Common word filters are a go

naughty_words/__init__.py

@@ -73,12 +73,7 @@ def run_filters(self, text, **kwargs):
             cur_text, cur_context = pre.process(cur_text, cur_context)
 
         # TODO: Loop through, run all filters
-        matches = []
+        matches = set()
         for filter in self._filters:
-            if kwargs['only_first']:
-                match = filter.filter(cur_text, cur_context, **kwargs)
-                if match is not []:
-                    return match
-            else:
-                matches.extend(filter.filter(cur_text, cur_context, **kwargs))
-        return matches if matches is not [] else None
+            matches = matches.union(set(filter.filter(cur_text, cur_context, **kwargs)))
+        return matches

naughty_words/defaults.py

@@ -18,4 +18,18 @@ def has_profanity(text, additional=None, blacklist=None, profanities=None):
     naughty_words = NaughtyWords(preprocessors=[EmptyPreprocessor()],
                                  filters=[CommonSubstitutions()],
                                  profanities=profanities)
-    return naughty_words.run_filters(text, only_first=True) is not None
+    return len(naughty_words.run_filters(text, only_first=True)) != 0
+
+
+def get_all_profanity(text, additional=None, blacklist=None, profanities=None):
+    if not profanities:
+        global profanity_list
+        profanities = profanity_list
+    if additional:
+        profanities = list(set(profanities).update(set(additional)))
+    if blacklist:
+        profanities = list(set(profanities).difference(set(blacklist)))
+    naughty_words = NaughtyWords(preprocessors=[EmptyPreprocessor()],
+                                 filters=[CommonSubstitutions()],
+                                 profanities=profanities)
+    return naughty_words.run_filters(text, only_first=False)

naughty_words/filters/common_substitutions.py

@@ -32,12 +32,15 @@ def filter(self, text: str,
         for profanity in profanities:
             # TODO add solidified case for stopping emoji
             alpha_num_word = re.sub('\W', '', profanity)
+            if alpha_num_word is '':
+                continue
             pattern = self.profanity_expression(alpha_num_word)
             if re.search(pattern, text):
                 if raise_on_match:
                     raise ProfanityException()
                 elif only_first:
-                    return profanity
+                    matches.append(profanity)
+                    return matches
                 else:
                     matches.append(profanity)
         return matches

naughty_words/wordlists/profanities.txt

@@ -1602,4 +1602,5 @@ pindick
 mutha fukkah
 niggardliness
 fister
-beaner
+beaner
+🖕

tests/test_filters.py

@@ -3,5 +3,11 @@
 
 from naughty_words.defaults import has_profanity
 
+
 def test_default_filter_no_match():
-    assert has_profanity("No profanity here") is False
+    assert has_profanity("No ducking profanity here") is False
+
+
+def test_default_filter_has_match():
+    assert has_profanity("You fucking know there's profanity here") is True
+