dlibrary/dlibrary.py

@@ -30,7 +30,6 @@ import rarfile
 import requests
 
 NUMBER_REGEX = re.compile('[0-9０-９]+')
-ALPHABETIC_NUMBERING_REGEX = re.compile('^(?P<prefix>[^a-zａ-ｚ0-9０-９]*)((?P<letter>[a-zａ-ｚ])(?P<suffix>[^a-zａ-ｚ0-9０-９]*))?$', re.I)
 
 DLSITE_ID_REGEX = re.compile('^[BR]J[0-9]+$')
 FANZA_ID_REGEX = re.compile('^d_[0-9]+$')
@@ -65,13 +64,11 @@ FRONT_COVER_REGEX = re.compile('(?<!裏)表紙(?!裏)|(?<!back[-_ ])(?<!back)cov
 BACK_COVER_REGEX = re.compile('裏表紙|hyou?sh?i[-_ ]?ura|ura[-_ ]?hyou?sh?i', re.I)
 BONUS_REGEX = re.compile('設定|キャラ|特典|ポスター|bonus', re.I)
 EPILOGUE_REGEX = re.compile('after|後日談|おまけ', re.I)
-AFTERWORD_REGEX = re.compile('あとがき', re.I)
 SPLITS = [
     { 'later': TEXTLESS_REGEX },
     { 'later': FXLESS_REGEX },
     { 'earlier': FRONT_COVER_REGEX, 'later': BACK_COVER_REGEX },
     { 'later': BONUS_REGEX },
-    { 'later': AFTERWORD_REGEX },
     { 'later': EPILOGUE_REGEX },
 ]
 
@@ -267,7 +264,7 @@ async def fetch_async(args):
                 print(f'Fetching DLSite metadata for {work_id}')
                 dlsite_metadata = await api.get_work(work_id)
                 if dlsite_metadata.work_type not in [dlsite_async.WorkType.MANGA, dlsite_async.WorkType.CG_ILLUSTRATIONS]:
-                    warn(f'Work {work_id} is not a manga or CG set, skipping')
+                    print(f'Work {work_id} is not a manga or CG set, skipping')
                     any_warnings = True
                     continue
                 db_row = {
@@ -907,39 +904,20 @@ def unique_hierarchical_prefix_numbering(entries, start_point=0):
 def alphabetic_numbering(entries, start_point):
     debug(f'Finding alphabetic numbering from start point {start_point} for {entries}')
     alphabetized = {}
-    prefix_suffix = None
     for entry in entries:
-        ending = nfc(entry.stem)[start_point:]
+        ending = nfc(entry.stem)[start_point:].strip(' -_()')
         debug(f'{entry} has ending {ending}')
-
-        ending_match = ALPHABETIC_NUMBERING_REGEX.fullmatch(ending)
-        if not ending_match:
-            debug('Ending has more than one letter, giving up')
+        if len(ending) > 1:
+            debug('Ending is more than one character, giving up')
             return None
-
-        current_prefix_suffix = (ending_match.group('prefix'), ending_match.group('suffix') or '')
-        if prefix_suffix is None:
-            prefix_suffix = current_prefix_suffix
-        elif current_prefix_suffix != prefix_suffix:
-            debug(f'Ending prefix/suffix does not match {prefix_suffix}, giving up')
-            return None
-
-        ending_letter = (ending_match.group('letter') or '').lower()
-        if ending_letter == '':
-            index = 0
-        elif ending_letter >= 'a' and ending_letter <= 'z':
-            index = ord(ending_letter) - ord('a') + 1
-        elif ending_letter >= 'ａ' and ending_letter <= 'ｚ':
-            index = ord(ending_letter) - ord('ａ') + 1
-        else:
+        index = 0 if ending == '' else ord(ending.lower()) - ord('a') + 1
+        if index < 0 or index > 26:
             debug('Ending is not a letter, giving up')
             return None
-
         if (index,) in alphabetized:
             debug(f'Index value {index} is already present, giving up')
             return None
         alphabetized[(index,)] = [entry]
-
     return alphabetized
 
 def check_extension(path, exts):