openlineage-python 1.15.0__tar.gz → 1.17.0__tar.gz

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlineage-python
-Version: 1.15.0
+Version: 1.17.0
 Summary: OpenLineage Python Client
 Author-email: OpenLineage <info@openlineage.io>
 Keywords: openlineage

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/constants.py

@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from __future__ import annotations
 
-__version__ = "1.15.0"
+__version__ = "1.17.0"
 
 DEFAULT_TIMEOUT_MS = 5000
 DEFAULT_NAMESPACE_NAME = "default"

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/base.py

@@ -6,7 +6,7 @@ from __future__ import annotations
 from enum import Enum
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.constants import DEFAULT_PRODUCER
 from openlineage.client.utils import RedactMixin
 
@@ -18,13 +18,13 @@ def set_producer(producer: str) -> None:
     PRODUCER = producer
 
 
-@define(kw_only=True)
+@attr.define(kw_only=True)
 class BaseEvent(RedactMixin):
-    eventTime: str = field()  # noqa: N815
+    eventTime: str = attr.field()  # noqa: N815
     """the time the event occurred at"""
 
-    producer: str = field(default="", kw_only=True)
-    schemaURL: str = field(  # noqa: N815
+    producer: str = attr.field(default="", kw_only=True)
+    schemaURL: str = attr.field(  # noqa: N815
         default="https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/BaseEvent", init=False
     )
     _base_skip_redact: ClassVar[list[str]] = ["producer", "schemaURL"]
@@ -66,12 +66,12 @@ class BaseEvent(RedactMixin):
         urlparse(value)
 
 
-@define
+@attr.define
 class BaseFacet(RedactMixin):
     """all fields of the base facet are prefixed with _ to avoid name conflicts in facets"""
 
-    _producer: str = field(default="", kw_only=True)
-    _schemaURL: str = field(  # noqa: N815
+    _producer: str = attr.field(default="", kw_only=True)
+    _schemaURL: str = attr.field(  # noqa: N815
         default="https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/BaseFacet", init=False
     )
     _base_skip_redact: ClassVar[list[str]] = ["_producer", "_schemaURL"]
@@ -103,7 +103,7 @@ class BaseFacet(RedactMixin):
         urlparse(value)
 
 
-@define
+@attr.define
 class Dataset(RedactMixin):
     namespace: str
     """The namespace containing that dataset"""
@@ -111,7 +111,7 @@ class Dataset(RedactMixin):
     name: str
     """The unique name for that dataset within that namespace"""
 
-    facets: dict[str, DatasetFacet] | None = field(factory=dict, kw_only=True)  # type: ignore[assignment]
+    facets: dict[str, DatasetFacet] | None = attr.field(factory=dict, kw_only=True)
     """The facets for this dataset"""
 
     _skip_redact: ClassVar[list[str]] = ["namespace", "name"]
@@ -121,7 +121,7 @@ class Dataset(RedactMixin):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/Dataset"
 
 
-@define(kw_only=True)
+@attr.define(kw_only=True)
 class DatasetEvent(BaseEvent):
     dataset: StaticDataset
 
@@ -130,11 +130,11 @@ class DatasetEvent(BaseEvent):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/DatasetEvent"
 
 
-@define
+@attr.define
 class DatasetFacet(BaseFacet):
     """A Dataset Facet"""
 
-    _deleted: bool | None = field(default=None, kw_only=True)
+    _deleted: bool | None = attr.field(default=None, kw_only=True)
     """set to true to delete a facet"""
 
     @staticmethod
@@ -157,11 +157,11 @@ class EventType(Enum):
     OTHER = "OTHER"
 
 
-@define
+@attr.define
 class InputDataset(Dataset):
     """An input dataset"""
 
-    inputFacets: dict[str, InputDatasetFacet] | None = field(factory=dict)  # type: ignore[assignment]# noqa: N815
+    inputFacets: dict[str, InputDatasetFacet] | None = attr.field(factory=dict)  # noqa: N815
     """The input facets for this dataset."""
 
     _additional_skip_redact: ClassVar[list[str]] = ["namespace", "name"]
@@ -171,7 +171,7 @@ class InputDataset(Dataset):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/InputDataset"
 
 
-@define
+@attr.define
 class InputDatasetFacet(BaseFacet):
     """An Input Dataset Facet"""
 
@@ -180,7 +180,7 @@ class InputDatasetFacet(BaseFacet):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/InputDatasetFacet"
 
 
-@define
+@attr.define
 class Job(RedactMixin):
     namespace: str
     """The namespace containing that job"""
@@ -188,7 +188,7 @@ class Job(RedactMixin):
     name: str
     """The unique name for that job within that namespace"""
 
-    facets: dict[str, JobFacet] | None = field(factory=dict)  # type: ignore[assignment]
+    facets: dict[str, JobFacet] | None = attr.field(factory=dict)
     """The job facets."""
 
     _skip_redact: ClassVar[list[str]] = ["namespace", "name"]
@@ -198,13 +198,13 @@ class Job(RedactMixin):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/Job"
 
 
-@define(kw_only=True)
+@attr.define(kw_only=True)
 class JobEvent(BaseEvent):
     job: Job
-    inputs: list[InputDataset] | None = field(factory=list)  # type: ignore[assignment]
+    inputs: list[InputDataset] | None = attr.field(factory=list)
     """The set of **input** datasets."""
 
-    outputs: list[OutputDataset] | None = field(factory=list)  # type: ignore[assignment]
+    outputs: list[OutputDataset] | None = attr.field(factory=list)
     """The set of **output** datasets."""
 
     @staticmethod
@@ -212,11 +212,11 @@ class JobEvent(BaseEvent):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/JobEvent"
 
 
-@define
+@attr.define
 class JobFacet(BaseFacet):
     """A Job Facet"""
 
-    _deleted: bool | None = field(default=None, kw_only=True)
+    _deleted: bool | None = attr.field(default=None, kw_only=True)
     """set to true to delete a facet"""
 
     @staticmethod
@@ -224,11 +224,11 @@ class JobFacet(BaseFacet):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/JobFacet"
 
 
-@define
+@attr.define
 class OutputDataset(Dataset):
     """An output dataset"""
 
-    outputFacets: dict[str, OutputDatasetFacet] | None = field(factory=dict)  # type: ignore[assignment]# noqa: N815
+    outputFacets: dict[str, OutputDatasetFacet] | None = attr.field(factory=dict)  # noqa: N815
     """The output facets for this dataset"""
 
     _additional_skip_redact: ClassVar[list[str]] = ["namespace", "name"]
@@ -238,7 +238,7 @@ class OutputDataset(Dataset):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/OutputDataset"
 
 
-@define
+@attr.define
 class OutputDatasetFacet(BaseFacet):
     """An Output Dataset Facet"""
 
@@ -247,12 +247,12 @@ class OutputDatasetFacet(BaseFacet):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/OutputDatasetFacet"
 
 
-@define
+@attr.define
 class Run(RedactMixin):
-    runId: str = field()  # noqa: N815
+    runId: str = attr.field()  # noqa: N815
     """The globally unique ID of the run associated with the job."""
 
-    facets: dict[str, RunFacet] | None = field(factory=dict)  # type: ignore[assignment]
+    facets: dict[str, RunFacet] | None = attr.field(factory=dict)
     """The run facets."""
 
     _skip_redact: ClassVar[list[str]] = ["runId"]
@@ -268,20 +268,20 @@ class Run(RedactMixin):
         UUID(value)
 
 
-@define(kw_only=True)
+@attr.define(kw_only=True)
 class RunEvent(BaseEvent):
     run: Run
     job: Job
-    eventType: EventType | None = field(default=None)  # noqa: N815
+    eventType: EventType | None = attr.field(default=None)  # noqa: N815
     """
     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 complete
     """
-    inputs: list[InputDataset] | None = field(factory=list)  # type: ignore[assignment]
+    inputs: list[InputDataset] | None = attr.field(factory=list)
     """The set of **input** datasets."""
 
-    outputs: list[OutputDataset] | None = field(factory=list)  # type: ignore[assignment]
+    outputs: list[OutputDataset] | None = attr.field(factory=list)
     """The set of **output** datasets."""
 
     _additional_skip_redact: ClassVar[list[str]] = ["eventType", "eventTime"]
@@ -291,7 +291,7 @@ class RunEvent(BaseEvent):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunEvent"
 
 
-@define
+@attr.define
 class RunFacet(BaseFacet):
     """A Run Facet"""
 
@@ -300,7 +300,7 @@ class RunFacet(BaseFacet):
         return "https://openlineage.io/spec/2-0-2/OpenLineage.json#/$defs/RunFacet"
 
 
-@define
+@attr.define
 class StaticDataset(Dataset):
     """A Dataset sent within static metadata events"""
 

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/column_lineage_dataset.py

@@ -5,35 +5,35 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import DatasetFacet
 from openlineage.client.utils import RedactMixin
 
 
-@define
+@attr.define
 class ColumnLineageDatasetFacet(DatasetFacet):
     fields: dict[str, Fields]
     """Column level lineage that maps output fields into input fields used to evaluate them."""
 
     @staticmethod
     def _get_schema() -> str:
-        return "https://openlineage.io/spec/facets/1-0-2/ColumnLineageDatasetFacet.json#/$defs/ColumnLineageDatasetFacet"
+        return "https://openlineage.io/spec/facets/1-1-0/ColumnLineageDatasetFacet.json#/$defs/ColumnLineageDatasetFacet"
 
 
-@define
+@attr.define
 class Fields(RedactMixin):
     inputFields: list[InputField]  # noqa: N815
-    transformationDescription: str | None = field(default=None)  # noqa: N815
+    transformationDescription: str | None = attr.field(default=None)  # noqa: N815
     """a string representation of the transformation applied"""
 
-    transformationType: str | None = field(default=None)  # noqa: N815
+    transformationType: str | None = attr.field(default=None)  # noqa: N815
     """
     IDENTITY|MASKED reflects a clearly defined behavior. IDENTITY: exact same as input; MASKED: no
     original data available (like a hash of PII for example)
     """
 
 
-@define
+@attr.define
 class InputField(RedactMixin):
     namespace: str
     """The input dataset namespace"""
@@ -44,4 +44,22 @@ class InputField(RedactMixin):
     field: str
     """The input field"""
 
+    transformations: list[Transformation] | None = attr.field(factory=list)
     _skip_redact: ClassVar[list[str]] = ["namespace", "name", "field"]
+
+
+@attr.define
+class Transformation(RedactMixin):
+    type: str
+    """The type of the transformation. Allowed values are: DIRECT, INDIRECT"""
+
+    subtype: str | None = attr.field(default=None)
+    """The subtype of the transformation"""
+
+    description: str | None = attr.field(default=None)
+    """a string representation of the transformation applied"""
+
+    masking: bool | None = attr.field(default=None)
+    """is transformation masking the data or not"""
+
+    _skip_redact: ClassVar[list[str]] = ["type", "subtype", "masking"]

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/data_quality_assertions_dataset.py

@@ -5,18 +5,18 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import InputDatasetFacet
 from openlineage.client.utils import RedactMixin
 
 
-@define
+@attr.define
 class Assertion(RedactMixin):
     assertion: str
     """Type of expectation test that dataset is subjected to"""
 
     success: bool
-    column: str | None = field(default=None)
+    column: str | None = attr.field(default=None)
     """
     Column that expectation is testing. It should match the name provided in SchemaDatasetFacet. If
     column field is empty, then expectation refers to whole dataset.
@@ -24,7 +24,7 @@ class Assertion(RedactMixin):
     _skip_redact: ClassVar[list[str]] = ["column"]
 
 
-@define
+@attr.define
 class DataQualityAssertionsDatasetFacet(InputDatasetFacet):
     """list of tests performed on dataset or dataset columns, and their results"""
 

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/data_quality_metrics_input_dataset.py

@@ -3,43 +3,43 @@
 
 from __future__ import annotations
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import InputDatasetFacet
 from openlineage.client.utils import RedactMixin
 
 
-@define
+@attr.define
 class ColumnMetrics(RedactMixin):
-    nullCount: int | None = field(default=None)  # noqa: N815
+    nullCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of null values in this column for the rows evaluated"""
 
-    distinctCount: int | None = field(default=None)  # noqa: N815
+    distinctCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of distinct values in this column for the rows evaluated"""
 
-    sum: float | None = field(default=None)
+    sum: float | None = attr.field(default=None)
     """The total sum of values in this column for the rows evaluated"""
 
-    count: float | None = field(default=None)
+    count: float | None = attr.field(default=None)
     """The number of values in this column"""
 
-    min: float | None = field(default=None)
-    max: float | None = field(default=None)
-    quantiles: dict[str, float] | None = field(factory=dict)  # type: ignore[assignment]
+    min: float | None = attr.field(default=None)
+    max: float | None = attr.field(default=None)
+    quantiles: dict[str, float] | None = attr.field(factory=dict)
     """The property key is the quantile. Examples: 0.1 0.25 0.5 0.75 1"""
 
 
-@define
+@attr.define
 class DataQualityMetricsInputDatasetFacet(InputDatasetFacet):
     columnMetrics: dict[str, ColumnMetrics]  # noqa: N815
     """The property key is the column name"""
 
-    rowCount: int | None = field(default=None)  # noqa: N815
+    rowCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of rows evaluated"""
 
-    bytes: int | None = field(default=None)
+    bytes: int | None = attr.field(default=None)
     """The size in bytes"""
 
-    fileCount: int | None = field(default=None)  # noqa: N815
+    fileCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of files evaluated"""
 
     @staticmethod

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/dataset_version_dataset.py

@@ -3,11 +3,11 @@
 
 from __future__ import annotations
 
-from attr import define
+import attr
 from openlineage.client.generated.base import DatasetFacet
 
 
-@define
+@attr.define
 class DatasetVersionDatasetFacet(DatasetFacet):
     datasetVersion: str  # noqa: N815
     """The version of the dataset."""

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/datasource_dataset.py

@@ -5,14 +5,14 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import DatasetFacet
 
 
-@define
+@attr.define
 class DatasourceDatasetFacet(DatasetFacet):
-    name: str | None = field(default=None)
-    uri: str | None = field(default=None)
+    name: str | None = attr.field(default=None)
+    uri: str | None = attr.field(default=None)
     _additional_skip_redact: ClassVar[list[str]] = ["name", "uri"]
 
     @staticmethod

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/documentation_dataset.py

@@ -3,11 +3,11 @@
 
 from __future__ import annotations
 
-from attr import define
+import attr
 from openlineage.client.generated.base import DatasetFacet
 
 
-@define
+@attr.define
 class DocumentationDatasetFacet(DatasetFacet):
     description: str
     """The description of the dataset."""

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/documentation_job.py

@@ -3,11 +3,11 @@
 
 from __future__ import annotations
 
-from attr import define
+import attr
 from openlineage.client.generated.base import JobFacet
 
 
-@define
+@attr.define
 class DocumentationJobFacet(JobFacet):
     description: str
     """The description of the job."""

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/error_message_run.py

@@ -5,11 +5,11 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import RunFacet
 
 
-@define
+@attr.define
 class ErrorMessageRunFacet(RunFacet):
     message: str
     """A human-readable string representing error message generated by observed system"""
@@ -17,7 +17,7 @@ class ErrorMessageRunFacet(RunFacet):
     programmingLanguage: str  # noqa: N815
     """Programming language the observed system uses."""
 
-    stackTrace: str | None = field(default=None)  # noqa: N815
+    stackTrace: str | None = attr.field(default=None)  # noqa: N815
     """A language-specific stack trace generated by observed system"""
 
     _additional_skip_redact: ClassVar[list[str]] = ["programmingLanguage"]

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/external_query_run.py

@@ -3,11 +3,11 @@
 
 from __future__ import annotations
 
-from attr import define
+import attr
 from openlineage.client.generated.base import RunFacet
 
 
-@define
+@attr.define
 class ExternalQueryRunFacet(RunFacet):
     externalQueryId: str  # noqa: N815
     """Identifier for the external system"""

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/extraction_error_run.py

@@ -3,29 +3,29 @@
 
 from __future__ import annotations
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import RunFacet
 from openlineage.client.utils import RedactMixin
 
 
-@define
+@attr.define
 class Error(RedactMixin):
     errorMessage: str  # noqa: N815
     """Text representation of extraction error message."""
 
-    stackTrace: str | None = field(default=None)  # noqa: N815
+    stackTrace: str | None = attr.field(default=None)  # noqa: N815
     """Stack trace of extraction error message"""
 
-    task: str | None = field(default=None)
+    task: str | None = attr.field(default=None)
     """
     Text representation of task that failed. This can be, for example, SQL statement that parser could
     not interpret.
     """
-    taskNumber: int | None = field(default=None)  # noqa: N815
+    taskNumber: int | None = attr.field(default=None)  # noqa: N815
     """Order of task (counted from 0)."""
 
 
-@define
+@attr.define
 class ExtractionErrorRunFacet(RunFacet):
     totalTasks: int  # noqa: N815
     """

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/job_type_job.py

@@ -3,11 +3,11 @@
 
 from __future__ import annotations
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import JobFacet
 
 
-@define
+@attr.define
 class JobTypeJobFacet(JobFacet):
     processingType: str  # noqa: N815
     """Job processing type like: BATCH or STREAMING"""
@@ -15,7 +15,7 @@ class JobTypeJobFacet(JobFacet):
     integration: str
     """OpenLineage integration type of this job: SPARK|DBT|AIRFLOW|FLINK"""
 
-    jobType: str | None = field(default=None)  # noqa: N815
+    jobType: str | None = attr.field(default=None)  # noqa: N815
     """Run type like: QUERY|COMMAND|DAG|TASK|JOB|MODEL"""
 
     @staticmethod

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/lifecycle_state_change_dataset.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 
 from enum import Enum
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import DatasetFacet
 from openlineage.client.utils import RedactMixin
 
@@ -21,12 +21,12 @@ class LifecycleStateChange(Enum):
     TRUNCATE = "TRUNCATE"
 
 
-@define
+@attr.define
 class LifecycleStateChangeDatasetFacet(DatasetFacet):
     lifecycleStateChange: LifecycleStateChange  # noqa: N815
     """The lifecycle state change."""
 
-    previousIdentifier: PreviousIdentifier | None = field(default=None)  # noqa: N815
+    previousIdentifier: PreviousIdentifier | None = attr.field(default=None)  # noqa: N815
     """Previous name of the dataset in case of renaming it."""
 
     @staticmethod
@@ -34,7 +34,7 @@ class LifecycleStateChangeDatasetFacet(DatasetFacet):
         return "https://openlineage.io/spec/facets/1-0-1/LifecycleStateChangeDatasetFacet.json#/$defs/LifecycleStateChangeDatasetFacet"
 
 
-@define
+@attr.define
 class PreviousIdentifier(RedactMixin):
     """Previous name of the dataset in case of renaming it."""
 

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/nominal_time_run.py

@@ -5,18 +5,18 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import RunFacet
 
 
-@define
+@attr.define
 class NominalTimeRunFacet(RunFacet):
-    nominalStartTime: str = field()  # noqa: N815
+    nominalStartTime: str = attr.field()  # noqa: N815
     """
     An [ISO-8601](https://en.wikipedia.org/wiki/ISO_8601) timestamp representing the nominal start time
     (included) of the run. AKA the schedule time
     """
-    nominalEndTime: str | None = field(default=None)  # noqa: N815
+    nominalEndTime: str | None = attr.field(default=None)  # noqa: N815
     """
     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)

{openlineage_python-1.15.0 → openlineage_python-1.17.0}/openlineage/client/generated/output_statistics_output_dataset.py

@@ -5,19 +5,19 @@ from __future__ import annotations
 
 from typing import ClassVar
 
-from attr import define, field
+import attr
 from openlineage.client.generated.base import OutputDatasetFacet
 
 
-@define
+@attr.define
 class OutputStatisticsOutputDatasetFacet(OutputDatasetFacet):
-    rowCount: int | None = field(default=None)  # noqa: N815
+    rowCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of rows written to the dataset"""
 
-    size: int | None = field(default=None)
+    size: int | None = attr.field(default=None)
     """The size in bytes written to the dataset"""
 
-    fileCount: int | None = field(default=None)  # noqa: N815
+    fileCount: int | None = attr.field(default=None)  # noqa: N815
     """The number of files written to the dataset"""
 
     _additional_skip_redact: ClassVar[list[str]] = ["rowCount", "size"]