From cee1ce6214fb0432330d18813a560b5d49aa0322 Mon Sep 17 00:00:00 2001 From: zx900930 Date: Fri, 19 Feb 2021 17:14:31 +0100 Subject: [PATCH] Fix false positive zh detection --- bazarr/list_subtitles.py | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/bazarr/list_subtitles.py b/bazarr/list_subtitles.py index 891116798..9bdc97b5c 100644 --- a/bazarr/list_subtitles.py +++ b/bazarr/list_subtitles.py @@ -58,11 +58,11 @@ def store_subtitles(original_path, reversed_path): brazilian_portuguese = [".pt-br", ".pob", "pb"] brazilian_portuguese_forced = [".pt-br.forced", ".pob.forced", "pb.forced"] - simplified_chinese_long = [".simplified"] - simplified_chinese_short = [".chs", ".sc", ".zhs", "hans", ".gb", u"简", u"双语"] + simplified_chinese_fuzzy = ["hans", u"简", u"双语"] + simplified_chinese = [".chs", ".sc", ".zhs", ".gb",".simplified"] simplified_chinese_forced = [".chs.forced", ".sc.forced", ".zhs.forced", "hans.forced", ".gb.forced", u"简体中文.forced", u"双语.forced"] - traditional_chinese_long = [".traditional"] - traditional_chinese_short = [".cht", ".tc", ".zh-tw", ".zht", "hant", "big5", u"繁", u"雙語"] + traditional_chinese_fuzzy = ["hant", u"繁", u"雙語"] + traditional_chinese = [".cht", ".tc", ".zh-tw", ".zht", ".big5", ".traditional"] traditional_chinese_forced = [".cht.forced", ".tc.forced", ".zht.forced", "hant.forced", ".big5.forced", u"繁體中文.forced", u"雙語.forced", "zh-tw.forced"] try: @@ -91,7 +91,7 @@ def store_subtitles(original_path, reversed_path): logging.debug("BAZARR external subtitles detected: " + "pb:forced") actual_subtitles.append( [str("pb:forced"), path_mappings.path_replace_reverse(subtitle_path)]) - elif any(ext in (str(subtitle_path).lower())[:-7] for ext in simplified_chinese_short) or (str(subtitle_path).lower())[:-11] in simplified_chinese_long: + elif str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(simplified_chinese)) or (str(subtitle_path).lower())[:-7] in simplified_chinese_fuzzy: logging.debug("BAZARR external subtitles detected: " + "zh") actual_subtitles.append( [str("zh"), path_mappings.path_replace_reverse(subtitle_path)]) @@ -99,7 +99,7 @@ def store_subtitles(original_path, reversed_path): logging.debug("BAZARR external subtitles detected: " + "zh:forced") actual_subtitles.append( [str("zh:forced"), path_mappings.path_replace_reverse(subtitle_path)]) - elif any(ext in (str(subtitle_path).lower())[:-7] for ext in traditional_chinese_short) or (str(subtitle_path).lower())[:-12] in traditional_chinese_long: + elif str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(traditional_chinese)) or (str(subtitle_path).lower())[:-7] in traditional_chinese_fuzzy: logging.debug("BAZARR external subtitles detected: " + "zt") actual_subtitles.append( [str("zt"), path_mappings.path_replace_reverse(subtitle_path)]) @@ -172,11 +172,11 @@ def store_subtitles_movie(original_path, reversed_path): brazilian_portuguese = [".pt-br", ".pob", "pb"] brazilian_portuguese_forced = [".pt-br.forced", ".pob.forced", "pb.forced"] - simplified_chinese_long = [".simplified"] - simplified_chinese_short = [".chs", ".sc", ".zhs", "hans", ".gb", u"简", u"双语"] + simplified_chinese_fuzzy = ["hans", u"简", u"双语"] + simplified_chinese = [".chs", ".sc", ".zhs", ".gb",".simplified"] simplified_chinese_forced = [".chs.forced", ".sc.forced", ".zhs.forced", "hans.forced", ".gb.forced", u"简体中文.forced", u"双语.forced"] - traditional_chinese_long = [".traditional"] - traditional_chinese_short = [".cht", ".tc", ".zh-tw", ".zht", "hant", "big5", u"繁", u"雙語"] + traditional_chinese_fuzzy = ["hant", u"繁", u"雙語"] + traditional_chinese = [".cht", ".tc", ".zh-tw", ".zht", ".big5", ".traditional"] traditional_chinese_forced = [".cht.forced", ".tc.forced", ".zht.forced", "hant.forced", ".big5.forced", u"繁體中文.forced", u"雙語.forced", "zh-tw.forced"] try: dest_folder = get_subtitle_destination_folder() or '' @@ -201,13 +201,13 @@ def store_subtitles_movie(original_path, reversed_path): elif str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(brazilian_portuguese_forced)): logging.debug("BAZARR external subtitles detected: " + "pb:forced") actual_subtitles.append([str("pb:forced"), path_mappings.path_replace_reverse_movie(subtitle_path)]) - elif any(ext in (str(subtitle_path).lower())[:-7] for ext in simplified_chinese_short) or (str(subtitle_path).lower())[:-11] in simplified_chinese_long: + elif str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(simplified_chinese)) or (str(subtitle_path).lower())[:-7] in simplified_chinese_fuzzy: logging.debug("BAZARR external subtitles detected: " + "zh") actual_subtitles.append([str("zh"), path_mappings.path_replace_reverse_movie(subtitle_path)]) elif any(ext in (str(os.path.splitext(subtitle)[0]).lower())[-12:] for ext in simplified_chinese_forced): logging.debug("BAZARR external subtitles detected: " + "zh:forced") actual_subtitles.append([str("zh:forced"), path_mappings.path_replace_reverse_movie(subtitle_path)]) - elif any(ext in (str(subtitle_path).lower())[:-7] for ext in traditional_chinese_short) or (str(subtitle_path).lower())[:-12] in traditional_chinese_long: + elif str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(traditional_chinese)) or (str(subtitle_path).lower())[:-7] in traditional_chinese_fuzzy: logging.debug("BAZARR external subtitles detected: " + "zt") actual_subtitles.append([str("zt"), path_mappings.path_replace_reverse_movie(subtitle_path)]) elif any(ext in (str(os.path.splitext(subtitle)[0]).lower())[-12:] for ext in traditional_chinese_forced): @@ -549,9 +549,9 @@ def guess_external_subtitles(dest_folder, subtitles): detected_language = guess_language(text) #add simplified and traditional chinese detection if detected_language == 'zh': - traditional_chinese_long = [".traditional"] - traditional_chinese_short = [".cht", ".tc", ".zh-tw", ".zht", "hant", "big5", u"繁", u"雙語"] - if any(ext in (str(subtitle_path).lower())[:-7] for ext in traditional_chinese_short) or (str(subtitle_path).lower())[:-12] in traditional_chinese_long: + traditional_chinese_fuzzy = ["hant", u"繁", u"雙語"] + traditional_chinese = [".cht", ".tc", ".zh-tw", ".zht", ".big5", ".traditional"] + if str(os.path.splitext(subtitle)[0]).lower().endswith(tuple(traditional_chinese)) or (str(subtitle_path).lower())[:-7] in traditional_chinese_fuzzy: detected_language == 'zt' except UnicodeDecodeError: detector = Detector()