databricks-sql-connector 4.0.0b3__tar.gz → 4.0.0b4__tar.gz

{databricks_sql_connector-4.0.0b3 → databricks_sql_connector-4.0.0b4}/CHANGELOG.md

@@ -1,5 +1,10 @@
 # Release History
 
+# 4.0.0 
+
+- Split the connector into two separate packages: `databricks-sql-connector` and `databricks-sqlalchemy`. The `databricks-sql-connector` package contains the core functionality of the connector, while the `databricks-sqlalchemy` package contains the SQLAlchemy dialect for the connector. 
+- Pyarrow dependency is now optional in `databricks-sql-connector`. Users needing arrow are supposed to explicitly install pyarrow 
+
 # 3.6.0 (2024-10-25)
 
 - Support encryption headers in the cloud fetch request (https://github.com/databricks/databricks-sql-python/pull/460 by @jackyhu-db)

{databricks_sql_connector-4.0.0b3 → databricks_sql_connector-4.0.0b4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: databricks-sql-connector
-Version: 4.0.0b3
+Version: 4.0.0b4
 Summary: Databricks SQL Connector for Python
 License: Apache-2.0
 Author: Databricks
@@ -13,11 +13,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Provides-Extra: alembic
-Provides-Extra: databricks-sqlalchemy
 Provides-Extra: pyarrow
-Requires-Dist: alembic (>=1.0.11,<2.0.0) ; extra == "alembic"
-Requires-Dist: databricks-sqlalchemy (>=2.0.0) ; extra == "databricks-sqlalchemy" or extra == "alembic"
 Requires-Dist: lz4 (>=4.0.2,<5.0.0)
 Requires-Dist: numpy (>=1.16.6,<2.0.0) ; python_version >= "3.8" and python_version < "3.11"
 Requires-Dist: numpy (>=1.23.4,<2.0.0) ; python_version >= "3.11"
@@ -37,9 +33,9 @@ Description-Content-Type: text/markdown
 [![PyPI](https://img.shields.io/pypi/v/databricks-sql-connector?style=flat-square)](https://pypi.org/project/databricks-sql-connector/)
 [![Downloads](https://pepy.tech/badge/databricks-sql-connector)](https://pepy.tech/project/databricks-sql-connector)
 
-The Databricks SQL Connector for Python allows you to develop Python applications that connect to Databricks clusters and SQL warehouses. It is a Thrift-based client with no dependencies on ODBC or JDBC. It conforms to the [Python DB API 2.0 specification](https://www.python.org/dev/peps/pep-0249/) and exposes a [SQLAlchemy](https://www.sqlalchemy.org/) dialect for use with tools like `pandas` and `alembic` which use SQLAlchemy to execute DDL. Use `pip install databricks-sql-connector[sqlalchemy]` to install with SQLAlchemy's dependencies. `pip install databricks-sql-connector[alembic]` will install alembic's dependencies.
+The Databricks SQL Connector for Python allows you to develop Python applications that connect to Databricks clusters and SQL warehouses. It is a Thrift-based client with no dependencies on ODBC or JDBC. It conforms to the [Python DB API 2.0 specification](https://www.python.org/dev/peps/pep-0249/).
 
-This connector uses Arrow as the data-exchange format, and supports APIs to directly fetch Arrow tables. Arrow tables are wrapped in the `ArrowQueue` class to provide a natural API to get several rows at a time.
+This connector uses Arrow as the data-exchange format, and supports APIs (e.g. `fetchmany_arrow`) to directly fetch Arrow tables. Arrow tables are wrapped in the `ArrowQueue` class to provide a natural API to get several rows at a time. [PyArrow](https://arrow.apache.org/docs/python/index.html) is required to enable this and use these APIs, you can install it via  `pip install pyarrow` or `pip install databricks-sql-connector[pyarrow]`.
 
 You are welcome to file an issue here for general use cases. You can also contact Databricks Support [here](help.databricks.com).
 
@@ -56,7 +52,12 @@ For the latest documentation, see
 
 ## Quickstart
 
-Install the library with `pip install databricks-sql-connector`
+### Installing the core library
+Install using `pip install databricks-sql-connector`
+
+### Installing the core library with PyArrow
+Install using `pip install databricks-sql-connector[pyarrow]`
+
 
 ```bash
 export DATABRICKS_HOST=********.databricks.com
@@ -94,6 +95,18 @@ or to a Databricks Runtime interactive cluster (e.g. /sql/protocolv1/o/123456789
 > to authenticate the target Databricks user account and needs to open the browser for authentication. So it 
 > can only run on the user's machine.
 
+## SQLAlchemy
+Starting from `databricks-sql-connector` version 4.0.0 SQLAlchemy support has been extracted to a new library `databricks-sqlalchemy`.
+
+- Github repository [databricks-sqlalchemy github](https://github.com/databricks/databricks-sqlalchemy)
+- PyPI [databricks-sqlalchemy pypi](https://pypi.org/project/databricks-sqlalchemy/)
+
+### Quick SQLAlchemy guide
+Users can now choose between using the SQLAlchemy v1 or SQLAlchemy v2 dialects with the connector core
+
+- Install the latest SQLAlchemy v1 using `pip install databricks-sqlalchemy~=1.0`
+- Install SQLAlchemy v2 using `pip install databricks-sqlalchemy`
+
 
 ## Contributing
 

{databricks_sql_connector-4.0.0b3 → databricks_sql_connector-4.0.0b4}/README.md

@@ -3,9 +3,9 @@
 [![PyPI](https://img.shields.io/pypi/v/databricks-sql-connector?style=flat-square)](https://pypi.org/project/databricks-sql-connector/)
 [![Downloads](https://pepy.tech/badge/databricks-sql-connector)](https://pepy.tech/project/databricks-sql-connector)
 
-The Databricks SQL Connector for Python allows you to develop Python applications that connect to Databricks clusters and SQL warehouses. It is a Thrift-based client with no dependencies on ODBC or JDBC. It conforms to the [Python DB API 2.0 specification](https://www.python.org/dev/peps/pep-0249/) and exposes a [SQLAlchemy](https://www.sqlalchemy.org/) dialect for use with tools like `pandas` and `alembic` which use SQLAlchemy to execute DDL. Use `pip install databricks-sql-connector[sqlalchemy]` to install with SQLAlchemy's dependencies. `pip install databricks-sql-connector[alembic]` will install alembic's dependencies.
+The Databricks SQL Connector for Python allows you to develop Python applications that connect to Databricks clusters and SQL warehouses. It is a Thrift-based client with no dependencies on ODBC or JDBC. It conforms to the [Python DB API 2.0 specification](https://www.python.org/dev/peps/pep-0249/).
 
-This connector uses Arrow as the data-exchange format, and supports APIs to directly fetch Arrow tables. Arrow tables are wrapped in the `ArrowQueue` class to provide a natural API to get several rows at a time.
+This connector uses Arrow as the data-exchange format, and supports APIs (e.g. `fetchmany_arrow`) to directly fetch Arrow tables. Arrow tables are wrapped in the `ArrowQueue` class to provide a natural API to get several rows at a time. [PyArrow](https://arrow.apache.org/docs/python/index.html) is required to enable this and use these APIs, you can install it via  `pip install pyarrow` or `pip install databricks-sql-connector[pyarrow]`.
 
 You are welcome to file an issue here for general use cases. You can also contact Databricks Support [here](help.databricks.com).
 
@@ -22,7 +22,12 @@ For the latest documentation, see
 
 ## Quickstart
 
-Install the library with `pip install databricks-sql-connector`
+### Installing the core library
+Install using `pip install databricks-sql-connector`
+
+### Installing the core library with PyArrow
+Install using `pip install databricks-sql-connector[pyarrow]`
+
 
 ```bash
 export DATABRICKS_HOST=********.databricks.com
@@ -60,6 +65,18 @@ or to a Databricks Runtime interactive cluster (e.g. /sql/protocolv1/o/123456789
 > to authenticate the target Databricks user account and needs to open the browser for authentication. So it 
 > can only run on the user's machine.
 
+## SQLAlchemy
+Starting from `databricks-sql-connector` version 4.0.0 SQLAlchemy support has been extracted to a new library `databricks-sqlalchemy`.
+
+- Github repository [databricks-sqlalchemy github](https://github.com/databricks/databricks-sqlalchemy)
+- PyPI [databricks-sqlalchemy pypi](https://pypi.org/project/databricks-sqlalchemy/)
+
+### Quick SQLAlchemy guide
+Users can now choose between using the SQLAlchemy v1 or SQLAlchemy v2 dialects with the connector core
+
+- Install the latest SQLAlchemy v1 using `pip install databricks-sqlalchemy~=1.0`
+- Install SQLAlchemy v2 using `pip install databricks-sqlalchemy`
+
 
 ## Contributing
 

{databricks_sql_connector-4.0.0b3 → databricks_sql_connector-4.0.0b4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "databricks-sql-connector"
-version = "4.0.0.b3"
+version = "4.0.0.b4"
 description = "Databricks SQL Connector for Python"
 authors = ["Databricks <databricks-sql-connector-maintainers@databricks.com>"]
 license = "Apache-2.0"
@@ -23,15 +23,9 @@ numpy = [
 ]
 openpyxl = "^3.0.10"
 urllib3 = ">=1.26"
-
-databricks-sqlalchemy = { version = ">=2.0.0", optional = true }
 pyarrow = { version = ">=14.0.1,<17", optional=true }
-alembic = { version = "^1.0.11", optional = true }
-
 
 [tool.poetry.extras]
-databricks-sqlalchemy = ["databricks-sqlalchemy"]
-alembic = ["databricks-sqlalchemy", "alembic"]
 pyarrow = ["pyarrow"]
 
 [tool.poetry.dev-dependencies]
@@ -45,9 +39,6 @@ pytest-dotenv = "^0.5.2"
 "Homepage" = "https://github.com/databricks/databricks-sql-python"
 "Bug Tracker" = "https://github.com/databricks/databricks-sql-python/issues"
 
-[tool.poetry.plugins."sqlalchemy.dialects"]
-"databricks" = "databricks.sqlalchemy:DatabricksDialect"
-
 [build-system]
 requires = ["poetry-core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
@@ -64,5 +55,5 @@ markers = {"reviewed" = "Test case has been reviewed by Databricks"}
 minversion = "6.0"
 log_cli = "false"
 log_cli_level = "INFO"
-testpaths = ["tests", "src/databricks/sqlalchemy/test_local"]
+testpaths = ["tests"]
 env_files = ["test.env"]

{databricks_sql_connector-4.0.0b3 → databricks_sql_connector-4.0.0b4}/src/databricks/sql/client.py

@@ -52,6 +52,13 @@ from databricks.sql.thrift_api.TCLIService.ttypes import (
 
 logger = logging.getLogger(__name__)
 
+if pyarrow is None:
+    logger.warning(
+        "[WARN] pyarrow is not installed by default since databricks-sql-connector 4.0.0,"
+        "any arrow specific api (e.g. fetchmany_arrow) and cloud fetch will be disabled."
+        "If you need these features, please run pip install pyarrow or pip install databricks-sql-connector[pyarrow] to install"
+    )
+
 DEFAULT_RESULT_BUFFER_SIZE_BYTES = 104857600
 DEFAULT_ARRAY_SIZE = 100000
 

databricks_sql_connector-4.0.0b3/src/databricks/sqlalchemy/__init__.py

@@ -1,6 +0,0 @@
-try:
-	from databricks_sqlalchemy import *
-except:
-	import warnings
-
-	warnings.warn("Install databricks-sqlalchemy plugin before using this")