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 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 calculate_similarity(file_name_1, file_name_2):
seq1 = fetch_machine_instruction_sequence(file_name_1)
seq2 = fetch_machine_instruction_sequence(file_name_2)
lcs_len_seq1_seq2 = lcs.find_lcs_len(seq1, seq2)
similarity = calculate_jaccard_coefficient(lcs_len_seq1_seq2, seq1, seq2)
return similarity
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:
llen = find_lcs_len(name, j)
if llen > maxlen:
c = [j]
maxlen = llen
elif llen == maxlen:
c.append(j)
ok = False
if c:
c.sort(key=len)
# print " ".join(c)
if (maxlen /
float(len(name))) > 0.6 and maxlen / float(len(c[0])) > 0.6:
ok = True
if ok:
name = i[2].encode('utf-8')
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:
llen = find_lcs_len(name, j)
if llen > maxlen:
c = [j]
maxlen = llen
elif llen == maxlen:
c.append(j)
ok = False
if c:
c.sort(key=len)
# print " ".join(c)
if (maxlen / float(len(name)) ) > 0.6 and maxlen/float(len(c[0])) > 0.6:
ok = True
if ok:
name = i[2].encode('utf-8')
p = []
