redup 0.1.1__tar.gz → 0.1.2__tar.gz

{redup-0.1.1 → redup-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.1.1
+Version: 0.1.2
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0

{redup-0.1.1 → redup-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "redup"
-version = "0.1.1"
+version = "0.1.2"
 description = "Code duplication analyzer and refactoring planner for LLMs"
 readme = "README.md"
 license = "Apache-2.0"
@@ -66,6 +66,7 @@ line-length = 100
 
 [tool.ruff.lint]
 select = ["E", "F", "W", "I", "UP", "B", "SIM"]
+ignore = ["B008"]
 
 [tool.mypy]
 python_version = "3.10"

{redup-0.1.1 → redup-0.1.2}/src/redup/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 
 from redup.core.models import (
     DuplicateFragment,
@@ -11,8 +11,8 @@ from redup.core.models import (
     RefactorSuggestion,
     ScanConfig,
 )
-from redup.core.scanner import scan_project
 from redup.core.pipeline import analyze
+from redup.core.scanner import scan_project
 
 __all__ = [
     "analyze",

{redup-0.1.1 → redup-0.1.2}/src/redup/cli_app/main.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 from enum import Enum
 from pathlib import Path
-from typing import Optional
 
 import typer
 
@@ -29,6 +28,11 @@ class OutputFormat(str, Enum):
     all = "all"
 
 
+DEFAULT_PATH = Path(".")
+DEFAULT_FORMAT = OutputFormat.toon
+DEFAULT_OUTPUT: Path | None = None
+
+
 def _write_output(content: str, output: Path | None, suffix: str) -> None:
     """Write content to file or stdout."""
     if output:
@@ -43,19 +47,19 @@ def _write_output(content: str, output: Path | None, suffix: str) -> None:
 @app.command()
 def scan(
     path: Path = typer.Argument(
-        Path("."),
+        DEFAULT_PATH,
         help="Project root directory to scan.",
         exists=True,
         dir_okay=True,
         file_okay=False,
     ),
     format: OutputFormat = typer.Option(
-        OutputFormat.toon,
+        DEFAULT_FORMAT,
         "--format", "-f",
         help="Output format.",
     ),
-    output: Optional[Path] = typer.Option(
-        None,
+    output: Path | None = typer.Option(
+        DEFAULT_OUTPUT,
         "--output", "-o",
         help="Output directory or file path. Defaults to stdout.",
     ),
@@ -118,7 +122,7 @@ def scan(
             output_dir = path / "redup_output"
         output_dir.mkdir(parents=True, exist_ok=True)
 
-        for fmt, renderer, suffix in [
+        for _fmt, renderer, suffix in [
             ("JSON", to_json, "json"),
             ("YAML", to_yaml, "yaml"),
             ("TOON", to_toon, "toon"),
@@ -139,8 +143,8 @@ def scan(
 def info() -> None:
     """Show reDUP version and configuration info."""
     typer.echo(f"reDUP v{redup.__version__}")
-    typer.echo(f"  Python package: redup")
-    typer.echo(f"  Repo: https://github.com/semcod/redup")
+    typer.echo("  Python package: redup")
+    typer.echo("  Repo: https://github.com/semcod/redup")
     typer.echo("")
     typer.echo("Optional dependencies:")
 

{redup-0.1.1 → redup-0.1.2}/src/redup/core/hasher.py

@@ -23,7 +23,7 @@ def _normalize_text(text: str) -> str:
             continue
         if stripped.startswith('"""') or stripped.startswith("'''"):
             continue
-        stripped = re.sub(r"#.*$", "", stripped)
+        stripped = re.sub(r'#.*$', "", stripped)
         stripped = stripped.strip()
         if stripped:
             lines.append(stripped)
@@ -49,7 +49,7 @@ def _normalize_ast_text(text: str) -> str:
     normalized = _normalize_text(text)
     normalized = re.sub(r'"[^"]*"', '"__STR__"', normalized)
     normalized = re.sub(r"'[^']*'", "'__STR__'", normalized)
-    normalized = re.sub(r"\b\d+\.?\d*\b", "__NUM__", normalized)
+    normalized = re.sub(r'\b\d+\.?\d*\b', "__NUM__", normalized)
     return normalized
 
 
@@ -122,16 +122,20 @@ def _ast_to_normalized_string(tree: object) -> str:
     return " ".join(parts)
 
 
+def _hash_text(text: str, normalizer: callable) -> str:
+    """Generic SHA-256 hash function with configurable normalizer."""
+    normalized = normalizer(text)
+    return hashlib.sha256(normalized.encode("utf-8")).hexdigest()[:16]
+
+
 def hash_block(text: str) -> str:
     """SHA-256 hash of normalized text."""
-    normalized = _normalize_text(text)
-    return hashlib.sha256(normalized.encode("utf-8")).hexdigest()[:16]
+    return _hash_text(text, _normalize_text)
 
 
 def hash_block_structural(text: str) -> str:
     """SHA-256 hash of deeply normalized text (variable names replaced)."""
-    normalized = _normalize_ast_text(text)
-    return hashlib.sha256(normalized.encode("utf-8")).hexdigest()[:16]
+    return _hash_text(text, _normalize_ast_text)
 
 
 @dataclass
@@ -175,22 +179,23 @@ def build_hash_index(blocks: list[CodeBlock], min_lines: int = 3) -> HashIndex:
     return index
 
 
-def find_exact_duplicates(index: HashIndex) -> dict[str, list[HashedBlock]]:
-    """Find groups of blocks with identical normalized text."""
+def _find_duplicates(hash_dict: dict[str, list[HashedBlock]]) -> dict[str, list[HashedBlock]]:
+    """Generic duplicate finder for any hash dictionary."""
     return {
         h: blocks
-        for h, blocks in index.exact.items()
+        for h, blocks in hash_dict.items()
         if len(blocks) > 1 and _blocks_from_different_locations(blocks)
     }
 
 
+def find_exact_duplicates(index: HashIndex) -> dict[str, list[HashedBlock]]:
+    """Find groups of blocks with identical normalized text."""
+    return _find_duplicates(index.exact)
+
+
 def find_structural_duplicates(index: HashIndex) -> dict[str, list[HashedBlock]]:
     """Find groups of blocks with identical structure (names may differ)."""
-    return {
-        h: blocks
-        for h, blocks in index.structural.items()
-        if len(blocks) > 1 and _blocks_from_different_locations(blocks)
-    }
+    return _find_duplicates(index.structural)
 
 
 def _blocks_from_different_locations(blocks: list[HashedBlock]) -> bool:

{redup-0.1.1 → redup-0.1.2}/src/redup/core/models.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 from dataclasses import dataclass, field
 from enum import Enum
 from pathlib import Path
-from typing import Optional
 
 
 class DuplicateType(str, Enum):
@@ -59,8 +58,8 @@ class DuplicateFragment:
     line_start: int
     line_end: int
     text: str = ""
-    function_name: Optional[str] = None
-    class_name: Optional[str] = None
+    function_name: str | None = None
+    class_name: str | None = None
 
     @property
     def line_count(self) -> int:
@@ -76,7 +75,7 @@ class DuplicateGroup:
     fragments: list[DuplicateFragment] = field(default_factory=list)
     similarity_score: float = 1.0
     normalized_hash: str = ""
-    normalized_name: Optional[str] = None
+    normalized_name: str | None = None
 
     @property
     def occurrences(self) -> int:
@@ -107,8 +106,8 @@ class RefactorSuggestion:
     group_id: str
     action: RefactorAction
     new_module: str
-    function_name: Optional[str] = None
-    class_name: Optional[str] = None
+    function_name: str | None = None
+    class_name: str | None = None
     original_files: list[str] = field(default_factory=list)
     risk_level: RiskLevel = RiskLevel.LOW
     priority: int = 0
@@ -131,7 +130,7 @@ class DuplicationMap:
     """Complete result of a reDUP analysis run."""
 
     project_path: str = ""
-    config: Optional[ScanConfig] = None
+    config: ScanConfig | None = None
     groups: list[DuplicateGroup] = field(default_factory=list)
     suggestions: list[RefactorSuggestion] = field(default_factory=list)
     stats: ScanStats = field(default_factory=ScanStats)

{redup-0.1.1 → redup-0.1.2}/src/redup/core/pipeline.py

@@ -2,15 +2,13 @@
 
 from __future__ import annotations
 
-from collections import defaultdict
-
 from redup.core.hasher import (
     HashedBlock,
     build_hash_index,
     find_exact_duplicates,
     find_structural_duplicates,
 )
-from redup.core.matcher import match_candidates, refine_structural_matches
+from redup.core.matcher import refine_structural_matches
 from redup.core.models import (
     DuplicateFragment,
     DuplicateGroup,
@@ -19,7 +17,7 @@ from redup.core.models import (
     ScanConfig,
 )
 from redup.core.planner import generate_suggestions
-from redup.core.scanner import CodeBlock, ScannedFile, scan_project
+from redup.core.scanner import CodeBlock, scan_project
 
 
 def _blocks_to_group(

{redup-0.1.1 → redup-0.1.2}/src/redup/core/planner.py

@@ -3,7 +3,6 @@
 from __future__ import annotations
 
 import os
-from collections import Counter
 
 from redup.core.models import (
     DuplicateGroup,
@@ -20,7 +19,7 @@ def _common_prefix(paths: list[str]) -> str:
         return ""
     parts_list = [p.split(os.sep) for p in paths]
     prefix: list[str] = []
-    for segments in zip(*parts_list):
+    for segments in zip(*parts_list, strict=True):
         if len(set(segments)) == 1:
             prefix.append(segments[0])
         else:

{redup-0.1.1 → redup-0.1.2}/src/redup/core/scanner.py

@@ -4,9 +4,9 @@ from __future__ import annotations
 
 import fnmatch
 import time
+from collections.abc import Iterator
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Iterator
 
 from redup.core.models import ScanConfig, ScanStats
 

{redup-0.1.1 → redup-0.1.2}/src/redup/reporters/yaml_reporter.py

@@ -10,7 +10,7 @@ def to_yaml(dup_map: DuplicationMap) -> str:
     try:
         import yaml
     except ImportError:
-        raise ImportError("pyyaml is required for YAML output: pip install pyyaml")
+        raise ImportError("pyyaml is required for YAML output: pip install pyyaml") from None
 
     from redup.reporters.json_reporter import _group_to_dict, _suggestion_to_dict
 

{redup-0.1.1 → redup-0.1.2}/src/redup.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: redup
-Version: 0.1.1
+Version: 0.1.2
 Summary: Code duplication analyzer and refactoring planner for LLMs
 Author-email: Tom Sapletta <tom@sapletta.com>
 License-Expression: Apache-2.0