emiler 0.2.1 → 0.2.2
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/.codeclimate.yml +26 -0
- data/.travis.yml +4 -0
- data/Gemfile +2 -0
- data/README.md +6 -1
- data/lib/emiler/jarowinkler.rb +34 -43
- data/lib/emiler/version.rb +1 -1
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0361dccbd493b95c973033250393401c2888c094
|
4
|
+
data.tar.gz: a03b7c228c9e3c8da609a5d44b20a1ab9c4450d6
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 68cc06b5d23967e4ca4921640d5c856a087a258fc977cd27e4b268d58c512e2b509ca4693b18044258079e44e8ab799a5f7a791a4f2aee6eb2d3a5afd3c2f613
|
7
|
+
data.tar.gz: 45567581427124b3718141db0bd043989ddc393cc3a4edae6b0b132380c6e487ce217c421e46bba62cfb349194d0ad309504ceab79fa01c66ef972762704831c
|
data/.codeclimate.yml
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
---
|
2
|
+
engines:
|
3
|
+
duplication:
|
4
|
+
enabled: true
|
5
|
+
config:
|
6
|
+
languages:
|
7
|
+
- ruby
|
8
|
+
- javascript
|
9
|
+
- python
|
10
|
+
- php
|
11
|
+
fixme:
|
12
|
+
enabled: true
|
13
|
+
rubocop:
|
14
|
+
enabled: true
|
15
|
+
ratings:
|
16
|
+
paths:
|
17
|
+
- "**.inc"
|
18
|
+
- "**.js"
|
19
|
+
- "**.jsx"
|
20
|
+
- "**.module"
|
21
|
+
- "**.php"
|
22
|
+
- "**.py"
|
23
|
+
- "**.rb"
|
24
|
+
exclude_paths:
|
25
|
+
- features/
|
26
|
+
- spec/
|
data/.travis.yml
CHANGED
data/Gemfile
CHANGED
data/README.md
CHANGED
@@ -1,7 +1,12 @@
|
|
1
1
|
# Emiler
|
2
2
|
|
3
3
|
Naïve distance calculation for emails. Returns “similar” basing on artificial
|
4
|
-
name and domain comparison.
|
4
|
+
name and domain comparison.
|
5
|
+
|
6
|
+
[](https://travis-ci.org/am-kantox/emiler)
|
7
|
+
[](https://codeclimate.com/github/am-kantox/emiler)
|
8
|
+
[](https://codeclimate.com/github/am-kantox/emiler/coverage)
|
9
|
+
[](https://codeclimate.com/github/am-kantox/emiler)
|
5
10
|
|
6
11
|
## Installation
|
7
12
|
|
data/lib/emiler/jarowinkler.rb
CHANGED
@@ -23,77 +23,68 @@ module FuzzyStringMatch
|
|
23
23
|
true
|
24
24
|
end
|
25
25
|
|
26
|
-
def getDistance(
|
27
|
-
a1 = s1.split(
|
28
|
-
a2 = s2.split(
|
26
|
+
def getDistance(s1, s2)
|
27
|
+
a1 = s1.split(//)
|
28
|
+
a2 = s2.split(//)
|
29
29
|
|
30
|
-
|
31
|
-
(max,min) = a1,a2
|
32
|
-
else
|
33
|
-
(max,min) = a2,a1
|
34
|
-
end
|
30
|
+
max, min = s1.size > s2.size ? [a1, a2] : [a2, a1]
|
35
31
|
|
36
|
-
range = [
|
37
|
-
indexes = Array.new(
|
38
|
-
flags = Array.new(
|
32
|
+
range = [(max.size / 2 - 1), 0].max
|
33
|
+
indexes = Array.new(min.size, -1)
|
34
|
+
flags = Array.new(max.size, false)
|
39
35
|
|
40
|
-
matches = 0
|
41
|
-
(0
|
36
|
+
matches = 0
|
37
|
+
(0...min.size).each do |mi|
|
42
38
|
c1 = min[mi]
|
43
39
|
xi = [mi - range, 0].max
|
44
40
|
xn = [mi + range + 1, max.size].min
|
45
41
|
|
46
|
-
(xi
|
47
|
-
|
48
|
-
indexes[mi] = i
|
49
|
-
flags[i] = true
|
50
|
-
matches += 1
|
51
|
-
break
|
52
|
-
end
|
53
|
-
}
|
54
|
-
}
|
42
|
+
(xi...xn).each do |i|
|
43
|
+
next unless !flags[i] && c1 == max[i]
|
55
44
|
|
56
|
-
|
57
|
-
|
45
|
+
indexes[mi] = i
|
46
|
+
flags[i] = true
|
47
|
+
matches += 1
|
48
|
+
break
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
ms1 = Array.new(matches, nil)
|
53
|
+
ms2 = Array.new(matches, nil)
|
58
54
|
|
59
55
|
si = 0
|
60
|
-
(0
|
61
|
-
if
|
56
|
+
(0...min.size).each do |i|
|
57
|
+
if indexes[i] != -1
|
62
58
|
ms1[si] = min[i]
|
63
59
|
si += 1
|
64
60
|
end
|
65
|
-
|
61
|
+
end
|
66
62
|
|
67
63
|
si = 0
|
68
|
-
(0
|
64
|
+
(0...max.size).each do |i|
|
69
65
|
if flags[i]
|
70
66
|
ms2[si] = max[i]
|
71
67
|
si += 1
|
72
68
|
end
|
73
|
-
|
69
|
+
end
|
74
70
|
|
75
71
|
transpositions = 0
|
76
|
-
(0
|
77
|
-
if ms1[mi] != ms2[mi]
|
78
|
-
|
79
|
-
end
|
80
|
-
}
|
72
|
+
(0...ms1.size).each do |mi|
|
73
|
+
transpositions += 1 if ms1[mi] != ms2[mi]
|
74
|
+
end
|
81
75
|
|
82
76
|
prefix = 0
|
83
|
-
(0
|
84
|
-
if s1[mi] == s2[mi]
|
85
|
-
|
86
|
-
|
87
|
-
break
|
88
|
-
end
|
89
|
-
}
|
77
|
+
(0...min.size).each do |mi|
|
78
|
+
prefix += 1 if s1[mi] == s2[mi]
|
79
|
+
break unless s1[mi] == s2[mi]
|
80
|
+
end
|
90
81
|
|
91
82
|
if 0 == matches
|
92
83
|
0.0
|
93
84
|
else
|
94
85
|
m = matches.to_f
|
95
|
-
t = (transpositions/ 2)
|
96
|
-
j = ((m / s1.size) + (m / s2.size) + ((m - t) / m)) / 3.0
|
86
|
+
t = (transpositions / 2)
|
87
|
+
j = ((m / s1.size) + (m / s2.size) + ((m - t) / m)) / 3.0
|
97
88
|
return j < THRESHOLD ? j : j + [0.1, 1.0 / max.size].min * prefix * (1 - j)
|
98
89
|
end
|
99
90
|
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: 0.2.
|
4
|
+
version: 0.2.2
|
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: 2016-05-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -75,6 +75,7 @@ executables:
|
|
75
75
|
extensions: []
|
76
76
|
extra_rdoc_files: []
|
77
77
|
files:
|
78
|
+
- ".codeclimate.yml"
|
78
79
|
- ".gitignore"
|
79
80
|
- ".rspec"
|
80
81
|
- ".rubocop.yml"
|