code2llm 0.5.117__tar.gz → 0.5.119__tar.gz

{code2llm-0.5.117 → code2llm-0.5.119}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2llm
-Version: 0.5.117
+Version: 0.5.119
 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
@@ -67,7 +67,7 @@ Dynamic: requires-python
 
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.117-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-0.5.119-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-57.3h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
 - 🤖 **LLM usage:** $7.5000 (166 commits)

{code2llm-0.5.117 → code2llm-0.5.119}/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-0.5.117-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-0.5.119-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-57.3h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
 
 - 🤖 **LLM usage:** $7.5000 (166 commits)

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/__init__.py

@@ -8,7 +8,7 @@ Includes NLP Processing Pipeline for query normalization, intent matching,
 and entity resolution with multilingual support.
 """
 
-__version__ = "0.5.117"
+__version__ = "0.5.119"
 __author__ = "STTS Project"
 
 # Core analysis components (lightweight, always needed)

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/analysis/call_graph.py

@@ -5,7 +5,7 @@ from typing import Optional, Set, List, Dict
 
 from code2llm.core.config import Config
 from code2llm.core.models import AnalysisResult, FlowEdge
-from code2llm.analysis.utils import ast_unparse
+from code2llm.analysis.utils import ast_unparse, qualified_name
 
 
 class CallGraphExtractor(ast.NodeVisitor):
@@ -140,12 +140,7 @@ class CallGraphExtractor(ast.NodeVisitor):
         self.generic_visit(node)
         
     def _qualified_name(self, name: str) -> str:
-        """Get fully qualified name."""
-        parts = [self.module_name]
-        if self.class_stack:
-            parts.append(self.class_stack[-1])
-        parts.append(name)
-        return '.'.join(parts)
+        return qualified_name(self.module_name, self.class_stack, name)
         
     def _resolve_call(self, node: ast.AST) -> Optional[str]:
         """Resolve a call to its full name."""

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/analysis/cfg.py

@@ -6,7 +6,7 @@ from typing import Optional
 
 from code2llm.core.config import Config
 from code2llm.core.models import AnalysisResult, FlowNode, FlowEdge, FunctionInfo
-from code2llm.analysis.utils import ast_unparse
+from code2llm.analysis.utils import ast_unparse, qualified_name
 
 
 class CFGExtractor(ast.NodeVisitor):
@@ -261,12 +261,7 @@ class CFGExtractor(ast.NodeVisitor):
             self.generic_visit(node)
             
     def _qualified_name(self, name: str) -> str:
-        """Get fully qualified name."""
-        parts = [self.module_name]
-        if self.class_stack:
-            parts.append(self.class_stack[-1])
-        parts.append(name)
-        return '.'.join(parts)
+        return qualified_name(self.module_name, self.class_stack, name)
         
     def _extract_condition(self, node: ast.AST) -> str:
         """Extract condition as string."""

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/analysis/data_analysis.py

@@ -1,6 +1,12 @@
-"""Data Analysis logic for code2llm - extracted from YAMLExporter."""
+"""Data Analysis logic for code2llm - split into focused analyzers.
 
-from typing import Any, Dict, List
+This module provides three analyzers:
+  - DataFlowAnalyzer: data pipelines, state patterns, dependencies, event flows
+  - OptimizationAdvisor: data types, optimization opportunities, process patterns
+  - DataAnalyzer: facade combining both analyzers (backward compatibility)
+"""
+
+from typing import Any, Dict, List, Tuple
 from code2llm.core.models import AnalysisResult
 
 
@@ -10,7 +16,7 @@ _OUTPUT_INDICATORS = ['serialize', 'format', 'write', 'save', 'send', 'output',
 _MAX_PIPELINES = 15
 
 
-def _categorize_functions(result: 'AnalysisResult'):
+def _categorize_functions(result: 'AnalysisResult') -> Tuple[list, list, list]:
     """Categorize functions into input/transform/output based on name patterns."""
     input_funcs, transform_funcs, output_funcs = [], [], []
     for func_name, func in result.functions.items():
@@ -284,3 +290,81 @@ class DataAnalyzer:
             opt['hub_optimization'].append({'function': hub['id'], 'connections': hub['in_degree'] + hub['out_degree'], 'optimization_type': 'split' if hub['out_degree'] > 10 else 'cache'})
         opt['potential_score'] = (len(opt['type_consolidation']) * 10 + len(opt['process_consolidation']) * 15 + len(opt['hub_optimization']) * 5) / 100.0
         return opt
+
+
+# ---------------------------------------------------------------------------
+# New focused analyzer classes (Step 5 refactoring)
+# ---------------------------------------------------------------------------
+
+class DataFlowAnalyzer:
+    """Analyze data flows: pipelines, state patterns, dependencies, and event flows.
+
+    Extracted from DataAnalyzer to provide focused data flow analysis.
+    """
+
+    def analyze(self, result: AnalysisResult) -> Dict[str, Any]:
+        """Perform complete data flow analysis."""
+        return {
+            'data_pipelines': self.find_data_pipelines(result),
+            'state_patterns': self.find_state_patterns(result),
+            'data_dependencies': self.find_data_dependencies(result),
+            'event_flows': self.find_event_flows(result),
+        }
+
+    def find_data_pipelines(self, result: AnalysisResult) -> list:
+        """Find data transformation pipelines (wrapper for backward compat)."""
+        # Delegate to the module-level helper via DataAnalyzer instance
+        return DataAnalyzer()._find_data_pipelines(result)
+
+    def find_state_patterns(self, result: AnalysisResult) -> list:
+        """Find state management patterns."""
+        return DataAnalyzer()._find_state_patterns(result)
+
+    def find_data_dependencies(self, result: AnalysisResult) -> list:
+        """Find cross-module data dependencies."""
+        return DataAnalyzer()._find_data_dependencies(result)
+
+    def find_event_flows(self, result: AnalysisResult) -> list:
+        """Find event-driven patterns."""
+        return DataAnalyzer()._find_event_flows(result)
+
+
+class OptimizationAdvisor:
+    """Analyze optimization opportunities: data types and process patterns.
+
+    Extracted from DataAnalyzer to provide focused optimization analysis.
+    """
+
+    def analyze(self, result: AnalysisResult) -> Dict[str, Any]:
+        """Perform complete optimization analysis."""
+        data_types = self.analyze_data_types(result)
+        data_flow_graph = self.build_data_flow_graph(result)
+        process_patterns = self.identify_process_patterns(result)
+        optimization_analysis = self.analyze_optimization_opportunities(
+            result, data_types, data_flow_graph
+        )
+
+        return {
+            'data_types': data_types,
+            'data_flow_graph': data_flow_graph,
+            'process_patterns': process_patterns,
+            'optimization_analysis': optimization_analysis,
+        }
+
+    def analyze_data_types(self, result: AnalysisResult) -> list:
+        """Analyze data types and usage."""
+        return DataAnalyzer()._analyze_data_types(result)
+
+    def build_data_flow_graph(self, result: AnalysisResult) -> dict:
+        """Build data flow graph from function relationships."""
+        return DataAnalyzer()._build_data_flow_graph(result)
+
+    def identify_process_patterns(self, result: AnalysisResult) -> list:
+        """Identify common data processing patterns."""
+        return DataAnalyzer()._identify_process_patterns(result)
+
+    def analyze_optimization_opportunities(
+        self, result: AnalysisResult, data_types: list, dfg: dict
+    ) -> dict:
+        """Analyze optimization opportunities in data handling."""
+        return DataAnalyzer()._analyze_optimization_opportunities(result, data_types, dfg)

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/analysis/utils/__init__.py

@@ -1,5 +1,5 @@
 """Shared AST utilities for analysis modules."""
 
-from .ast_helpers import get_ast, find_function_node, expr_to_str, ast_unparse
+from .ast_helpers import get_ast, find_function_node, expr_to_str, ast_unparse, qualified_name
 
-__all__ = ["get_ast", "find_function_node", "expr_to_str", "ast_unparse"]
+__all__ = ["get_ast", "find_function_node", "expr_to_str", "ast_unparse", "qualified_name"]

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/analysis/utils/ast_helpers.py

@@ -57,6 +57,19 @@ def ast_unparse(node: Optional[ast.AST], default_none: str = "None") -> str:
         return str(node)
 
 
+def qualified_name(module_name: str, class_stack: list, name: str) -> str:
+    """Build a fully-qualified dotted name from module, optional class scope, and name.
+
+    Shared replacement for the identical ``_qualified_name`` methods in
+    ``CallGraphExtractor`` and ``CFGExtractor``.
+    """
+    parts = [module_name]
+    if class_stack:
+        parts.append(class_stack[-1])
+    parts.append(name)
+    return '.'.join(parts)
+
+
 def expr_to_str(node: ast.expr) -> Optional[str]:
     """Convert an AST expression to a dotted string (for call-name extraction).
 

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/core/file_cache.py

@@ -9,6 +9,12 @@ from typing import Any, Optional, Tuple
 import ast
 
 
+def make_cache_key(file_path: str, content: str) -> str:
+    """Generate a cache key from file stem and MD5 of content."""
+    content_hash = hashlib.md5(content.encode()).hexdigest()[:16]
+    return f"{Path(file_path).stem}_{content_hash}"
+
+
 class FileCache:
     """Cache for parsed AST files."""
     
@@ -26,9 +32,7 @@ class FileCache:
             return f"{Path(file_path).stem}_unknown"
 
     def _get_cache_key(self, file_path: str, content: str) -> str:
-        """Generate cache key from file path and content hash (legacy)."""
-        content_hash = hashlib.md5(content.encode()).hexdigest()[:16]
-        return f"{Path(file_path).stem}_{content_hash}"
+        return make_cache_key(file_path, content)
     
     def _get_cache_path(self, cache_key: str) -> Path:
         """Get cache file path."""

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/core/streaming/cache.py

@@ -1,10 +1,11 @@
 """Memory-efficient streaming cache with LRU eviction."""
 
 import ast
-import hashlib
 from pathlib import Path
 from typing import Dict, List, Optional, Tuple
 
+from code2llm.core.file_cache import make_cache_key
+
 
 class StreamingFileCache:
     """Memory-efficient cache with LRU eviction."""
@@ -17,9 +18,7 @@ class StreamingFileCache:
         self._access_order: List[str] = []
     
     def _get_cache_key(self, file_path: str, content: str) -> str:
-        """Generate cache key."""
-        content_hash = hashlib.md5(content.encode()).hexdigest()[:16]
-        return f"{Path(file_path).stem}_{content_hash}"
+        return make_cache_key(file_path, content)
     
     def _evict_if_needed(self) -> None:
         """Evict oldest entries if cache is full."""

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/exporters/article_view.py

@@ -7,15 +7,11 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, List
 
+from code2llm.exporters.base import ViewGeneratorMixin
 
-class ArticleViewGenerator:
-    """Generate status.md — publishable project health article."""
 
-    def generate(self, data: Dict[str, Any], output_path: str) -> None:
-        lines = self._render(data)
-        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
-        with open(output_path, "w", encoding="utf-8") as f:
-            f.write("\n".join(lines) + "\n")
+class ArticleViewGenerator(ViewGeneratorMixin):
+    """Generate status.md — publishable project health article."""
 
     def _render(self, data: Dict[str, Any]) -> List[str]:
         proj = data.get("project", {})

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/exporters/context_view.py

@@ -6,15 +6,11 @@ Generates context.md from project.yaml data.
 from pathlib import Path
 from typing import Any, Dict, List
 
+from code2llm.exporters.base import ViewGeneratorMixin
 
-class ContextViewGenerator:
-    """Generate context.md from project.yaml data."""
 
-    def generate(self, data: Dict[str, Any], output_path: str) -> None:
-        lines = self._render(data)
-        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
-        with open(output_path, "w", encoding="utf-8") as f:
-            f.write("\n".join(lines) + "\n")
+class ContextViewGenerator(ViewGeneratorMixin):
+    """Generate context.md from project.yaml data."""
 
     def _render(self, data: Dict[str, Any]) -> List[str]:
         proj = data.get("project", {})

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/exporters/flow_constants.py

@@ -15,6 +15,19 @@ EXCLUDE_PATTERNS = {
     'dist', 'build', 'egg-info', '.tox', '.mypy_cache',
 }
 
+def is_excluded_path(path: str) -> bool:
+    """Return True if *path* matches any standard exclusion pattern (venv, cache, etc.)."""
+    if not path:
+        return False
+    path_lower = path.lower().replace('\\', '/')
+    for pattern in EXCLUDE_PATTERNS:
+        if f'/{pattern}/' in path_lower or path_lower.startswith(f'{pattern}/'):
+            return True
+        if pattern in path_lower.split('/'):
+            return True
+    return False
+
+
 # Rekomendacje podziału typów hub: typ -> sugerowane pod-interfejsy
 HUB_SPLIT_RECOMMENDATIONS = {
     "AnalysisResult": [

{code2llm-0.5.117 → code2llm-0.5.119}/code2llm/exporters/flow_exporter.py

@@ -17,7 +17,7 @@ from pathlib import Path
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 from .base import BaseExporter, export_format
-from .flow_constants import CC_HIGH, FAN_OUT_THRESHOLD, EXCLUDE_PATTERNS, HUB_SPLIT_RECOMMENDATIONS, HUB_TYPE_THRESHOLD
+from .flow_constants import CC_HIGH, FAN_OUT_THRESHOLD, EXCLUDE_PATTERNS, HUB_SPLIT_RECOMMENDATIONS, HUB_TYPE_THRESHOLD, is_excluded_path
 from .flow_renderer import FlowRenderer
 from code2llm.core.models import (
     AnalysisResult, FunctionInfo, ClassInfo, ModuleInfo, FlowNode
@@ -382,12 +382,4 @@ class FlowExporter(BaseExporter):
     # utility helpers
     # ------------------------------------------------------------------
     def _is_excluded(self, path: str) -> bool:
-        if not path:
-            return False
-        path_lower = path.lower().replace('\\', '/')
-        for pattern in EXCLUDE_PATTERNS:
-            if f'/{pattern}/' in path_lower or path_lower.startswith(f'{pattern}/'):
-                return True
-            if pattern in path_lower.split('/'):
-                return True
-        return False
+        return is_excluded_path(path)

code2llm-0.5.119/code2llm/exporters/index_generator/__init__.py

@@ -0,0 +1,73 @@
+"""Index HTML Generator — web-based file browser for all generated outputs.
+
+Generates index.html that provides a GitHub Pages-ready interface
+for browsing all generated analysis files (toon, md, yaml, json, etc.)
+
+This package provides three components:
+  - FileScanner: scans output directory and collects file metadata
+  - HTMLRenderer: generates HTML with CSS and JavaScript
+  - IndexHTMLGenerator: facade combining scanner and renderer
+"""
+
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from .scanner import FileScanner, get_file_types, get_default_file_info, FILE_TYPES
+from .renderer import HTMLRenderer
+
+
+class IndexHTMLGenerator:
+    """Generate index.html for browsing all generated files.
+
+    This is a facade class that combines FileScanner and HTMLRenderer
+    to provide a simple interface for generating the index file.
+    """
+
+    # Backward compatibility: expose FILE_TYPES at class level
+    FILE_TYPES = FILE_TYPES
+
+    def __init__(self, output_dir: Path):
+        self.output_dir = Path(output_dir).resolve()
+        self._scanner = FileScanner(self.output_dir)
+        self._renderer = HTMLRenderer()
+
+    def generate(self) -> Path:
+        """Generate index.html in the output directory."""
+        files = self._scanner.scan()
+        html = self._renderer.render(files)
+        index_path = self.output_dir / 'index.html'
+        with open(index_path, 'w', encoding='utf-8') as f:
+            f.write(html)
+        return index_path
+
+    def scan_files(self) -> List[Dict[str, Any]]:
+        """Scan and return file metadata without generating HTML."""
+        return self._scanner.scan()
+
+    def render_html(self, files: List[Dict[str, Any]]) -> str:
+        """Render HTML from pre-scanned file list."""
+        return self._renderer.render(files)
+
+
+# Convenience function for direct usage
+def generate_index_html(output_dir: Path) -> Path:
+    """Generate index.html in the specified directory.
+
+    Args:
+        output_dir: Directory containing generated analysis files
+
+    Returns:
+        Path to the generated index.html file
+    """
+    return IndexHTMLGenerator(output_dir).generate()
+
+
+__all__ = [
+    'IndexHTMLGenerator',
+    'FileScanner',
+    'HTMLRenderer',
+    'generate_index_html',
+    'get_file_types',
+    'get_default_file_info',
+    'FILE_TYPES',
+]