Merge branch 'main' into fix-oauth-log

Author: kravets-levko

.github/CODEOWNERS

@@ -2,4 +2,4 @@
 # the repo. Unless a later match takes precedence, these
 # users will be requested for review when someone opens a
 # pull request.
-*       @susodapop @arikfr @yunbodeng-db @andrefurlan-db
+*       @rcypher-databricks @arikfr @yunbodeng-db @andrefurlan-db @jackyhu-db @benc-db @kravets-levko

.github/workflows/code-quality-checks.yml

@@ -1,5 +1,5 @@
 name: Code Quality Checks
-on: 
+on:
   push:
     branches:
       - main
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9, "3.10", "3.11"]
+        python-version: [3.8, 3.9, "3.10", "3.11"]
     steps:
       #----------------------------------------------
       #       check-out repo and set-up python
@@ -29,7 +29,6 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: ${{ matrix.python-version == 3.7 && '1.5.1' || 'latest'  }}
           virtualenvs-create: true
           virtualenvs-in-project: true
           installer-parallel: true
@@ -63,7 +62,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9, "3.10"]
+        python-version: [3.8, 3.9, "3.10"]
     steps:
       #----------------------------------------------
       #       check-out repo and set-up python
@@ -81,7 +80,6 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: ${{ matrix.python-version == 3.7 && '1.5.1' || 'latest'  }}
           virtualenvs-create: true
           virtualenvs-in-project: true
           installer-parallel: true
@@ -116,7 +114,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7, 3.8, 3.9, "3.10"]
+        python-version: [3.8, 3.9, "3.10"]
     steps:
       #----------------------------------------------
       #       check-out repo and set-up python
@@ -134,7 +132,6 @@ jobs:
       - name: Install Poetry
         uses: snok/install-poetry@v1
         with:
-          version: ${{ matrix.python-version == 3.7 && '1.5.1' || 'latest'  }}
           virtualenvs-create: true
           virtualenvs-in-project: true
           installer-parallel: true
@@ -160,7 +157,7 @@ jobs:
       - name: Install library
         run: poetry install --no-interaction
       #----------------------------------------------
-      #              black the code
+      #              mypy the code
       #----------------------------------------------
       - name: Mypy
         run: poetry run mypy --install-types --non-interactive src

.github/workflows/integration.yml

@@ -0,0 +1,59 @@
+name: Integration Tests
+on:
+  push:
+    paths-ignore:
+      - "**.MD"
+      - "**.md"
+
+jobs:
+  run-e2e-tests:
+    runs-on: ubuntu-latest
+    environment: azure-prod
+    env:
+      DATABRICKS_SERVER_HOSTNAME: ${{ secrets.DATABRICKS_HOST }}
+      DATABRICKS_HTTP_PATH: ${{ secrets.TEST_PECO_WAREHOUSE_HTTP_PATH }}
+      DATABRICKS_TOKEN: ${{ secrets.DATABRICKS_TOKEN }}
+      DATABRICKS_CATALOG: peco
+      DATABRICKS_USER: ${{ secrets.TEST_PECO_SP_ID }}
+    steps:
+      #----------------------------------------------
+      #       check-out repo and set-up python
+      #----------------------------------------------
+      - name: Check out repository
+        uses: actions/checkout@v3
+      - name: Set up python
+        id: setup-python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      #----------------------------------------------
+      #  -----  install & configure poetry  -----
+      #----------------------------------------------
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      #----------------------------------------------
+      #       load cached venv if cache exists
+      #----------------------------------------------
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v2
+        with:
+          path: .venv
+          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ github.event.repository.name }}-${{ hashFiles('**/poetry.lock') }}
+      #----------------------------------------------
+      # install dependencies if cache does not exist
+      #----------------------------------------------
+      - name: Install dependencies
+        run: poetry install --no-interaction --all-extras
+      #----------------------------------------------
+      #              run test suite
+      #----------------------------------------------
+      - name: Run e2e tests
+        run: poetry run python -m pytest tests/e2e
+      - name: Run SQL Alchemy tests
+        run: poetry run python -m pytest src/databricks/sqlalchemy/test_local

CHANGELOG.md

@@ -1,28 +1,82 @@
 # Release History
 
-## 2.9.4 (Unreleased)
+# (Unreleased)
 
-- Other: Introduce SQLAlchemy dialect compliance test suite and enumerate all excluded tests
+- Fix: our logger would raise an uncaught exception under certain oauth error conditions
+
+# 3.1.2 (2024-04-18)
+
+- Remove broken cookie code (#379)
+- Small typing fixes (#382, #384 thanks @wyattscarpenter)
+
+# 3.1.1 (2024-03-19)
+
+- Don't retry requests that fail with code 403 (#373)
+- Assume a default retry-after for 429/503 (#371)
+- Fix boolean literals (#357)
+
+# 3.1.0 (2024-02-16)
+
+- Revert retry-after behavior to be exponential backoff (#349)
+- Support Databricks OAuth on Azure (#351)
+- Support Databricks OAuth on GCP (#338)
+
+# 3.0.3 (2024-02-02)
+
+- Revised docstrings and examples for OAuth (#339)
+- Redact the URL query parameters from the urllib3.connectionpool logs (#341)
+
+# 3.0.2 (2024-01-25)
+
+- SQLAlchemy dialect now supports table and column comments (thanks @cbornet!)
+- Fix: SQLAlchemy dialect now correctly reflects TINYINT types (thanks @TimTheinAtTabs!)
+- Fix: `server_hostname` URIs that included `https://` would raise an exception
+- Other: pinned to `pandas<=2.1` and `urllib3>=1.26` to avoid runtime errors in dbt-databricks (#330)
+
+## 3.0.1 (2023-12-01)
+
+- Other: updated docstring comment about default parameterization approach (#287)
+- Other: added tests for reading complex types and revised docstrings and type hints (#293)
+- Fix: SQLAlchemy dialect raised DeprecationWarning due to `dbapi` classmethod (#294)
+- Fix: SQLAlchemy dialect could not reflect TIMESTAMP_NTZ columns (#296)
+
+## 3.0.0 (2023-11-17)
+
+- Remove support for Python 3.7
+- Add support for native parameterized SQL queries. Requires DBR 14.2 and above. See docs/parameters.md for more info.
+- Completely rewritten SQLAlchemy dialect
+  - Adds support for SQLAlchemy >= 2.0 and drops support for SQLAlchemy 1.x
+  - Full e2e test coverage of all supported features
+  - Detailed usage notes in `README.sqlalchemy.md`
+  - Adds support for:
+    - New types: `TIME`, `TIMESTAMP`, `TIMESTAMP_NTZ`, `TINYINT`
+    - `Numeric` type scale and precision, like `Numeric(10,2)`
+    - Reading and writing `PrimaryKeyConstraint` and `ForeignKeyConstraint`
+    - Reading and writing composite keys
+    - Reading and writing from views
+    - Writing `Identity` to tables (i.e. autoincrementing primary keys)
+    - `LIMIT` and `OFFSET` for paging through results
+    - Caching metadata calls
+- Enable cloud fetch by default. To disable, set `use_cloud_fetch=False` when building `databricks.sql.client`.
 - Add integration tests for Databricks UC Volumes ingestion queries
 - Add `_retry_max_redirects` config
 - Enable cloud fetch by default. To disable, set `use_cloud_fetch=False` when building `databricks.sql.client`.
-- Fix: our logger would raise an uncaught exception under certain oauth error conditions
 
 ## 2.9.3 (2023-08-24)
 
 - Fix: Connections failed when urllib3~=1.0.0 is installed (#206)
 
 ## 2.9.2 (2023-08-17)
 
-__Note: this release was yanked from Pypi on 13 September 2023 due to compatibility issues with environments where `urllib3<=2.0.0` were installed. The log changes are incorporated into version 2.9.3 and greater.__
+**Note: this release was yanked from Pypi on 13 September 2023 due to compatibility issues with environments where `urllib3<=2.0.0` were installed. The log changes are incorporated into version 2.9.3 and greater.**
 
 - Other: Add `examples/v3_retries_query_execute.py` (#199)
 - Other: suppress log message when `_enable_v3_retries` is not `True` (#199)
 - Other: make this connector backwards compatible with `urllib3>=1.0.0` (#197)
 
 ## 2.9.1 (2023-08-11)
 
-__Note: this release was yanked from Pypi on 13 September 2023 due to compatibility issues with environments where `urllib3<=2.0.0` were installed.__
+**Note: this release was yanked from Pypi on 13 September 2023 due to compatibility issues with environments where `urllib3<=2.0.0` were installed.**
 
 - Other: Explicitly pin urllib3 to ^2.0.0 (#191)
 
@@ -75,6 +129,7 @@ __Note: this release was yanked from Pypi on 13 September 2023 due to compatibil
 - Other: Relax sqlalchemy required version as it was unecessarily strict.
 
 ## 2.5.0 (2023-04-14)
+
 - Add support for External Auth providers
 - Fix: Python HTTP proxies were broken
 - Other: All Thrift requests that timeout during connection will be automatically retried
@@ -96,8 +151,8 @@ __Note: this release was yanked from Pypi on 13 September 2023 due to compatibil
 
 ## 2.2.2 (2023-01-03)
 
-- Support custom oauth client id and redirect port 
-- Fix: Add none check on _oauth_persistence in DatabricksOAuthProvider
+- Support custom oauth client id and redirect port
+- Fix: Add none check on \_oauth_persistence in DatabricksOAuthProvider
 
 ## 2.2.1 (2022-11-29)
 
@@ -129,57 +184,71 @@ Huge thanks to @dbaxa for contributing this change!
 
 - Add retry logic for `GetOperationStatus` requests that fail with an `OSError`
 - Reorganised code to use Poetry for dependency management.
+
 ## 2.0.2 (2022-05-04)
+
 - Better exception handling in automatic connection close
 
 ## 2.0.1 (2022-04-21)
+
 - Fixed Pandas dependency in setup.cfg to be >= 1.2.0
 
 ## 2.0.0 (2022-04-19)
+
 - Initial stable release of V2
-- Added better support for complex types, so that in Databricks runtime 10.3+, Arrays, Maps and Structs will get 
+- Added better support for complex types, so that in Databricks runtime 10.3+, Arrays, Maps and Structs will get
   deserialized as lists, lists of tuples and dicts, respectively.
 - Changed the name of the metadata arg to http_headers
 
 ## 2.0.b2 (2022-04-04)
+
 - Change import of collections.Iterable to collections.abc.Iterable to make the library compatible with Python 3.10
 - Fixed bug with .tables method so that .tables works as expected with Unity-Catalog enabled endpoints
 
 ## 2.0.0b1 (2022-03-04)
+
 - Fix packaging issue (dependencies were not being installed properly)
 - Fetching timestamp results will now return aware instead of naive timestamps
 - The client will now default to using simplified error messages
 
 ## 2.0.0b (2022-02-08)
+
 - Initial beta release of V2. V2 is an internal re-write of large parts of the connector to use Databricks edge features. All public APIs from V1 remain.
-- Added Unity Catalog support (pass catalog and / or  schema key word args to the .connect method to select initial schema and catalog)
+- Added Unity Catalog support (pass catalog and / or schema key word args to the .connect method to select initial schema and catalog)
 
 ---
 
 **Note**: The code for versions prior to `v2.0.0b` is not contained in this repository. The below entries are included for reference only.
 
 ---
+
 ## 1.0.0 (2022-01-20)
+
 - Add operations for retrieving metadata
 - Add the ability to access columns by name on result rows
 - Add the ability to provide configuration settings on connect
 
 ## 0.9.4 (2022-01-10)
+
 - Improved logging and error messages.
 
 ## 0.9.3 (2021-12-08)
+
 - Add retries for 429 and 503 HTTP responses.
 
 ## 0.9.2 (2021-12-02)
+
 - (Bug fix) Increased Thrift requirement from 0.10.0 to 0.13.0 as 0.10.0 was in fact incompatible
 - (Bug fix) Fixed error message after query execution failed -SQLSTATE and Error message were misplaced
 
 ## 0.9.1 (2021-09-01)
+
 - Public Preview release, Experimental tag removed
 - minor updates in internal build/packaging
 - no functional changes
 
 ## 0.9.0 (2021-08-04)
+
 - initial (Experimental) release of pyhive-forked connector
 - Python DBAPI 2.0 (PEP-0249), thrift based
 - see docs for more info: https://docs.databricks.com/dev-tools/python-sql-connector.html

README.md

@@ -11,7 +11,7 @@ You are welcome to file an issue here for general use cases. You can also contac
 
 ## Requirements
 
-Python 3.7 or above is required.
+Python 3.8 or above is required.
 
 ## Documentation
 
@@ -47,8 +47,7 @@ connection = sql.connect(
   access_token=access_token)
 
 cursor = connection.cursor()
-
-cursor.execute('SELECT * FROM RANGE(10)')
+cursor.execute('SELECT :param `p`, * FROM RANGE(10)', {"param": "foo"})
 result = cursor.fetchall()
 for row in result:
   print(row)

conftest.py

@@ -0,0 +1,44 @@
+import os
+import pytest
+
+
+@pytest.fixture(scope="session")
+def host():
+    return os.getenv("DATABRICKS_SERVER_HOSTNAME")
+
+
+@pytest.fixture(scope="session")
+def http_path():
+    return os.getenv("DATABRICKS_HTTP_PATH")
+
+
+@pytest.fixture(scope="session")
+def access_token():
+    return os.getenv("DATABRICKS_TOKEN")
+
+
+@pytest.fixture(scope="session")
+def ingestion_user():
+    return os.getenv("DATABRICKS_USER")
+
+
+@pytest.fixture(scope="session")
+def catalog():
+    return os.getenv("DATABRICKS_CATALOG")
+
+
+@pytest.fixture(scope="session")
+def schema():
+    return os.getenv("DATABRICKS_SCHEMA", "default")
+
+
+@pytest.fixture(scope="session", autouse=True)
+def connection_details(host, http_path, access_token, ingestion_user, catalog, schema):
+    return {
+        "host": host,
+        "http_path": http_path,
+        "access_token": access_token,
+        "ingestion_user": ingestion_user,
+        "catalog": catalog,
+        "schema": schema,
+    }