Last active
April 20, 2016 06:24
-
-
Save huangziwei/655e5948a729e376de87 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class getSentences(object): | |
def __init__(self, dirname): | |
self.dirname = dirname | |
def split_paragraph(self, raw): | |
def is_punt(char): | |
stop = ['。', '!', '…', '?'] | |
return char in stop # 判断是否要分句的标点符号 | |
def is_other_punt(char): | |
other_punts = [')'] | |
return char in other_punts | |
raw = re.sub('\n|“|”', '', raw) | |
sents = [] | |
start = 0 | |
quo = 0 | |
for i, char in enumerate(raw): | |
if ( i < (len(raw) - 1) | |
and is_punt(char) | |
and not (is_punt(raw[i+1]) or is_other_punt(raw[i+1])) | |
and quo != 1): | |
# print(i, char) | |
sents.append(raw[start:i+1]) | |
start = i+1 | |
else: | |
continue | |
if start < len(raw): | |
sents.append(raw[start:]) | |
return sents | |
def __iter__(self): | |
for file in glob.glob(self.dirname + '/*'): | |
for paragraph in codecs.open(file, 'r'): | |
for line in self.split_paragraph(paragraph): | |
# yield list(jieba.cut(line)) | |
yield line |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment