From 24946ec4e3eb7757d88cdcb6afff03a149429e33 Mon Sep 17 00:00:00 2001
From: "Val Neekman (AvidCoder)" <un33kvu@gmail.com>
Date: Thu, 25 Jan 2024 11:24:52 -0500
Subject: [PATCH] pre normalize

---
 CHANGELOG.md           | 5 +++--
 slugify/__version__.py | 2 +-
 slugify/slugify.py     | 9 ++++++---
 test.py                | 4 ++++
 4 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 395e538..015c5bb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,7 +1,8 @@
 ## Work in progress
 
-- Added typing to API and expose `py.typed`.
-- Formally support 3.12
+## 8.0.2
+
+- Normalize text before converting to unicode. (chuckyblack - thx)
 
 ## 8.0.1
 
diff --git a/slugify/__version__.py b/slugify/__version__.py
index a558d9b..dbbff9f 100644
--- a/slugify/__version__.py
+++ b/slugify/__version__.py
@@ -5,4 +5,4 @@
 __url__ = 'https://github.com/un33k/python-slugify'
 __license__ = 'MIT'
 __copyright__ = 'Copyright 2022 Val Neekman @ Neekware Inc.'
-__version__ = '8.0.1'
+__version__ = '8.0.2'
diff --git a/slugify/slugify.py b/slugify/slugify.py
index 21bdaeb..9242e3e 100644
--- a/slugify/slugify.py
+++ b/slugify/slugify.py
@@ -118,8 +118,11 @@ def slugify(
     # replace quotes with dashes - pre-process
     text = QUOTE_PATTERN.sub(DEFAULT_SEPARATOR, text)
 
-    # decode unicode
-    if not allow_unicode:
+    # normalize text, convert to unicode if required
+    if allow_unicode:
+        text = unicodedata.normalize('NFKC', text)
+    else:
+        text = unicodedata.normalize('NFKD', text)
         text = unidecode.unidecode(text)
 
     # ensure text is still in unicode
@@ -144,7 +147,7 @@ def slugify(
         except Exception:
             pass
 
-    # translate
+    # re normalize text
     if allow_unicode:
         text = unicodedata.normalize('NFKC', text)
     else:
diff --git a/test.py b/test.py
index 931f38f..995affa 100644
--- a/test.py
+++ b/test.py
@@ -36,6 +36,10 @@ def test_phonetic_conversion_of_eastern_scripts(self):
         self.assertEqual(r, "ying-shi-ma")
 
     def test_accented_text(self):
+        txt = '𝐚́́𝕒́àéé'
+        r = slugify(txt)
+        self.assertEqual(r, "aaaee")
+    
         txt = 'C\'est déjà l\'été.'
         r = slugify(txt)
         self.assertEqual(r, "c-est-deja-l-ete")