Task/migrate up to python 3.12.0

.github/workflows/install-dependencies-and-run-tests.yml

@@ -0,0 +1,51 @@
+name: Test Python package new version
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install Linux dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y \
+          gcc \
+          libkrb5-dev \
+          libsasl2-dev \
+          python3-dev \
+          python3-all-dev
+    - name: Update pip version
+      run: |
+        python -m pip install --upgrade pip
+    - name: Install dependencies
+      run: |
+        pip install -r test/requirements.txt
+    - name: Build new version of the package
+      run: |
+        python -m build
+    - name: Install the new version of the package
+      run: |
+        pip install dist/*.tar.gz
+    - name: Test with pytest
+      env:
+        HOSTNAME: ${{ secrets.HOSTNAME }}
+        PORT: ${{ secrets.PORT }}
+        PROTOCOL: ${{ secrets.PROTOCOL }}
+        ONTOLOGY: ${{ secrets.ONTOLOGY }}
+        USERNAME: ${{ secrets.USERNAME }}
+        PASSWORD: ${{ secrets.PASSWORD }}
+        CONNECT_ARGS: ${{ secrets.CONNECT_ARGS }}
+      run: |
+        pytest

.gitignore

@@ -51,8 +51,9 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-test.py
-test/
+test/env*
+test/.python-version
+test/.env
 
 # Translations
 *.mo

MANIFEST.in

@@ -1 +1,2 @@
-include examples/*
+include examples/*
+include thrift/transport/THttpClient.py

README.md

@@ -1,11 +1,12 @@
-![Timbr logo](https://timbr.ai/wp-content/uploads/2023/06/timbr-ai-l-5-226x60-1.png)
+![Timbr logo](https://timbr.ai/wp-content/uploads/2025/01/logotimbrai230125.png)
 
 [![FOSSA Status](https://app.fossa.com/api/projects/custom%2B50508%2Fgithub.com%2FWPSemantix%2Ftimbr_python_SQLAlchemy.svg?type=shield&issueType=license)](https://app.fossa.com/projects/custom%2B50508%2Fgithub.com%2FWPSemantix%2Ftimbr_python_SQLAlchemy?ref=badge_shield&issueType=license)
 [![FOSSA Status](https://app.fossa.com/api/projects/custom%2B50508%2Fgithub.com%2FWPSemantix%2Ftimbr_python_SQLAlchemy.svg?type=shield&issueType=security)](https://app.fossa.com/projects/custom%2B50508%2Fgithub.com%2FWPSemantix%2Ftimbr_python_SQLAlchemy?ref=badge_shield&issueType=security)
 
-[![Python 3.7.13](https://img.shields.io/badge/python-3.7.13+-blue.svg)](https://www.python.org/downloads/release/python-3713/)
-[![Python 3.8](https://img.shields.io/badge/python-3.8-blue.svg)](https://www.python.org/downloads/release/python-3820/)
 [![Python 3.9](https://img.shields.io/badge/python-3.9-blue.svg)](https://www.python.org/downloads/release/python-3921/)
+[![Python 3.10](https://img.shields.io/badge/python-3.10-blue.svg)](https://www.python.org/downloads/release/python-31017/)
+[![Python 3.11](https://img.shields.io/badge/python-3.11-blue.svg)](https://www.python.org/downloads/release/python-31112/)
+[![Python 3.12](https://img.shields.io/badge/python-3.12-blue.svg)](https://www.python.org/downloads/release/python-3129/)
 
 [![PypiVersion](https://img.shields.io/pypi/v/pytimbr-sqla.svg)](https://badge.fury.io/py/pytimbr-sqla)
 
@@ -14,7 +15,7 @@ This project is a python connector to timbr using SQLAlchemy.
 
 ## Dependencies
 - Access to a timbr-server
-- Python from 3.7.13 or newer
+- Python from 3.9.13 or newer
 - Support SQLAlchemy 1.4.36 or newer but not version 2.x yet.
 - For <b>Linux</b> based machines only install those dependencies first:
   - gcc
@@ -27,10 +28,9 @@ This project is a python connector to timbr using SQLAlchemy.
 - Ubuntu example:
   - apt install gcc, heimdal-dev, krb5, python-devel, python-dev, python-all-dev, libsasl2-dev
 
-
 ## Installation
 - Install as clone repository:
-  - Install Python: https://www.python.org/downloads/release/python-3713/
+  - Install Python: https://www.python.org/downloads/release/python-3913/
   - Run the following command to install the Python dependencies: `pip install -r requirements.txt`
 
 - Install using pip and git:
@@ -39,15 +39,6 @@ This project is a python connector to timbr using SQLAlchemy.
 - Install using pip:
   - `pip install pytimbr-sqla`
 
-## Known issues
-If you encounter a problem installing `PyHive` with sasl dependencies on windows, install the following wheel (for 64bit Windows) by running:
-
-`pip install https://download.lfd.uci.edu/pythonlibs/archived/cp37/sasl-0.3.1-cp37-cp37m-win_amd64.whl`
-
-For Python 3.9:
-
-`pip install https://download.lfd.uci.edu/pythonlibs/archived/sasl-0.3.1-cp39-cp39-win_amd64.whl`
-
 ## Sample usage
 - For an example of how to use the Python SQLAlchemy connector for timbr, follow this [example file](examples/example.py)
 - For an example of how to use the Python SQLAlchemy connector with 'PyHive' as async query for timbr, follow this [example file](examples/pyhive_async_example.py)

requirements.txt

@@ -1,8 +1,8 @@
-future==0.18.3
-python-dateutil==2.8.2
-sasl>=0.2.1
-thrift>=0.13.0
-thrift_sasl>=0.1.0
+future==1.0.0
+python-dateutil==2.9.0
+ldap3
+thrift==0.21.0
+thrift_sasl==0.4.3
 pure-sasl>=0.6.2
 sqlalchemy>=1.4.36,<2.0.0
-requests_kerberos>=0.12.0
+requests_kerberos==0.15.0

setup.py

@@ -5,28 +5,28 @@
 
 setuptools.setup(
   name='pytimbr_sqla',
-  version='1.0.7',
+  version='2.0.0',
   author='timbr',
   author_email='contact@timbr.ai',
   description='Timbr Python SQLAlchemy connector',
   long_description=long_description,
   long_description_content_type="text/markdown",
   url='https://github.com/WPSemantix/timbr_python_SQLAlchemy',
-  download_url = 'https://github.com/WPSemantix/timbr_python_SQLAlchemy/archive/refs/tags/v1.0.7.tar.gz',
+  download_url = 'https://github.com/WPSemantix/timbr_python_SQLAlchemy/archive/refs/tags/v2.0.0.tar.gz',
   project_urls={
     "Bug Tracker": "https://github.com/WPSemantix/timbr_python_SQLAlchemy/issues"
   },
   license='MIT',
-  packages=['pytimbr_sqla', 'TCLIService'],
+  packages=['pytimbr_sqla', 'TCLIService', 'thrift', 'thrift.transport'],
   install_requires=[
-    'future',
-    'python-dateutil',
-    'sasl>=0.2.1',
-    'thrift>=0.13.0',
-    'thrift_sasl>=0.1.0',
+    'future==1.0.0',
+    'python-dateutil==2.9.0',
+    'ldap3',
+    'thrift_sasl==0.4.3',
     'pure-sasl>=0.6.2',
     'sqlalchemy>=1.4.36,<2.0.0',
-    'requests_kerberos>=0.12.0',
+    'requests_kerberos==0.15.0',
+    'pyhive==0.7.0',
   ],
   extras_require={},
   package_data={},
@@ -64,9 +64,10 @@
     'Topic :: Software Development :: Build Tools',
     'License :: OSI Approved :: MIT License',
     'Programming Language :: Python :: 3',
-    'Programming Language :: Python :: 3.7',
-    'Programming Language :: Python :: 3.8',
     'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
   ],
   entry_points={
     'sqlalchemy.dialects': [

test/conftest.py

@@ -0,0 +1,20 @@
+import os
+import json
+import pytest
+from dotenv import load_dotenv
+
+# Load .env file if it exists
+load_dotenv(override=True)
+
+# Global fixture to load config values
+@pytest.fixture(scope="session")
+def test_config():
+  return {
+    "hostname": os.getenv("HOSTNAME"),
+    "port": os.getenv("PORT"),
+    "protocol": os.getenv("PROTOCOL"),
+    "ontology": os.getenv("ONTOLOGY"),
+    "username": os.getenv("USERNAME"),
+    "password": os.getenv("PASSWORD"),
+    "connect_args": json.loads(os.getenv("CONNECT_ARGS", "{}"))
+  }

test/test_hive_dialect.py

@@ -0,0 +1,41 @@
+import pytest
+from utils import get_connection_uri_using_hive_dialect, run_query_using_hive_dialect
+
+def create_engine_and_run_query(config, is_async=False):
+  """
+  Creates a SQLAlchemy engine and runs a query using the Hive dialect.
+  """
+  uri = get_connection_uri_using_hive_dialect(
+    hostname=config['hostname'],
+    port=config['port'],
+    protocol=config['protocol'],
+    ontology=config['ontology'],
+    username=config['username'],
+    password=config['password']
+  )
+  return run_query_using_hive_dialect(
+    uri,
+    "SHOW CONCEPTS",
+    config['connect_args'],
+    is_async,
+  )
+
+def test_run_sync_query(test_config):
+  results_obj = create_engine_and_run_query(test_config, is_async=False)
+  results_data = results_obj["results"]
+  results_headers = results_obj["headers"]
+
+  assert results_obj is not None, "Query did not return any results"
+  assert len(results_data) > 0, "Query returned no rows"
+  assert len(results_headers) > 0, "Query returned no columns"
+  assert all(len(row) == len(results_headers) for row in results_data), "Row length does not match header length"
+
+def test_run_async_query(test_config):
+  results_obj = create_engine_and_run_query(test_config, is_async=True)
+  results_data = results_obj["results"]
+  results_headers = results_obj["headers"]
+
+  assert results_obj is not None, "Query did not return any results"
+  assert len(results_data) > 0, "Query returned no rows"
+  assert len(results_headers) > 0, "Query returned no columns"
+  assert all(len(row) == len(results_headers) for row in results_data), "Row length does not match header length"

test/test_timbr_dialect.py

@@ -0,0 +1,20 @@
+import pytest
+from utils import run_query_using_timbr_dialect, get_connection_uri_using_timbr_dialect
+
+def test_run_query(test_config):
+  uri = get_connection_uri_using_timbr_dialect(
+    hostname=test_config['hostname'],
+    port=test_config['port'],
+    protocol=test_config['protocol'],
+    ontology=test_config['ontology'],
+    username=test_config['username'],
+    password=test_config['password']
+  )
+  results_obj = run_query_using_timbr_dialect(uri, "SHOW CONCEPTS", connect_args=test_config['connect_args'])
+  results_data = results_obj["results"]
+  results_headers = results_obj["headers"]
+
+  assert results_obj is not None, "Query did not return any results"
+  assert len(results_data) > 0, "Query returned no rows"
+  assert len(results_headers) > 0, "Query returned no columns"
+  assert all(len(row) == len(results_headers) for row in results_data), "Row length does not match header length"

test/utils.py

@@ -0,0 +1,118 @@
+from sqlalchemy import create_engine
+from TCLIService.ttypes import TOperationState
+
+def set_dialect_for_new_connection_uri(dialect: str, uri: str) -> str:
+  """
+  Sets the dialect for a new connection URI.
+
+  :param dialect: The database dialect to use (e.g., 'timbr', 'hive').
+  :param connection_uri: The original connection URI.
+
+  :return: A new connection URI with the specified dialect.
+  """
+  if not uri.startswith(f"{dialect}+"):
+    return f"{dialect}+{uri}"
+  return uri
+
+def get_connection_uri_using_timbr_dialect(hostname: str, port: int, protocol: str, ontology: str, username: str, password: str) -> str:
+  """
+  Constructs a connection URI for the database using the provided parameters.
+
+  :param hostname: The hostname of the database server.
+  :param port: The port number on which the database server is listening.
+  :param protocol: The protocol to use (e.g., 'http', 'https').
+  :param ontology: The ontology or database name.
+  :param username: The username for authentication.
+  :param password: The password for authentication.
+
+  :return: A formatted connection URI string.
+  """
+  return f"timbr+{protocol}://{username}@{ontology}:{password}@{hostname}:{port}"
+
+def get_connection_uri_using_hive_dialect(hostname: str, port: int, protocol: str, ontology: str, username: str, password: str) -> str:
+  """
+  Constructs a connection URI for the Hive database using the provided parameters.
+
+  :param hostname: The hostname of the Hive server.
+  :param port: The port number on which the Hive server is listening.
+  :param protocol: The protocol to use (e.g., 'http', 'https').
+  :param ontology: The ontology or database name.
+  :param username: The username for authentication.
+  :param password: The password for authentication.
+
+  :return: A formatted connection URI string for Hive.
+  """
+  return f"hive+{protocol}://{username}@{ontology}:{password}@{hostname}:{port}"
+
+def run_query_using_timbr_dialect(uri: str, query: str, connect_args={}) -> object:
+  """
+  Connects to a database using the given URI,
+  executes the provided SQL query,
+  and returns the result object.
+  """
+  # Create new sqlalchemy connection
+  engine = create_engine(uri, connect_args=connect_args)
+
+  # Connect to the created engine
+  conn = engine.connect()
+
+  # Execute a query
+  res_obj = conn.execute(query)
+
+  results_headers = res_obj.keys()
+  results = res_obj.fetchall()
+  connect_args = connect_args or {}
+
+  # Display the results of the execution formatted as a table
+  # Print the columns name
+  print(f"index | {' | '.join(results_headers)}")
+  # Print a separator line
+  print("-" * ((len(results_headers)+1) * 10))
+  # Print the results
+  for res_index, result in enumerate(results, start=1):
+    print(f"{res_index} | {' | '.join(map(str, result))}")
+
+  return dict(results=results, headers=results_headers)
+
+def run_query_using_hive_dialect(uri: str, query: str, connect_args={}, is_async=False) -> object:
+  """
+  Connects to a Hive database using the given URI,
+  executes the provided SQL query,
+  and returns the result object.
+  """
+  # Create new sqlalchemy connection
+  engine = create_engine(uri, connect_args=connect_args)
+
+  # Connect to the created engine
+  conn = engine.connect()
+
+  if is_async:
+    dbapi_conn = engine.raw_connection()
+    cursor = dbapi_conn.cursor()
+
+    # Use the connection to execute a query
+    cursor.execute(query)
+
+    # Check the status of this execution
+    status = cursor.poll().operationState
+    while status in (TOperationState.INITIALIZED_STATE, TOperationState.RUNNING_STATE):
+      status = cursor.poll().operationState
+    # Get the results of the execution
+    results_headers = [(desc[0], desc[1]) for desc in cursor.description]
+    results = cursor.fetchall()
+
+  else:
+    # Use the connection to execute a query
+    res_obj = conn.execute(query)
+    results_headers = [(desc[0], desc[1]) for desc in res_obj.cursor.description]
+    results = res_obj.fetchall()
+
+  # Print the columns name
+  for name, col_type in results_headers:
+    print(f"{name} - {col_type}")
+
+  # Print the results
+  for result in results:
+    print(result)
+
+  return dict(results=results, headers=results_headers)

thrift/__init__.py

@@ -0,0 +1 @@
+# This file makes Python treat the directory as a package.