Load data into a column-based time partitioning table

Load data into a table that uses column-based time partitioning.

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"
	"time"

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

// importPartitionedTable demonstrates specifing time partitioning for a BigQuery table when loading
// CSV data from Cloud Storage.
func importPartitionedTable(projectID, destDatasetID, destTableID 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-by-date.csv")
	gcsRef.SkipLeadingRows = 1
	gcsRef.Schema = bigquery.Schema{
		{Name: "name", Type: bigquery.StringFieldType},
		{Name: "post_abbr", Type: bigquery.StringFieldType},
		{Name: "date", Type: bigquery.DateFieldType},
	}
	loader := client.Dataset(destDatasetID).Table(destTableID).LoaderFrom(gcsRef)
	loader.TimePartitioning = &bigquery.TimePartitioning{
		Field:      "date",
		Expiration: 90 * 24 * time.Hour,
	}
	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.JobId;
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;
import com.google.cloud.bigquery.TimePartitioning;
import java.time.Duration;
import java.time.temporal.ChronoUnit;
import java.util.UUID;

public class LoadPartitionedTable {

  public static void main(String[] args) throws Exception {
    // TODO(developer): Replace these variables before running the sample.
    String datasetName = "MY_DATASET_NAME";
    String tableName = "MY_TABLE_NAME";
    String sourceUri = "/path/to/file.csv";
    loadPartitionedTable(datasetName, tableName, sourceUri);
  }

  public static void loadPartitionedTable(String datasetName, String tableName, String sourceUri)
      throws Exception {
    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);

      Schema schema =
          Schema.of(
              Field.of("name", StandardSQLTypeName.STRING),
              Field.of("post_abbr", StandardSQLTypeName.STRING),
              Field.of("date", StandardSQLTypeName.DATE));

      // Configure time partitioning. For full list of options, see:
      // https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#TimePartitioning
      TimePartitioning partitioning =
          TimePartitioning.newBuilder(TimePartitioning.Type.DAY)
              .setField("date")
              .setExpirationMs(Duration.of(90, ChronoUnit.DAYS).toMillis())
              .build();

      LoadJobConfiguration loadJobConfig =
          LoadJobConfiguration.builder(tableId, sourceUri)
              .setFormatOptions(FormatOptions.csv())
              .setSchema(schema)
              .setTimePartitioning(partitioning)
              .build();

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

      // Load data from a GCS parquet file into the table
      // Blocks until this load table job completes its execution, either failing or succeeding.
      Job completedJob = loadJob.waitFor();

      // Check for errors
      if (completedJob == null) {
        throw new Exception("Job not executed since it no longer exists.");
      } else if (completedJob.getStatus().getError() != null) {
        // You can also look at queryJob.getStatus().getExecutionErrors() for all
        // errors, not just the latest one.
        throw new Exception(
            "BigQuery was unable to load into the table due to an error: \n"
                + loadJob.getStatus().getError());
      }
      System.out.println("Data successfully loaded into time partitioned table during load job");
    } catch (BigQueryException | InterruptedException e) {
      System.out.println(
          "Data not loaded into time partitioned table during load job \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 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-by-date.csv';

async function loadTablePartitioned() {
  // Load data into a table that uses column-based time partitioning.

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

  // Configure the load job. For full list of options, see:
  // https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad
  const partitionConfig = {
    type: 'DAY',
    expirationMs: '7776000000', // 90 days
    field: 'date',
  };

  const metadata = {
    sourceFormat: 'CSV',
    skipLeadingRows: 1,
    schema: {
      fields: [
        {name: 'name', type: 'STRING'},
        {name: 'post_abbr', type: 'STRING'},
        {name: 'date', type: 'DATE'},
      ],
    },
    location: 'US',
    timePartitioning: partitionConfig,
  };

  // 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;
  }
}

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"),
        bigquery.SchemaField("date", "DATE"),
    ],
    skip_leading_rows=1,
    time_partitioning=bigquery.TimePartitioning(
        type_=bigquery.TimePartitioningType.DAY,
        field="date",  # Name of the column to use for partitioning.
        expiration_ms=7776000000,  # 90 days.
    ),
)
uri = "gs://cloud-samples-data/bigquery/us-states/us-states-by-date.csv"

load_job = client.load_table_from_uri(
    uri, table_id, job_config=job_config
)  # Make an API request.

load_job.result()  # Wait for the job to complete.

table = client.get_table(table_id)
print("Loaded {} rows to table {}".format(table.num_rows, table_id))