From 072aa6ce12c505ff28deef6d4e46963635a9100d Mon Sep 17 00:00:00 2001
From: Miro Mannino <miro.mannino@gmail.com>
Date: Wed, 16 Aug 2023 10:43:28 +0400
Subject: [PATCH] Updating clean_markup function to be compatible with
 Extractor.__init__()  and Extractor.clean_text()

---
 wikiextractor/clean.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/wikiextractor/clean.py b/wikiextractor/clean.py
index 3320c19a..0e03aa91 100644
--- a/wikiextractor/clean.py
+++ b/wikiextractor/clean.py
@@ -33,13 +33,12 @@ def clean_markup(markup, keep_links=False, ignore_headers=True):
     if not keep_links:
         ignoreTag('a')
 
-    extractor = Extractor(0, '', [])
+    extractor = Extractor(0, '', [], '', '')
 
     # returns a list of strings
     paragraphs = extractor.clean_text(markup,
                                       mark_headers=True,
-                                      expand_templates=False,
-                                      escape_doc=True)
+                                      expand_templates=False)
     resetIgnoredTags()
 
     if ignore_headers: