From a884974a9c054fcc8c4b9ce9525921ba0e994788 Mon Sep 17 00:00:00 2001
From: lordwelch <timmy@narnian.us>
Date: Sun, 26 Sep 2021 17:06:30 -0700
Subject: [PATCH] Improve issue identification

Move title sanitizing code to utils module
Update issue identifier to compare sanitized names
---
 comicapi/utils.py | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/comicapi/utils.py b/comicapi/utils.py
index f82f99a..05bacc2 100644
--- a/comicapi/utils.py
+++ b/comicapi/utils.py
@@ -21,6 +21,7 @@ import re
 import platform
 import locale
 import codecs
+import unicodedata
 
 
 class UtilsVars:
@@ -151,6 +152,21 @@ def removearticles(text):
     return newText
 
 
+def sanitize_title(text):
+    # normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
+    # this will probably cause issues with titles in other character sets e.g. chinese, japanese
+    text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore').decode('ascii')
+    # comicvine keeps apostrophes a part of the word
+    text = text.replace("'", "")
+    text = text.replace("\"", "")
+    # comicvine ignores punctuation and accents
+    text = re.sub(r'[^A-Za-z0-9]+',' ', text)
+    # remove extra space and articles and all lower case
+    text = removearticles(text).lower().strip()
+
+    return text
+
+
 def unique_file(file_name):
     counter = 1
     # returns ('/path/file', '.ext')