Add support for src language auto-detection when not input -SRC lan…

…guage

CHANGELOG.md

@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - [Added](#addedunreleased)
   - [Changed](#changedunreleased)
   - [Fixed](#fixedunreleased)
+  - [Removed](#removedunreleased)
 - [0.5.6-alpha - 2020-03-20](#056-alpha---2020-03-20)
   - [Added](#added056-alpha)
   - [Changed](#changed056-alpha)
@@ -58,6 +59,7 @@ Click up arrow to go back to TOC.
 - Add stop words to split events in merge_src_assfile method.
 - Add punctuations split in merge_src_assfile method.
 - Add limitation in SplitIntoAudioPiece with an audio length of at least 4 bytes.
+- Add support for src language auto-detection when not input `-SRC` language.
 
 #### Changed(Unreleased)
 

autosub/cmdline_utils.py

@@ -99,15 +99,15 @@ def list_args(args):
             print("{column_1}{column_2}".format(
                 column_1=lang_code_utils.wjust(_("Lang code"), 18),
                 column_2=_("Description")))
-            for code, language in sorted(constants.TRANSLATION_LANGUAGE_CODES.items()):
+            for code, language in sorted(googletrans.constants.LANGUAGES.items()):
                 print("{column_1}{column_2}".format(
                     column_1=lang_code_utils.wjust(code, 18),
                     column_2=language))
         else:
             print(_("Match py-googletrans lang codes."))
             lang_code_utils.match_print(
                 dsr_lang=args.list_translation_codes,
-                match_list=list(constants.TRANSLATION_LANGUAGE_CODES.keys()),
+                match_list=list(googletrans.constants.LANGUAGES.keys()),
                 min_score=args.min_score)
         return True
 
@@ -423,18 +423,11 @@ def validate_aovp_args(args):  # pylint: disable=too-many-branches, too-many-ret
                 elif 'src' not in args.best_match:
                     args.best_match.add('src')
 
-            is_src_matched = False
-            is_dst_matched = False
+            args.src_language = args.src_language.lower()
+            args.dst_language = args.dst_language.lower()
 
-            for key in googletrans.constants.LANGUAGES:
-                if args.src_language.lower() == key.lower():
-                    args.src_language = key
-                    is_src_matched = True
-                if args.dst_language.lower() == key.lower():
-                    args.dst_language = key
-                    is_dst_matched = True
-
-            if not is_src_matched:
+            if args.src_language != 'auto' and \
+                    args.src_language not in googletrans.constants.LANGUAGES:
                 if args.best_match and 'src' in args.best_match:
                     print(_("Let translation source lang code "
                             "to match py-googletrans lang codes."))
@@ -456,7 +449,7 @@ def validate_aovp_args(args):  # pylint: disable=too-many-branches, too-many-ret
                           "Or use \"-bm\"/\"--best-match\" to get a best match.").format(
                               src=args.src_language))
 
-            if not is_dst_matched:
+            if args.dst_language not in googletrans.constants.LANGUAGES:
                 if args.best_match and 'd' in args.best_match:
                     print(_("Let translation destination lang code "
                             "to match py-googletrans lang codes."))
@@ -516,18 +509,11 @@ def validate_sp_args(args):  # pylint: disable=too-many-branches,too-many-return
             raise exceptions.AutosubException(
                 _("Error: Destination language not provided."))
 
-        is_src_matched = False
-        is_dst_matched = False
-
-        for key in googletrans.constants.LANGUAGES:
-            if args.src_language.lower() == key.lower():
-                args.src_language = key
-                is_src_matched = True
-            if args.dst_language.lower() == key.lower():
-                args.dst_language = key
-                is_dst_matched = True
+        args.src_language = args.src_language.lower()
+        args.dst_language = args.dst_language.lower()
 
-        if not is_src_matched:
+        if args.src_language != 'auto' and\
+                args.src_language not in googletrans.constants.LANGUAGES:
             if args.best_match and 'src' in args.best_match:
                 print(
                     _("Warning: Source language \"{src}\" not supported. "
@@ -554,7 +540,7 @@ def validate_sp_args(args):  # pylint: disable=too-many-branches,too-many-return
                       "Or use \"-bm\"/\"--best-match\" to get a best match.").format(
                           src=args.src_language))
 
-        if not is_dst_matched:
+        if args.dst_language not in googletrans.constants.LANGUAGES:
             if args.best_match and 'd' in args.best_match:
                 print(
                     _("Warning: Destination language \"{dst}\" not supported. "
@@ -800,7 +786,7 @@ def sub_trans(  # pylint: disable=too-many-branches, too-many-statements, too-ma
 
     # text translation
     # use googletrans
-    translated_text = core.list_to_googletrans(
+    translated_text, args.src_language = core.list_to_googletrans(
         text_list,
         src_language=args.src_language,
         dst_language=args.dst_language,
@@ -1365,7 +1351,7 @@ def audio_or_video_prcs(  # pylint: disable=too-many-branches, too-many-statemen
                 pass
 
             # text translation
-            translated_text = core.list_to_googletrans(
+            translated_text, args.src_language = core.list_to_googletrans(
                 text_list,
                 src_language=args.src_language,
                 dst_language=args.dst_language,

autosub/constants.py

@@ -210,119 +210,10 @@
     'ur-in': 'Urdu (India)',
     'ur-pk': 'Urdu (Pakistan)',
     'vi-vn': 'Vietnamese (Vietnam)',
-    'yue-hant-hk' : 'Chinese, Cantonese (Traditional, Hong Kong)',
+    'yue-hant-hk': 'Chinese, Cantonese (Traditional, Hong Kong)',
     'zu-za': 'Zulu (South Africa)'
 }
 
-TRANSLATION_LANGUAGE_CODES = {
-    'af': 'Afrikaans',
-    'am': 'Amharic',
-    'ar': 'Arabic',
-    'az': 'Azerbaijani',
-    'be': 'Belarusian',
-    'bg': 'Bulgarian',
-    'bn': 'Bengali',
-    'bs': 'Bosnian',
-    'ca': 'Catalan',
-    'ceb': 'Cebuano',
-    'co': 'Corsican',
-    'cs': 'Czech',
-    'cy': 'Welsh',
-    'da': 'Danish',
-    'de': 'German',
-    'el': 'Greek',
-    'en': 'English',
-    'eo': 'Esperanto',
-    'es': 'Spanish',
-    'et': 'Estonian',
-    'eu': 'Basque',
-    'fa': 'Persian',
-    'fi': 'Finnish',
-    'fr': 'French',
-    'fy': 'Frisian',
-    'ga': 'Irish',
-    'gd': 'Scots Gaelic',
-    'gl': 'Galician',
-    'gu': 'Gujarati',
-    'ha': 'Hausa',
-    'haw': 'Hawaiian',
-    'he': 'Hebrew',
-    'hi': 'Hindi',
-    'hmn': 'Hmong',
-    'hr': 'Croatian',
-    'ht': 'Haitian Creole',
-    'hu': 'Hungarian',
-    'hy': 'Armenian',
-    'id': 'Indonesian',
-    'ig': 'Igbo',
-    'is': 'Icelandic',
-    'it': 'Italian',
-    'iw': 'Hebrew',
-    'ja': 'Japanese',
-    'jw': 'Javanese',
-    'ka': 'Georgian',
-    'kk': 'Kazakh',
-    'km': 'Khmer',
-    'kn': 'Kannada',
-    'ko': 'Korean',
-    'ku': 'Kurdish',
-    'ky': 'Kyrgyz',
-    'la': 'Latin',
-    'lb': 'Luxembourgish',
-    'lo': 'Lao',
-    'lt': 'Lithuanian',
-    'lv': 'Latvian',
-    'mg': 'Malagasy',
-    'mi': 'Maori',
-    'mk': 'Macedonian',
-    'ml': 'Malayalam',
-    'mn': 'Mongolian',
-    'mr': 'Marathi',
-    'ms': 'Malay',
-    'mt': 'Maltese',
-    'my': 'Myanmar(Burmese)',
-    'ne': 'Nepali',
-    'nl': 'Dutch',
-    'no': 'Norwegian',
-    'ny': 'Nyanja(Chichewa)',
-    'pa': 'Punjabi',
-    'pl': 'Polish',
-    'ps': 'Pashto',
-    'pt': 'Portuguese(Portugal,Brazil)',
-    'ro': 'Romanian',
-    'ru': 'Russian',
-    'sd': 'Sindhi',
-    'si': 'Sinhala(Sinhalese)',
-    'sk': 'Slovak',
-    'sl': 'Slovenian',
-    'sm': 'Samoan',
-    'sn': 'Shona',
-    'so': 'Somali',
-    'sq': 'Albanian',
-    'sr': 'Serbian',
-    'st': 'Sesotho',
-    'su': 'Sundanese',
-    'sv': 'Swedish',
-    'sw': 'Swahili',
-    'ta': 'Tamil',
-    'te': 'Telugu',
-    'tg': 'Tajik',
-    'th': 'Thai',
-    'tl': 'Tagalog(Filipino)',
-    'tr': 'Turkish',
-    'uk': 'Ukrainian',
-    'ur': 'Urdu',
-    'uz': 'Uzbek',
-    'vi': 'Vietnamese',
-    'xh': 'Xhosa',
-    'yi': 'Yiddish',
-    'yo': 'Yoruba',
-    'zh': 'Chinese (Simplified)',
-    'zh-cn': 'Chinese (Simplified)',
-    'zh-tw': 'Chinese (Traditional)',
-    'zu': 'Zulu'
-}
-
 OUTPUT_FORMAT = {
     'srt': 'SubRip',
     'ass': 'Advanced SubStation Alpha',

autosub/core.py

@@ -575,9 +575,9 @@ def list_to_googletrans(  # pylint: disable=too-many-locals, too-many-arguments,
     if not text_list:
         return None
 
-    print(_("\nTranslating text from \"{0}\" to \"{1}\".").format(
-        src_language,
-        dst_language))
+    translator = googletrans.Translator(
+        user_agent=user_agent,
+        service_urls=service_urls)
 
     size = 0
     i = 0
@@ -630,6 +630,16 @@ def list_to_googletrans(  # pylint: disable=too-many-locals, too-many-arguments,
         valid_index.append(i)
         # valid_index for valid text position end
 
+    if src_language == "auto":
+        content_to_trans = '\n'.join(text_list[i:partial_index[0]])
+        result_src = translator.detect(content_to_trans).lang
+    else:
+        result_src = src_language
+
+    print(_("\nTranslating text from \"{0}\" to \"{1}\".").format(
+        result_src,
+        dst_language))
+
     widgets = [_("Translation: "),
                progressbar.Percentage(), ' ',
                progressbar.Bar(), ' ',
@@ -642,9 +652,6 @@ def list_to_googletrans(  # pylint: disable=too-many-locals, too-many-arguments,
         # total position
         j = 0
         # valid_index position
-        translator = googletrans.Translator(
-            user_agent=user_agent,
-            service_urls=service_urls)
 
         for index in partial_index:
             content_to_trans = '\n'.join(text_list[i:index])
@@ -654,6 +661,7 @@ def list_to_googletrans(  # pylint: disable=too-many-locals, too-many-arguments,
                                                dest=dst_language,
                                                src=src_language)
             result_text = translation.text.translate(str.maketrans('’', '\''))
+            result_src = translation.src
             result_list = result_text.split('\n')
             k = 0
             len_result_list = len(result_list)
@@ -702,7 +710,7 @@ def list_to_googletrans(  # pylint: disable=too-many-locals, too-many-arguments,
         print(_("Cancelling translation."))
         return 1
 
-    return translated_text
+    return translated_text, result_src
 
 
 def list_to_sub_str(

autosub/options.py

@@ -150,18 +150,15 @@ def get_cmd_parser():  # pylint: disable=too-many-statements
     lang_group.add_argument(
         '-SRC', '--src-language',
         metavar=_('lang_code'),
+        default='auto',
         help=_("Lang code/Lang tag for translation source language. "
-               "If not given, use langcodes to get a best matching "
-               "of the \"-S\"/\"--speech-language\". "
-               "If using py-googletrans as the method to translate, "
-               "WRONG INPUT STOP RUNNING. "
+               "If not given, use py-googletrans to auto-detect the src language. "
                "(arg_num = 1) (default: %(default)s)"))
 
     lang_group.add_argument(
         '-D', '--dst-language',
         metavar=_('lang_code'),
         help=_("Lang code/Lang tag for translation destination language. "
-               "Same attention in the \"-SRC\"/\"--src-language\". "
                "(arg_num = 1) (default: %(default)s)"))
 
     lang_group.add_argument(
@@ -170,7 +167,7 @@ def get_cmd_parser():  # pylint: disable=too-many-statements
         nargs="*",
         help=_("Allow langcodes to get a best matching lang code "
                "when your input is wrong. "
-               "Only functional for py-googletrans and Google Speech V2. "
+               "Only functional for py-googletrans and Google Speech API. "
                "Available modes: "
                "s, src, d, all. "
                "\"s\" for \"-S\"/\"--speech-language\". "

docs/CHANGELOG.zh-Hans.md

@@ -56,6 +56,7 @@
 - 添加停用词用于merge_src_assfile方法里的断句。
 - 添加标点符号分割功能在merge_src_assfile方法里。
 - 添加音频长度至少为4字节的检测，在SplitIntoAudioPiece里。
+- 添加源语言自动识别功能，当不输入`-SRC`选项时。
 
 #### 改动(未发布)