DRAFT: Bug Fixes (#55)

* fix: key errors related to name splitting

linkedin2username.py

@@ -87,12 +87,20 @@ def clean_name(name):
         name = re.sub("[ß]", 'ss', name)
         name = re.sub("[ñ]", 'n', name)
 
+        # Get rid of all things in parenthesis. Lots of people put various credentials, etc
+        name = re.sub(r'\([^()]*\)', '', name)
+
         # The lines below basically trash anything weird left over.
         # A lot of users have funny things in their names, like () or ''
         # People like to feel special, I guess.
         allowed_chars = re.compile('[^a-zA-Z -]')
         name = allowed_chars.sub('', name)
 
+        # Next, we get rid of common titles. Thanks ChatGPT for the help.
+        titles = ['mr', 'miss', 'mrs', 'phd', 'prof', 'professor', 'md', 'dr', 'mba']
+        pattern = "\\b(" + "|".join(titles) + ")\\b"
+        name = re.sub(pattern, '', name)
+
         # The line below tries to consolidate white space between words
         # and get rid of leading/trailing spaces.
         name = re.sub(r'\s+', ' ', name).strip()
@@ -112,7 +120,7 @@ def split_name(name):
         if len(parsed) > 2:
             split_name = {'first': parsed[0], 'second': parsed[-2], 'last': parsed[-1]}
         else:
-            split_name = {'first': parsed[0], 'last': parsed[-1]}
+            split_name = {'first': parsed[0], 'second': '', 'last': parsed[-1]}
 
         return split_name
 
@@ -121,7 +129,7 @@ def f_last(self):
         names = set()
         names.add(self.name['first'][0] + self.name['last'])
 
-        if len(self.name) == 3:
+        if self.name['second']:
             names.add(self.name['first'][0] + self.name['second'])
 
         return names
@@ -131,7 +139,7 @@ def f_dot_last(self):
         names = set()
         names.add(self.name['first'][0] + '.' + self.name['last'])
 
-        if len(self.name) == 3:
+        if self.name['second']:
             names.add(self.name['first'][0] + '.' + self.name['second'])
 
         return names
@@ -141,7 +149,7 @@ def last_f(self):
         names = set()
         names.add(self.name['last'] + self.name['first'][0])
 
-        if len(self.name) == 3:
+        if self.name['second']:
             names.add(self.name['second'] + self.name['first'][0])
 
         return names
@@ -151,7 +159,7 @@ def first_dot_last(self):
         names = set()
         names.add(self.name['first'] + '.' + self.name['last'])
 
-        if len(self.name) == 3:
+        if self.name['second']:
             names.add(self.name['first'] + '.' + self.name['second'])
 
         return names
@@ -161,7 +169,7 @@ def first_l(self):
         names = set()
         names.add(self.name['first'] + self.name['last'][0])
 
-        if len(self.name) == 3:
+        if self.name['second']:
             names.add(self.name['first'] + self.name['second'][0])
 
         return names
@@ -608,7 +616,6 @@ def do_loops(session, company_id, outer_loops, args):
                 new_names += len(found_employees)
                 employee_list.extend(found_employees)
 
-
                 sys.stdout.write(f"    [*] Added {str(new_names)} new names. "
                                  f"Running total: {str(len(employee_list))}"
                                  "              \r")

tests/test_linkedin2username.py

@@ -7,7 +7,7 @@
     1: "John Smith",
     2: "John Davidson-Smith",
     3: "John-Paul Smith-Robinson",
-    4: "José Gonzáles"
+    4: "José Gonzáles",
 }
 
 
@@ -123,6 +123,15 @@ def test_clean_name():
     mutator = NameMutator("xxx")
     assert mutator.clean_name("  🙂Ànèôõö    ßï🙂  ") == "aneooo ssi"
 
+    name = "Dr. Hannibal Lecter, PhD."
+    assert mutator.clean_name(name) == "hannibal lecter"
+
+    name = "Mr. Fancy Pants MD, PhD, MBA"
+    assert mutator.clean_name(name) == "fancy pants"
+
+    name = "Mr. Cert Dude (OSCP, OSCE)"
+    assert mutator.clean_name(name) == "cert dude"
+
 
 def test_split_name():
     mutator = NameMutator("xxx")
@@ -131,7 +140,7 @@ def test_split_name():
     assert mutator.split_name(name) == {"first": "madonna", "second": "wayne", "last": "gacey"}
 
     name = "twiggy ramirez"
-    assert mutator.split_name(name) == {"first": "twiggy", "last": "ramirez"}
+    assert mutator.split_name(name) == {"first": "twiggy", "second": "", "last": "ramirez"}
 
     name = "brian warner is marilyn manson"
     assert mutator.split_name(name) == {"first": "brian", "second": "marilyn", "last": "manson"}