fix: harden edge cases in cloud upload, local doc_type, and PDF utilities

- cloud.py: replace bare resp['doc_id'] with .get() + CloudAPIError
- local.py: case-insensitive doc_type comparison for .PDF extensions
- utils.py: add else branch to get_pdf_name for non-str/BytesIO inputs
- utils.py: raise ValueError in get_page_tokens when PyMuPDF path invalid

pageindex/backend/cloud.py

@@ -214,7 +214,9 @@ class CloudBackend:
         with open(file_path, "rb") as f:
             resp = self._request("POST", "/doc/", files={"file": f}, data=data)
 
-        doc_id = resp["doc_id"]
+        doc_id = resp.get("doc_id")
+        if not doc_id:
+            raise CloudAPIError("Cloud API upload response missing 'doc_id'")
 
         # Poll until indexing completes. The cloud API signals readiness via
         # status == "completed"; retrieval_ready is not a reliable indicator.

pageindex/backend/local.py

@@ -230,7 +230,7 @@ class LocalBackend:
         # stripped (if_add_node_text=False, the default). Reachable only for a
         # custom StorageEngine that doesn't cache pages (the built-in
         # SQLiteStorage always does).
-        if doc["doc_type"] == "pdf":
+        if doc["doc_type"].lower() == "pdf":
             return get_pdf_page_content(doc["file_path"], page_nums)
         else:
             parser = self._resolve_parser(doc["file_path"])

pageindex/index/utils.py

@@ -748,6 +748,8 @@ def get_pdf_name(pdf_path):
         meta = pdf_reader.metadata
         pdf_name = meta.title if meta and meta.title else 'Untitled'
         pdf_name = sanitize_filename(pdf_name)
+    else:
+        pdf_name = os.path.basename(str(pdf_path))
     return pdf_name
 
 
@@ -820,6 +822,8 @@ def get_page_tokens(pdf_path, model=None, pdf_parser="PyPDF2"):
             doc = pymupdf.open(stream=pdf_stream, filetype="pdf")
         elif isinstance(pdf_path, str) and os.path.isfile(pdf_path) and pdf_path.lower().endswith(".pdf"):
             doc = pymupdf.open(pdf_path)
+        else:
+            raise ValueError(f"Invalid pdf_path for PyMuPDF: {pdf_path!r}")
         page_list = []
         for page in doc:
             page_text = page.get_text()