detect epilogues in auto collation
This commit is contained in:
parent
ef0c115f0f
commit
61a7eb07f9
|
@ -25,6 +25,7 @@ FANZA_ID_REGEX = re.compile('^d_[0-9]+$')
|
|||
FAKKU_ID_REGEX = re.compile('.*_FAKKU$')
|
||||
|
||||
TEXTLESS_REGEX = re.compile('(台詞|セリフ)(な|無)し|notext|textless')
|
||||
EPILOGUE_REGEX = re.compile('after|後日談')
|
||||
ALT_VERSIONS = ['褐色', '日焼け', 'pink', '金髪', '白肌']
|
||||
|
||||
IMAGE_FILE_EXTENSIONS = ['.png', '.jpg', '.jpeg', '.gif', '.tiff']
|
||||
|
@ -345,6 +346,26 @@ def collate(args):
|
|||
collation_staging_area.rmdir()
|
||||
con.close()
|
||||
|
||||
def collate_regex_later(srcs, dest, regex, start_index):
|
||||
matching = []
|
||||
nonmatching = []
|
||||
for src in srcs:
|
||||
if regex.search(src.name):
|
||||
matching.append(src)
|
||||
else:
|
||||
nonmatching.append(src)
|
||||
|
||||
if not (matching and nonmatching):
|
||||
return False
|
||||
|
||||
nonmatching_pages = collate_from_paths(nonmatching, dest, start_index)
|
||||
if nonmatching_pages is None:
|
||||
return None
|
||||
matching_pages = collate_from_paths(matching, dest, start_index+nonmatching_pages)
|
||||
if matching_pages is None:
|
||||
return None
|
||||
return nonmatching_pages + matching_pages
|
||||
|
||||
def collate_from_paths(srcs, dest, start_index):
|
||||
if len(srcs) == 1 and srcs[0].is_dir():
|
||||
return collate_from_paths(ls_ignore(srcs[0]), dest, start_index)
|
||||
|
@ -356,21 +377,13 @@ def collate_from_paths(srcs, dest, start_index):
|
|||
if len(srcs) == 0:
|
||||
return 0
|
||||
|
||||
with_text = []
|
||||
textless = []
|
||||
for src in srcs:
|
||||
if TEXTLESS_REGEX.search(src.name):
|
||||
textless.append(src)
|
||||
else:
|
||||
with_text.append(src)
|
||||
if with_text and textless:
|
||||
text_pages = collate_from_paths(with_text, dest, start_index)
|
||||
if text_pages is None:
|
||||
return None
|
||||
textless_pages = collate_from_paths(textless, dest, start_index+text_pages)
|
||||
if textless_pages is None:
|
||||
return None
|
||||
return text_pages + textless_pages
|
||||
textless_split = collate_regex_later(srcs, dest, TEXTLESS_REGEX, start_index)
|
||||
if textless_split != False:
|
||||
return textless_split
|
||||
|
||||
epilogue_split = collate_regex_later(srcs, dest, EPILOGUE_REGEX, start_index)
|
||||
if epilogue_split != False:
|
||||
return epilogue_split
|
||||
|
||||
if all(src.is_file() and src.suffix.lower() in IMAGE_FILE_EXTENSIONS for src in srcs):
|
||||
ordering = complete_prefix_number_ordering(srcs)
|
||||
|
|
Loading…
Reference in a new issue