From 1213013ac230e09b728581d7e00174e31f44fbb8 Mon Sep 17 00:00:00 2001
From: OthmanEmpire <oz.alikhan@gmail.com>
Date: Tue, 21 Nov 2023 11:35:58 +0300
Subject: [PATCH 1/2] added regex for saudi arabian passports

---
 definitions.json | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/definitions.json b/definitions.json
index 2633140..6728686 100644
--- a/definitions.json
+++ b/definitions.json
@@ -141,6 +141,16 @@
          "<<<<"
       ]
    },
+   "Saudi Arabian Passport": {
+      "regex":"(?:P<SAU)(?:[A-Z0-9<].+)",
+      "region":"Saudi Arabia",
+      "keywords":[
+         "Passport",
+         "Saudi Arabia",
+         "SAU",
+         "<<<<"
+      ]
+   },
    "Nebraska Driver's License": {
       "regex":"[A-Z]{1}[0-9]{9,11}",
       "region":"United States",

From 6b415b6121d40de572280035a205f1c8e1ab5482 Mon Sep 17 00:00:00 2001
From: OthmanEmpire <oz.alikhan@gmail.com>
Date: Tue, 21 Nov 2023 12:44:09 +0300
Subject: [PATCH 2/2] Fixed bug where definitions.json would not open properly
 on Windows

---
 text_utils.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/text_utils.py b/text_utils.py
index 6d27239..9d1fe42 100644
--- a/text_utils.py
+++ b/text_utils.py
@@ -39,7 +39,7 @@ def string_tokenizer(text):
 def similarity(a, b): return difflib.SequenceMatcher(None, a, b).ratio() * 100
 
 def get_regexes():
-    with open('definitions.json') as json_file:
+    with open('definitions.json', "r", encoding='utf-8') as json_file:
         _rules = json.load(json_file)
         return _rules
 
@@ -133,4 +133,4 @@ def keywords_classify_pii(rules, intelligible_text_list):
                     ) > 80: scores[key] += 1
 
     return scores
-    
\ No newline at end of file
+