code2llm 0.5.108__tar.gz → 0.5.109__tar.gz

{code2llm-0.5.108 → code2llm-0.5.109}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2llm
-Version: 0.5.108
+Version: 0.5.109
 Summary: High-performance Python code flow analysis with optimized TOON format - CFG, DFG, call graphs, and intelligent code queries
 Home-page: https://github.com/wronai/stts
 Author: STTS Project
@@ -50,6 +50,7 @@ Requires-Dist: tree-sitter-ruby>=0.21
 Provides-Extra: dev
 Requires-Dist: pytest>=6.2; extra == "dev"
 Requires-Dist: pytest-cov>=2.12; extra == "dev"
+Requires-Dist: pytest-xdist>=3.0; extra == "dev"
 Requires-Dist: black>=21.0; extra == "dev"
 Requires-Dist: flake8>=3.9; extra == "dev"
 Requires-Dist: mypy>=0.910; extra == "dev"
@@ -66,7 +67,7 @@ Dynamic: requires-python
 
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.108-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.109-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
 ![AI Cost](https://img.shields.io/badge/AI%20Cost-$7.50-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-53.7h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
 - 🤖 **LLM usage:** $7.5000 (154 commits)

{code2llm-0.5.108 → code2llm-0.5.109}/README.md

@@ -3,7 +3,7 @@
 
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.108-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.109-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
 ![AI Cost](https://img.shields.io/badge/AI%20Cost-$7.50-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-53.7h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
 - 🤖 **LLM usage:** $7.5000 (154 commits)

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm/__init__.py

@@ -8,7 +8,7 @@ Includes NLP Processing Pipeline for query normalization, intent matching,
 and entity resolution with multilingual support.
 """
 
-__version__ = "0.5.108"
+__version__ = "0.5.109"
 __author__ = "STTS Project"
 
 # Core analysis components (lightweight, always needed)

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm/cli_commands.py

@@ -109,71 +109,101 @@ def print_start_info(args, source_path: Path, output_dir: Path) -> None:
 
 def validate_chunked_output(output_dir: Path, args) -> bool:
     """Validate generated chunked output.
-    
+
     Checks:
     1. All chunks have required files (analysis.toon, context.md, evolution.toon.yaml)
     2. Files are not empty
     3. Report summary
-    
+
     Returns True if valid, False otherwise.
     """
     if not output_dir.exists():
         print(f"✗ Output directory does not exist: {output_dir}", file=sys.stderr)
         return False
-    
-    # Find all chunk directories
-    chunk_dirs = [d for d in output_dir.iterdir() if d.is_dir()]
-    
+
+    chunk_dirs = _get_chunk_dirs(output_dir)
     if not chunk_dirs:
         print(f"✗ No chunk directories found in: {output_dir}", file=sys.stderr)
         return False
-    
+
     required_files = ['analysis.toon.yaml', 'context.md', 'evolution.toon.yaml']
+    issues, valid_chunks = _validate_chunks(chunk_dirs, required_files)
+
+    _print_validation_summary(chunk_dirs, valid_chunks, issues)
+    return len(issues) == 0
+
+
+def _get_chunk_dirs(output_dir: Path) -> list[Path]:
+    """Find all chunk directories in output directory."""
+    return [d for d in output_dir.iterdir() if d.is_dir()]
+
+
+def _validate_chunks(chunk_dirs: list[Path], required_files: list[str]) -> tuple:
+    """Validate all chunks and return issues and valid chunks."""
     issues = []
     valid_chunks = []
-    
-    print(f"\n🔍 Validating {len(chunk_dirs)} chunks in: {output_dir}")
+
+    print(f"\n🔍 Validating {len(chunk_dirs)} chunks")
     print("-" * 50)
-    
+
     for chunk_dir in sorted(chunk_dirs):
-        chunk_name = chunk_dir.name
-        chunk_issues = []
-        
-        for req_file in required_files:
-            file_path = chunk_dir / req_file
-            if not file_path.exists():
-                chunk_issues.append(f"  missing {req_file}")
-            elif file_path.stat().st_size == 0:
-                chunk_issues.append(f"  empty {req_file}")
-        
+        chunk_issues = _validate_single_chunk(chunk_dir, required_files)
+
         if chunk_issues:
-            issues.append((chunk_name, chunk_issues))
-            print(f"✗ {chunk_name}")
-            for issue in chunk_issues:
-                print(f"    {issue}")
+            issues.append((chunk_dir.name, chunk_issues))
+            _print_chunk_errors(chunk_dir.name, chunk_issues)
         else:
-            # Get file sizes
-            sizes = []
-            for req_file in required_files:
-                size = (chunk_dir / req_file).stat().st_size
-                sizes.append(f"{req_file}:{size//1024}KB" if size > 1024 else f"{req_file}:{size}B")
-            valid_chunks.append(chunk_name)
-            print(f"✓ {chunk_name} ({', '.join(sizes)})")
-    
+            sizes = _get_file_sizes(chunk_dir, required_files)
+            valid_chunks.append(chunk_dir.name)
+            print(f"✓ {chunk_dir.name} ({sizes})")
+
     print("-" * 50)
+    return issues, valid_chunks
+
+
+def _validate_single_chunk(chunk_dir: Path, required_files: list[str]) -> list[str]:
+    """Validate a single chunk directory. Returns list of issues."""
+    chunk_issues = []
+
+    for req_file in required_files:
+        file_path = chunk_dir / req_file
+        if not file_path.exists():
+            chunk_issues.append(f"  missing {req_file}")
+        elif file_path.stat().st_size == 0:
+            chunk_issues.append(f"  empty {req_file}")
+
+    return chunk_issues
+
+
+def _get_file_sizes(chunk_dir: Path, required_files: list[str]) -> str:
+    """Get formatted file sizes for a chunk."""
+    sizes = []
+    for req_file in required_files:
+        size = (chunk_dir / req_file).stat().st_size
+        sizes.append(f"{req_file}:{size//1024}KB" if size > 1024 else f"{req_file}:{size}B")
+    return ", ".join(sizes)
+
+
+def _print_chunk_errors(chunk_name: str, chunk_issues: list[str]) -> None:
+    """Print errors for a chunk."""
+    print(f"✗ {chunk_name}")
+    for issue in chunk_issues:
+        print(f"    {issue}")
+
+
+def _print_validation_summary(chunk_dirs: list, valid_chunks: list, issues: list) -> None:
+    """Print validation summary report."""
     print(f"\n📊 Validation Summary:")
     print(f"  Total chunks: {len(chunk_dirs)}")
     print(f"  Valid: {len(valid_chunks)}")
     print(f"  Issues: {len(issues)}")
-    
+
     if issues:
         print(f"\n⚠️  {len(issues)} chunk(s) have issues:")
-        for chunk_name, chunk_issues in issues:
+        for chunk_name, _ in issues:
             print(f"    - {chunk_name}")
-        return False
     else:
         print(f"\n✅ All {len(valid_chunks)} chunks are valid!")
-        return True
 
 
 def generate_llm_context(args_list):

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm/exporters/yaml_exporter.py

@@ -132,24 +132,40 @@ class YAMLExporter(Exporter):
         connected: Set[str] = set()
         edges: List[Dict] = []
         seen_pairs: Set[Tuple[str, str]] = set()
-        
+
         for func_name, fi in result.functions.items():
-            for callee in fi.calls[:max_calls]:
-                resolved = self._resolve_callee(callee, result.functions)
-                if resolved and resolved != func_name:
-                    connected.add(func_name)
-                    connected.add(resolved)
-                    pair = (func_name, resolved)
-                    if pair not in seen_pairs:
-                        seen_pairs.add(pair)
-                        edges.append(self._create_edge(func_name, resolved, callee))
-                        if len(edges) >= max_edges:
-                            return connected, edges
             if len(edges) >= max_edges:
-                return connected, edges
-        
+                break
+            self._process_function_calls(
+                func_name, fi, result.functions, max_calls, max_edges,
+                connected, edges, seen_pairs
+            )
+
         return connected, edges
 
+    def _process_function_calls(
+        self, func_name: str, fi: FunctionInfo, functions: Dict[str, FunctionInfo],
+        max_calls: int, max_edges: int, connected: Set[str], edges: List[Dict],
+        seen_pairs: Set[Tuple[str, str]]
+    ) -> None:
+        """Process calls for a single function."""
+        for callee in fi.calls[:max_calls]:
+            if len(edges) >= max_edges:
+                break
+            resolved = self._resolve_callee(callee, functions)
+            if self._should_add_edge(func_name, resolved, seen_pairs):
+                connected.add(func_name)
+                connected.add(resolved)
+                seen_pairs.add((func_name, resolved))
+                edges.append(self._create_edge(func_name, resolved, callee))
+
+    @staticmethod
+    def _should_add_edge(func_name: str, resolved: Optional[str], seen_pairs: Set[Tuple[str, str]]) -> bool:
+        """Check if edge should be added (valid callee and not duplicate)."""
+        if not resolved or resolved == func_name:
+            return False
+        return (func_name, resolved) not in seen_pairs
+
     @staticmethod
     def _create_edge(caller: str, resolved: str, callee: str) -> Dict:
         """Create edge dict with call type classification."""

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm/nlp/__init__.py

@@ -4,7 +4,7 @@ Provides query normalization, intent matching, and entity resolution
 with multilingual support and fuzzy matching.
 """
 
-__version__ = "0.5.108"
+__version__ = "0.5.109"
 
 from .pipeline import NLPPipeline
 from .normalization import QueryNormalizer

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2llm
-Version: 0.5.108
+Version: 0.5.109
 Summary: High-performance Python code flow analysis with optimized TOON format - CFG, DFG, call graphs, and intelligent code queries
 Home-page: https://github.com/wronai/stts
 Author: STTS Project
@@ -50,6 +50,7 @@ Requires-Dist: tree-sitter-ruby>=0.21
 Provides-Extra: dev
 Requires-Dist: pytest>=6.2; extra == "dev"
 Requires-Dist: pytest-cov>=2.12; extra == "dev"
+Requires-Dist: pytest-xdist>=3.0; extra == "dev"
 Requires-Dist: black>=21.0; extra == "dev"
 Requires-Dist: flake8>=3.9; extra == "dev"
 Requires-Dist: mypy>=0.910; extra == "dev"
@@ -66,7 +67,7 @@ Dynamic: requires-python
 
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.108-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
+![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.109-blue) ![Python](https://img.shields.io/badge/python-3.9+-blue) ![License](https://img.shields.io/badge/license-Apache--2.0-green)
 ![AI Cost](https://img.shields.io/badge/AI%20Cost-$7.50-orange) ![Human Time](https://img.shields.io/badge/Human%20Time-53.7h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
 - 🤖 **LLM usage:** $7.5000 (154 commits)

{code2llm-0.5.108 → code2llm-0.5.109}/code2llm.egg-info/requires.txt

@@ -24,6 +24,7 @@ tree-sitter-ruby>=0.21
 [dev]
 pytest>=6.2
 pytest-cov>=2.12
+pytest-xdist>=3.0
 black>=21.0
 flake8>=3.9
 mypy>=0.910

{code2llm-0.5.108 → code2llm-0.5.109}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code2llm"
-version = "0.5.108"
+version = "0.5.109"
 description = "High-performance Python code flow analysis with optimized TOON format - CFG, DFG, call graphs, and intelligent code queries"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -67,6 +67,7 @@ dependencies = [
 dev = [
     "pytest>=6.2",
     "pytest-cov>=2.12",
+    "pytest-xdist>=3.0",
     "black>=21.0",
     "flake8>=3.9",
     "mypy>=0.910",
@@ -94,6 +95,10 @@ ignore_missing_imports = true
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 python_files = "test_*.py"
+addopts = "-n auto"  # Run tests in parallel using pytest-xdist
+markers = [
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')"
+]
 
 [tool.pfix]
 # Self-healing Python configuration

{code2llm-0.5.108 → code2llm-0.5.109}/setup.py

@@ -4,7 +4,7 @@ from setuptools import setup, find_packages
 import os
 
 # Read version
-version = "0.5.107"
+version = "0.5.108"
 
 # Read long description
 def read_readme():

{code2llm-0.5.108 → code2llm-0.5.109}/tests/test_edge_cases.py

@@ -50,22 +50,23 @@ class TestEdgeCases:
         finally:
             shutil.rmtree(tmp_dir)
     
+    @pytest.mark.slow
     def test_very_large_file(self):
         """Handle very large Python file."""
         tmp_dir = Path(tempfile.mkdtemp())
         try:
-            # Create large file (1000 functions)
-            lines = [f"def func_{i}(): pass" for i in range(1000)]
+            # Create large file (200 functions - reduced from 1000 for faster tests)
+            lines = [f"def func_{i}(): pass" for i in range(200)]
             (tmp_dir / "large.py").write_text('\n'.join(lines))
-            
+
             config = Config(
                 mode="static",
                 filters=FilterConfig(exclude_patterns=[], min_function_lines=1)
             )
             analyzer = ProjectAnalyzer(config)
             result = analyzer.analyze_project(str(tmp_dir))
-            
-            assert result.get_function_count() >= 1000
+
+            assert result.get_function_count() >= 200
         finally:
             shutil.rmtree(tmp_dir)