("bigquery.NewClient: %w", err)
	}
	defer client.Close()

	gcsRef := bigquery.NewGCSReference("gs://cloud-samples-data/bigquery/us-states/us-states.csv")
	gcsRef.SourceFormat = bigquery.CSV
	gcsRef.AutoDetect = true
	gcsRef.SkipLeadingRows = 1
	loader := client.Dataset(datasetID).Table(tableID).LoaderFrom(gcsRef)

	job, err := loader.Run(ctx)
	if err != nil {
		return err
	}
	status, err := job.Wait(ctx)
	if err != nil {
		return err
	}

	if status.Err() != nil {
		return fmt.Errorf("job completed with error: %w", status.Err())
	}
	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。

在 GitHub 上查看反馈

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.CsvOptions;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.LoadJobConfiguration;
import com.google.cloud.bigquery.TableId;

// Sample to load CSV data with autodetect schema from Cloud Storage into a new BigQuery table
public class LoadCsvFromGcsAutodetect {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    String sourceUri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv";
    loadCsvFromGcsAutodetect(datasetName, tableName, sourceUri);
  }

  public static void loadCsvFromGcsAutodetect(
      String datasetName, String tableName, String sourceUri) {
    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();

      TableId tableId = TableId.of(datasetName, tableName);

      // Skip header row in the file.
      CsvOptions csvOptions = CsvOptions.newBuilder().setSkipLeadingRows(1).build();

      LoadJobConfiguration loadConfig =
          LoadJobConfiguration.newBuilder(tableId, sourceUri)
              .setFormatOptions(csvOptions)
              .setAutodetect(true)
              .build();

      // Load data from a GCS CSV file into the table
      Job job = bigquery.create(JobInfo.of(loadConfig));
      // Blocks until this load table job completes its execution, either failing or succeeding.
      job = job.waitFor();
      if (job.isDone() && job.getStatus().getError() == null) {
        System.out.println("CSV Autodetect from GCS successfully loaded in a table");
      } else {
        System.out.println(
            "BigQuery was unable to load into the table due to an error:"
                + job.getStatus().getError());
      }
    } catch (BigQueryException | InterruptedException e) {
      System.out.println("Column not added during load append \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。

在 GitHub 上查看反馈

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

// Instantiate clients
const bigquery = new BigQuery();
const storage = new Storage();

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

/**
 * This sample loads the CSV file at
 * https://storage.googleapis.com/cloud-samples-data/bigquery/us-states/us-states.csv
 *
 * TODO(developer): Replace the following lines with the path to your file
 */
const bucketName = 'cloud-samples-data';
const filename = 'bigquery/us-states/us-states.csv';

async function loadCSVFromGCSAutodetect() {
  // Imports a GCS file into a table with autodetected schema.

  // Configure the load job. For full list of options, see:
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad
  const metadata = {
    sourceFormat: 'CSV',
    skipLeadingRows: 1,
    autodetect: true,
    location: 'US',
  };

  // Load data from a Google Cloud Storage file into the table
  const [job] = await bigquery
    .dataset(datasetId)
    .table(tableId)
    .load(storage.bucket(bucketName).file(filename), metadata);
  // load() waits for the job to finish
  console.log(`Job ${job.id} completed.`);
}

PHP

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

在 GitHub 上查看反馈

use Google\Cloud\BigQuery\BigQueryClient;

/**
 * Imports data to the given table from csv file present in GCS by auto
 * detecting options and schema.
 *
 * @param string $projectId The project Id of your Google Cloud Project.
 * @param string $datasetId The BigQuery dataset ID.
 * @param string $tableId The BigQuery table ID.
 */
function import_from_storage_csv_autodetect(
    string $projectId,
    string $datasetId,
    string $tableId = 'us_states'
): void {
    // instantiate the bigquery table service
    $bigQuery = new BigQueryClient([
      'projectId' => $projectId,
    ]);
    $dataset = $bigQuery->dataset($datasetId);
    $table = $dataset->table($tableId);

    // create the import job
    $gcsUri = 'gs://cloud-samples-data/bigquery/us-states/us-states.csv';
    $loadConfig = $table->loadFromStorage($gcsUri)->autodetect(true)->skipLeadingRows(1);
    $job = $table->runJob($loadConfig);

    // check if the job is complete
    $job->reload();
    if (!$job->isComplete()) {
        throw new \Exception('Job has not yet completed', 500);
    }
    // check if the job has errors
    if (isset($job->info()['status']['errorResult'])) {
        $error = $job->info()['status']['errorResult']['message'];
        printf('Error running job: %s' . PHP_EOL, $error);
    } else {
        print('Data imported successfully' . PHP_EOL);
    }
}

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。

在 GitHub 上查看反馈

from google.cloud import bigquery

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

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

# Set the encryption key to use for the destination.
# TODO: Replace this key with a key you have created in KMS.
# kms_key_name = "projects/{}/locations/{}/keyRings/{}/cryptoKeys/{}".format(
#     "cloud-samples-tests", "us", "test", "test"
# )
job_config = bigquery.LoadJobConfig(
    autodetect=True,
    skip_leading_rows=1,
    # The source format defaults to CSV, so the line below is optional.
    source_format=bigquery.SourceFormat.CSV,
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.
load_job.result()  # Waits for the job to complete.
destination_table = client.get_table(table_id)
print("Loaded {} rows.".format(destination_table.num_rows))

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。