From cee2d548c6dd9cd19aae3f91e624191ab64179c1 Mon Sep 17 00:00:00 2001
From: OneNewDev <onenewdev@mailbox.org>
Date: Sat, 28 May 2022 19:39:24 +0200
Subject: [PATCH] add further comments

---
 tagger.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tagger.py b/tagger.py
index 03c18f7..8d094e3 100644
--- a/tagger.py
+++ b/tagger.py
@@ -7,12 +7,14 @@ from urllib.parse import unquote_plus
 
 from exclude import EXCLUDED_WORDS
 
+# Einstellungen
 SOURCE_DIR = Path('data')
 SOURCE_FILENAME = 'index.txt'
 OUTPUT_FILE = 'tags.json'
 TAGS_PER_ARTICLE = 5
 JSON_INDENT = 2
 
+# Wegen Performance vordefinierte Variablen
 _UPPER_CHECK = re.compile(r'[A-Z]')
 
 
@@ -41,9 +43,11 @@ class FileScanner(HTMLParser):
             text = unquote_plus(text)
             # Textteile in einzelne Wörter aufteilen
             words += re.split(r'[ /\-_#\n.?=]', text)
-        print(f'\nFile {self.file.parent.name} contains {len(words)} words')
+        # Die Anzahl, der Wörter in der aktuellen Datei, auf der Konsole ausgeben
+        title = self.file.parent.name
+        print(f'\nFile {title} contains {len(words)} words')
         # Titel in einzelne Wörter aufteilen
-        title_words = set(self.file.parent.name.split('-'))
+        title_words = set(title.split('-'))
         for word in words:
             # Verschiedene Zeichen vom Anfang und Ende der Wörter entfernen.
             tag_name = word.strip(".,:;!\"'<>()")