Examples with SpannerChangeStreamsToBigQueryOptions com.google.cloud.teleport.v2.options.SpannerChangeStreamsToBigQueryOptions used on opensource projects

Example 1 with SpannerChangeStreamsToBigQueryOptions

use of com.google.cloud.teleport.v2.options.SpannerChangeStreamsToBigQueryOptions in project DataflowTemplates by GoogleCloudPlatform.

the class SpannerChangeStreamsToBigQuery method run.

/**
 * Runs the pipeline with the supplied options.
 *
 * @param options The execution parameters to the pipeline.
 * @return The result of the pipeline execution.
 */
public static PipelineResult run(SpannerChangeStreamsToBigQueryOptions options) {
    setOptions(options);
    validateOptions(options);
    /**
     * Stages: 1) Read {@link DataChangeRecord} from change stream. 2) Create {@link
     * FailsafeElement} of {@link Mod} JSON and merge from: - {@link DataChangeRecord}. - GCS Dead
     * letter queue. 3) Convert {@link Mod} JSON into {@link TableRow} by reading from Spanner at
     * commit timestamp. 4) Append {@link TableRow} to BigQuery. 5) Write Failures from 2), 3) and
     * 4) to GCS dead letter queue.
     */
    Pipeline pipeline = Pipeline.create(options);
    DeadLetterQueueManager dlqManager = buildDlqManager(options);
    String spannerProjectId = getSpannerProjectId(options);
    String dlqDirectory = dlqManager.getRetryDlqDirectoryWithDateTime();
    String tempDlqDirectory = dlqManager.getRetryDlqDirectory() + "tmp/";
    // Retrieve and parse the startTimestamp and endTimestamp.
    Timestamp startTimestamp = options.getStartTimestamp().isEmpty() ? Timestamp.now() : Timestamp.parseTimestamp(options.getStartTimestamp());
    Timestamp endTimestamp = options.getEndTimestamp().isEmpty() ? Timestamp.MAX_VALUE : Timestamp.parseTimestamp(options.getEndTimestamp());
    SpannerConfig spannerConfig = SpannerConfig.create().withHost(ValueProvider.StaticValueProvider.of(options.getSpannerHost())).withProjectId(spannerProjectId).withInstanceId(options.getSpannerInstanceId()).withDatabaseId(options.getSpannerDatabase()).withRpcPriority(options.getSpannerRpcPriority());
    SpannerIO.ReadChangeStream readChangeStream = SpannerIO.readChangeStream().withSpannerConfig(spannerConfig).withMetadataInstance(options.getSpannerMetadataInstanceId()).withMetadataDatabase(options.getSpannerMetadataDatabase()).withChangeStreamName(options.getSpannerChangeStreamName()).withInclusiveStartAt(startTimestamp).withInclusiveEndAt(endTimestamp).withRpcPriority(options.getSpannerRpcPriority());
    String spannerMetadataTableName = options.getSpannerMetadataTableName();
    if (spannerMetadataTableName != null) {
        readChangeStream = readChangeStream.withMetadataTable(spannerMetadataTableName);
    }
    PCollection<DataChangeRecord> dataChangeRecord = pipeline.apply("Read from Spanner Change Streams", readChangeStream).apply("Reshuffle DataChangeRecord", Reshuffle.viaRandomKey());
    PCollection<FailsafeElement<String, String>> sourceFailsafeModJson = dataChangeRecord.apply("DataChangeRecord To Mod JSON", ParDo.of(new DataChangeRecordToModJsonFn())).apply("Wrap Mod JSON In FailsafeElement", ParDo.of(new DoFn<String, FailsafeElement<String, String>>() {

        @ProcessElement
        public void process(@Element String input, OutputReceiver<FailsafeElement<String, String>> receiver) {
            receiver.output(FailsafeElement.of(input, input));
        }
    })).setCoder(FAILSAFE_ELEMENT_CODER);
    PCollectionTuple dlqModJson = dlqManager.getReconsumerDataTransform(pipeline.apply(dlqManager.dlqReconsumer(options.getDlqRetryMinutes())));
    PCollection<FailsafeElement<String, String>> retryableDlqFailsafeModJson = dlqModJson.get(DeadLetterQueueManager.RETRYABLE_ERRORS).setCoder(FAILSAFE_ELEMENT_CODER);
    PCollection<FailsafeElement<String, String>> failsafeModJson = PCollectionList.of(sourceFailsafeModJson).and(retryableDlqFailsafeModJson).apply("Merge Source And DLQ Mod JSON", Flatten.pCollections());
    ImmutableSet.Builder<String> ignoreFieldsBuilder = ImmutableSet.builder();
    for (String ignoreField : options.getIgnoreFields().split(",")) {
        ignoreFieldsBuilder.add(ignoreField);
    }
    ImmutableSet<String> ignoreFields = ignoreFieldsBuilder.build();
    FailsafeModJsonToTableRowTransformer.FailsafeModJsonToTableRowOptions failsafeModJsonToTableRowOptions = FailsafeModJsonToTableRowTransformer.FailsafeModJsonToTableRowOptions.builder().setSpannerConfig(spannerConfig).setSpannerChangeStream(options.getSpannerChangeStreamName()).setIgnoreFields(ignoreFields).setCoder(FAILSAFE_ELEMENT_CODER).build();
    FailsafeModJsonToTableRowTransformer.FailsafeModJsonToTableRow failsafeModJsonToTableRow = new FailsafeModJsonToTableRowTransformer.FailsafeModJsonToTableRow(failsafeModJsonToTableRowOptions);
    PCollectionTuple tableRowTuple = failsafeModJson.apply("Mod JSON To TableRow", failsafeModJsonToTableRow);
    BigQueryDynamicDestinations.BigQueryDynamicDestinationsOptions bigQueryDynamicDestinationsOptions = BigQueryDynamicDestinations.BigQueryDynamicDestinationsOptions.builder().setSpannerConfig(spannerConfig).setChangeStreamName(options.getSpannerChangeStreamName()).setIgnoreFields(ignoreFields).setBigQueryProject(getBigQueryProjectId(options)).setBigQueryDataset(options.getBigQueryDataset()).setBigQueryTableTemplate(options.getBigQueryChangelogTableNameTemplate()).build();
    WriteResult writeResult = tableRowTuple.get(failsafeModJsonToTableRow.transformOut).apply("Write To BigQuery", BigQueryIO.<TableRow>write().to(BigQueryDynamicDestinations.of(bigQueryDynamicDestinationsOptions)).withFormatFunction(element -> removeIntermediateMetadataFields(element)).withFormatRecordOnFailureFunction(element -> element).withCreateDisposition(CreateDisposition.CREATE_IF_NEEDED).withWriteDisposition(Write.WriteDisposition.WRITE_APPEND).withExtendedErrorInfo().withMethod(Write.Method.STREAMING_INSERTS).withFailedInsertRetryPolicy(InsertRetryPolicy.retryTransientErrors()));
    PCollection<String> transformDlqJson = tableRowTuple.get(failsafeModJsonToTableRow.transformDeadLetterOut).apply("Failed Mod JSON During Table Row Transformation", MapElements.via(new StringDeadLetterQueueSanitizer()));
    PCollection<String> bqWriteDlqJson = writeResult.getFailedInsertsWithErr().apply("Failed Mod JSON During BigQuery Writes", MapElements.via(new BigQueryDeadLetterQueueSanitizer()));
    PCollectionList.of(transformDlqJson).and(bqWriteDlqJson).apply("Merge Failed Mod JSON From Transform And BigQuery", Flatten.pCollections()).apply("Write Failed Mod JSON To DLQ", DLQWriteTransform.WriteDLQ.newBuilder().withDlqDirectory(dlqDirectory).withTmpDirectory(tempDlqDirectory).setIncludePaneInfo(true).build());
    PCollection<FailsafeElement<String, String>> nonRetryableDlqModJsonFailsafe = dlqModJson.get(DeadLetterQueueManager.PERMANENT_ERRORS).setCoder(FAILSAFE_ELEMENT_CODER);
    nonRetryableDlqModJsonFailsafe.apply("Write Mod JSON With Non-retryable Error To DLQ", MapElements.via(new StringDeadLetterQueueSanitizer())).setCoder(StringUtf8Coder.of()).apply(DLQWriteTransform.WriteDLQ.newBuilder().withDlqDirectory(dlqManager.getSevereDlqDirectoryWithDateTime()).withTmpDirectory(dlqManager.getSevereDlqDirectory() + "tmp/").setIncludePaneInfo(true).build());
    return pipeline.run();
}

Example 2 with SpannerChangeStreamsToBigQueryOptions

use of com.google.cloud.teleport.v2.options.SpannerChangeStreamsToBigQueryOptions in project DataflowTemplates by GoogleCloudPlatform.

the class SpannerChangeStreamsToBigQuery method main.

/**
 * Main entry point for executing the pipeline.
 *
 * @param args The command-line arguments to the pipeline.
 */
public static void main(String[] args) {
    LOG.info("Starting to replicate change records from Spanner change streams to BigQuery");
    SpannerChangeStreamsToBigQueryOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().as(SpannerChangeStreamsToBigQueryOptions.class);
    run(options);
}