0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

more raw regexp strings

Browse source
This commit is contained in:
j 2024-08-30 13:30:47 +02:00
commit ae10c5c9b9
11 changed files with 45 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

30
ox/movie.py
View file

@ -25,7 +25,7 @@ The Title[ ([SXX][EYY[+ZZ|-ZZ]])[ Episode Title]][.Version][.Part XY[.Part Title
def format_path(data, directory_key='director'):
def format_underscores(string):
return re.sub('^\.|\.$|:|/|\?|<|>', '_', string)
return re.sub(r'^\.|\.$|:|/|\?|<|>', '_', string)
director = data['directorSort'] or ['Unknown Director']
title = data['seriesTitle' if data['isEpisode'] else 'title'] or 'Untitled'
year = data['seriesYear' if data['isEpisode'] else 'year'] or None
@ -199,14 +199,14 @@ def parse_path(path, directory_key='director'):
string = re.sub('^_', '.', string)
string = re.sub('_$', '.', string)
# '_.foo$' or '_ (' is '?'
string = re.sub(re.compile('_(?=(\.\w+$| \())', re.U), '?', string)
string = re.sub(re.compile(r'_(?=(\.\w+$| \())', re.U), '?', string)
# ' _..._ ' is '<...>'
string = re.sub('(?<= )_(.+)_(?= )', '<\g<1>>', string)
# 'foo_bar' or 'foo _ bar' is '/'
string = re.sub(re.compile('(?<=\w)_(?=\w)', re.U), '/', string)
string = re.sub(re.compile(r'(?<=\w)_(?=\w)', re.U), '/', string)
string = re.sub(' _ ', ' / ', string)
# 'foo_ ' is ':'
string = re.sub(re.compile('(?<=[\w\)\]])_ ', re.U), ': ', string)
string = re.sub(re.compile(r'(?<=[\w\)\]])_ ', re.U), ': ', string)
string = unicodedata.normalize('NFD', string)
return string
@ -238,14 +238,14 @@ def parse_path(path, directory_key='director'):
# title, year
data['title'] = data['year'] = None
if title:
match = re.search(' \(\d{4}(-(\d{4})?)?\)$', title)
match = re.search(r' \(\d{4}(-(\d{4})?)?\)$', title)
data['title'] = title[:-len(match.group(0))] if match else title
data['year'] = match.group(0)[2:-1] if match else None
file_title = re.sub('[/:]', '_', data['title'])
# (remove title from beginning of filename if the rest contains a dot)
file = re.sub('^' + re.escape(file_title) + '(?=.*\.)', '', file)
# (split by nospace+dot+word, but remove spaces preceding extension)
parts = re.split('(?<!\s)\.(?=\w)', re.sub('\s+(?=.\w+$)', '', file))
parts = re.split(r'(?<!\s)\.(?=\w)', re.sub(r'\s+(?=.\w+$)', '', file))
title, parts, extension = [
parts[0],
parts[1:-1],
@ -256,7 +256,7 @@ def parse_path(path, directory_key='director'):
# season, episode, episodes, episodeTitle
data['season'] = data['episode'] = data['episodeTitle'] = None
data['episodes'] = []
match = re.search(' \((S\d{2})?(E\d{2}([+-]\d{2})?)?\)(.+)?', title)
match = re.search(r' \((S\d{2})?(E\d{2}([+-]\d{2})?)?\)(.+)?', title)
if match:
if match.group(1):
data['season'] = int(match.group(1)[1:])
@ -267,7 +267,7 @@ def parse_path(path, directory_key='director'):
data['episodes'] = range(int(match.group(2)[1:3]), int(match.group(2)[-2:]) + 1)
if match.group(4):
data['episodeTitle'] = match.group(4)[1:]
while data['episodeTitle'] and len(parts) and re.search('^\w+\.*$', parts[0]) and not re.search('^[a-z]{2}$', parts[0]):
while data['episodeTitle'] and len(parts) and re.search(r'^\w+\.*$', parts[0]) and not re.search(r'^[a-z]{2}$', parts[0]):
data['episodeTitle'] += '.%s' % parts.pop(0)
# isEpisode, seriesTitle, seriesYear
data['isEpisode'] = False
@ -343,14 +343,14 @@ def parse_movie_path(path):
if title.startswith('_'):
title = '.' + title[1:]
year = find_re(title, '(\(\d{4}\))')
year = find_re(title, r'(\(\d{4}\))')
if not year:
year = find_re(title, '(\(\d{4}-\d*\))')
year = find_re(title, r'(\(\d{4}-\d*\))')
if year and title.endswith(year):
title = title[:-len(year)].strip()
year = year[1:-1]
if '-' in year:
year = find_re(year, '\d{4}')
year = find_re(year, r'\d{4}')
#director
if len(parts) == 4:
@ -373,7 +373,7 @@ def parse_movie_path(path):
language = ''
#season/episode/episodeTitle
match = re.compile('(.+?) \((S(\d+))?(E(\d+))?\)( (.+?))?\.').match(parts[-1])
match = re.compile(r'(.+?) \((S(\d+))?(E(\d+))?\)( (.+?))?\.').match(parts[-1])
if match:
seriesTitle = match.group(1)
season = match.group(3)
@ -386,13 +386,13 @@ def parse_movie_path(path):
if episode and not season:
season = 1
else:
season = find_re(parts[-1], '\.Season (\d+)\.')
season = find_re(parts[-1], r'\.Season (\d+)\.')
if season:
season = int(season)
else:
season = None
episode = find_re(parts[-1], '\.Episode[s]* ([\d+]+)\.')
episode = find_re(parts[-1], r'\.Episode[s]* ([\d+]+)\.')
if episode:
episode = episode.split('+')[0]
episode = int(episode)
@ -422,7 +422,7 @@ def parse_movie_path(path):
title = u'%s %s' % (title, episodeTitle)
#part
part = find_re(parts[-1], '\.Part (\d+)\.')
part = find_re(parts[-1], r'\.Part (\d+)\.')
if part:
part = int(part)
else: