Rooba
/
jellyfish
mirror of https://github.com/jamesturk/jellyfish.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Changed jaro-winkler to only perform winkler step if both strings are at least 4 characters long

This commit is contained in:
David McKean 2014-07-24 16:19:27 -06:00
parent 8e7689fba8
commit f5a907c4de
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cjellyfish/jaro.c
View File

@ -105,7 +105,7 @@ double _jaro_winkler(const char *ying, const char *yang,
weight /= 3.0;
// Continue to boost the weight if the strings are similar
if (winklerize && weight > 0.7) {
if (winklerize && weight > 0.7 && ying_length > 3 && yang_length > 3) {
// Adjust for having up to the first 4 characters in common
j = (min_len >= 4) ? 4 : min_len;

2
jellyfish/_jellyfish.py
View File

@ -84,7 +84,7 @@ def _jaro_winkler(ying, yang, long_tolerance, winklerize):
(common_chars-trans_count) / common_chars)) / 3
# winkler modification: continue to boost if strings are similar
if winklerize and weight > 0.7:
if winklerize and weight > 0.7 and ying_len > 3 and yang_len > 3:
# adjust for up to first 4 chars in common
j = max(min_len, 4)
i = 0