openmetadata-ingestion 1.3.3.0rc1__py3-none-any.whl → 1.3.4.0__py3-none-any.whl

metadata/generated/schema/type/entityReference.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityReference.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityReferenceList.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityReferenceList.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityRelationship.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityRelationship.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/entityUsage.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/entityUsage.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/filterPattern.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/filterPattern.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/function.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/function.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/include.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/include.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/jdbcConnection.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/jdbcConnection.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/lifeCycle.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/lifeCycle.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/paging.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/paging.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/profile.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/profile.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/queryParserData.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/queryParserData.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/reaction.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/reaction.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schedule.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schedule.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/schema.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/schema.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableQuery.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableQuery.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tableUsageCount.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tableUsageCount.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/tagLabel.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/tagLabel.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageDetails.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageDetails.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/usageRequest.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/usageRequest.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/generated/schema/type/votes.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  type/votes.json
-#   timestamp: 2024-04-10T12:09:11+00:00
+#   timestamp: 2024-05-07T11:23:54+00:00
 
 from __future__ import annotations
 

metadata/profiler/interface/sqlalchemy/profiler_interface.py

@@ -189,6 +189,7 @@ class SQAProfilerInterface(ProfilerInterface, SQAInterfaceMixin):
                 runner=runner,
                 metrics=metrics,
                 conn_config=self.service_connection_config,
+                entity=self.table_entity,
             )
             row = table_metric_computer.compute()
             if row:

metadata/profiler/orm/functions/table_metric_computer.py

@@ -22,6 +22,8 @@ from sqlalchemy import Column, MetaData, Table, func, inspect, literal, select
 from sqlalchemy.sql.expression import ColumnOperators, and_, cte
 from sqlalchemy.types import String
 
+from metadata.generated.schema.entity.data.table import Table as OMTable
+from metadata.generated.schema.entity.data.table import TableType
 from metadata.profiler.metrics.registry import Metrics
 from metadata.profiler.orm.registry import Dialects
 from metadata.profiler.processor.runner import QueryRunner
@@ -31,7 +33,7 @@ logger = profiler_interface_registry_logger()
 
 COLUMN_COUNT = "columnCount"
 COLUMN_NAMES = "columnNames"
-ROW_COUNT = "rowCount"
+ROW_COUNT = Metrics.ROW_COUNT().name()
 SIZE_IN_BYTES = "sizeInBytes"
 CREATE_DATETIME = "createDateTime"
 
@@ -43,13 +45,16 @@ ERROR_MSG = (
 class AbstractTableMetricComputer(ABC):
     """Base table computer"""
 
-    def __init__(self, runner: QueryRunner, metrics: List[Metrics], conn_config):
+    def __init__(
+        self, runner: QueryRunner, metrics: List[Metrics], conn_config, entity: OMTable
+    ):
         """Instantiate base table computer"""
         self._runner = runner
         self._metrics = metrics
         self._conn_config = conn_config
         self._database = self._runner._session.get_bind().url.database
         self._table = self._runner.table
+        self._entity = entity
 
     @property
     def database(self):
@@ -141,16 +146,6 @@ class AbstractTableMetricComputer(ABC):
 class BaseTableMetricComputer(AbstractTableMetricComputer):
     """Base table computer"""
 
-    def _check_and_return(self, res):
-        """Check if the result is None and return the result or fallback
-
-        Args:
-            res (object): result
-        """
-        if res.rowCount is None:
-            return super().compute()
-        return res
-
     def compute(self):
         """Default compute behavior for table metrics"""
         return self.runner.select_first_from_table(
@@ -236,7 +231,9 @@ class OracleTableMetricComputer(BaseTableMetricComputer):
         )
 
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
         return res
@@ -263,7 +260,9 @@ class ClickHouseTableMetricComputer(BaseTableMetricComputer):
         )
 
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
         return res
@@ -307,7 +306,9 @@ class BigQueryTableMetricComputer(BaseTableMetricComputer):
         )
 
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
         return res
@@ -336,7 +337,9 @@ class BigQueryTableMetricComputer(BaseTableMetricComputer):
             where_clause,
         )
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
         return res
@@ -363,9 +366,16 @@ class MySQLTableMetricComputer(BaseTableMetricComputer):
         )
 
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
+        res = res._asdict()
+        # innodb row count is an estimate we need to patch the row count with COUNT(*)
+        # https://dev.mysql.com/doc/refman/8.3/en/information-schema-innodb-tablestats-table.html
+        row_count = self.runner.select_first_from_table(Metrics.ROW_COUNT().fn())
+        res.update({ROW_COUNT: row_count.rowCount})
         return res
 
 
@@ -390,7 +400,9 @@ class RedshiftTableMetricComputer(BaseTableMetricComputer):
             columns, self._build_table("svv_table_info", "pg_catalog"), where_clause
         )
         res = self.runner._session.execute(query).first()
-        if res.rowCount is None:
+        if res.rowCount is None or (
+            res.rowCount == 0 and self._entity.tableType == TableType.View
+        ):
             # if we don't have any row count, fallback to the base logic
             return super().compute()
         return res
@@ -400,9 +412,15 @@ class TableMetricComputer:
     """Table Metric Construct"""
 
     def __init__(
-        self, dialect: str, runner: QueryRunner, metrics: List[Metrics], conn_config
+        self,
+        dialect: str,
+        runner: QueryRunner,
+        metrics: List[Metrics],
+        conn_config,
+        entity: OMTable,
     ):
         """Instantiate table metric computer with a dialect computer"""
+        self._entity = entity
         self._dialect = dialect
         self._runner = runner
         self._metrics = metrics
@@ -413,6 +431,7 @@ class TableMetricComputer:
                 runner=self._runner,
                 metrics=self._metrics,
                 conn_config=self._conn_config,
+                entity=self._entity,
             )
         )