korcen 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

korcen/korcen.py

@@ -137,7 +137,7 @@ FALSE_POSITIVE_PATTERNS_GENERAL = [
     '줫습니다', '줫음', '줫잖아', '줫겠지', '쫒아', '쫒는', '쫒기다', '쫒기라', '쫒기로',
     '쫒기를', '쫒기며', '쫒기는', '쫒기나', '쫒겨', '쫒겻', '쫒겼', '쫒았', '쫒다', '쫒고',
     '줫는', '줫어', '줬는', '줫군', '줬다', '줬어', '천조', '쫒기', '해줫더니', '줫다', '내쫒은',
-    '내쫒다', '좇아',
+    '내쫒다', '좇아', "날개",
     'ㅡ'
 ]
 FALSE_POSITIVE_PATTERNS_MINOR = [
@@ -162,7 +162,7 @@ FALSE_POSITIVE_PATTERNS_SEXUAL = [
     '빨간색', '초록색', '보라색', '청색', '핑크색', '남색', '검은색', '하양색', '주황색', '연두색',
     '스공', '스시', '스키장', '스킨', '스킬', '스틸', '스탑', '스트레스', '해야', '카시야스', '야스톤', '유니섹스', '스튜디오',
     '위대한', '소유자', '작업자', '자기위로', '위대하지', '암살자', '학자',
-    'freenude',
+    'freenude', "상자"
 ]
 FALSE_POSITIVE_PATTERNS_BELITTLE = [
     '려운지', '무서운지', '라운지', '운지법', '싸운지', '운지버섯', '운지린다', '깔보다', '깔보시',
@@ -356,7 +356,7 @@ def build_flexible_regex(pattern_in_processed_text: str):
 
     reverse_multi_map = {}
     for k, v in MULTI_CHAR_REPLACEMENTS.items():
-         reverse_multi_map.setdefault(v.lower(), set()).add(k)
+        reverse_multi_map.setdefault(v.lower(), set()).add(k)
 
     for char in pattern_in_processed_text:
         char_lower = char.lower()
@@ -456,7 +456,7 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
     if level == 'english' and BETTER_PROFANITY_LOADED:
         fp_regex_english = get_false_positive_regex('english')
         if fp_regex_english:
-             text_for_better_profanity = fp_regex_english.sub('', text_for_better_profanity)
+            text_for_better_profanity = fp_regex_english.sub('', text_for_better_profanity)
 
         text_for_better_profanity = text_for_better_profanity.replace("*", "")
 
@@ -467,12 +467,12 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
             censored_words_in_segment = re.findall(r'\b\w*▩+\w*\b', censored_text.lower())
 
             if censored_words_in_segment:
-                 original_words_split = text_for_better_profanity.split()
-                 censored_words_split = censored_text.split()
-                 for ow, cw in zip(original_words_split, censored_words_split):
-                      if '▩' in cw:
-                           detected_word_approx = ow
-                           break
+                original_words_split = text_for_better_profanity.split()
+                censored_words_split = censored_text.split()
+                for ow, cw in zip(original_words_split, censored_words_split):
+                    if '▩' in cw:
+                        detected_word_approx = ow
+                        break
 
             if detected_word_approx:
                 normalized_detected_word = normalize_for_custom_comparison(detected_word_approx)
@@ -550,7 +550,7 @@ def highlight_profanity(text: str, id: int = None, level: str = 'general', highl
 
     if level.lower() == 'all':
         levels = ['general', 'minor', 'sexual', 'belittle', 'race', 'parent', 
-                  'special', 'politics']
+                'special', 'politics']
         
         if BETTER_PROFANITY_LOADED:
             levels.append('english')
@@ -625,7 +625,7 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
             return include_match.group(0)
 
     if processed_text in EXACT_MATCH_PROFANITY and level == 'general':
-         pass
+        pass
 
     fp_regex = get_false_positive_regex(level)
     text_without_false_positives = fp_regex.sub('', processed_text) if fp_regex else processed_text
@@ -641,14 +641,14 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
                 detected_word = None
                 for ow, cw in zip(original_words, censored_words):
                     if '▩' in cw:
-                         detected_word = ow.lower()
-                         break
+                        detected_word = ow.lower()
+                        break
 
                 if detected_word:
                     normalized_detected_word = normalize_for_custom_comparison(detected_word)
                     for exclude_regex in CUSTOM_EXCLUDE_REGEXES:
-                         if exclude_regex.fullmatch(normalized_detected_word):
-                             return None
+                        if exclude_regex.fullmatch(normalized_detected_word):
+                            return None
                     return detected_word
 
                 fallback_pattern = "english_profanity_detected"
@@ -678,7 +678,7 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
         normalized_detected_profanity = normalize_for_custom_comparison(detected_profanity_string)
         for exclude_regex in CUSTOM_EXCLUDE_REGEXES:
             if exclude_regex.fullmatch(normalized_detected_profanity):
-                 return None
+                return None
 
         return detected_profanity_string
 
@@ -686,7 +686,7 @@ def check_and_report_profanity_pattern(text: str, level: str = 'general'):
         normalized_processed_text = normalize_for_custom_comparison(processed_text)
         for exclude_regex in CUSTOM_EXCLUDE_REGEXES:
             if exclude_regex.fullmatch(normalized_processed_text):
-                 return None
+                return None
         return processed_text
 
     return None

{korcen-1.0.0.dist-info → korcen-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: korcen
-Version: 1.0.0
+Version: 1.0.1
 Summary: 한국어 비속어 검열
 Home-page: https://github.com/KR-korcen/korcen
 Author: Tanat

{korcen-1.0.0.dist-info → korcen-1.0.1.dist-info}/RECORD

@@ -5,14 +5,14 @@ korcen/chinese.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/english.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/general.py,sha256=mGX9Sw-z9nT0hNYoPOPxD68dIi0nlhRnfqnUxLF3rLI,25595
 korcen/japanese.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-korcen/korcen.py,sha256=1e5SrP-uFXxzgilBOa6x5DOXB4iOt0Pn7QvOTS6T5Gk,64223
+korcen/korcen.py,sha256=7xJSNNGNXro0IsSZMByXC0GQq23NaZDTVjbL405P_kU,64220
 korcen/minor.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/parent.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/politics.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/race.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/sexual.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 korcen/special.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-korcen-1.0.0.dist-info/METADATA,sha256=lUyJWDekepPANXIS8HyXDwlrjPIahBrLMqPfPKdVrwE,465
-korcen-1.0.0.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-korcen-1.0.0.dist-info/top_level.txt,sha256=2LtNKXroHMOGgMokwiUPWwsJt5kmJ7yhkZ4bmtROZ5c,7
-korcen-1.0.0.dist-info/RECORD,,
+korcen-1.0.1.dist-info/METADATA,sha256=-4z5cBCvoxvDu-mUwI89x-1G6eF0XLntFA1hyPEbyMI,465
+korcen-1.0.1.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+korcen-1.0.1.dist-info/top_level.txt,sha256=2LtNKXroHMOGgMokwiUPWwsJt5kmJ7yhkZ4bmtROZ5c,7
+korcen-1.0.1.dist-info/RECORD,,