rust-crate-pipeline 1.4.0__py3-none-any.whl → 1.4.2__py3-none-any.whl

rust_crate_pipeline/utils/logging_utils.py

@@ -4,11 +4,12 @@ import time
 import psutil
 import logging
 from functools import wraps
-from typing import Optional
+from typing import Any, Callable, Dict, Optional, Union
 
 
-def configure_logging(log_dir: Optional[str] = None,
-                      log_level: int = logging.INFO) -> logging.Logger:
+def configure_logging(
+    log_dir: Optional[str] = None, log_level: int = logging.INFO
+) -> logging.Logger:
     """
     Configure global logging with file and console handlers
 
@@ -25,54 +26,58 @@ def configure_logging(log_dir: Optional[str] = None,
     # Console handler
     console_handler = logging.StreamHandler()
     console_handler.setLevel(log_level)
-    console_format = logging.Formatter(
-        "%(asctime)s [%(levelname)s] %(message)s")
+    console_format = logging.Formatter("%(asctime)s [%(levelname)s] %(message)s")
     console_handler.setFormatter(console_format)
     logger.addHandler(console_handler)
 
     # File handler
     if log_dir:
         log_file = os.path.join(
-            log_dir, f"pipeline_{
-                time.strftime('%Y%m%d-%H%M%S')}.log")
+            log_dir,
+            f"pipeline_{
+                time.strftime('%Y%m%d-%H%M%S')}.log",
+        )
         file_handler = logging.FileHandler(log_file)
         file_handler.setLevel(log_level)
         file_format = logging.Formatter(
-            "%(asctime)s [%(levelname)s] %(name)s: %(message)s")
+            "%(asctime)s [%(levelname)s] %(name)s: %(message)s"
+        )
         file_handler.setFormatter(file_format)
         logger.addHandler(file_handler)
 
     return logger
 
 
-def log_execution_time(func):
+def log_execution_time(func: Callable[..., Any]) -> Callable[..., Any]:
     """Decorator to log function execution time"""
+
     @wraps(func)
-    def wrapper(*args, **kwargs):
+    def wrapper(*args, **kwargs) -> None:
         start_time = time.time()
         result = func(*args, **kwargs)
         end_time = time.time()
-        logging.info(
-            f"{func.__name__} executed in {end_time - start_time:.2f} seconds")
+        logging.info(f"{func.__name__} executed in {end_time - start_time:.2f} seconds")
         return result
+
     return wrapper
 
 
-def log_resource_usage():
+def log_resource_usage() -> Dict[str, Any]:
     """Log current resource utilization (CPU, memory, disk)"""
     cpu_percent = psutil.cpu_percent()
     mem = psutil.virtual_memory()
-    disk = psutil.disk_usage('.')
+    disk = psutil.disk_usage(".")
 
     logging.info(
         f"Resource Usage - CPU: {cpu_percent}%, Memory: {
             mem.percent}%, Disk: {
-            disk.percent}%")
+            disk.percent}%"
+    )
 
     return {
         "cpu_percent": cpu_percent,
         "memory_percent": mem.percent,
         "disk_percent": disk.percent,
         "memory_available": mem.available,
-        "disk_free": disk.free
+        "disk_free": disk.free,
     }

rust_crate_pipeline/version.py

@@ -1,47 +1,79 @@
-"""Version information for rust-crate-pipeline."""
-
-__version__ = "1.4.0"
-__version_info__ = tuple(int(x) for x in __version__.split("."))
-
-# Version history
-# 1.4.0 - Major Release: Rule Zero Compliance Audit Complete
-#         - Completed comprehensive Rule Zero alignment audit
-#         - Eliminated all code redundancy and dead code
-#         - Achieved 100% test coverage (22/22 tests passing)
-#         - Refactored to pure asyncio architecture (thread-free)
-#         - Suppressed Pydantic deprecation warnings
-#         - Full production readiness with Docker support
-#         - Enhanced documentation with PyPI cross-references
-#         - Certified Rule Zero compliance across all four principles
-# 1.3.1 - Bug Fix Release: Crawl4AI Integration Cleanup
-#         - Fixed CSS selector syntax errors in Crawl4AI integration
-#         - Cleaned up duplicate and obsolete test files
-#         - Resolved import conflicts between workspace and integration configs
-#         - Improved error handling in enhanced scraping module
-#         - Standardized on direct llama.cpp approach (removed Ollama dependencies)
-#         - Enhanced Rule Zero compliance with transparent cleanup process
-# 1.3.0 - Quality & Integration Release: Comprehensive code quality improvements
-#         - Fixed all critical PEP 8 violations (F821, F811, E114)
-#         - Enhanced error handling with graceful dependency fallbacks
-#         - Improved module integration and import path resolution
-#         - Added comprehensive test validation (21/21 tests passing)
-#         - Enhanced async support and Unicode handling
-#         - Production-ready CLI interfaces with robust error handling
-#         - Full Rule Zero compliance validation
-# 1.2.0 - Major release: Production-ready, cleaned codebase
-#         - Unified documentation into single comprehensive README
-#         - Removed all non-essential development and test files
-#         - Optimized for PyPI distribution and Docker deployment
-#         - Enhanced GitHub token integration and setup
-# 1.1.2 - Production release: Cleaned up non-essential files
-#         - Unified documentation into single README
-#         - Optimized for PyPI distribution
-# 1.1.1 - Bug fix: Added missing python-dateutil dependency
-#         - Fixed relativedelta import error
-# 1.1.0 - Updated author and contact information
-#         - Enhanced package configuration
-# 0.1.0 - Initial release
-#         - Core pipeline functionality
-#         - AI-powered metadata enrichment
-#         - Dependency analysis
-#         - PyPI package setup
+from typing import Dict, List, Tuple, Optional, Any
+"""Version information for rust-crate-pipeline."""
+
+__version__ = "1.4.2"
+__version_info__ = tuple(int(x) for x in __version__.split("-")[0].split("."))
+__author__ = "SigilDERG Team"
+__email__ = "sigilderg@example.com"
+
+# Version history
+# 1.4.2 - Maintenance Release
+#         - Updated project to version 1.4.2
+#         - General maintenance and dependency updates
+# 1.2.5-dev.20250621 - Dev branch: experimental, not a formal
+# release. Originated from v1.2.5.
+# 1.2.5 - Last official release.
+# 1.5.1 - Configuration Standardization Release: Model Path Consistency
+#         - Standardized all configuration to use GGUF model paths
+#         - Updated CLI defaults for --crawl4ai-model to
+#           ~/models/deepseek/deepseek-coder-6.7b-instruct.Q4_K_M.gguf
+#         - Enhanced Rule Zero alignment with transparent configuration practices
+#         - Updated all test files to use consistent GGUF model path references
+#         - Comprehensive documentation updates for proper model configuration
+#         - Removed inconsistent Ollama references in favor of llama-cpp-python
+#         - Ensured CLI help text and JSON examples reflect correct model paths
+# 1.5.0 - Major Release: Enhanced Web Scraping with Crawl4AI Integration
+#         - Integrated Crawl4AI for advanced web scraping capabilities
+#         - Added JavaScript-rendered content extraction via Playwright
+#         - Enhanced README parsing with LLM-powered content analysis
+#         - New CLI options: --enable-crawl4ai, --disable-crawl4ai, --crawl4ai-model
+#         - Enhanced configuration with local GGUF model paths and crawl4ai_timeout
+#         - Comprehensive test coverage for all Crawl4AI features
+#         - Rule Zero compliant with full transparency and audit trails
+# 1.4.0 - Major Release: Rule Zero Compliance Audit Complete
+#         - Completed comprehensive Rule Zero alignment audit
+#         - Eliminated all code redundancy and dead code
+#         - Achieved 100% test coverage (22/22 tests passing)
+#         - Refactored to pure asyncio architecture (thread-free)
+#         - Suppressed Pydantic deprecation warnings
+#         - Full production readiness with Docker support
+#         - Enhanced documentation with PyPI cross-references
+#         - Certified Rule Zero compliance across all four principles
+# 1.3.1 - Bug Fix Release: Crawl4AI Integration Cleanup
+#         - Fixed CSS selector syntax errors in Crawl4AI integration
+#         - Cleaned up duplicate and obsolete test files
+#         - Resolved import conflicts between workspace and integration configs
+#         - Improved error handling in enhanced scraping module
+#         - Standardized on direct llama.cpp approach (removed Ollama dependencies)
+#         - Enhanced Rule Zero compliance with transparent cleanup process
+#         - Fixed type annotation compatibility issues
+#         - Fixed Python 3.9 compatibility for type annotations
+#         - Updated dict[str, Any] to "dict[str, Any]" format
+#         - Fixed Union type expressions in conditional imports
+#         - Resolved IDE linter errors in network.py, pipeline.py, and production_config.py
+#         - Improved code quality and maintainability
+# 1.3.0 - Quality & Integration Release: Comprehensive code quality improvements
+#         - Fixed all critical PEP 8 violations (F821, F811, E114)
+#         - Enhanced error handling with graceful dependency fallbacks
+#         - Improved module integration and import path resolution
+#         - Added comprehensive test validation (21/21 tests passing)
+#         - Enhanced async support and Unicode handling
+#         - Production-ready CLI interfaces with robust error handling
+#         - Full Rule Zero compliance validation
+# 1.2.0 - Major release: Production-ready, cleaned codebase
+#         - Unified documentation into single comprehensive README
+#         - Removed all non-essential development and test files
+#         - Optimized for PyPI distribution and Docker deployment
+#         - Enhanced GitHub token integration and setup
+# 1.1.2 - Production release: Cleaned up non-essential files
+#         - Unified documentation into single README
+#         - Optimized for PyPI distribution
+# 1.1.1 - Bug fix: Added missing python-dateutil dependency
+#         - Fixed relativedelta import error
+# 1.1.0 - Updated author and contact information
+#         - Enhanced package configuration
+# 0.1.0 - Initial release
+#         - Core pipeline functionality
+#         - AI-powered metadata enrichment
+#         - Dependency analysis
+#         - PyPI package setup