Add source code files

src/codeguard/analyzers/language_detector.py

@@ -0,0 +1,71 @@
+"""Language detection module."""
+
+from pathlib import Path
+from typing import Optional
+from codeguard.core.models import Language
+
+
+class LanguageDetector:
+    EXTENSION_MAP = {
+        ".py": Language.PYTHON,
+        ".pyw": Language.PYTHON,
+        ".js": Language.JAVASCRIPT,
+        ".jsx": Language.JAVASCRIPT,
+        ".ts": Language.TYPESCRIPT,
+        ".tsx": Language.TYPESCRIPT,
+        ".go": Language.GO,
+        ".rs": Language.RUST,
+    }
+
+    SHEBANG_PATTERNS = {
+        "python": [b"python", b"python3", b"python2"],
+        "bash": [b"bash", b"sh"],
+    }
+
+    def __init__(self):
+        pass
+
+    def detect(self, file_path: Path) -> Optional[Language]:
+        ext = file_path.suffix.lower()
+        return self.EXTENSION_MAP.get(ext)
+
+    def detect_from_content(self, content: bytes) -> Optional[Language]:
+        if not content:
+            return None
+
+        first_line = content.split(b"\n")[0].lower()
+
+        for lang, patterns in self.SHEBANG_PATTERNS.items():
+            for pattern in patterns:
+                if pattern in first_line:
+                    if lang == "python":
+                        return Language.PYTHON
+
+        return None
+
+    def is_supported(self, file_path: Path) -> bool:
+        return self.detect(file_path) is not None
+
+    def get_language_by_name(self, name: str) -> Optional[Language]:
+        name = name.lower()
+        for lang in Language:
+            if lang.value == name:
+                return lang
+        return None
+
+    def chunk_code(self, code: str, max_tokens: int = 8000) -> list[str]:
+        lines = code.split("\n")
+        chunks = []
+        current_chunk = []
+
+        for line in lines:
+            current_chunk.append(line)
+            if len("".join(current_chunk)) > max_tokens:
+                if current_chunk:
+                    chunks.append("\n".join(current_chunk[:-1]))
+                current_chunk = [line]
+
+        if current_chunk:
+            chunks.append("\n".join(current_chunk))
+
+        return chunks if chunks else [code]