emiler 0.1.0 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/emiler.gemspec +1 -1
- data/lib/emiler.rb +5 -8
- data/lib/emiler/jarowinkler.rb +101 -0
- data/lib/emiler/version.rb +1 -1
- metadata +5 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 88c02b12935d6916f9499df2a434905469268109
|
4
|
+
data.tar.gz: 60f9eb13edbbaf3fd9dec3726840fad647a6dd38
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f382fcf45028650029f23230dd8f1f9445d21394fcdb8f49e252ed067cbf55876ec78f386002cad7acd0e7000fbbc36b59cdde84b5b9c05eb7470a2ebe0aa86e
|
7
|
+
data.tar.gz: c23d478e3b23404e8dfb408f62df2a5db66c65a2c9b003de02d879940ee2a259c75e4035ee27781a35cf4138c555be2aaf44865e53c83f2f54575ce48eae2757
|
data/emiler.gemspec
CHANGED
@@ -24,7 +24,7 @@ Gem::Specification.new do |spec|
|
|
24
24
|
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
25
25
|
spec.require_paths = ['lib']
|
26
26
|
|
27
|
-
spec.add_development_dependency 'bundler', '~> 1
|
27
|
+
spec.add_development_dependency 'bundler', '~> 1'
|
28
28
|
spec.add_development_dependency 'rake', '~> 10.0'
|
29
29
|
spec.add_development_dependency 'rspec', '~> 3.0'
|
30
30
|
spec.add_development_dependency 'pry', '~> 0.10'
|
data/lib/emiler.rb
CHANGED
@@ -1,24 +1,21 @@
|
|
1
1
|
require 'emiler/version'
|
2
|
-
require '
|
2
|
+
require 'emiler/jarowinkler'
|
3
3
|
|
4
4
|
module Emiler
|
5
|
-
USE_PURE = ENV['USE_PURE_JW']
|
6
5
|
INEXACT_MATCH_COEFFICIENT = ENV['INEXACT_MATCH_COEFFICIENT'] || 0.8
|
7
6
|
RAISE_ON_MALFORMED_EMAIL = ENV['RAISE_ON_MALFORMED_EMAIL']
|
8
7
|
|
9
8
|
class JW
|
10
9
|
attr_reader :jw
|
11
|
-
def initialize
|
12
|
-
@jw = FuzzyStringMatch::
|
10
|
+
def initialize
|
11
|
+
@jw = FuzzyStringMatch::JaroWinklerPure.new
|
13
12
|
end
|
14
13
|
|
15
14
|
def distance s1, s2
|
16
15
|
@jw.getDistance s1, s2
|
17
16
|
end
|
18
17
|
|
19
|
-
|
20
|
-
PURE = USE_PURE ? JW.new(:pure) : nil
|
21
|
-
MATCHER = PURE || NATIVE
|
18
|
+
MATCHER = JW.new
|
22
19
|
DUMMY = { jw: 0, full: 0, name: 0, domain: 0, result: false }.freeze
|
23
20
|
|
24
21
|
private :initialize
|
@@ -32,7 +29,7 @@ module Emiler
|
|
32
29
|
|
33
30
|
# rubocop:disable Metrics/AbcSize
|
34
31
|
def similarity e1, e2
|
35
|
-
e1, e2 = [e1, e2].map(&:downcase)
|
32
|
+
e1, e2 = [e1, e2].map(&:to_s).map(&:downcase)
|
36
33
|
em1, em2 = [e1, e2].map { |e| e.split '@' }
|
37
34
|
|
38
35
|
if em1.size != 2 || em2.size != 2
|
@@ -0,0 +1,101 @@
|
|
1
|
+
#
|
2
|
+
# Fuzzy String Match
|
3
|
+
#
|
4
|
+
# Copyright 2010-2011 Kiyoka Nishiyama
|
5
|
+
#
|
6
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
7
|
+
# you may not use this file except in compliance with the License.
|
8
|
+
# You may obtain a copy of the License at
|
9
|
+
#
|
10
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
11
|
+
#
|
12
|
+
# Unless required by applicable law or agreed to in writing, software
|
13
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
14
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
15
|
+
# See the License for the specific language governing permissions and
|
16
|
+
# limitations under the License.
|
17
|
+
#
|
18
|
+
module FuzzyStringMatch
|
19
|
+
class JaroWinklerPure
|
20
|
+
THRESHOLD = 0.7
|
21
|
+
|
22
|
+
def pure?
|
23
|
+
true
|
24
|
+
end
|
25
|
+
|
26
|
+
def getDistance( s1, s2 )
|
27
|
+
a1 = s1.split( // )
|
28
|
+
a2 = s2.split( // )
|
29
|
+
|
30
|
+
if s1.size > s2.size
|
31
|
+
(max,min) = a1,a2
|
32
|
+
else
|
33
|
+
(max,min) = a2,a1
|
34
|
+
end
|
35
|
+
|
36
|
+
range = [ (max.size / 2 - 1), 0 ].max
|
37
|
+
indexes = Array.new( min.size, -1 )
|
38
|
+
flags = Array.new( max.size, false )
|
39
|
+
|
40
|
+
matches = 0;
|
41
|
+
(0 ... min.size).each { |mi|
|
42
|
+
c1 = min[mi]
|
43
|
+
xi = [mi - range, 0].max
|
44
|
+
xn = [mi + range + 1, max.size].min
|
45
|
+
|
46
|
+
(xi ... xn).each { |i|
|
47
|
+
if (not flags[i]) && ( c1 == max[i] )
|
48
|
+
indexes[mi] = i
|
49
|
+
flags[i] = true
|
50
|
+
matches += 1
|
51
|
+
break
|
52
|
+
end
|
53
|
+
}
|
54
|
+
}
|
55
|
+
|
56
|
+
ms1 = Array.new( matches, nil )
|
57
|
+
ms2 = Array.new( matches, nil )
|
58
|
+
|
59
|
+
si = 0
|
60
|
+
(0 ... min.size).each { |i|
|
61
|
+
if (indexes[i] != -1)
|
62
|
+
ms1[si] = min[i]
|
63
|
+
si += 1
|
64
|
+
end
|
65
|
+
}
|
66
|
+
|
67
|
+
si = 0
|
68
|
+
(0 ... max.size).each { |i|
|
69
|
+
if flags[i]
|
70
|
+
ms2[si] = max[i]
|
71
|
+
si += 1
|
72
|
+
end
|
73
|
+
}
|
74
|
+
|
75
|
+
transpositions = 0
|
76
|
+
(0 ... ms1.size).each { |mi|
|
77
|
+
if ms1[mi] != ms2[mi]
|
78
|
+
transpositions += 1
|
79
|
+
end
|
80
|
+
}
|
81
|
+
|
82
|
+
prefix = 0
|
83
|
+
(0 ... min.size).each { |mi|
|
84
|
+
if s1[mi] == s2[mi]
|
85
|
+
prefix += 1
|
86
|
+
else
|
87
|
+
break
|
88
|
+
end
|
89
|
+
}
|
90
|
+
|
91
|
+
if 0 == matches
|
92
|
+
0.0
|
93
|
+
else
|
94
|
+
m = matches.to_f
|
95
|
+
t = (transpositions/ 2)
|
96
|
+
j = ((m / s1.size) + (m / s2.size) + ((m - t) / m)) / 3.0;
|
97
|
+
return j < THRESHOLD ? j : j + [0.1, 1.0 / max.size].min * prefix * (1 - j)
|
98
|
+
end
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
data/lib/emiler/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: emiler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Aleksei Matiushkin
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-05-
|
11
|
+
date: 2016-05-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '1
|
19
|
+
version: '1'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '1
|
26
|
+
version: '1'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: rake
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -103,6 +103,7 @@ files:
|
|
103
103
|
- bin/setup
|
104
104
|
- emiler.gemspec
|
105
105
|
- lib/emiler.rb
|
106
|
+
- lib/emiler/jarowinkler.rb
|
106
107
|
- lib/emiler/version.rb
|
107
108
|
homepage: https://kantox.com
|
108
109
|
licenses:
|