From 819d6d51b9998d7ac1fcf834f36f0692ec51a10f Mon Sep 17 00:00:00 2001
From: OneNewDev <onenewdev@mailbox.org>
Date: Sat, 28 May 2022 15:34:41 +0200
Subject: [PATCH] unquote url

---
 tagger.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tagger.py b/tagger.py
index 299d084..0299aa1 100644
--- a/tagger.py
+++ b/tagger.py
@@ -2,6 +2,7 @@ import json
 import re
 from dataclasses import dataclass
 from html.parser import HTMLParser
+from urllib.parse import unquote_plus
 from pathlib import Path
 
 from exclude import EXCLUDED_WORDS
@@ -33,6 +34,7 @@ class FileScanner(HTMLParser):
         words_with_usage = {}
         words = []
         for text in self.texte:
+            text = unquote_plus(text)
             words += re.split(r'[ /\-_#\n.?=]', text)
         print(f'\nFile {self.file.parent.name} contains {len(words)} words')
         title_words = set(self.file.parent.name.split('-'))