def searchRecursive( node, letter, word, previousRow, results, maxCost ):
columns = len( word ) + 1
currentRow = [ previousRow[0] + 1 ]
# Build one row for the letter, with a column for each letter in the target
# word, plus one for the empty string at column 0
for column in xrange( 1, columns ):
insertCost = currentRow[column - 1] + 1
deleteCost = previousRow[column] + 1
if word[column - 1] == letter or pinyin.get(word[column - 1])==pinyin.get(letter):
replaceCost = previousRow[ column - 1 ]
else:
replaceCost = previousRow[ column - 1 ] + 1
currentRow.append( min( insertCost, deleteCost, replaceCost ) )
# if the last entry in the row indicates the optimal cost is less than the
# maximum cost, and there is a word in this trie node, then add it.
if currentRow[-1] <= maxCost and node.word != None:
results.append( [node.word, currentRow[-1]] )
# if any entries in the row are less than the maximum cost, then
# recursively search each branch of the trie
if min( currentRow ) <= maxCost:
for letter in node.children:
searchRecursive( node.children[letter], letter, word, currentRow,
results, maxCost )
def test_numbers(self):
"""Test the get/get_consonant/get_vowel function for arabic numbsers
"""
self.assertEqual(pinyin.get('2'), u'er')
self.assertEqual(pinyin.get('1234567890'), u'yiersansiwuliuqibajiuling')
self.assertEqual(pinyin.get_consonant('1'), u'y')
self.assertEqual(pinyin.get_vowel('1'), u'i')
def insertMongo(cont):
print(type1+'#########')
print(type2+'#########')
print(type3+'#########')
global keyword
global key
global value
keyword = []
tech = []
if cont == None:
pass
tech = [{"名称":[type3]},]
flaga = 0
for item in content:
words = wordslist()
for word in words:
name = word[0].strip('\n')
name = name.strip(" ")
datasource = word[1]
# print('--------------%r-------------' % word)
if name in item:
keyword +=((name,datasource),)
if '【' in item:
if flaga == 1:
tech += [{key:value},]
#print("key=="+key+"value: :"+str(value)+'\n\n\n')
else: flaga=1
item = item.replace('【','')
item = item.replace('】','')
key = item.replace(' ','')
key = key.strip('\n')
value = []
continue
else:
value.append(item)
#print("key=="+key+"value::"+str(value)+'\n\n\n')
tech += [{key:value},]
keyword = set(keyword)
result = []
for i in list(keyword):
keysss = {}
keysss["name"] = i[0]
keysss["datasource"] = i[1]
result += [keysss,]
key_word = {"keyword":result}
tech = {"content":tech}
tech.update(key_word)
rank = (("rankone",type1.strip('\n')),("ranktwo",type2.strip('\n')),("rankthree",type3.strip('\n')),("source","diag_rule"),)
tech.update(dict(rank))
sort = (("sortrankone",pinyin.get(str(type1).strip('\n'))),("sortranktwo",pinyin.get(str(type2).strip('\n'))),("sortrankthree",pinyin.get(str(type3).strip('\n'))),)
index = {"index":type3.strip('\n')}
tech.update(index)
tech.update(sort)
#w.write(str(type3).strip('\n')+"$$"+"diag_rule"+"\n")
knowledgeBase.insert(tech)
print(tech)
def Line5():
noun = open('../data/freqword_n.txt', encoding='utf-8').readlines()
verb = open('../data/freqword_v.txt', encoding='utf-8').readlines()
nounlist = []
for word in noun:
# outfile.write(pinyin.get(word, format="strip")+" ")
i = 0
while i<len(word):
if word[i:i+2]!="\n":
nounlist.append(word[i:i+2])
i=i+3
verblist = []
for word in verb:
i = 0
while i<len(word):
if word[i:i+2]!="\n":
verblist.append(word[i:i+2])
i=i+3
# sentence = ""
count = 0
num = 0
rhythm = ""
rhythmList = ["a", "e", "i", "o", "u"]
while num < 4:
i = random.randint(1, len(nounlist)-1)
i1 = random.randint(1, len(nounlist)-1)
j = random.randint(1, len(verblist)-1)
ind = 0
ind1 = 0
if (num == 1):
rhythm = ""
verse = pinyin.get(nounlist[i1][1], format="strip")
for p in range(len(verse)-1, -1, -1):
if verse[p] in rhythmList:
ind = p
rhythm = verse[ind:len(verse)]
if (num == 3):
ind1 = 0
verse1 = pinyin.get(nounlist[i1][1], format="strip")
for p in range(len(verse1)-1, -1, -1):
if verse1[p] in rhythmList:
ind1 = p
while verse1[ind1: len(verse1)] != rhythm:
i1 = random.randint(1, len(nounlist)-1)
verse1 = pinyin.get(nounlist[i1][1], format="strip")
for p in range(len(verse1)-1, -1, -1):
if verse1[p] in rhythmList:
ind1 = p
print(nounlist[i]+verblist[j][1]+nounlist[i1])
num += 1
def test_init_contact(self):
"""
初始化联系信息
"""
import xlrd
book = xlrd.open_workbook('d:/a.xls')
sheet = book.sheets()[0]
max_row = sheet.nrows
print 'begin init database'
name_dict = {}
max_row = 3
for i in range(2, max_row):
print 'row', i
dept = sheet.row_values(i)[1].encode("utf-8").strip()
job = sheet.row_values(i)[2].encode("utf-8").strip()
name = sheet.row_values(i)[3].encode("utf-8").strip()
name_pinyin = pinyin.get(name)
name_shot = pinyin.get_initial(name, '')
username = name_pinyin
mobile = str(sheet.row_values(i)[4])
telephone = str(sheet.row_values(i)[5])
innerphone = str(sheet.row_values(i)[6])
fax = str(sheet.row_values(i)[7])
#去掉那些float的.
mobile = self.remove_dot(mobile)
telephone = self.remove_dot(telephone)
innerphone = self.remove_dot(innerphone)
fax = self.remove_dot(fax)
#统计重复的名字拼音
if name_pinyin in name_dict:
username = username + str(name_dict[name_pinyin])
name_dict[name_pinyin] += 1
pass
else:
name_dict[name_pinyin]=1
print name, job, mobile, telephone, innerphone, fax, dept, pinyin.get(name), name_shot, username
#创建到数据库
user = User.objects.get(username='******');
qbinfo = QBContactInfo(duty=job, mobile=mobile, telephone=telephone, innerphone=innerphone, fax=fax)
qbinfo.user = user
qbinfo.save()
print len(name_dict)
print name_dict
print 'end'
def test_get(self):
self.assertEqual(pinyin.get('你好'),
pinyin.get('你好', format="diacritical"))
self.assertEqual(pinyin.get(u('你好'), format="strip"), u('nihao'))
self.assertEqual(pinyin.get(u('你好'), format="numerical"), u('ni3hao3'))
self.assertEqual(pinyin.get(u('你好'), format="diacritical"), u('nǐhǎo'))
self.assertEqual(pinyin.get('你好吗?'), u('nǐhǎoma?'))
self.assertEqual(pinyin.get('你好吗？'), u('nǐhǎoma？'))
self.assertEqual(pinyin.get('你好'), u('nǐhǎo'))
self.assertEqual(pinyin.get('叶'), u('yè'))
self.assertEqual(pinyin.get('少女'), u('shǎonv̌'))
def parse_small_city(self, response):
item = response.meta['item']
request_list = []
url_set = set()
#category
category_url_list = response.xpath('//li[@class="term-list-item"]//ul[@class="desc Fix"]//li/a[starts-with(@onclick, "pageTracker._trackPageview(\'dp_home_food_hotdaohang_fenlei")]/@href').extract()
category_list = response.xpath('//li[@class="term-list-item"]//ul[@class="desc Fix"]//li/a[starts-with(@onclick, "pageTracker._trackPageview(\'dp_home_food_hotdaohang_fenlei")]/text()').extract()
#area
region_data = response.xpath('//div[@class="pop-panel ep_quick-search ep_quick-search-regions Fix"]/div[@class="dp-option-wrap"]/dl').extract()
for region in region_data:
region_html = Selector(text=region)
region_id = region_html.xpath('//dt/a/@data-value').extract()[0].strip()
region = region_html.xpath('//dt/a/strong/text()').extract()[0].strip('[]\n\r\t ')
area_list = region_html.xpath('//ul/li/a/text()').extract()
area_id_list = region_html.xpath('//ul/li/a/@data-value').extract()
for area_index, area in enumerate(area_list):
for cate_index, category in enumerate(category_list):
one_item = deepcopy(item)
one_item['category'] = category.strip()
one_item['region'] = region.strip()
one_item['region_code'] = pinyin.get(one_item['region'])
one_item['area'] = area.strip()
one_item['area_code'] = pinyin.get(one_item['area'])
url = "".join(['http://www.dianping.com', category_url_list[cate_index], 'r', area_id_list[area_index]])
small_city_xx_cnt += 1
print('大城市商圈分类url数量:\t'+str(small_city_xx_cnt))
print(url)
print(one_item['city'])
print(one_item['category'])
print(one_item['area'])
if url not in url_set:
url_set.add(url)
else:
continue
global small_city_xx_cnt
request_list.append(Request(url,
method='GET',
meta={'item': one_item},
headers=headers,
cookies=None,
body=None,
priority=0,
errback=None,
encoding=response.encoding,
callback=self.parse_restaurant_list))
return request_list
def parse_big_city(self, response):
item = response.meta['item']
request_list = []
url_set = set()
#category
category_id_list = response.xpath('//div[@class="secondary-category J-secondary-category"]/a[starts-with(@onclick, "pageTracker._trackPageview(\'dp_head_guangzhou_food_fenlei")]/@href').extract()
category_list = response.xpath('//div[@class="secondary-category J-secondary-category"]/a[starts-with(@onclick, "pageTracker._trackPageview(\'dp_head_guangzhou_food_fenlei")]/text()').extract()
#area
js = re.search('<script class="J_auto-load" type="text/plain">([\s\S]*?)</script>', response.body).group(1)
data = Selector(text=js)
region_data = data.xpath('//div[@class="fpp_business"]//dl').extract()
for region in region_data:
region_html = Selector(text=region)
region = region_html.xpath('//dt/a/text()').extract()[0].strip('[]\n\r\t ')
area_list = region_html.xpath('//li/a/text()').extract()
area_url_list = region_html.xpath('//li/a/@href').extract()
for area_index, area in enumerate(area_list):
for cate_index, category in enumerate(category_list):
one_item = deepcopy(item)
one_item['category'] = category.strip()
one_item['region'] = region
one_item['region_code'] = pinyin.get(one_item['region'])
one_item['area'] = area.strip()
one_item['area_code'] = pinyin.get(one_item['area'])
url = "".join(['http://www.dianping.com', area_url_list[area_index], 'g', category_id_list[cate_index]])
print('大城市商圈分类url数量:\t'+str(big_city_xx_cnt))
print(one_item['city'])
print(one_item['category'])
print(one_item['area'])
print(url)
if url not in url_set:
url_set.add(url)
else:
continue
global big_city_xx_cnt
big_city_xx_cnt += 1
request_list.append(Request(url,
method='GET',
meta={'item': one_item},
headers=headers,
cookies=None,
body=None,
priority=0,
errback=None,
encoding=response.encoding,
callback=self.parse_restaurant_list))
return request_list
def makeVariants(ptxt):
ptxt = ptxt.strip()
plst = list(ptxt)
for i in range(0, len(plst), 1):
plst[i] = pinyin.get(plst[i])
roman = u'.'.join(plst)
en = pinyin.get(ptxt)
try:
en = en[0].upper() + en[1:].lower()
except:
print ptxt
print en
raise
return [ptxt, roman, en]
def register(request):
if request.method == 'POST':
form = UserCreationForm(request.POST)
if form.is_valid():
cd = form.cleaned_data
new_user = form.save()
new_user.first_name = cd['first_name']
new_user.last_name = cd['last_name']
new_user.email = cd['username']
new_user.save()
aDomain = pinyin.get('-'.join(cd['first_name'] + cd['last_name']))
regex = '^' + aDomain + '(-\d+)?'
same_name = AccountModel.objects.filter(
aDomain__regex=regex).order_by('-aUser__id')
if not same_name:
p = AccountModel(aUser=new_user, aDomain=aDomain)
else:
the_last = same_name[0].aDomain
regex1 = re.compile('^' + aDomain + '$')
regex2 = re.compile('^' + aDomain + '-(\d+)')
match1 = re.match(regex1, the_last)
match2 = re.match(regex2, the_last)
if match1:
p = AccountModel(aUser=new_user, aDomain=aDomain + '-1')
else:
match2.group(1)
p = AccountModel(
aUser=new_user, aDomain=aDomain + '-' + str(int(match2.group(1)) + 1))
p.save()
return redirect("/register")
else:
form = UserCreationForm()
ctx = {'form': form}
ctx.update(csrf(request))
return render(request, "register.html", ctx)
def get_role2feature_info(domain_name, role_name):
domain_pinyin = pinyin.get(domain_name, format='strip', delimiter='_')
role_name_en = domain_ch2en_dict[role_name]
_id = domain_pinyin + '_' + role_name_en
try:
es_result = es.get(index=weibo_role_index_name,
doc_type=weibo_role_index_type,
id=_id)['_source']
feature_info_dict = es_result
feature_filter_dict = dict()
feature_filter_dict['political_side'] = json.loads(
feature_info_dict['political_side'])
try:
feature_filter_dict['psy_feature'] = json.loads(
feature_info_dict['psy_feature'])
except:
feature_filter_dict['psy_feature'] = []
#print
return feature_filter_dict
except:
return []
def add(self, town):
cursor = connection.cursor()
cursor.execute("INSERT INTO town (id, province, city, county, name, " \
"pinyin) VALUES (?, ?, ?, ?, ?, ?)",
(town.id, town.county.city.province.id, town.county.city.id,\
town.county.id, town.name, pinyin.get(town.name),))
connection.commit()
def add(self, county):
cursor = connection.cursor()
cursor.execute("INSERT INTO county (id, province, city, name, pinyin)" \
" VALUES (?, ?, ?, ?, ?)",
(county.id, county.city.province.id, county.city.id, \
county.name, pinyin.get(county.name),))
connection.commit()
def to_city(self, var_str, type):
if isinstance(var_str, str):
if var_str == 'None':
return ''
else:
stringHead = ''
stringFull = ''
for single in var_str:
stringFull += pinyin.get(single, format='strip', delimiter="")
stringHead += pinyin.get(single, format='strip', delimiter="")[0]
if type == "FULL":
return stringFull
elif type == "HEAD":
return stringHead
else:
return ''
def get_add_opinion_corpus(task_detail):
mark = False
corpus_name = task_detail['corpus_name']
corpus_pinyin = pinyin.get(corpus_name, format='strip', delimiter='_')
item_dict = {}
item_dict['corpus_name'] = corpus_name
item_dict['corpus_pinyin'] = corpus_pinyin
item_dict['submitter'] = task_detail['submitter']
item_dict['status'] = 0
try:
es.get(index=opinion_corpus_index_name,
doc_type=opinion_corpus_index_type,
id=corpus_pinyin)
return 'exists'
except:
try:
es.index(index=opinion_corpus_index_name,
doc_type=opinion_corpus_index_type,
body=item_dict,
id=corpus_pinyin)
mark = True
r_r.lpush(opinion_expand_task_queue_name, json.dumps(item_dict))
except:
pass
return mark
def upload():
if request.method == 'POST':
file_val = request.files['file']
# print('filename:', file_val.filename)
if file_val and allowed_file(file_val.filename):
ascii_name = pinyin.get(file_val.filename)
filename = secure_filename(ascii_name)
file_path = os.path.join(current_app.config['UPLOAD_FOLDER'], filename)
file_val.save(file_path)
# cloud_sight
try:
cloud_img = CloudImage(file=open(file_path, 'rb'), locale=LOCALE, lang=LANG)
except:
return jsonify(type='mistake', content=None)
try:
os.remove(file_path)
except:
print('Remove failed. file not found.')
if cloud_img:
result = cloud_img.result()
if result:
# print('result is', result.encode('utf-8'))
return jsonify(type='result', content=result)
else:
print('result is None')
return jsonify(type='mistake', content=None)
else:
print('cloud_img is None')
return jsonify(type='mistake', content=None)
def search(query,tag):
if tag=='song':
songid=anydbm.open('id_song.db','r')
daopai=anydbm.open('daopai_song.db','r')
elif tag=='singer':
songid=anydbm.open('id_singer.db','r')
daopai=anydbm.open('daopai_singer.db','r')
elif tag=='both':
songid=anydbm.open('id_both.db','r')
daopai=anydbm.open('daopai_both.db','r')
counthash={}
out=[]
for i in query.decode('utf-8'):
try:
if i>= u'\u4e00' and i<=u'\u9fa5':
idstr2=daopai[pinyin.get(i)]
ids2=idstr2.split(' ')
idstr=daopai[i.encode('utf-8')]
ids=idstr.split(' ')
counthash = mat2hash(ids,counthash)
except:
continue
keys=sorted(counthash.iteritems(),key=lambda counthash:counthash[1],reverse=True)
loop=0
for i in keys:
if loop>100:break
newsong=songid[i[0]]
out.append(newsong)
loop+=1
return out
def domain_create_task(domain_name,create_type,create_time,submitter,description,remark,compute_status=0):
task_id = pinyin.get(domain_name,format='strip',delimiter='_')
try:
es.get(index=weibo_domain_index_name,doc_type=weibo_domain_index_type,id=task_id)['_source']
return 'domain name exists!'
except:
try:
domain_task_dict = dict()
#domain_task_dict['xnr_user_no'] = xnr_user_no
domain_task_dict['domain_pinyin'] = pinyin.get(domain_name,format='strip',delimiter='_')
domain_task_dict['domain_name'] = domain_name
domain_task_dict['create_type'] = json.dumps(create_type)
domain_task_dict['create_time'] = create_time
domain_task_dict['submitter'] = submitter
domain_task_dict['description'] = description
domain_task_dict['remark'] = remark
domain_task_dict['compute_status'] = compute_status
r.lpush(weibo_target_domain_detect_queue_name,json.dumps(domain_task_dict))
item_exist = dict()
#item_exist['xnr_user_no'] = domain_task_dict['xnr_user_no']
item_exist['domain_pinyin'] = domain_task_dict['domain_pinyin']
item_exist['domain_name'] = domain_task_dict['domain_name']
item_exist['create_type'] = domain_task_dict['create_type']
item_exist['create_time'] = domain_task_dict['create_time']
item_exist['submitter'] = domain_task_dict['submitter']
item_exist['description'] = domain_task_dict['description']
item_exist['remark'] = domain_task_dict['remark']
item_exist['group_size'] = ''
item_exist['compute_status'] = 0 # 存入创建信息
es.index(index=weibo_domain_index_name,doc_type=weibo_domain_index_type,id=item_exist['domain_pinyin'],body=item_exist)
mark = True
except:
mark =False
return mark
def get_show_domain_group_detail_portrait(domain_name):
domain_pinyin = pinyin.get(domain_name, format='strip', delimiter='_')
es_result = es.get(index=tw_domain_index_name,doc_type=tw_domain_index_type,\
id=domain_pinyin)['_source']
member_uids = es_result['member_uids']
es_mget_result = es_user_portrait.mget(index=portrait_index_name,doc_type=portrait_index_type,\
body={'ids':member_uids})['docs']
result_all = []
for result in es_mget_result:
item = {}
item['uid'] = ''
item['nick_name'] = ''
item['photo_url'] = ''
item['domain'] = ''
item['sensitive'] = ''
item['location'] = ''
item['fans_num'] = ''
item['friends_num'] = ''
# item['gender'] = ''
item['home_page'] = ""
item['influence'] = ''
if result['found']:
item['uid'] = result['_id']
result = result['_source']
if result.has_key('uname'):
item['nick_name'] = result['uname']
if result.has_key('photo_url'):
item['photo_url'] = result['photo_url']
if result.has_key('domain'):
item['domain'] = result['domain']
if result.has_key('sensitive'):
item['sensitive'] = result['sensitive']
if result.has_key('location'):
item['location'] = result['location']
if result.has_key('fansnum'):
item['fans_num'] = result['fansnum']
if result.has_key('friends_num'):
item['friends_num'] = result['friendsnum']
# item['gender'] = result['gender']
if result.has_key('screenname'):
item['home_page'] = "https://twitter.com/" + result[
'screenname']
if result.has_key('influence'):
item['influence'] = get_influence_relative(
item['uid'], result['influence'])
# else:
# item['uid'] = result['_id']
# item['nick_name'] = ''
# item['photo_url'] = ''
# item['domain'] = ''
# item['sensitive'] = ''
# item['location'] = ''
# item['fans_num'] = ''
# item['friends_num'] = ''
# # item['gender'] = ''
# item['home_page'] = ""
# item['influence'] = ''
result_all.append(item)
return result_all
def assembly(self, imgs, categorys):
print('Assembly data begins...')
results = []
wb = xlrd.open_workbook('sources/data-2019.10.31.xlsx')
total = 0
for si in range(wb.nsheets):
sh = wb.sheet_by_index(si)
rows = sh.nrows - 2
total += rows
category = categorys[sh.name]
prefix = pinyin.get_initial(sh.name, '').upper()
print('************* %s: %drows *************' % (sh.name, rows))
for ri in range(2, sh.nrows):
ind = int(sh.cell_value(ri, 0))
name = sh.cell_value(ri, 1).strip()
unit = sh.cell_value(ri, 2).strip()
price = sh.cell_value(ri, 3)
ptype = sh.row(ri)[3].ctype
if ptype == 1:
price = price.strip()
yind = price.find('元')
if yind != -1:
price = float(price[:yind])
else:
price = 0.0
elif ptype == 0:
price = 0.0
imgpath = None
try:
imgpath = imgs['%s%d' % (pinyin.get(sh.name[:2],
format='strip'), ind)]
except Exception as e:
print('Image not found: %s(%s)' % (name, e))
row = {
'id': str(uuid.uuid1()).replace('-', ''),
'numeration': '%s%06d' % (prefix, ind),
'name': name,
'img': imgpath,
'price': price,
'unit': unit,
'specs': '%.2f/%s' % (price, unit),
'amount': 0,
'category': category,
'enabled': 1,
'create_by': 'admin',
'create_time': datetime.datetime.now()
}
results.append(row)
print('End of assembly data. Total: %d rows.' % total)
return results
def _sent_pyin(self,sent):
"""
return the pinyin of sent
:param sent:
:return:
"""
pyins = pinyin.get(sent, delimiter= ' ', format='strip')
return pyins
def xm_pinyin(name_list): for n in name_list: try: xm = pinyin.get(n, format="strip") yield xm except Exception as e: yield None
def getCityPinYin():
import pinyin
sql_str = "select city_name from city where parent_id <> 0 and parent_id <> 2"
res = sqlExecute(sql_str)
res_pinyin = []
for item in res:
res_pinyin.append(pinyin.get(item, format='strip'))
return res_pinyin
def get_audio():
r = sr.Recognizer()
with sr.Microphone() as source:
r.adjust_for_ambient_noise(source)
audio = r.listen(source)
said = ''
try:
said = r.recognize_google(audio, language='zh-CN')
transText = ts.sogou(said, from_language='zh', to_language='en')
print(said + '\n')
print(pinyin.get(said, format="strip", delimiter=" ") + '\n')
print(pinyin.get(said, format="numerical") + '\n')
print(transText + '\n')
except Exception as e:
print('L2ChineseBruh :) ' + str(e))
return said.lower()
def get_string_with_only_char_in_list(col, char_list=var_name_char_list):
col = pinyin.get(col, format="strip")
res = u""
for ch in col:
if ch in char_list:
res += ch
col = res
return col
def to_pinyin(var_str):
if (isinstance(var_str, str) or isinstance(var_str, unicode)):
if var_str == 'None':
return ""
else:
return pinyin.get(var_str, format='strip', delimiter="")
else:
return 'wrong'
def api_sentence_jieba():
r = request.get_json()
return jsonify([{
"word":
seg,
"pinyin":
pinyin.get(seg) if regex.search(r"\p{IsHan}", seg) else ""
} for seg in jieba.cut(r["entry"])])
def get_delete_domain(domain_name):
domain_pinyin = pinyin.get(domain_name,format='strip',delimiter='_')
try:
es.delete(index=fb_domain_index_name,doc_type=fb_domain_index_type,id=domain_pinyin)
mark = True
except:
mark = False
return mark
def get_show_domain_role_info(domain_name, role_name):
domain_pinyin = pinyin.get(domain_name, format='strip', delimiter='_')
role_en = fb_domain_ch2en_dict[role_name]
task_id = domain_pinyin + '_' + role_en
es_result = es.get(index=fb_role_index_name,
doc_type=fb_role_index_type,
id=task_id)['_source']
return es_result
def to_pinyin(var_str):
if isinstance(var_str, str):
if var_str == 'None':
return ""
else:
return pinyin.get(var_str, format='strip', delimiter="")
else:
return '类型不对'
def get_export_example_model(domain_name,role_name):
domain_pinyin = pinyin.get(domain_name,format='strip',delimiter='_')
role_en = fb_domain_ch2en_dict[role_name]
task_id = 'fb_' + domain_pinyin + '_' + role_en
example_model_file_name = EXAMPLE_MODEL_PATH + task_id + '.json'
with open(example_model_file_name,"r") as dump_f:
es_result = json.load(dump_f)
return es_result
def generate_river_entitylist(table):
"""Get river entity list"""
nrows = table.nrows
riverlist = []
for i in range(nrows):
row = table.row_values(i)
while '' in row:
row.remove('')
UUID = str_uni('null')
valid_time = "21/11/2017"
transact_time = time.strftime("%d/%m/%Y")
tag = []
member = river_extract_restinfo.river_extract_member(row[0])
riverCode_dict = river_extract_restinfo.extract_riverCode()
member_riverCode = river_extract_restinfo.extract_member_riverCode(
row[0], riverCode_dict)
belongs_to = uni_str(row[2])
function = []
rule = []
coords = river_extract_coords.sort_river(
'H:\spatial entity\EXP_waterway\waterways.shp', uni_str(row[0]))
cpoint, bbox, ghcode = river_extract_restinfo.adapt_ghash(coords)
river_len = river_extract_restinfo.length(coords)
meta = dict(note=str_uni('null'),
precision=str_uni('null'),
produce_time=str_uni('null'),
producer=str_uni('null'),
security_level=str_uni('null'))
properties = dict(name=uni_str(row[0]),
type="river",
pinyin=pinyin.get(row[0], format='strip'),
length=repr(river_len) + "km",
riverCode=row[1],
ghashCode=ghcode)
relation = dict(flooded_area=str_uni('null'))
geometry = dict(Type="MultiLine",
coordinates=coords,
bbox=bbox,
center_point=cpoint,
version_time="21/11/2017",
SRID="EPSG 4326")
# generate a single_river_entity
single_river_entity = dict(UUID=UUID,
valid_time=valid_time,
transact_time=transact_time,
tag=tag,
member=member,
member_riverCode=member_riverCode,
belongs_to=belongs_to,
function=function,
rule=rule,
meta=meta,
propertities=properties,
relation=relation,
geometry=geometry)
riverlist.append(single_river_entity)
print("river entity transform done.")
return riverlist
def _get_unique_slug(self):
slug = pinyin.get(self.name, format='strip', delimiter='')
# slug = slugify(f"{self.name}")
unique_slug = slug
num = 1
while Group.objects.filter(slug=unique_slug).exists():
unique_slug = '{}-{}'.format(slug, num)
num += 1
return unique_slug
def next_vocab():
global index
vocab_list.append([])
vocab_list[index].append(var.get())
num_pinyin = pin.get(vocab_list[index][0], format='numerical')
vocab_list[index].append(num_pinyin)
print(len(vocab_list))
index += 1
master.switch_frame(SetChar)
def weather_month_history(city, year):
name_py = pinyin.get(city, format="strip", delimiter="")
citycode = city2code(name_py)
url = 'http://service.envicloud.cn:8082/v2/monthlymete/AMFJAY1JYWKXNTQYOTCXMJK2NZM0/%s/%s' % (
citycode, year)
payload = ""
headers = {'cache-control': "no-cache"}
response = re.request("GET", url, data=payload, headers=headers)
return json.loads(response.text)
def process_row(key, value):
import pinyin
out = ''
for i in value:
out += i
out += '\t'
out += pinyin.get(key, format='strip', delimiter=' ')
out += '\t1\n'
return out
def insertMongo(cont):
keyword = []
global key
global value
symps = []
if cont == None:
pass
symps=[{"症状名称":[type1]},]
flaga = 0
for item in content:
words = wordslist()
for word in words:
name = word[0].strip('\n')
name = name.strip(" ")
datasource = word[1]
# print('--------------%r-------------' % word)
if name in item:
keyword +=((name,datasource),)
if re.match(level2,item):
if flaga == 1:
symps += [{key:value},]
#print("key=="+key+"value::"+str(value)+'\n\n\n')
else: flaga=1
key = re.match(level2,item).group(1)
key = key.strip('\n')
value = []
continue
else:
value.append(item)
#print("key=="+key+"value::"+str(value)+'\n\n\n')
# sympton += ((key,value),)
keyword = set(keyword)
result = []
for i in list(keyword):
keysss = {}
keysss["name"] = i[0]
keysss["datasource"] = i[1]
result += [keysss,]
print(result)
key_word = {"keyword":result}
print(symps)
sympton = {"content":symps }
sympton.update(key_word)
rank = (("rankone",str(type1).strip('\n')),("ranktwo",""),("rankthree",""),("source","common_symptom"),)
sympton.update(dict(rank))
sort = (("sortrankone",pinyin.get(str(type1).strip('\n'))),("sortranktwo",""),("sortrankthree",""),)
index = {"index":str(type1).strip('\n')}
sympton.update(index)
sympton.update(dict(sort))
w.write(str(type1)+"$$"+"common_symptom"+"\n")
knowledgeBase.insert(sympton)
print(sympton)
def szm_pinyin(name_list):
for n in name_list:
try:
name = unicode(n, 'utf-8') # 转换unicode
szm = str(''.join([ pinyin.get(l, format="strip")[0] for l in list(name) ]))
yield szm
except Exception as e:
yield None
def move_to_pinyin():
global index
vocab_list.append([])
vocab_list[index].append(var.get())
num_pinyin = pin.get(vocab_list[index][0], format='numerical')
vocab_list[index].append(num_pinyin)
print(len(vocab_list))
index = 0
master.switch_frame(CheckPinyin)
def projectx_aliases(self, data_aliases, source):
#import pdb;pdb.set_trace()
px_aliases = []
for aliases in data_aliases:
if aliases.get("type") == 'alias' and aliases.get(
"source_name") == source:
px_aliases.append(
unidecode.unidecode(pinyin.get(aliases.get("alias"))))
return px_aliases
def before_import(self, dataset, dry_run, **kwargs):
schoolClasses = []
genders = []
universalFirstNames = []
universalLastNames = []
for row in dataset.dict:
schoolClass = self.get_schoolClass(row['学校'], row['班级'])
schoolClasses.append(schoolClass)
gender = self.get_gender(row['性别'])
genders.append(gender)
universalFirstNames.append(
pinyin.get(row['名'], format="strip").capitalize())
universalLastNames.append(
pinyin.get(row['姓'], format="strip").capitalize())
dataset.append_col(schoolClasses, header='schoolClass')
dataset.append_col(genders, header='gender')
dataset.append_col(universalFirstNames, header='universalFirstName')
dataset.append_col(universalLastNames, header='universalLastName')
def to_pinyin(var_str):
if isinstance(var_str, str):
if var_str == 'None':
return ""
else:
return pinyin.get(var_str, format='strip', delimiter="")
else:
return '类型不对'
def get_en_name(cn_names): # 不要拼音
en_names = []
for n in cn_names:
cn = n[:-2]
# en = pinyin.get(cn) # 默认有读音
en = pinyin.get(cn, format='strip', delimiter=' ') # 无拼音
en = ''.join([s.capitalize() for s in en.split(' ')])
en_names.append(n.replace(cn, en))
return en_names
def get_city_pinyin():
import pinyin
sql_str = "SELECT name FROM city WHERE parent_id <> 0"
cities_pinyin = []
for item in execute_sql(sql_str):
cities_pinyin.append(pinyin.get(item, format='strip'))
cities_pinyin.remove('zhongqing')
cities_pinyin.append('chongqing')
return cities_pinyin
def add(self, village):
cursor = connection.cursor()
cursor.execute("INSERT INTO village (id, province, city, county, " \
"town, category, name, pinyin) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
(village.id, village.town.county.city.province.id, \
village.town.county.city.id,\
village.town.county.id, village.town.id, village.category,
village.name, pinyin.get(village.name),))
connection.commit()
def add(self, village):
cursor = connection.cursor()
cursor.execute("INSERT INTO village (id, province, city, county, " \
"town, category, name, pinyin) VALUES (?, ?, ?, ?, ?, ?, ?, ?)",
(village.id, village.town.county.city.province.id, \
village.town.county.city.id,\
village.town.county.id, village.town.id, village.category,
village.name, pinyin.get(village.name),))
connection.commit()
def process_item(self, item, spider):
if spider.name not in ['meituan']:
return item
if self.filter_dic.get(item['restaurant_name']) == item['address']:
print(item['restaurant_name'])
print(item['address'])
raise DropItem("Duplicate item found: %s" % item)
else:
self.filter_dic[item['restaurant_name']] = item['address']
try:
item['lng'], item['lat'] = gaode_to_baidu(float(item['lng']), float(item['lat']))
item['province_code'] = pinyin.get(item['province'])
item['city_code'] = pinyin.get(item['city'])
item['region_code'] = pinyin.get(item['region'])
item['area_code'] = pinyin.get(item['area'])
except BaseException as e:
print(e)
return item
def ajax_get_macro_trendline():
task_name = request.args.get('task_name', '')
pinyin_task_name = pinyin.get(task_name.encode('utf-8'),
format='strip',
delimiter="_")
r_pinyin_task_name = "trendline_" + pinyin_task_name
results = r_trendline.get(r_pinyin_task_name)
return results
def ajax_get_macro_prediction():
task_name = request.args.get('task_name', '')
pinyin_task_name = pinyin.get(task_name.encode('utf-8'),
format='strip',
delimiter="_")
weibo_count, user_count, rank = get_macro_prediction_count(
pinyin_task_name)
return json.dumps([weibo_count, user_count, rank])
def test_get(self):
"""Test function pinyin.get
"""
self.assertEqual(pinyin.get('ÄãºÃ'), u'nihao')
self.assertEqual(pinyin.get('ÄãºÃÂð?'), u'nihaoma?')
self.assertEqual(pinyin.get('ÄãºÃÂð£¿'), u'nihaoma£¿')
self.assertEqual(pinyin.get('ÄãºÃ'), u'nihao')
self.assertEqual(pinyin.get('Ò¶'), u'ye')
self.assertEqual(pinyin.get('ÄãºÃ', " "), u'ni hao')
self.assertEqual(pinyin.get('ÄãºÃÂð?', " "), u'ni hao ma ?')
self.assertEqual(pinyin.get('ÄãºÃÂð£¿', " "), u'ni hao ma £¿')
def insertMongo(cont):
words = wordslist()
rank = ()
sort = ()
medic = []
keyword = ()
for word in words:
name = word[0].strip('\n')
name = name.strip(" ")
datasource = word[1]
if name in result:
keyword +=((name,datasource),)
names = med_name.split(' ')
name_med = names[0].strip('\n')
# print(names[0].strip('\n'))
rank = (("rankone",type1),("ranktwo",type2),("rankthree",name_med,))
rank += (("source","medicine"),)
index = {"index":name_med};
levela = re.compile('【(\w+)】([\w。；（(.)）、：~/，%]+)')
medic += [{'药品名称':med_name.strip('\n')},]
if type3:
medic += [{'药品类别':type3},]
item = re.finditer(levela,result)
for i in item:
medic += [{i.group(1).strip('￥'):i.group(2).strip('￥')},]
keyword = set(keyword)
res = []
for it in keyword:
keysss = {}
keysss["name"] = it[0]
keysss["datasource"] = it[1]
res += [keysss,]
key_word = {"keyword":res}
medic = {"content":medic}
meds = medic.copy()
meds.update(key_word)
meds.update(dict(rank))
sort = {"sortrankone":pinyin.get(str(type1).strip('\n')),"sortranktwo":pinyin.get(str(type2).strip('\n')),"sortrankthree":pinyin.get(str(med_name).strip('\n')),}
meds.update(sort)
meds.update(index)
print(meds)
mediciness.insert(meds)
def pinyin():
parser = argparse.ArgumentParser()
parser.add_argument("chars", help="Input chinese words")
args = parser.parse_args()
if not args.chars:
parser.print_help()
return
print(get(compat.u(args.chars)))
def import_qingbank_user(filepath=None):
import pinyin
import xlrd
import uuid
from dxc.services import api_contact, api_department
book = xlrd.open_workbook('d:/2014.xls')
sheet = book.sheets()[0]
max_row = sheet.nrows
print 'Begin init qingbank contact'
name_dict = {}
# max_row = 3
repeat_id = []
for i in range(1, max_row):
print str.format('{0}/{1}', i, max_row)
employee_id = sheet.row_values(i)[9].strip()
desc = None
if employee_id is None or employee_id=='':
employee_id = str(uuid.uuid1())
desc = u'非在编人员'
dept_name = sheet.row_values(i)[1].strip()
duty = sheet.row_values(i)[2].strip()
name = sheet.row_values(i)[3].strip()
name_pinyin = pinyin.get(name)
name_shot = pinyin.get_initial(name, '')
mobile = sheet.row_values(i)[4]
if isinstance(mobile, float):
mobile = str(int(mobile))
mobile.strip()
tel = sheet.row_values(i)[5]
if isinstance(tel, float):
tel = str(int(tel))
tel.strip()
fax = sheet.row_values(i)[6]
if isinstance(fax, float):
fax = str(int(fax))
fax.strip()
# 创建到数据库
user = user_datastore.get_user(employee_id + '@qingbank.cn')
if user is not None:
print 'already exist the same id: ' + user.username
user.contact.description = 'dept_name'
repeat_id.append(user.username)
continue
user = user_datastore.create_user(username=employee_id, password=name_pinyin, email=employee_id + '@qingbank.cn')
db.session.commit()
dept = api_department.first(name=dept_name)
if dept is None:
dept = api_department.create(name=dept_name)
api_contact.create(name=name, name_pinyin=name_pinyin, name_shot=name_shot,
user_id=user.id, department_id=dept.id, duty=duty, mobile=mobile, telephone=tel, fax=fax, description=desc)
print repeat_id
def get_cache_file(self, text):
delimiter = '#'
pys = pinyin.get(text, delimiter=delimiter)
if pys:
pys = pys.split(delimiter)
pys=[py for py in pys if re.match('[a-zA-Z]', py)]
pys = ''.join(pys)
pys = pys[:251-6-1]
suffix = hashlib.sha1(text+str(self.get_tts_session_params())).hexdigest()[:6]
filename = os.path.join(self.cache_dir, pys+'_'+suffix+'.wav')
return filename
def xm_pinyin(filename,newfile): with open(filename,'r') as f: for n in f.readlines(): try: name = pinyin.get(n.rstrip()) except: pass with open(newfile,'a') as ff: ff.writelines(name+'\n')
def srtHanziToPinyin(self):
"""
Converts all hanzi to pinyin
"""
subs_pinyin = {}
for key in self.srtDB:
one_sub = self.srtDB[key]
pin = pinyin.get(one_sub.subText)
new_sub = _SrtEntry(one_sub.subNumber, one_sub.timeFrame, pin)
subs_pinyin[key] = new_sub
return SrtObject(subs_pinyin)
def addPinyinToHanziSrt(self):
"""
Appends pinyin to hanzi text
"""
subs_merged = {}
for key in self.srtDB:
one_sub = self.srtDB[key]
pin = pinyin.get(one_sub.subText)
new_sub = _SrtEntry(one_sub.subNumber, one_sub.timeFrame,
one_sub.subText + pin)
subs_merged[key] = new_sub
return SrtObject(subs_merged)
def szm_pinyin(filename,newfile): with open(filename,'r') as f: for n in f.readlines(): try: name = unicode(n.rstrip(),'utf-8') # 转换unicode szm = ''.join([ pinyin.get(l)[0] for l in list(name)]) except: pass with open(newfile,'a') as ff: ff.writelines(szm+'\n')
def test_get(self):
self.assertEqual(pinyin.get('你好'), 'nihao')
self.assertEqual(pinyin.get(u('你好')), 'nihao')
self.assertEqual(pinyin.get('你好吗?'), 'nihaoma?')
self.assertEqual(pinyin.get('你好吗？'), u('nihaoma？'))
self.assertEqual(pinyin.get('你好'), 'nihao')
self.assertEqual(pinyin.get('叶'), 'ye')
def insertMongo(cont):
global key
global value
keyword = []
emergency = []
if cont == None:
pass
emergency = [{"症状名称":type1},]
flaga = 0
for item in content:
words = wordslist()
for word in words:
name = word[0].strip('\n')
name = name.strip(" ")
datasource = word[1]
# print('--------------%r-------------' % word)
if name in item:
keyword +=((name,datasource),)
if re.match(level1,item):
if flaga == 1:
emergency += [{key:value},]
#print("key=="+key+"value::"+str(value)+'\n\n\n')
else: flaga=1
key = re.match(level1,item).group(1)
key = key.strip('\n')
value = []
continue
else:
value.append(item)
#print("key=="+key+"value::"+str(value)+'\n\n\n')
emergency += [{key:value},]
#emergency = dict(emergency)
keyword = set(keyword)
result = []
for i in list(keyword):
keysss = {}
keysss["name"] = i[0]
keysss["datasource"] = i[1]
result += [keysss,]
print(result)
key_word = {"keyword":result}
emergency = {"content":emergency}
emergency.update(key_word)
rank = (("rankone",type1.strip('\n')),("ranktwo",""),("rankthree",""),("source","emergency"),)
emergency.update(dict(rank))
index = {"index":type1.strip('\n')}
sort = (("sortrankone",pinyin.get(str(type1).strip('\n'))),("sortranktwo",""),("sortrankthree",""),)
emergency.update(index)
emergency.update(dict(sort))
w.write(str(type1).strip('\n')+"$$"+"emergency"+"\n")
knowledgeBase.insert(emergency)
