From 6b7989b4b40e8d57e36e13b329a183652e777676 Mon Sep 17 00:00:00 2001
From: NeedmeFordev <124189514+spider-yamet@users.noreply.github.com>
Date: Wed, 1 Apr 2026 23:12:27 -0700
Subject: [PATCH] Add file type validation (#13802)

### What problem does this PR solve?

This PR fixes WebDAV sync behavior for unsupported file types
([#13795](https://github.com/infiniflow/ragflow/issues/13795)).

Previously, the WebDAV connector selected files primarily by modified
time (and size threshold) and could still pass unsupported extensions
into the download/document-generation path. This caused unnecessary
processing and inconsistent behavior compared with connectors that
validate file type earlier.

This change adds extension validation in two places:

1. **Early filter during recursive listing** to skip unsupported files
before they enter the download flow.
2. **Defensive filter before download/document creation** to prevent
unsupported files from being processed if any listing edge case slips
through.

It also wires `allow_images` into the WebDAV sync path so image
extension handling follows connector policy.

Scope is intentionally limited to WebDAV for a focused bug-fix PR.

### Type of change

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

### How was this tested?

- Manual verification with mixed file types under the configured WebDAV
path:
  - supported: `.pdf`, `.txt`, `.md`
  - unsupported: `.exe`, `.bin`, `.dat`
- Triggered full sync and polling sync.
- Confirmed unsupported files are skipped before download.
- Confirmed supported files are still indexed normally.
- Confirmed image handling follows `allow_images` setting.

Fixes: #13795
---
 common/data_source/webdav_connector.py | 22 +++++++++++++++++++++-
 rag/svr/sync_data_source.py            |  1 +
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/common/data_source/webdav_connector.py b/common/data_source/webdav_connector.py
index ec06a64e19..b860c0b61a 100644
--- a/common/data_source/webdav_connector.py
+++ b/common/data_source/webdav_connector.py
@@ -8,6 +8,7 @@ from webdav4.client import Client as WebDAVClient
 
 from common.data_source.utils import (
     get_file_ext,
+    is_accepted_file_ext,
 )
 from common.data_source.config import DocumentSource, INDEX_BATCH_SIZE, BLOB_STORAGE_SIZE_THRESHOLD
 from common.data_source.exceptions import (
@@ -16,7 +17,7 @@ from common.data_source.exceptions import (
     CredentialExpiredError,
     InsufficientPermissionsError
 )
-from common.data_source.interfaces import LoadConnector, PollConnector
+from common.data_source.interfaces import LoadConnector, OnyxExtensionType, PollConnector
 from common.data_source.models import Document, SecondsSinceUnixEpoch, GenerateDocumentsOutput
 
 
@@ -49,6 +50,16 @@ class WebDAVConnector(LoadConnector, PollConnector):
         self._allow_images: bool | None = None
         self.size_threshold: int | None = BLOB_STORAGE_SIZE_THRESHOLD
 
+    def _build_extension_type(self) -> OnyxExtensionType:
+        extension_type = OnyxExtensionType.Plain | OnyxExtensionType.Document
+        if bool(self._allow_images):
+            extension_type |= OnyxExtensionType.Multimedia
+        return extension_type
+
+    def _is_supported_file(self, file_name: str) -> bool:
+        file_ext = get_file_ext(file_name)
+        return is_accepted_file_ext(file_ext, self._build_extension_type())
+
     def set_allow_images(self, allow_images: bool) -> None:
         """Set whether to process images"""
         logging.info(f"Setting allow_images to {allow_images}.")
@@ -129,6 +140,11 @@ class WebDAVConnector(LoadConnector, PollConnector):
                         continue
                 else:
                     try:
+                        file_name = os.path.basename(item_path)
+                        if not self._is_supported_file(file_name):
+                            logging.debug(f"Skipping file {item_path} due to unsupported extension.")
+                            continue
+
                         modified_time = item.get('modified')
                         if modified_time:
                             if isinstance(modified_time, datetime):
@@ -194,6 +210,10 @@ class WebDAVConnector(LoadConnector, PollConnector):
         batch: list[Document] = []
         for file_path, file_info in files:
             file_name = os.path.basename(file_path)
+
+            if not self._is_supported_file(file_name):
+                logging.debug(f"Skipping file {file_path} due to unsupported extension.")
+                continue
             
             size_bytes = file_info.get('size', 0)
             if (
diff --git a/rag/svr/sync_data_source.py b/rag/svr/sync_data_source.py
index 1e95c4b166..203cf862d5 100644
--- a/rag/svr/sync_data_source.py
+++ b/rag/svr/sync_data_source.py
@@ -712,6 +712,7 @@ class WebDAV(SyncBase):
             base_url=self.conf["base_url"],
             remote_path=self.conf.get("remote_path", "/")
         )
+        self.connector.set_allow_images(self.conf.get("allow_images", False))
         self.connector.load_credentials(self.conf["credentials"])
 
         logging.info(f"Task info: reindex={task['reindex']}, poll_range_start={task['poll_range_start']}")