snowflake-data-validation 1.3.1__tar.gz → 1.3.2__tar.gz

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-data-validation
-Version: 1.3.1
+Version: 1.3.2
 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/
@@ -33,6 +33,7 @@ Requires-Dist: pandas>=2.2.3
 Requires-Dist: pyarrow>=14.0.0
 Requires-Dist: pydantic-yaml>=1.4.0
 Requires-Dist: pydantic>=2.0
+Requires-Dist: ruamel-yaml>=0.18.0
 Requires-Dist: snowflake-connector-python>=4.0.0
 Requires-Dist: toml>=0.10.2
 Requires-Dist: typer>=0.15.3

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/pyproject.toml

@@ -31,6 +31,7 @@ dependencies = [
   "snowflake-connector-python>=4.0.0",
   "pandas>=2.2.3",
   "pyarrow>=14.0.0",
+  "ruamel.yaml>=0.18.0",
   "toml>=0.10.2",
   "jinja2>=3.1.6",
   "pydantic>=2.0",
@@ -111,6 +112,9 @@ packages = [
   "src/snowflake",
 ]
 
+[tool.hatch.build.targets.wheel.force-include]
+"../shared" = "shared"
+
 [tool.hatch.build.targets.sdist]
 directory = "dist"
 exclude = ["/.github", "/.idea"]
@@ -125,8 +129,14 @@ include = [
 [tool.hatch.envs.default]
 features = ["development", "sqlserver", "teradata", "redshift"]
 python = "3.12"
+dependencies = [
+  "shared @ {root:uri}/../shared",
+]
 
 [tool.hatch.envs.test]
+dependencies = [
+  "shared @ {root:uri}/../shared",
+]
 
 [tool.hatch.envs.test_all]
 template = 'test'

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/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__ = "1.3.1"
+__version__ = "1.3.2"

snowflake_data_validation-1.3.2/src/snowflake/snowflake_data_validation/common_cli/cli_sync_validation.py

@@ -0,0 +1,54 @@
+# 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.
+
+"""Shared CLI sync validation functions for data validation."""
+
+import logging
+
+import typer
+
+from snowflake.snowflake_data_validation.utils import configuration_file_synchronizer
+
+
+LOGGER = logging.getLogger(__name__)
+
+
+def sync_validation_results(
+    configuration_file_path: str,
+    execution_summary_report_file_path: str,
+) -> None:
+    """Sync the configuration file with the execution summary report.
+
+    Remove tables and views that passed all validation levels.
+
+    Args:
+        configuration_file_path: Path to the configuration file.
+        execution_summary_report_file_path: Path to the execution summary report file.
+
+    """
+    try:
+        configuration_file_synchronizer.sync_configuration_file(
+            configuration_file_path=configuration_file_path,
+            execution_summary_report_file_path=execution_summary_report_file_path,
+        )
+        typer.secho(
+            "Configuration file updated successfully based on validation results.",
+            fg=typer.colors.GREEN,
+        )
+
+        LOGGER.info(
+            "Configuration file updated successfully based on validation results."
+        )
+
+    except Exception as e:
+        typer.secho(f"Error syncing configuration file: {e}", fg=typer.colors.RED)
+        LOGGER.error("Error syncing configuration file: %s", e)

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/comparison_orchestrator.py

@@ -15,6 +15,8 @@
 
 import logging
 
+from collections.abc import Callable
+
 from snowflake.snowflake_data_validation.configuration.model.table_configuration import (
     TableConfiguration,
 )
@@ -68,6 +70,9 @@ class ComparisonOrchestrator:
         connection_pool_manager: ConnectionPoolManager,
         context: Context,
         max_threads: int,
+        progress_callback: (
+            Callable[[str, list[str], Context | None], None] | None
+        ) = None,
     ):
         """Initialize the orchestrator.
 
@@ -75,6 +80,10 @@ class ComparisonOrchestrator:
             connection_pool_manager: Connection pool manager for threaded processing
             context: Validation context containing configuration and runtime info
             max_threads: Maximum number of threads for parallel table processing
+            progress_callback: Optional callback for progress reporting. When
+                provided, it replaces the default stdout/pipe-based progress
+                reporting in ValidationProgressReporter.
+                Signature: (table_name: str, columns: list[str], context: Context | None) -> None
 
         """
         LOGGER.debug("Initializing ComparisonOrchestrator")
@@ -87,7 +96,9 @@ class ComparisonOrchestrator:
         # Initialize orchestration modules
         self.metadata_processor = TableMetadataProcessor()
         self.execution_engine = ParallelExecutionEngine(max_threads=self.max_threads)
-        self.progress_reporter = ValidationProgressReporter()
+        self.progress_reporter = ValidationProgressReporter(
+            progress_callback=progress_callback,
+        )
         self.db_manager = ValidationDatabaseManager()
         self.console_progress_reporter = ConsoleProgressReporter(
             output_handler=self.context.output_handler
@@ -102,11 +113,18 @@ class ComparisonOrchestrator:
     def from_validation_environment(
         cls,
         validation_env: ValidationEnvironmentObject,
+        progress_callback: (
+            Callable[[str, list[str], Context | None], None] | None
+        ) = None,
     ) -> "ComparisonOrchestrator":
         """Create a ComparisonOrchestrator from a ValidationEnvironmentObject.
 
         Args:
             validation_env: ValidationEnvironmentObject instance containing all required components
+            progress_callback: Optional callback for progress reporting. When
+                provided, it replaces the default stdout/pipe-based progress
+                reporting in ValidationProgressReporter.
+                Signature: (table_name: str, columns: list[str], context: Context | None) -> None
 
         Returns:
             ComparisonOrchestrator: Configured orchestrator ready to run validation
@@ -140,6 +158,7 @@ class ComparisonOrchestrator:
             connection_pool_manager=connection_pool_manager,
             context=validation_env.context,
             max_threads=optimal_max_threads,
+            progress_callback=progress_callback,
         )
 
     @log

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/executer/executor_factory.py

@@ -65,6 +65,9 @@ from snowflake.snowflake_data_validation.snowflake.query.query_generator_snowfla
 from snowflake.snowflake_data_validation.snowflake.script_writer.script_writer_snowflake import (
     ScriptWriterSnowflake,
 )
+from snowflake.snowflake_data_validation.sqlserver.connector.connector_sql_server import (
+    ConnectorSqlServer,
+)
 from snowflake.snowflake_data_validation.sqlserver.extractor.metadata_extractor_sqlserver import (
     MetadataExtractorSQLServer,
 )
@@ -253,6 +256,14 @@ class ExecutorFactory:
         query_generator = config.query_generator()
         LOGGER.debug("Created query generator for platform: %s", platform)
 
+        # Propagate SQL Server version capabilities to the query generator
+        if platform == Platform.SQLSERVER and isinstance(connector, ConnectorSqlServer):
+            query_generator.supports_string_agg = connector.supports_string_agg
+            LOGGER.debug(
+                "SQL Server query generator: supports_string_agg=%s",
+                connector.supports_string_agg,
+            )
+
         # Select the appropriate extractor class based on type
         if extractor_type == ExtractorType.METADATA_EXTRACTOR:
             extractor_class = config.metadata_extractor

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/extractor/sql_queries_template_generator.py

@@ -285,6 +285,7 @@ class SQLQueriesTemplateGenerator:
         database_name: str,
         schema_name: str,
         table_id: int,
+        supports_string_agg: bool = True,
     ) -> str:
         template_file = f"{platform}_compute_md5_sql.j2"
         try:
@@ -305,6 +306,7 @@ class SQLQueriesTemplateGenerator:
                 fetch=fetch,
                 offset=offset,
                 table_id=table_id,
+                supports_string_agg=supports_string_agg,
             )
             return sql
         except jinja2.exceptions.TemplateNotFound:

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/orchestration/validation_progress_reporter.py

@@ -16,6 +16,8 @@
 import logging
 import os
 
+from collections.abc import Callable
+
 import pandas as pd
 
 from snowflake.snowflake_data_validation.orchestration.html_report import (
@@ -74,7 +76,26 @@ def _apply_status_emoji(df: pd.DataFrame, column: str = "STATUS") -> pd.DataFram
 
 
 class ValidationProgressReporter:
-    """Handles progress reporting and validation report management."""
+    """Handles progress reporting and validation report management.
+
+    Accepts an optional custom progress callback at construction time. When
+    provided, ``report_progress_for_table`` delegates to the custom callback
+    instead of the default stdout/pipe-based ``report_progress()`` mechanism.
+
+    Args:
+        progress_callback: Optional callback invoked for each table.
+            Signature: (table_name: str, columns: list[str], context: Context | None) -> None
+
+    """
+
+    def __init__(
+        self,
+        progress_callback: (
+            Callable[[str, list[str], Context | None], None] | None
+        ) = None,
+    ):
+        """Initialize the reporter with an optional custom progress callback."""
+        self._progress_callback = progress_callback
 
     @log
     def report_progress_for_table(
@@ -85,12 +106,28 @@ class ValidationProgressReporter:
     ) -> None:
         """Report progress for a specific table.
 
+        If a custom progress callback was provided at construction, it is
+        called instead of the default reporting logic.
+
         Args:
             table_name: Name of the table being processed
             column_selection_list: List of columns being validated
             context: Validation context for run_id and run_start_time (optional)
 
         """
+        if self._progress_callback is not None:
+            try:
+                self._progress_callback(table_name, column_selection_list, context)
+            except Exception as e:
+                LOGGER.warning(
+                    "Error in custom progress callback for table %s: %s. "
+                    "This is non-critical and validation will continue.",
+                    table_name,
+                    str(e),
+                )
+            return
+
+        # Default behaviour: report via stdout/pipe (CLI IPC mode)
         # Only report progress if console output is not enabled
         if (
             context

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/redshift/extractor/templates/redshift_chunks_md5_table_template.sql.j2

@@ -1,4 +1,4 @@
 CREATE TEMPORARY TABLE IF NOT EXISTS "CHUNKS_MD5_{{ normalized_fully_qualified_name }}_{{ table_id }}"(
-    CHUNK_ID VARCHAR(100),
+    CHUNK_ID VARCHAR(1000),
     CHUNK_MD5_VALUE VARCHAR(32)
 );

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/redshift/redshift_cli.py

@@ -22,6 +22,9 @@ from snowflake.snowflake_data_validation.common_cli.cli_partitioning import (
     run_column_partitioning_helper,
     run_row_partitioning_helper,
 )
+from snowflake.snowflake_data_validation.common_cli.cli_sync_validation import (
+    sync_validation_results,
+)
 from snowflake.snowflake_data_validation.comparison_orchestrator import (
     ComparisonOrchestrator,
 )
@@ -692,3 +695,39 @@ def redshift_column_partitioning_helper():
     for each table.
     """
     run_column_partitioning_helper(Platform.REDSHIFT)
+
+
+@redshift_app.command(
+    "sync-validation-results",
+    help=(
+        "Remove from the configuration file the tables and views that passed "
+        "all validations levels in the given execution summary report file"
+    ),
+)
+@handle_validation_errors
+def redshift_sync_validation_results(
+    configuration_file_path: Annotated[
+        str,
+        typer.Option(
+            "--configuration-file-path",
+            "-cfp",
+            help="Path to the configuration file",
+        ),
+    ],
+    execution_summary_report_file_path: Annotated[
+        str,
+        typer.Option(
+            "--execution-summary-report-file-path",
+            "-esrfp",
+            help="Path to the execution summary report file",
+        ),
+    ],
+):
+    """Sync the configuration file with the execution summary report.
+
+    Remove tables and views that passed all validation levels.
+    """
+    sync_validation_results(
+        configuration_file_path=configuration_file_path,
+        execution_summary_report_file_path=execution_summary_report_file_path,
+    )

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/snowflake/extractor/templates/snowflake_chunks_md5_table_template.sql.j2

@@ -1,4 +1,4 @@
 CREATE OR REPLACE TEMPORARY TABLE {{ database_name }}.{{ schema_name }}."CHUNKS_MD5_{{ normalized_fully_qualified_name }}_{{ table_id }}"(
-    CHUNK_ID VARCHAR(100),
+    CHUNK_ID VARCHAR(1000),
     CHUNK_MD5_VALUE VARCHAR(32)
 )

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/snowflake/snowflake_cli.py

@@ -24,6 +24,9 @@ from snowflake.snowflake_data_validation.common_cli.cli_partitioning import (
     run_column_partitioning_helper,
     run_row_partitioning_helper,
 )
+from snowflake.snowflake_data_validation.common_cli.cli_sync_validation import (
+    sync_validation_results,
+)
 from snowflake.snowflake_data_validation.comparison_orchestrator import (
     ComparisonOrchestrator,
 )
@@ -649,3 +652,39 @@ def snowflake_column_partitioning_helper():
     for each table.
     """
     run_column_partitioning_helper(Platform.SNOWFLAKE)
+
+
+@snowflake_app.command(
+    "sync-validation-results",
+    help=(
+        "Remove from the configuration file the tables and views that passed "
+        "all validations levels in the given execution summary report file"
+    ),
+)
+@handle_validation_errors
+def snowflake_sync_validation_results(
+    configuration_file_path: Annotated[
+        str,
+        typer.Option(
+            "--configuration-file-path",
+            "-cfp",
+            help="Path to the configuration file",
+        ),
+    ],
+    execution_summary_report_file_path: Annotated[
+        str,
+        typer.Option(
+            "--execution-summary-report-file-path",
+            "-esrfp",
+            help="Path to the execution summary report file",
+        ),
+    ],
+):
+    """Sync the configuration file with the execution summary report.
+
+    Remove tables and views that passed all validation levels.
+    """
+    sync_validation_results(
+        configuration_file_path=configuration_file_path,
+        execution_summary_report_file_path=execution_summary_report_file_path,
+    )

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/sqlserver/connector/connector_sql_server.py

@@ -19,6 +19,10 @@ import struct
 
 from typing import Literal
 
+from shared.sqlserver.constants import SUPPORTED_ODBC_DRIVERS
+from shared.sqlserver.odbc_driver_utils import get_best_sqlserver_driver
+from shared.sqlserver.version_detection import detect_sql_server_version
+
 from snowflake.snowflake_data_validation.connector.connector_base import (
     ConnectorBase as BaseConnector,
 )
@@ -71,7 +75,7 @@ AZURE_SQL_SCOPE = "https://database.windows.net/.default"
 
 # SQL Server Authentication connection strings
 SQLSERVER_CONNECTION_STRING = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server},{port};"
     "DATABASE={database};"
     "UID={user};"
@@ -81,7 +85,7 @@ SQLSERVER_CONNECTION_STRING = (
 )
 
 SQLSERVER_CONNECTION_STRING_NAMED = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server};"
     "DATABASE={database};"
     "UID={user};"
@@ -92,7 +96,7 @@ SQLSERVER_CONNECTION_STRING_NAMED = (
 
 # Windows Authentication connection strings (Trusted Connection)
 SQLSERVER_CONNECTION_STRING_WIN_AUTH = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server},{port};"
     "DATABASE={database};"
     "Trusted_Connection=yes;"
@@ -101,7 +105,7 @@ SQLSERVER_CONNECTION_STRING_WIN_AUTH = (
 )
 
 SQLSERVER_CONNECTION_STRING_WIN_AUTH_NAMED = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server};"
     "DATABASE={database};"
     "Trusted_Connection=yes;"
@@ -111,7 +115,7 @@ SQLSERVER_CONNECTION_STRING_WIN_AUTH_NAMED = (
 
 # Azure Entra ID connection strings (token-based authentication)
 SQLSERVER_CONNECTION_STRING_AZURE_TOKEN = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server},{port};"
     "DATABASE={database};"
     "TrustServerCertificate={trust_server_certificate};"
@@ -119,14 +123,13 @@ SQLSERVER_CONNECTION_STRING_AZURE_TOKEN = (
 )
 
 SQLSERVER_CONNECTION_STRING_AZURE_TOKEN_NAMED = (
-    "DRIVER={{ODBC Driver 18 for SQL Server}};"
+    "DRIVER={{{driver}}};"
     "SERVER={server};"
     "DATABASE={database};"
     "TrustServerCertificate={trust_server_certificate};"
     "Encrypt={encrypt}"
 )
 
-
 class ConnectorSqlServer(BaseConnector):
     """Connector for SQL Server database."""
 
@@ -136,6 +139,52 @@ class ConnectorSqlServer(BaseConnector):
         self.connection: object | None = None
         self.pyodbc = import_mssql()
 
+        # SQL Server version detection properties (set after connection)
+        self.sql_server_major_version: int | None = None
+        self.is_azure_sql_db: bool = False
+        self.supports_string_agg: bool = True  # Safe default for 2017+
+
+    def _detect_odbc_driver(self) -> str:
+        """Auto-detect the best available ODBC driver for SQL Server.
+
+        Delegates to shared.sqlserver.odbc_driver_utils.get_best_sqlserver_driver().
+
+        Returns:
+            str: The name of the detected ODBC driver.
+
+        Raises:
+            ConnectionError: If no compatible ODBC driver is found.
+
+        """
+        driver = get_best_sqlserver_driver()
+        if driver is None:
+            raise ConnectionError(
+                "No compatible ODBC driver found for SQL Server. "
+                "Please install one of the following:\n"
+                + "\n".join(f"  - {d}" for d in SUPPORTED_ODBC_DRIVERS[:2])
+                + "\nSee: https://learn.microsoft.com/en-us/sql/connect/odbc/download-odbc-driver-for-sql-server"
+            )
+        LOGGER.info("Using %s (auto-detected)", driver)
+        return driver
+
+    def _detect_sql_server_version(self) -> None:
+        """Detect the SQL Server version and set capability flags.
+
+        Delegates to shared.sqlserver.version_detection.detect_sql_server_version().
+        Updates instance attributes based on the detected version info.
+
+        This method is called after connection verification and should not raise
+        exceptions — version detection failure defaults to supports_string_agg=True.
+
+        """
+        if self.connection is None:
+            return
+
+        version_info = detect_sql_server_version(self.connection)
+        self.sql_server_major_version = version_info.major_version
+        self.is_azure_sql_db = version_info.is_azure_sql_db
+        self.supports_string_agg = version_info.supports_string_agg
+
     def _get_azure_access_token(
         self,
         mode: SqlServerMode,
@@ -351,6 +400,9 @@ class ConnectorSqlServer(BaseConnector):
 
         """
         try:
+            # Auto-detect the ODBC driver
+            driver = self._detect_odbc_driver()
+
             # Determine if this is a named instance connection
             is_named_instance = (
                 re.match(NAMED_INSTANCE_PATTERN_DETAILED, host) is not None
@@ -362,6 +414,7 @@ class ConnectorSqlServer(BaseConnector):
                 # Windows Authentication (Trusted Connection)
                 if is_named_instance and not is_custom_port:
                     self.string_connection = SQLSERVER_CONNECTION_STRING_WIN_AUTH_NAMED.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -370,6 +423,7 @@ class ConnectorSqlServer(BaseConnector):
                     )
                 else:
                     self.string_connection = SQLSERVER_CONNECTION_STRING_WIN_AUTH.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -386,6 +440,7 @@ class ConnectorSqlServer(BaseConnector):
                 # Azure Entra ID Authentication (token-based)
                 if is_named_instance and not is_custom_port:
                     self.string_connection = SQLSERVER_CONNECTION_STRING_AZURE_TOKEN_NAMED.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -394,6 +449,7 @@ class ConnectorSqlServer(BaseConnector):
                     )
                 else:
                     self.string_connection = SQLSERVER_CONNECTION_STRING_AZURE_TOKEN.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -426,6 +482,7 @@ class ConnectorSqlServer(BaseConnector):
                 # SQL Server Authentication (username/password)
                 if is_named_instance and not is_custom_port:
                     self.string_connection = SQLSERVER_CONNECTION_STRING_NAMED.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -436,6 +493,7 @@ class ConnectorSqlServer(BaseConnector):
                     )
                 else:
                     self.string_connection = SQLSERVER_CONNECTION_STRING.format(
+                        driver=driver,
                         server=host,
                         port=port,
                         database=database,
@@ -457,7 +515,7 @@ class ConnectorSqlServer(BaseConnector):
 
     @log
     def _verify_connection(self):
-        """Verify the connection by executing a simple test query.
+        """Verify the connection by executing a simple test query and detect server version.
 
         Raises:
             ConnectionError: If connection verification fails
@@ -474,6 +532,10 @@ class ConnectorSqlServer(BaseConnector):
                 cursor.execute("SELECT 1")
                 cursor.fetchone()
             LOGGER.debug("SQL Server connection verified successfully")
+
+            # Detect SQL Server version after successful verification
+            self._detect_sql_server_version()
+
         except Exception as e:
             LOGGER.error("Failed to verify SQL Server connection: %s", str(e))
             self.connection = None

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/sqlserver/extractor/templates/sqlserver_chunks_md5_table_template.sql.j2

@@ -1,4 +1,4 @@
 CREATE TABLE "#CHUNKS_MD5_{{ normalized_fully_qualified_name }}_{{ table_id }}"(
-    CHUNK_ID VARCHAR(100),
+    CHUNK_ID VARCHAR(1000),
     CHUNK_MD5_VALUE VARCHAR(32)
 );

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/sqlserver/extractor/templates/sqlserver_compute_md5_sql.j2

@@ -49,7 +49,17 @@ SELECT
 FROM "#ROW_CONCATENATED_{{ chunk_id }}_{{ table_id }}";
 
 INSERT INTO "#CHUNKS_MD5_{{ normalized_fully_qualified_name }}_{{ table_id }}"
+{% if supports_string_agg %}
 SELECT
     '{{ chunk_id }}',
     CONVERT(VARCHAR(32), HASHBYTES('MD5', STRING_AGG(CAST(ROW_MD5 AS VARCHAR(MAX)), '')), 2)
 FROM "#ROW_MD5_{{ chunk_id }}_{{ table_id }}";
+{% else %}
+SELECT
+    '{{ chunk_id }}',
+    CONVERT(VARCHAR(32), HASHBYTES('MD5',
+        (SELECT CAST(ROW_MD5 AS VARCHAR(MAX))
+         FROM "#ROW_MD5_{{ chunk_id }}_{{ table_id }}"
+         FOR XML PATH(''), TYPE).value('.', 'VARCHAR(MAX)')
+    ), 2);
+{% endif %}

{snowflake_data_validation-1.3.1 → snowflake_data_validation-1.3.2}/src/snowflake/snowflake_data_validation/sqlserver/query/query_generator_sqlserver.py

@@ -36,9 +36,16 @@ LOGGER = logging.getLogger(__name__)
 class QueryGeneratorSqlServer(QueryGeneratorBase):
     """SQL Server-specific implementation of query generator."""
 
-    def __init__(self):
-        """Initialize the SQL Server query generator."""
+    def __init__(self, supports_string_agg: bool = True):
+        """Initialize the SQL Server query generator.
+
+        Args:
+            supports_string_agg: Whether the target SQL Server supports STRING_AGG
+                (SQL Server 2017+ or Azure SQL DB). Defaults to True.
+
+        """
         super().__init__(platform=Platform.SQLSERVER)
+        self.supports_string_agg = supports_string_agg
 
     def cte_query_generator(
         self,
@@ -128,6 +135,7 @@ class QueryGeneratorSqlServer(QueryGeneratorBase):
             database_name=table_context.database_name,
             schema_name=table_context.schema_name,
             table_id=table_context.id,
+            supports_string_agg=self.supports_string_agg,
         )
 
         return query