snowflake-data-validation 1.3.2__tar.gz → 1.3.3__tar.gz

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/.gitignore

@@ -104,7 +104,7 @@ ipython_config.py
 # pyenv
 #   For a library or package, you might want to ignore these files since the code is
 #   intended to run in multiple environments; otherwise, check them in:
-# .python-version
+.python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: snowflake-data-validation
-Version: 1.3.2
+Version: 1.3.3
 Summary: Snowflake Data Validation
-Project-URL: Bug Tracker, https://github.com/snowflakedb/migrations-data-validation/issues
-Project-URL: Source code, https://github.com/snowflakedb/migrations-data-validation/
+Project-URL: Bug Tracker, https://github.com/snowflake-eng/migrations-data-validation/issues
+Project-URL: Source code, https://github.com/snowflake-eng/migrations-data-validation/
 Author-email: "Snowflake, Inc." <snowflake-python-libraries-dl@snowflake.com>
 License: Snowflake Conversion Software Terms
 License-File: LICENSE
@@ -30,9 +30,11 @@ Requires-Dist: cryptography>=3.4.0
 Requires-Dist: deepdiff>=8.0.0
 Requires-Dist: jinja2>=3.1.6
 Requires-Dist: pandas>=2.2.3
+Requires-Dist: polars>=1.0.0
 Requires-Dist: pyarrow>=14.0.0
 Requires-Dist: pydantic-yaml>=1.4.0
 Requires-Dist: pydantic>=2.0
+Requires-Dist: pyyaml>=6.0
 Requires-Dist: ruamel-yaml>=0.18.0
 Requires-Dist: snowflake-connector-python>=4.0.0
 Requires-Dist: toml>=0.10.2

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/pyproject.toml

@@ -30,7 +30,9 @@ dependencies = [
   "deepdiff>=8.0.0",
   "snowflake-connector-python>=4.0.0",
   "pandas>=2.2.3",
+  "polars>=1.0.0",
   "pyarrow>=14.0.0",
+  "PyYAML>=6.0",
   "ruamel.yaml>=0.18.0",
   "toml>=0.10.2",
   "jinja2>=3.1.6",
@@ -85,8 +87,8 @@ redshift = [
 ]
 
 [project.urls]
-"Bug Tracker" = "https://github.com/snowflakedb/migrations-data-validation/issues"
-"Source code" = "https://github.com/snowflakedb/migrations-data-validation/"
+"Bug Tracker" = "https://github.com/snowflake-eng/migrations-data-validation/issues"
+"Source code" = "https://github.com/snowflake-eng/migrations-data-validation/"
 
 [tool.hatch.version]
 path = "src/snowflake/snowflake_data_validation/__version__.py"

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/src/snowflake/snowflake_data_validation/__init__.py

@@ -34,6 +34,10 @@ Main Components
 ComparisonOrchestrator
     Main class for orchestrating data comparisons between source and target systems
 
+public
+    Library API module providing decoupled validation steps (query generation,
+    execution, validation) that can be called independently
+
 CLI Interface
     Command-line interface available via `main_cli` module for:
     - Setting up database connections
@@ -47,7 +51,7 @@ Supported Dialects
 
 Example Usage
 -------------
-Programmatic API:
+Programmatic API (Orchestrator):
 >>> from snowflake.snowflake_data_validation import ComparisonOrchestrator
 >>> # Set up extractors, context, and configuration
 >>> orchestrator = ComparisonOrchestrator(
@@ -57,6 +61,13 @@ Programmatic API:
 ... )
 >>> orchestrator.run_sync_comparison()
 
+Programmatic API (Decoupled Steps):
+>>> from snowflake.snowflake_data_validation import public
+>>> # Generate and execute queries independently
+>>> schema_query = public.generate_schema_query(table_context)
+>>> result = public.execute_query(table_context, connector, schema_query)
+>>> validation_result = public.validate_schema(source_df, target_df)
+
 Command Line Interface:
 
 .. code-block:: bash
@@ -86,6 +97,7 @@ import snowflake.snowflake_data_validation.utils as utils
 import snowflake.snowflake_data_validation.snowflake as snowflake
 import snowflake.snowflake_data_validation.sqlserver as sqlserver
 import snowflake.snowflake_data_validation.redshift as redshift
+import snowflake.snowflake_data_validation.public as public
 import logging
 
 
@@ -105,6 +117,7 @@ __all__ = [
     "snowflake",
     "sqlserver",
     "redshift",
+    "public",
 ]
 
 

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/src/snowflake/snowflake_data_validation/__version__.py

@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.3.2"
+__version__ = "1.3.3"

{snowflake_data_validation-1.3.2 → snowflake_data_validation-1.3.3}/src/snowflake/snowflake_data_validation/configuration/model/validation_configuration.py

@@ -19,16 +19,21 @@ from pydantic import BaseModel, model_validator
 
 from snowflake.snowflake_data_validation.utils.constants import (
     MAX_FAILED_ROWS_NUMBER_DEFAULT_VALUE,
+    RowValidationMode,
 )
 
 
 class ValidationConfiguration(BaseModel):
-    """Class representing the validation levels to be applied to a table."""
+    """Class representing the validation levels to be applied to a table.
+
+    `row_validation` enables/disables row-level validation.
+    `row_validation_mode` selects the mode: 'default', 'cell', or other supported modes.
+    """
 
     schema_validation: bool | None = False
     metrics_validation: bool | None = False
-    row_validation: bool | None = False
-    # Custom templates path for validation scripts.
+    row_validation: bool = False
+    row_validation_mode: RowValidationMode = RowValidationMode.ROW
     custom_templates_path: Path | None = None
     max_failed_rows_number: int = MAX_FAILED_ROWS_NUMBER_DEFAULT_VALUE
     exclude_metrics: bool = False
@@ -38,10 +43,10 @@ class ValidationConfiguration(BaseModel):
     def validate_configuration(self) -> "ValidationConfiguration":
         """Validate the configuration after initialization.
 
-        This method checks if at least one validation type is enabled.
+        This method checks if at least one validation type is enabled and validates row_validation_mode.
 
         Raises:
-            ValueError: If no validation type is enabled.
+            ValueError: If no validation type is enabled or invalid mode is set.
 
         """
         if not self.model_dump(exclude_none=True):

snowflake_data_validation-1.3.3/src/snowflake/snowflake_data_validation/executer/async_generation_executor.py

@@ -0,0 +1,255 @@
+# Copyright 2026 Snowflake Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+
+# http://www.apache.org/licenses/LICENSE-2.0
+
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Asynchronous Query Generation Executor with decoupled workflow steps.
+
+This module provides the AsyncGenerationExecutor class that generates async
+comparison queries and writes them to files instead of executing actual validation.
+
+The generation workflow follows the decoupled pattern using the public workflow API:
+1. Query Generation - Uses data_validation_api.generate_schema_query / generate_metrics_query
+2. Query Output - Write generated queries to files via public API functions
+
+Note: This executor only performs query generation (Step 1) and writes the queries
+to files. The execution and validation steps happen separately in async validation mode.
+"""
+
+import logging
+
+from snowflake.snowflake_data_validation.executer.base_validation_executor import (
+    BaseValidationExecutor,
+    validation_handler,
+)
+from snowflake.snowflake_data_validation.public import (
+    data_validation_api,
+)
+from snowflake.snowflake_data_validation.utils.base_output_handler import (
+    OutputMessageLevel,
+)
+from snowflake.snowflake_data_validation.utils.logging_utils import log
+from snowflake.snowflake_data_validation.utils.model.table_context import TableContext
+
+
+LOGGER = logging.getLogger(__name__)
+
+
+class AsyncGenerationExecutor(BaseValidationExecutor):
+    """Executor for asynchronous query generation operations.
+
+    This executor generates async comparison queries and writes them to files
+    instead of executing actual validation. Uses script writers to delegate
+    the actual file generation and writing operations.
+
+    The workflow is decoupled to clearly separate query generation from
+    the file writing operation:
+    1. Generate queries for source and target platforms
+    2. Write queries to files using script writers
+    """
+
+    @validation_handler(
+        "Schema validation async generation failed.",
+        "Error generating schema validation queries: {error}",
+    )
+    @log
+    def execute_schema_validation(
+        self,
+        source_table_context: TableContext,
+        target_table_context: TableContext,
+        column_mappings: dict[str, str],
+    ) -> bool:
+        """Generate schema validation queries and write to files.
+
+        This method uses the decoupled workflow with public API:
+        1. Generate schema query for source using data_validation_api
+        2. Generate schema query for target using data_validation_api
+        3. Write both queries to files via public API functions
+
+        Args:
+            source_table_context: Source table context.
+            target_table_context: Target table context.
+            column_mappings: Mapping of source to target columns.
+
+        Returns:
+            bool: True if queries are successfully generated and written.
+
+        """
+        LOGGER.info(
+            "Generating schema validation queries for table: %s",
+            source_table_context.fully_qualified_name,
+        )
+
+        try:
+            # Step 1: Generate queries using public API
+            source_query = data_validation_api.generate_schema_query(
+                source_table_context
+            )
+            target_query = data_validation_api.generate_schema_query(
+                target_table_context
+            )
+
+            LOGGER.debug(
+                "Generated schema queries for source: %s and target: %s",
+                source_table_context.fully_qualified_name,
+                target_table_context.fully_qualified_name,
+            )
+
+            # Step 2: Write queries to files via public API
+            # Use report_path from extractors (ScriptWriterBase instances)
+            data_validation_api.write_schema_query_to_script(
+                table_context=source_table_context,
+                generated_query=source_query,
+                output_directory=self.source_extractor.report_path,
+                timestamp=self.context.run_start_time,
+            )
+
+            data_validation_api.write_schema_query_to_script(
+                table_context=target_table_context,
+                generated_query=target_query,
+                output_directory=self.source_extractor.report_path,
+                timestamp=self.context.run_start_time,
+            )
+
+            self.context.output_handler.handle_message(
+                header="Schema validation queries generated.",
+                message=f"Queries generated for table: {source_table_context.fully_qualified_name}",
+                level=OutputMessageLevel.SUCCESS,
+            )
+            return True
+        except Exception:
+            return False
+
+    @validation_handler(
+        "Metrics validation async generation failed.",
+        "Error generating metrics validation queries: {error}",
+    )
+    @log
+    def execute_metrics_validation(
+        self,
+        source_table_context: TableContext,
+        target_table_context: TableContext,
+        column_mappings: dict[str, str],
+    ) -> bool:
+        """Generate metrics validation queries and write to files.
+
+        This method uses the decoupled workflow with public API:
+        1. Generate metrics query for source using data_validation_api
+        2. Generate metrics query for target using data_validation_api
+        3. Write both queries to files via public API functions
+
+        Args:
+            source_table_context: Source table context.
+            target_table_context: Target table context.
+            column_mappings: Mapping of source to target columns.
+
+        Returns:
+            bool: True if queries are successfully generated and written.
+
+        """
+        LOGGER.info(
+            "Generating metrics validation queries for table: %s",
+            source_table_context.fully_qualified_name,
+        )
+
+        try:
+            source_query = data_validation_api.generate_metrics_query(
+                source_table_context
+            )
+            target_query = data_validation_api.generate_metrics_query(
+                target_table_context
+            )
+
+            LOGGER.debug(
+                "Generated metrics queries for source: %s and target: %s",
+                source_table_context.fully_qualified_name,
+                target_table_context.fully_qualified_name,
+            )
+
+            data_validation_api.write_metrics_query_to_script(
+                table_context=source_table_context,
+                generated_query=source_query,
+                output_directory=self.source_extractor.report_path,
+                timestamp=self.context.run_start_time,
+            )
+
+            data_validation_api.write_metrics_query_to_script(
+                table_context=target_table_context,
+                generated_query=target_query,
+                output_directory=self.target_extractor.report_path,
+                timestamp=self.context.run_start_time,
+            )
+
+            self.context.output_handler.handle_message(
+                header="Metrics validation queries generated.",
+                message=f"Queries generated for table: {target_table_context.fully_qualified_name}",
+                level=OutputMessageLevel.SUCCESS,
+            )
+            return True
+        except Exception:
+            return False
+
+    @validation_handler(
+        "Row validation async generation failed.",
+        "Error in row validation async generation: {error}",
+    )
+    @log
+    def execute_row_validation(
+        self,
+        source_table_context: TableContext,
+        target_table_context: TableContext,
+    ) -> bool:
+        """Generate row validation queries (placeholder implementation).
+
+        Note: Row validation async generation is not yet implemented.
+
+        Args:
+            source_table_context: Source table context for validation.
+            target_table_context: Target table context for validation.
+
+        Returns:
+            bool: True (placeholder - always succeeds).
+
+        """
+        LOGGER.info(
+            "Row validation async generation skipped for table: %s",
+            source_table_context.fully_qualified_name,
+        )
+
+        self.context.output_handler.handle_message(
+            header="Row validation async generation skipped.",
+            message="Row validation async generation is not yet implemented.",
+            level=OutputMessageLevel.INFO,
+        )
+        return True
+
+    def _get_schema_validation_message(self, table_configuration: TableContext) -> str:
+        """Get async generation message for schema validation."""
+        return (
+            f"Generating async schema validation queries for {table_configuration.fully_qualified_name} "
+            f"with columns {table_configuration.column_selection_list}."
+        )
+
+    def _get_metrics_validation_message(self, table_configuration: TableContext) -> str:
+        """Get async generation message for metrics validation."""
+        return (
+            f"Generating async metrics validation queries for {table_configuration.fully_qualified_name} "
+            f"with columns {table_configuration.column_selection_list}."
+        )
+
+    def _get_row_validation_message(self, table_configuration: TableContext) -> str:
+        """Get async generation message for row validation."""
+        return (
+            f"Generating async row validation queries for {table_configuration.fully_qualified_name} "
+            f"with columns {table_configuration.column_selection_list}."
+        )