jaro_winkler 1.2.7 → 1.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5de1821108ec68b1c02ad1b83731e669d15a5e20
-  data.tar.gz: 4686731f92f9f7bb3b790943f07bc148b63ad0ad
+  metadata.gz: 13eaf9c47df66ba5c9883611ee7a1c8468cc9e7a
+  data.tar.gz: 7c43db047cfb1aaade4c0d6f2c907ed19f8a79ab
 SHA512:
-  metadata.gz: 6ffa1c7caa063549e0b271601a6c049c679e8fcb6eacf9297f7c83276117fa43ecebd268e96f5f4ca378501edfba383d1ea4f8f8c6f06f50afd01254609c18e4
-  data.tar.gz: c042a318557e8539e42b41cdd3d5f776e68655a8a89357a90a92bc29f9a18e5bbbf37f7c86e76d43b942e64e78d7c35eaac3e3bad936d25524d4e1322098565c
+  metadata.gz: 57421be340741b44879c3104689363a7ca2897014a6e9cd0c3fcaa524b29abf1a5db370cab72e4de0299f26ca2e14357ce24f7b8b7cafce97ca1527c27c46798
+  data.tar.gz: 8db803506546b4a99dd7e267bc561c90664282b4c8dc253f22695a0a8cc55df64e559be3c7e68cb26e05fd4ca08626481a82c82128f8616e0a2b378b29012413

data/README.md

@@ -14,7 +14,7 @@ gem install jaro_winkler
 require 'jaro_winkler'
 JaroWinkler.distance "MARTHA", "MARHTA"
 # => 0.9611
-JaroWinkler.distance "MARTHA", "marhta", case_match: true
+JaroWinkler.distance "MARTHA", "marhta", ignore_case: true
 # => 0.9611
 JaroWinkler.distance "MARTHA", "MARHTA", weight: 0.2
 # => 0.9778
@@ -30,7 +30,7 @@ JaroWinkler.r_distance "MARTHA", "MARHTA" # Pure Ruby
 
 Name        | Type    | Default | Note
 ----------- | ------  | ------- | ------------------------------------------------------------------------------------------------------------
-case_match  | boolean | false   | All lower case characters are converted to upper case prior to the comparison.
+ignore_case | boolean | false   | All lower case characters are converted to upper case prior to the comparison.
 weight      | number  | 0.1     | A constant scaling factor for how much the score is adjusted upwards for having common prefixes.
 threshold   | number  | 0.7     | The prefix bonus is only added when the compared strings have a Jaro distance above the threshold.
 

data/ext/jaro_winkler/distance.c

@@ -5,7 +5,7 @@
 
 Option* option_new(){
   Option *opt = calloc(1, sizeof(Option));
-  opt->case_match = 0;
+  opt->ignore_case = 0;
   opt->weight = 0.1;
   opt->threshold = 0.7;
   return opt;
@@ -42,7 +42,7 @@ double c_distance(char *s1, int byte_len1, char *s2, int byte_len2, Option *opt)
   int ary_1_len, ary_2_len;
   unsigned long long *ary_1 = codepoints(s1, byte_len1, &ary_1_len), *ary_2 = codepoints(s2, byte_len2, &ary_2_len);
 
-  if(opt->case_match){
+  if(opt->ignore_case){
     for(int i = 0; i < ary_1_len; ++i) if(ary_1[i] < 256 && islower(ary_1[i])) ary_1[i] -= 32;
     for(int i = 0; i < ary_2_len; ++i) if(ary_2[i] < 256 && islower(ary_2[i])) ary_2[i] -= 32;
   }

data/ext/jaro_winkler/distance.h

@@ -2,7 +2,7 @@
 #define DISTANCE_H 1
 
 typedef struct{
-  char case_match;
+  char ignore_case;
   double weight, threshold;
 } Option;
 

data/ext/jaro_winkler/jaro_winkler.c

@@ -15,11 +15,11 @@ VALUE rb_distance(int argc, VALUE *argv, VALUE self){
   if(TYPE(opt) == T_HASH){
     VALUE weight = rb_hash_aref(opt, ID2SYM(rb_intern("weight")));
     VALUE threshold = rb_hash_aref(opt, ID2SYM(rb_intern("threshold")));
-    VALUE case_match = rb_hash_aref(opt, ID2SYM(rb_intern("case_match")));
+    VALUE ignore_case = rb_hash_aref(opt, ID2SYM(rb_intern("ignore_case")));
     if(!NIL_P(weight)) c_opt->weight = NUM2DBL(weight);
     if(c_opt->weight > 0.25) rb_raise(rb_eRuntimeError, "Scaling factor should not exceed 0.25, otherwise the distance can become larger than 1.");
     if(!NIL_P(threshold)) c_opt->threshold = NUM2DBL(threshold);
-    if(!NIL_P(case_match)) c_opt->case_match = (TYPE(case_match) == T_FALSE || NIL_P(case_match)) ? 0 : 1;
+    if(!NIL_P(ignore_case)) c_opt->ignore_case = (TYPE(ignore_case) == T_FALSE || NIL_P(ignore_case)) ? 0 : 1;
   }
   VALUE ret = rb_float_new(c_distance(StringValuePtr(s1), RSTRING_LEN(s1), StringValuePtr(s2), RSTRING_LEN(s2), c_opt));
   free(c_opt);

data/lib/jaro_winkler.rb

@@ -42,10 +42,10 @@ module JaroWinkler
   end
 
   def r_distance s1, s2, options = {}
-    options = {weight: 0.1, threshold: 0.7, case_match: false}.merge options
-    weight, threshold, case_match = options[:weight], options[:threshold], options[:case_match]
+    options = {weight: 0.1, threshold: 0.7, ignore_case: false}.merge options
+    weight, threshold, ignore_case = options[:weight], options[:threshold], options[:ignore_case]
     raise 'Scaling factor should not exceed 0.25, otherwise the distance can become larger than 1' if weight > 0.25
-    s1, s2     = s1.upcase, s2.upcase if case_match
+    s1, s2     = s1.upcase, s2.upcase if ignore_case
     distance   = jaro_distance(s1, s2)
     prefix     = 0
     max_length = [4, s1.length, s2.length].min

data/lib/jaro_winkler/version.rb

@@ -1,3 +1,3 @@
 module JaroWinkler
-  VERSION = "1.2.7"
+  VERSION = "1.2.8"
 end

data/spec/jaro_winkler_spec.rb

@@ -31,18 +31,32 @@ describe JaroWinkler do
   end
 
   it 'works with UTF-8' do
-    expect(c_distance('變形金剛4:絕跡重生', '變形金剛4: 絕跡重生')).to eq c_distance('0123456789', '01234x56789')
+    expect(c_distance('變形金剛4:絕跡重生', '變形金剛4: 絕跡重生')).to be_within(0.0001).of(0.9818)
+    expect(c_distance('連勝文', '連勝丼')).to be_within(0.0001).of(0.8222)
+    expect(c_distance('馬英九', '馬英丸')).to be_within(0.0001).of(0.8222)
   end
 
-  it 'can ignore case' do
-    expect(r_distance('MARTHA', 'marhta', case_match: true)).to be_within(0.0001).of(0.9611)
-    expect(c_distance('MARTHA', 'marhta', case_match: true)).to be_within(0.0001).of(0.9611)
+  it 'sets ignore_case' do
+    params = 'MARTHA', 'marhta', {ignore_case: true}
+    expect(r_distance(*params)).to be_within(0.0001).of(0.9611)
+    expect(c_distance(*params)).to be_within(0.0001).of(0.9611)
   end
 
-  it 'can set weight' do
-    expect(r_distance('MARTHA', 'MARHTA', weight: 0.2)).to be_within(0.0001).of(0.9778)
-    expect(c_distance('MARTHA', 'MARHTA', weight: 0.2)).to be_within(0.0001).of(0.9778)
-    expect{ r_distance('MARTHA', 'MARHTA', weight: 0.26) }.to raise_error
-    expect{ c_distance('MARTHA', 'MARHTA', weight: 0.26) }.to raise_error
+  it 'sets weight' do
+    params = 'MARTHA', 'MARHTA', {weight: 0.2}
+    expect(r_distance(*params)).to be_within(0.0001).of(0.9778)
+    expect(c_distance(*params)).to be_within(0.0001).of(0.9778)
+  end
+
+  it 'sets threshold' do
+    params = 'MARTHA', 'MARHTA', {threshold: 0.99}
+    expect(r_distance(*params)).to be_within(0.0001).of(0.9445)
+    expect(c_distance(*params)).to be_within(0.0001).of(0.9445)
+  end
+
+  it 'throws exception when weight exceeding 0.25' do
+    params = 'MARTHA', 'MARHTA', {weight: 0.26}
+    expect{ r_distance(*params) }.to raise_error
+    expect{ c_distance(*params) }.to raise_error
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: jaro_winkler
 version: !ruby/object:Gem::Version
-  version: 1.2.7
+  version: 1.2.8
 platform: ruby
 authors:
 - Jian Weihang