code2llm 0.5.102__tar.gz → 0.5.104__tar.gz

{code2llm-0.5.102 → code2llm-0.5.104}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code2llm
-Version: 0.5.102
+Version: 0.5.104
 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
@@ -37,6 +37,16 @@ Requires-Dist: vulture>=2.10
 Requires-Dist: tiktoken>=0.5
 Requires-Dist: tree-sitter>=0.21
 Requires-Dist: tree-sitter-python>=0.21
+Requires-Dist: tree-sitter-javascript>=0.21
+Requires-Dist: tree-sitter-typescript>=0.21
+Requires-Dist: tree-sitter-go>=0.21
+Requires-Dist: tree-sitter-rust>=0.21
+Requires-Dist: tree-sitter-java>=0.21
+Requires-Dist: tree-sitter-c>=0.21
+Requires-Dist: tree-sitter-cpp>=0.22
+Requires-Dist: tree-sitter-c-sharp>=0.21
+Requires-Dist: tree-sitter-php>=0.22
+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"
@@ -53,16 +63,13 @@ Dynamic: requires-python
 
 # code2llm - Generated Analysis Files
 
-
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.102-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-51.2h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
+![AI Cost](https://img.shields.io/badge/AI%20Cost-$7.50-yellow) ![AI Model](https://img.shields.io/badge/AI%20Model-openrouter%2Fqwen%2Fqwen3-coder-next-lightgrey)
 
-- 🤖 **LLM usage:** $7.5000 (148 commits)
-- 👤 **Human dev:** ~$5123 (51.2h @ $100/h, 30min dedup)
+This project uses AI-generated code. Total cost: **$7.5000** with **153** AI commits.
 
-Generated on 2026-03-31 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
+Generated on 2026-04-09 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/models/openrouter/qwen/qwen3-coder-next)
 
 ---
 
@@ -390,10 +397,10 @@ code2llm ./ -f yaml --separate-orphans
 ---
 
 **Generated by**: `code2llm ./ -f all --readme`  
-**Analysis Date**: 2026-03-31  
-**Total Functions**: 934  
-**Total Classes**: 106  
-**Modules**: 122  
+**Analysis Date**: 2026-04-09  
+**Total Functions**: 1011  
+**Total Classes**: 111  
+**Modules**: 131  
 
 For more information about code2llm, visit: https://github.com/tom-sapletta/code2llm
 

{code2llm-0.5.102 → code2llm-0.5.104}/README.md

@@ -1,15 +1,12 @@
 # code2llm - Generated Analysis Files
 
-
 ## AI Cost Tracking
 
-![PyPI](https://img.shields.io/badge/pypi-costs-blue) ![Version](https://img.shields.io/badge/version-0.5.102-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-51.2h-blue) ![Model](https://img.shields.io/badge/Model-openrouter%2Fqwen%2Fqwen3--coder--next-lightgrey)
+![AI Cost](https://img.shields.io/badge/AI%20Cost-$7.50-yellow) ![AI Model](https://img.shields.io/badge/AI%20Model-openrouter%2Fqwen%2Fqwen3-coder-next-lightgrey)
 
-- 🤖 **LLM usage:** $7.5000 (148 commits)
-- 👤 **Human dev:** ~$5123 (51.2h @ $100/h, 30min dedup)
+This project uses AI-generated code. Total cost: **$7.5000** with **153** AI commits.
 
-Generated on 2026-03-31 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/qwen/qwen3-coder-next)
+Generated on 2026-04-09 using [openrouter/qwen/qwen3-coder-next](https://openrouter.ai/models/openrouter/qwen/qwen3-coder-next)
 
 ---
 
@@ -337,10 +334,10 @@ code2llm ./ -f yaml --separate-orphans
 ---
 
 **Generated by**: `code2llm ./ -f all --readme`  
-**Analysis Date**: 2026-03-31  
-**Total Functions**: 934  
-**Total Classes**: 106  
-**Modules**: 122  
+**Analysis Date**: 2026-04-09  
+**Total Functions**: 1011  
+**Total Classes**: 111  
+**Modules**: 131  
 
 For more information about code2llm, visit: https://github.com/tom-sapletta/code2llm
 

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/__init__.py

@@ -8,7 +8,7 @@ Includes NLP Processing Pipeline for query normalization, intent matching,
 and entity resolution with multilingual support.
 """
 
-__version__ = "0.5.102"
+__version__ = "0.5.104"
 __author__ = "STTS Project"
 
 # Core analysis components (lightweight, always needed)

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/cli_commands.py

@@ -128,7 +128,7 @@ def validate_chunked_output(output_dir: Path, args) -> bool:
         print(f"✗ No chunk directories found in: {output_dir}", file=sys.stderr)
         return False
     
-    required_files = ['analysis.toon', 'context.md', 'evolution.toon.yaml']
+    required_files = ['analysis.toon.yaml', 'context.md', 'evolution.toon.yaml']
     issues = []
     valid_chunks = []
     

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/core/lang/base.py

@@ -420,15 +420,34 @@ def analyze_c_family(
     patterns: Dict,
     lang_config: Dict,
     cc_lang: str = 'c_family',
+    ext: str = '',
 ) -> Dict:
     """Shared analyzer for C-family languages (Java, C#, C++, etc.).
 
-    Reduces boilerplate duplication across Java/C#/C++ analyzers.
+    Uses tree-sitter when available (10× faster), falls back to regex.
     """
-    result = _extract_declarations(
-        content, file_path, module_name,
-        patterns, stats, lang_config,
-    )
+    result = None
+
+    # Try tree-sitter first (much faster)
+    if ext:
+        try:
+            from .ts_parser import parse_source
+            from .ts_extractors import extract_declarations_ts
+            tree = parse_source(content, ext)
+            if tree:
+                result = extract_declarations_ts(
+                    tree, content.encode('utf-8'), ext, file_path, module_name
+                )
+        except ImportError:
+            pass  # tree-sitter not installed
+
+    # Fallback to regex
+    if result is None:
+        result = _extract_declarations(
+            content, file_path, module_name,
+            patterns, stats, lang_config,
+        )
+
     calculate_complexity_regex(content, result, lang=cc_lang)
     extract_calls_regex(content, module_name, result)
     stats['files_processed'] += 1

code2llm-0.5.104/code2llm/core/lang/cpp.py

@@ -0,0 +1,35 @@
+"""C++ analyzer (regex-based, with tree-sitter support)."""
+
+import re
+from typing import Dict
+
+from code2llm.core.lang.base import analyze_c_family
+
+# C++-specific patterns
+_CPP_PATTERNS = {
+    'import': re.compile(r'^\s*#include\s*["<]([^">]+)[">]'),
+    'class': re.compile(
+        r'^\s*(?:class|struct)\s+(\w+)'
+        r'(?:\s*:\s*(?:public|private|protected)\s+(\w+))?'
+    ),
+    'function': re.compile(
+        r'^\s*(?:virtual\s+|static\s+|inline\s+)?'
+        r'(?:[\w:*&<>\s]+\s+)?'
+        r'(\w+)\s*\([^)]*\)'
+    ),
+}
+
+_CPP_CONFIG = {
+    'index_files': (),
+    'brace_track': True,
+    'reserved': {'if', 'for', 'while', 'switch', 'return', 'catch', 'class'},
+}
+
+
+def analyze_cpp(content: str, file_path: str, module_name: str,
+                ext: str, stats: Dict) -> Dict:
+    """Analyze C++ files using shared C-family extraction."""
+    return analyze_c_family(
+        content, file_path, module_name, stats,
+        _CPP_PATTERNS, _CPP_CONFIG, ext=ext,
+    )

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/core/lang/csharp.py

@@ -38,5 +38,5 @@ def analyze_csharp(content: str, file_path: str, module_name: str,
     """Analyze C# files using shared C-family extraction."""
     return analyze_c_family(
         content, file_path, module_name, stats,
-        _CSHARP_PATTERNS, _CSHARP_CONFIG,
+        _CSHARP_PATTERNS, _CSHARP_CONFIG, ext=ext,
     )

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/core/lang/go_lang.py

@@ -1,16 +1,14 @@
-"""Go analyzer (regex-based)."""
+"""Go analyzer (regex-based, with tree-sitter support)."""
 
 import re
-from pathlib import Path
 from typing import Dict
 
 from code2llm.core.models import ClassInfo, FunctionInfo, ModuleInfo
 from code2llm.core.lang.base import calculate_complexity_regex, extract_calls_regex
 
 
-def analyze_go(content: str, file_path: str, module_name: str,
-               ext: str, stats: Dict) -> Dict:
-    """Analyze Go files using regex-based parsing."""
+def _analyze_go_regex(content: str, file_path: str, module_name: str, stats: Dict) -> Dict:
+    """Regex fallback for Go analysis."""
     result = {
         'module': ModuleInfo(name=module_name, file=file_path, is_package=False),
         'functions': {},
@@ -20,7 +18,6 @@ def analyze_go(content: str, file_path: str, module_name: str,
     }
 
     lines = content.split('\n')
-
     import_pattern = re.compile(r'^\s*import\s+(?:\(\s*["\']([^"\']+)["\']|["\']([^"\']+)["\'])')
     func_pattern = re.compile(r'^\s*func\s+(?:\([^)]+\)\s+)?(\w+)\s*\(')
     struct_pattern = re.compile(r'^\s*type\s+(\w+)\s+struct')
@@ -31,14 +28,12 @@ def analyze_go(content: str, file_path: str, module_name: str,
         if not line or line.startswith('//'):
             continue
 
-        # Imports
         import_match = import_pattern.match(line)
         if import_match:
             imp = import_match.group(1) or import_match.group(2)
             if imp:
                 result['module'].imports.append(imp)
 
-        # Functions
         func_match = func_pattern.match(line)
         if func_match:
             func_name = func_match.group(1)
@@ -53,7 +48,6 @@ def analyze_go(content: str, file_path: str, module_name: str,
             result['module'].functions.append(qualified_name)
             stats['functions_found'] += 1
 
-        # Structs (treated as classes)
         struct_match = struct_pattern.match(line)
         if struct_match:
             class_name = struct_match.group(1)
@@ -66,7 +60,6 @@ def analyze_go(content: str, file_path: str, module_name: str,
             result['module'].classes.append(qualified_name)
             stats['classes_found'] += 1
 
-        # Interfaces
         interface_match = interface_pattern.match(line)
         if interface_match:
             class_name = interface_match.group(1)
@@ -79,9 +72,31 @@ def analyze_go(content: str, file_path: str, module_name: str,
             result['module'].classes.append(qualified_name)
             stats['classes_found'] += 1
 
-    # Regex-based complexity estimation and call extraction
+    return result
+
+
+def analyze_go(content: str, file_path: str, module_name: str,
+               ext: str, stats: Dict) -> Dict:
+    """Analyze Go files. Uses tree-sitter when available, regex fallback."""
+    result = None
+
+    # Try tree-sitter first
+    try:
+        from .ts_parser import parse_source
+        from .ts_extractors import extract_declarations_ts
+        tree = parse_source(content, ext)
+        if tree:
+            result = extract_declarations_ts(
+                tree, content.encode('utf-8'), ext, file_path, module_name
+            )
+    except ImportError:
+        pass
+
+    # Fallback to regex
+    if result is None:
+        result = _analyze_go_regex(content, file_path, module_name, stats)
+
     calculate_complexity_regex(content, result, lang='go')
     extract_calls_regex(content, module_name, result)
-
     stats['files_processed'] += 1
     return result

{code2llm-0.5.102 → code2llm-0.5.104}/code2llm/core/lang/java.py

@@ -39,5 +39,5 @@ def analyze_java(content: str, file_path: str, module_name: str,
     """Analyze Java files using shared C-family extraction."""
     return analyze_c_family(
         content, file_path, module_name, stats,
-        _JAVA_PATTERNS, _JAVA_CONFIG,
+        _JAVA_PATTERNS, _JAVA_CONFIG, ext=ext,
     )

code2llm-0.5.104/code2llm/core/lang/php.py

@@ -0,0 +1,66 @@
+import re
+from typing import Dict, Optional, Tuple
+from code2llm.core.models import ClassInfo, FunctionInfo, ModuleInfo
+from code2llm.core.lang.base import calculate_complexity_regex, extract_calls_regex, _extract_declarations
+
+def _parse_php_metadata(content: str, module_name: str, result: Dict) -> Tuple[Optional[str], bool]:
+    lines = content.split('\n')
+    current_namespace = None
+    in_php = False
+    for line in lines:
+        line = line.strip()
+        if line.startswith('<?php') or line.startswith('<?'):
+            in_php = True
+            continue
+        if line == '?>':
+            in_php = False
+            continue
+        if not in_php: continue
+        ns_match = re.match(r'^namespace\s+([\\\w]+)', line)
+        if ns_match:
+            current_namespace = ns_match.group(1)
+            continue
+        use_match = re.match(r'^use\s+([\\\w]+)', line)
+        if use_match:
+            result['module'].imports.append(use_match.group(1))
+    return current_namespace, in_php
+
+def _adjust_qualified_names(result: Dict, module_name: str, namespace: str) -> None:
+    ns_prefix = f".{namespace}"
+    for key in ['classes', 'functions']:
+        new_items = {}
+        for qname, item in list(result[key].items()):
+            new_qname = qname.replace(f"{module_name}.", f"{module_name}{ns_prefix}.", 1)
+            item.qualified_name = new_qname
+            new_items[new_qname] = item
+        result[key] = new_items
+        result['module'].__setattr__(key, list(new_items.keys()))
+
+def _extract_php_traits(content: str, file_path: str, module_name: str, namespace: Optional[str], result: Dict, stats: Dict) -> None:
+    trait_pattern = re.compile(r'^\s*trait\s+(\w+)')
+    for line_no, line in enumerate(content.split('\n'), 1):
+        tm = trait_pattern.match(line.strip())
+        if tm:
+            tname = tm.group(1)
+            qual = f"{module_name}.{namespace + '.' if namespace else ''}{tname}"
+            result['classes'][qual] = ClassInfo(name=tname, qualified_name=qual, file=file_path, line=line_no, module=module_name, bases=[], methods=[], docstring="")
+            result['module'].classes.append(qual)
+            stats['classes_found'] += 1
+
+def analyze_php(content: str, file_path: str, module_name: str, ext: str, stats: Dict) -> Dict:
+    patterns = {
+        'import': re.compile(r'^(?:include|require|include_once|require_once)\s*["\']([^"\']+)["\']'),
+        'class': re.compile(r'(?:abstract\s+|final\s+)?class\s+(\w+)(?:\s+extends\s+(\w+))?(?:\s+implements\s+([\w,\s\\]+))?'),
+        'interface': re.compile(r'interface\s+(\w+)'),
+        'function': re.compile(r'(?:public\s+|private\s+|protected\s+)?(?:static\s+)?function\s+(\w+)\s*\('),
+    }
+    lang_config = {'index_files': (), 'brace_track': True, 'reserved': {'if', 'for', 'while', 'switch', 'return', 'catch', 'echo', 'print'}}
+    result = _extract_declarations(content, file_path, module_name, patterns, stats, lang_config)
+    namespace, _ = _parse_php_metadata(content, module_name, result)
+    if namespace:
+        _adjust_qualified_names(result, module_name, namespace)
+    _extract_php_traits(content, file_path, module_name, namespace, result, stats)
+    calculate_complexity_regex(content, result, lang='c_family')
+    extract_calls_regex(content, module_name, result)
+    stats['files_processed'] += 1
+    return result

code2llm-0.5.104/code2llm/core/lang/ts_extractors.py

@@ -0,0 +1,180 @@
+"""Tree-sitter based declaration extractors — fast CST traversal.
+
+Each language has specific node types for functions, classes, methods.
+This module provides unified extraction using tree-sitter queries.
+"""
+
+from typing import Dict, List, Optional, Any
+from pathlib import Path
+
+from code2llm.core.models import ClassInfo, FunctionInfo, ModuleInfo
+
+
+# Node type mappings per language
+FUNCTION_TYPES = {
+    'python': ('function_definition', 'async_function_definition'),
+    'javascript': ('function_declaration', 'function_expression', 'arrow_function', 'method_definition'),
+    'typescript': ('function_declaration', 'function_expression', 'arrow_function', 'method_definition'),
+    'go': ('function_declaration', 'method_declaration'),
+    'rust': ('function_item', 'impl_item'),
+    'java': ('method_declaration', 'constructor_declaration'),
+    'c': ('function_definition',),
+    'cpp': ('function_definition', 'template_function'),
+    'csharp': ('method_declaration', 'constructor_declaration'),
+    'php': ('function_definition', 'method_declaration'),
+    'ruby': ('method', 'singleton_method'),
+}
+
+CLASS_TYPES = {
+    'python': ('class_definition',),
+    'javascript': ('class_declaration', 'class_expression'),
+    'typescript': ('class_declaration', 'class_expression', 'interface_declaration'),
+    'go': ('type_declaration',),
+    'rust': ('struct_item', 'enum_item', 'impl_item', 'trait_item'),
+    'java': ('class_declaration', 'interface_declaration', 'enum_declaration'),
+    'c': ('struct_specifier',),
+    'cpp': ('class_specifier', 'struct_specifier'),
+    'csharp': ('class_declaration', 'interface_declaration', 'struct_declaration'),
+    'php': ('class_declaration', 'interface_declaration', 'trait_declaration'),
+    'ruby': ('class', 'module'),
+}
+
+EXT_TO_LANG = {
+    '.py': 'python',
+    '.js': 'javascript', '.jsx': 'javascript', '.mjs': 'javascript', '.cjs': 'javascript',
+    '.ts': 'typescript', '.tsx': 'typescript',
+    '.go': 'go',
+    '.rs': 'rust',
+    '.java': 'java',
+    '.c': 'c', '.h': 'c',
+    '.cpp': 'cpp', '.cc': 'cpp', '.cxx': 'cpp', '.hpp': 'cpp', '.hxx': 'cpp',
+    '.cs': 'csharp',
+    '.php': 'php',
+    '.rb': 'ruby',
+}
+
+
+def _get_node_text(node, source_bytes: bytes) -> str:
+    """Extract text content of a node."""
+    return source_bytes[node.start_byte:node.end_byte].decode('utf-8', errors='replace')
+
+
+def _find_name_node(node) -> Optional[Any]:
+    """Find the name/identifier child of a node."""
+    for child in node.children:
+        if child.type in ('identifier', 'name', 'property_identifier', 'type_identifier'):
+            return child
+        # For method definitions, look for property_identifier
+        if child.type == 'property_identifier':
+            return child
+    # Fallback: look in named children
+    for child in node.children:
+        if 'name' in child.type or 'identifier' in child.type:
+            return child
+    return None
+
+
+def _extract_functions_ts(tree, source_bytes: bytes, lang: str, 
+                          module_name: str, file_path: str) -> Dict[str, FunctionInfo]:
+    """Extract functions using tree-sitter traversal."""
+    functions = {}
+    func_types = FUNCTION_TYPES.get(lang, ())
+    
+    def visit(node, class_context: Optional[str] = None):
+        if node.type in func_types:
+            name_node = _find_name_node(node)
+            if name_node:
+                name = _get_node_text(name_node, source_bytes)
+                if class_context:
+                    qname = f"{module_name}.{class_context}.{name}"
+                else:
+                    qname = f"{module_name}.{name}"
+                
+                # Count lines
+                start_line = node.start_point[0] + 1
+                end_line = node.end_point[0] + 1
+                line_count = end_line - start_line + 1
+                
+                functions[qname] = FunctionInfo(
+                    name=name,
+                    qualified_name=qname,
+                    file=file_path,
+                    line=start_line,
+                    end_line=end_line,
+                    line_count=line_count,
+                    is_method=class_context is not None,
+                    class_name=class_context,
+                )
+        
+        # Recurse, tracking class context
+        new_class = None
+        class_types = CLASS_TYPES.get(lang, ())
+        if node.type in class_types:
+            name_node = _find_name_node(node)
+            if name_node:
+                new_class = _get_node_text(name_node, source_bytes)
+        
+        for child in node.children:
+            visit(child, new_class or class_context)
+    
+    visit(tree.root_node)
+    return functions
+
+
+def _extract_classes_ts(tree, source_bytes: bytes, lang: str,
+                        module_name: str, file_path: str) -> Dict[str, ClassInfo]:
+    """Extract classes using tree-sitter traversal."""
+    classes = {}
+    class_types = CLASS_TYPES.get(lang, ())
+    
+    def visit(node):
+        if node.type in class_types:
+            name_node = _find_name_node(node)
+            if name_node:
+                name = _get_node_text(name_node, source_bytes)
+                qname = f"{module_name}.{name}"
+                start_line = node.start_point[0] + 1
+                end_line = node.end_point[0] + 1
+                
+                classes[qname] = ClassInfo(
+                    name=name,
+                    qualified_name=qname,
+                    file=file_path,
+                    line=start_line,
+                    end_line=end_line,
+                )
+        
+        for child in node.children:
+            visit(child)
+    
+    visit(tree.root_node)
+    return classes
+
+
+def extract_declarations_ts(
+    tree,
+    source_bytes: bytes,
+    ext: str,
+    file_path: str,
+    module_name: str,
+) -> Dict:
+    """Extract all declarations from a tree-sitter tree.
+    
+    Returns dict compatible with regex-based _extract_declarations.
+    """
+    lang = EXT_TO_LANG.get(ext, 'generic')
+    
+    functions = _extract_functions_ts(tree, source_bytes, lang, module_name, file_path)
+    classes = _extract_classes_ts(tree, source_bytes, lang, module_name, file_path)
+    
+    return {
+        'module': ModuleInfo(
+            name=module_name,
+            file=file_path,
+            is_package=Path(file_path).name in ('__init__.py', 'index.js', 'index.ts', 'mod.rs', 'lib.rs'),
+        ),
+        'functions': functions,
+        'classes': classes,
+        'nodes': {},
+        'edges': [],
+    }