Examples with GoogleCloudDataplexV1Asset com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset used on opensource projects

Example 1 with GoogleCloudDataplexV1Asset

use of com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset in project DataflowTemplates by GoogleCloudPlatform.

the class DataplexFileFormatConversion method run.

/**
 * Runs the pipeline to completion with the specified options.
 *
 * @return The pipeline result.
 */
public static PipelineResult run(Pipeline pipeline, FileFormatConversionOptions options, DataplexClient dataplex, OutputPathProvider outputPathProvider) throws IOException {
    boolean isInputAsset = ASSET_PATTERN.matcher(options.getInputAssetOrEntitiesList()).matches();
    if (!isInputAsset && !ENTITIES_PATTERN.matcher(options.getInputAssetOrEntitiesList()).matches()) {
        throw new IllegalArgumentException("Either input asset or input entities list must be provided");
    }
    GoogleCloudDataplexV1Asset outputAsset = dataplex.getAsset(options.getOutputAsset());
    if (outputAsset == null || outputAsset.getResourceSpec() == null || !DataplexAssetResourceSpec.STORAGE_BUCKET.name().equals(outputAsset.getResourceSpec().getType()) || outputAsset.getResourceSpec().getName() == null) {
        throw new IllegalArgumentException("Output asset must be an existing asset with resource spec name being a GCS bucket and" + " resource spec type of " + DataplexAssetResourceSpec.STORAGE_BUCKET.name());
    }
    String outputBucket = outputAsset.getResourceSpec().getName();
    Predicate<String> inputFilesFilter;
    switch(options.getWriteDisposition()) {
        case OVERWRITE:
            inputFilesFilter = inputFilePath -> true;
            break;
        case FAIL:
            Set<String> outputFilePaths = getAllOutputFilePaths(outputBucket);
            inputFilesFilter = inputFilePath -> {
                if (outputFilePaths.contains(inputFilePathToOutputFilePath(outputPathProvider, inputFilePath, outputBucket, options.getOutputFileFormat()))) {
                    throw new WriteDispositionException(String.format("The file %s already exists in the output asset bucket: %s", inputFilePath, outputBucket));
                }
                return true;
            };
            break;
        case SKIP:
            outputFilePaths = getAllOutputFilePaths(outputBucket);
            inputFilesFilter = inputFilePath -> !outputFilePaths.contains(inputFilePathToOutputFilePath(outputPathProvider, inputFilePath, outputBucket, options.getOutputFileFormat()));
            break;
        default:
            throw new UnsupportedOperationException("Unsupported existing file behaviour: " + options.getWriteDisposition());
    }
    ImmutableList<GoogleCloudDataplexV1Entity> entities = isInputAsset ? dataplex.getCloudStorageEntities(options.getInputAssetOrEntitiesList()) : dataplex.getEntities(Splitter.on(',').trimResults().splitToList(options.getInputAssetOrEntitiesList()));
    boolean convertingFiles = false;
    for (GoogleCloudDataplexV1Entity entity : entities) {
        ImmutableList<GoogleCloudDataplexV1Partition> partitions = dataplex.getPartitions(entity.getName());
        if (partitions.isEmpty()) {
            String outputPath = outputPathProvider.outputPathFrom(entity.getDataPath(), outputBucket);
            Iterator<String> inputFilePaths = getFilesFromFilePattern(entityToFileSpec(entity)).filter(inputFilesFilter).iterator();
            convertingFiles = inputFilePaths.hasNext();
            inputFilePaths.forEachRemaining(inputFilePath -> pipeline.apply("Convert " + shortenDataplexName(entity.getName()), new ConvertFiles(entity, inputFilePath, options, outputPath)));
        } else {
            for (GoogleCloudDataplexV1Partition partition : partitions) {
                String outputPath = outputPathProvider.outputPathFrom(partition.getLocation(), outputBucket);
                Iterator<String> inputFilePaths = getFilesFromFilePattern(partitionToFileSpec(partition)).filter(inputFilesFilter).iterator();
                convertingFiles = inputFilePaths.hasNext();
                inputFilePaths.forEachRemaining(inputFilePath -> pipeline.apply("Convert " + shortenDataplexName(partition.getName()), new ConvertFiles(entity, inputFilePath, options, outputPath)));
            }
        }
    }
    if (!convertingFiles) {
        pipeline.apply("Nothing to convert", new NoopTransform());
    }
    return pipeline.run();
}

Example 2 with GoogleCloudDataplexV1Asset

use of com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset in project DataflowTemplates by GoogleCloudPlatform.

the class DataplexJdbcIngestion method main.

/**
 * Main entry point for pipeline execution.
 *
 * @param args Command line arguments to the pipeline.
 */
public static void main(String[] args) throws IOException {
    DataplexJdbcIngestionOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().as(DataplexJdbcIngestionOptions.class);
    Pipeline pipeline = Pipeline.create(options);
    DataplexClient dataplexClient = DefaultDataplexClient.withDefaultClient(options.getGcpCredential());
    String assetName = options.getOutputAsset();
    GoogleCloudDataplexV1Asset asset = resolveAsset(assetName, dataplexClient);
    DynamicDataSourceConfiguration dataSourceConfig = configDataSource(options);
    String assetType = asset.getResourceSpec().getType();
    if (DataplexAssetResourceSpec.BIGQUERY_DATASET.name().equals(assetType)) {
        buildBigQueryPipeline(pipeline, options, dataSourceConfig);
    } else if (DataplexAssetResourceSpec.STORAGE_BUCKET.name().equals(assetType)) {
        String targetRootPath = "gs://" + asset.getResourceSpec().getName() + "/" + options.getOutputTable();
        buildGcsPipeline(pipeline, options, dataSourceConfig, targetRootPath);
    } else {
        throw new IllegalArgumentException(String.format("Asset " + assetName + " is of type " + assetType + ". Only " + DataplexAssetResourceSpec.BIGQUERY_DATASET.name() + "and " + DataplexAssetResourceSpec.STORAGE_BUCKET.name() + " supported."));
    }
    pipeline.run();
}

Example 3 with GoogleCloudDataplexV1Asset

use of com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset in project DataflowTemplates by GoogleCloudPlatform.

the class DataplexJdbcIngestion method resolveAsset.

/**
 * Resolves a Dataplex asset.
 *
 * @param assetName Asset name from which the Dataplex asset will be resolved.
 * @param dataplexClient Dataplex client to connect to Dataplex via asset name.
 * @return The resolved asset
 */
private static GoogleCloudDataplexV1Asset resolveAsset(String assetName, DataplexClient dataplexClient) throws IOException {
    LOG.info("Resolving asset: {}", assetName);
    GoogleCloudDataplexV1Asset asset = dataplexClient.getAsset(assetName);
    checkNotNull(asset.getResourceSpec(), "Asset has no ResourceSpec.");
    String assetType = asset.getResourceSpec().getType();
    checkNotNull(assetType, "Asset has no type.");
    LOG.info("Resolved resource type: {}", assetType);
    String resourceName = asset.getResourceSpec().getName();
    checkNotNull(resourceName, "Asset has no resource name.");
    LOG.info("Resolved resource name: {}", resourceName);
    return asset;
}

Example 4 with GoogleCloudDataplexV1Asset

use of com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset in project DataflowTemplates by GoogleCloudPlatform.

the class DefaultDataplexClient method shouldSkipCreatingMetadata.

/**
 * Determines if we should skip creating metadata under {@code assetName}.
 *
 * <p>Currently, we skip creating metadata if discovery is enabled on either the zone or asset.
 * Trying to create metadata manually when this is enabled can lead to undefined behavior.
 *
 * @param assetName name of the asset to check
 * @return true if we should skip metadata creation, false otherwise
 */
private boolean shouldSkipCreatingMetadata(String assetName) throws IOException {
    GoogleCloudDataplexV1Asset asset = getAsset(assetName);
    if (asset.getDiscoverySpec().getEnabled()) {
        LOG.warn("Automatic discovery enabled for asset `{}`.", assetName);
        return true;
    }
    String zoneName = getZoneFromAsset(assetName);
    GoogleCloudDataplexV1Zone zone = getZone(zoneName);
    if (zone.getDiscoverySpec().getEnabled()) {
        LOG.warn("Automatic discovery enabled for zone `{}`", zoneName);
        return true;
    }
    return false;
}

Example 5 with GoogleCloudDataplexV1Asset

use of com.google.api.services.dataplex.v1.model.GoogleCloudDataplexV1Asset in project DataflowTemplates by GoogleCloudPlatform.

the class DataplexBigQueryToGcs method resolveAsset.

/**
 * Resolves a Dataplex asset name into the corresponding resource spec, verifying that the asset
 * is of the correct type.
 */
private static String resolveAsset(DataplexClient dataplex, String assetName, DataplexAssetResourceSpec expectedType) throws IOException {
    LOG.info("Resolving asset: {}", assetName);
    GoogleCloudDataplexV1Asset asset = dataplex.getAsset(assetName);
    checkNotNull(asset.getResourceSpec(), "Asset has no ResourceSpec.");
    String type = asset.getResourceSpec().getType();
    if (!expectedType.name().equals(type)) {
        throw new IllegalArgumentException(String.format("Asset %s is of type %s, expected: %s.", assetName, type, expectedType.name()));
    }
    String resourceName = asset.getResourceSpec().getName();
    checkNotNull(resourceName, "Asset has no resource name.");
    LOG.info("Resolved resource name: {}", resourceName);
    return resourceName;
}