Package io.openlineage.client
Class OpenLineage
java.lang.Object
io.openlineage.client.OpenLineage
Usage:
URI producer = URI.create("http://my.producer/uri");
OpenLineage ol = new OpenLineage(producer);
UUID runId = UUID.randomUUID();
RunFacets runFacets =
ol.newRunFacetsBuilder().nominalTime(ol.newNominalTimeRunFacet(now, now)).build();
Run run = ol.newRun(runId, runFacets);
String name = "jobName";
String namespace = "namespace";
JobFacets jobFacets = ol.newJobFacetsBuilder().build();
Job job = ol.newJob(namespace, name, jobFacets);
List<InputDataset> inputs = Arrays.asList(ol.newInputDataset("ins", "input", null, null));
List<OutputDataset> outputs = Arrays.asList(ol.newOutputDataset("ons", "output", null, null));
RunEvent runStateUpdate =
ol.newRunEvent(now, OpenLineage.RunEvent.EventType.START, run, job, inputs, outputs);
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic interface
Interface for BaseEventstatic interface
Interface for BaseFacetstatic interface
static final class
model class for ColumnLineageDatasetFacetfinal class
builder class for ColumnLineageDatasetFacetstatic final class
model class for ColumnLineageDatasetFacetFieldsstatic final class
model class for ColumnLineageDatasetFacetFieldsAdditionalstatic final class
builder class for ColumnLineageDatasetFacetFieldsAdditionalstatic final class
builder class for ColumnLineageDatasetFacetFieldsstatic final class
model class for DataQualityAssertionsDatasetFacetstatic final class
model class for DataQualityAssertionsDatasetFacetAssertionsstatic final class
builder class for DataQualityAssertionsDatasetFacetAssertionsfinal class
builder class for DataQualityAssertionsDatasetFacetstatic final class
model class for DataQualityMetricsInputDatasetFacetfinal class
builder class for DataQualityMetricsInputDatasetFacetstatic final class
model class for DataQualityMetricsInputDatasetFacetColumnMetricsstatic final class
model class for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalstatic final class
builder class for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalstatic final class
model class for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesstatic final class
builder class for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesstatic final class
builder class for DataQualityMetricsInputDatasetFacetColumnMetricsstatic interface
Interface for Datasetstatic final class
model class for DatasetEventfinal class
builder class for DatasetEventstatic interface
Interface for DatasetFacetstatic final class
model class for DatasetFacetsstatic final class
builder class for DatasetFacetsstatic final class
model class for DatasetTypeDatasetFacetfinal class
builder class for DatasetTypeDatasetFacetstatic final class
model class for DatasetVersionDatasetFacetfinal class
builder class for DatasetVersionDatasetFacetstatic final class
model class for DatasourceDatasetFacetfinal class
builder class for DatasourceDatasetFacetstatic class
static class
static class
static class
static class
static final class
model class for DocumentationDatasetFacetfinal class
builder class for DocumentationDatasetFacetstatic final class
model class for DocumentationJobFacetfinal class
builder class for DocumentationJobFacetstatic final class
model class for EnvironmentVariablestatic final class
builder class for EnvironmentVariablestatic final class
model class for EnvironmentVariablesRunFacetfinal class
builder class for EnvironmentVariablesRunFacetstatic final class
model class for ErrorMessageRunFacetfinal class
builder class for ErrorMessageRunFacetstatic final class
model class for ExternalQueryRunFacetfinal class
builder class for ExternalQueryRunFacetstatic final class
model class for ExtractionErrorRunFacetfinal class
builder class for ExtractionErrorRunFacetstatic final class
model class for ExtractionErrorRunFacetErrorsstatic final class
builder class for ExtractionErrorRunFacetErrorsstatic final class
model class for GcpDataprocRunFacetfinal class
builder class for GcpDataprocRunFacetstatic final class
model class for GcpLineageJobFacetfinal class
builder class for GcpLineageJobFacetstatic final class
model class for GcpLineageJobFacetOriginstatic final class
builder class for GcpLineageJobFacetOriginstatic final class
model class for IcebergCommitReportOutputDatasetFacetfinal class
builder class for IcebergCommitReportOutputDatasetFacetstatic final class
model class for IcebergCommitReportOutputDatasetFacetCommitMetricsstatic final class
builder class for IcebergCommitReportOutputDatasetFacetCommitMetricsstatic final class
model class for IcebergCommitReportOutputDatasetFacetMetadatastatic final class
builder class for IcebergCommitReportOutputDatasetFacetMetadatastatic final class
model class for IcebergScanReportInputDatasetFacetfinal class
builder class for IcebergScanReportInputDatasetFacetstatic final class
model class for IcebergScanReportInputDatasetFacetMetadatastatic final class
builder class for IcebergScanReportInputDatasetFacetMetadatastatic final class
model class for IcebergScanReportInputDatasetFacetScanMetricsstatic final class
builder class for IcebergScanReportInputDatasetFacetScanMetricsstatic final class
model class for InputDatasetstatic final class
builder class for InputDatasetstatic interface
Interface for InputDatasetFacetstatic final class
model class for InputDatasetInputFacetsstatic final class
builder class for InputDatasetInputFacetsstatic final class
model class for InputFieldstatic final class
builder class for InputFieldstatic final class
model class for InputFieldTransformationsstatic final class
builder class for InputFieldTransformationsstatic final class
model class for InputStatisticsInputDatasetFacetfinal class
builder class for InputStatisticsInputDatasetFacetstatic final class
model class for Jobstatic final class
builder class for Jobstatic final class
model class for JobEventfinal class
builder class for JobEventstatic interface
Interface for JobFacetstatic final class
model class for JobFacetsstatic final class
builder class for JobFacetsstatic final class
model class for JobTypeJobFacetfinal class
builder class for JobTypeJobFacetstatic final class
model class for LifecycleStateChangeDatasetFacetfinal class
builder class for LifecycleStateChangeDatasetFacetstatic final class
model class for LifecycleStateChangeDatasetFacetPreviousIdentifierstatic final class
builder class for LifecycleStateChangeDatasetFacetPreviousIdentifierstatic final class
model class for NominalTimeRunFacetfinal class
builder class for NominalTimeRunFacetstatic final class
model class for OutputDatasetstatic final class
builder class for OutputDatasetstatic interface
Interface for OutputDatasetFacetstatic final class
model class for OutputDatasetOutputFacetsstatic final class
builder class for OutputDatasetOutputFacetsstatic final class
model class for OutputStatisticsOutputDatasetFacetfinal class
builder class for OutputStatisticsOutputDatasetFacetstatic final class
model class for OwnershipDatasetFacetfinal class
builder class for OwnershipDatasetFacetstatic final class
model class for OwnershipDatasetFacetOwnersstatic final class
builder class for OwnershipDatasetFacetOwnersstatic final class
model class for OwnershipJobFacetfinal class
builder class for OwnershipJobFacetstatic final class
model class for OwnershipJobFacetOwnersstatic final class
builder class for OwnershipJobFacetOwnersstatic final class
model class for ParentRunFacetfinal class
builder class for ParentRunFacetstatic final class
model class for ParentRunFacetJobstatic final class
builder class for ParentRunFacetJobstatic final class
model class for ParentRunFacetRootstatic final class
builder class for ParentRunFacetRootstatic final class
model class for ParentRunFacetRunstatic final class
builder class for ParentRunFacetRunstatic final class
model class for ProcessingEngineRunFacetfinal class
builder class for ProcessingEngineRunFacetstatic final class
model class for RootJobstatic final class
builder class for RootJobstatic final class
model class for RootRunstatic final class
builder class for RootRunstatic final class
model class for Runstatic final class
builder class for Runstatic final class
model class for RunEventfinal class
builder class for RunEventstatic interface
Interface for RunFacetstatic final class
model class for RunFacetsstatic final class
builder class for RunFacetsstatic final class
model class for SchemaDatasetFacetfinal class
builder class for SchemaDatasetFacetstatic final class
model class for SchemaDatasetFacetFieldsstatic final class
builder class for SchemaDatasetFacetFieldsstatic final class
model class for SourceCodeJobFacetfinal class
builder class for SourceCodeJobFacetstatic final class
model class for SourceCodeLocationJobFacetfinal class
builder class for SourceCodeLocationJobFacetstatic final class
model class for SQLJobFacetfinal class
builder class for SQLJobFacetstatic final class
model class for StaticDatasetstatic final class
builder class for StaticDatasetstatic final class
model class for StorageDatasetFacetfinal class
builder class for StorageDatasetFacetstatic final class
model class for SymlinksDatasetFacetfinal class
builder class for SymlinksDatasetFacetstatic final class
model class for SymlinksDatasetFacetIdentifiersstatic final class
builder class for SymlinksDatasetFacetIdentifiersstatic final class
model class for TagsDatasetFacetfinal class
builder class for TagsDatasetFacetstatic final class
model class for TagsDatasetFacetFieldsstatic final class
builder class for TagsDatasetFacetFieldsstatic final class
model class for TagsJobFacetfinal class
builder class for TagsJobFacetstatic final class
model class for TagsJobFacetFieldsstatic final class
builder class for TagsJobFacetFieldsstatic final class
model class for TagsRunFacetfinal class
builder class for TagsRunFacetstatic final class
model class for TagsRunFacetFieldsstatic final class
builder class for TagsRunFacetFields -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionnewColumnLineageDatasetFacet
(OpenLineage.ColumnLineageDatasetFacetFields fields, List<OpenLineage.InputField> dataset) Factory method for ColumnLineageDatasetFacetCreates a builder for ColumnLineageDatasetFacetFactory method for ColumnLineageDatasetFacetFieldsnewColumnLineageDatasetFacetFieldsAdditional
(List<OpenLineage.InputField> inputFields, String transformationDescription, String transformationType) Factory method for ColumnLineageDatasetFacetFieldsAdditionalCreates a builder for ColumnLineageDatasetFacetFieldsAdditionalCreates a builder for ColumnLineageDatasetFacetFieldsnewDataQualityAssertionsDatasetFacet
(List<OpenLineage.DataQualityAssertionsDatasetFacetAssertions> assertions) Factory method for DataQualityAssertionsDatasetFacetnewDataQualityAssertionsDatasetFacetAssertions
(String assertion, Boolean success, String column) Factory method for DataQualityAssertionsDatasetFacetAssertionsCreates a builder for DataQualityAssertionsDatasetFacetAssertionsCreates a builder for DataQualityAssertionsDatasetFacetnewDataQualityMetricsInputDatasetFacet
(Long rowCount, Long bytes, Long fileCount, OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetrics columnMetrics) Factory method for DataQualityMetricsInputDatasetFacetCreates a builder for DataQualityMetricsInputDatasetFacetFactory method for DataQualityMetricsInputDatasetFacetColumnMetricsnewDataQualityMetricsInputDatasetFacetColumnMetricsAdditional
(Long nullCount, Long distinctCount, Double sum, Double count, Double min, Double max, OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles quantiles) Factory method for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalCreates a builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalFactory method for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesCreates a builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesCreates a builder for DataQualityMetricsInputDatasetFacetColumnMetricsnewDatasetEvent
(ZonedDateTime eventTime, OpenLineage.StaticDataset dataset) Factory method for DatasetEventCreates a builder for DatasetEventnewDatasetFacets
(OpenLineage.DatasourceDatasetFacet dataSource, OpenLineage.DatasetVersionDatasetFacet version, OpenLineage.DatasetTypeDatasetFacet datasetType, OpenLineage.StorageDatasetFacet storage, OpenLineage.ColumnLineageDatasetFacet columnLineage, OpenLineage.LifecycleStateChangeDatasetFacet lifecycleStateChange, OpenLineage.TagsDatasetFacet tags, OpenLineage.DocumentationDatasetFacet documentation, OpenLineage.SchemaDatasetFacet schema, OpenLineage.OwnershipDatasetFacet ownership, OpenLineage.SymlinksDatasetFacet symlinks) Factory method for DatasetFacetsCreates a builder for DatasetFacetsnewDatasetTypeDatasetFacet
(String datasetType, String subType) Factory method for DatasetTypeDatasetFacetCreates a builder for DatasetTypeDatasetFacetnewDatasetVersionDatasetFacet
(String datasetVersion) Factory method for DatasetVersionDatasetFacetCreates a builder for DatasetVersionDatasetFacetnewDatasourceDatasetFacet
(String name, URI uri) Factory method for DatasourceDatasetFacetCreates a builder for DatasourceDatasetFacetnewDocumentationDatasetFacet
(String description) Factory method for DocumentationDatasetFacetCreates a builder for DocumentationDatasetFacetnewDocumentationJobFacet
(String description) Factory method for DocumentationJobFacetCreates a builder for DocumentationJobFacetnewEnvironmentVariable
(String name, String value) Factory method for EnvironmentVariableCreates a builder for EnvironmentVariablenewEnvironmentVariablesRunFacet
(List<OpenLineage.EnvironmentVariable> environmentVariables) Factory method for EnvironmentVariablesRunFacetCreates a builder for EnvironmentVariablesRunFacetnewErrorMessageRunFacet
(String message, String programmingLanguage, String stackTrace) Factory method for ErrorMessageRunFacetCreates a builder for ErrorMessageRunFacetnewExternalQueryRunFacet
(String externalQueryId, String source) Factory method for ExternalQueryRunFacetCreates a builder for ExternalQueryRunFacetnewExtractionErrorRunFacet
(Long totalTasks, Long failedTasks, List<OpenLineage.ExtractionErrorRunFacetErrors> errors) Factory method for ExtractionErrorRunFacetCreates a builder for ExtractionErrorRunFacetnewExtractionErrorRunFacetErrors
(String errorMessage, String stackTrace, String task, Long taskNumber) Factory method for ExtractionErrorRunFacetErrorsCreates a builder for ExtractionErrorRunFacetErrorsnewGcpDataprocRunFacet
(String appId, String appName, String batchId, String batchUuid, String clusterName, String clusterUuid, String jobId, String jobUuid, String projectId, String queryNodeName, String jobType, String sessionId, String sessionUuid) Factory method for GcpDataprocRunFacetCreates a builder for GcpDataprocRunFacetnewGcpLineageJobFacet
(String displayName, OpenLineage.GcpLineageJobFacetOrigin origin) Factory method for GcpLineageJobFacetCreates a builder for GcpLineageJobFacetnewGcpLineageJobFacetOrigin
(String sourceType, String name) Factory method for GcpLineageJobFacetOriginCreates a builder for GcpLineageJobFacetOriginnewIcebergCommitReportOutputDatasetFacet
(Double snapshotId, Double sequenceNumber, String operation, OpenLineage.IcebergCommitReportOutputDatasetFacetCommitMetrics commitMetrics, OpenLineage.IcebergCommitReportOutputDatasetFacetMetadata metadata) Factory method for IcebergCommitReportOutputDatasetFacetCreates a builder for IcebergCommitReportOutputDatasetFacetnewIcebergCommitReportOutputDatasetFacetCommitMetrics
(Double totalDuration, Double attempts, Double addedDataFiles, Double removedDataFiles, Double totalDataFiles, Double addedDeleteFiles, Double addedEqualityDeleteFiles, Double addedPositionalDeleteFiles, Double addedDVs, Double removedDeleteFiles, Double removedEqualityDeleteFiles, Double removedPositionalDeleteFiles, Double removedDVs, Double totalDeleteFiles, Double addedRecords, Double removedRecords, Double totalRecords, Double addedFilesSizeInBytes, Double removedFilesSizeInBytes, Double totalFilesSizeInBytes, Double addedPositionalDeletes, Double removedPositionalDeletes, Double totalPositionalDeletes, Double addedEqualityDeletes, Double removedEqualityDeletes, Double totalEqualityDeletes) Factory method for IcebergCommitReportOutputDatasetFacetCommitMetricsCreates a builder for IcebergCommitReportOutputDatasetFacetCommitMetricsFactory method for IcebergCommitReportOutputDatasetFacetMetadataCreates a builder for IcebergCommitReportOutputDatasetFacetMetadatanewIcebergScanReportInputDatasetFacet
(Double snapshotId, String filter, Double schemaId, List<String> projectedFieldNames, OpenLineage.IcebergScanReportInputDatasetFacetScanMetrics scanMetrics, OpenLineage.IcebergScanReportInputDatasetFacetMetadata metadata) Factory method for IcebergScanReportInputDatasetFacetCreates a builder for IcebergScanReportInputDatasetFacetFactory method for IcebergScanReportInputDatasetFacetMetadataCreates a builder for IcebergScanReportInputDatasetFacetMetadatanewIcebergScanReportInputDatasetFacetScanMetrics
(Double totalPlanningDuration, Double resultDataFiles, Double resultDeleteFiles, Double totalDataManifests, Double totalDeleteManifests, Double scannedDataManifests, Double skippedDataManifests, Double totalFileSizeInBytes, Double totalDeleteFileSizeInBytes, Double skippedDataFiles, Double skippedDeleteFiles, Double scannedDeleteManifests, Double skippedDeleteManifests, Double indexedDeleteFiles, Double equalityDeleteFiles, Double positionalDeleteFiles) Factory method for IcebergScanReportInputDatasetFacetScanMetricsCreates a builder for IcebergScanReportInputDatasetFacetScanMetricsnewInputDataset
(String namespace, String name, OpenLineage.DatasetFacets facets, OpenLineage.InputDatasetInputFacets inputFacets) Factory method for InputDatasetCreates a builder for InputDatasetnewInputDatasetInputFacets
(OpenLineage.DataQualityAssertionsDatasetFacet dataQualityAssertions, OpenLineage.InputStatisticsInputDatasetFacet inputStatistics, OpenLineage.DataQualityMetricsInputDatasetFacet dataQualityMetrics, OpenLineage.IcebergScanReportInputDatasetFacet iceberg_scan_report) Factory method for InputDatasetInputFacetsCreates a builder for InputDatasetInputFacetsnewInputField
(String namespace, String name, String field, List<OpenLineage.InputFieldTransformations> transformations) Factory method for InputFieldCreates a builder for InputFieldnewInputFieldTransformations
(String type, String subtype, String description, Boolean masking) Factory method for InputFieldTransformationsCreates a builder for InputFieldTransformationsnewInputStatisticsInputDatasetFacet
(Long rowCount, Long size, Long fileCount) Factory method for InputStatisticsInputDatasetFacetCreates a builder for InputStatisticsInputDatasetFacetnewJob
(String namespace, String name, OpenLineage.JobFacets facets) Factory method for JobCreates a builder for JobnewJobEvent
(ZonedDateTime eventTime, OpenLineage.Job job, List<OpenLineage.InputDataset> inputs, List<OpenLineage.OutputDataset> outputs) Factory method for JobEventCreates a builder for JobEventnewJobFacets
(OpenLineage.JobTypeJobFacet jobType, OpenLineage.SourceCodeJobFacet sourceCode, OpenLineage.GcpLineageJobFacet gcp_lineage, OpenLineage.SQLJobFacet sql, OpenLineage.OwnershipJobFacet ownership, OpenLineage.SourceCodeLocationJobFacet sourceCodeLocation, OpenLineage.TagsJobFacet tags, OpenLineage.DocumentationJobFacet documentation) Factory method for JobFacetsCreates a builder for JobFacetsnewJobTypeJobFacet
(String processingType, String integration, String jobType) Factory method for JobTypeJobFacetCreates a builder for JobTypeJobFacetnewLifecycleStateChangeDatasetFacet
(OpenLineage.LifecycleStateChangeDatasetFacet.LifecycleStateChange lifecycleStateChange, OpenLineage.LifecycleStateChangeDatasetFacetPreviousIdentifier previousIdentifier) Factory method for LifecycleStateChangeDatasetFacetCreates a builder for LifecycleStateChangeDatasetFacetnewLifecycleStateChangeDatasetFacetPreviousIdentifier
(String name, String namespace) Factory method for LifecycleStateChangeDatasetFacetPreviousIdentifierCreates a builder for LifecycleStateChangeDatasetFacetPreviousIdentifiernewNominalTimeRunFacet
(ZonedDateTime nominalStartTime, ZonedDateTime nominalEndTime) Factory method for NominalTimeRunFacetCreates a builder for NominalTimeRunFacetnewOutputDataset
(String namespace, String name, OpenLineage.DatasetFacets facets, OpenLineage.OutputDatasetOutputFacets outputFacets) Factory method for OutputDatasetCreates a builder for OutputDatasetnewOutputDatasetOutputFacets
(OpenLineage.IcebergCommitReportOutputDatasetFacet iceberg_scan_report, OpenLineage.OutputStatisticsOutputDatasetFacet outputStatistics) Factory method for OutputDatasetOutputFacetsCreates a builder for OutputDatasetOutputFacetsnewOutputStatisticsOutputDatasetFacet
(Long rowCount, Long size, Long fileCount) Factory method for OutputStatisticsOutputDatasetFacetCreates a builder for OutputStatisticsOutputDatasetFacetFactory method for OwnershipDatasetFacetCreates a builder for OwnershipDatasetFacetnewOwnershipDatasetFacetOwners
(String name, String type) Factory method for OwnershipDatasetFacetOwnersCreates a builder for OwnershipDatasetFacetOwnersFactory method for OwnershipJobFacetCreates a builder for OwnershipJobFacetnewOwnershipJobFacetOwners
(String name, String type) Factory method for OwnershipJobFacetOwnersCreates a builder for OwnershipJobFacetOwnersnewParentRunFacet
(OpenLineage.ParentRunFacetRun run, OpenLineage.ParentRunFacetJob job, OpenLineage.ParentRunFacetRoot root) Factory method for ParentRunFacetCreates a builder for ParentRunFacetnewParentRunFacetJob
(String namespace, String name) Factory method for ParentRunFacetJobCreates a builder for ParentRunFacetJobFactory method for ParentRunFacetRootCreates a builder for ParentRunFacetRootnewParentRunFacetRun
(UUID runId) Factory method for ParentRunFacetRunCreates a builder for ParentRunFacetRunnewProcessingEngineRunFacet
(String version, String name, String openlineageAdapterVersion) Factory method for ProcessingEngineRunFacetCreates a builder for ProcessingEngineRunFacetnewRootJob
(String namespace, String name) Factory method for RootJobCreates a builder for RootJobnewRootRun
(UUID runId) Factory method for RootRunCreates a builder for RootRunnewRun
(UUID runId, OpenLineage.RunFacets facets) Factory method for RunCreates a builder for RunnewRunEvent
(ZonedDateTime eventTime, OpenLineage.RunEvent.EventType eventType, OpenLineage.Run run, OpenLineage.Job job, List<OpenLineage.InputDataset> inputs, List<OpenLineage.OutputDataset> outputs) Factory method for RunEventCreates a builder for RunEventnewRunFacets
(OpenLineage.ExternalQueryRunFacet externalQuery, OpenLineage.GcpDataprocRunFacet gcp_dataproc, OpenLineage.ExtractionErrorRunFacet extractionError, OpenLineage.ParentRunFacet parent, OpenLineage.NominalTimeRunFacet nominalTime, OpenLineage.TagsRunFacet tags, OpenLineage.ErrorMessageRunFacet errorMessage, OpenLineage.EnvironmentVariablesRunFacet environmentVariables, OpenLineage.ProcessingEngineRunFacet processing_engine) Factory method for RunFacetsCreates a builder for RunFacetsFactory method for SchemaDatasetFacetCreates a builder for SchemaDatasetFacetnewSchemaDatasetFacetFields
(String name, String type, String description, List<OpenLineage.SchemaDatasetFacetFields> fields) Factory method for SchemaDatasetFacetFieldsCreates a builder for SchemaDatasetFacetFieldsnewSourceCodeJobFacet
(String language, String sourceCode) Factory method for SourceCodeJobFacetCreates a builder for SourceCodeJobFacetnewSourceCodeLocationJobFacet
(String type, URI url, String repoUrl, String path, String version, String tag, String branch) Factory method for SourceCodeLocationJobFacetCreates a builder for SourceCodeLocationJobFacetnewSQLJobFacet
(String query) Factory method for SQLJobFacetCreates a builder for SQLJobFacetnewStaticDataset
(String namespace, String name, OpenLineage.DatasetFacets facets) Factory method for StaticDatasetCreates a builder for StaticDatasetnewStorageDatasetFacet
(String storageLayer, String fileFormat) Factory method for StorageDatasetFacetCreates a builder for StorageDatasetFacetFactory method for SymlinksDatasetFacetCreates a builder for SymlinksDatasetFacetnewSymlinksDatasetFacetIdentifiers
(String namespace, String name, String type) Factory method for SymlinksDatasetFacetIdentifiersCreates a builder for SymlinksDatasetFacetIdentifiersFactory method for TagsDatasetFacetCreates a builder for TagsDatasetFacetnewTagsDatasetFacetFields
(String key, String value, String source, String field) Factory method for TagsDatasetFacetFieldsCreates a builder for TagsDatasetFacetFieldsFactory method for TagsJobFacetCreates a builder for TagsJobFacetnewTagsJobFacetFields
(String key, String value, String source) Factory method for TagsJobFacetFieldsCreates a builder for TagsJobFacetFieldsFactory method for TagsRunFacetCreates a builder for TagsRunFacetnewTagsRunFacetFields
(String key, String value, String source) Factory method for TagsRunFacetFieldsCreates a builder for TagsRunFacetFields
-
Constructor Details
-
OpenLineage
Starting point to create OpenLineage objects. Use the OpenLineage instance to create events and facets- Parameters:
producer
- the identifier of the library using the client to generate OpenLineage events
-
-
Method Details
-
newSchemaDatasetFacetFields
public OpenLineage.SchemaDatasetFacetFields newSchemaDatasetFacetFields(String name, String type, String description, List<OpenLineage.SchemaDatasetFacetFields> fields) Factory method for SchemaDatasetFacetFields- Parameters:
name
- The name of the field.type
- The type of the field.description
- The description of the field.fields
- Nested struct fields.- Returns:
- SchemaDatasetFacetFields
-
newSchemaDatasetFacetFieldsBuilder
Creates a builder for SchemaDatasetFacetFields- Returns:
- a new builder for SchemaDatasetFacetFields
-
newParentRunFacet
public OpenLineage.ParentRunFacet newParentRunFacet(OpenLineage.ParentRunFacetRun run, OpenLineage.ParentRunFacetJob job, OpenLineage.ParentRunFacetRoot root) Factory method for ParentRunFacet- Parameters:
run
- the runjob
- the jobroot
- the root- Returns:
- ParentRunFacet
-
newParentRunFacetBuilder
Creates a builder for ParentRunFacet- Returns:
- a new builder for ParentRunFacet
-
newOutputStatisticsOutputDatasetFacet
public OpenLineage.OutputStatisticsOutputDatasetFacet newOutputStatisticsOutputDatasetFacet(Long rowCount, Long size, Long fileCount) Factory method for OutputStatisticsOutputDatasetFacet- Parameters:
rowCount
- The number of rows written to the datasetsize
- The size in bytes written to the datasetfileCount
- The number of files written to the dataset- Returns:
- OutputStatisticsOutputDatasetFacet
-
newOutputStatisticsOutputDatasetFacetBuilder
public OpenLineage.OutputStatisticsOutputDatasetFacetBuilder newOutputStatisticsOutputDatasetFacetBuilder()Creates a builder for OutputStatisticsOutputDatasetFacet- Returns:
- a new builder for OutputStatisticsOutputDatasetFacet
-
newExtractionErrorRunFacetErrors
public OpenLineage.ExtractionErrorRunFacetErrors newExtractionErrorRunFacetErrors(String errorMessage, String stackTrace, String task, Long taskNumber) Factory method for ExtractionErrorRunFacetErrors- Parameters:
errorMessage
- Text representation of extraction error message.stackTrace
- Stack trace of extraction error messagetask
- Text representation of task that failed. This can be, for example, SQL statement that parser could not interpret.taskNumber
- Order of task (counted from 0).- Returns:
- ExtractionErrorRunFacetErrors
-
newExtractionErrorRunFacetErrorsBuilder
Creates a builder for ExtractionErrorRunFacetErrors- Returns:
- a new builder for ExtractionErrorRunFacetErrors
-
newJobTypeJobFacet
public OpenLineage.JobTypeJobFacet newJobTypeJobFacet(String processingType, String integration, String jobType) Factory method for JobTypeJobFacet- Parameters:
processingType
- Job processing type like: BATCH or STREAMINGintegration
- OpenLineage integration type of this job: for example SPARK|DBT|AIRFLOW|FLINKjobType
- Run type, for example: QUERY|COMMAND|DAG|TASK|JOB|MODEL. This is an integration-specific field.- Returns:
- JobTypeJobFacet
-
newJobTypeJobFacetBuilder
Creates a builder for JobTypeJobFacet- Returns:
- a new builder for JobTypeJobFacet
-
newRun
Factory method for Run- Parameters:
runId
- The globally unique ID of the run associated with the job.facets
- The run facets.- Returns:
- Run
-
newRunBuilder
Creates a builder for Run- Returns:
- a new builder for Run
-
newParentRunFacetRoot
public OpenLineage.ParentRunFacetRoot newParentRunFacetRoot(OpenLineage.RootRun run, OpenLineage.RootJob job) Factory method for ParentRunFacetRoot- Parameters:
run
- the runjob
- the job- Returns:
- ParentRunFacetRoot
-
newParentRunFacetRootBuilder
Creates a builder for ParentRunFacetRoot- Returns:
- a new builder for ParentRunFacetRoot
-
newExternalQueryRunFacet
public OpenLineage.ExternalQueryRunFacet newExternalQueryRunFacet(String externalQueryId, String source) Factory method for ExternalQueryRunFacet- Parameters:
externalQueryId
- Identifier for the external systemsource
- source of the external query- Returns:
- ExternalQueryRunFacet
-
newExternalQueryRunFacetBuilder
Creates a builder for ExternalQueryRunFacet- Returns:
- a new builder for ExternalQueryRunFacet
-
newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles()Factory method for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles- Returns:
- DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles
-
newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesBuilder
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesBuilder newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantilesBuilder()Creates a builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles- Returns:
- a new builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles
-
newOutputDatasetOutputFacets
public OpenLineage.OutputDatasetOutputFacets newOutputDatasetOutputFacets(OpenLineage.IcebergCommitReportOutputDatasetFacet iceberg_scan_report, OpenLineage.OutputStatisticsOutputDatasetFacet outputStatistics) Factory method for OutputDatasetOutputFacets- Parameters:
iceberg_scan_report
- the iceberg_scan_reportoutputStatistics
- the outputStatistics- Returns:
- OutputDatasetOutputFacets
-
newOutputDatasetOutputFacetsBuilder
Creates a builder for OutputDatasetOutputFacets- Returns:
- a new builder for OutputDatasetOutputFacets
-
newNominalTimeRunFacet
public OpenLineage.NominalTimeRunFacet newNominalTimeRunFacet(ZonedDateTime nominalStartTime, ZonedDateTime nominalEndTime) Factory method for NominalTimeRunFacet- Parameters:
nominalStartTime
- An [ISO-8601](https://en.wikipedia.org/wiki/ISO_8601) timestamp representing the nominal start time (included) of the run. AKA the schedule timenominalEndTime
- An [ISO-8601](https://en.wikipedia.org/wiki/ISO_8601) timestamp representing the nominal end time (excluded) of the run. (Should be the nominal start time of the next run)- Returns:
- NominalTimeRunFacet
-
newNominalTimeRunFacetBuilder
Creates a builder for NominalTimeRunFacet- Returns:
- a new builder for NominalTimeRunFacet
-
newInputDatasetFacet
- Returns:
- InputDatasetFacet
-
newColumnLineageDatasetFacetFieldsAdditional
public OpenLineage.ColumnLineageDatasetFacetFieldsAdditional newColumnLineageDatasetFacetFieldsAdditional(List<OpenLineage.InputField> inputFields, String transformationDescription, String transformationType) Factory method for ColumnLineageDatasetFacetFieldsAdditional- Parameters:
inputFields
- the inputFieldstransformationDescription
- a string representation of the transformation appliedtransformationType
- IDENTITY|MASKED reflects a clearly defined behavior. IDENTITY: exact same as input; MASKED: no original data available (like a hash of PII for example)- Returns:
- ColumnLineageDatasetFacetFieldsAdditional
-
newColumnLineageDatasetFacetFieldsAdditionalBuilder
public OpenLineage.ColumnLineageDatasetFacetFieldsAdditionalBuilder newColumnLineageDatasetFacetFieldsAdditionalBuilder()Creates a builder for ColumnLineageDatasetFacetFieldsAdditional- Returns:
- a new builder for ColumnLineageDatasetFacetFieldsAdditional
-
newDataQualityMetricsInputDatasetFacetColumnMetricsAdditional
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditional newDataQualityMetricsInputDatasetFacetColumnMetricsAdditional(Long nullCount, Long distinctCount, Double sum, Double count, Double min, Double max, OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalQuantiles quantiles) Factory method for DataQualityMetricsInputDatasetFacetColumnMetricsAdditional- Parameters:
nullCount
- The number of null values in this column for the rows evaluateddistinctCount
- The number of distinct values in this column for the rows evaluatedsum
- The total sum of values in this column for the rows evaluatedcount
- The number of values in this columnmin
- the minmax
- the maxquantiles
- The property key is the quantile. Examples: 0.1 0.25 0.5 0.75 1- Returns:
- DataQualityMetricsInputDatasetFacetColumnMetricsAdditional
-
newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalBuilder
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsAdditionalBuilder newDataQualityMetricsInputDatasetFacetColumnMetricsAdditionalBuilder()Creates a builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditional- Returns:
- a new builder for DataQualityMetricsInputDatasetFacetColumnMetricsAdditional
-
newDataQualityMetricsInputDatasetFacet
public OpenLineage.DataQualityMetricsInputDatasetFacet newDataQualityMetricsInputDatasetFacet(Long rowCount, Long bytes, Long fileCount, OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetrics columnMetrics) Factory method for DataQualityMetricsInputDatasetFacet- Parameters:
rowCount
- The number of rows evaluatedbytes
- The size in bytesfileCount
- The number of files evaluatedcolumnMetrics
- The property key is the column name- Returns:
- DataQualityMetricsInputDatasetFacet
-
newDataQualityMetricsInputDatasetFacetBuilder
public OpenLineage.DataQualityMetricsInputDatasetFacetBuilder newDataQualityMetricsInputDatasetFacetBuilder()Creates a builder for DataQualityMetricsInputDatasetFacet- Returns:
- a new builder for DataQualityMetricsInputDatasetFacet
-
newDocumentationJobFacet
Factory method for DocumentationJobFacet- Parameters:
description
- The description of the job.- Returns:
- DocumentationJobFacet
-
newDocumentationJobFacetBuilder
Creates a builder for DocumentationJobFacet- Returns:
- a new builder for DocumentationJobFacet
-
newInputDatasetInputFacets
public OpenLineage.InputDatasetInputFacets newInputDatasetInputFacets(OpenLineage.DataQualityAssertionsDatasetFacet dataQualityAssertions, OpenLineage.InputStatisticsInputDatasetFacet inputStatistics, OpenLineage.DataQualityMetricsInputDatasetFacet dataQualityMetrics, OpenLineage.IcebergScanReportInputDatasetFacet iceberg_scan_report) Factory method for InputDatasetInputFacets- Parameters:
dataQualityAssertions
- the dataQualityAssertionsinputStatistics
- the inputStatisticsdataQualityMetrics
- the dataQualityMetricsiceberg_scan_report
- the iceberg_scan_report- Returns:
- InputDatasetInputFacets
-
newInputDatasetInputFacetsBuilder
Creates a builder for InputDatasetInputFacets- Returns:
- a new builder for InputDatasetInputFacets
-
newSQLJobFacet
Factory method for SQLJobFacet- Parameters:
query
- the query- Returns:
- SQLJobFacet
-
newSQLJobFacetBuilder
Creates a builder for SQLJobFacet- Returns:
- a new builder for SQLJobFacet
-
newOutputDataset
public OpenLineage.OutputDataset newOutputDataset(String namespace, String name, OpenLineage.DatasetFacets facets, OpenLineage.OutputDatasetOutputFacets outputFacets) Factory method for OutputDataset- Parameters:
namespace
- The namespace containing that datasetname
- The unique name for that dataset within that namespacefacets
- The facets for this datasetoutputFacets
- The output facets for this dataset- Returns:
- OutputDataset
-
newOutputDatasetBuilder
Creates a builder for OutputDataset- Returns:
- a new builder for OutputDataset
-
newTagsDatasetFacetFields
public OpenLineage.TagsDatasetFacetFields newTagsDatasetFacetFields(String key, String value, String source, String field) Factory method for TagsDatasetFacetFields- Parameters:
key
- Key that identifies the tagvalue
- The value of the fieldsource
- The source of the tag. INTEGRATION|USER|DBT CORE|SPARK|etc.field
- Identifies the field in a dataset if a tag applies to one- Returns:
- TagsDatasetFacetFields
-
newTagsDatasetFacetFieldsBuilder
Creates a builder for TagsDatasetFacetFields- Returns:
- a new builder for TagsDatasetFacetFields
-
newRootJob
Factory method for RootJob- Parameters:
namespace
- The namespace containing root jobname
- The unique name containing root job within that namespace- Returns:
- RootJob
-
newRootJobBuilder
Creates a builder for RootJob- Returns:
- a new builder for RootJob
-
newDocumentationDatasetFacet
Factory method for DocumentationDatasetFacet- Parameters:
description
- The description of the dataset.- Returns:
- DocumentationDatasetFacet
-
newDocumentationDatasetFacetBuilder
Creates a builder for DocumentationDatasetFacet- Returns:
- a new builder for DocumentationDatasetFacet
-
newSourceCodeLocationJobFacet
public OpenLineage.SourceCodeLocationJobFacet newSourceCodeLocationJobFacet(String type, URI url, String repoUrl, String path, String version, String tag, String branch) Factory method for SourceCodeLocationJobFacet- Parameters:
type
- the source control systemurl
- the full http URL to locate the filerepoUrl
- the URL to the repositorypath
- the path in the repo containing the source filesversion
- the current version deployed (not a branch name, the actual unique version)tag
- optional tag namebranch
- optional branch name- Returns:
- SourceCodeLocationJobFacet
-
newSourceCodeLocationJobFacetBuilder
Creates a builder for SourceCodeLocationJobFacet- Returns:
- a new builder for SourceCodeLocationJobFacet
-
newIcebergScanReportInputDatasetFacet
public OpenLineage.IcebergScanReportInputDatasetFacet newIcebergScanReportInputDatasetFacet(Double snapshotId, String filter, Double schemaId, List<String> projectedFieldNames, OpenLineage.IcebergScanReportInputDatasetFacetScanMetrics scanMetrics, OpenLineage.IcebergScanReportInputDatasetFacetMetadata metadata) Factory method for IcebergScanReportInputDatasetFacet- Parameters:
snapshotId
- Snapshot ID of the iceberg tablefilter
- Filter used to scan the iceberg tableschemaId
- Schema ID of the iceberg tableprojectedFieldNames
- List of field names that are projected from the iceberg tablescanMetrics
- the scanMetricsmetadata
- the metadata- Returns:
- IcebergScanReportInputDatasetFacet
-
newIcebergScanReportInputDatasetFacetBuilder
public OpenLineage.IcebergScanReportInputDatasetFacetBuilder newIcebergScanReportInputDatasetFacetBuilder()Creates a builder for IcebergScanReportInputDatasetFacet- Returns:
- a new builder for IcebergScanReportInputDatasetFacet
-
newDatasetTypeDatasetFacet
public OpenLineage.DatasetTypeDatasetFacet newDatasetTypeDatasetFacet(String datasetType, String subType) Factory method for DatasetTypeDatasetFacet- Parameters:
datasetType
- Dataset type, for example: FILE|STREAM|MODEL|TABLE|VIEW.subType
- Optional sub-type within the dataset type (e.g., BEST VALIDATION under MODEL CHECKPOINT).- Returns:
- DatasetTypeDatasetFacet
-
newDatasetTypeDatasetFacetBuilder
Creates a builder for DatasetTypeDatasetFacet- Returns:
- a new builder for DatasetTypeDatasetFacet
-
newJob
Factory method for Job- Parameters:
namespace
- The namespace containing that jobname
- The unique name for that job within that namespacefacets
- The job facets.- Returns:
- Job
-
newJobBuilder
Creates a builder for Job- Returns:
- a new builder for Job
-
newDatasetVersionDatasetFacet
Factory method for DatasetVersionDatasetFacet- Parameters:
datasetVersion
- The version of the dataset.- Returns:
- DatasetVersionDatasetFacet
-
newDatasetVersionDatasetFacetBuilder
Creates a builder for DatasetVersionDatasetFacet- Returns:
- a new builder for DatasetVersionDatasetFacet
-
newSymlinksDatasetFacetIdentifiers
public OpenLineage.SymlinksDatasetFacetIdentifiers newSymlinksDatasetFacetIdentifiers(String namespace, String name, String type) Factory method for SymlinksDatasetFacetIdentifiers- Parameters:
namespace
- The dataset namespacename
- The dataset nametype
- Identifier type- Returns:
- SymlinksDatasetFacetIdentifiers
-
newSymlinksDatasetFacetIdentifiersBuilder
public OpenLineage.SymlinksDatasetFacetIdentifiersBuilder newSymlinksDatasetFacetIdentifiersBuilder()Creates a builder for SymlinksDatasetFacetIdentifiers- Returns:
- a new builder for SymlinksDatasetFacetIdentifiers
-
newIcebergCommitReportOutputDatasetFacet
public OpenLineage.IcebergCommitReportOutputDatasetFacet newIcebergCommitReportOutputDatasetFacet(Double snapshotId, Double sequenceNumber, String operation, OpenLineage.IcebergCommitReportOutputDatasetFacetCommitMetrics commitMetrics, OpenLineage.IcebergCommitReportOutputDatasetFacetMetadata metadata) Factory method for IcebergCommitReportOutputDatasetFacet- Parameters:
snapshotId
- Snapshot ID of the iceberg tablesequenceNumber
- Sequence number of the iceberg tableoperation
- Operation that was performed on the iceberg tablecommitMetrics
- the commitMetricsmetadata
- the metadata- Returns:
- IcebergCommitReportOutputDatasetFacet
-
newIcebergCommitReportOutputDatasetFacetBuilder
public OpenLineage.IcebergCommitReportOutputDatasetFacetBuilder newIcebergCommitReportOutputDatasetFacetBuilder()Creates a builder for IcebergCommitReportOutputDatasetFacet- Returns:
- a new builder for IcebergCommitReportOutputDatasetFacet
-
newTagsJobFacetFields
public OpenLineage.TagsJobFacetFields newTagsJobFacetFields(String key, String value, String source) Factory method for TagsJobFacetFields- Parameters:
key
- Key that identifies the tagvalue
- The value of the fieldsource
- The source of the tag. INTEGRATION|USER|DBT CORE|SPARK|etc.- Returns:
- TagsJobFacetFields
-
newTagsJobFacetFieldsBuilder
Creates a builder for TagsJobFacetFields- Returns:
- a new builder for TagsJobFacetFields
-
newOutputDatasetFacet
- Returns:
- OutputDatasetFacet
-
newStaticDataset
public OpenLineage.StaticDataset newStaticDataset(String namespace, String name, OpenLineage.DatasetFacets facets) Factory method for StaticDataset- Parameters:
namespace
- The namespace containing that datasetname
- The unique name for that dataset within that namespacefacets
- The facets for this dataset- Returns:
- StaticDataset
-
newStaticDatasetBuilder
Creates a builder for StaticDataset- Returns:
- a new builder for StaticDataset
-
newTagsRunFacet
Factory method for TagsRunFacet- Parameters:
tags
- The tags applied to the run facet- Returns:
- TagsRunFacet
-
newTagsRunFacetBuilder
Creates a builder for TagsRunFacet- Returns:
- a new builder for TagsRunFacet
-
newLifecycleStateChangeDatasetFacet
public OpenLineage.LifecycleStateChangeDatasetFacet newLifecycleStateChangeDatasetFacet(OpenLineage.LifecycleStateChangeDatasetFacet.LifecycleStateChange lifecycleStateChange, OpenLineage.LifecycleStateChangeDatasetFacetPreviousIdentifier previousIdentifier) Factory method for LifecycleStateChangeDatasetFacet- Parameters:
lifecycleStateChange
- The lifecycle state change.previousIdentifier
- Previous name of the dataset in case of renaming it.- Returns:
- LifecycleStateChangeDatasetFacet
-
newLifecycleStateChangeDatasetFacetBuilder
public OpenLineage.LifecycleStateChangeDatasetFacetBuilder newLifecycleStateChangeDatasetFacetBuilder()Creates a builder for LifecycleStateChangeDatasetFacet- Returns:
- a new builder for LifecycleStateChangeDatasetFacet
-
newRunEvent
public OpenLineage.RunEvent newRunEvent(ZonedDateTime eventTime, OpenLineage.RunEvent.EventType eventType, OpenLineage.Run run, OpenLineage.Job job, List<OpenLineage.InputDataset> inputs, List<OpenLineage.OutputDataset> outputs) Factory method for RunEvent- Parameters:
eventTime
- the time the event occurred ateventType
- the current transition of the run state. It is required to issue 1 START event and 1 of [ COMPLETE, ABORT, FAIL ] event per run. Additional events with OTHER eventType can be added to the same run. For example to send additional metadata after the run is completerun
- the runjob
- the jobinputs
- The set of **input** datasets.outputs
- The set of **output** datasets.- Returns:
- RunEvent
-
newRunEventBuilder
Creates a builder for RunEvent- Returns:
- a new builder for RunEvent
-
newIcebergCommitReportOutputDatasetFacetMetadata
public OpenLineage.IcebergCommitReportOutputDatasetFacetMetadata newIcebergCommitReportOutputDatasetFacetMetadata()Factory method for IcebergCommitReportOutputDatasetFacetMetadata- Returns:
- IcebergCommitReportOutputDatasetFacetMetadata
-
newIcebergCommitReportOutputDatasetFacetMetadataBuilder
public OpenLineage.IcebergCommitReportOutputDatasetFacetMetadataBuilder newIcebergCommitReportOutputDatasetFacetMetadataBuilder()Creates a builder for IcebergCommitReportOutputDatasetFacetMetadata- Returns:
- a new builder for IcebergCommitReportOutputDatasetFacetMetadata
-
newTagsDatasetFacet
public OpenLineage.TagsDatasetFacet newTagsDatasetFacet(List<OpenLineage.TagsDatasetFacetFields> tags) Factory method for TagsDatasetFacet- Parameters:
tags
- The tags applied to the dataset facet- Returns:
- TagsDatasetFacet
-
newTagsDatasetFacetBuilder
Creates a builder for TagsDatasetFacet- Returns:
- a new builder for TagsDatasetFacet
-
newRootRun
Factory method for RootRun- Parameters:
runId
- The globally unique ID of the root run associated with the root job.- Returns:
- RootRun
-
newRootRunBuilder
Creates a builder for RootRun- Returns:
- a new builder for RootRun
-
newRunFacet
- Returns:
- RunFacet
-
newOwnershipJobFacetOwners
Factory method for OwnershipJobFacetOwners- Parameters:
name
- the identifier of the owner of the Job. It is recommended to define this as a URN. For example application:foo, user:jdoe, team:datatype
- The type of ownership (optional)- Returns:
- OwnershipJobFacetOwners
-
newOwnershipJobFacetOwnersBuilder
Creates a builder for OwnershipJobFacetOwners- Returns:
- a new builder for OwnershipJobFacetOwners
-
newGcpLineageJobFacet
public OpenLineage.GcpLineageJobFacet newGcpLineageJobFacet(String displayName, OpenLineage.GcpLineageJobFacetOrigin origin) Factory method for GcpLineageJobFacet- Parameters:
displayName
- The name of the job to be used on UIorigin
- the origin- Returns:
- GcpLineageJobFacet
-
newGcpLineageJobFacetBuilder
Creates a builder for GcpLineageJobFacet- Returns:
- a new builder for GcpLineageJobFacet
-
newJobEvent
public OpenLineage.JobEvent newJobEvent(ZonedDateTime eventTime, OpenLineage.Job job, List<OpenLineage.InputDataset> inputs, List<OpenLineage.OutputDataset> outputs) Factory method for JobEvent- Parameters:
eventTime
- the time the event occurred atjob
- the jobinputs
- The set of **input** datasets.outputs
- The set of **output** datasets.- Returns:
- JobEvent
-
newJobEventBuilder
Creates a builder for JobEvent- Returns:
- a new builder for JobEvent
-
newOwnershipDatasetFacetOwners
public OpenLineage.OwnershipDatasetFacetOwners newOwnershipDatasetFacetOwners(String name, String type) Factory method for OwnershipDatasetFacetOwners- Parameters:
name
- the identifier of the owner of the Dataset. It is recommended to define this as a URN. For example application:foo, user:jdoe, team:datatype
- The type of ownership (optional)- Returns:
- OwnershipDatasetFacetOwners
-
newOwnershipDatasetFacetOwnersBuilder
Creates a builder for OwnershipDatasetFacetOwners- Returns:
- a new builder for OwnershipDatasetFacetOwners
-
newExtractionErrorRunFacet
public OpenLineage.ExtractionErrorRunFacet newExtractionErrorRunFacet(Long totalTasks, Long failedTasks, List<OpenLineage.ExtractionErrorRunFacetErrors> errors) Factory method for ExtractionErrorRunFacet- Parameters:
totalTasks
- The number of distinguishable tasks in a run that were processed by OpenLineage, whether successfully or not. Those could be, for example, distinct SQL statements.failedTasks
- The number of distinguishable tasks in a run that were processed not successfully by OpenLineage. Those could be, for example, distinct SQL statements.errors
- the errors- Returns:
- ExtractionErrorRunFacet
-
newExtractionErrorRunFacetBuilder
Creates a builder for ExtractionErrorRunFacet- Returns:
- a new builder for ExtractionErrorRunFacet
-
newDataQualityMetricsInputDatasetFacetColumnMetrics
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetrics newDataQualityMetricsInputDatasetFacetColumnMetrics()Factory method for DataQualityMetricsInputDatasetFacetColumnMetrics- Returns:
- DataQualityMetricsInputDatasetFacetColumnMetrics
-
newDataQualityMetricsInputDatasetFacetColumnMetricsBuilder
public OpenLineage.DataQualityMetricsInputDatasetFacetColumnMetricsBuilder newDataQualityMetricsInputDatasetFacetColumnMetricsBuilder()Creates a builder for DataQualityMetricsInputDatasetFacetColumnMetrics- Returns:
- a new builder for DataQualityMetricsInputDatasetFacetColumnMetrics
-
newInputField
public OpenLineage.InputField newInputField(String namespace, String name, String field, List<OpenLineage.InputFieldTransformations> transformations) Factory method for InputField- Parameters:
namespace
- The input dataset namespacename
- The input dataset namefield
- The input fieldtransformations
- the transformations- Returns:
- InputField
-
newInputFieldBuilder
Creates a builder for InputField- Returns:
- a new builder for InputField
-
newInputStatisticsInputDatasetFacet
public OpenLineage.InputStatisticsInputDatasetFacet newInputStatisticsInputDatasetFacet(Long rowCount, Long size, Long fileCount) Factory method for InputStatisticsInputDatasetFacet- Parameters:
rowCount
- The number of rows readsize
- The size in bytes readfileCount
- The number of files read- Returns:
- InputStatisticsInputDatasetFacet
-
newInputStatisticsInputDatasetFacetBuilder
public OpenLineage.InputStatisticsInputDatasetFacetBuilder newInputStatisticsInputDatasetFacetBuilder()Creates a builder for InputStatisticsInputDatasetFacet- Returns:
- a new builder for InputStatisticsInputDatasetFacet
-
newJobFacets
public OpenLineage.JobFacets newJobFacets(OpenLineage.JobTypeJobFacet jobType, OpenLineage.SourceCodeJobFacet sourceCode, OpenLineage.GcpLineageJobFacet gcp_lineage, OpenLineage.SQLJobFacet sql, OpenLineage.OwnershipJobFacet ownership, OpenLineage.SourceCodeLocationJobFacet sourceCodeLocation, OpenLineage.TagsJobFacet tags, OpenLineage.DocumentationJobFacet documentation) Factory method for JobFacets- Parameters:
jobType
- the jobTypesourceCode
- the sourceCodegcp_lineage
- the gcp_lineagesql
- the sqlownership
- the ownershipsourceCodeLocation
- the sourceCodeLocationtags
- the tagsdocumentation
- the documentation- Returns:
- JobFacets
-
newJobFacetsBuilder
Creates a builder for JobFacets- Returns:
- a new builder for JobFacets
-
newIcebergCommitReportOutputDatasetFacetCommitMetrics
public OpenLineage.IcebergCommitReportOutputDatasetFacetCommitMetrics newIcebergCommitReportOutputDatasetFacetCommitMetrics(Double totalDuration, Double attempts, Double addedDataFiles, Double removedDataFiles, Double totalDataFiles, Double addedDeleteFiles, Double addedEqualityDeleteFiles, Double addedPositionalDeleteFiles, Double addedDVs, Double removedDeleteFiles, Double removedEqualityDeleteFiles, Double removedPositionalDeleteFiles, Double removedDVs, Double totalDeleteFiles, Double addedRecords, Double removedRecords, Double totalRecords, Double addedFilesSizeInBytes, Double removedFilesSizeInBytes, Double totalFilesSizeInBytes, Double addedPositionalDeletes, Double removedPositionalDeletes, Double totalPositionalDeletes, Double addedEqualityDeletes, Double removedEqualityDeletes, Double totalEqualityDeletes) Factory method for IcebergCommitReportOutputDatasetFacetCommitMetrics- Parameters:
totalDuration
- Duration of the commit in MILLISECONDSattempts
- Number of attempts made to commit the iceberg tableaddedDataFiles
- Number of data files that are added during the commitremovedDataFiles
- Number of data files that are removed during the committotalDataFiles
- Total number of data files that are present in the iceberg tableaddedDeleteFiles
- Number of delete files that are added during the commitaddedEqualityDeleteFiles
- Number of added equality delete filesaddedPositionalDeleteFiles
- Number of added positional delete filesaddedDVs
- Number of added DVsremovedDeleteFiles
- Number of delete files that are removed during the commitremovedEqualityDeleteFiles
- Number of removed equality delete filesremovedPositionalDeleteFiles
- Number of removed positional delete filesremovedDVs
- Number of removed DVstotalDeleteFiles
- Total number of temporary delete files that are present in the iceberg tableaddedRecords
- Number of records that are added during the commitremovedRecords
- Number of records that are removed during the committotalRecords
- Number of records that are present in the iceberg tableaddedFilesSizeInBytes
- Number of files size in bytes that are added during the commitremovedFilesSizeInBytes
- Number of files size in bytes that are removed during the committotalFilesSizeInBytes
- Number of files size in bytes in the iceberg tableaddedPositionalDeletes
- Number of positional deletes that are added during the commitremovedPositionalDeletes
- Number of positional deletes that are removed during the committotalPositionalDeletes
- Number of positional deletes that are present in the iceberg tableaddedEqualityDeletes
- Number of equality deletes that are added during the commitremovedEqualityDeletes
- Number of equality deletes that are removed during the committotalEqualityDeletes
- Number of equality deletes that are present in the iceberg table- Returns:
- IcebergCommitReportOutputDatasetFacetCommitMetrics
-
newIcebergCommitReportOutputDatasetFacetCommitMetricsBuilder
public OpenLineage.IcebergCommitReportOutputDatasetFacetCommitMetricsBuilder newIcebergCommitReportOutputDatasetFacetCommitMetricsBuilder()Creates a builder for IcebergCommitReportOutputDatasetFacetCommitMetrics- Returns:
- a new builder for IcebergCommitReportOutputDatasetFacetCommitMetrics
-
newDatasetFacet
- Returns:
- DatasetFacet
-
newDeletedDatasetFacet
- Returns:
- a deleted DatasetFacet
-
newOwnershipDatasetFacet
public OpenLineage.OwnershipDatasetFacet newOwnershipDatasetFacet(List<OpenLineage.OwnershipDatasetFacetOwners> owners) Factory method for OwnershipDatasetFacet- Parameters:
owners
- The owners of the dataset.- Returns:
- OwnershipDatasetFacet
-
newOwnershipDatasetFacetBuilder
Creates a builder for OwnershipDatasetFacet- Returns:
- a new builder for OwnershipDatasetFacet
-
newEnvironmentVariablesRunFacet
public OpenLineage.EnvironmentVariablesRunFacet newEnvironmentVariablesRunFacet(List<OpenLineage.EnvironmentVariable> environmentVariables) Factory method for EnvironmentVariablesRunFacet- Parameters:
environmentVariables
- The environment variables for the run.- Returns:
- EnvironmentVariablesRunFacet
-
newEnvironmentVariablesRunFacetBuilder
Creates a builder for EnvironmentVariablesRunFacet- Returns:
- a new builder for EnvironmentVariablesRunFacet
-
newDatasetFacets
public OpenLineage.DatasetFacets newDatasetFacets(OpenLineage.DatasourceDatasetFacet dataSource, OpenLineage.DatasetVersionDatasetFacet version, OpenLineage.DatasetTypeDatasetFacet datasetType, OpenLineage.StorageDatasetFacet storage, OpenLineage.ColumnLineageDatasetFacet columnLineage, OpenLineage.LifecycleStateChangeDatasetFacet lifecycleStateChange, OpenLineage.TagsDatasetFacet tags, OpenLineage.DocumentationDatasetFacet documentation, OpenLineage.SchemaDatasetFacet schema, OpenLineage.OwnershipDatasetFacet ownership, OpenLineage.SymlinksDatasetFacet symlinks) Factory method for DatasetFacets- Parameters:
dataSource
- the dataSourceversion
- the versiondatasetType
- the datasetTypestorage
- the storagecolumnLineage
- the columnLineagelifecycleStateChange
- the lifecycleStateChangetags
- the tagsdocumentation
- the documentationschema
- the schemaownership
- the ownershipsymlinks
- the symlinks- Returns:
- DatasetFacets
-
newDatasetFacetsBuilder
Creates a builder for DatasetFacets- Returns:
- a new builder for DatasetFacets
-
newOwnershipJobFacet
public OpenLineage.OwnershipJobFacet newOwnershipJobFacet(List<OpenLineage.OwnershipJobFacetOwners> owners) Factory method for OwnershipJobFacet- Parameters:
owners
- The owners of the job.- Returns:
- OwnershipJobFacet
-
newOwnershipJobFacetBuilder
Creates a builder for OwnershipJobFacet- Returns:
- a new builder for OwnershipJobFacet
-
newParentRunFacetJob
Factory method for ParentRunFacetJob- Parameters:
namespace
- The namespace containing that jobname
- The unique name for that job within that namespace- Returns:
- ParentRunFacetJob
-
newParentRunFacetJobBuilder
Creates a builder for ParentRunFacetJob- Returns:
- a new builder for ParentRunFacetJob
-
newGcpLineageJobFacetOrigin
public OpenLineage.GcpLineageJobFacetOrigin newGcpLineageJobFacetOrigin(String sourceType, String name) Factory method for GcpLineageJobFacetOrigin- Parameters:
sourceType
- Type of the source. Possible values can be found in GCP documentation (https://cloud.google.com/data-catalog/docs/reference/data-lineage/rest/v1/projects.locations.processes#SourceType)name
- If the sourceType isn't CUSTOM, the value of this field should be a GCP resource name of the system, which reports lineage. The project and location parts of the resource name must match the project and location of the lineage resource being created. More details in GCP documentation https://cloud.google.com/data-catalog/docs/reference/data-lineage/rest/v1/projects.locations.processes#origin- Returns:
- GcpLineageJobFacetOrigin
-
newGcpLineageJobFacetOriginBuilder
Creates a builder for GcpLineageJobFacetOrigin- Returns:
- a new builder for GcpLineageJobFacetOrigin
-
newErrorMessageRunFacet
public OpenLineage.ErrorMessageRunFacet newErrorMessageRunFacet(String message, String programmingLanguage, String stackTrace) Factory method for ErrorMessageRunFacet- Parameters:
message
- A human-readable string representing error message generated by observed systemprogrammingLanguage
- Programming language the observed system uses.stackTrace
- A language-specific stack trace generated by observed system- Returns:
- ErrorMessageRunFacet
-
newErrorMessageRunFacetBuilder
Creates a builder for ErrorMessageRunFacet- Returns:
- a new builder for ErrorMessageRunFacet
-
newJobFacet
- Returns:
- JobFacet
-
newDeletedJobFacet
- Returns:
- a deleted JobFacet
-
newRunFacets
public OpenLineage.RunFacets newRunFacets(OpenLineage.ExternalQueryRunFacet externalQuery, OpenLineage.GcpDataprocRunFacet gcp_dataproc, OpenLineage.ExtractionErrorRunFacet extractionError, OpenLineage.ParentRunFacet parent, OpenLineage.NominalTimeRunFacet nominalTime, OpenLineage.TagsRunFacet tags, OpenLineage.ErrorMessageRunFacet errorMessage, OpenLineage.EnvironmentVariablesRunFacet environmentVariables, OpenLineage.ProcessingEngineRunFacet processing_engine) Factory method for RunFacets- Parameters:
externalQuery
- the externalQuerygcp_dataproc
- the gcp_dataprocextractionError
- the extractionErrorparent
- the parentnominalTime
- the nominalTimetags
- the tagserrorMessage
- the errorMessageenvironmentVariables
- the environmentVariablesprocessing_engine
- the processing_engine- Returns:
- RunFacets
-
newRunFacetsBuilder
Creates a builder for RunFacets- Returns:
- a new builder for RunFacets
-
newSchemaDatasetFacet
public OpenLineage.SchemaDatasetFacet newSchemaDatasetFacet(List<OpenLineage.SchemaDatasetFacetFields> fields) Factory method for SchemaDatasetFacet- Parameters:
fields
- The fields of the data source.- Returns:
- SchemaDatasetFacet
-
newSchemaDatasetFacetBuilder
Creates a builder for SchemaDatasetFacet- Returns:
- a new builder for SchemaDatasetFacet
-
newSourceCodeJobFacet
Factory method for SourceCodeJobFacet- Parameters:
language
- Language in which source code of this job was written.sourceCode
- Source code of this job.- Returns:
- SourceCodeJobFacet
-
newSourceCodeJobFacetBuilder
Creates a builder for SourceCodeJobFacet- Returns:
- a new builder for SourceCodeJobFacet
-
newIcebergScanReportInputDatasetFacetMetadata
public OpenLineage.IcebergScanReportInputDatasetFacetMetadata newIcebergScanReportInputDatasetFacetMetadata()Factory method for IcebergScanReportInputDatasetFacetMetadata- Returns:
- IcebergScanReportInputDatasetFacetMetadata
-
newIcebergScanReportInputDatasetFacetMetadataBuilder
public OpenLineage.IcebergScanReportInputDatasetFacetMetadataBuilder newIcebergScanReportInputDatasetFacetMetadataBuilder()Creates a builder for IcebergScanReportInputDatasetFacetMetadata- Returns:
- a new builder for IcebergScanReportInputDatasetFacetMetadata
-
newColumnLineageDatasetFacet
public OpenLineage.ColumnLineageDatasetFacet newColumnLineageDatasetFacet(OpenLineage.ColumnLineageDatasetFacetFields fields, List<OpenLineage.InputField> dataset) Factory method for ColumnLineageDatasetFacet- Parameters:
fields
- Column level lineage that maps output fields into input fields used to evaluate them.dataset
- Column level lineage that affects the whole dataset. This includes filtering, sorting, grouping (aggregates), joining, window functions, etc.- Returns:
- ColumnLineageDatasetFacet
-
newColumnLineageDatasetFacetBuilder
Creates a builder for ColumnLineageDatasetFacet- Returns:
- a new builder for ColumnLineageDatasetFacet
-
newDataQualityAssertionsDatasetFacet
public OpenLineage.DataQualityAssertionsDatasetFacet newDataQualityAssertionsDatasetFacet(List<OpenLineage.DataQualityAssertionsDatasetFacetAssertions> assertions) Factory method for DataQualityAssertionsDatasetFacet- Parameters:
assertions
- the assertions- Returns:
- DataQualityAssertionsDatasetFacet
-
newDataQualityAssertionsDatasetFacetBuilder
public OpenLineage.DataQualityAssertionsDatasetFacetBuilder newDataQualityAssertionsDatasetFacetBuilder()Creates a builder for DataQualityAssertionsDatasetFacet- Returns:
- a new builder for DataQualityAssertionsDatasetFacet
-
newDatasetEvent
public OpenLineage.DatasetEvent newDatasetEvent(ZonedDateTime eventTime, OpenLineage.StaticDataset dataset) Factory method for DatasetEvent- Parameters:
eventTime
- the time the event occurred atdataset
- the dataset- Returns:
- DatasetEvent
-
newDatasetEventBuilder
Creates a builder for DatasetEvent- Returns:
- a new builder for DatasetEvent
-
newTagsJobFacet
Factory method for TagsJobFacet- Parameters:
tags
- The tags applied to the job facet- Returns:
- TagsJobFacet
-
newTagsJobFacetBuilder
Creates a builder for TagsJobFacet- Returns:
- a new builder for TagsJobFacet
-
newProcessingEngineRunFacet
public OpenLineage.ProcessingEngineRunFacet newProcessingEngineRunFacet(String version, String name, String openlineageAdapterVersion) Factory method for ProcessingEngineRunFacet- Parameters:
version
- Processing engine version. Might be Airflow or Spark version.name
- Processing engine name, e.g. Airflow or SparkopenlineageAdapterVersion
- OpenLineage adapter package version. Might be e.g. OpenLineage Airflow integration package version- Returns:
- ProcessingEngineRunFacet
-
newProcessingEngineRunFacetBuilder
Creates a builder for ProcessingEngineRunFacet- Returns:
- a new builder for ProcessingEngineRunFacet
-
newLifecycleStateChangeDatasetFacetPreviousIdentifier
public OpenLineage.LifecycleStateChangeDatasetFacetPreviousIdentifier newLifecycleStateChangeDatasetFacetPreviousIdentifier(String name, String namespace) Factory method for LifecycleStateChangeDatasetFacetPreviousIdentifier- Parameters:
name
- the namenamespace
- the namespace- Returns:
- LifecycleStateChangeDatasetFacetPreviousIdentifier
-
newLifecycleStateChangeDatasetFacetPreviousIdentifierBuilder
public OpenLineage.LifecycleStateChangeDatasetFacetPreviousIdentifierBuilder newLifecycleStateChangeDatasetFacetPreviousIdentifierBuilder()Creates a builder for LifecycleStateChangeDatasetFacetPreviousIdentifier- Returns:
- a new builder for LifecycleStateChangeDatasetFacetPreviousIdentifier
-
newInputFieldTransformations
public OpenLineage.InputFieldTransformations newInputFieldTransformations(String type, String subtype, String description, Boolean masking) Factory method for InputFieldTransformations- Parameters:
type
- The type of the transformation. Allowed values are: DIRECT, INDIRECTsubtype
- The subtype of the transformationdescription
- a string representation of the transformation appliedmasking
- is transformation masking the data or not- Returns:
- InputFieldTransformations
-
newInputFieldTransformationsBuilder
Creates a builder for InputFieldTransformations- Returns:
- a new builder for InputFieldTransformations
-
newEnvironmentVariable
Factory method for EnvironmentVariable- Parameters:
name
- The name of the environment variable.value
- The value of the environment variable.- Returns:
- EnvironmentVariable
-
newEnvironmentVariableBuilder
Creates a builder for EnvironmentVariable- Returns:
- a new builder for EnvironmentVariable
-
newIcebergScanReportInputDatasetFacetScanMetrics
public OpenLineage.IcebergScanReportInputDatasetFacetScanMetrics newIcebergScanReportInputDatasetFacetScanMetrics(Double totalPlanningDuration, Double resultDataFiles, Double resultDeleteFiles, Double totalDataManifests, Double totalDeleteManifests, Double scannedDataManifests, Double skippedDataManifests, Double totalFileSizeInBytes, Double totalDeleteFileSizeInBytes, Double skippedDataFiles, Double skippedDeleteFiles, Double scannedDeleteManifests, Double skippedDeleteManifests, Double indexedDeleteFiles, Double equalityDeleteFiles, Double positionalDeleteFiles) Factory method for IcebergScanReportInputDatasetFacetScanMetrics- Parameters:
totalPlanningDuration
- Duration of the scan in MILLISECONDSresultDataFiles
- List of data files that are read during the scanresultDeleteFiles
- List of delete files that are read during the scantotalDataManifests
- Total number of manifests that are scanned during the scantotalDeleteManifests
- Total number of delete manifests that are scanned during the scanscannedDataManifests
- Number of data manifests that are scanned during the scanskippedDataManifests
- Number of data manifests that are skipped during the scantotalFileSizeInBytes
- Total file size in bytes that are read during the scantotalDeleteFileSizeInBytes
- Total delete file size in bytes that are read during the scanskippedDataFiles
- Number of data files that are skipped during the scanskippedDeleteFiles
- Number of delete files that are skipped during the scanscannedDeleteManifests
- Number of delete manifests that are scanned during the scanskippedDeleteManifests
- Number of delete manifests that are skipped during the scanindexedDeleteFiles
- Number of delete files that are indexed during the scanequalityDeleteFiles
- Number of delete files that are equality indexed during the scanpositionalDeleteFiles
- Number of delete files that are positional indexed during the scan- Returns:
- IcebergScanReportInputDatasetFacetScanMetrics
-
newIcebergScanReportInputDatasetFacetScanMetricsBuilder
public OpenLineage.IcebergScanReportInputDatasetFacetScanMetricsBuilder newIcebergScanReportInputDatasetFacetScanMetricsBuilder()Creates a builder for IcebergScanReportInputDatasetFacetScanMetrics- Returns:
- a new builder for IcebergScanReportInputDatasetFacetScanMetrics
-
newTagsRunFacetFields
public OpenLineage.TagsRunFacetFields newTagsRunFacetFields(String key, String value, String source) Factory method for TagsRunFacetFields- Parameters:
key
- Key that identifies the tagvalue
- The value of the fieldsource
- The source of the tag. INTEGRATION|USER|DBT CORE|SPARK|etc.- Returns:
- TagsRunFacetFields
-
newTagsRunFacetFieldsBuilder
Creates a builder for TagsRunFacetFields- Returns:
- a new builder for TagsRunFacetFields
-
newDataQualityAssertionsDatasetFacetAssertions
public OpenLineage.DataQualityAssertionsDatasetFacetAssertions newDataQualityAssertionsDatasetFacetAssertions(String assertion, Boolean success, String column) Factory method for DataQualityAssertionsDatasetFacetAssertions- Parameters:
assertion
- Type of expectation test that dataset is subjected tosuccess
- the successcolumn
- Column that expectation is testing. It should match the name provided in SchemaDatasetFacet. If column field is empty, then expectation refers to whole dataset.- Returns:
- DataQualityAssertionsDatasetFacetAssertions
-
newDataQualityAssertionsDatasetFacetAssertionsBuilder
public OpenLineage.DataQualityAssertionsDatasetFacetAssertionsBuilder newDataQualityAssertionsDatasetFacetAssertionsBuilder()Creates a builder for DataQualityAssertionsDatasetFacetAssertions- Returns:
- a new builder for DataQualityAssertionsDatasetFacetAssertions
-
newParentRunFacetRun
Factory method for ParentRunFacetRun- Parameters:
runId
- The globally unique ID of the run associated with the job.- Returns:
- ParentRunFacetRun
-
newParentRunFacetRunBuilder
Creates a builder for ParentRunFacetRun- Returns:
- a new builder for ParentRunFacetRun
-
newGcpDataprocRunFacet
public OpenLineage.GcpDataprocRunFacet newGcpDataprocRunFacet(String appId, String appName, String batchId, String batchUuid, String clusterName, String clusterUuid, String jobId, String jobUuid, String projectId, String queryNodeName, String jobType, String sessionId, String sessionUuid) Factory method for GcpDataprocRunFacet- Parameters:
appId
- Application ID set by the resource manager. For spark jobs, it is set in the spark configuration of the current context.appName
- App name which may be provided by the user, or some default is used by the resource manager. For spark jobs, it is set in the spark configuration of the current context.batchId
- Populated only for Dataproc serverless batches. The resource id of the batch.batchUuid
- Populated only for Dataproc serverless batches. A UUID generated by the service when it creates the batch.clusterName
- Populated only for Dataproc GCE workloads. The cluster name is unique within a GCP project.clusterUuid
- Populated only for Dataproc GCE workloads. A UUID generated by the service at the time of cluster creation.jobId
- Populated only for Dataproc GCE workloads. If not specified by the user, the job ID will be provided by the service.jobUuid
- Populated only for Dataproc GCE workloads. A UUID that uniquely identifies a job within the project over time.projectId
- The GCP project ID that the resource belongs to.queryNodeName
- The name of the query node in the executed Spark Plan. Often used to describe the command being executed.jobType
- Identifies whether the process is a job (on a Dataproc cluster), a batch or a session.sessionId
- Populated only for Dataproc serverless interactive sessions. The resource id of the session, used for URL generation.sessionUuid
- Populated only for Dataproc serverless interactive sessions. A UUID generated by the service when it creates the session.- Returns:
- GcpDataprocRunFacet
-
newGcpDataprocRunFacetBuilder
Creates a builder for GcpDataprocRunFacet- Returns:
- a new builder for GcpDataprocRunFacet
-
newColumnLineageDatasetFacetFields
Factory method for ColumnLineageDatasetFacetFields- Returns:
- ColumnLineageDatasetFacetFields
-
newColumnLineageDatasetFacetFieldsBuilder
public OpenLineage.ColumnLineageDatasetFacetFieldsBuilder newColumnLineageDatasetFacetFieldsBuilder()Creates a builder for ColumnLineageDatasetFacetFields- Returns:
- a new builder for ColumnLineageDatasetFacetFields
-
newSymlinksDatasetFacet
public OpenLineage.SymlinksDatasetFacet newSymlinksDatasetFacet(List<OpenLineage.SymlinksDatasetFacetIdentifiers> identifiers) Factory method for SymlinksDatasetFacet- Parameters:
identifiers
- the identifiers- Returns:
- SymlinksDatasetFacet
-
newSymlinksDatasetFacetBuilder
Creates a builder for SymlinksDatasetFacet- Returns:
- a new builder for SymlinksDatasetFacet
-
newStorageDatasetFacet
public OpenLineage.StorageDatasetFacet newStorageDatasetFacet(String storageLayer, String fileFormat) Factory method for StorageDatasetFacet- Parameters:
storageLayer
- Storage layer provider with allowed values: iceberg, delta.fileFormat
- File format with allowed values: parquet, orc, avro, json, csv, text, xml.- Returns:
- StorageDatasetFacet
-
newStorageDatasetFacetBuilder
Creates a builder for StorageDatasetFacet- Returns:
- a new builder for StorageDatasetFacet
-
newInputDataset
public OpenLineage.InputDataset newInputDataset(String namespace, String name, OpenLineage.DatasetFacets facets, OpenLineage.InputDatasetInputFacets inputFacets) Factory method for InputDataset- Parameters:
namespace
- The namespace containing that datasetname
- The unique name for that dataset within that namespacefacets
- The facets for this datasetinputFacets
- The input facets for this dataset.- Returns:
- InputDataset
-
newInputDatasetBuilder
Creates a builder for InputDataset- Returns:
- a new builder for InputDataset
-
newDatasourceDatasetFacet
Factory method for DatasourceDatasetFacet- Parameters:
name
- the nameuri
- the uri- Returns:
- DatasourceDatasetFacet
-
newDatasourceDatasetFacetBuilder
Creates a builder for DatasourceDatasetFacet- Returns:
- a new builder for DatasourceDatasetFacet
-