From 060f600f2da9ceda353ebf6ccf2d99a08f5c404b Mon Sep 17 00:00:00 2001
From: xxyzz <gitpull@protonmail.com>
Date: Fri, 13 Oct 2023 10:06:23 +0800
Subject: [PATCH 1/2] Fix "A-z" regex range overlaps with "a-z" error

---
 src/wiktextract/clean.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/wiktextract/clean.py b/src/wiktextract/clean.py
index 1556eec0..5b3409aa 100644
--- a/src/wiktextract/clean.py
+++ b/src/wiktextract/clean.py
@@ -1438,7 +1438,7 @@ def repl_1_syntaxhighlight(m):
         )
         title = re.sub(r"(?s)\[\[\s*:?([^]|#<>]+?)\s*(#[^][|<>]*?)?\]\]",
                        repl_1, title)
-        title = re.sub(r"(?s)\[\[\s*(([a-zA-z0-9]+)\s*:)?\s*([^][#|<>]+?)"
+        title = re.sub(r"(?s)\[\[\s*(([a-zA-Z0-9]+)\s*:)?\s*([^][#|<>]+?)"
                        r"\s*(#[^][|]*?)?\|?\]\]",
                        repl_link, title)
         title = re.sub(r"(?s)\[\[\s*([^][|<>]+?)\s*\|"

From 01ba40afc08ab0275551ec84b7c1f213defce755 Mon Sep 17 00:00:00 2001
From: xxyzz <gitpull@protonmail.com>
Date: Fri, 13 Oct 2023 14:28:40 +0800
Subject: [PATCH 2/2] Fix regex backtracking alert

---
 src/wiktextract/clean.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/wiktextract/clean.py b/src/wiktextract/clean.py
index 5b3409aa..8b1e9fec 100644
--- a/src/wiktextract/clean.py
+++ b/src/wiktextract/clean.py
@@ -1376,11 +1376,11 @@ def repl_1_syntaxhighlight(m):
     # Remove <sup> with previewonly class (generated e.g. by {{taxlink|...}})
     title = re.sub(r'(?si)<sup\b[^>]*?\bclass="[^"<>]*?'
                    r'\bpreviewonly\b[^>]*?>'
-                   r'((<[^<>]>[^<>]*</[^<>]*>)|.)*?</sup\s*>',
+                   r'.+?</sup\s*>',
                    "", title)
     # Remove <strong class="error">...</strong>
     title = re.sub(r'(?si)<strong\b[^>]*?\bclass="[^"]*?\berror\b[^>]*?>'
-                   r'((<.*?</.[^>]>)|.)*?</strong\s*>',
+                   r'.+?</strong\s*>',
                    "", title)
     # Change <div> and </div> to newlines.  Ditto for tr, li, table, dl, ul, ol
     title = re.sub(r"(?si)</?(div|tr|li|table|dl|ul|ol)\b[^>]*>",