xenofem/dlibrary
1
0
Fork 0
Code Issues 3 Pull requests Packages Projects Releases Wiki Activity

more regexes, shorten regex flags

Browse source
This commit is contained in:
xenofem 2024-02-22 19:24:01 -05:00
parent 15410ca8ba
commit 3ed462972a
1 changed files with 18 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

28
dlibrary/dlibrary.py
View file

@ -27,22 +27,30 @@ DLSITE_ID_REGEX = re.compile('^[BR]J[0-9]+$')
FANZA_ID_REGEX = re.compile('^d_[0-9]+$')
FAKKU_ID_REGEX = re.compile('.*_FAKKU$')
HI_RES_REGEX = re.compile('高解像度', re.IGNORECASE)
NO_TONE_REGEX = re.compile('トーン(効果)?[な無]し|グレースケール', re.IGNORECASE)
TONE_REGEX = re.compile('トーン(版|(効果)?[有あ]り)', re.IGNORECASE)
COLOR_REGEX = re.compile('カラー', re.IGNORECASE)
MONOCHROME_REGEX = re.compile('モノクロ', re.IGNORECASE)
HI_RES_REGEX = re.compile('高解像度', re.I)
NO_TONE_REGEX = re.compile('トーン(効果)?[な無]し|グレースケール', re.I)
TONE_REGEX = re.compile('トーン(版|(効果)?[有あ]り)', re.I)
COLOR_REGEX = re.compile('カラー', re.I)
MONOCHROME_REGEX = re.compile('モノクロ', re.I)
IMAGE_QUALITY_REGEXES = [
{ 'better': HI_RES_REGEX },
{ 'better': NO_TONE_REGEX, 'worse': TONE_REGEX },
{ 'better': COLOR_REGEX, 'worse': MONOCHROME_REGEX },
]
TEXTLESS_REGEX = re.compile('(台詞|セリフ|せりふ|テキスト|文字)((な|無)し|抜き)|notext|textless', re.IGNORECASE)
FRONT_COVER_REGEX = re.compile('(^|[^裏])表紙|cover|hyoushi', re.IGNORECASE)
BACK_COVER_REGEX = re.compile('裏表紙', re.IGNORECASE)
BONUS_REGEX = re.compile('設定|キャラ', re.IGNORECASE)
EPILOGUE_REGEX = re.compile('after|後日談|おまけ', re.IGNORECASE)
LANGUAGE_REGEXES = {
'en_US': re.compile('english|英語', re.I),
'ja_JP': re.compile('日本語', re.I),
'zh_CN': re.compile('(^|[^體])中文|中国語', re.I),
'zh_TW': re.compile('繁體中文', re.I),
'ko_KR': re.compile('한국어', re.I),
}
TEXTLESS_REGEX = re.compile('(台詞|セリフ|せりふ|テキスト|文字)((な|無)し|抜き)|notext|textless', re.I)
FRONT_COVER_REGEX = re.compile('(^|[^裏])表紙|cover|hyoushi', re.I)
BACK_COVER_REGEX = re.compile('裏表紙', re.I)
BONUS_REGEX = re.compile('設定|キャラ|特典|ポスター', re.I)
EPILOGUE_REGEX = re.compile('after|後日談|おまけ', re.I)
SPLITS = [
{ 'later': TEXTLESS_REGEX },
{ 'earlier': FRONT_COVER_REGEX, 'later': BACK_COVER_REGEX },