BigQuery から Dataflow に読み込む

コレクションでコンテンツを整理 必要に応じて、コンテンツの保存と分類を行います。

import com.google.common.collect.ImmutableMap;
import java.util.List;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.managed.Managed;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.Row;
import org.apache.beam.sdk.values.TypeDescriptors;

public class BigQueryReadWithProjectionAndFiltering {
  public static void main(String[] args) {
    // Parse the pipeline options passed into the application. Example:
    //   --projectId=$PROJECT_ID --datasetName=$DATASET_NAME --tableName=$TABLE_NAME
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptionsFactory.register(ExamplePipelineOptions.class);
    ExamplePipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation()
        .as(ExamplePipelineOptions.class);

    String tableSpec = String.format("%s:%s.%s",
        options.getProjectId(),
        options.getDatasetName(),
        options.getTableName());

    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("table", tableSpec)
        .put("row_restriction", "age > 18")
        .put("fields", List.of("user_name", "age"))
        .build();

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        .apply(Managed.read(Managed.BIGQUERY).withConfig(config)).getSinglePCollection()
        .apply(MapElements
            .into(TypeDescriptors.strings())
            // Access individual fields in the row.
            .via((Row row) -> {
              String output = String.format("Name: %s, Age: %s%n",
                  row.getString("user_name"),
                  row.getInt64("age"));
              System.out.println(output);
              return output;
            }));
    pipeline.run().waitUntilFinish();
  }
}

import com.google.common.collect.ImmutableMap;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.managed.Managed;
import org.apache.beam.sdk.options.PipelineOptions;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.Row;
import org.apache.beam.sdk.values.TypeDescriptors;

public class BigQueryReadFromQuery {
  public static void main(String[] args) {
    // The SQL query to run inside BigQuery.
    final String queryString =
        "SELECT repo_name as repo, COUNT(*) as count "
            + "FROM `bigquery-public-data.github_repos.sample_commits` "
            + "GROUP BY repo_name";

    // Parse the pipeline options passed into the application.
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation().create();

    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("query", queryString)
        .build();

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        .apply(Managed.read(Managed.BIGQUERY).withConfig(config)).getSinglePCollection()
        .apply(MapElements
            .into(TypeDescriptors.strings())
            // Access individual fields in the row.
            .via((Row row) -> {
              String output = String.format("Repo: %s, commits: %d%n",
                  row.getString("repo"),
                  row.getInt64("count"));
              System.out.println(output);
              return output;
            }));
    pipeline.run().waitUntilFinish();
  }
}

import org.apache.avro.generic.GenericRecord;
import org.apache.avro.util.Utf8;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.coders.DefaultCoder;
import org.apache.beam.sdk.extensions.avro.coders.AvroCoder;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.TypedRead;
import org.apache.beam.sdk.io.gcp.bigquery.SchemaAndRecord;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.transforms.SerializableFunction;
import org.apache.beam.sdk.values.TypeDescriptor;

public class BigQueryReadAvro {

  // A custom datatype to hold a record from the source table.
  @DefaultCoder(AvroCoder.class)
  public static class MyData {
    public String name;
    public Long age;

    // Function to convert Avro records to MyData instances.
    public static class FromSchemaAndRecord
            implements SerializableFunction<SchemaAndRecord, MyData> {
      @Override public MyData apply(SchemaAndRecord elem) {
        MyData data = new MyData();
        GenericRecord record = elem.getRecord();
        data.name = ((Utf8) record.get("user_name")).toString();
        data.age = (Long) record.get("age");
        return data;
      }
    }
  }

  public static void main(String[] args) {
    // Parse the pipeline options passed into the application. Example:
    //   --projectId=$PROJECT_ID --datasetName=$DATASET_NAME --tableName=$TABLE_NAME
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptionsFactory.register(ExamplePipelineOptions.class);
    ExamplePipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation()
        .as(ExamplePipelineOptions.class);

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        // Read table data into Avro records, using an application-defined parsing function.
        .apply(BigQueryIO.read(new MyData.FromSchemaAndRecord())
            .from(String.format("%s:%s.%s",
                options.getProjectId(),
                options.getDatasetName(),
                options.getTableName()))
            .withMethod(TypedRead.Method.DIRECT_READ))
        // The output from the previous step is a PCollection<MyData>.
        .apply(MapElements
            .into(TypeDescriptor.of(MyData.class))
            .via((MyData x) -> {
              System.out.printf("Name: %s, Age: %d%n", x.name, x.age);
              return x;
            }));
    pipeline.run().waitUntilFinish();
  }
}

import com.google.api.services.bigquery.model.TableRow;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.TypedRead.Method;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.TypeDescriptor;

public class BiqQueryReadTableRows {
  public static void main(String[] args) {
    // Parse the pipeline options passed into the application. Example:
    //   --projectId=$PROJECT_ID --datasetName=$DATASET_NAME --tableName=$TABLE_NAME
    // For more information, see https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    PipelineOptionsFactory.register(ExamplePipelineOptions.class);
    ExamplePipelineOptions options = PipelineOptionsFactory.fromArgs(args)
        .withValidation()
        .as(ExamplePipelineOptions.class);

    // Create a pipeline and apply transforms.
    Pipeline pipeline = Pipeline.create(options);
    pipeline
        // Read table data into TableRow objects.
        .apply(BigQueryIO.readTableRows()
            .from(String.format("%s:%s.%s",
                options.getProjectId(),
                options.getDatasetName(),
                options.getTableName()))
            .withMethod(Method.DIRECT_READ)
        )
        // The output from the previous step is a PCollection<TableRow>.
        .apply(MapElements
            .into(TypeDescriptor.of(TableRow.class))
            // Use TableRow to access individual fields in the row.
            .via((TableRow row) -> {
              var name = (String) row.get("user_name");
              var age = (String) row.get("age");
              System.out.printf("Name: %s, Age: %s%n", name, age);
              return row;
            }));
    pipeline.run().waitUntilFinish();
  }
}