def seq_matcher(name1, name2):
name1 = unicode(
unicodedata.normalize('NFKD', name1).encode('ascii', 'ignore'),
'utf-8')
name2 = unicode(name2, 'utf-8')
name2 = unicode(
unicodedata.normalize('NFKD', name2).encode('ascii', 'ignore'),
'utf-8')
soundex = fuzzy.Soundex(4)
name1 = soundex(name1)
name2 = soundex(name2)
# dmeta = fuzzy.DMetaphone()
# name1 = dmeta(name1)[0]
# name2 = dmeta(name2)[0]
# name1 = fuzzy.nysiis(name1)
# name2 = fuzzy.nysiis(name2)
m = SequenceMatcher(None, name1, name2)
# Calculate an edit distance"abcef"
# print 'm',m.ratio()
e = editdist.distance(name1, name2)
# print 'e',e
sm = StringMatcher(seq1=name1, seq2=name2)
# return e
# print sm.distance()
return sm.distance()
def processText(self, text1, text2):
if(text1 == text2) :
return 0.
String_test = StringMatcher()
String_test.set_seqs(text1, text2)
dist = String_test.distance()
# dist = tds.levenshtein(text1,text2)
return float(dist) / max(len(text1),len(text2))
def processText(self, text1, text2):
if (text1 == text2):
return 0.
String_test = StringMatcher()
String_test.set_seqs(text1, text2)
dist = String_test.distance()
# dist = tds.levenshtein(text1,text2)
return float(dist) / max(len(text1), len(text2))
def editdist(self,string1,string2):
a=StringMatcher(None,string1.lower(),string2.lower())
return a.distance()