redup 0.3.8__tar.gz → 0.3.10__tar.gz

{redup-0.3.8 → redup-0.3.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.3.8
+Version: 0.3.10
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0
@@ -83,7 +83,7 @@ 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-0.3.8-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.3.10-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-0.3.8 → redup-0.3.10}/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-0.3.8-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.3.10-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-0.3.8 → redup-0.3.10}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "redup"
-version = "0.3.8"
+version = "0.3.10"
 description = "Code duplication analyzer and refactoring planner for LLMs"
 readme = "README.md"
 license = "Apache-2.0"

{redup-0.3.8 → redup-0.3.10}/src/redup/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.3.8"
+__version__ = "0.3.10"
 
 from redup.core.models import (
     DuplicateFragment,

{redup-0.3.8 → redup-0.3.10}/src/redup/cli_app/main.py

@@ -226,6 +226,11 @@ def scan(
         "--max-workers",
         help="Number of parallel workers (default: CPU count).",
     ),
+    incremental: bool = typer.Option(
+        False,
+        "--incremental",
+        help="Use hash cache to skip unchanged files (creates .redup_cache.json).",
+    ),
 ) -> None:
     """Scan a project for code duplicates and generate a refactoring map."""
     config = _build_config_with_file_support(path, extensions, min_lines, min_similarity, include_tests)

redup-0.3.10/src/redup/core/hash_cache.py

@@ -0,0 +1,104 @@
+"""Hash cache for incremental reDUP scans.
+
+Stores SHA-256 hashes of files to skip unchanged files in subsequent scans.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+from pathlib import Path
+from typing import Any
+
+
+class HashCache:
+    """Cache for file hashes to enable incremental scanning."""
+    
+    def __init__(self, cache_path: Path | None = None):
+        if cache_path is None:
+            cache_path = Path(".redup_cache.json")
+        self.cache_path = cache_path
+        self._cache: dict[str, dict[str, Any]] = {}
+        self._load()
+    
+    def _load(self) -> None:
+        """Load cache from disk."""
+        if self.cache_path.exists():
+            try:
+                with open(self.cache_path, 'r', encoding='utf-8') as f:
+                    self._cache = json.load(f)
+            except (json.JSONDecodeError, IOError):
+                self._cache = {}
+    
+    def save(self) -> None:
+        """Save cache to disk."""
+        try:
+            with open(self.cache_path, 'w', encoding='utf-8') as f:
+                json.dump(self._cache, f, indent=2)
+        except IOError:
+            pass  # Cache save is best-effort
+    
+    def get_file_hash(self, file_path: Path) -> str:
+        """Calculate hash of file content."""
+        try:
+            with open(file_path, 'rb') as f:
+                return hashlib.sha256(f.read()).hexdigest()[:16]
+        except (IOError, OSError):
+            return ""
+    
+    def is_unchanged(self, file_path: Path, config_hash: str = "") -> bool:
+        """Check if file is unchanged since last scan."""
+        path_str = str(file_path)
+        
+        if path_str not in self._cache:
+            return False
+        
+        entry = self._cache[path_str]
+        current_hash = self.get_file_hash(file_path)
+        
+        # Check content hash and config
+        return (
+            entry.get("content_hash") == current_hash and
+            entry.get("config_hash") == config_hash
+        )
+    
+    def update(self, file_path: Path, file_results: dict[str, Any], config_hash: str = "") -> None:
+        """Update cache entry for a file."""
+        path_str = str(file_path)
+        content_hash = self.get_file_hash(file_path)
+        
+        self._cache[path_str] = {
+            "content_hash": content_hash,
+            "config_hash": config_hash,
+            "mtime": file_path.stat().st_mtime if file_path.exists() else 0,
+            "results": file_results,
+        }
+    
+    def invalidate(self, file_path: Path | None = None) -> None:
+        """Invalidate cache for a file or entire cache."""
+        if file_path is None:
+            self._cache = {}
+        else:
+            path_str = str(file_path)
+            self._cache.pop(path_str, None)
+    
+    def get_cached_results(self, file_path: Path) -> dict[str, Any] | None:
+        """Get cached results for unchanged file."""
+        path_str = str(file_path)
+        
+        if path_str in self._cache:
+            return self._cache[path_str].get("results")
+        return None
+    
+    def clear(self) -> None:
+        """Clear entire cache."""
+        self._cache = {}
+        if self.cache_path.exists():
+            self.cache_path.unlink()
+
+
+def _config_to_hash(config: Any) -> str:
+    """Convert config to a hash string for cache validation."""
+    import json
+    config_str = json.dumps(config, sort_keys=True, default=str)
+    return hashlib.sha256(config_str.encode()).hexdigest()[:8]

{redup-0.3.8 → redup-0.3.10}/src/redup/core/scanner.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import fnmatch
+import functools
 import time
 from collections.abc import Iterator
 from dataclasses import dataclass, field
@@ -40,7 +41,8 @@ class ScannedFile:
         return len(self.lines)
 
 
-def _should_exclude(path: Path, patterns: list[str]) -> bool:
+@functools.lru_cache(maxsize=1000)
+def _should_exclude(path: Path, patterns: tuple[str, ...]) -> bool:
     """Check if a path matches any exclusion pattern."""
     name = path.name
     str_path = str(path)
@@ -63,7 +65,7 @@ def _collect_files(config: ScanConfig) -> Iterator[Path]:
     root = config.root.resolve()
     for ext in config.extensions:
         for path in root.rglob(f"*{ext}"):
-            if _should_exclude(path, config.exclude_patterns):
+            if _should_exclude(path, tuple(config.exclude_patterns)):
                 continue
             if not config.include_tests and _is_test_file(path):
                 continue
@@ -100,7 +102,9 @@ def _extract_blocks_sliding(lines: list[str], min_lines: int) -> list[tuple[int,
             chunk = non_empty[start_idx : start_idx + window_size]
             first_line = chunk[0][0] + 1
             last_line = chunk[-1][0] + 1
-            text = "\n".join(line.strip() for _, line in chunk)
+            # Optimized: reduce string operations
+            lines = [line.strip() for _, line in chunk]
+            text = "\n".join(lines)
             blocks.append((first_line, last_line, text))
 
     return blocks

{redup-0.3.8 → redup-0.3.10}/src/redup.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.3.8
+Version: 0.3.10
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0
@@ -83,7 +83,7 @@ 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-0.3.8-green.svg)](https://pypi.org/project/redup/)
+[![Version](https://img.shields.io/badge/version-0.3.10-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-0.3.8 → redup-0.3.10}/src/redup.egg-info/SOURCES.txt

@@ -14,6 +14,7 @@ src/redup/cli_app/main.py
 src/redup/core/__init__.py
 src/redup/core/config.py
 src/redup/core/differ.py
+src/redup/core/hash_cache.py
 src/redup/core/hasher.py
 src/redup/core/lsh_matcher.py
 src/redup/core/matcher.py

{redup-0.3.8 → redup-0.3.10}/tests/test_scanner.py

@@ -13,15 +13,15 @@ from redup.core.scanner import (
 
 
 def test_should_exclude_git():
-    assert _should_exclude(Path(".git/config"), [".git"])
+    assert _should_exclude(Path(".git/config"), (".git",))
 
 
 def test_should_exclude_venv():
-    assert _should_exclude(Path("project/venv/lib/site.py"), ["venv"])
+    assert _should_exclude(Path("project/venv/lib/site.py"), ("venv",))
 
 
 def test_should_not_exclude_normal():
-    assert not _should_exclude(Path("src/main.py"), [".git", "venv"])
+    assert not _should_exclude(Path("src/main.py"), (".git", "venv"))
 
 
 def test_is_test_file():