acryl-datahub-cloud 0.3.12rc8__tar.gz → 0.3.12rc10__tar.gz

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/PKG-INFO

@@ -1,97 +1,97 @@
 Metadata-Version: 2.4
 Name: acryl-datahub-cloud
-Version: 0.3.12rc8
+Version: 0.3.12rc10
 Requires-Dist: avro-gen3==0.7.16
 Requires-Dist: acryl-datahub
 Requires-Dist: croniter
 Requires-Dist: pytz
 Requires-Dist: types-croniter
 Provides-Extra: datahub-lineage-features
+Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
 Requires-Dist: pandas; extra == "datahub-lineage-features"
-Requires-Dist: duckdb; extra == "datahub-lineage-features"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-lineage-features"
+Requires-Dist: duckdb; extra == "datahub-lineage-features"
 Requires-Dist: pyarrow; extra == "datahub-lineage-features"
-Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
 Provides-Extra: datahub-reporting-forms
+Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
+Requires-Dist: boto3; extra == "datahub-reporting-forms"
 Requires-Dist: pandas; extra == "datahub-reporting-forms"
+Requires-Dist: termcolor==2.5.0; extra == "datahub-reporting-forms"
 Requires-Dist: duckdb; extra == "datahub-reporting-forms"
 Requires-Dist: pyarrow; extra == "datahub-reporting-forms"
-Requires-Dist: boto3; extra == "datahub-reporting-forms"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
-Requires-Dist: termcolor==2.5.0; extra == "datahub-reporting-forms"
 Provides-Extra: datahub-reporting-extract-graph
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
+Requires-Dist: boto3; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
-Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-reporting-extract-graph"
+Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-graph"
-Requires-Dist: boto3; extra == "datahub-reporting-extract-graph"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
 Provides-Extra: datahub-reporting-extract-sql
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
+Requires-Dist: boto3; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
 Requires-Dist: duckdb; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-sql"
-Requires-Dist: boto3; extra == "datahub-reporting-extract-sql"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
 Provides-Extra: datahub-usage-reporting
-Requires-Dist: pandas; extra == "datahub-usage-reporting"
-Requires-Dist: duckdb; extra == "datahub-usage-reporting"
-Requires-Dist: numpy<2; extra == "datahub-usage-reporting"
-Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-reporting"
-Requires-Dist: pyarrow; extra == "datahub-usage-reporting"
-Requires-Dist: boto3; extra == "datahub-usage-reporting"
-Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
 Requires-Dist: pydantic<2; extra == "datahub-usage-reporting"
 Requires-Dist: polars==1.30.0; extra == "datahub-usage-reporting"
-Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
 Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-reporting"
+Requires-Dist: duckdb; extra == "datahub-usage-reporting"
+Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
+Requires-Dist: boto3; extra == "datahub-usage-reporting"
+Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
+Requires-Dist: pandas; extra == "datahub-usage-reporting"
 Requires-Dist: termcolor==2.5.0; extra == "datahub-usage-reporting"
+Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-reporting"
+Requires-Dist: numpy<2; extra == "datahub-usage-reporting"
+Requires-Dist: pyarrow; extra == "datahub-usage-reporting"
 Provides-Extra: datahub-metadata-sharing
 Requires-Dist: tenacity; extra == "datahub-metadata-sharing"
 Provides-Extra: datahub-action-request-owner
 Requires-Dist: tenacity; extra == "datahub-action-request-owner"
 Provides-Extra: acryl-cs-issues
+Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Requires-Dist: openai; extra == "acryl-cs-issues"
 Requires-Dist: zenpy; extra == "acryl-cs-issues"
 Requires-Dist: jinja2; extra == "acryl-cs-issues"
-Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Provides-Extra: datahub-forms-notifications
 Requires-Dist: tenacity; extra == "datahub-forms-notifications"
 Provides-Extra: all
-Requires-Dist: duckdb; extra == "all"
-Requires-Dist: elasticsearch==7.13.4; extra == "all"
-Requires-Dist: boto3; extra == "all"
-Requires-Dist: tenacity; extra == "all"
-Requires-Dist: pyarrow<=18.0.0; extra == "all"
-Requires-Dist: jinja2; extra == "all"
 Requires-Dist: slack-sdk; extra == "all"
 Requires-Dist: zenpy; extra == "all"
-Requires-Dist: termcolor==2.5.0; extra == "all"
+Requires-Dist: elasticsearch==7.13.4; extra == "all"
 Requires-Dist: pandas; extra == "all"
-Requires-Dist: numpy<2; extra == "all"
+Requires-Dist: termcolor==2.5.0; extra == "all"
 Requires-Dist: opensearch-py==2.4.2; extra == "all"
+Requires-Dist: numpy<2; extra == "all"
 Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: pydantic<2; extra == "all"
 Requires-Dist: polars==1.30.0; extra == "all"
 Requires-Dist: scipy<=1.14.1; extra == "all"
 Requires-Dist: openai; extra == "all"
+Requires-Dist: duckdb; extra == "all"
+Requires-Dist: tenacity; extra == "all"
+Requires-Dist: pyarrow<=18.0.0; extra == "all"
+Requires-Dist: boto3; extra == "all"
+Requires-Dist: jinja2; extra == "all"
 Provides-Extra: dev
-Requires-Dist: pandas; extra == "dev"
-Requires-Dist: duckdb; extra == "dev"
-Requires-Dist: numpy<2; extra == "dev"
-Requires-Dist: opensearch-py==2.4.2; extra == "dev"
-Requires-Dist: pyarrow; extra == "dev"
-Requires-Dist: boto3; extra == "dev"
-Requires-Dist: elasticsearch==7.13.4; extra == "dev"
 Requires-Dist: pydantic<2; extra == "dev"
-Requires-Dist: tenacity; extra == "dev"
 Requires-Dist: polars==1.30.0; extra == "dev"
-Requires-Dist: pyarrow<=18.0.0; extra == "dev"
-Requires-Dist: jinja2; extra == "dev"
+Requires-Dist: acryl-datahub[dev]; extra == "dev"
 Requires-Dist: scipy<=1.14.1; extra == "dev"
 Requires-Dist: slack-sdk; extra == "dev"
 Requires-Dist: openai; extra == "dev"
-Requires-Dist: acryl-datahub[dev]; extra == "dev"
+Requires-Dist: duckdb; extra == "dev"
+Requires-Dist: tenacity; extra == "dev"
+Requires-Dist: pyarrow<=18.0.0; extra == "dev"
+Requires-Dist: boto3; extra == "dev"
 Requires-Dist: zenpy; extra == "dev"
+Requires-Dist: elasticsearch==7.13.4; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Requires-Dist: jinja2; extra == "dev"
 Requires-Dist: termcolor==2.5.0; extra == "dev"
+Requires-Dist: opensearch-py==2.4.2; extra == "dev"
+Requires-Dist: numpy<2; extra == "dev"
+Requires-Dist: pyarrow; extra == "dev"
 Dynamic: provides-extra
 Dynamic: requires-dist

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/_codegen_config.json

@@ -1,6 +1,6 @@
 {
   "name": "acryl-datahub-cloud",
-  "version": "0.3.12rc8",
+  "version": "0.3.12rc10",
   "install_requires": [
     "avro-gen3==0.7.16",
     "acryl-datahub"

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/datahub_reporting/datahub_form_reporting.py

@@ -10,7 +10,7 @@ from pydantic import BaseModel
 from acryl_datahub_cloud.elasticsearch.graph_service import BaseModelRow
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
 from datahub.ingestion.graph.client import DataHubGraph
-from datahub.ingestion.graph.filters import RawSearchFilterRule
+from datahub.ingestion.graph.filters import RawSearchFilter
 from datahub.metadata.schema_classes import (
     DomainPropertiesClass,
     FormAssociationClass,
@@ -149,7 +149,7 @@ class DataHubFormReportingData(FormData):
             )
         )
 
-    def get_form_existence_or_filters(self) -> List[RawSearchFilterRule]:
+    def get_form_existence_or_filters(self) -> RawSearchFilter:
         """
         Datasets must either have completedForms or incompleteForms assigned to
         them
@@ -157,25 +157,41 @@ class DataHubFormReportingData(FormData):
         if self.allowed_forms:
             return [
                 {
-                    "field": "completedForms",
-                    "condition": "EQUAL",
-                    "values": self.allowed_forms,
+                    "and": [
+                        {
+                            "field": "completedForms",
+                            "condition": "EQUAL",
+                            "values": self.allowed_forms,
+                        }
+                    ]
                 },
                 {
-                    "field": "incompleteForms",
-                    "condition": "EQUAL",
-                    "values": self.allowed_forms,
+                    "and": [
+                        {
+                            "field": "incompleteForms",
+                            "condition": "EQUAL",
+                            "values": self.allowed_forms,
+                        }
+                    ]
                 },
             ]
         else:
             return [
                 {
-                    "field": "completedForms",
-                    "condition": "EXISTS",
+                    "and": [
+                        {
+                            "field": "completedForms",
+                            "condition": "EXISTS",
+                        }
+                    ]
                 },
                 {
-                    "field": "incompleteForms",
-                    "condition": "EXISTS",
+                    "and": [
+                        {
+                            "field": "incompleteForms",
+                            "condition": "EXISTS",
+                        }
+                    ]
                 },
             ]
 
@@ -293,7 +309,7 @@ class DataHubFormReportingData(FormData):
         extra_fields = [f for f in self.DataHubDatasetSearchRow.__fields__]
         # TODO: Replace with the new search/filter SDK.
         result = self.graph.get_results_by_filter(
-            extra_or_filters=[{"and": self.get_form_existence_or_filters()}],
+            extra_or_filters=self.get_form_existence_or_filters(),
             extra_source_fields=extra_fields,
             skip_cache=True,
         )

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/metadata/schema.avsc

@@ -14983,6 +14983,15 @@
         "doc": "Overall rank of the dataset based on the the last 30 days insert/update operation count on a platform\nIt returns one plus the number of rows proceeding or equals to the current row in the ordering. "
       },
       {
+        "Searchable": {
+          "/*": {
+            "addToFilters": true,
+            "fieldName": "topUsersLast30Days",
+            "fieldType": "URN",
+            "filterNameOverride": "Top users last 30 days",
+            "hasValuesFieldName": "hasTopUsersLast30Days"
+          }
+        },
         "Urn": "Urn",
         "urn_is_array": true,
         "type": [

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/metadata/schemas/UsageFeatures.avsc

@@ -160,6 +160,15 @@
       "doc": "Overall rank of the dataset based on the the last 30 days insert/update operation count on a platform\nIt returns one plus the number of rows proceeding or equals to the current row in the ordering. "
     },
     {
+      "Searchable": {
+        "/*": {
+          "addToFilters": true,
+          "fieldName": "topUsersLast30Days",
+          "fieldType": "URN",
+          "filterNameOverride": "Top users last 30 days",
+          "hasValuesFieldName": "hasTopUsersLast30Days"
+        }
+      },
       "type": [
         "null",
         {

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/sdk/assertion_input/assertion_input.py

@@ -911,9 +911,7 @@ class _AssertionInput(ABC):
         enabled: bool = True,
         schedule: Optional[Union[str, models.CronScheduleClass]] = None,
         detection_mechanism: DetectionMechanismInputTypes = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         source_type: str = models.AssertionSourceTypeClass.NATIVE,  # Verified on init to be a valid enum value
         created_by: Union[str, CorpUserUrn],
@@ -932,7 +930,11 @@ class _AssertionInput(ABC):
             display_name: The display name of the assertion. If not provided, a random display name will be generated.
             enabled: Whether the assertion is enabled. Defaults to True.
             detection_mechanism: The detection mechanism to be used for the assertion.
-            incident_behavior: The incident behavior to be applied to the assertion.
+            incident_behavior: The incident behavior to be applied to the assertion. Accepts:
+                - String values: "raise_on_fail", "resolve_on_pass"
+                - Enum values: AssertionIncidentBehavior.RAISE_ON_FAIL, AssertionIncidentBehavior.RESOLVE_ON_PASS
+                - Lists of any of the above values
+                - None (default behavior)
             tags: The tags to be applied to the assertion.
             source_type: The source type of the assertion. Defaults to models.AssertionSourceTypeClass.NATIVE.
             created_by: The actor that created the assertion.
@@ -1321,9 +1323,7 @@ class _SmartFreshnessAssertionInput(
         sensitivity: Optional[Union[str, InferenceSensitivity]] = None,
         exclusion_windows: Optional[ExclusionWindowInputTypes] = None,
         training_data_lookback_days: Optional[int] = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,
@@ -1504,9 +1504,7 @@ class _SmartVolumeAssertionInput(_AssertionInput, _HasSmartAssertionInputs):
         sensitivity: Optional[Union[str, InferenceSensitivity]] = None,
         exclusion_windows: Optional[ExclusionWindowInputTypes] = None,
         training_data_lookback_days: Optional[int] = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/sdk/assertion_input/freshness_assertion_input.py

@@ -5,7 +5,7 @@ from acryl_datahub_cloud.sdk.assertion_input.assertion_input import (
     DEFAULT_DAILY_SCHEDULE,
     HIGH_WATERMARK_ALLOWED_FIELD_TYPES,
     LAST_MODIFIED_ALLOWED_FIELD_TYPES,
-    AssertionIncidentBehavior,
+    AssertionIncidentBehaviorInputTypes,
     DetectionMechanismInputTypes,
     FieldSpecType,
     TimeWindowSizeInputTypes,
@@ -49,9 +49,7 @@ class _FreshnessAssertionInput(_AssertionInput, _HasFreshnessFeatures):
         enabled: bool = True,
         schedule: Optional[Union[str, models.CronScheduleClass]] = None,
         detection_mechanism: DetectionMechanismInputTypes = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/sdk/assertion_input/smart_column_metric_assertion_input.py

@@ -8,7 +8,7 @@ from acryl_datahub_cloud.sdk.assertion_input.assertion_input import (
     NO_PARAMETER_OPERATORS,
     RANGE_OPERATORS,
     SINGLE_VALUE_OPERATORS,
-    AssertionIncidentBehavior,
+    AssertionIncidentBehaviorInputTypes,
     AssertionInfoInputType,
     DetectionMechanismInputTypes,
     ExclusionWindowInputTypes,
@@ -282,9 +282,7 @@ class _SmartColumnMetricAssertionInput(_AssertionInput, _HasSmartAssertionInputs
         sensitivity: Optional[Union[str, InferenceSensitivity]] = None,
         exclusion_windows: Optional[ExclusionWindowInputTypes] = None,
         training_data_lookback_days: Optional[int] = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,
@@ -312,7 +310,7 @@ class _SmartColumnMetricAssertionInput(_AssertionInput, _HasSmartAssertionInputs
             sensitivity: The sensitivity of the assertion.
             exclusion_windows: The exclusion windows of the assertion.
             training_data_lookback_days: The training data lookback days of the assertion.
-            incident_behavior: The incident behavior of the assertion.
+            incident_behavior: The incident behavior of the assertion. Accepts strings, enum values, lists, or None.
             tags: The tags of the assertion.
             created_by: The creator of the assertion.
             created_at: The creation time of the assertion.

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/sdk/assertion_input/sql_assertion_input.py

@@ -8,7 +8,7 @@ from acryl_datahub_cloud.sdk.assertion_input.assertion_input import (
     DEFAULT_EVERY_SIX_HOURS_SCHEDULE,
     RANGE_OPERATORS,
     SINGLE_VALUE_NUMERIC_OPERATORS,
-    AssertionIncidentBehavior,
+    AssertionIncidentBehaviorInputTypes,
     FieldSpecType,
     _AssertionInput,
     _try_parse_and_validate_schema_classes_enum,
@@ -162,9 +162,7 @@ class _SqlAssertionInput(_AssertionInput):
         display_name: Optional[str] = None,
         enabled: bool = True,
         schedule: Optional[Union[str, models.CronScheduleClass]] = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,

{acryl_datahub_cloud-0.3.12rc8 → acryl_datahub_cloud-0.3.12rc10}/src/acryl_datahub_cloud/sdk/assertion_input/volume_assertion_input.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel, Extra
 
 from acryl_datahub_cloud.sdk.assertion_input.assertion_input import (
     DEFAULT_EVERY_SIX_HOURS_SCHEDULE,
-    AssertionIncidentBehavior,
+    AssertionIncidentBehaviorInputTypes,
     DetectionMechanismInputTypes,
     FieldSpecType,
     _AssertionInput,
@@ -530,9 +530,7 @@ class _VolumeAssertionInput(_AssertionInput):
         enabled: bool = True,
         schedule: Optional[Union[str, models.CronScheduleClass]] = None,
         detection_mechanism: DetectionMechanismInputTypes = None,
-        incident_behavior: Optional[
-            Union[AssertionIncidentBehavior, list[AssertionIncidentBehavior]]
-        ] = None,
+        incident_behavior: Optional[AssertionIncidentBehaviorInputTypes] = None,
         tags: Optional[TagsInputType] = None,
         created_by: Union[str, CorpUserUrn],
         created_at: datetime,