class PinyinTests(unittest.TestCase):
def setUp(self):
import cpinyin
cpinyin.install()
from xpinyin import Pinyin
self.p = Pinyin()
def test_get_pinyin_with_default_splitter(self):
self.assertEqual(self.p.get_pinyin(u'上海'), u'shang-hai')
def test_get_pinyin_with_splitter(self):
self.assertEqual(self.p.get_pinyin(u'上海', splitter=u''), u'shanghai')
def test_get_pinyin_mixed_words(self):
self.assertEqual(self.p.get_pinyin(u'Apple发布iOS7', splitter=u'-'),
u'Apple-fa-bu-iOS7')
def test_get_pinyin_with_tone_marks(self):
self.assertEqual(self.p.get_pinyin(u'上海', tone_marks=u'marks'),
u'sh\xe0ng-h\u01cei')
def test_get_pinyin_with_tone_marks(self):
self.assertEqual(self.p.get_pinyin(u'秋', tone_marks=u'marks'), u'qiū')
def test_get_initial(self):
self.assertEqual(self.p.get_initial(u'你'), u'N')
def test_get_initials(self):
self.assertEqual(self.p.get_initials(u'你好'), u'N-H')
def test_get_initials_with_splitter(self):
self.assertEqual(self.p.get_initials(u'你好', u' '), u'N H')
self.assertEqual(self.p.get_initials(u'你好', u''), u'NH')
def ab(self):
try:
# 拼音
p = Pinyin()
if self.args['EditType'] == 'add':
sql = "INSERT INTO Carder(Carder_MarkName, Carder_Mobile, " \
"Carder_Address, Carder_User, Carder_BankUserName, " \
"Carder_BankNumber, Carder_BankLive, Carder_Type, " \
"Carder_CarNumber, Carder_BakInfo, Carder_CarType, Carder_PY) " \
"values ('{0}','{1}','{2}','{3}','{4}','{5}','{6}','{7}','{8}','{9}','{10}','{11}')" \
.format(safe(self.args.get('Carder_MarkName', '')),
safe(self.args.get('Carder_Mobile', '')),
safe(self.args.get('Carder_Address', '')),
safe(self.args.get('Carder_User', '')),
safe(self.args.get('Carder_BankUserName', '')),
safe(self.args.get('Carder_BankNumber', '')),
safe(self.args.get('Carder_BankLive', '')),
safe(self.args.get('Carder_Type', '')),
safe(self.args.get('Carder_CarNumber', '')),
safe(self.args.get('Carder_BakInfo', '')),
safe(self.args.get('Carder_CarType', '')),
p.get_initials(self.args.get('Carder_MarkName', ''), ''))
conn.eDB(sql)
res_id = conn.sDB("select cast(IDENT_CURRENT('Carder') as nvarchar(20)) as ID")[0]
self.args['ID'] = int(res_id['ID'])
else:
sql = "UPDATE Carder Set Carder_MarkName = '{0}', Carder_Mobile = '{1}', " \
"Carder_Address = '{2}', Carder_User = '******', Carder_BankUserName = '******', " \
"Carder_BankNumber = '{5}', Carder_BankLive = '{6}', Carder_Type = '{7}', " \
"Carder_CarNumber = '{8}', Carder_BakInfo = '{9}', Carder_CarType = '{10}', " \
"Carder_PY = '{11}' where ID='{12}'" \
.format(safe(self.args.get('Carder_MarkName', '')),
safe(self.args.get('Carder_Mobile', '')),
safe(self.args.get('Carder_Address', '')),
safe(self.args.get('Carder_User', '')),
safe(self.args.get('Carder_BankUserName', '')),
safe(self.args.get('Carder_BankNumber', '')),
safe(self.args.get('Carder_BankLive', '')),
safe(self.args.get('Carder_Type', '')),
safe(self.args.get('Carder_CarNumber', '')),
safe(self.args.get('Carder_BakInfo', '')),
safe(self.args.get('Carder_CarType', '')),
p.get_initials(self.args.get('Carder_MarkName', ''), ''),
safe(self.args.get('ID', '')))
conn.eDB(sql)
return str(json.dumps({"err": False, "data": self.args}))
except Exception as err:
return str(json.dumps({"err": str(err)}))
def addCatagory(name, parent_name, meta_title, meta_keyword, meta_description,
hot_tag, hot_brand, author, cover_image):
'''
增加一个目录，一级目录的parent_id=0
'''
db = DBAccess()
db.dbName = "zixun"
p = Pinyin()
if not name:
raise MyDefineError("名称不能为空")
names_all = getAllObjectUrlsOrNames('catagory', 'name')
if name in names_all:
raise MyDefineError("栏目已存在")
if parent_name:
parent_id = getObjectIdWithName('catagory', parent_name)
if not parent_id:
raise MyDefineError("父栏目不存在")
else:
parent_id = 0
url = str(p.get_initials(name.decode('utf-8'), '')).lower()
urls_all = getAllObjectUrlsOrNames('catagory', 'url')
while url in urls_all:
url += str(random.randint(0, 30))
sql = "insert into catagory (name, parent_id,url, meta_title,meta_keyword,meta_description,cover_image) values ('%s','%s','%s','%s','%s','%s','%s')" \
%(name,parent_id,url,meta_title,meta_keyword,meta_description,cover_image)
catagory_id = db.execNonQuery(sql)
if hot_tag:
updateHotTag(catagory_id, hot_tag)
if hot_brand:
updateHotBrand(catagory_id, hot_brand)
recordFlow(author, "add", "catagory", sql)
return
def parse_village(response):
print('==> %s' % response.url)
pid = response.meta['pid']
p = Pinyin()
try:
for tr in response.xpath('//tr[@class="villagetr"]'):
item = RegionItem()
item['adCode'] = tr.xpath('td[1]/text()')[0].extract()
item['name'] = tr.xpath('td[3]/text()')[0].extract()
if '居民委员会' in item['name']:
item['name'] = item['name'].replace('居民委员会', '')
if '村民委员会' in item['name']:
item['name'] = item['name'].replace('村民委员会', '村')
if '村委会委会' in item['name']:
item['name'] = item['name'].replace('村委会委会', '村')
if '居委会' in item['name']:
item['name'] = item['name'].replace('居委会', '')
if '村村村委会' in item['name']:
item['name'] = item['name'].replace('村村村委会', '村')
if '村村委会' in item['name']:
item['name'] = item['name'].replace('村村委会', '村')
if '村村' in item['name']:
item['name'] = item['name'].replace('村村', '村')
item['py'] = p.get_pinyin(item['name'], ' ')
item['initial'] = p.get_initials(item['name'], '')[0:1]
item['level'] = 5
item['parent'] = pid
yield item
except IndexError:
pass
def parse_town(self, response):
print('==> %s' % response.url)
pid = response.meta['pid']
p = Pinyin()
for tr in response.xpath('//tr[@class="towntr"]'):
item = RegionItem()
item['adCode'] = tr.xpath('td[1]/a/text()')[0].extract()[0:9]
item['name'] = tr.xpath('td[2]/a/text()')[0].extract()
if '办事处' in item['name']:
item['name'] = item['name'].replace('办事处', '')
item['py'] = p.get_pinyin(item['name'], ' ')
item['initial'] = p.get_initials(item['name'], '')[0:1]
item['level'] = 4
item['parent'] = pid
yield item
url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/%s/%s/%s/%s.html' % (
pid[0:2], pid[2:4], pid[4:6], item['adCode'])
request = scrapy.Request(url,
callback=self.parse_village,
dont_filter=True)
request.meta['pid'] = item['adCode']
yield request
def handle(self, *args, **options):
hellspawns = Hellspawn.objects.all()
p = Pinyin()
for hell in hellspawns:
hell.name_pinyin = p.get_pinyin(hell.name, '')
hell.name_abbr = p.get_initials(hell.name, '')
hell.save()
def parse_county(self, response):
print('==> %s' % response.url)
pid = response.meta['pid']
p = Pinyin()
for tr in response.xpath('//tr[@class="countytr"]'):
item = RegionItem()
item['level'] = 3
item['parent'] = pid
try:
item['adCode'] = tr.xpath('td[1]/a/text()')[0].extract()[0:6]
item['name'] = tr.xpath('td[2]/a/text()')[0].extract()
url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/%s/%s/%s.html' % (
pid[0:2], pid[2:4], item['adCode'])
request = scrapy.Request(url,
callback=self.parse_town,
dont_filter=True)
request.meta['pid'] = item['adCode']
yield request
except IndexError:
item['adCode'] = tr.xpath('td[1]/text()')[0].extract()[0:6]
item['name'] = tr.xpath('td[2]/text()')[0].extract()
item['py'] = p.get_pinyin(item['name'], ' ')
item['initial'] = p.get_initials(item['name'], '')[0:1]
yield item
def addBrand(name, description, company_name, company_website, brand_classify,
company_address, meta_title, meta_keyword, meta_description,
cover_image, author):
'''
增加品牌
'''
db = DBAccess()
db.dbName = "zixun"
p = Pinyin()
names_all = getAllObjectUrlsOrNames("brand", 'name')
if name in names_all:
raise MyDefineError("品牌已存在")
url = str(p.get_initials(name.decode('utf-8'), '')).lower()
urls_all = getAllObjectUrlsOrNames("brand", 'url')
while url in urls_all:
url += str(random.randint(0, 30))
create_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
sql = "insert into brand (name,description,url,company_name,company_website,brand_classify,company_address,meta_title,meta_keyword,meta_description,cover_image,author,create_time,update_time) values ('%s','%s','%s','%s','%s','%s','%s','%s','%s','%s','%s','%s','%s','%s')"\
%(name,description,url,company_name,company_website,brand_classify,company_address,meta_title,meta_keyword,meta_description,cover_image,author,create_time,create_time)
brand_id = db.execNonQuery(sql)
recordFlow(author, "add", "brand", sql)
return brand_id
def addTag(parent_name, name, meta_title, meta_keyword, meta_description,
author):
'''
增加标签
'''
db = DBAccess()
db.dbName = "zixun"
r = getRedisObj()
p = Pinyin()
if parent_name:
parent_id = getObjectIdWithName('tag', parent_name)
if not parent_id:
raise MyDefineError("一级标签不存在")
else:
parent_id = 0
names_all = getAllObjectUrlsOrNames("tag", 'name')
if name in names_all:
raise MyDefineError("标签已存在")
url = str(p.get_initials(name.decode('utf-8'), '')).lower()
urls_all = getAllObjectUrlsOrNames('tag', 'url')
while url in urls_all:
url += str(random.randint(0, 30))
update_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
sql = "insert into tag (name,url,update_time,parent_id,meta_title,meta_keyword,meta_description) values ('%s','%s','%s',%s,'%s','%s','%s')"\
%(name,url,update_time,parent_id,meta_title,meta_keyword,meta_description)
tag_id = db.execNonQuery(sql)
recordFlow(author, "add", "tag", sql)
return tag_id
def read_stock_code(dirs):
p=Pinyin()
for mydir in dirs:
with open(mydir) as f:
data=f.readlines()
ix=0
while ix<len(data):
s=data[ix].strip('\n').split('=')
if not s[0]:
ix+=1
continue
if len(s)<2:
ix+=2
continue
code=s[0]
cnames=s[1].split('|')
if len(cnames)>1:
chineseName=cnames[0].replace(' ','')
initial=''
for i in p.get_initials(cnames[0].replace(' ','')).replace('-',''):
cod=ord(i)
if 65312<cod<65339:
i=chr(cod-65248)
initial=initial+i
spareCode=cnames[1][:-2]
else:
chineseName=cnames[0].replace(' ','')
initial=''
for i in p.get_initials(cnames[0].replace(' ','')).replace('-',''):
cod=ord(i)
if 65312<cod<65339:
i=chr(cod-65248)
initial=initial+i
spareCode=None
bazaar=None
if mydir[-9:-7]=='16':
bazaar='sh'
elif mydir[-9:-7]=='32':
bazaar='sz'
elif '176' in mydir:
bazaar='hk'
yield [code,chineseName,initial,spareCode,bazaar]
ix+=1
print(mydir)
def getShortPin():
print u'[-]姓名转缩写'
pinyin = Pinyin()
for name in cnnames:
py = pinyin.get_initials(name.strip(), '').lower()
print '{}---{}'.format(name.strip().decode('utf-8').encode('gbk'), py)
username.add(py)
print u'[-]姓名转姓名全拼'
for name in cnnames:
xing = name.strip()[0]
ming = name.strip()[1:]
pyxing = pinyin.get_pinyin(xing, '')
pyming = pinyin.get_initials(ming, '').lower()
py = '{}{}'.format(pyxing, pyming)
print '{}---{}'.format(name.strip().decode('utf-8').encode('gbk'), py)
username.add(py)
info['ennames'] = list(username)
def save(self, without_valid=False, *args, **kwargs):
p = Pinyin()
full_pinyin = p.get_pinyin(smart_str(self.title), '')
first_pinyin = p.get_initials(smart_str(self.title), '').lower()
self.search_word = " ".join([full_pinyin, first_pinyin])
update_logger.info('video path: ' + str(self.video))
if self.description is None or self.description == "":
self.description = default_description(self)
if self.local_video != '' and self.local_video is not None:
basename = Path(self.local_video).relative_to(
Path(settings.LOCAL_MEDIA_ROOT))
self.video.name = str(Path(settings.LOCAL_MEDIA_URL) / basename)
update_logger.debug("save local_video to filefield done")
if without_valid:
ret = super(Vod, self).save(*args, **kwargs)
return ret
super(Vod, self).save(*args, **kwargs)
if os.path.splitext(str(self.video))[1] not in ['.mp4', '.m3u8']:
p = threading.Thread(target=ff, args=(self, ))
p.start()
try:
if self.video != None and self.video != '':
relative_path = Path(self.video.name).relative_to(
settings.MEDIA_URL) # Djan%20go.mp4
rel_name = uri_to_iri(relative_path) # Djan go.mp4
# Make sure the self.video.name is not in the LOCAL_FOLDER
if not self.video.name.startswith(settings.LOCAL_FOLDER_NAME) and \
not self.video.name.startswith(settings.RECORD_MEDIA_FOLDER):
self.video.name = str(rel_name)
update_logger.info('save path: ' + self.save_path)
update_logger.info('video name: ' + str(self.video.name))
update_logger.info('size: ' + self.video.file.size)
self.file_size = humanfriendly.format_size(
self.video.file.size)
# duration = VideoFileClip(self.video.path).duration
# self.duration = time_formate(duration)
else:
print("video file is None")
except:
pass
try:
if self.image:
self.image.name = str(
uri_to_iri(
Path(self.image.name).relative_to(settings.MEDIA_URL)))
except:
pass
return super(Vod, self).save(*args, **kwargs)
def SH(wordlists, char=""): #获取拼音首拼大写
p = Pinyin()
pwd = os.getcwd() + "\\dic"
if (os.path.exists(pwd) == False):
os.makedirs(pwd)
else:
with open("./dic/SH.txt", "w", encoding="utf-8") as f:
for word in wordlist:
str0 = p.get_initials(word, char)
f.write(str0)
print("拼音首拼大写--->>>" + str0)
def parse_bus_list(self, req, result):
soup = BeautifulSoup(result, "html.parser")
for line in soup.find_all("script")[2]:
if "var data = " in line:
bus_list = [str(eval(x)) for x in line.split("[")[1].split("];")[0].split(",")]
else:
bus_list = []
p = Pinyin()
bus_dict = {p.get_initials(x, ""): x for x in bus_list}
with open("buseslist.txt", "w", encoding="utf-8") as f:
f.write(str(bus_dict))
def __init__(self):
self.city = input("请输入城市名:\n")
p = Pinyin()
city_name = p.get_initials(self.city, '').lower()
self.url = 'http://{0}.ganji.com/v/zhaopinxinxi/p1/'.format(city_name)
self.save_path = r'G:\data\ganji.csv'
file_dir = os.path.split(self.save_path)[0]
if not os.path.isdir(file_dir):
os.makedirs(file_dir)
if not os.path.exists(self.save_path):
os.system(r'echo > %s' % self.save_path)
def welcome(request):
if request.user.is_authenticated():
return redirect('/')
appname = u"延伸"
pagename ='welcome'
if request.method == 'POST':
username = request.POST['username']
password = request.POST['password']
action = request.POST['action']
if username == '' or password =='' or action == '':
message = '抱歉，服务器开小差了，注册失败。'
return locals()
if action == 'login':
user = authenticate(username=username, password=password)
if user is not None:
if user.is_active:
login(request, user)
return redirect('/')
else:
message = '账户已被注销。'
return locals()
else:
message = 'Email 或密码错误。'
return locals()
elif action == 'reg':
if Profile.objects.filter(email=username).exists():
message = '您已经注册过了。'
return locals()
else:
try:
user = Profile.objects.create_user(email=username, password=password)
user.first_name = request.POST['firstname']
user.last_name = request.POST['lastname']
p = Pinyin()
user.pinyin = p.get_pinyin(user.last_name + user.first_name, ' ')
for char in user.last_name + user.first_name:
user.pinyin += p.get_initials(char)
user.contact_info = json.JSONEncoder().encode({"next_id":2, "data":[{"info_id":1, "type":"Email", "key": u"电子邮箱", "value": user.email}]})
user.save()
category = Category.objects.create(name=u'未分组', owner=user, privilege='{"1":false}')
category.save()
except ValidationError:
message = '请输入正确的 Email 地址。'
return locals()
if user:
user = authenticate(username=username, password=password)
login(request, user)
return redirect('/me/?first=1')
else:
message = '抱歉，服务器开小差了，注册失败。'
return locals()
else:
return locals()
def get_letter(name):
"""
get first letter
:author: lishanZheng
:date: 2020/01/08
"""
pinyin = Pinyin()
if name == '':
return 'Z'
letter = pinyin.get_initials(name, u'')[0]
return letter
def get_pinyin():
p = Pinyin()
for results in query_by_pagination(session, GoodsInventory):
for itm in results:
itm.py = p.get_initials(itm.name, '').replace(' ', '')
try:
session.commit()
except Exception as e:
logging.exception(
'ERROR in commit session site {0} reason {1}'.format(
'null', e))
session.rollback()
def draw_bar():
data = '''北 京 7355291
天 津 3963604
河 北 20813492
山 西 10654162
内 蒙 古 8470472
辽 宁 15334912
吉 林 9162183
黑 龙 江 13192935
上 海 8893483
江 苏 25635291
浙 江 20060115
安 徽 19322432
福 建 11971873
江 西 11847841
山 东 30794664
河 南 26404973
湖 北 17253385
湖 南 19029894
广 东 32222752
广 西 13467663
海 南 2451819
重 庆 10272559
四 川 26383458
贵 州 10745630
云 南 12695396
西 藏 689521
陕 西 11084516
甘 肃 7113833
青 海 1586635
宁 夏 1945064
新 疆 6902850'''
data = data.split('\n')
d = {}
pinyin = Pinyin()
for i in data:
k = pinyin.get_initials(i[:6].strip().replace(' ',''),'')
v = int(i[6:].strip())
d[k] = v
pt.figure(figsize=(9,6))
ind = np.arange(len(d))
pt.bar(ind,d.values(),alpha=0.9,width=0.5,facecolor = 'lightskyblue',edgecolor = 'white',label = '人口',lw=1)
pt.xticks(ind,d.keys())
pt.plot(ind,d.values(),color='red',label='plot',lw=1,alpha=0.6)
pt.title('china population')
pt.legend(loc = "upper left")
pt.savefig(f'{random.randint(1,100)}.png')
pt.show()
def get_citypair(filename):
pinyin = Pinyin()
f = open(filename, encoding='utf-8')
citys_list = [i.strip().lstrip() for i in f.readlines()]
f.close()
citys_pinyin = [
pinyin.get_initials(
i,
splitter='',
).lower() for i in citys_list
]
return dict(
zip(citys_pinyin,
[pinyin.get_pinyin(i, splitter='') for i in citys_list])).items()
def query_fulltext_code(code):
pinyin = Pinyin()
initials = []
for letter in pinyin.get_initials(code, splitter=' ').lower().split(' '):
if letter.isalpha():
initials.append(letter * 4)
logging.debug(initials)
analysed_code = pinyin.get_pinyin(code, splitter=u' ') + ' ' + ' '.join(initials)
logging.debug(analysed_code)
clause = "MATCH(`codepinyin`, `codepinyininitials`) AGAINST (%s)"
query = yield dbutil.do(Event.select(SQL('*, ' + clause + ' AS similarity', analysed_code)).where(
SQL(clause, analysed_code)).limit(4).dicts)
events = [event for event in query]
logging.debug(events)
return events
def insert_shortname(self): # 一次性产生全部用户的拼音首字母大写
conn = self.init_db()
cur = conn.cursor()
row = cur.execute("select * from 35txl") # 显示这个数据表有多少行
x = cur.fetchall()
p = Pinyin()
sqli = "update 35txl set shortname=%s where id=%s" # 35txl为表名
i = 0
while (i < row):
shortname = p.get_initials(x[i][1], u'')
i = i + 1
cur.execute(sqli, (shortname, i))
cur.close()
conn.commit()
conn.close()
def save(self, without_valid=False, *args, **kwargs):
print("------- save vod -------")
p = Pinyin()
full_pinyin = p.get_pinyin(smart_str(self.title), '')
first_pinyin = p.get_initials(smart_str(self.title), '').lower()
self.search_word = " ".join([full_pinyin, first_pinyin])
print("video path:", self.video)
if self.description is None or self.description == "":
self.description = default_description(self)
if self.local_video != '' and self.local_video is not None:
basename = Path(self.local_video).relative_to(Path(settings.LOCAL_MEDIA_ROOT))
self.video.name = str(Path(settings.LOCAL_MEDIA_URL) / basename)
print("save local_video to filefield done")
if without_valid:
ret = super(Vod, self).save(*args, **kwargs)
return ret
super(Vod, self).save(*args, **kwargs)
try:
if self.video != None and self.video != '':
basename = Path(self.video.name).name # Djan%20go.mp4
rel_name = uri_to_iri(basename) # Djan go.mp4
# Make sure the self.video.name is not in the LOCAL_FOLDER
if not self.video.name.startswith(settings.LOCAL_FOLDER_NAME) and \
not self.video.name.startswith(settings.RECORD_MEDIA_FOLDER):
self.video.name = str(Path(self.save_path) / rel_name)
print("save_path:", self.save_path)
print(self.video.name)
print('size:', self.video.file.size)
self.file_size = humanfriendly.format_size(self.video.file.size)
# duration = VideoFileClip(self.video.path).duration
# self.duration = time_formate(duration)
# print(self.duration)
else:
print("video file is None")
except:
pass
try:
if self.image:
# self.image.name = os.path.join(self.save_path, os.path.basename(uri_to_iri(self.image.name)))
self.image.name = Path(self.save_path) / Path(uri_to_iri(self.image.name)).name
except:
pass
return super(Vod, self).save(*args, **kwargs)
def nameSpy(fo):
p = Pinyin()
name_dict = dict()
name_dict_2 = dict()
'''建两个字典，
第一个保存例如:zsw:张三五,张三无；zs:张三，张伞
第二个保存：sw:张三无，司三五 也就是两个字以上的名字的字的后两个字的简拼
'''
for line in fo:
# print(line.strip(),end="")
s = p.get_initials(line.strip(), u'').lower()
# print(s)
if s.__len__() > 2:
s_2 = s[-2:]
name_dict_2.setdefault(s_2, []).append(line.strip())
# 获取名字的简拼，"王五六"->"wwl"
name_dict.setdefault(s, []).append(line.strip())
# 更新字典,这里字典的值为列表
return name_dict, name_dict_2
def new_topic(request):
"""创建新的主题"""
pinyin = Pinyin()
if request.method != 'POST':
#当操作为非提交数据时，则创建一个新的表单
form = TopicForm()
else:
#当操作为提交数据时，则对数据进行处理
form = TopicForm(request.POST)
if form.is_valid():
#获取post数据
new_topic = form.save(commit=False)
new_topic.name = pinyin.get_initials(new_topic.text, splitter='')
new_topic.save()
return HttpResponseRedirect(reverse('learning_logs:topics'))
context = {'form':form}
return render(request, 'learning_logs/new_topic.html', context)
def post(self):
try:
data = json.loads(self.request.body.decode())
logging.debug(data)
event = dict_to_model(Event, data)
event.createtime = datetime.datetime.now()
pinyin = Pinyin()
event.codepinyin = pinyin.get_pinyin(event.code, splitter=' ')
initials = []
for letter in pinyin.get_initials(event.code,
splitter=' ').lower().split(' '):
if letter.isalpha():
initials.append(letter * 4)
event.codepinyininitials = ' '.join(initials)
yield dbutil.do(event.save)
self.write(Response(status=1, msg='恭喜你，活动发布成功！', result={}).json())
ioloop.IOLoop.current().spawn_callback(event_service.create_qrcode,
event)
except Exception as e:
self.write(Response(msg='sorry，亲，活动发布失败').json())
logging.exception('CreateEventHandler error: {0}'.format(str(e)))
def post(self):
try:
data = json.loads(self.request.body.decode())
logging.debug(data)
event = dict_to_model(Event, data)
event.createtime = datetime.datetime.now()
pinyin = Pinyin()
event.codepinyin = pinyin.get_pinyin(event.code, splitter=' ')
initials = []
for letter in pinyin.get_initials(event.code, splitter=' ').lower().split(' '):
if letter.isalpha():
initials.append(letter * 4)
event.codepinyininitials = ' '.join(initials)
yield dbutil.do(event.save)
self.write(Response(
status=1, msg='恭喜你，活动发布成功！',
result={}
).json())
ioloop.IOLoop.current().spawn_callback(event_service.create_qrcode, event)
except Exception as e:
self.write(Response(msg='sorry，亲，活动发布失败').json())
logging.exception('CreateEventHandler error: {0}'.format(str(e)))
def new_entry(request, topic_name):
"""在特定的主题中创建新的科目"""
pinyin = Pinyin()
topic = Topic.objects.get(name=topic_name)
if request.method != 'POST':
#当操作为非提交数据时，则创建一个新的表单
form = EntryForm()
else:
#当操作为提交数据时，则对数据进行处理
form = EntryForm(data=request.POST)
if form.is_valid():
new_entry = form.save(commit=False)
new_entry.topic = topic
new_entry.name = pinyin.get_initials(new_entry.text, splitter='')
new_entry.save()
return HttpResponseRedirect(reverse('learning_logs:entries', args=[topic.name]))
context = {'topic':topic, 'form':form}
return render(request, 'learning_logs/new_entry.html', context)
def get_site_from_csv():
p = Pinyin()
now = get_now_time_with_timezone()
py_list = []
with codecs.open('ip.csv', encoding='utf-8') as f1:
for line in f1:
name, bos, fuel = line.split(',')
py = p.get_initials(name, '').replace(' ', '')
if py in py_list:
py = '{0}{1}'.format(py, random.randint(0, 100))
py_list.append(py)
site = Site()
site.name = name
site.fuel_server = fuel.strip()
site.bos_server = bos.strip()
site.slug = py
site.create_time = now
site.modify_time = now
site.original_create_time = now
site.check = False
site.lock = 1000
session.add(site)
session.commit()
def run(self):
try:
p = Pinyin()
for stock in self.stocks:
no = stock.get('no')
request = urllib2.Request('http://hq.sinajs.cn/list=' + self.get_stock_with_prefix(no))
response = urllib2.urlopen(request)
result = response.read().decode('gbk')
text = re.sub('var.+=[^"]*"', '', result)
infos = text.split(',')
stockName = p.get_initials(self.strQ2B(infos[0]), u'')
yesterdayPrice = float(infos[2])
curPrice = float(infos[3])
percent = (curPrice / yesterdayPrice - 1) * 100,
percentStr = str('%0.2f'%percent) + "%"
self.priceList.append({'no':no, 'name':stockName, 'percent': percentStr})
return
except (urllib2.HTTPError) as (e):
err = '%s: HTTP error %s contacting API' % (__name__, str(e.code))
except (urllib2.URLError) as (e):
err = '%s: URL error %s contacting API' % (__name__, str(e.reason))
sublime.error_message(err)
def new_blog(request, topic_name, entry_name):
"""在特定主题中的某个科目下创建新的条目"""
pinyin = Pinyin()
topic = Topic.objects.get(name=topic_name)
entry = Entry.objects.get(name=entry_name)
if request.method != 'POST':
#当操作为非提交数据时，则创建一个新的表单
form = BlogForm()
else:
#当操作为提交数据时，则对数据进行处理
form = BlogForm(data=request.POST)
if form.is_valid():
new_blog = form.save(commit=False)
new_blog.entry = entry
new_blog.owner = request.user
new_blog.name = pinyin.get_initials(new_blog.title, splitter='')
new_blog.save()
return HttpResponseRedirect(reverse('learning_logs:blogs', args=[topic_name, entry_name]))
context = {'topic':topic,'entry':entry, 'form':form}
return render(request, 'learning_logs/new_blog.html', context)
def parse(self, response):
print('==> %s' % response.url)
p = Pinyin()
try:
for tr in response.xpath('//tr[@class="provincetr"]'):
for td in tr.xpath('td'):
item = RegionItem()
item['adCode'] = td.xpath('a/@href')[0].extract()[0:-5]
item['name'] = td.xpath('a/text()')[0].extract()
item['py'] = p.get_pinyin(item['name'], ' ')
item['initial'] = p.get_initials(item['name'], '')[0:1]
item['level'] = 1
item['parent'] = ''
yield item
url = 'http://www.stats.gov.cn/tjsj/tjbz/tjyqhdmhcxhfdm/2017/%s.html' % item[
'adCode']
request = scrapy.Request(url,
callback=self.parse_city,
dont_filter=True)
request.meta['pid'] = item['adCode']
yield request
except IndexError:
pass
def lev():
arith = arithmetic()
pinyindisdic = {}
initialdisdic = {}
disdic = {}
sym_pinyin_dic = {}
sym_initial_dic = {}
drug_pinyin_dic = {}
drug_initial_dic = {}
with open("sym_pinyin.txt", "r") as f:
data = f.readlines()
for i in data:
sym_pinyin_dic[i.split(':')[1].split()[0]] = i.split(':')[0]
with open("sym_initial.txt", "r") as f:
data = f.readlines()
for i in data:
sym_initial_dic[i.split(':')[1].split()[0]] = i.split(':')[0]
with open("drug_pinyin.txt", "r") as f:
data = f.readlines()
for i in data:
drug_pinyin_dic[i.split(':')[1].split()[0]] = i.split(':')[0]
with open("drug_initial.txt", "r") as f:
data = f.readlines()
for i in data:
drug_initial_dic[i.split(':')[1].split()[0]] = i.split(':')[0]
with open("trie.txt", "r") as f:
data = f.readlines()
data = [codeutil(i.split()[0]) for i in data]
p = Pinyin()
input_word = data[0]
pinyin = p.get_pinyin(input_word, '')
initial = p.get_initials(input_word, '')
#print input_word,pinyin,initial
for i in data[1:]:
disdic[i] = arith.levenshtein(data[0], i)
f = zip(disdic.values(), disdic.keys())
f = sorted(f)
minf = f[0][0]
#print sym_pinyin_dic.keys()[:5]
for i in f:
if pinyin in sym_pinyin_dic and i[0] == minf:
#print pinyin
if pinyin in drug_pinyin_dic and i[0] == minf:
#print drug_pinyin_dic[pinyin], pinyin, i[0]
pass
#print sym_pinyin_dic[pinyin],pinyin,i[0]
return sym_pinyin_dic[pinyin]
elif initial in sym_initial_dic and i[0] == minf:
if initial in drug_initial_dic and i[0] == minf:
#print drug_initial_dic[initial], initial, i[0]
pass
print sym_initial_dic[initial], initial, i[0]
return sym_initial_dic[initial]
else:
#print i[0],i[1]
return i[1]
#!/usr/bin/env python #-*- coding:UTF-8 -*- import sys; from xpinyin import Pinyin p = Pinyin() # default splitter is `-` print p.get_pinyin(u"上海") # show tone marks print p.get_pinyin(u"上海", show_tone_marks=True) # remove splitter print p.get_pinyin(u"上海", '') # set splitter as whitespace print p.get_pinyin(u"上海", ' ') print p.get_initial(u"上") print p.get_initials(u"上海") print p.get_initials(u"上海", u'') print p.get_initials(u"上海", u' ') #如果方法中传入变量，那么直接加前缀是不可以了。而是要将变量转为utf-8编码： wordvalue = '中国' wordvalue= unicode(wordvalue,'utf-8') s = p.get_initials(wordvalue, u'').lower() print s
