A trivial Cloud Dataflow pipeline that reads from Spanner and writes to BigQuery

SpannerToBigQuery.java

package org.polleyg;

import com.google.api.services.bigquery.model.TableFieldSchema;
import com.google.api.services.bigquery.model.TableRow;
import com.google.api.services.bigquery.model.TableSchema;
import com.google.cloud.spanner.Struct;
import org.apache.beam.runners.dataflow.options.DataflowPipelineOptions;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO;
import org.apache.beam.sdk.io.gcp.spanner.SpannerIO;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.values.PCollection;

import java.util.ArrayList;
import java.util.List;

import static org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.Write.CreateDisposition.CREATE_IF_NEEDED;
import static org.apache.beam.sdk.io.gcp.bigquery.BigQueryIO.Write.WriteDisposition.WRITE_TRUNCATE;

/**
 * Do some randomness
 */
public class TemplatePipeline {
    public static void main(String[] args) {
        PipelineOptionsFactory.register(DataflowPipelineOptions.class);
        DataflowPipelineOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().as(DataflowPipelineOptions.class);
        Pipeline pipeline = Pipeline.create(options);
        PCollection<Struct> records = pipeline.apply("read_from_spanner",
                SpannerIO.read()
                        .withInstanceId("spanner-to-dataflow-to-bq")
                        .withDatabaseId("the-dude")
                        .withQuery("SELECT * FROM Singers"));
        records.apply("convert-2-bq-row", ParDo.of(new DoFn<Struct, TableRow>() {
            @ProcessElement
            public void processElement(ProcessContext c) throws Exception {
                TableRow row = new TableRow();
                row.set("id", c.element().getLong("SingerId"));
                row.set("first", c.element().getString("FirstName"));
                row.set("last", c.element().getString("LastName"));
                c.output(row);
            }
        })).apply("write-to-bq", BigQueryIO.writeTableRows()
                .to(String.format("%s:spanner_to_bigquery.singers", options.getProject()))
                .withCreateDisposition(CREATE_IF_NEEDED)
                .withWriteDisposition(WRITE_TRUNCATE)
                .withSchema(getTableSchema()));
        pipeline.run();
    }

    private static TableSchema getTableSchema() {
        List<TableFieldSchema> fields = new ArrayList<>();
        fields.add(new TableFieldSchema().setName("id").setType("INTEGER"));
        fields.add(new TableFieldSchema().setName("first").setType("STRING"));
        fields.add(new TableFieldSchema().setName("last").setType("STRING"));
        return new TableSchema().setFields(fields);
    }
}