first commit

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/rag_cut/parsers/pdf/ocr.py

@@ -0,0 +1,57 @@
+"""Optional OCR for cropped image/table regions."""
+
+from __future__ import annotations
+
+import io
+from pathlib import Path
+
+import fitz
+
+
+def ocr_pixmap(pix: fitz.Pixmap) -> str:
+    """Run OCR on a pixmap; returns empty string when OCR is unavailable."""
+    try:
+        import pytesseract
+        from PIL import Image
+    except ImportError:
+        return ""
+
+    try:
+        image = Image.open(io.BytesIO(pix.tobytes("png")))
+        return _ocr_pil(image)
+    except Exception:
+        return ""
+
+
+def ocr_image_file(path: Path) -> str:
+    try:
+        import pytesseract  # noqa: F401
+        from PIL import Image
+    except ImportError:
+        return ""
+
+    try:
+        return _ocr_pil(Image.open(path))
+    except Exception:
+        return ""
+
+
+def _ocr_pil(image) -> str:
+    import pytesseract
+
+    for lang in ("chi_tra+eng", "chi_sim+eng", "eng"):
+        try:
+            text = pytesseract.image_to_string(image, lang=lang)
+            cleaned = " ".join(text.split())
+            if cleaned:
+                return cleaned
+        except Exception:
+            continue
+    return ""
+
+
+def describe_visual(ocr_text: str, kind: str, label: str) -> str:
+    """Lightweight image/table description without an external vision model."""
+    if ocr_text:
+        return f"{kind}：{ocr_text[:300]}"
+    return f"{kind}：{label}"