From c7345cb3a3dd85f372e9b51696b76b3f15e26dd9 Mon Sep 17 00:00:00 2001
From: Stefano Pigozzi <me@steffo.eu>
Date: Thu, 2 Feb 2023 04:12:56 +0100
Subject: [PATCH] In Potts' tokenizer, use `html.entities` instead of
 `htmlentitydefs`

---
 unimore_bda_6/vendor/potts.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/unimore_bda_6/vendor/potts.py b/unimore_bda_6/vendor/potts.py
index 2178c43..5b0c8d9 100644
--- a/unimore_bda_6/vendor/potts.py
+++ b/unimore_bda_6/vendor/potts.py
@@ -3,6 +3,7 @@ This file is a vendored version of `Christopher Potts' tokenizer <http://sentime
 
 It has been altered to be used with Python 3.10, but the code is mostly the same.
 
+=========================
 Original module docstring
 =========================
 
@@ -51,7 +52,7 @@ __email__ = "See the author's website"
 ######################################################################
 
 import re
-import htmlentitydefs
+import html.entities
 
 ######################################################################
 # The following strings are components in the regular expression
@@ -204,7 +205,7 @@ class Tokenizer:
         for ent in ents:
             entname = ent[1:-1]
             try:            
-                s = s.replace(ent, unichr(htmlentitydefs.name2codepoint[entname]))
+                s = s.replace(ent, unichr(html.entities.name2codepoint[entname]))
             except:
                 pass                    
             s = s.replace(amp, " and ")