refactor(goal): code analysis engine

changes:
  - file: analyzer.py
    area: analyzer
    modified: [_scan_files, ProjectAnalyzer]
  - file: cli.py
    area: cli
    modified: [main]

dependencies:
  flow: "cli→analyzer"
  - cli.py -> analyzer.py

stats:
  lines: "+74/-46 (net +28)"
  files: 2
  complexity: "Large structural change (normalized)"

Author: tom-sapletta-com

CHANGELOG.md

@@ -1,3 +1,15 @@
+## [1.0.46] - 2026-02-26
+
+### Summary
+
+refactor(goal): code analysis engine
+
+### Other
+
+- update code2logic/analyzer.py
+- update code2logic/cli.py
+
+
 ## [1.0.45] - 2026-02-26
 
 ### Summary

VERSION

@@ -1 +1 @@
-1.0.45
+1.0.46

code2logic/__init__.py

@@ -18,7 +18,7 @@
     >>> print(output)
 """
 
-__version__ = "1.0.45"
+__version__ = "1.0.46"
 __author__ = "Softreck"
 __email__ = "info@softreck.dev"
 __license__ = "MIT"

code2logic/analyzer.py

@@ -5,6 +5,7 @@
 """
 
 import logging
+import os
 import sys
 import time
 from collections import defaultdict
@@ -218,63 +219,89 @@ def analyze(self) -> ProjectInfo:
 
     def _scan_files(self):
         """Scan and parse all source files."""
-        for fp in self.root_path.rglob('*'):
-            if not fp.is_file():
-                continue
-
-            # Skip ignored directories
-            if any(d in fp.parts for d in self.IGNORE_DIRS):
-                continue
-
-            # Skip ignored files
-            if fp.name in self.IGNORE_FILES:
-                continue
+        scan_start = time.time()
+        files_seen = 0
+        files_parsed = 0
+        files_matched = 0
+        scan_progress_every = 500
+
+        for root, dirnames, filenames in os.walk(self.root_path):
+            dirnames[:] = [d for d in dirnames if d not in self.IGNORE_DIRS]
+            for filename in filenames:
+                files_seen += 1
+                fp = Path(root) / filename
+
+                if filename in self.IGNORE_FILES:
+                    continue
 
-            ext = fp.suffix.lower()
-            language = self.LANGUAGE_EXTENSIONS.get(ext)
-            if language is None and ext == '':
-                try:
-                    with fp.open('r', encoding='utf-8', errors='ignore') as f:
-                        language = self._language_from_shebang(f.readline())
-                except Exception:
-                    language = None
+                ext = fp.suffix.lower()
+                language = self.LANGUAGE_EXTENSIONS.get(ext)
+                if language is None and ext == '':
+                    try:
+                        with fp.open('r', encoding='utf-8', errors='ignore') as f:
+                            language = self._language_from_shebang(f.readline())
+                    except Exception:
+                        language = None
 
-            if language is None:
-                continue
+                if language is None:
+                    continue
 
-            self.languages[language] += 1
+                files_matched += 1
+                self.languages[language] += 1
 
-            # Read file
-            try:
-                content = fp.read_text(encoding='utf-8', errors='ignore')
-            except Exception:
-                continue
+                if self.verbose and files_seen > 0 and (files_seen % scan_progress_every) == 0:
+                    log.info(
+                        "Scan progress: seen=%d matched=%d parsed=%d modules=%d time=%.2fs",
+                        files_seen,
+                        files_matched,
+                        files_parsed,
+                        len(self.modules),
+                        time.time() - scan_start,
+                    )
 
-            rel_path = str(fp.relative_to(self.root_path))
+                try:
+                    content = fp.read_text(encoding='utf-8', errors='ignore')
+                except Exception:
+                    continue
 
-            # Try Tree-sitter first, then fallback
-            module = None
-            try:
-                if self.ts_parser and self.ts_parser.is_available(language):
-                    module = self.ts_parser.parse(rel_path, content, language)
-            except Exception as e:
-                if self.verbose:
-                    log.debug("Tree-sitter parser failed for %s: %s", rel_path, e)
+                try:
+                    rel_path = str(fp.relative_to(self.root_path))
+                except Exception:
+                    rel_path = str(fp)
 
-            if module is None:
+                module = None
                 try:
-                    module = self.fallback_parser.parse(rel_path, content, language)
+                    if self.ts_parser and self.ts_parser.is_available(language):
+                        module = self.ts_parser.parse(rel_path, content, language)
                 except Exception as e:
                     if self.verbose:
-                        log.debug("Fallback parser failed for %s: %s", rel_path, e)
-                    continue
+                        log.debug("Tree-sitter parser failed for %s: %s", rel_path, e)
+
+                if module is None:
+                    try:
+                        module = self.fallback_parser.parse(rel_path, content, language)
+                    except Exception as e:
+                        if self.verbose:
+                            log.debug("Fallback parser failed for %s: %s", rel_path, e)
+                        continue
+
+                if module:
+                    files_parsed += 1
+                    try:
+                        module.file_bytes = fp.stat().st_size
+                    except Exception:
+                        module.file_bytes = len(content.encode('utf-8', errors='ignore'))
+                    self.modules.append(module)
 
-            if module:
-                try:
-                    module.file_bytes = fp.stat().st_size
-                except Exception:
-                    module.file_bytes = len(content.encode('utf-8', errors='ignore'))
-                self.modules.append(module)
+        if self.verbose:
+            log.info(
+                "Scan finished: seen=%d matched=%d parsed=%d modules=%d time=%.2fs",
+                files_seen,
+                files_matched,
+                files_parsed,
+                len(self.modules),
+                time.time() - scan_start,
+            )
 
     def _detect_entrypoints(self) -> List[str]:
         """Detect project entry points."""

code2logic/cli.py

@@ -510,6 +510,7 @@ def _code2logic_llm_cli(argv: list[str]) -> None:
 
 
 def main(argv=None):
+    cli_start = time.time()
     parser = argparse.ArgumentParser(
         description='Analyze source code and generate logical representations',
         formatter_class=argparse.RawDescriptionHelpFormatter

logic2code/__init__.py

@@ -14,5 +14,5 @@
 from .generator import CodeGenerator, GeneratorConfig, GenerationResult
 from .renderers import PythonRenderer
 
-__version__ = '1.0.45'
+__version__ = '1.0.46'
 __all__ = ['CodeGenerator', 'GeneratorConfig', 'GenerationResult', 'PythonRenderer']

logic2test/__init__.py

@@ -15,5 +15,5 @@
 from .parsers import LogicParser
 from .templates import TestTemplate
 
-__version__ = '1.0.45'
+__version__ = '1.0.46'
 __all__ = ['TestGenerator', 'GeneratorConfig', 'GenerationResult', 'LogicParser', 'TestTemplate']

lolm/__init__.py

@@ -76,7 +76,7 @@
 )
 from .clients import LLMRateLimitError
 
-__version__ = '1.0.45'
+__version__ = '1.0.46'
 __all__ = [
     # Config
     'LLMConfig',

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "code2logic"
-version = "1.0.45"
+version = "1.0.46"
 description = "Code2Logic - Source code to logical representation converter for LLM analysis, featuring Tree-sitter parsing, dependency graph analysis, and multi-language support."
 readme = "README.md"
 license = "Apache-2.0"

tests/samples/sample_reexport/__init__.py

@@ -18,4 +18,4 @@
     "ProcessingError",
 ]
 
-__version__ = "1.0.45"
+__version__ = "1.0.46"