use of com.google.api.services.dataplex.v1.CloudDataplex.Projects.Locations.Lakes.Zones.Entities.Partitions 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();
}
use of com.google.api.services.dataplex.v1.CloudDataplex.Projects.Locations.Lakes.Zones.Entities.Partitions in project DataflowTemplates by GoogleCloudPlatform.
the class DefaultDataplexClient method createPartitions.
/**
* Handles creation of partitions. Each partition is logged after being created.
*/
private void createPartitions(ImmutableMap<String, ImmutableList<PartitionMetadata>> entityNameToPartition) throws IOException {
for (Map.Entry<String, ImmutableList<PartitionMetadata>> entry : entityNameToPartition.entrySet()) {
ImmutableList<GoogleCloudDataplexV1Partition> partitions = entry.getValue().stream().map(PartitionMetadata::toDataplexPartition).collect(toImmutableList());
for (GoogleCloudDataplexV1Partition partition : partitions) {
GoogleCloudDataplexV1Partition result = client.projects().locations().lakes().zones().entities().partitions().create(entry.getKey(), partition).execute();
LOG.info("Created partition '{}' under entity '{}'", result.getName(), entry.getKey());
}
}
}
use of com.google.api.services.dataplex.v1.CloudDataplex.Projects.Locations.Lakes.Zones.Entities.Partitions in project DataflowTemplates by GoogleCloudPlatform.
the class DefaultDataplexClient method getPartitions.
@Override
public ImmutableList<GoogleCloudDataplexV1Partition> getPartitions(String entityName) throws IOException {
ImmutableList.Builder<GoogleCloudDataplexV1Partition> result = ImmutableList.builder();
Partitions partitions = client.projects().locations().lakes().zones().entities().partitions();
GoogleCloudDataplexV1ListPartitionsResponse response = partitions.list(entityName).execute();
if (response.getPartitions() == null) {
return ImmutableList.of();
}
result.addAll(response.getPartitions());
// the result of the list is paginated with the default page size being 10
while (response.getNextPageToken() != null) {
response = partitions.list(entityName).setPageToken(response.getNextPageToken()).execute();
result.addAll(response.getPartitions());
}
return result.build();
}
use of com.google.api.services.dataplex.v1.CloudDataplex.Projects.Locations.Lakes.Zones.Entities.Partitions in project DataflowTemplates by GoogleCloudPlatform.
the class DefaultDataplexClientTest method testGetPartitionsByEntityName.
@Test
public void testGetPartitionsByEntityName() throws IOException {
CloudDataplex cloudDataplexClient = mock(CloudDataplex.class, Answers.RETURNS_DEEP_STUBS);
Partitions partitions = mock(Partitions.class, Answers.RETURNS_DEEP_STUBS);
when(cloudDataplexClient.projects().locations().lakes().zones().entities().partitions()).thenReturn(partitions);
GoogleCloudDataplexV1Partition partition1 = new GoogleCloudDataplexV1Partition().setName("partition1");
GoogleCloudDataplexV1Partition partition2 = new GoogleCloudDataplexV1Partition().setName("partition2");
GoogleCloudDataplexV1Partition partition3 = new GoogleCloudDataplexV1Partition().setName("partition2");
GoogleCloudDataplexV1ListPartitionsResponse response1 = new GoogleCloudDataplexV1ListPartitionsResponse().setPartitions(ImmutableList.of(partition1, partition2)).setNextPageToken(PAGE_TOKEN);
GoogleCloudDataplexV1ListPartitionsResponse response2 = new GoogleCloudDataplexV1ListPartitionsResponse().setPartitions(ImmutableList.of(partition3));
when(partitions.list("entity0").execute()).thenReturn(response1);
when(partitions.list("entity0").setPageToken(eq(PAGE_TOKEN)).execute()).thenReturn(response2);
assertEquals(ImmutableList.of(partition1, partition2, partition3), DefaultDataplexClient.withClient(cloudDataplexClient).getPartitions("entity0"));
}
use of com.google.api.services.dataplex.v1.CloudDataplex.Projects.Locations.Lakes.Zones.Entities.Partitions in project DataflowTemplates by GoogleCloudPlatform.
the class DefaultDataplexClientTest method testCreateEntitiesWhenDiscoveryEnabled.
@Test
public void testCreateEntitiesWhenDiscoveryEnabled() throws IOException {
CloudDataplex dataplex = mock(CloudDataplex.class, Answers.RETURNS_DEEP_STUBS);
Zones zones = getZones(dataplex);
Assets assets = getAssets(dataplex);
// Don't care about the order they're checked, so set up for two calls.
when(assets.get(any()).execute()).thenReturn(createAsset(ENABLED_ASSET_DISCOVERY_SPEC)).thenReturn(createAsset(DISABLED_ASSET_DISCOVERY_SPEC));
when(zones.get(any()).execute()).thenReturn(createZone(ENABLED_ZONE_DISCOVERY_SPEC)).thenReturn(createZone(DISABLED_ZONE_DISCOVERY_SPEC));
DataplexClient client = DefaultDataplexClient.withClient(dataplex);
client.createMetadata(ASSET_NAME1, ImmutableList.of(UNUSED_METADATA), CreateBehavior.UPDATE_IF_EXISTS);
client.createMetadata(ASSET_NAME1, ImmutableList.of(UNUSED_METADATA), CreateBehavior.UPDATE_IF_EXISTS);
verify(assets, atLeastOnce()).get(ASSET_NAME1);
verify(zones, atLeastOnce()).get(ZONE_NAME);
// Enough to know nothing was done with partitions
verify(zones, never()).entities();
}
Aggregations