Initial MVP

src/kb_search/ingest/detector.py

@@ -0,0 +1,54 @@
+"""File type detection and routing."""
+
+from pathlib import Path
+
+EXTENSION_MAP = {
+    # Docling-handled formats
+    ".pdf": ("pdf", None),
+    ".docx": ("pdf", None),  # Docling handles DOCX too
+    ".html": ("pdf", None),
+    ".htm": ("pdf", None),
+    ".png": ("pdf", None),
+    ".jpg": ("pdf", None),
+    ".jpeg": ("pdf", None),
+    ".tiff": ("pdf", None),
+    ".bmp": ("pdf", None),
+    ".webp": ("pdf", None),
+    # Markdown / text
+    ".md": ("markdown", None),
+    ".markdown": ("markdown", None),
+    ".txt": ("markdown", None),
+    # Code
+    ".py": ("code", "python"),
+    ".sh": ("code", "bash"),
+    ".bash": ("code", "bash"),
+    ".go": ("code", "go"),
+}
+
+SUPPORTED_EXTENSIONS = set(EXTENSION_MAP.keys())
+
+
+def detect_type(path: Path, force_type: str | None = None,
+                force_language: str | None = None) -> tuple[str, str | None]:
+    """Detect document type and language from file extension.
+
+    Returns (doc_type, language) tuple.
+    Raises ValueError for unsupported file types.
+    """
+    if force_type:
+        return force_type, force_language
+
+    ext = path.suffix.lower()
+    if ext not in EXTENSION_MAP:
+        supported = ", ".join(sorted(SUPPORTED_EXTENSIONS))
+        raise ValueError(f"Unsupported file type '{ext}'. Supported: {supported}")
+
+    doc_type, language = EXTENSION_MAP[ext]
+    if force_language:
+        language = force_language
+    return doc_type, language
+
+
+def is_supported(path: Path) -> bool:
+    """Check if a file has a supported extension."""
+    return path.suffix.lower() in SUPPORTED_EXTENSIONS