def name_tran(str):
test = PinYin()
test.load_word()
str[0]
family = test.hanzi2pinyin(string=str[0])[0]
last = u''
print(str[1:])
for word in test.hanzi2pinyin(string=str[1:]):
last = last + word
name_en = last.title() + u' ' + family.title()
return name_en
def zcf(namelist):
"""
:param namelist:
:return If the match returns a list of numbers, else return None:
"""
nlist = []
flag = 0
test = PinYin()
test.load_word()
key = raw_input("关键词 : ")
for x in range(len(namelist)):
#print namelist[x]
t = test.hanzi2pinyin(str(namelist[x]))
charnum = len(list(namelist[x].decode('utf-8')))
flag2 = True
if len(key) == charnum:
#print str(len(key)) + " " + str(charnum)
for xx in range(charnum):
flag2 = (t[xx][0] == key[xx]) and flag2
else:
continue
if flag2 is True:
flag += 1
nlist.append(x)
if flag == 0:
return None
else:
return nlist
def writeCityName():
if not os.path.exists('cityName.csv'):
url = "http://www.zxinc.org/gb2260.htm"
print 'start reading ...'
response = urllib.urlopen(url)
page = response.read()
page = page.decode('utf8')
print 'reading done...'
pattern = re.compile(ur'([\u4e00-\u9fa5]{2,5}市)')
match = pattern.findall(page)
if match:
try:
with open('cityName.csv', 'wb') as csvfile:
csvWrite = csv.writer(csvfile,
delimiter=' ',
quotechar='|',
quoting=csv.QUOTE_MINIMAL)
csvfile.write(codecs.BOM_UTF8)
test = PinYin()
test.load_word()
for result in match:
result = result.encode('utf8')
py = test.hanzi2pinyin(string=result[:-3])
csvWrite.writerow([result[:-3], py[-1]])
print 'write done!'
except Exception as e:
print e
finally:
csvfile.close()
else:
print 'cityName.csv detected'
class rhyRobot:
#if baidu doesnot work.Try use proxy.
def __init__(self):
self.pinYinRobot = PinYin()
self.pinYinRobot.load_word()
self.shengMu = [
"b", "p", "m", "f", "d", "t", "n", "l", "g", "k", "h", "j", "q",
"x", "zh", "ch", "sh", "r", "z", "c", "s", "y", "w"
]
self.zhengTi = [
"zhi", "chi", "shi", "ri", "zi", "ci", "si", "yu", "ye", "yue",
"yuan", "yin", "yun", "ying"
]
print("pinYinRobot is loaded")
def findRhyForWords(self, chinese):
pinYinList = self.pinYinRobot.hanzi2pinyin(chinese)
for singleWord in pinYinList:
for zhengTi in self.zhengTi:
if (singleWord == zhengTi):
print singleWord + " is whole,cant rhy"
return
pinYinTuple = self.__findPinYinTuple(pinYinList)
allPossibleWord = self.__findAllPosiblePinYin(pinYinTuple)
print allPossibleWord
def __getResultFromBaidu(self, allPossibleWord):
pass
def __getResultFromLocal(self, allPossibleWord):
pass
def __findAllPosiblePinYin(self, pinYinTuple):
shengMuLen = len(self.shengMu)
myLoopMachine = LoopMachine(len(pinYinTuple), shengMuLen)
allPossibleWord = []
while (myLoopMachine.shouldStop()):
loopIndex = myLoopMachine.getLoopIndex()
newWord = ''
appendFlag = True
for i in range(len(loopIndex)):
wordToAppend = self.shengMu[loopIndex[i]] + pinYinTuple[i][1]
if (possibleDict.has_key(wordToAppend) == False):
appendFlag = False
break
newWord = newWord + wordToAppend + ' '
if (appendFlag == True):
allPossibleWord.append((newWord, 0))
myLoopMachine.incr()
return allPossibleWord
def __findPinYinTuple(self, pinYinList):
pinYinTuple = []
for item in pinYinList:
if (item[:2] == "zh" or item[:2] == "ch" or item[:2] == "sh"):
pinYinTuple.append((item[:2], item[2:]))
else:
pinYinTuple.append((item[:1], item[1:]))
return pinYinTuple
def post(self):
p = PinYin(dict_file=os.path.join(os.path.dirname(__file__), 'libs','pinyin','word.data'))
p.load_word()
phone = Phone()
phone.name = cgi.escape(self.request.get("name"))
phone.phone = int(cgi.escape(self.request.get("phone")))
phone.department = cgi.escape(self.request.get("department"))
phone.name_pinyin = ''.join(p.hanzi2pinyin(string=phone.name))
phone.department_pinyin = ''.join(p.hanzi2pinyin(string=phone.department))
phone.hire_date = datetime.datetime.now().date()
phone.put()
path = os.path.join(os.path.dirname(__file__), 'templates','success.html')
self.response.out.write(template.render(path,{}))
def t2():
test = PinYin()
test.load_word()
#string = u"Kottlers古玩城"
#string = u"Head 2 Toe发型店"
#string = u"蓝"
#print string
#print test.hanzi2pinyin(string=string)
#print Cartesian_product(test.hanzi2pinyin(string=string))
name = u"普季(商城)"
name = u"Kottlers古玩城"
name = u"hello 艾压(重庆店)山"
name = u"库兰达（库兰达热带雨林）"
#name = u"盛文甘hello店(店)"
#name = u"义乌三期市场（原篁园市场）"
print name
p = re.compile(u'[\u4e00-\u9fa5]+')
p_eng = re.compile(u'[a-zA-Z]+')
j = 0
strs = []
while (j < len(name)):
#for j in xrange(len(name)):
# if j
if j + 1 == len(name):
strs.append(name[j])
else:
print(name[j], name[j + 1]), is_hz_py(name[j], name[j + 1])
if not is_hz_py(name[j], name[j + 1]):
print name[j], j
strs.append(name[j] + u" ")
else:
strs.append(name[j])
j += 1
name = "".join(strs)
ch_names = p.findall(name)
tmp = name
ll = []
mydict = {}
cnames = "".join([ch_name for ch_name in ch_names])
#pys = test.hanzi2pinyin(string=cnames)
pys = Cartesian_product(test.hanzi2pinyin(string=cnames))
print cnames, pys, ch_names
for p in pys:
tmp2 = name
for ch_name in ch_names:
m = re.search(ch_name, cnames)
_start = m.start()
_end = m.end()
replace = " ".join([k for k in p.split()[_start:_end]])
print _start, _end, replace, tmp2
tmp2 = re.sub(ch_name, replace, tmp2, 1)
print tmp2
def t2():
test = PinYin()
test.load_word()
#string = u"Kottlers古玩城"
#string = u"Head 2 Toe发型店"
#string = u"蓝"
#print string
#print test.hanzi2pinyin(string=string)
#print Cartesian_product(test.hanzi2pinyin(string=string))
name = u"普季(商城)"
name = u"Kottlers古玩城"
name = u"hello 艾压(重庆店)山"
name = u"库兰达（库兰达热带雨林）"
#name = u"盛文甘hello店(店)"
#name = u"义乌三期市场（原篁园市场）"
print name
p = re.compile(u'[\u4e00-\u9fa5]+')
p_eng = re.compile(u'[a-zA-Z]+')
j = 0
strs = []
while (j<len(name)):
#for j in xrange(len(name)):
# if j
if j+1 == len(name):
strs.append(name[j])
else:
print (name[j], name[j+1]), is_hz_py(name[j], name[j+1])
if not is_hz_py(name[j], name[j+1]):
print name[j], j
strs.append(name[j]+u" ")
else:
strs.append(name[j])
j += 1
name = "".join(strs)
ch_names = p.findall(name)
tmp = name
ll = []
mydict = {}
cnames = "".join([ch_name for ch_name in ch_names])
#pys = test.hanzi2pinyin(string=cnames)
pys = Cartesian_product(test.hanzi2pinyin(string=cnames))
print cnames, pys, ch_names
for p in pys:
tmp2 = name
for ch_name in ch_names:
m = re.search(ch_name, cnames)
_start = m.start()
_end = m.end()
replace = " ".join([k for k in p.split()[_start:_end]])
print _start, _end, replace, tmp2
tmp2 = re.sub(ch_name, replace, tmp2, 1)
print tmp2
def Convert(self):
py_engine = PinYin()
py_engine.load_word()
contact = list()
f = open(self.filename,'r')
for line in open(self.filename):
line = f.readline()
k = re.findall(r"(\N\:[^\;]*\;[^\;]*\;[^\;]*\;[^\;]*\;)", line)
if k:
if k[0].find(';') - 2 > 3:
xing = k[0][2: 5]
ming = k[0][5: k[0].find(';')] + k[0][k[0].find(';') + 1 : k[0].find(';', k[0].find(';')+1)]
else:
xing = k[0][2: k[0].find(';') ]
ming = k[0][k[0].find(';') + 1 : k[0].find(';', k[0].find(';')+1)]
contact.append('N:'+xing+';'+ming+';'+";;\n")
phones = py_engine.hanzi2pinyin(string=xing)
line = "X-PHONETIC-LAST-NAME:"
for item in phones:
if item != '':
line = line + item.capitalize()
line += "\n"
contact.append(line)
phones = py_engine.hanzi2pinyin(string=ming)
line = "X-PHONETIC-FIRST-NAME:"
for item in phones:
if item != '':
line = line + item.capitalize()
line += "\n"
contact.append(line)
else:
contact.append(line)
fout = open("ok_"+self.filename, 'w')
for line in contact:
fout.write(line)
def idiomFind(x):
if x == None:
raise Exception
else:
with open('idiom.txt','r') as f:
base = f.readlines()
random.shuffle(base)
j = 0
for i in base:
c = i[:3].decode('utf8')
if len(i)>1:
try:
test = PinYin()
test.load_word()
py = test.hanzi2pinyin(c)[0]
if (py == x):
return i
except:
continue
return None
def Convert(self):
py_engine = PinYin()
py_engine.load_word()
contact = list()
f = open(self.filename,'r')
for line in open(self.filename):
line = f.readline()
contact.append(line)
k = re.findall(r"(\N\:[^\;]*\;)", line)
if k:
phones = py_engine.hanzi2pinyin(string=k[0])
line = "X-PHONETIC-LAST-NAME:"
for item in phones:
if item != '':
line = line + item.capitalize()
line += "\n"
contact.append(line)
fout = open(filename, 'w')
for line in contact:
fout.write(line)
def main(args):
test = PinYin()
test.load_word()
conn = getconn()
cursor = conn.cursor()
cursor.execute('select rname,rid from roominfo where py_name is null')
# cursor.execute('select cname,area from area_name_map where py_name is null')
rows = cursor.fetchall()
for row in rows:
myword = row[0].encode("utf8")
pylist = test.hanzi2pinyin(string=myword)
pystr = pylist[0]
for w in pylist[1:]:
pystr = pystr + w[0]
# cursor.execute('update area_name_map set py_name=? where cname=? and area=?',(pystr,row[0],row[1]))
cursor.execute('update roominfo set py_name=? where rid=?',
(pystr, row[1]))
conn.commit()
conn.close()
array3 = lists[2]
array4 = lists[3]
with open('dict.txt', 'r') as userDict:
for i in userDict:
i.strip('\r\n')
f.write(array1 + i.strip() + '\n')
f.write(array1 + array2 + array3[0:1] + i.strip() + '\n')
f.write(array1 + array2[0:1] + array3[0:1] + array4[0:1] + i.strip() + '\n')
f.write(array1[0:1] + array2[0:1] + array3[0:1] + array4[0:1] + i.strip() + '\n')
f.write(array1.capitalize() + array2[0:1] + array3[0:1] + array4[0:1] + i.strip() + '\n')
f.write(array1.capitalize()[0:1] + array2[0:1] + array3[0:1] + array4[0:1] + i.strip() + '\n')
#f.close()
print array1 + array2 + array3[0:1] + array4[0:1]
print array1 + array2[0:1] + array3[0:1] + array4[0:1]
print array1[0:1] + array2[0:1] + array3[0:1] + array4[0:1]
print array1.capitalize() + array2[0:1] + array3[0:1] + array4[0:1]
print array1.capitalize()[0:1] + array2[0:1] + array3[0:1] + array4[0:1]
with open('username.txt', 'r') as un:
for userinfo in un:
lists = test.hanzi2pinyin(string=userinfo.strip())
if len(lists) == 2:
listsTwo(lists)
elif len(lists) == 3:
listsThree(lists)
elif len(lists) == 4:
listsFour(lists)
else:
print 'you chinese name maybe ==1 or > 4 ,please current'
#un.close()
f.close()
f.write(array1 + array2 + array3[0:1] + i.strip() + '\n')
f.write(array1 + array2[0:1] + array3[0:1] + array4[0:1] +
i.strip() + '\n')
f.write(array1[0:1] + array2[0:1] + array3[0:1] + array4[0:1] +
i.strip() + '\n')
f.write(array1.capitalize() + array2[0:1] + array3[0:1] +
array4[0:1] + i.strip() + '\n')
f.write(array1.capitalize()[0:1] + array2[0:1] + array3[0:1] +
array4[0:1] + i.strip() + '\n')
#f.close()
print array1 + array2 + array3[0:1] + array4[0:1]
print array1 + array2[0:1] + array3[0:1] + array4[0:1]
print array1[0:1] + array2[0:1] + array3[0:1] + array4[0:1]
print array1.capitalize() + array2[0:1] + array3[0:1] + array4[0:1]
print array1.capitalize()[0:1] + array2[0:1] + array3[0:1] + array4[0:1]
with open('username.txt', 'r') as un:
for userinfo in un:
lists = test.hanzi2pinyin(string=userinfo.strip())
if len(lists) == 2:
listsTwo(lists)
elif len(lists) == 3:
listsThree(lists)
elif len(lists) == 4:
listsFour(lists)
else:
print 'you chinese name maybe ==1 or > 4 ,please current'
#un.close()
f.close()
'my puzzle of PYthon' print( [str(a) + str(b) for a in ["1","2"] for b in ["a", "b"] ] ) # 1a .... from pinyin import PinYin test = PinYin() test.load_word() a = test.hanzi2pinyin(string='钓鱼岛是中国的') print(a) # Python 3 renamed the unicode type to str unicode_or_str = "钓鱼岛是中国的" print()
'my puzzle of PYthon' print([str(a) + str(b) for a in ["1", "2"] for b in ["a", "b"]]) # 1a .... from pinyin import PinYin test = PinYin() test.load_word() a = test.hanzi2pinyin(string='钓鱼岛是中国的') print(a) # Python 3 renamed the unicode type to str unicode_or_str = "钓鱼岛是中国的" print()
# -*- coding:utf-8 -*-
from pinyin import PinYin
import sys
if __name__ == "__main__":
test = PinYin()
test.load_word()
# string = "测试文本"
f = open(sys.argv[1],'r')
f2 = open("dict/"+"short_"+sys.argv[1].split("/")[-1],'w')
f3 = open("dict/"+"full_"+sys.argv[1].split("/")[-1],'w')
for i in f:
# ch_str = i.split(" ")[1].strip()
ch_str = i.strip()
print "\""+ch_str+"\""
short_arr = test.hanzi2pinyin(string=ch_str)
short_str = ""
for x in short_arr:
try:
print x
short_str += x[0]
except:
continue
print short_str
f2.write(short_str+" "+ch_str+"\n")
f3.write("".join(short_arr)+" "+ch_str+"\n")
f2.close()
f3.close()
# print "in: %s" % string
def getPinYin(hanzi):
test = PinYin()
test.load_word()
return test.hanzi2pinyin(string=hanzi)
# -*- coding: utf-8 -*-
from pinyin import PinYin
import json
def load(file):
with open(file) as json_file:
# json.load可以将文件转化为字典，loads可以将字符串转化为字典
data = json.load(json_file)
return data
#这个程序的作用是，读取分好词的结果，转化成拼音
input = load('out.json')
print len(input)
test = PinYin()
test.load_word()
st = []
for i in input:
st.append(str(test.hanzi2pinyin(string=i)))
print len(st)
json_dic = json.dumps(st)
fo = open("out_pinyin.json", "wb")
fo.write(json_dic)
# 关闭打开的文件
fo.close()
