def prepare_russian_sentences(self):
rows = FileManager.get_file_rows(self.russian_sentences_filename)
res = []
for row in rows:
res.append(RussianSentence(row))
return res
def prepare_english_sentences(self):
rows = FileManager.get_file_rows(self.english_sentences_filename)
res = []
for row in rows:
res.append(EnglishSentence(row))
return res
def get_translated_lines(input_file: str):
res = []
file_rows = FileManager.get_file_rows(input_file)
for i, file_row in enumerate(file_rows):
if file_row != '\n':
res.append(file_row)
return res
def get_timelines(input_file: str) -> list:
res = []
file_rows = FileManager.get_file_rows(input_file)
for i, file_row in enumerate(file_rows):
if Subtitle.is_timeline(file_row):
res.append(file_row)
return res
def prepare_timelines_string_length(input_file: str, output_file: str):
result = []
file_rows = FileManager.get_file_rows(input_file)
subtitles = HandleFunctions.get_subtitles(file_rows)
for i, subtitle in enumerate(subtitles):
if i - 1 < len(subtitles) and subtitle.is_large_subtitle():
splitted_subtitle_list = subtitle.split()
result = result + splitted_subtitle_list
else:
result.append(subtitle)
for i, subtitle in enumerate(result):
HandleFunctions.save_str_to_file(output_file, subtitle.timeline.to_string().strip() + '\n')
HandleFunctions.save_str_to_file(output_file, subtitle.subtitle_string.to_string().strip() + '\n')
HandleFunctions.save_str_to_file(output_file, '\n')
def fix(self):
caption_rows = FileManager.get_file_rows(self.input_filename)
for i, caption_row in enumerate(caption_rows):
if Subtitle.is_timeline(caption_row):
if i + 3 < len(caption_rows):
timeline_splitted = caption_row.split(',')
timeline_splitted_next = caption_rows[i + 3].split(',')
HandleFunctions.save_str_to_file(
self.output_filename, timeline_splitted[0] + ',' +
timeline_splitted_next[0] + '\n')
else:
HandleFunctions.save_str_to_file(self.output_filename,
caption_row)
else:
HandleFunctions.save_str_to_file(self.output_filename,
caption_row)
def start(self):
captions_raw = FileManager.get_file_rows(self.captions_filename)
result = []
# Для каждой строки caption определяем номер предложения и количество символов
for caption_raw in captions_raw:
caption_line = CaptionLine(caption_raw)
if TextHelper.is_new_line(caption_raw):
result.append(caption_line)
continue
if caption_line.substrings_cnt == 1:
eng_sentence = self.get_first_not_handled_english_sentence()
percent = int(caption_line.get_full_len() /
eng_sentence.get_full_len() * 100)
eng_sentence.add_percent(percent)
sentence_part = self.get_first_not_empty_russian_sentence(
).get_part_of_string_by_percent(percent)
caption_line.add_formatted_text(sentence_part)
if caption_line.substrings_cnt > 1:
for i in range(caption_line.substrings_cnt):
eng_sentence = self.get_first_not_handled_english_sentence(
)
len_cap_line = len(caption_line.substrings[i])
percent = int(len_cap_line / eng_sentence.get_full_len() *
100)
eng_sentence.add_percent(percent)
sentence_part = self.get_first_not_empty_russian_sentence(
).get_part_of_string_by_percent(percent)
caption_line.add_formatted_text(sentence_part)
result.append(caption_line)
self.save_list_to_file(result)
def remove_timelines(input_file: str, output_file: str):
file_rows = FileManager.get_file_rows(input_file)
for i, file_row in enumerate(file_rows):
if not Subtitle.is_timeline(file_row):
HandleFunctions.save_str_to_file(output_file, file_row)
output_file = os.getcwd() + '/files/res.sbv'
# print("Enter translated subs file...")
subs_file = os.getcwd() + '/files/captions_rus_result.sbv'
hF.concat_translate_with_timelines(input_file, output_file, subs_file)
if operation == 3:
input_file = 'files/captions_concatted_rus.sbv'
output_file = 'files/result.sbv'
hF.prepare_timelines_string_length(input_file, output_file)
if operation == 4:
input_file = 'files/captions_without_timelines.sbv'
punctuation_file = 'files/punctuation.txt'
output_file = os.getcwd() + '/files/captions_without_timelines_improved.sbv'
transcribe_text_improver = TranscribeTextImprover(FileManager.get_file_rows(input_file), FileManager.get_file_rows(punctuation_file), output_file)
transcribe_text_improver.start()
if operation == 5:
input_file = os.getcwd() + '/files/captions_without_timelines.sbv'
output_file = os.getcwd() + '/files/captions_for_google_translate.sbv'
preparator = ToGoogleTranslateCaptionsPreparator(input_file, output_file)
preparator.start()
if operation == 6:
eng_file = os.getcwd() + '/files/captions_for_google_translate.sbv'
rus_file = os.getcwd() + '/files/captions_russian_raw.sbv'
captions_file = os.getcwd() + '/files/captions_without_timelines.sbv'
output_file = os.getcwd() + '/files/captions_rus_result.sbv'
