Add UTF-8 encoding support for query data and update version to 2.1.0

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

@@ -10,7 +10,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.11", "3.12"]
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}

README.md

@@ -3,7 +3,6 @@
 [![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2FWPSemantix%2Ftimbr_python_http.svg?type=shield&issueType=license)](https://app.fossa.com/projects/git%2Bgithub.com%2FWPSemantix%2Ftimbr_python_http?ref=badge_shield&issueType=license)
 [![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2FWPSemantix%2Ftimbr_python_http.svg?type=shield&issueType=security)](https://app.fossa.com/projects/git%2Bgithub.com%2FWPSemantix%2Ftimbr_python_http?ref=badge_shield&issueType=security)
 
-[![Python 3.9](https://img.shields.io/badge/python-3.9-blue)](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/)
@@ -15,7 +14,7 @@ This project is a pure python connector to timbr (no dependencies required).
 
 ## Dependencies
 - Access to a timbr-server
-- Python from 3.9.13 or newer
+- Python from 3.10 or newer
 
 ## Installation
 - Install as clone repository:

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pytimbr_api"
-version = "2.0.0"
+version = "2.1.0"
 description = "Timbr REST API connector"
 readme = "README.md"
 license = "MIT"
@@ -34,12 +34,11 @@ classifiers = [
   "Intended Audience :: Developers",
   "Topic :: Software Development :: Build Tools",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12"
 ]
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 dependencies = [
   "requests>=2.32.4"
 ]

pytimbr_api/timbr_http_connector.py

@@ -28,7 +28,7 @@ def run_query(
     url: str,
     ontology: str,
     token: str,
-    query: str,
+    query: str | bytes,
     datasource: str = None,
     nested: str = 'false',
     verify_ssl: bool = True,
@@ -66,7 +66,7 @@ def run_query(
     response = requests.post(
       f'{base_url}timbr/openapi/ontology/{ontology}/query{datasource_addition}',
       headers = headers,
-      data = query,
+      data = query.encode('utf-8') if isinstance(query, str) else query,
       verify = verify_ssl,
     )
     return _parse_response(response)

test/conftest.py

@@ -39,4 +39,5 @@ def test_config():
     "jwt_password": os.getenv("JWT_PASSWORD"),
     "jwt_scope": os.getenv("JWT_SCOPE"),
     "jwt_secret": os.getenv("JWT_SECRET"),
+    "timbr_user_password": os.getenv("TIMBR_USER_PASSWORD"),
   }

test/test_encoding.py

@@ -0,0 +1,78 @@
+import pytest
+from pytimbr_api.timbr_http_connector import run_query
+
+
+def test_run_query_with_unicode_characters(test_config):
+    """Test that queries with unicode characters are properly encoded to UTF-8."""
+    url = test_config['url']
+    ontology = test_config['ontology']
+    token = test_config['token']
+
+    # Query with unicode characters - using simple SELECT with unicode strings
+    # This tests that UTF-8 encoding works without requiring specific tables
+    query_with_unicode = "SELECT '测试' as chinese, 'café' as french, '😀' as emoji"
+
+    results = run_query(url, ontology, token, query_with_unicode)
+
+    assert results is not None, "Results should not be None for unicode query"
+    assert len(results) > 0, "Results should contain data"
+    # Verify unicode characters are correctly processed in results
+    first_row = results[0]
+    assert first_row['chinese'] == '测试', "Chinese characters should be preserved"
+    assert first_row['french'] == 'café', "French accented characters should be preserved"
+    assert first_row['emoji'] == '😀', "Emoji should be preserved"
+
+
+def test_run_query_with_already_encoded_bytes(test_config):
+    """Test that queries already encoded as bytes are handled correctly."""
+    url = test_config['url']
+    ontology = test_config['ontology']
+    token = test_config['token']
+
+    # Query already encoded as bytes
+    query_as_bytes = b"SELECT 1"
+
+    results = run_query(url, ontology, token, query_as_bytes)
+
+    assert results is not None, "Results should not be None for bytes query"
+    assert len(results) > 0, "Results should contain data"
+
+
+def test_run_query_with_special_sql_characters(test_config):
+    """Test that queries with special SQL characters are properly encoded."""
+    url = test_config['url']
+    ontology = test_config['ontology']
+    token = test_config['token']
+
+    # Query with special characters that need proper encoding
+    query_with_special_chars = "SELECT 'O''Brien' as name, '©' as copyright"
+
+    results = run_query(url, ontology, token, query_with_special_chars)
+
+    assert results is not None, "Results should not be None for query with special characters"
+    assert len(results) > 0, "Results should contain data"
+    # Verify special characters are correctly processed in results
+    first_row = results[0]
+    assert first_row['name'] == "O'Brien", "Apostrophe in name should be preserved"
+    assert first_row['copyright'] == '©', "Copyright symbol should be preserved"
+
+
+def test_run_query_with_multilingual_text(test_config):
+    """Test that queries with multiple languages are properly encoded."""
+    url = test_config['url']
+    ontology = test_config['ontology']
+    token = test_config['token']
+
+    # Query with multiple languages (Latin, Cyrillic, Arabic, Japanese)
+    query_multilingual = "SELECT 'Hello' as english, 'Привет' as russian, 'مرحبا' as arabic, 'こんにちは' as japanese"
+
+    results = run_query(url, ontology, token, query_multilingual)
+
+    assert results is not None, "Results should not be None for multilingual query"
+    assert len(results) > 0, "Results should contain data"
+    # Verify multilingual characters are correctly processed in results
+    first_row = results[0]
+    assert first_row['english'] == 'Hello', "English text should be preserved"
+    assert first_row['russian'] == 'Привет', "Russian Cyrillic text should be preserved"
+    assert first_row['arabic'] == 'مرحبا', "Arabic text should be preserved"
+    assert first_row['japanese'] == 'こんにちは', "Japanese text should be preserved"

test/test_user_impersonation.py

@@ -4,12 +4,12 @@
 from pytimbr_api.timbr_http_connector import run_query
 import uuid
 
-create_granting_user_stmt = "CREATE USER {username} OPTIONS(email='{username}@timbr-test.ai', password='{password}', first_name='{first_name}', last_name='{last_name}');" \
+create_granting_user_stmt = "CREATE USER {username} PASSWORD '{password}' OPTIONS(email='{username}@timbr-test.ai', first_name='{first_name}', last_name='{last_name}');" \
                    "GRANT QUERY ON ALL DATASOURCE TO USER {username};" \
                    "GRANT ACCESS ON ALL ONTOLOGY TO USER {username};" \
                    "GRANT EDIT ON ALL USER TO USER {username};"
 
-create_impersonating_user_stmt = "CREATE USER {username} OPTIONS(email='{username}@timbr-test.ai', password='{password}', first_name='{first_name}', last_name='{last_name}');" \
+create_impersonating_user_stmt = "CREATE USER {username} PASSWORD '{password}' OPTIONS(email='{username}@timbr-test.ai', first_name='{first_name}', last_name='{last_name}');" \
                    "GRANT ACCESS ON ALL ONTOLOGY TO USER {username};" \
                    "GRANT QUERY ON ALL USER TO USER {username};"
 
@@ -24,13 +24,15 @@
 
 # Generate unique suffix using timestamp and UUID
 unique_suffix = str(uuid.uuid4())[:8]
-granting_user = f"timbr_python_http_granting_user_{unique_suffix}"
-impersonating_user = f"timbr_python_http_impersonating_user_{unique_suffix}"
+# granting_user = f"timbr_granting_{unique_suffix}"
+# impersonating_user = f"timbr_impersonating_{unique_suffix}"
+granting_user = f"timbr_granting"
+impersonating_user = f"timbr_impersonating"
 
 def create_users(test_config):
     print("Creating users...")
-    granting_user_stmt = create_granting_user_stmt.format(username=granting_user, password="SecurePassword123", first_name="Granting", last_name="User")
-    impersonating_user_stmt = create_impersonating_user_stmt.format(username=impersonating_user, password="SecurePassword123", first_name="Impersonating", last_name="User")
+    granting_user_stmt = create_granting_user_stmt.format(username=granting_user, password=test_config['timbr_user_password'], first_name="Granting", last_name="User")
+    impersonating_user_stmt = create_impersonating_user_stmt.format(username=impersonating_user, password=test_config['timbr_user_password'], first_name="Impersonating", last_name="User")
 
     run_query(
         url=test_config['url'],
@@ -120,15 +122,15 @@ def drop_users(test_config):
 def setup_test_users(test_config):
     """Fixture to create users at the start and drop them at the end"""
     # Setup: Create users
-    create_users(test_config)
+    # create_users(test_config)
 
     yield test_config  # This provides the test_config to the test
 
     # Teardown: Drop users (runs even if tests fail)
-    try:
-        drop_users(test_config)
-    except Exception as e:
-        print(f"Warning: Failed to drop users during teardown: {e}")
+    # try:
+        # drop_users(test_config)
+    # except Exception as e:
+        # print(f"Warning: Failed to drop users during teardown: {e}")
 
 class TestUserImpersonation:
     def test_user_impersonation(self, setup_test_users):