def key_word_test():
filename = 'key_test.txt'
with codecs.open(filename, 'r', 'utf-8') as file:
content = file.read()
keys = extract_keywords(content)
#print ','.join(keys)
print summarize1(content)
print summarize2(content)
print summarize3(content)
def infosum():
print 'loading data'
h = codecs.open(testnote, 'r', 'utf-8')
text = h.read()
text = re.sub(r'\d\d\d\d-\d\d-\d\d \d\d:\d\d:\d\d','', text)
text = re.sub(r'\d\d\d\d-\d\d-\d\d','', text)
text = re.sub(r'','',text)
text = re.sub(r'[.*](.*)','',text)
print 'keywords:'
tags = jieba.analyse.extract_tags(text, topK=15)
print ','.join(tags)
print 'sum1:'
print summarize1(text)
print 'sum2:'
print summarize2(text)
print 'sum3:'
print summarize3(text)
print 'length:' + str(len(text))
print 'sum:' + str(len(summarize2(text)))
def infosum():
print 'loading data'
h = codecs.open(testnote, 'r', 'utf-8')
text = h.read()
text = re.sub(r'\d\d\d\d-\d\d-\d\d \d\d:\d\d:\d\d', '', text)
text = re.sub(r'\d\d\d\d-\d\d-\d\d', '', text)
text = re.sub(r'', '', text)
text = re.sub(r'[.*](.*)', '', text)
print 'keywords:'
tags = jieba.analyse.extract_tags(text, topK=15)
print ','.join(tags)
print 'sum1:'
print summarize1(text)
print 'sum2:'
print summarize2(text)
print 'sum3:'
print summarize3(text)
print 'length:' + str(len(text))
print 'sum:' + str(len(summarize2(text)))