jaro_winkler 1.3.6 → 1.3.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d48fca750c919028bdf13a2145bf431919a2c924
-  data.tar.gz: 134da623e4f99a708cf83f7e2e961a8882ecffb8
+  metadata.gz: 7687918cbfcaa8ffb589f1d1383ac2e6611e235f
+  data.tar.gz: e8129522a42193023a77593dddfe3917eafe3f68
 SHA512:
-  metadata.gz: 7476d0dcd726f7d6b2405c861b139f99b22c71e21e48607beab76c1a29a11b6e9398c33943e8bfcff042b18fdea2d66f858283df17bbfd4e351a3ca93ee8f05a
-  data.tar.gz: 1c0a9c5b3521e761c752bc19a09a24052da3a46357195b9a86c86815418fc55bbe090b44db738bf086a44aabb1056f660a1584f1c8c7d01d124faf20623041b4
+  metadata.gz: be7befc2a7e5c5a2866ba7e4995bf99a0f9d75bfab3e01c806a1d39b10b0a27975f795f2330248e96e5673a8ce81d0ef01fa12a6d18f3f2cf73ff9de28764a60
+  data.tar.gz: 3183fb3c534e1c1820ee16cd6a81bfcd35899ffc586e5ac064f5e4deace965d5507b83ca1d4a1fe3d8d30cc894da72eb998f1119ec3223a61c50c072d7e2029d

data/ext/jaro_winkler/jaro.c

@@ -27,10 +27,10 @@ double jaro_winkler_distance(char* short_str, int short_str_len, char* long_str,
   int window_size = long_codes_len/2 - 1;
   if(window_size < 0) window_size = 0;
 
-  char short_codes_flag[MAX_WORD_LENGTH];
-  char long_codes_flag[MAX_WORD_LENGTH];
-  memset(short_codes_flag, 0, MAX_WORD_LENGTH);
-  memset(long_codes_flag, 0, MAX_WORD_LENGTH);
+  char short_codes_flag[short_str_len];
+  char long_codes_flag[long_str_len];
+  memset(short_codes_flag, 0, short_str_len);
+  memset(long_codes_flag, 0, long_str_len);
 
   // count number of matching characters
   int match_count = 0;

data/ext/jaro_winkler/jaro.h

@@ -2,7 +2,6 @@
 #define LIBJARO_JARO_H
 
 #define SWAP(x, y) do{ __typeof__(x) SWAP = x; x = y; y = SWAP; }while(0)
-#define MAX_WORD_LENGTH 64
 #define DEFAULT_WEIGHT 0.1
 #define DEFAULT_THRESHOLD 0.7
 

data/lib/jaro_winkler/version.rb

@@ -1,3 +1,3 @@
 module JaroWinkler
-  VERSION = "1.3.6"
+  VERSION = "1.3.7"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jaro_winkler
 version: !ruby/object:Gem::Version
-  version: 1.3.6
+  version: 1.3.7
 platform: ruby
 authors:
 - Jian Weihang
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-22 00:00:00.000000000 Z
+date: 2015-09-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -111,24 +111,12 @@ dependencies:
 description: It's a implementation of Jaro-Winkler distance algorithm, it uses C extension
   and will fallback to pure Ruby version in JRuby. Both implementation supports UTF-8
   string.
-email:
-- tonytonyjan@gmail.com
+email: tonytonyjan@gmail.com
 executables: []
 extensions:
 - ext/jaro_winkler/extconf.rb
 extra_rdoc_files: []
 files:
-- ".gitignore"
-- ".rspec"
-- ".travis.yml"
-- Gemfile
-- LICENSE.txt
-- README.md
-- Rakefile
-- benchmark/native.rb
-- benchmark/native.txt
-- benchmark/pure.rb
-- benchmark/pure.txt
 - ext/jaro_winkler/adj_matrix.c
 - ext/jaro_winkler/adj_matrix.h
 - ext/jaro_winkler/code.c
@@ -138,14 +126,10 @@ files:
 - ext/jaro_winkler/jaro.h
 - ext/jaro_winkler/jaro_winkler.c
 - ext/jaro_winkler/murmur_hash2.c
-- jaro_winkler.gemspec
 - lib/jaro_winkler.rb
 - lib/jaro_winkler/adjusting_table.rb
 - lib/jaro_winkler/fallback.rb
 - lib/jaro_winkler/version.rb
-- spec/adjusting_table_spec.rb
-- spec/jaro_winkler_spec.rb
-- spec/spec_helper.rb
 homepage: https://github.com/tonytonyjan/jaro_winkler
 licenses:
 - MIT
@@ -166,12 +150,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.4.5.1
 signing_key: 
 specification_version: 4
 summary: Ruby & C implementation of Jaro-Winkler distance algorithm which both support
   UTF-8 string.
-test_files:
-- spec/adjusting_table_spec.rb
-- spec/jaro_winkler_spec.rb
-- spec/spec_helper.rb
+test_files: []

data/.gitignore

@@ -1,14 +0,0 @@
-/.bundle/
-/.yardoc
-/Gemfile.lock
-/_yardoc/
-/coverage/
-/doc/
-/pkg/
-/spec/reports/
-/tmp/
-*.bundle
-*.so
-*.o
-*.a
-mkmf.log

data/.rspec

@@ -1,2 +0,0 @@
---color
---require spec_helper

data/.travis.yml

@@ -1,6 +0,0 @@
-language: ruby
-rvm:
-  - 2.2.0
-  - 2.1.5
-  - 2.0.0
-  - 1.9.3

data/Gemfile

@@ -1,2 +0,0 @@
-source 'https://rubygems.org'
-gemspec

data/LICENSE.txt

@@ -1,22 +0,0 @@
-Copyright (c) 2014 Jian Weihang
-
-MIT License
-
-Permission is hereby granted, free of charge, to any person obtaining
-a copy of this software and associated documentation files (the
-"Software"), to deal in the Software without restriction, including
-without limitation the rights to use, copy, modify, merge, publish,
-distribute, sublicense, and/or sell copies of the Software, and to
-permit persons to whom the Software is furnished to do so, subject to
-the following conditions:
-
-The above copyright notice and this permission notice shall be
-included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
-LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
-OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
-WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -1,129 +0,0 @@
-[![Build Status](https://travis-ci.org/tonytonyjan/jaro_winkler.svg?branch=master)](https://travis-ci.org/tonytonyjan/jaro_winkler)
-
-It's an implementation of [Jaro-Winkler distance](http://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance) algorithm, it uses C extension and will fallback to pure Ruby version in JRuby. Both of them supports UTF-8 string.
-
-# Installation
-
-```
-gem install jaro_winkler
-```
-
-# Usage
-
-```ruby
-require 'jaro_winkler'
-JaroWinkler.distance "MARTHA", "MARHTA"
-# => 0.9611
-JaroWinkler.distance "MARTHA", "marhta", ignore_case: true
-# => 0.9611
-JaroWinkler.distance "MARTHA", "MARHTA", weight: 0.2
-# => 0.9778
-
-# Force the strategy
-JaroWinkler.c_distance "MARTHA", "MARHTA" # C extension
-JaroWinkler.r_distance "MARTHA", "MARHTA" # Pure Ruby
-```
-
-## Options
-
-Name        | Type    | Default | Note
------------ | ------  | ------- | ------------------------------------------------------------------------------------------------------------
-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.
-adj_table   | boolean | false   | The option is used to give partial credit for characters that may be errors due to known phonetic or character recognition errors. A typical example is to match the letter "O" with the number "0".
-
-# Adjusting Table
-
-## Default Table
-
-```
-['A', 'E'], ['A', 'I'], ['A', 'O'], ['A', 'U'], ['B', 'V'], ['E', 'I'], ['E', 'O'], ['E', 'U'], ['I', 'O'], ['I', 'U'],
-['O', 'U'], ['I', 'Y'], ['E', 'Y'], ['C', 'G'], ['E', 'F'], ['W', 'U'], ['W', 'V'], ['X', 'K'], ['S', 'Z'], ['X', 'S'],
-['Q', 'C'], ['U', 'V'], ['M', 'N'], ['L', 'I'], ['Q', 'O'], ['P', 'R'], ['I', 'J'], ['2', 'Z'], ['5', 'S'], ['8', 'B'],
-['1', 'I'], ['1', 'L'], ['0', 'O'], ['0', 'Q'], ['C', 'K'], ['G', 'J'], ['E', ' '], ['Y', ' '], ['S', ' ']
-```
-
-## How it works?
-
-Original Formula:
-
-![origin](https://chart.googleapis.com/chart?cht=tx&chs&chl=%5Cbegin%7Bcases%7D0%26%7B%5Ctext%7Bif%20%7Dm%3D0%7D%5C%5C%5Cfrac%7B1%7D%7B3%7D(%5Cfrac%7Bm%7D%7B%5Cleft%7Cs1%5Cright%7C%7D%2B%5Cfrac%7Bm%7D%7B%5Cleft%7Cs2%5Cright%7C%7D%2B%5Cfrac%7Bm-t%7D%7Bm%7D)%26%5Ctext%7Bothers%7D%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&chs&chl=%5Cbegin%7Bcases%7D0%26%5Ctext%7Bif%20%7Dm%3D0%5C%5C%5Cfrac%7B1%7D%7B3%7D(%5Cfrac%7B%5Cfrac%7Bs%7D%7B10%7D%2Bm%7D%7B%5Cleft%7Cs1%5Cright%7C%7D%2B%5Cfrac%7B%5Cfrac%7Bs%7D%7B10%7D%2Bm%7D%7B%5Cleft%7Cs2%5Cright%7C%7D%2B%5Cfrac%7Bm-t%7D%7Bm%7D)%26%5Ctext%7Bothers%7D%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.
-
-I reinvent this wheel because of the naming in `fuzzy-string-match` such as `getDistance` breaks convention, and some weird code like `a1 = s1.split( // )` (`s1.chars` could be better), furthermore, it's bugged (see tables below).
-
-# Compare with other gems
-
-                | jaro_winkler | fuzzystringmatch | hotwater    | amatch
---------------- | ------------ | ---------------- | --------    | ------
-UTF-8 Suport    | **Yes**      | Pure Ruby only   | No          | No
-Windows Support | **Yes**      |                  | No          | **Yes**
-Adjusting Table | **Yes**      | No               | No          | No
-Native          | **Yes**      | **Yes**          | **Yes**     | **Yes**
-Pure Ruby       | **Yes**      | **Yes**          | No          | No
-Speed           | Medium       | **Fast**         | Medium      | Slow
-Bug Found       | **Not Yet**  | Yes              | **Not Yet** | Yes
-
-For `Bug Found`, I made a rake task to build the table below, the source code is in `Rakefile`:
-
-str_1      | str_2      | origin | jaro_winkler | fuzzystringmatch | hotwater | amatch
----        | ---        | ---    | ---          | ---              | ---      | ---
-"henka"    | "henkan"   | 0.9667 | 0.9667       | **0.9722**       | 0.9667   | **0.9444**
-"al"       | "al"       | 1.0    | 1.0          | 1.0              | 1.0      | 1.0
-"martha"   | "marhta"   | 0.9611 | 0.9611       | 0.9611           | 0.9611   | **0.9444**
-"jones"    | "johnson"  | 0.8324 | 0.8324       | 0.8324           | 0.8324   | **0.7905**
-"abcvwxyz" | "cabvwxyz" | 0.9583 | 0.9583       | 0.9583           | 0.9583   | 0.9583
-"dwayne"   | "duane"    | 0.84   | 0.84         | 0.84             | 0.84     | **0.8222**
-"dixon"    | "dicksonx" | 0.8133 | 0.8133       | 0.8133           | 0.8133   | **0.7667**
-"fvie"     | "ten"      | 0.0    | 0.0          | 0.0              | 0.0      | 0.0
-
-- The origin result is from the [original C implementation by the author of the algorithm](http://web.archive.org/web/20100227020019/http://www.census.gov/geo/msb/stand/strcmp.c).
-- Test data are borrowed from [fuzzy-string-match's rspec file](https://github.com/kiyoka/fuzzy-string-match/blob/master/test/basic_pure_spec.rb).
-
-# Benchmark
-
-## Pure Ruby
-
-                 | user     | system   | total    | real
----------------- | -------- | -------- | -------- | ------------
-jaro_winkler     | 1.300000 | 0.000000 | 1.300000 | (  1.299802)
-fuzzystringmatch | 1.510000 | 0.000000 | 1.510000 | (  1.510136)
-
-- jaro_winkler (1.3.1)
-- fuzzy-string-match (0.9.6)
-
-## Native
-
-                 | user     | system   | total    | real
----------------- | -------- | -------- | -------- | ------------
-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)
-
-- jaro_winkler (1.3.1)
-- fuzzy-string-match (0.9.6)
-- hotwater (0.1.2)
-- amatch (0.3.0)
-
-# Todo
-
-- Custom adjusting word table.
-- The algorithm between C and Ruby are different.

data/Rakefile

@@ -1,51 +0,0 @@
-require "bundler/gem_tasks"
-require "rake/extensiontask"
-require 'rspec/core/rake_task'
-
-RSpec::Core::RakeTask.new(:spec)
-Rake::ExtensionTask.new("jaro_winkler") do |ext|
-  ext.lib_dir = "lib/jaro_winkler"
-end
-
-task default: [:compile, :spec]
-
-desc 'type can be "native" or "pure"'
-task :benchmark, :type do |t, args|
-  args.with_defaults(type: :all)
-  ROOT_PATH = File.expand_path('..', __FILE__)
-  LIB_PATH = File.join(ROOT_PATH, 'lib')
-  BENCHMARK_PATH = File.join(ROOT_PATH, 'benchmark')
-
-  files = File.join(BENCHMARK_PATH, args[:type] == :all ? '*.rb' : "#{args[:type]}.rb")
-  Dir[files].each do |path|
-    output_path = File.join(BENCHMARK_PATH, File.basename(path, '*.rb').sub('.rb', '.txt'))
-    cmd = "RUBYLIB=#{LIB_PATH} ruby #{path}"
-    puts cmd
-    output = `#{cmd}`
-    File.write(output_path, output)
-  end
-end
-
-task :compare do
-  require 'jaro_winkler'
-  require 'fuzzystringmatch'
-  require 'hotwater'
-  require 'amatch'
-  @ary = [['henka', 'henkan'], ['al', 'al'], ['martha', 'marhta'], ['jones', 'johnson'], ['abcvwxyz', 'cabvwxyz'], ['dwayne', 'duane'], ['dixon', 'dicksonx'], ['fvie', 'ten'], ['San Francisco', 'Santa Monica']]
-  table = []
-  table << %w[str_1 str_2 jaro_winkler fuzzystringmatch hotwater amatch]
-  table << %w[--- --- --- --- --- ---]
-  jarow = FuzzyStringMatch::JaroWinkler.create(:native)
-  @ary.each do |str_1, str_2|
-    table << ["\"#{str_1}\"", "\"#{str_2}\"", JaroWinkler.distance(str_1, str_2).round(4), jarow.getDistance(str_1, str_2).round(4), Hotwater.jaro_winkler_distance(str_1, str_2).round(4), Amatch::Jaro.new(str_1).match(str_2).round(4)]
-  end
-  col_len = []
-  table.first.length.times{ |i| col_len << table.map{ |row| row[i].to_s.length }.max }
-  table.first.each_with_index{ |title, i| "%-#{col_len[i]}s" % title }
-  table.each_with_index do |row|
-    row.each_with_index do |col, i|
-      row[i] = "%-#{col_len[i]}s" % col.to_s
-    end
-  end
-  table.each{|row| puts row.join(' | ')}
-end

data/benchmark/native.rb

@@ -1,26 +0,0 @@
-require 'benchmark'
-require 'jaro_winkler'
-require 'fuzzystringmatch'
-require 'hotwater'
-require 'amatch'
-ary = [['al', 'al'], ['martha', 'marhta'], ['jones', 'johnson'], ['abcvwxyz', 'cabvwxyz'], ['dwayne', 'duane'], ['dixon', 'dicksonx'], ['fvie', 'ten']]
-
-n = 100000
-Benchmark.bmbm do |x|
-  x.report 'jaro_winkler' do
-    n.times{ ary.each{ |str1, str2| JaroWinkler.c_distance(str1, str2) } }
-  end
-
-  x.report 'fuzzystringmatch' do
-    jarow = FuzzyStringMatch::JaroWinkler.create(:native)
-    n.times{ ary.each{ |str1, str2| jarow.getDistance(str1, str2) } }
-  end
-
-  x.report 'hotwater' do
-    n.times{ ary.each{ |str1, str2| Hotwater.jaro_winkler_distance(str1, str2) } }
-  end
-
-  x.report 'amatch' do
-    n.times{ ary.each{ |str1, str2| Amatch::Jaro.new(str1).match(str2) } }
-  end
-end

data/benchmark/native.txt

@@ -1,12 +0,0 @@
-Rehearsal ----------------------------------------------------
-jaro_winkler       0.350000   0.000000   0.350000 (  0.348383)
-fuzzystringmatch   0.330000   0.020000   0.350000 (  0.354850)
-hotwater           0.280000   0.000000   0.280000 (  0.278819)
-amatch             0.980000   0.000000   0.980000 (  0.983325)
-------------------------------------------- total: 1.960000sec
-
-                       user     system      total        real
-jaro_winkler       0.330000   0.000000   0.330000 (  0.331923)
-fuzzystringmatch   0.140000   0.000000   0.140000 (  0.135655)
-hotwater           0.280000   0.000000   0.280000 (  0.276728)
-amatch             0.930000   0.010000   0.940000 (  0.932943)

data/benchmark/pure.rb

@@ -1,16 +0,0 @@
-require 'benchmark'
-require 'jaro_winkler'
-require 'fuzzystringmatch'
-ary = [['al', 'al'], ['martha', 'marhta'], ['jones', 'johnson'], ['abcvwxyz', 'cabvwxyz'], ['dwayne', 'duane'], ['dixon', 'dicksonx'], ['fvie', 'ten']]
-
-n = 10000
-Benchmark.bmbm do |x|
-  x.report 'jaro_winkler' do
-    n.times{ ary.each{ |str1, str2| JaroWinkler.r_distance(str1, str2) } }
-  end
-
-  x.report 'fuzzystringmatch' do
-    jarow = FuzzyStringMatch::JaroWinkler.create(:pure)
-    n.times{ ary.each{ |str1, str2| jarow.getDistance(str1, str2) } }
-  end
-end

data/benchmark/pure.txt

@@ -1,8 +0,0 @@
-Rehearsal ----------------------------------------------------
-jaro_winkler       1.300000   0.000000   1.300000 (  1.300723)
-fuzzystringmatch   1.500000   0.010000   1.510000 (  1.497842)
-------------------------------------------- total: 2.810000sec
-
-                       user     system      total        real
-jaro_winkler       1.300000   0.000000   1.300000 (  1.299802)
-fuzzystringmatch   1.510000   0.000000   1.510000 (  1.510136)

data/jaro_winkler.gemspec

@@ -1,30 +0,0 @@
-# coding: utf-8
-lib = File.expand_path('../lib', __FILE__)
-$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
-require 'jaro_winkler/fallback'
-require 'jaro_winkler/version'
-
-Gem::Specification.new do |spec|
-  spec.name          = "jaro_winkler"
-  spec.version       = JaroWinkler::VERSION
-  spec.authors       = ["Jian Weihang"]
-  spec.email         = ["tonytonyjan@gmail.com"]
-  spec.extensions    = ["ext/jaro_winkler/extconf.rb"]
-  spec.summary       = %q{Ruby & C implementation of Jaro-Winkler distance algorithm which both support UTF-8 string.}
-  spec.description   = %q{It's a implementation of Jaro-Winkler distance algorithm, it uses C extension and will fallback to pure Ruby version in JRuby. Both implementation supports UTF-8 string.}
-  spec.homepage      = "https://github.com/tonytonyjan/jaro_winkler"
-  spec.license       = "MIT"
-
-  spec.files         = `git ls-files -z`.split("\x0")
-  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
-  spec.require_paths = ["lib"]
-
-  spec.add_development_dependency "bundler", "~> 1.7"
-  spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "rake-compiler"
-  spec.add_development_dependency "rspec"
-  spec.add_development_dependency "fuzzy-string-match"
-  spec.add_development_dependency "hotwater"
-  spec.add_development_dependency "amatch"
-end

data/spec/adjusting_table_spec.rb

@@ -1,8 +0,0 @@
-# spec/adjusting_table_spec.rb
-require 'jaro_winkler'
-
-describe JaroWinkler::DEFAULT_ADJ_TABLE do
-  it 'should not be empty' do
-    expect(JaroWinkler::DEFAULT_ADJ_TABLE).not_to be_empty
-  end
-end

data/spec/jaro_winkler_spec.rb

@@ -1,69 +0,0 @@
-# encoding: utf-8
-require 'jaro_winkler'
-include JaroWinkler
-
-shared_examples 'common' do |strategy|
-  it 'works' do
-    expect(send(strategy, 'henka','henkan')).to be_within(0.0001).of(0.9667)
-    expect(send(strategy, 'al','al')).to be_within(0.0001).of(1.0)
-    expect(send(strategy, 'martha','marhta')).to be_within(0.0001).of(0.9611)
-    expect(send(strategy, 'jones','johnson')).to be_within(0.0001).of(0.8323)
-    expect(send(strategy, 'abcvwxyz','cabvwxyz')).to be_within(0.0001).of(0.9583)
-    expect(send(strategy, 'dwayne','duane')).to be_within(0.0001).of(0.8400)
-    expect(send(strategy, 'dixon','dicksonx')).to be_within(0.0001).of(0.8133)
-    expect(send(strategy, 'fvie','ten')).to be_within(0.0001).of(0.0)
-    expect(send(strategy, 'tony','tony')).to be_within(0.0001).of(1.0)
-    expect(send(strategy, 'tonytonyjan','tonytonyjan')).to be_within(0.0001).of(1.0)
-    expect(send(strategy, 'x','x')).to be_within(0.0001).of(1.0)
-    expect(send(strategy, '','')).to be_within(0.0001).of(0.0)
-    expect(send(strategy, 'tony','')).to be_within(0.0001).of(0.0)
-    expect(send(strategy, '','tony')).to be_within(0.0001).of(0.0)
-    expect(send(strategy, 'tonytonyjan','tony')).to be_within(0.0001).of(0.8727)
-    expect(send(strategy, 'tony','tonytonyjan')).to be_within(0.0001).of(0.8727)
-  end
-
-  it 'works with UTF-8' do
-    expect(send(strategy, '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(send(strategy, '連勝文','連勝丼')).to be_within(0.0001).of(0.8222)
-    expect(send(strategy, '馬英九','馬英丸')).to be_within(0.0001).of(0.8222)
-    expect(send(strategy, '良い','いい')).to be_within(0.0001).of(0.6666)
-  end
-
-  it 'sets ignore_case' do
-    expect(send(strategy, 'MARTHA', 'marhta', ignore_case: true)).to be_within(0.0001).of(0.9611)
-  end
-
-  it 'sets weight' do
-    expect(send(strategy, 'MARTHA', 'MARHTA', weight: 0.2)).to be_within(0.0001).of(0.9778)
-  end
-
-  it 'sets threshold' do
-    expect(send(strategy, 'MARTHA', 'MARHTA', threshold: 0.99)).to be_within(0.0001).of(0.9445)
-  end
-
-
-  it 'works with adjusting table' do
-    expect(send(strategy, 'HENKA', 'HENKAN', adj_table: true)).to be_within(0.0001).of(0.9667) # m=5, t=0, s=0
-    expect(send(strategy, 'AL', 'AL', adj_table: true)).to be_within(0.0001).of(1.0) # m=2, t=0, s=0
-    expect(send(strategy, 'MARTHA', 'MARHTA', adj_table: true)).to be_within(0.0001).of(0.9611) # m=6, t=1, s=0
-    expect(send(strategy, 'JONES', 'JOHNSON', adj_table: true)).to be_within(0.0001).of(0.8598) # m=4, t=0, s=3
-    expect(send(strategy, 'ABCVWXYZ', 'CABVWXYZ', adj_table: true)).to be_within(0.0001).of(0.9583) # m=8, t=1, s=0
-    expect(send(strategy, 'DWAYNE', 'DUANE', adj_table: true)).to be_within(0.0001).of(0.8730) # m=4, t=0, s=3
-    expect(send(strategy, 'DIXON', 'DICKSONX', adj_table: true)).to be_within(0.0001).of(0.8393) # m=4, t=0, s=3
-    expect(send(strategy, 'FVIE', 'TEN', adj_table: true)).to be_within(0.0001).of(0.0)
-  end
-
-  context 'with weight exceeding 0.25' do
-    it 'throws exception' do
-      expect{ send(strategy, 'MARTHA', 'MARHTA', weight: 0.26) }.to raise_error
-    end
-  end
-end
-
-describe 'Pure Ruby' do
-  include_examples 'common', :r_distance
-end
-
-describe 'C extention' do
-  include_examples 'common', :c_distance
-end

data/spec/spec_helper.rb

@@ -1,89 +0,0 @@
-# This file was generated by the `rspec --init` command. Conventionally, all
-# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
-# The generated `.rspec` file contains `--require spec_helper` which will cause this
-# file to always be loaded, without a need to explicitly require it in any files.
-#
-# Given that it is always loaded, you are encouraged to keep this file as
-# light-weight as possible. Requiring heavyweight dependencies from this file
-# will add to the boot time of your test suite on EVERY test run, even for an
-# individual file that may not need all of that loaded. Instead, consider making
-# a separate helper file that requires the additional dependencies and performs
-# the additional setup, and require it from the spec files that actually need it.
-#
-# The `.rspec` file also contains a few flags that are not defaults but that
-# users commonly want.
-#
-# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
-RSpec.configure do |config|
-  # rspec-expectations config goes here. You can use an alternate
-  # assertion/expectation library such as wrong or the stdlib/minitest
-  # assertions if you prefer.
-  config.expect_with :rspec do |expectations|
-    # This option will default to `true` in RSpec 4. It makes the `description`
-    # and `failure_message` of custom matchers include text for helper methods
-    # defined using `chain`, e.g.:
-    # be_bigger_than(2).and_smaller_than(4).description
-    #   # => "be bigger than 2 and smaller than 4"
-    # ...rather than:
-    #   # => "be bigger than 2"
-    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
-  end
-
-  # rspec-mocks config goes here. You can use an alternate test double
-  # library (such as bogus or mocha) by changing the `mock_with` option here.
-  config.mock_with :rspec do |mocks|
-    # Prevents you from mocking or stubbing a method that does not exist on
-    # a real object. This is generally recommended, and will default to
-    # `true` in RSpec 4.
-    mocks.verify_partial_doubles = true
-  end
-
-# The settings below are suggested to provide a good initial experience
-# with RSpec, but feel free to customize to your heart's content.
-=begin
-  # These two settings work together to allow you to limit a spec run
-  # to individual examples or groups you care about by tagging them with
-  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
-  # get run.
-  config.filter_run :focus
-  config.run_all_when_everything_filtered = true
-
-  # Limits the available syntax to the non-monkey patched syntax that is recommended.
-  # For more details, see:
-  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
-  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
-  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
-  config.disable_monkey_patching!
-
-  # This setting enables warnings. It's recommended, but in some cases may
-  # be too noisy due to issues in dependencies.
-  config.warnings = true
-
-  # Many RSpec users commonly either run the entire suite or an individual
-  # file, and it's useful to allow more verbose output when running an
-  # individual spec file.
-  if config.files_to_run.one?
-    # Use the documentation formatter for detailed output,
-    # unless a formatter has already been configured
-    # (e.g. via a command-line flag).
-    config.default_formatter = 'doc'
-  end
-
-  # Print the 10 slowest examples and example groups at the
-  # end of the spec run, to help surface which specs are running
-  # particularly slow.
-  config.profile_examples = 10
-
-  # Run specs in random order to surface order dependencies. If you find an
-  # order dependency and want to debug it, you can fix the order by providing
-  # the seed, which is printed after each run.
-  #     --seed 1234
-  config.order = :random
-
-  # Seed global randomization in this process using the `--seed` CLI option.
-  # Setting this allows you to use `--seed` to deterministically reproduce
-  # test failures related to randomization by passing the same `--seed` value
-  # as the one that triggered the failure.
-  Kernel.srand config.seed
-=end
-end