Github/guess-filename.py
2
0
Fork 1
mirror of https://github.com/novoid/guess-filename.py.git synced 2026-02-16 13:24:15 +00:00
Code Issues Projects Releases Packages Wiki Activity

more efficient fuzzy match for exact matches

Browse source
This commit is contained in:
Karl Voit 2016-03-09 18:12:28 +01:00
parent 8d95218dbd
commit b393c96f15
1 changed files with 12 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
guessfilename.py
View file

@ -220,14 +220,17 @@ class GuessFilename(object):
for entry in entries:
assert(type(entry) == unicode or type(entry) == str)
#logging.debug(u"fuzzy_contains_all_of(%s, %s) ... " % (string[:30], str(entry[:30])))
similarity = fuzz.partial_ratio(string, entry)
if similarity > 64:
#logging.debug(u"MATCH fuzzy_contains_all_of(%s, %s) == %i" % (string, str(entry), similarity))
pass
else:
#logging.debug(u"¬ MATCH fuzzy_contains_all_of(%s, %s) == %i" % (string, str(entry), similarity))
return False
#logging.debug(u"fuzzy_contains_all_of(%s..., %s...) ... " % (string[:30], str(entry[:30])))
if not entry in string:
## if entry is found in string (exactly), try with fuzzy search:
similarity = fuzz.partial_ratio(string, entry)
if similarity > 64:
#logging.debug(u"MATCH fuzzy_contains_all_of(%s..., %s) == %i" % (string[:30], str(entry), similarity))
pass
else:
logging.debug(u"¬ MATCH fuzzy_contains_all_of(%s..., %s) == %i" % (string[:30], str(entry), similarity))
return False
return True
@ -281,7 +284,7 @@ class GuessFilename(object):
#logging.debug("get_euro_charge_from_context extracted float: [%s]" % floatstring)
return floatstring
else:
logging.debug(u"get_euro_charge_from_context was not able to extract a float: [%s] + [%s] + [%s]" % (before, string[:30] + u"...", after))
logging.debug(u"get_euro_charge_from_context was not able to extract a float: between [%s] and [%s] within [%s]" % (before, after, string[:30] + u"..."))
import pdb; pdb.set_trace()
return False