def cut_input(input):
'''
cut a input string, return utf-8 string
'''
result = norm_seg(input)
wordsList = []
for w in result:
if w.word.strip() == '' or w.flag.strip() == '':
continue
wordsList.append(w.word)
with open(project_path + '/stopwords') as f:
stop_words = []
data = f.readline().strip()
while data:
stop_words.append(data)
data = f.readline().strip()
drop_word_list = [] # 需要删掉的word
for word in wordsList:
if word.encode('utf-8').strip() in stop_words:
drop_word_list.append(word)
elif len(word.encode('utf-8').strip()) == len(word.strip()):
drop_word_list.append(word)
for drop_word in drop_word_list:
wordsList.remove(drop_word)
words = " ".join(wordsList)
return words.encode('utf-8')
def cut_seg(self, sentence=''):
'''
:param special_words: ['美丽 a', '转发 v']
:param industrys: 行业字典， 2汽车， 7美妆， 0 新词
:return:
'''
words = norm_seg(sentence)
return words
def cut_input(process_data):
'''
cut a input string, return utf-8 string jieba中文分词的处理
'''
result = norm_seg(process_data)
words_list = []
for w in result:
if w.word.strip() == '':
continue
words_list.append(w.word)
words = " ".join(words_list)
return words.encode('utf-8')
def cut_input(input):
'''
cut a input string, return utf-8 string
'''
result = norm_seg(input)
wordsList = []
for w in result:
if w.word.strip() == '' or w.flag.strip() == '':
continue
wordsList.append(w.word)
words = " ".join(wordsList)
return words.encode('utf-8')
def cut_input(input, posFlag):
'''
cut a input string, return utf-8 string
'''
if posFlag == True:
result = norm_seg(input)
wordsList = []
for w in result:
wordsList.append(w.word + '_' + w.flag)
words = " ".join(wordsList)
else:
words = " ".join(norm_cut(input))
#return words.encode('utf-8')
return words
def cut_input(input, flag=False):
'''
cut a input string, return utf-8 string
'''
result = norm_seg(input)
wordsList = []
for w in result:
if w.word.strip() == '' or w.flag.strip() == '':
continue
if flag:
wordsList.append(w.word + '_' + w.flag)
else:
wordsList.append(w.word)
return " ".join(wordsList).encode('utf8')
def count_words(self, lwords):
"""
:param lwords:
:return: dwords type is dict ; key :word#flag value :freq
"""
jieba.enable_parallel(10) # start many processes
word_flags = [] # {word#flag : freq},{word:sex}
for context in lwords:
for sub in norm_seg(context):
w = sub.word
if self.oGWF.isGeneralWord(w.encode('utf-8')) or w.strip() == '':
continue
if len(w) >= int(self.word_length):
key = '%s#%s' % (w, sub.flag)
word_flags.append(key)
logger.info('count is starting')
jieba.disable_parallel()
dwords = Counter(word_flags)
return dwords
def cut(self, sentence='', special_words=[], industrys=[]):
'''
:param special_words: ['美丽 a', '转发 v']
:param industrys: 行业字典， 2汽车， 7美妆， 0 新词
:return:
'''
f_special_dict = self.f_inner_dict
if special_words and f_special_dict:
f_special_dict = self.__set_new_dic(special_words)
if os.path.exists(f_special_dict):
jieba.set_dictionary(f_special_dict)
load_industrydict(industrys)
print sentence
words = norm_seg(sentence)
if special_words and os.path.exists(
f_special_dict) and self.f_inner_dict != f_special_dict:
cmd = 'rm -rf %s' % f_special_dict
os.system(cmd)
return words
def cut_input_plus(input, sBrand):
'''
cut a input string, return utf-8 string
'''
result = norm_seg(input)
wordsList = []
wordsPosList = []
posDict = {'all': []}
bIsBrand = False
sBrand0 = ""
for w in result:
if w.word.strip() == '' or w.flag.strip() == '':
continue
w.word = w.word.strip().encode('utf8')
w.flag = w.flag.strip().encode('utf8')
if sBrand == w.word:
bIsBrand = True
if len(w.word.split(' ')) > 1:
w.word = "#kong#".join(w.word.split(' '))
if bIsBrand:
sBrand0 = w.word
wordsList.append(w.word)
wordsPosList.append(w.word + '_' + w.flag)
if not w.flag in posDict:
posDict[w.flag] = []
posDict[w.flag].append(w.word)
posDict['all'].append(w.word)
words_posFlag = " ".join(wordsPosList)
words = " ".join(wordsList)
if sBrand0 != "":
sBrand = sBrand0
return bIsBrand, words, words_posFlag, posDict, sBrand
def cut_input(input):
'''
cut a input string, return utf-8 string
'''
result = norm_seg(input)
wordsList = []
wordsPosList = []
posDict = {'all': []}
for w in result:
if w.word.strip() == '' or w.flag.strip() == '':
continue
wordsList.append(w.word)
wordsPosList.append(w.word + '_' + w.flag)
if not w.flag in posDict:
posDict[w.flag] = []
posDict[w.flag].append(w.word.encode('utf-8'))
posDict['all'].append(w.word.encode('utf-8'))
words_posFlag = " ".join(wordsPosList)
words = " ".join(wordsList)
return words.encode('utf-8'), words_posFlag.encode('utf-8'), posDict
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
1.test suggest_freq
2.test load industry_dict
3.test special word (If the word contains spaces, add to userword / specialword )
industry_dict = {2:"car_dict",7:"makeup.dict"}
"""
from jieba import suggest_freq
from jieba.norm import norm_seg, load_industrydict
#print suggest_freq('小黑瓶',True)
#test 2
testword = ['长安欧尚', "睿骋cc", "行动力", "蓝水粉水小黑瓶"]
load_industrydict([2, 7])
for i in testword:
for word in norm_seg(i):
print word.word, word.flag
