snowflake-data-validation 1.24.2__tar.gz → 1.25.1__tar.gz

{snowflake_data_validation-1.24.2 → snowflake_data_validation-1.25.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-data-validation
-Version: 1.24.2
+Version: 1.25.1
 Summary: Snowflake 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/
@@ -89,9 +89,9 @@ Description-Content-Type: text/markdown
 [![License](https://img.shields.io/badge/License-Snowflake%20Conversion%20Software-blue)](https://www.snowflake.com/en/legal/technical-services-and-education/conversion-software-terms/)
 [![Python](https://img.shields.io/badge/python-3.10--3.13-blue)](https://www.python.org/downloads/)
 
-**Snowflake Data Validation** is a command-line tool and Python library for validating data migrations and ensuring data quality between source and target databases, with support for SQL Server, Redshift, Teradata, and Oracle as source systems.
+**Snowflake Data Validation** is a Python library for validating data migrations and ensuring data quality between source and target databases, with support for SQL Server, Redshift, Teradata, and Oracle as source systems.
 
-> 📖 **For detailed usage instructions, configuration examples, and CLI reference, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).**
+> 📖 **For detailed usage instructions and configuration examples, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).**
 
 ---
 
@@ -99,7 +99,6 @@ Description-Content-Type: text/markdown
 
 - **Multi-level validation**: Schema validation, statistical metrics, and row-level data integrity checks.
 - **Multiple source platforms**: SQL Server, Redshift, Teradata, Oracle.
-- **User-friendly CLI**: Comprehensive commands for automation and orchestration.
 - **Parallel processing**: Multi-threaded table validation for faster execution.
 - **Offline validation**: Extract source data as Parquet files for validation without source access.
 - **Flexible configuration**: YAML-based workflows with per-table customization.
@@ -139,27 +138,6 @@ pip install "snowflake-data-validation[all]"
 
 ---
 
-## 🔄 Execution Modes
-
-| Mode | Command | Description |
-|------|---------|-------------|
-| **Sync Validation** | `run-validation` | Real-time comparison between source and target databases |
-| **Source Extraction** | `source-validate` | Extract source data to Parquet files for offline validation |
-| **Async Validation** | `run-async-validation` | Validate using pre-extracted Parquet files |
-| **Script Generation** | `generate-validation-scripts` | Generate SQL scripts for manual execution |
-
-**Supported Dialects**: `sqlserver`, `snowflake`, `redshift`, `teradata`, `oracle`
-
-**CLI entry point**: from the repo (or an install), run the package module — for example:
-
-```bash
-python -m snowflake.snowflake_data_validation redshift run-validation -dvf path/to/config.yaml
-```
-
-Do not use `python -m snowflake.snowflake_data_validation.main_cli` for subcommands; that path exits after logging without dispatching to `redshift` / `sqlserver` / etc.
-
----
-
 ## 🔍 Validation Levels
 
 Validation runs **L1 schema**, **L2 metrics**, and optionally **L3 row** (and cell / hybrid modes where configured). Each level emits per-column (or per-criterion) rows with a `STATUS` of `SUCCESS` or `FAILURE`; the run is considered passing at that level only when **no failure rows** are present.
@@ -199,24 +177,31 @@ Performs row-by-row comparison:
 
 ---
 
-## CLI commands
-
-```bash
-snowflake-data-validation <source_dialect> <command> [options]
-# Short alias: sdv <source_dialect> <command> [options]
-```
+## 📚 Documentation
 
-Supported dialects include `sqlserver`, `teradata`, `redshift`, and `oracle`. Common commands: `run-validation`, `run-async-validation`, `source-validate`, and `generate-validation-scripts`. The dialect must match `source_platform` in your configuration file.
+For configuration options and examples, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).
 
 ---
 
-## 📚 Documentation
+## Changelog
 
-For complete command reference, configuration options, and examples, see the [Data Validation CLI](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).
+### v1.25.1
 
----
+**Improvements**
 
-## Changelog
+- Removed the deprecated `sdv` CLI layer; Cloud Data Validation via the Data Exchange Agent is now the only supported execution path.
+
+### v1.25.0
+
+**New features**
+
+- Added automatic primary key inference for SQL Server, Teradata, and Redshift.
+- Added BigQuery support for cloud Data Validation (L1/L2/L3).
+- Added Redshift data type coverage for data migration and validation.
+
+**Improvements**
+
+- Improved numeric canonical rendering with scale-aware precision for Oracle, Teradata, Redshift, and PostgreSQL.
 
 ### v1.24.2
 

{snowflake_data_validation-1.24.2 → snowflake_data_validation-1.25.1}/README.md

@@ -3,9 +3,9 @@
 [![License](https://img.shields.io/badge/License-Snowflake%20Conversion%20Software-blue)](https://www.snowflake.com/en/legal/technical-services-and-education/conversion-software-terms/)
 [![Python](https://img.shields.io/badge/python-3.10--3.13-blue)](https://www.python.org/downloads/)
 
-**Snowflake Data Validation** is a command-line tool and Python library for validating data migrations and ensuring data quality between source and target databases, with support for SQL Server, Redshift, Teradata, and Oracle as source systems.
+**Snowflake Data Validation** is a Python library for validating data migrations and ensuring data quality between source and target databases, with support for SQL Server, Redshift, Teradata, and Oracle as source systems.
 
-> 📖 **For detailed usage instructions, configuration examples, and CLI reference, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).**
+> 📖 **For detailed usage instructions and configuration examples, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).**
 
 ---
 
@@ -13,7 +13,6 @@
 
 - **Multi-level validation**: Schema validation, statistical metrics, and row-level data integrity checks.
 - **Multiple source platforms**: SQL Server, Redshift, Teradata, Oracle.
-- **User-friendly CLI**: Comprehensive commands for automation and orchestration.
 - **Parallel processing**: Multi-threaded table validation for faster execution.
 - **Offline validation**: Extract source data as Parquet files for validation without source access.
 - **Flexible configuration**: YAML-based workflows with per-table customization.
@@ -53,27 +52,6 @@ pip install "snowflake-data-validation[all]"
 
 ---
 
-## 🔄 Execution Modes
-
-| Mode | Command | Description |
-|------|---------|-------------|
-| **Sync Validation** | `run-validation` | Real-time comparison between source and target databases |
-| **Source Extraction** | `source-validate` | Extract source data to Parquet files for offline validation |
-| **Async Validation** | `run-async-validation` | Validate using pre-extracted Parquet files |
-| **Script Generation** | `generate-validation-scripts` | Generate SQL scripts for manual execution |
-
-**Supported Dialects**: `sqlserver`, `snowflake`, `redshift`, `teradata`, `oracle`
-
-**CLI entry point**: from the repo (or an install), run the package module — for example:
-
-```bash
-python -m snowflake.snowflake_data_validation redshift run-validation -dvf path/to/config.yaml
-```
-
-Do not use `python -m snowflake.snowflake_data_validation.main_cli` for subcommands; that path exits after logging without dispatching to `redshift` / `sqlserver` / etc.
-
----
-
 ## 🔍 Validation Levels
 
 Validation runs **L1 schema**, **L2 metrics**, and optionally **L3 row** (and cell / hybrid modes where configured). Each level emits per-column (or per-criterion) rows with a `STATUS` of `SUCCESS` or `FAILURE`; the run is considered passing at that level only when **no failure rows** are present.
@@ -113,24 +91,31 @@ Performs row-by-row comparison:
 
 ---
 
-## CLI commands
-
-```bash
-snowflake-data-validation <source_dialect> <command> [options]
-# Short alias: sdv <source_dialect> <command> [options]
-```
+## 📚 Documentation
 
-Supported dialects include `sqlserver`, `teradata`, `redshift`, and `oracle`. Common commands: `run-validation`, `run-async-validation`, `source-validate`, and `generate-validation-scripts`. The dialect must match `source_platform` in your configuration file.
+For configuration options and examples, see the [official documentation](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).
 
 ---
 
-## 📚 Documentation
+## Changelog
 
-For complete command reference, configuration options, and examples, see the [Data Validation CLI](https://docs.snowflake.com/en/migrations/snowconvert-docs/data-validation-cli/CLI_QUICK_REFERENCE).
+### v1.25.1
 
----
+**Improvements**
 
-## Changelog
+- Removed the deprecated `sdv` CLI layer; Cloud Data Validation via the Data Exchange Agent is now the only supported execution path.
+
+### v1.25.0
+
+**New features**
+
+- Added automatic primary key inference for SQL Server, Teradata, and Redshift.
+- Added BigQuery support for cloud Data Validation (L1/L2/L3).
+- Added Redshift data type coverage for data migration and validation.
+
+**Improvements**
+
+- Improved numeric canonical rendering with scale-aware precision for Oracle, Teradata, Redshift, and PostgreSQL.
 
 ### v1.24.2
 

{snowflake_data_validation-1.24.2 → snowflake_data_validation-1.25.1}/pyproject.toml

@@ -60,10 +60,6 @@ name = "snowflake-data-validation"
 readme = "README.md"
 requires-python = '>=3.10'
 
-[project.scripts]
-sdv = "snowflake.snowflake_data_validation.main_cli:data_validation_app"
-snowflake-data-validation = "snowflake.snowflake_data_validation.main_cli:data_validation_app"
-
 [project.optional-dependencies]
 all = ["snowflake-data-validation[development,sqlserver,teradata,redshift,postgresql,azure-synapse,sqlite]"]
 development = [

{snowflake_data_validation-1.24.2 → snowflake_data_validation-1.25.1}/src/snowflake/snowflake_data_validation/__init__.py

@@ -25,7 +25,6 @@ Features
 --------
 - Multi-level data validation (Level 1: table metadata, Level 2: column metadata)
 - Support for multiple source systems (SQL Server, Snowflake)
-- CLI interface for validation operations
 - Configurable validation processes
 - Progress reporting and detailed validation reports
 
@@ -38,12 +37,6 @@ 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
-    - Running validation operations
-    - Managing configuration files
-
 Supported Dialects
 ------------------
 - Snowflake to Snowflake validation
@@ -68,18 +61,6 @@ Programmatic API (Decoupled Steps):
 >>> result = public.execute_query(table_context, connector, schema_query)
 >>> validation_result = public.validate_schema(source_df, target_df)
 
-Command Line Interface:
-
-.. code-block:: bash
-
-    # Set up SQL Server connection
-    python -m snowflake.snowflake_data_validation sqlserver source-connection \
-        --host localhost --port 1433 --username user --password pass --database mydb
-
-    # Run validation
-    python -m snowflake.snowflake_data_validation sqlserver run-validation \
-        --data-validation-config-file config.json
-
 For more detailed examples and usage, please refer to the documentation.
 """
 
@@ -98,6 +79,7 @@ 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.oracle as oracle
+import snowflake.snowflake_data_validation.bigquery as bigquery
 import snowflake.snowflake_data_validation.public as public
 import logging
 
@@ -119,6 +101,7 @@ __all__ = [
     "sqlserver",
     "redshift",
     "oracle",
+    "bigquery",
     "public",
 ]
 

snowflake_data_validation-1.25.1/src/snowflake/snowflake_data_validation/bigquery/__init__.py

@@ -0,0 +1,29 @@
+# Copyright 2026 Snowflake Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+"""
+Snowflake Data Validation BigQuery
+=====================================
+
+This package provides BigQuery-specific query generation for data validation.
+
+BigQuery participates as a *source* platform whose row extraction is driven by
+the Data Exchange Agent (DEA). The desktop package only owns the query
+generator and the SQL/YAML templates required to produce parity-preserving
+BigQuery SQL for L1 (schema), L2 (metrics) and L3 (row-hash) validation against
+a Snowflake target. It does not open BigQuery connections itself.
+
+Main Components
+----------------
+- QueryGeneratorBigQuery: BigQuery-specific SQL generation (inline SELECT path).
+- extractor/templates: BigQuery normalization, metrics and metadata templates.
+"""
+
+from snowflake.snowflake_data_validation.bigquery.query.query_generator_bigquery import (
+    QueryGeneratorBigQuery,
+)
+
+
+__all__ = [
+    "QueryGeneratorBigQuery",
+]

snowflake_data_validation-1.25.1/src/snowflake/snowflake_data_validation/bigquery/extractor/__init__.py

@@ -0,0 +1,16 @@
+# 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.
+
+"""BigQuery extractor templates (normalization, metrics, metadata)."""

snowflake_data_validation-1.25.1/src/snowflake/snowflake_data_validation/bigquery/extractor/templates/bigquery_cell_validation_data_select.sql.j2

@@ -0,0 +1,16 @@
+{% import 'query_modifiers.sql.j2' as qm with context %}
+{{ qm.locking_prefix(query_modifiers) }}SELECT
+{% for column in column_collection %}
+    {% if column.nullable %}
+        RTRIM(COALESCE({{ datatypes_normalization_renderer_templates[column.name] }}, '{{ null_hashing_sentinel }}')) AS `{{ column.name }}`{% if not loop.last %},{% endif %}
+    {% else %}
+        RTRIM({{ datatypes_normalization_renderer_templates[column.name] }}) AS `{{ column.name }}`{% if not loop.last %},{% endif %}
+    {% endif %}
+{% endfor %}
+FROM (
+    SELECT * {{ qm.render_from_clause(query_modifiers, fully_qualified_name, 't') }}
+    {% if has_where_clause %} WHERE {{ where_clause }} {% endif %}
+    {% if order_by_columns %}
+    ORDER BY {% for c in order_by_columns %} `{{ c }}`{% if not loop.last %}, {% endif %}{% endfor %}
+    {% endif %}
+) __ordered