taleinat
/
fuzzysearch
mirror of https://github.com/taleinat/fuzzysearch.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fixed one test and two bugs in find_near_matches() 

all tests passing!
This commit is contained in:
Tal Einat 2013-11-12 10:18:42 +02:00
parent 08974f39bb
commit 881ff4c0bc
2 changed files with 14 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
fuzzysearch/fuzzysearch.py
View File

@ -54,15 +54,23 @@ def find_near_matches(subsequence, sequence, max_l_dist=0):
# if this sequence char is *not* the candidate's next expected char
else:
# we can try skipping a sequence or sub-sequence char, unless
# this candidate has already skipped the maximum allowed number
# of characters
# we can try skipping a sequence or sub-sequence char (or both),
# unless this candidate has already skipped the maximum allowed
# number of characters
if cand.dist == max_l_dist:
continue
# add a candidate skipping a sequence char
new_candidates.append(cand._replace(dist=cand.dist + 1))
if index + 1 < len(sequence) and cand.subseq_index + 1 < _subseq_len:
# add a candidate skipping both a sequence char and a
# subsequence char
new_candidates.append(cand._replace(
dist=cand.dist + 1,
subseq_index=cand.subseq_index+1,
))
# try skipping subsequence chars
for n_skipped in xrange(1, max_l_dist - cand.dist + 1):
# if skipping n_skipped sub-sequence chars reaches the end
@ -78,7 +86,7 @@ def find_near_matches(subsequence, sequence, max_l_dist=0):
# add a candidate skipping n_skipped subsequence chars
new_candidates.append(cand._replace(
dist=cand.dist + n_skipped,
subseq_index=cand.subseq_index + n_skipped,
subseq_index=cand.subseq_index + n_skipped + 1,
))
break
# note: if the above loop ends without a break, that means that

4
tests/test_fuzzysearch.py
View File

@ -130,8 +130,8 @@ class TestFuzzySearchBase(object):
def test_double_last_items(self):
self.assertEquals(
[Match(start=3, end=8, dist=0)],
self.search('defgh', 'abcdefghghi', max_l_dist=3),
[Match(start=2, end=8, dist=0)],
self.search('cdefgh', 'abcdefghghi', max_l_dist=3),
)
def test_missing_second_item(self):