import tools
import sys
if __name__ == "__main__":
for line in open(sys.argv[1], "r").readlines():
line = tools.format_white_space(line)
line = tools.strQ2B(line)
line = tools.remove_control_character(line)
sentences = tools.chapter_to_sentences(line.strip())
sentences = tools.gather_sentences(sentences)
for sentence in sentences:
s = tools.strip_punctuation(sentence)
if len(s) > 1 and tools.have_chinese(s):
print(s)
def __clean_raw_file(self, raw):
lower_str = raw.lower()
return tools.strip_punctuation(lower_str)
def __clean_raw_file__(self,raw):
str_lower = raw.lower()
return tools.strip_punctuation(str_lower)