12 feature request refactor configuration architecture for better clilibrary separation

CHANGELOG.md

@@ -5,14 +5,38 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.1.12] - 2025-07-21
+
+### Changed
+- **BREAKING CHANGE**: Refactored `Codeanalyzer` constructor to use `AnalysisOptions` dataclass [in response to #12](https://github.com/codellm-devkit/codeanalyzer-python/issues/12)
+  - Replaced multiple individual parameters with single `AnalysisOptions` object for cleaner API
+  - Improved type safety and configuration management through centralized options structure
+  - Enhanced maintainability and extensibility for future configuration additions
+  - Updated CLI integration to create and pass `AnalysisOptions` instance
+  - Maintained backward compatibility in terms of functionality while improving code architecture
+
+### Added
+- New `AnalysisOptions` dataclass in `codeanalyzer.options` module [in response to #12](https://github.com/codellm-devkit/codeanalyzer-python/issues/12)
+  - Centralized configuration structure with all analysis parameters
+  - Type-safe configuration with proper defaults and validation
+  - Support for `OutputFormat` enum integration
+  - Clean separation between CLI and library configuration handling
+
+### Technical Details
+- Added new `codeanalyzer.options` package with `AnalysisOptions` dataclass
+- Updated `Codeanalyzer.__init__()` to accept single `options` parameter instead of 9 individual parameters
+- Modified CLI handler in `__main__.py` to create `AnalysisOptions` instance from command line arguments
+- Improved code organization and maintainability for configuration management
+- Enhanced API design following best practices for parameter object patterns
+
 ## [0.1.11] - 2025-07-21
 
 ### Fixed
 - **CRITICAL**: Fixed NumPy build failure on Python 3.12+ (addresses [#19](https://github.com/codellm-devkit/codeanalyzer-python/issues/19))
   - Updated NumPy dependency constraints to handle Python 3.12+ compatibility
   - Split NumPy version constraints into three tiers:
     - `numpy>=1.21.0,<1.24.0` for Python < 3.11
-    - `numpy>=1.24.0,<2.0.0` for Python 3.11.x  
+    - `numpy>=1.24.0,<2.0.0` for Python 3.11.x
     - `numpy>=1.26.0,<2.0.0` for Python 3.12+ (requires NumPy 1.26+ which supports Python 3.12)
   - Resolves `ModuleNotFoundError: No module named 'distutils'` errors on Python 3.12+
   - Ensures compatibility with Python 3.12 which removed `distutils` from the standard library

codeanalyzer/__main__.py

@@ -7,107 +7,62 @@
 from codeanalyzer.utils import _set_log_level, logger
 from codeanalyzer.config import OutputFormat
 from codeanalyzer.schema import model_dump_json
+from codeanalyzer.options import AnalysisOptions
 
 def main(
-    input: Annotated[
-        Path, typer.Option("-i", "--input", help="Path to the project root directory.")
-    ],
-    output: Annotated[
-        Optional[Path],
-        typer.Option("-o", "--output", help="Output directory for artifacts."),
-    ] = None,
-    format: Annotated[
-        OutputFormat,
-        typer.Option(
-            "-f",
-            "--format",
-            help="Output format: json or msgpack.",
-            case_sensitive=False,
-        ),
-    ] = OutputFormat.JSON,
-    analysis_level: Annotated[
-        int,
-        typer.Option("-a", "--analysis-level", help="1: symbol table, 2: call graph."),
-    ] = 1,
-    using_codeql: Annotated[
-        bool, typer.Option("--codeql/--no-codeql", help="Enable CodeQL-based analysis.")
-    ] = False,
-    using_ray: Annotated[
-        bool,
-        typer.Option(
-            "--ray/--no-ray", help="Enable Ray for distributed analysis."
-        ),
-    ] = False,
-    rebuild_analysis: Annotated[
-        bool,
-        typer.Option(
-            "--eager/--lazy",
-            help="Enable eager or lazy analysis. Defaults to lazy.",
-        ),
-    ] = False,
-    skip_tests: Annotated[
-        bool,
-        typer.Option(
-            "--skip-tests/--include-tests",
-            help="Skip test files in analysis.",
-        ),
-    ] = True,
-    file_name: Annotated[
-        Optional[Path],
-        typer.Option(
-            "--file-name",
-            help="Analyze only the specified file (relative to input directory).",
-        ),
-    ] = None,
-    cache_dir: Annotated[
-        Optional[Path],
-        typer.Option(
-            "-c",
-            "--cache-dir",
-            help="Directory to store analysis cache. Defaults to '.codeanalyzer' in the input directory.",
-        ),
-    ] = None,
-    clear_cache: Annotated[
-        bool,
-        typer.Option("--clear-cache/--keep-cache", help="Clear cache after analysis. By default, cache is retained."),
-    ] = False,
-    verbosity: Annotated[
-        int, typer.Option("-v", count=True, help="Increase verbosity: -v, -vv, -vvv")
-    ] = 0,
+    input: Annotated[Path, typer.Option("-i", "--input", help="Path to the project root directory.")],
+    output: Optional[Path] = typer.Option(None, "-o", "--output"),
+    format: OutputFormat = typer.Option(OutputFormat.JSON, "-f", "--format"),
+    analysis_level: int = typer.Option(1, "-a", "--analysis-level"),
+    using_codeql: bool = typer.Option(False, "--codeql/--no-codeql"),
+    using_ray: bool = typer.Option(False, "--ray/--no-ray"),
+    rebuild_analysis: bool = typer.Option(False, "--eager/--lazy"),
+    skip_tests: bool = typer.Option(True, "--skip-tests/--include-tests"),
+    file_name: Optional[Path] = typer.Option(None, "--file-name"),
+    cache_dir: Optional[Path] = typer.Option(None, "-c", "--cache-dir"),
+    clear_cache: bool = typer.Option(False, "--clear-cache/--keep-cache"),
+    verbosity: int = typer.Option(0, "-v", count=True),
 ):
-    """Static Analysis on Python source code using Jedi, Astroid, and Treesitter."""
-    _set_log_level(verbosity)
+    options = AnalysisOptions(
+        input=input,
+        output=output,
+        format=format,
+        analysis_level=analysis_level,
+        using_codeql=using_codeql,
+        using_ray=using_ray,
+        rebuild_analysis=rebuild_analysis,
+        skip_tests=skip_tests,
+        file_name=file_name,
+        cache_dir=cache_dir,
+        clear_cache=clear_cache,
+        verbosity=verbosity,
+    )
 
-    if not input.exists():
-        logger.error(f"Input path '{input}' does not exist.")
+    _set_log_level(options.verbosity)
+    if not options.input.exists():
+        logger.error(f"Input path '{options.input}' does not exist.")
         raise typer.Exit(code=1)
 
-    # Validate file_name if provided
-    if file_name is not None:
-        full_file_path = input / file_name
+    if options.file_name is not None:
+        full_file_path = options.input / options.file_name
         if not full_file_path.exists():
-            logger.error(f"Specified file '{file_name}' does not exist in '{input}'.")
+            logger.error(f"Specified file '{options.file_name}' does not exist in '{options.input}'.")
             raise typer.Exit(code=1)
         if not full_file_path.is_file():
-            logger.error(f"Specified path '{file_name}' is not a file.")
+            logger.error(f"Specified path '{options.file_name}' is not a file.")
             raise typer.Exit(code=1)
-        if not str(file_name).endswith('.py'):
-            logger.error(f"Specified file '{file_name}' is not a Python file (.py).")
+        if not str(options.file_name).endswith('.py'):
+            logger.error(f"Specified file '{options.file_name}' is not a Python file (.py).")
             raise typer.Exit(code=1)
 
-    with Codeanalyzer(
-        input, analysis_level, skip_tests, using_codeql, rebuild_analysis, cache_dir, clear_cache, using_ray, file_name
-    ) as analyzer:
+    with Codeanalyzer(options) as analyzer:
         artifacts = analyzer.analyze()
 
-        # Handle output based on format
-        if output is None:
-            # Output to stdout (only for JSON)
+        if options.output is None:
             print(model_dump_json(artifacts, separators=(",", ":")))
         else:
-            # Output to file
-            output.mkdir(parents=True, exist_ok=True)
-            _write_output(artifacts, output, format)
+            options.output.mkdir(parents=True, exist_ok=True)
+            _write_output(artifacts, options.output, options.format)
 
 
 def _write_output(artifacts, output_dir: Path, format: OutputFormat):
@@ -130,7 +85,6 @@ def _write_output(artifacts, output_dir: Path, format: OutputFormat):
             f"Compression ratio: {artifacts.get_compression_ratio():.1%} of JSON size"
         )
 
-
 app = typer.Typer(
     callback=main,
     name="codeanalyzer",

codeanalyzer/core.py

@@ -14,6 +14,7 @@
 from codeanalyzer.syntactic_analysis.exceptions import SymbolTableBuilderRayError
 from codeanalyzer.syntactic_analysis.symbol_table_builder import SymbolTableBuilder
 from codeanalyzer.utils import ProgressBar
+from codeanalyzer.options import AnalysisOptions
 
 @ray.remote
 def _process_file_with_ray(py_file: Union[Path, str], project_dir: Union[Path, str], virtualenv: Union[Path, str, None]) -> Dict[str, PyModule]:
@@ -43,40 +44,25 @@ class Codeanalyzer:
     """Core functionality for CodeQL analysis.
 
     Args:
-        project_dir (Union[str, Path]): The root directory of the project to analyze.
-        virtualenv (Optional[Path]): Path to the virtual environment directory.
-        using_codeql (bool): Whether to use CodeQL for analysis.
-        rebuild_analysis (bool): Whether to force rebuild the database.
-        clear_cache (bool): Whether to delete the cached directory after analysis.
-        analysis_depth (int): Depth of analysis (reserved for future use).
+        options (AnalysisOptions): Analysis configuration options containing all necessary parameters.
     """
 
-    def __init__(
-        self,
-        project_dir: Union[str, Path],
-        analysis_depth: int,
-        skip_tests: bool,
-        using_codeql: bool,
-        rebuild_analysis: bool,
-        cache_dir: Optional[Path],
-        clear_cache: bool,
-        using_ray: bool,
-        file_name: Optional[Path] = None,
-    ) -> None:
-        self.analysis_depth = analysis_depth
-        self.project_dir = Path(project_dir).resolve()
-        self.skip_tests = skip_tests
-        self.using_codeql = using_codeql
-        self.rebuild_analysis = rebuild_analysis
+    def __init__(self, options: AnalysisOptions) -> None:
+        self.options = options
+        self.analysis_depth = options.analysis_level
+        self.project_dir = Path(options.input).resolve()
+        self.skip_tests = options.skip_tests
+        self.using_codeql = options.using_codeql
+        self.rebuild_analysis = options.rebuild_analysis
         self.cache_dir = (
-            cache_dir.resolve() if cache_dir is not None else self.project_dir
+            options.cache_dir.resolve() if options.cache_dir is not None else self.project_dir
         ) / ".codeanalyzer"
-        self.clear_cache = clear_cache
+        self.clear_cache = options.clear_cache
         self.db_path: Optional[Path] = None
         self.codeql_bin: Optional[Path] = None
         self.virtualenv: Optional[Path] = None
-        self.using_ray: bool = using_ray
-        self.file_name: Optional[Path] = file_name
+        self.using_ray: bool = options.using_ray
+        self.file_name: Optional[Path] = options.file_name
 
     @staticmethod
     def _cmd_exec_helper(

codeanalyzer/options/__init__.py

@@ -0,0 +1,3 @@
+from .options import AnalysisOptions
+
+__all__ = ["AnalysisOptions"]

codeanalyzer/options/options.py

@@ -0,0 +1,25 @@
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional
+from enum import Enum
+
+
+class OutputFormat(str, Enum):
+    JSON = "json"
+    MSGPACK = "msgpack"
+
+
+@dataclass
+class AnalysisOptions:
+    input: Path
+    output: Optional[Path] = None
+    format: OutputFormat = OutputFormat.JSON
+    analysis_level: int = 1
+    using_codeql: bool = False
+    using_ray: bool = False
+    rebuild_analysis: bool = False
+    skip_tests: bool = True
+    file_name: Optional[Path] = None
+    cache_dir: Optional[Path] = None
+    clear_cache: bool = False
+    verbosity: int = 0

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "codeanalyzer-python"
-version = "0.1.11"
+version = "0.1.12"
 description = "Static Analysis on Python source code using Jedi, CodeQL and Treesitter."
 readme = "README.md"
 authors = [