From 77a950cc32fc407df49293e4ef5eaaa7eda786ea Mon Sep 17 00:00:00 2001
From: Vit Novotny <witiko@mail.muni.cz>
Date: Sat, 26 Jun 2021 02:00:58 +0200
Subject: [PATCH] Fix an encoding error
---
scripts/common.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/scripts/common.py b/scripts/common.py
index 5821a26d..06c18339 100644
--- a/scripts/common.py
+++ b/scripts/common.py
@@ -696,7 +696,7 @@ def _read_page_languages_hocr(f):
if not content.strip(): # the file is empty
return dict()
html5_parser = etree.HTMLParser(huge_tree=True)
- xml_document = etree.fromstring(content, html5_parser)
+ xml_document = etree.fromstring(content.encode('utf-8'), html5_parser)
languages = defaultdict(lambda: 0.0)
--
GitLab