Load: JSON

Loads JSON file from Google Cloud Storage, using an explicit schema.

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 Google.Apis.Bigquery.v2.Data;
using Google.Cloud.BigQuery.V2;
using System;

public class BigQueryLoadTableGcsJson
{
    public void LoadTableGcsJson(
        string projectId = "your-project-id",
        string datasetId = "your_dataset_id"
    )
    {
        BigQueryClient client = BigQueryClient.Create(projectId);
        var gcsURI = "gs://cloud-samples-data/bigquery/us-states/us-states.json";
        var dataset = client.GetDataset(datasetId);
        var schema = new TableSchemaBuilder {
            { "name", BigQueryDbType.String },
            { "post_abbr", BigQueryDbType.String }
        }.Build();
        TableReference destinationTableRef = dataset.GetTableReference(
            tableId: "us_states");
        // Create job configuration
        var jobOptions = new CreateLoadJobOptions()
        {
            SourceFormat = FileFormat.NewlineDelimitedJson
        };
        // Create and run job
        BigQueryJob loadJob = client.CreateLoadJob(
            sourceUri: gcsURI, destination: destinationTableRef,
            schema: schema, options: jobOptions);
        loadJob = loadJob.PollUntilCompleted().ThrowOnAnyError();  // Waits for the job to complete.
        // Display the number of rows uploaded
        BigQueryTable table = client.GetTable(destinationTableRef);
        Console.WriteLine(
            $"Loaded {table.Resource.NumRows} rows to {table.FullyQualifiedId}");
    }
}

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"

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

// importJSONExplicitSchema demonstrates loading newline-delimited JSON data from Cloud Storage
// into a BigQuery table and providing an explicit schema for the data.
func importJSONExplicitSchema(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: %v", err)
	}
	defer client.Close()

	gcsRef := bigquery.NewGCSReference("gs://cloud-samples-data/bigquery/us-states/us-states.json")
	gcsRef.SourceFormat = bigquery.JSON
	gcsRef.Schema = bigquery.Schema{
		{Name: "name", Type: bigquery.StringFieldType},
		{Name: "post_abbr", Type: bigquery.StringFieldType},
	}
	loader := client.Dataset(datasetID).Table(tableID).LoaderFrom(gcsRef)
	loader.WriteDisposition = bigquery.WriteEmpty

	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: %v", status.Err())
	}
	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.Field;
import com.google.cloud.bigquery.FormatOptions;
import com.google.cloud.bigquery.Job;
import com.google.cloud.bigquery.JobInfo;
import com.google.cloud.bigquery.LoadJobConfiguration;
import com.google.cloud.bigquery.Schema;
import com.google.cloud.bigquery.StandardSQLTypeName;
import com.google.cloud.bigquery.TableId;

// Sample to load JSON data from Cloud Storage into a new BigQuery table
public class LoadJsonFromGcs {

  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.json";
    Schema schema =
        Schema.of(
            Field.of("name", StandardSQLTypeName.STRING),
            Field.of("post_abbr", StandardSQLTypeName.STRING));
    loadJsonFromGcs(datasetName, tableName, sourceUri, schema);
  }

  public static void loadJsonFromGcs(
      String datasetName, String tableName, String sourceUri, Schema schema) {
    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);
      LoadJobConfiguration loadConfig =
          LoadJobConfiguration.newBuilder(tableId, sourceUri)
              .setFormatOptions(FormatOptions.json())
              .setSchema(schema)
              .build();

      // Load data from a GCS JSON 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()) {
        System.out.println("Json 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

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 libraries
const {BigQuery} = require('@google-cloud/bigquery');
const {Storage} = require('@google-cloud/storage');

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

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

async function loadJSONFromGCS() {
  // Imports a GCS file into a table with manually defined schema.

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

  // Configure the load job. For full list of options, see:
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad
  const metadata = {
    sourceFormat: 'NEWLINE_DELIMITED_JSON',
    schema: {
      fields: [
        {name: 'name', type: 'STRING'},
        {name: 'post_abbr', type: 'STRING'},
      ],
    },
    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.`);

  // Check the job's status for errors
  const errors = job.status.errors;
  if (errors && errors.length > 0) {
    throw errors;
  }
}

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.

use Google\Cloud\BigQuery\BigQueryClient;
use Google\Cloud\Core\ExponentialBackoff;

/** Uncomment and populate these variables in your code */
// $projectId  = 'The Google project ID';
// $datasetId  = 'The BigQuery dataset ID';
// $tableId    = 'us_states';

// 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.json';
$schema = [
    'fields' => [
        ['name' => 'name', 'type' => 'string'],
        ['name' => 'post_abbr', 'type' => 'string']
    ]
];
$loadConfig = $table->loadFromStorage($gcsUri)->schema($schema)->sourceFormat('NEWLINE_DELIMITED_JSON');
$job = $table->runJob($loadConfig);
// poll the job until it is complete
$backoff = new ExponentialBackoff(10);
$backoff->execute(function () use ($job) {
    print('Waiting for job to complete' . PHP_EOL);
    $job->reload();
    if (!$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

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 table to create.
# table_id = "your-project.your_dataset.your_table_name"

job_config = bigquery.LoadJobConfig(
    schema=[
        bigquery.SchemaField("name", "STRING"),
        bigquery.SchemaField("post_abbr", "STRING"),
    ],
    source_format=bigquery.SourceFormat.NEWLINE_DELIMITED_JSON,
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"

load_job = client.load_table_from_uri(
    uri,
    table_id,
    location="US",  # Must match the destination dataset location.
    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))