redup 0.4.4__tar.gz → 0.4.6__tar.gz

{redup-0.4.4 → redup-0.4.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.4.4
+Version: 0.4.6
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0
@@ -27,6 +27,7 @@ Requires-Dist: typer>=0.12.0
 Requires-Dist: rich>=13.0
 Requires-Dist: pydantic>=2.0
 Requires-Dist: tomli>=2.0; python_version < "3.11"
+Requires-Dist: python-dotenv>=1.0
 Provides-Extra: all
 Requires-Dist: redup[fast]; extra == "all"
 Requires-Dist: redup[fuzzy]; extra == "all"
@@ -92,7 +93,7 @@ Dynamic: license-file
 [![PyPI](https://img.shields.io/pypi/v/redup)](https://pypi.org/project/redup/)
 [![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
-[![Version](https://img.shields.io/badge/version-0.4.4-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.4.6-green.svg)](https://pypi.org/project/redup/)
 
 reDUP scans codebases for duplicated functions, blocks, and structural patterns — then builds a prioritized refactoring map that LLMs can consume to eliminate redundancy systematically.
 

{redup-0.4.4 → redup-0.4.6}/README.md

@@ -5,7 +5,7 @@
 [![PyPI](https://img.shields.io/pypi/v/redup)](https://pypi.org/project/redup/)
 [![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
-[![Version](https://img.shields.io/badge/version-0.4.4-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.4.6-green.svg)](https://pypi.org/project/redup/)
 
 reDUP scans codebases for duplicated functions, blocks, and structural patterns — then builds a prioritized refactoring map that LLMs can consume to eliminate redundancy systematically.
 

{redup-0.4.4 → redup-0.4.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "redup"
-version = "0.4.4"
+version = "0.4.6"
 description = "Code duplication analyzer and refactoring planner for LLMs"
 readme = "README.md"
 license = "Apache-2.0"
@@ -31,6 +31,7 @@ dependencies = [
     "rich>=13.0",
     "pydantic>=2.0",
     "tomli>=2.0; python_version<'3.11'",
+    "python-dotenv>=1.0",
 ]
 
 [project.optional-dependencies]

{redup-0.4.4 → redup-0.4.6}/src/redup/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.4.4"
+__version__ = "0.4.6"
 
 from redup.core.models import (
     DuplicateFragment,

{redup-0.4.4 → redup-0.4.6}/src/redup/cli_app/main.py

@@ -13,6 +13,7 @@ import typer
 warnings.filterwarnings("ignore", category=SyntaxWarning)
 
 import redup  # noqa: E402
+from redup.config import config as global_config, reload_config  # noqa: E402
 from redup.core.config import create_sample_redup_toml, load_config  # noqa: E402
 from redup.core.models import DuplicationMap, ScanConfig  # noqa: E402
 
@@ -35,7 +36,8 @@ OutputFormat = Literal["json", "yaml", "toon", "markdown", "all", "enhanced", "c
 
 
 DEFAULT_PATH = Path(".")
-DEFAULT_FORMAT: OutputFormat = "toon"
+# Use centralized config for defaults
+DEFAULT_FORMAT: OutputFormat = global_config.DEFAULT_FORMAT  # type: ignore
 DEFAULT_OUTPUT: Path | None = None
 
 
@@ -78,14 +80,15 @@ def scan(
         "--include-tests",
         help="Include test files. Overrides config.",
     ),
-    functions_only: bool = typer.Option(
-        True,
-        "--functions-only/--no-functions-only",
-        help="Only analyze function-level duplicates (default: enabled for speed).",
+    no_functions_only: bool = typer.Option(
+        False,
+        "--no-functions-only",
+        help="Analyze all code, not just functions (default: functions-only for speed).",
     ),
     parallel: bool = typer.Option(
         False,
-        "--parallel/--no-parallel",
+        "--parallel",
+        "--no-parallel",
         help="Use parallel scanning for large projects (default: disabled due to issues).",
     ),
     max_workers: int | None = typer.Option(
@@ -98,10 +101,10 @@ def scan(
         "--incremental",
         help="Use incremental scanning with caching.",
     ),
-    memory_cache: bool = typer.Option(
-        True,
-        "--memory-cache/--no-memory-cache",
-        help="Use memory cache for faster scanning.",
+    no_memory_cache: bool = typer.Option(
+        False,
+        "--no-memory-cache",
+        help="Disable memory cache for scanning.",
     ),
     max_cache_mb: int = typer.Option(
         512,
@@ -122,8 +125,8 @@ def scan(
     """Scan a project for code duplicates."""
     return scan_command(
         path, format, output, extensions, min_lines, min_similarity,
-        include_tests, functions_only, parallel, max_workers,
-        incremental, memory_cache, max_cache_mb, fuzzy, fuzzy_threshold
+        include_tests, not no_functions_only, parallel, max_workers,
+        incremental, not no_memory_cache, max_cache_mb, fuzzy, fuzzy_threshold
     )
 
 

{redup-0.4.4 → redup-0.4.6}/src/redup/cli_app/output_writer.py

@@ -3,6 +3,7 @@
 from pathlib import Path
 from typing import Any
 
+from redup.config import config, get_default_filename
 from redup.core.models import DuplicationMap
 from redup.reporters.json_reporter import to_json
 from redup.reporters.markdown_reporter import to_markdown
@@ -15,9 +16,9 @@ from redup.reporters.enhanced_reporter import EnhancedReporter
 def write_output(content: str, output: Path | None, suffix: str) -> None:
     """Write content to file or stdout."""
     import typer
-    
+
     if output:
-        target = output if output.suffix else output / f"duplication.{suffix}"
+        target = output if output.suffix else output / get_default_filename(suffix)
         target.parent.mkdir(parents=True, exist_ok=True)
         target.write_text(content, encoding="utf-8")
         typer.echo(f"  → {target}")
@@ -70,7 +71,7 @@ def write_results(dup_map: DuplicationMap, format: str, output: Any, path: Path)
             base_dir = path
         
         for fmt, content in formats.items():
-            target = base_dir / f"duplication.{fmt}"
+            target = base_dir / get_default_filename(fmt)
             target.write_text(content, encoding="utf-8")
             typer.echo(f"  → {target}")
     else:

{redup-0.4.4 → redup-0.4.6}/src/redup/cli_app/scan_commands.py

@@ -21,11 +21,11 @@ def scan_command(
     min_lines: Any = typer.Option(None, "--min-lines", help="Minimum block size (lines). Overrides config."),
     min_similarity: Any = typer.Option(None, "--min-sim", help="Minimum similarity score (0.0-1.0). Overrides config."),
     include_tests: bool = typer.Option(False, "--include-tests", help="Include test files in analysis."),
-    functions_only: bool = typer.Option(True, "--functions-only/--no-functions-only", help="Only analyze function-level duplicates (default: enabled for speed)."),
+    functions_only: bool = typer.Option(True, "--functions-only", help="Only analyze function-level duplicates (default: enabled for speed)."),
     parallel: bool = typer.Option(False, "--parallel", help="Use parallel processing for faster analysis."),
     max_workers: Any = typer.Option(None, "--max-workers", help="Maximum number of parallel workers."),
     incremental: bool = typer.Option(False, "--incremental", help="Use incremental scanning (cache-based)."),
-    memory_cache: bool = typer.Option(True, "--memory-cache/--no-memory-cache", help="Use memory cache for faster processing."),
+    memory_cache: bool = typer.Option(True, "--memory-cache", help="Use memory cache for faster processing."),
     max_cache_mb: int = typer.Option(512, "--max-cache-mb", help="Maximum memory cache size in MB."),
     fuzzy: bool = typer.Option(False, "--fuzzy", help="Enable fuzzy similarity detection."),
     fuzzy_threshold: float = typer.Option(0.8, "--fuzzy-threshold", help="Fuzzy similarity threshold (0.0-1.0)."),

redup-0.4.6/src/redup/config.py

@@ -0,0 +1,172 @@
+"""Centralized configuration for reDUP with .env file support.
+
+This module provides global configuration settings that can be customized via:
+1. Environment variables (REDUP_* prefix)
+2. .env files in the project directory
+3. redup.toml configuration file
+4. Programmatic overrides
+
+Example .env file:
+    REDUP_DEFAULT_OUTPUT_FILENAME=duplication.toon.yaml
+    REDUP_DEFAULT_FORMAT=toon
+    REDUP_MIN_LINES=5
+"""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+from typing import Any
+
+# Try to load .env file if python-dotenv is available
+try:
+    from dotenv import load_dotenv
+
+    # Load .env from current working directory if it exists
+    _env_path = Path.cwd() / ".env"
+    if _env_path.exists():
+        load_dotenv(_env_path, override=True)
+except ImportError:
+    load_dotenv = None  # type: ignore
+
+
+class RedupConfig:
+    """Global configuration container for reDUP settings.
+
+    Attributes can be set via:
+    - Environment variables (REDUP_* prefix, e.g., REDUP_DEFAULT_OUTPUT_FILENAME)
+    - .env files in the project directory (loaded automatically)
+    - Direct attribute assignment (e.g., config.DEFAULT_OUTPUT_FILENAME = "...")
+    """
+
+    # Output settings
+    DEFAULT_OUTPUT_FILENAME: str = "duplication.toon.yaml"
+    DEFAULT_FORMAT: str = "toon"
+    DEFAULT_OUTPUT_DIR: str = "."
+
+    # Scan settings
+    DEFAULT_MIN_LINES: int = 3
+    DEFAULT_MIN_SIMILARITY: float = 0.85
+    DEFAULT_EXTENSIONS: str = ".py"
+    DEFAULT_INCLUDE_TESTS: bool = False
+
+    # Performance settings
+    DEFAULT_PARALLEL: bool = False
+    DEFAULT_MAX_WORKERS: int | None = None
+    DEFAULT_INCREMENTAL: bool = False
+    DEFAULT_MEMORY_CACHE: bool = True
+    DEFAULT_MAX_CACHE_MB: int = 512
+
+    # Fuzzy settings
+    DEFAULT_FUZZY: bool = False
+    DEFAULT_FUZZY_THRESHOLD: float = 0.8
+
+    # LSH settings
+    DEFAULT_LSH_ENABLED: bool = True
+    DEFAULT_LSH_MIN_LINES: int = 50
+    DEFAULT_LSH_THRESHOLD: float = 0.8
+
+    # Cache settings
+    DEFAULT_CACHE_DIR: str = ".redup/cache"
+
+    @classmethod
+    def _env_name(cls, attr_name: str) -> str:
+        """Convert attribute name to environment variable name."""
+        return f"REDUP_{attr_name}"
+
+    @classmethod
+    def _load_from_env(cls) -> dict[str, Any]:
+        """Load configuration from environment variables."""
+        config = {}
+        for attr_name in dir(cls):
+            if attr_name.startswith("DEFAULT_"):
+                env_name = cls._env_name(attr_name)
+                value = os.getenv(env_name)
+                if value is not None:
+                    # Convert to appropriate type based on default
+                    default_value = getattr(cls, attr_name)
+                    if isinstance(default_value, bool):
+                        config[attr_name] = value.lower() in ("true", "1", "yes", "on")
+                    elif isinstance(default_value, int):
+                        try:
+                            config[attr_name] = int(value)
+                        except ValueError:
+                            pass
+                    elif isinstance(default_value, float):
+                        try:
+                            config[attr_name] = float(value)
+                        except ValueError:
+                            pass
+                    else:
+                        config[attr_name] = value
+        return config
+
+    @classmethod
+    def reload(cls, env_path: Path | None = None) -> None:
+        """Reload configuration from .env file and environment variables.
+
+        Args:
+            env_path: Optional path to .env file. If None, looks for .env in current directory.
+        """
+        # Load from .env file if specified or found
+        if load_dotenv is not None:
+            if env_path is not None:
+                if env_path.exists():
+                    load_dotenv(env_path, override=True)
+            else:
+                cwd_env = Path.cwd() / ".env"
+                if cwd_env.exists():
+                    load_dotenv(cwd_env, override=True)
+
+        # Update class attributes from environment variables
+        for attr_name, value in cls._load_from_env().items():
+            setattr(cls, attr_name, value)
+
+    @classmethod
+    def get(cls, attr_name: str, default: Any = None) -> Any:
+        """Get configuration value by name."""
+        if hasattr(cls, attr_name):
+            return getattr(cls, attr_name)
+        return default
+
+    @classmethod
+    def set(cls, attr_name: str, value: Any) -> None:
+        """Set configuration value by name."""
+        if hasattr(cls, attr_name):
+            setattr(cls, attr_name, value)
+        else:
+            raise AttributeError(f"No such config attribute: {attr_name}")
+
+
+# Global config instance
+config = RedupConfig()
+
+# Load initial configuration from .env if present
+config.reload()
+
+
+def get_default_filename(suffix: str | None = None) -> str:
+    """Get default output filename.
+
+    Args:
+        suffix: Optional file suffix. If None, uses the suffix from DEFAULT_OUTPUT_FILENAME.
+
+    Returns:
+        Default filename string.
+    """
+    if suffix is None:
+        return config.DEFAULT_OUTPUT_FILENAME
+    # If suffix is provided, construct filename from base + suffix
+    base = config.DEFAULT_OUTPUT_FILENAME.rsplit(".", 1)[0]
+    return f"{base}.{suffix}"
+
+
+def reload_config(env_path: Path | None = None) -> None:
+    """Reload configuration from .env file.
+
+    This function can be called to reload settings when .env file changes.
+
+    Args:
+        env_path: Optional path to .env file. If None, looks for .env in current directory.
+    """
+    config.reload(env_path)

{redup-0.4.4 → redup-0.4.6}/src/redup/core/config.py

@@ -14,6 +14,7 @@ except ImportError:
     except ImportError:
         tomllib = None
 
+from redup.config import config as global_config, reload_config
 from redup.core.models import ScanConfig
 
 
@@ -50,11 +51,20 @@ def load_config() -> dict[str, Any]:
     
     Priority order:
     1. Environment variables (REDUP_*)
-    2. redup.toml in current directory
-    3. [tool.redup] in pyproject.toml
-    4. Defaults
+    2. .env file in current directory (auto-loaded via redup.config)
+    3. redup.toml in current directory
+    4. [tool.redup] in pyproject.toml
+    5. Global config defaults (redup.config)
     """
-    config = {}
+    # Start with global config defaults (already includes .env if present)
+    config = {
+        "extensions": global_config.DEFAULT_EXTENSIONS,
+        "min_lines": global_config.DEFAULT_MIN_LINES,
+        "min_similarity": global_config.DEFAULT_MIN_SIMILARITY,
+        "include_tests": global_config.DEFAULT_INCLUDE_TESTS,
+        "output": global_config.DEFAULT_OUTPUT_DIR,
+        "format": global_config.DEFAULT_FORMAT,
+    }
     
     # Load from redup.toml
     config.update(_get_config_from_redup_toml())
@@ -116,6 +126,11 @@ def create_sample_redup_toml() -> str:
     """Create a sample redup.toml configuration file content."""
     return """# reDUP Configuration File
 # See https://github.com/semcod/redup for documentation
+#
+# You can also use a .env file in your project directory:
+#   REDUP_DEFAULT_OUTPUT_FILENAME=my_duplication.yaml
+#   REDUP_DEFAULT_FORMAT=toon
+#   REDUP_MIN_LINES=5
 
 [scan]
 # File extensions to scan (comma-separated)
@@ -143,6 +158,8 @@ max_lines = 100
 [output]
 # Default output format
 format = "toon"
+# Default output filename (can include suffix)
+filename = "duplication.toon.yaml"
 # Default output directory (relative to project root)
 output = "redup_output"
 

{redup-0.4.4 → redup-0.4.6}/src/redup.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.4.4
+Version: 0.4.6
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0
@@ -27,6 +27,7 @@ Requires-Dist: typer>=0.12.0
 Requires-Dist: rich>=13.0
 Requires-Dist: pydantic>=2.0
 Requires-Dist: tomli>=2.0; python_version < "3.11"
+Requires-Dist: python-dotenv>=1.0
 Provides-Extra: all
 Requires-Dist: redup[fast]; extra == "all"
 Requires-Dist: redup[fuzzy]; extra == "all"
@@ -92,7 +93,7 @@ Dynamic: license-file
 [![PyPI](https://img.shields.io/pypi/v/redup)](https://pypi.org/project/redup/)
 [![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](https://python.org)
-[![Version](https://img.shields.io/badge/version-0.4.4-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.4.6-green.svg)](https://pypi.org/project/redup/)
 
 reDUP scans codebases for duplicated functions, blocks, and structural patterns — then builds a prioritized refactoring map that LLMs can consume to eliminate redundancy systematically.
 

{redup-0.4.4 → redup-0.4.6}/src/redup.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ README.md
 pyproject.toml
 src/redup/__init__.py
 src/redup/__main__.py
+src/redup/config.py
 src/redup/mcp_server.py
 src/redup.egg-info/PKG-INFO
 src/redup.egg-info/SOURCES.txt

{redup-0.4.4 → redup-0.4.6}/src/redup.egg-info/requires.txt

@@ -2,6 +2,7 @@ pyyaml>=6.0
 typer>=0.12.0
 rich>=13.0
 pydantic>=2.0
+python-dotenv>=1.0
 
 [:python_version < "3.11"]
 tomli>=2.0

{redup-0.4.4 → redup-0.4.6}/tests/test_e2e.py

@@ -139,7 +139,7 @@ class TestCLIScanToon:
             "scan", str(project_with_duplicates), "-f", "toon", "-o", str(out)
         ])
         assert result.exit_code == 0
-        toon_file = out / "duplication.toon"
+        toon_file = out / "duplication.toon.yaml"
         assert toon_file.exists()
         content = toon_file.read_text()
         assert "DUPLICATES" in content
@@ -239,7 +239,7 @@ class TestCLIScanAll:
         assert result.exit_code == 0
         assert (out / "duplication.json").exists()
         assert (out / "duplication.yaml").exists()
-        assert (out / "duplication.toon").exists()
+        assert (out / "duplication.toon.yaml").exists()
 
     def test_format_all_json_valid(self, project_with_duplicates: Path, tmp_path: Path):
         out = tmp_path / "output"
@@ -256,7 +256,7 @@ class TestCLIScanAll:
             "scan", str(project_with_duplicates), "-f", "all",
             "-o", str(out), "--functions-only"
         ])
-        toon = (out / "duplication.toon").read_text()
+        toon = (out / "duplication.toon.yaml").read_text()
         assert "REFACTOR" in toon
 
     def test_all_three_formats_consistent(self, project_with_duplicates: Path, tmp_path: Path):
@@ -267,7 +267,7 @@ class TestCLIScanAll:
             "-o", str(out), "--functions-only"
         ])
         json_data = json.loads((out / "duplication.json").read_text())
-        toon_text = (out / "duplication.toon").read_text()
+        toon_text = (out / "duplication.toon.yaml").read_text()
         yaml_text = (out / "duplication.yaml").read_text()
 
         json_groups = json_data["summary"]["total_groups"]
@@ -423,7 +423,7 @@ class TestFullRoundtrip:
         # All files created
         assert (out / "duplication.json").exists()
         assert (out / "duplication.yaml").exists()
-        assert (out / "duplication.toon").exists()
+        assert (out / "duplication.toon.yaml").exists()
 
         # JSON parseable
         json_data = json.loads((out / "duplication.json").read_text())
@@ -431,7 +431,7 @@ class TestFullRoundtrip:
         json_saved = json_data["summary"]["total_saved_lines"]
 
         # TOON mentions same numbers
-        toon = (out / "duplication.toon").read_text()
+        toon = (out / "duplication.toon.yaml").read_text()
         assert f"dup_groups:    {json_groups}" in toon
         assert f"saved_lines:   {json_saved}" in toon