Fix: manual parser with mineru (#11336)

### What problem does this PR solve?

Fix: manual parser with mineru #11320
Fix: missing parameter in mineru #11334
Fix: add outlines parameter for pdf parsers

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

rag/app/manual.py

@@ -216,6 +216,30 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             **kwargs
         )
 
+        def _normalize_section(section):
+            # pad section to length 3: (txt, sec_id, poss)
+            if len(section) == 1:
+                section = (section[0], "", [])
+            elif len(section) == 2:
+                section = (section[0], "", section[1])
+            elif len(section) != 3:
+                raise ValueError(f"Unexpected section length: {len(section)} (value={section!r})")
+
+            txt, sec_id, poss = section
+            if isinstance(poss, str):
+                poss = pdf_parser.extract_positions(poss)
+                first = poss[0]          # tuple: ([pn], x1, x2, y1, y2)
+                pn = first[0]           
+
+                if isinstance(pn, list):
+                    pn = pn[0]           # [pn] -> pn
+                    poss[0] = (pn, *first[1:])
+
+            return (txt, sec_id, poss)
+        
+
+        sections = [_normalize_section(sec) for sec in sections]
+
         if not sections and not tbls:
             return []
 

rag/app/naive.py

@@ -70,6 +70,7 @@ def by_mineru(filename, binary=None, from_page=0, to_page=100000, lang="Chinese"
         callback=callback,
         output_dir=os.environ.get("MINERU_OUTPUT_DIR", ""),
         backend=os.environ.get("MINERU_BACKEND", "pipeline"),
+        server_url=os.environ.get("MINERU_SERVER_URL", ""),
         delete_output=bool(int(os.environ.get("MINERU_DELETE_OUTPUT", 1))),
     )
     return sections, tables, pdf_parser