def handle(school):
name = school[1]
match = []
if name.replace(' ', '').isalpha():
top = 2900110
else:
top = 34050
school_id = [k for k, v in SCHOOL_UNIVERSITY.iteritems() if v == name]
if not school_id:
match = [(i, find_lcs_len(v.encode('utf-8'), name.encode('utf-8')))
for i, v in SCHOOL_UNIVERSITY.iteritems() if i <= top]
match = sorted(match, key=lambda x: x[1], reverse=True)[:10]
print '\n--------%s--------\n' % name
get = getIndex('\n'.join([
'选择:\t' + str(match.index(i)) + ' ' + SCHOOL_UNIVERSITY[i[0]]
for i in match
]))
if get < 10:
school_id = match[get][0]
else:
school_id = 0
if school_id:
print '\n\n++++++%s++++++++' % SCHOOL_UNIVERSITY[school_id]
else:
school_id = school_id[0]
name = school[2]
match = []
depDict = defaultdict(str)
dep_id = 0
if name.replace(' ', ''):
if school_id and type(
school_id
) is int and school_id in SCHOOL_UNIVERSITY_DEPARTMENT_ID:
for id in SCHOOL_UNIVERSITY_DEPARTMENT_ID[school_id]:
depDict[id] = SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME[id]
else:
depDict = SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME
dep_id = []
for k, v in depDict.iteritems():
mlen = find_lcs_len(name.encode('utf-8'), v.encode('utf-8'))
if mlen > 3:
dep_id.append((k, mlen))
dep_id.sort(key=lambda x: x[1])
if not dep_id:
dep_id = 0
else:
dep_id = dep_id[0][0]
print name, SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME[dep_id]
return [school[0], school_id, dep_id]
def handleSchool(school):
school_id = [k for k,v in SCHOOL_UNIVERSITY.iteritems() if v==school[1]]
dep_id = [ k for k,v in SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME.iteritems() if v==school[2]]
if school_id and dep_id:
school_id=school_id[0]
dep_id=dep_id[0]
return (school[0],school_id,dep_id,school[3],school[4])
MANUAL_LIST.append(school)
def handle(school):
name = school[1]
match = []
if name.replace(' ', '').isalpha():
top = 2900110
else:
top = 34050
school_id = [k for k, v in SCHOOL_UNIVERSITY.iteritems() if v == name]
if not school_id:
match = [(i, find_lcs_len(v.encode('utf-8'), name.encode('utf-8'))) for i, v in SCHOOL_UNIVERSITY.iteritems() if i <= top]
match = sorted(match, key=lambda x:x[1], reverse=True)[:10]
print '\n--------%s--------\n'% name
get = getIndex('\n'.join(['选择:\t'+str(match.index(i))+' '+SCHOOL_UNIVERSITY[i[0]] for i in match]))
if get < 10:
school_id = match[get][0]
else:
school_id = 0
if school_id:
print '\n\n++++++%s++++++++'%SCHOOL_UNIVERSITY[school_id]
else:
school_id = school_id[0]
name = school[2]
match = []
depDict = defaultdict(str)
dep_id = 0
if name.replace(' ', ''):
if school_id and type(school_id) is int and school_id in SCHOOL_UNIVERSITY_DEPARTMENT_ID:
for id in SCHOOL_UNIVERSITY_DEPARTMENT_ID[school_id]:
depDict[id] = SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME[id]
else:
depDict = SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME
dep_id = []
for k,v in depDict.iteritems():
mlen = find_lcs_len(name.encode('utf-8'),v.encode('utf-8'))
if mlen > 3:
dep_id.append((k,mlen))
dep_id.sort(key=lambda x:x[1])
if not dep_id:
dep_id = 0
else:
dep_id = dep_id[0][0]
print name,SCHOOL_UNIVERSITY_DEPARTMENT_ID2NAME[dep_id]
return [school[0], school_id, dep_id]
name = name.replace('大学', '大').replace('科学技术', '科').replace(
'中国',
'中').replace('师范', '师').replace('科技', '科').replace('交通', '交').replace(
'财经', '财').replace('工业', '工').replace('北京', '北').replace(
'科学', '科').replace('农业', '农').decode('utf-8')
if name.endswith(u"大") and len(name) > 2:
name = name[:-1]
return name
with open('to_be_verified', 'r') as to_be_verifyed:
data = loads(to_be_verifyed.read())
#shuffle(data)
_SCHOOL_UNIVERSITY = dict(
(replace_name(v), k) for k, v in SCHOOL_UNIVERSITY.iteritems())
f = open('out2.txt', 'w')
err = open('logging2', 'w')
fcount = 0
for pos, i in enumerate(data):
_name = i[1]
name = replace_name(_name)
print name
if not name: continue
c = []
maxlen = 0
for j, id in _SCHOOL_UNIVERSITY.iteritems():
if len(set(name) & set(j)) >= 2:
from random import shuffle
def replace_name(name):
name = ftoj(name.decode('utf-8'))
if type(name) is unicode:
name = name.encode('utf-8')
name = name.replace('大学', '大').replace('科学技术', '科').replace('中国', '中').replace('师范', '师').replace('科技', '科').replace('交通', '交').replace('财经', '财').replace('工业', '工').replace('北京', '北').replace('科学', '科').replace('农业', '农').decode('utf-8')
if name.endswith(u"大") and len(name) > 2:
name = name[:-1]
return name
with open('to_be_verified', 'r') as to_be_verifyed:
data = loads(to_be_verifyed.read())
#shuffle(data)
_SCHOOL_UNIVERSITY = dict((replace_name(v), k) for k, v in SCHOOL_UNIVERSITY.iteritems())
f = open('out2.txt', 'w')
err = open('logging2','w')
fcount = 0
for pos, i in enumerate(data):
_name = i[1]
name = replace_name(_name)
print name
if not name: continue
c = []
maxlen = 0
for j, id in _SCHOOL_UNIVERSITY.iteritems():