From a674338c219f2e266e8e6f300dbd257a0f960c7a Mon Sep 17 00:00:00 2001
From: buua436 <66937541+buua436@users.noreply.github.com>
Date: Thu, 27 Nov 2025 17:54:49 +0800
Subject: [PATCH] Fix: remove garbage filtering rules (#11567)

### What problem does this PR solve?
change:

remove garbage filtering rules

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 deepdoc/vision/layout_recognizer.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/deepdoc/vision/layout_recognizer.py b/deepdoc/vision/layout_recognizer.py
index 8068cbc07..5b79e2bf5 100644
--- a/deepdoc/vision/layout_recognizer.py
+++ b/deepdoc/vision/layout_recognizer.py
@@ -17,7 +17,7 @@
 import logging
 import math
 import os
-import re
+# import re
 from collections import Counter
 from copy import deepcopy
 
@@ -62,8 +62,9 @@ class LayoutRecognizer(Recognizer):
 
     def __call__(self, image_list, ocr_res, scale_factor=3, thr=0.2, batch_size=16, drop=True):
         def __is_garbage(b):
-            patt = [r"^•+$", "^[0-9]{1,2} / ?[0-9]{1,2}$", r"^[0-9]{1,2} of [0-9]{1,2}$", "^http://[^ ]{12,}", "\\(cid *: *[0-9]+ *\\)"]
-            return any([re.search(p, b["text"]) for p in patt])
+            return False
+            # patt = [r"^•+$", "^[0-9]{1,2} / ?[0-9]{1,2}$", r"^[0-9]{1,2} of [0-9]{1,2}$", "^http://[^ ]{12,}", "\\(cid *: *[0-9]+ *\\)"]
+            # return any([re.search(p, b["text"]) for p in patt])
 
         if self.client:
             layouts = self.client.predict(image_list)