jaro_winkler 1.3.0 → 1.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2d6d2ce4d12911ca5891bbf2bdc8c6fdc8e81415
-  data.tar.gz: 9cdfa4369a6131b82c76b4fe8072c9395fa8e8ff
+  metadata.gz: 77f956f70c8b182eae7e78f336c377bc1b4bfa8f
+  data.tar.gz: 17bead21ccd72a4d1c6137cf4f612b1d1c036e26
 SHA512:
-  metadata.gz: 192c9452f5159a26fc152a33e77a0f5de20b7f072eb4d3f93ec8f743bb1bd80b6a7d32852efd61eb00c2f1af617f5e8a423e61cf4d64edcf565628bb81b8ed9e
-  data.tar.gz: 5f36c58fa716b3f4ba442d0bd551606d5fc25844a25c26888cf236e799ba7720aa305eced293e70cfdc7dba73bf070436945774d49ea5d99a324bbc8d81182bb
+  metadata.gz: a4c0e7786621635addc80d7c0c18276ef720c1e9690c61f74b506cf5627368cb5862073e96447cef6739ab044d18aa159db492e3bdc182a483809bd273979fd3
+  data.tar.gz: 83800c9061918d37f3be5a5b4f3137346425328a33f013dbd37dd58f3c818dd4e411605f372aabd0c6a5501a694ddf5928246e96d5e931af5e5468cc2d699777

data/README.md

@@ -42,6 +42,25 @@ adj_table   | boolean | false   | The option is used to give partial credit for
 ['1', 'I'], ['1', 'L'], ['0', 'O'], ['0', 'Q'], ['C', 'K'], ['G', 'J'], ['E', ' '], ['Y', ' '], ['S', ' ']
 ```
 
+## How Adjusting Table Work
+
+origin formula:
+
+![origin](https://chart.googleapis.com/chart?cht=tx&chl=%5Cbegin%7Bcases%7D%200%20%26%20m%3D0%20%5C%5C%20%5Cfrac%20%7B%201%20%7D%7B%203%20%7D%20(%5Cfrac%20%7B%20m%20%7D%7B%20%5Cleft%7C%20s1%20%5Cright%7C%20%20%7D%20%2B%5Cfrac%20%7B%20m%20%7D%7B%20%5Cleft%7C%20s2%20%5Cright%7C%20%20%7D%20%2B%5Cfrac%20%7B%20m-t%20%7D%7B%20m%20%7D%20)%20%26%20others%20%5Cend%7Bcases%7D)
+
+where
+
+- `m` is the number of matching characters.
+- `t` is half the number of transpositions.
+
+with adjusting table:
+
+![adj](https://chart.googleapis.com/chart?cht=tx&chl=%5Cbegin%7Bcases%7D%200%20%26%20m%3D0%20%5C%5C%20%5Cfrac%20%7B%201%20%7D%7B%203%20%7D%20(%5Cfrac%20%7B%20%5Cfrac%20%7B%20s%20%7D%7B%2010%20%7D%20%2Bm%20%7D%7B%20%5Cleft%7C%20s1%20%5Cright%7C%20%20%7D%20%2B%5Cfrac%20%7B%20%5Cfrac%20%7B%20s%20%7D%7B%2010%20%7D%20%2Bm%20%7D%7B%20%5Cleft%7C%20s2%20%5Cright%7C%20%20%7D%20%2B%5Cfrac%20%7B%20m-t%20%7D%7B%20m%20%7D%20)%20%26%20others%20%5Cend%7Bcases%7D)
+
+where
+
+- `s` is the number of nonmatching but similar characters.
+
 # Why This?
 
 There is also another similar gem named [fuzzy-string-match](https://github.com/kiyoka/fuzzy-string-match) which both provides C and Ruby version as well.
@@ -106,3 +125,4 @@ amatch           | 0.960000 | 0.010000 | 0.970000 | (  0.964803)
 
 - Custom adjusting word table.
 - If the adjusting table is ASCII encoded, use dense matrix instread of sparse matrix to speed up.
+- Call by reference instead of call by value to enhance performance.

data/benchmark/native.txt

@@ -1,12 +1,12 @@
 Rehearsal ----------------------------------------------------
-jaro_winkler       0.370000   0.000000   0.370000 (  0.367923)
-fuzzystringmatch   0.340000   0.030000   0.370000 (  0.372721)
-hotwater           0.310000   0.000000   0.310000 (  0.313405)
-amatch             0.970000   0.000000   0.970000 (  0.968318)
-------------------------------------------- total: 2.020000sec
+jaro_winkler       0.350000   0.000000   0.350000 (  0.358591)
+fuzzystringmatch   0.360000   0.020000   0.380000 (  0.381666)
+hotwater           0.340000   0.000000   0.340000 (  0.337789)
+amatch             1.010000   0.000000   1.010000 (  1.010946)
+------------------------------------------- total: 2.080000sec
 
                        user     system      total        real
-jaro_winkler       0.390000   0.000000   0.390000 (  0.392408)
-fuzzystringmatch   0.150000   0.000000   0.150000 (  0.151552)
-hotwater           0.320000   0.000000   0.320000 (  0.317740)
-amatch             0.960000   0.010000   0.970000 (  0.964803)
+jaro_winkler       0.350000   0.010000   0.360000 (  0.345293)
+fuzzystringmatch   0.140000   0.000000   0.140000 (  0.138711)
+hotwater           0.310000   0.000000   0.310000 (  0.306498)
+amatch             0.960000   0.000000   0.960000 (  0.961509)

data/ext/jaro_winkler/distance.c

@@ -37,7 +37,7 @@ static char matrix_find(Matrix matrix, unsigned long long code_1, unsigned long
 
 Option option_new(){
   Option opt;
-  opt.ignore_case = 0;
+  opt.ignore_case = opt.adj_table = 0;
   opt.weight = 0.1;
   opt.threshold = 0.7;
   return opt;

data/lib/jaro_winkler/version.rb

@@ -1,3 +1,3 @@
 module JaroWinkler
-  VERSION = "1.3.0"
+  VERSION = "1.3.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jaro_winkler
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.3.1
 platform: ruby
 authors:
 - Jian Weihang