Merge pull request #27 from othmanalikhan-security/master

Added a Regex Definition for Saudi Arabian Passports

Author: 0x4f53

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",

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
-    
+