refactor(code2llm): code analysis engine

changes:
  - file: analyzer.py
    area: analyzer
    modified: [_collect_files, ProjectAnalyzer, analyze_project]
  - file: file_filter.py
    area: core
    modified: [FastFileFilter, should_process]
  - file: gitignore.py
    area: core
    modified: [GitIgnoreParser, is_ignored]

dependencies:
  flow: "analyzer→file_filter→gitignore"
  - analyzer.py -> file_filter.py
  - file_filter.py -> gitignore.py

stats:
  lines: "+3/-39 (net -36)"
  files: 3
  complexity: "-171% complexity (refactor win)"

Author: tom-sapletta-com

CHANGELOG.md

@@ -1,5 +1,12 @@
 ## [Unreleased]
 
+## [0.5.133] - 2026-04-20
+
+### Other
+- Update code2llm/core/analyzer.py
+- Update code2llm/core/file_filter.py
+- Update code2llm/core/gitignore.py
+
 ## [0.5.132] - 2026-04-20
 
 ### Other

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-0.5.132-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-0.5.133-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)

VERSION

@@ -1 +1 @@
-0.5.132
+0.5.133

code2llm/__init__.py

@@ -8,7 +8,7 @@
 and entity resolution with multilingual support.
 """
 
-__version__ = "0.5.132"
+__version__ = "0.5.133"
 __author__ = "STTS Project"
 
 # Core analysis components (lightweight, always needed)

code2llm/core/analyzer.py

@@ -43,12 +43,7 @@ def __init__(self, config: Optional[Config] = None, project_path: Optional[Path]
     def analyze_project(self, project_path: str) -> AnalysisResult:
         """Analyze entire project."""
         start_time = time.time()
-        print(f"DEBUG analyze_project: input project_path={project_path}")
-        print(f"DEBUG analyze_project: self.project_path before={self.project_path}")
         project_path = self._resolve_project_path(project_path)
-        print(f"DEBUG analyze_project: project_path after resolve={project_path}")
-        print(f"DEBUG analyze_project: self.project_path after={self.project_path}")
-        print(f"DEBUG analyze_project: file_filter.project_path={self.file_filter.project_path}")
         files = self._collect_files(project_path)
 
         if self.config.verbose:
@@ -67,9 +62,7 @@ def analyze_project(self, project_path: str) -> AnalysisResult:
                 print(f"   ... and {len(files_to_analyze) - 10} more")
             print()
 
-        print(f"DEBUG analyze_project: files_to_analyze={len(files_to_analyze)}")
         fresh_results = self._run_analysis(files_to_analyze)
-        print(f"DEBUG analyze_project: fresh_results={len(fresh_results)}")
         self._store_to_persistent_cache(pcache, files_to_analyze, fresh_results)
 
         merged = self._merge_results(cached_results + fresh_results, str(project_path))
@@ -214,10 +207,6 @@ def _collect_files(self, project_path: Path) -> List[Tuple[str, str]]:
                 if not self.file_filter.should_process(file_str):
                     continue
 
-                # DEBUG
-                if 'vendor' in file_str.lower():
-                    print(f"DEBUG _collect_files: COLLECTED vendor file: {file_str}")
-
                 # Calculate module name from relative path
                 rel = os.path.relpath(file_str, project_str)
                 parts = rel.replace('\\', '/').split('/')
@@ -231,10 +220,6 @@ def _collect_files(self, project_path: Path) -> List[Tuple[str, str]]:
 
                 files.append((file_str, module_name))
 
-        # DEBUG
-        vendor_count = len([f for f, m in files if 'vendor' in f.lower()])
-        print(f"DEBUG _collect_files: total={len(files)}, vendor={vendor_count}")
-
         return files
 
     def _analyze_parallel(self, files: List[Tuple[str, str]]) -> List[Dict]:

code2llm/core/file_filter.py

@@ -98,20 +98,10 @@ def should_process(self, file_path: str) -> bool:
         path_lower = file_path.lower()
         basename_lower = Path(file_path).name.lower()
 
-        passes_gitignore = self._passes_gitignore(file_path)
-        passes_excludes = self._passes_excludes(path_lower, basename_lower)
-        passes_includes = self._passes_includes(path_lower)
-
-        # DEBUG
-        if 'vendor' in file_path.lower():
-            print(f"DEBUG should_process: {file_path}")
-            print(f"  passes_gitignore={passes_gitignore}, passes_excludes={passes_excludes}, passes_includes={passes_includes}")
-            print(f"  _gitignore_parser={self._gitignore_parser}, project_path={self.project_path}")
-
         return (
-            passes_gitignore and
-            passes_excludes and
-            passes_includes
+            self._passes_gitignore(file_path) and
+            self._passes_excludes(path_lower, basename_lower) and
+            self._passes_includes(path_lower)
         )
 
     def _passes_line_count(self, line_count: int) -> bool:

code2llm/core/gitignore.py

@@ -110,22 +110,11 @@ def is_ignored(self, file_path: Path, project_root: Path) -> bool:
         except ValueError:
             return False
 
-        # DEBUG
-        if 'vendor' in path_str:
-            print(f"DEBUG is_ignored: path_str={path_str}, entries={len(self._entries)}")
-
         ignored = False
         for entry in self._entries:
             if entry.regex.search(path_str):
-                # DEBUG
-                if 'vendor' in path_str:
-                    print(f"DEBUG is_ignored: MATCHED pattern={entry.regex.pattern}, is_negated={entry.is_negated}")
                 ignored = not entry.is_negated
 
-        # DEBUG
-        if 'vendor' in path_str:
-            print(f"DEBUG is_ignored: result={ignored}")
-
         return ignored
 
 

code2llm/nlp/__init__.py

@@ -4,7 +4,7 @@
 with multilingual support and fuzzy matching.
 """
 
-__version__ = "0.5.132"
+__version__ = "0.5.133"
 
 from .pipeline import NLPPipeline
 from .normalization import QueryNormalizer

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "code2llm"
-version = "0.5.132"
+version = "0.5.133"
 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"