Insertion en flux continu de types de données complexes

Insérez des données de différents types compatibles avec BigQuery dans une table.

Exemple de code

Go

Avant d'essayer cet exemple, suivez les instructions de configuration pour Go du guide de démarrage rapide de BigQuery : Utiliser les bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Go.

Pour vous authentifier auprès de BigQuery, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez la page Configurer l'authentification pour les bibliothèques clientes.

import (
	"context"
	"fmt"
	"time"

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

// ComplexType represents a complex row item
type ComplexType struct {
	Name         string                 `bigquery:"name"`
	Age          int                    `bigquery:"age"`
	School       []byte                 `bigquery:"school"`
	Location     bigquery.NullGeography `bigquery:"location"`
	Measurements []float64              `bigquery:"measurements"`
	DatesTime    DatesTime              `bigquery:"datesTime"`
}

// DatesTime shows different date/time representation
type DatesTime struct {
	Day        civil.Date     `bigquery:"day"`
	FirstTime  civil.DateTime `bigquery:"firstTime"`
	SecondTime civil.Time     `bigquery:"secondTime"`
	ThirdTime  time.Time      `bigquery:"thirdTime"`
}

// insertingDataTypes demonstrates inserting data into a table using the streaming insert mechanism.
func insertingDataTypes(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()

	// Manually defining schema
	schema := bigquery.Schema{
		{Name: "name", Type: bigquery.StringFieldType},
		{Name: "age", Type: bigquery.IntegerFieldType},
		{Name: "school", Type: bigquery.BytesFieldType},
		{Name: "location", Type: bigquery.GeographyFieldType},
		{Name: "measurements", Type: bigquery.FloatFieldType, Repeated: true},
		{Name: "datesTime", Type: bigquery.RecordFieldType, Schema: bigquery.Schema{
			{Name: "day", Type: bigquery.DateFieldType},
			{Name: "firstTime", Type: bigquery.DateTimeFieldType},
			{Name: "secondTime", Type: bigquery.TimeFieldType},
			{Name: "thirdTime", Type: bigquery.TimestampFieldType},
		}},
	}
	// Infer schema from struct
	// schema, err := bigquery.InferSchema(ComplexType{})

	table := client.Dataset(datasetID).Table(tableID)
	err = table.Create(ctx, &bigquery.TableMetadata{
		Schema: schema,
	})
	if err != nil {
		return fmt.Errorf("table.Create: %w", err)
	}
	day, err := civil.ParseDate("2019-01-12")
	if err != nil {
		return fmt.Errorf("civil.ParseDate: %w", err)
	}
	firstTime, err := civil.ParseDateTime("2019-02-17T11:24:00.000")
	if err != nil {
		return fmt.Errorf("civil.ParseDateTime: %w", err)
	}
	secondTime, err := civil.ParseTime("14:00:00")
	if err != nil {
		return fmt.Errorf("civil.ParseTime: %w", err)
	}
	thirdTime, err := time.Parse(time.RFC3339Nano, "2020-04-27T18:07:25.356Z")
	if err != nil {
		return fmt.Errorf("time.Parse: %w", err)
	}
	row := &ComplexType{
		Name:         "Tom",
		Age:          30,
		School:       []byte("Test University"),
		Location:     bigquery.NullGeography{GeographyVal: "POINT(1 2)", Valid: true},
		Measurements: []float64{50.05, 100.5},
		DatesTime: DatesTime{
			Day:        day,
			FirstTime:  firstTime,
			SecondTime: secondTime,
			ThirdTime:  thirdTime,
		},
	}
	rows := []*ComplexType{row}
	// Uncomment to simulate insert errors.
	// This example row is missing required fields.
	// badRow := &ComplexType{
	// 	Name: "John",
	// 	Age:  24,
	// }
	// rows = append(rows, badRow)

	inserter := table.Inserter()
	err = inserter.Put(ctx, rows)
	if err != nil {
		if multiErr, ok := err.(bigquery.PutMultiError); ok {
			for _, putErr := range multiErr {
				fmt.Printf("failed to insert row %d with err: %v \n", putErr.RowIndex, putErr.Error())
			}
		}
		return err
	}
	return nil
}

Java

Avant d'essayer cet exemple, suivez les instructions de configuration pour Java du guide de démarrage rapide de BigQuery à l'aide de bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Java.

Pour vous authentifier auprès de BigQuery, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez la page Configurer l'authentification pour les bibliothèques clientes.

import com.google.cloud.bigquery.BigQuery;
import com.google.cloud.bigquery.BigQueryError;
import com.google.cloud.bigquery.BigQueryException;
import com.google.cloud.bigquery.BigQueryOptions;
import com.google.cloud.bigquery.Field;
import com.google.cloud.bigquery.InsertAllRequest;
import com.google.cloud.bigquery.InsertAllResponse;
import com.google.cloud.bigquery.Schema;
import com.google.cloud.bigquery.StandardSQLTypeName;
import com.google.cloud.bigquery.StandardTableDefinition;
import com.google.cloud.bigquery.TableDefinition;
import com.google.cloud.bigquery.TableId;
import com.google.cloud.bigquery.TableInfo;
import java.util.Base64;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

// Sample to insert data types in a table
public class InsertingDataTypes {

  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";
    insertingDataTypes(datasetName, tableName);
  }

  public static void insertingDataTypes(String datasetName, String tableName) {
    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();

      // Inserting data types
      Field name = Field.of("name", StandardSQLTypeName.STRING);
      Field age = Field.of("age", StandardSQLTypeName.INT64);
      Field school = Field.of("school", StandardSQLTypeName.BYTES);
      Field location = Field.of("location", StandardSQLTypeName.GEOGRAPHY);
      Field measurements =
          Field.newBuilder("measurements", StandardSQLTypeName.FLOAT64)
              .setMode(Field.Mode.REPEATED)
              .build();
      Field day = Field.of("day", StandardSQLTypeName.DATE);
      Field firstTime = Field.of("firstTime", StandardSQLTypeName.DATETIME);
      Field secondTime = Field.of("secondTime", StandardSQLTypeName.TIME);
      Field thirdTime = Field.of("thirdTime", StandardSQLTypeName.TIMESTAMP);
      Field datesTime =
          Field.of("datesTime", StandardSQLTypeName.STRUCT, day, firstTime, secondTime, thirdTime);
      Schema schema = Schema.of(name, age, school, location, measurements, datesTime);

      TableId tableId = TableId.of(datasetName, tableName);
      TableDefinition tableDefinition = StandardTableDefinition.of(schema);
      TableInfo tableInfo = TableInfo.newBuilder(tableId, tableDefinition).build();

      bigquery.create(tableInfo);

      // Inserting Sample data
      Map<String, Object> datesTimeContent = new HashMap<>();
      datesTimeContent.put("day", "2019-1-12");
      datesTimeContent.put("firstTime", "2019-02-17 11:24:00.000");
      datesTimeContent.put("secondTime", "14:00:00");
      datesTimeContent.put("thirdTime", "2020-04-27T18:07:25.356Z");

      Map<String, Object> rowContent = new HashMap<>();
      rowContent.put("name", "Tom");
      rowContent.put("age", 30);
      rowContent.put("school", Base64.getEncoder().encodeToString("Test University".getBytes()));
      rowContent.put("location", "POINT(1 2)");
      rowContent.put("measurements", new Float[] {50.05f, 100.5f});
      rowContent.put("datesTime", datesTimeContent);

      InsertAllResponse response =
          bigquery.insertAll(InsertAllRequest.newBuilder(tableId).addRow(rowContent).build());

      if (response.hasErrors()) {
        // If any of the insertions failed, this lets you inspect the errors
        for (Map.Entry<Long, List<BigQueryError>> entry : response.getInsertErrors().entrySet()) {
          System.out.println("Response error: \n" + entry.getValue());
        }
      }
      System.out.println("Rows successfully inserted into table");
    } catch (BigQueryException e) {
      System.out.println("Insert operation not performed \n" + e.toString());
    }
  }
}

Ruby

Avant d'essayer cet exemple, suivez les instructions de configuration pour Ruby du guide de démarrage rapide de BigQuery à l'aide de bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API BigQuery pour Ruby.

Pour vous authentifier auprès de BigQuery, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez la page Configurer l'authentification pour les bibliothèques clientes.

require "google/cloud/bigquery"
require "base64"

##
# Inserts a row with various data types into a table.
#
# @param dataset_id [String] The ID of the dataset to create the table in.
# @param table_id   [String] The ID of the table to create.
def inserting_data_types dataset_id, table_id
  bigquery = Google::Cloud::Bigquery.new
  dataset = bigquery.dataset dataset_id
  table = dataset.table table_id

  # Create the table if it doesn't exist.
  unless table
    dataset.create_table table_id do |t|
      t.string "name"
      t.integer "age"
      t.bytes "school"
      t.geography "location"
      t.float "measurements", mode: :repeated
      t.record "datesTime" do |s|
        s.date "day"
        s.datetime "firstTime"
        s.time "secondTime"
        s.timestamp "thirdTime"
      end
    end
    table = dataset.table table_id
  end

  dates_time_content = {
    "day"        => "2019-1-12",
    "firstTime"  => "2019-02-17 11:24:00.000",
    "secondTime" => "14:00:00",
    "thirdTime"  => "2020-04-27T18:07:25.356Z"
  }

  row_content = {
    "name"         => "Tom",
    "age"          => 30,
    "school"       => Base64.strict_encode64("Test University"),
    "location"     => "POINT(1 2)",
    "measurements" => [50.05, 100.5],
    "datesTime"    => dates_time_content
  }

  response = table.insert [row_content]

  if response.success?
    puts "Rows successfully inserted into table"
  else
    puts "Insert operation not performed"
    response.insert_errors.each do |error|
      puts "Error: #{error.errors}"
    end
  end
end

Étape suivante

Pour rechercher et filtrer des exemples de code pour d'autres produits Google Cloud , consultez l'explorateur d'exemplesGoogle Cloud .