first commit

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

backend/rag_cut/parsers/pdf_parser.py

@@ -0,0 +1,31 @@
+"""PDF parser entry point — delegates to the PyMuPDF pipeline."""
+
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+from rag_cut.models import Block
+from rag_cut.parsers.base import BaseParser
+from rag_cut.parsers.mineru_adapter import parse_pdf_with_mineru
+from rag_cut.parsers.pdf.noise_filter import filter_noise_blocks
+from rag_cut.parsers.pdf.pipeline import parse_pdf
+
+
+class PdfParser(BaseParser):
+    def parse(self, path: Path, assets_dir: Path) -> list[Block]:
+        engine = os.getenv("RAG_CUT_PDF_ENGINE", "auto").strip().lower()
+        if engine not in {"auto", "mineru", "pymupdf"}:
+            engine = "auto"
+
+        blocks: list[Block] | None = None
+        if engine in {"auto", "mineru"}:
+            blocks = parse_pdf_with_mineru(path, assets_dir)
+            if blocks is None and engine == "mineru":
+                raise RuntimeError("MinerU parsing failed or MinerU is not installed")
+
+        if blocks is None:
+            blocks = parse_pdf(path, assets_dir)
+
+        # filter_noise_blocks already includes TOC removal.
+        return filter_noise_blocks(blocks)