mirror
/
bazarr
mirror of https://github.com/morpheus65535/bazarr
1
0
Fork 0
Code Issues Releases Wiki Activity

no log: added failsafe to encoding detection

This commit is contained in:
morpheus65535 2023-06-23 10:06:46 -04:00
parent edfbb1a5ca
commit f371d0585b
1 changed files with 20 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
bazarr/subtitles/indexer/utils.py
View File

@ -76,25 +76,26 @@ def guess_external_subtitles(dest_folder, subtitles, media_type, previously_inde
with open(subtitle_path, 'rb') as f:
text = f.read()
encoding = detect(text)['encoding']
if not encoding:
encoding = detect(text)
if encoding and 'encoding' in encoding:
encoding = detect(text)['encoding']
else:
logging.debug("BAZARR skipping this subtitles because we can't guess the encoding. "
"It's probably a binary file: " + subtitle_path)
continue
if 'UTF' in encoding:
text = text.decode('utf-8')
detected_language = guess_language(text)
# add simplified and traditional chinese detection
if detected_language == 'zh':
traditional_chinese_fuzzy = [u"繁", u"雙語"]
traditional_chinese = [".cht", ".tc", ".zh-tw", ".zht", ".zh-hant", ".zhhant", ".zh_hant",
".hant", ".big5", ".traditional"]
if str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(traditional_chinese)) or (str(subtitle_path).lower())[:-5] in traditional_chinese_fuzzy:
detected_language == 'zt'
else:
text = text.decode(encoding)
text = text.decode(encoding)
detected_language = guess_language(text)
# add simplified and traditional chinese detection
if detected_language == 'zh':
traditional_chinese_fuzzy = [u"繁", u"雙語"]
traditional_chinese = [".cht", ".tc", ".zh-tw", ".zht", ".zh-hant", ".zhhant", ".zh_hant",
".hant", ".big5", ".traditional"]
if str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(traditional_chinese)) or \
(str(subtitle_path).lower())[:-5] in traditional_chinese_fuzzy:
detected_language = 'zt'
if detected_language:
logging.debug("BAZARR external subtitles detected and guessed this language: " + str(
detected_language))
@ -127,15 +128,14 @@ def guess_external_subtitles(dest_folder, subtitles, media_type, previously_inde
with open(subtitle_path, 'rb') as f:
text = f.read()
encoding = detect(text)['encoding']
if not encoding:
encoding = detect(text)
if encoding and 'encoding' in encoding:
encoding = detect(text)['encoding']
else:
logging.debug("BAZARR skipping this subtitles because we can't guess the encoding. "
"It's probably a binary file: " + subtitle_path)
continue
if 'UTF' in encoding:
text = text.decode('utf-8')
else:
text = text.decode(encoding)
text = text.decode(encoding)
if bool(re.search(hi_regex, text)):
subtitles[subtitle] = Language.rebuild(subtitles[subtitle], forced=False, hi=True)