From 49fdf4edd9b5c0eab0e8baa7417bce74c4a6b81e Mon Sep 17 00:00:00 2001
From: Ivan Gabaldon <igabaldon@inetol.net>
Date: Fri, 27 Jun 2025 17:52:12 +0200
Subject: [PATCH] [fix] utils: truncated result (#4949)

Make sure to prase everything before returning.

Related: \
```
FAIL: test_html_to_text (tests.unit.test_utils.TestUtils.test_html_to_text)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/runner/work/searxng/searxng/tests/unit/test_utils.py", line 53, in test_html_to_text
    self.assertEqual(utils.html_to_text(r"regexp: (?<![a-zA-Z]"), "regexp: (?<![a-zA-Z]")
    ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: 'regexp: (?' != 'regexp: (?<![a-zA-Z]'
- regexp: (?
+ regexp: (?<![a-zA-Z]
```
---
 searx/utils.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/searx/utils.py b/searx/utils.py
index 3c60851fa..7b7cd8f5d 100644
--- a/searx/utils.py
+++ b/searx/utils.py
@@ -161,9 +161,11 @@ def html_to_text(html_str: str) -> str:
     s = _HTMLTextExtractor()
     try:
         s.feed(html_str)
+        s.close()
     except AssertionError:
         s = _HTMLTextExtractor()
         s.feed(escape(html_str, quote=True))
+        s.close()
     except _HTMLTextExtractorException:
         logger.debug("HTMLTextExtractor: invalid HTML\n%s", html_str)
     return s.get_text()