def set_color(self, line):
diffstring = ""
sm = StringMatcher(seq1=self.line, seq2=line)
mb = sm.get_matching_blocks()
i = 0
for block in mb:
diffstring += "\x1b[33m%s\x1b[0m" % self.line[i:block[0]]
diffstring += self.line[block[0]:block[0] + block[2]]
i = block[0] + block[2]
self.colored_line = diffstring
def testEqual(self):
m = StringMatcher(None, self.s1, self.s1a)
Ratio = m.ratio()
self.assertEqual(intr(100*Ratio), 100)
m = StringMatcher(None, self.s8, self.s8a)
Ratio = m.ratio()
self.assertEqual(intr(100*Ratio), 100)
m = StringMatcher(None, self.s9, self.s9a)
Ratio = m.ratio()
self.assertEqual(intr(100*Ratio), 100)
def compare_sentences(new_sentences, old_sentences):
rows = []
for new_sentence in new_sentences:
max_score = 0
for old_sentence in old_sentences:
if StringMatcher(None, new_sentence[0],
old_sentence).ratio() > max_score:
max_score = StringMatcher(None, new_sentence[0],
old_sentence).ratio()
if max_score > .75:
break
rows.append(
dict(sentence_id=new_sentence[1],
max_score=max_score,
sentence_length=len(new_sentence[0].split(" "))))
return rows
def compare_single_sentence(new_sentence, old_sentences):
max_score = 0
old_sentence_id = ''
for old_sentence in old_sentences:
if StringMatcher(None, new_sentence['sentence'],
old_sentence['sentence']).ratio() > max_score:
max_score = StringMatcher(None, new_sentence['sentence'],
old_sentence['sentence']).ratio()
old_sentence_id = old_sentence['id']
if max_score == 1:
break
results = dict(sentence_id=new_sentence['id'],
old_sentence_id=old_sentence_id,
max_score=max_score,
sentence_length=len(new_sentence['sentence'].split(" ")))
return results
def testPartialRatio(self):
if len(self.s1) <= len(self.s3):
shorter = self.s1
longer = self.s3
else:
shorter = self.s3
longer = self.s1
m = StringMatcher(None, shorter, longer)
blocks = m.get_matching_blocks()
# each block represents a sequence of matching characters in a string
# of the form (idx_1, idx_2, len)
# the best partial match will block align with at least one of those blocks
# e.g. shorter = "abcd", longer = XXXbcdeEEE
# block = (1,3,3)
# best score === ratio("abcd", "Xbcd")
scores = []
for block in blocks:
long_start = block[1] - block[0] if (block[1] - block[0]) > 0 else 0
long_end = long_start + len(shorter)
long_substr = longer[long_start:long_end]
m2 = StringMatcher(None, shorter, long_substr)
r = m2.ratio()
if r > .995:
return 100
else:
scores.append(r)
self.assertEqual(intr(100*max(scores)), 100)
def partial_ratio2(s1, s2):
""""Return the ratio of the most similar substring
as a number between 0 and 100."""
if s1 is None:
raise TypeError("s1 is None")
if s2 is None:
raise TypeError("s2 is None")
s1, s2 = utils.make_type_consistent(s1, s2)
if len(s1) == 0 or len(s2) == 0:
return 0
shorter = s1
longer = s2
m = SequenceMatcher(None, shorter, longer)
blocks = m.get_matching_blocks()
# each block represents a sequence of matching characters in a string
# of the form (idx_1, idx_2, len)
# the best partial match will block align with at least one of those blocks
# e.g. shorter = "abcd", longer = XXXbcdeEEE
# block = (1,3,3)
# best score === ratio("abcd", "Xbcd")
scores = []
for block in blocks:
long_start = block[1] - block[0] if (block[1] - block[0]) > 0 else 0
long_end = long_start + len(shorter)
long_substr = longer[long_start:long_end]
m2 = SequenceMatcher(None, shorter, long_substr)
r = m2.ratio()
if r > .995:
return 100
else:
scores.append(r)
return int(100 * max(scores))
def testCaseInsensitive(self): m = StringMatcher(None, self.s1, self.s2) Ratio = m.ratio() self.assertNotEqual(intr(100*Ratio), 100)