gender_detector 0.1.2 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/lib/gender_detector.rb +65 -48
- data/lib/gender_detector/version.rb +1 -11
- metadata +58 -38
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: fdee5d9e457b4a5c4c9e6dd8f52e64cd86fe1bff
|
4
|
+
data.tar.gz: 41b06696c8af71759cfffc69c9268471a8cb578d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: c799a9cb5b317826b83f3ed794ca4cdf9e501956fcd111cd8f9762ccc49bfcad68a4b49a42fdc888968b7e4edef49df3824d9335fc4989aa7d2fa69cf8e0cf3d
|
7
|
+
data.tar.gz: 609ff37bf50849e52ee38922101f81b4fe8db973765b5f7f4b638c63adc6406f59423c29f2f3ce60cf5bed7caa4e09de323d0b35ef3a58d788e7e5d757c5da7a
|
data/lib/gender_detector.rb
CHANGED
@@ -1,13 +1,17 @@
|
|
1
1
|
require 'gender_detector/version'
|
2
2
|
|
3
|
-
|
4
|
-
|
3
|
+
# Main class for interacting with the data file
|
5
4
|
class GenderDetector
|
6
|
-
COUNTRIES = [
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
5
|
+
COUNTRIES = [:great_britain, :ireland, :usa, :italy, :malta, :portugal,
|
6
|
+
:spain, :france, :belgium, :luxembourg, :the_netherlands,
|
7
|
+
:east_frisia, :germany, :austria, :swiss, :iceland, :denmark,
|
8
|
+
:norway, :sweden, :finland, :estonia, :latvia, :lithuania,
|
9
|
+
:poland, :czech_republic, :slovakia, :hungary, :romania,
|
10
|
+
:bulgaria, :bosniaand, :croatia, :kosovo, :macedonia,
|
11
|
+
:montenegro, :serbia, :slovenia, :albania, :greece, :russia,
|
12
|
+
:belarus, :moldova, :ukraine, :armenia, :azerbaijan, :georgia,
|
13
|
+
:the_stans, :turkey, :arabia, :israel, :china, :india, :japan,
|
14
|
+
:korea, :vietnam, :other_countries].freeze
|
11
15
|
|
12
16
|
ISO_3166_MAPPING = {
|
13
17
|
'AE' => :arabia, 'AL' => :albania, 'AM' => :armenia, 'AT' => :austria,
|
@@ -19,20 +23,21 @@ class GenderDetector
|
|
19
23
|
'GR' => :greece, 'HK' => :china, 'HR' => :croatia, 'HU' => :hungary,
|
20
24
|
'IE' => :ireland, 'IL' => :israel, 'IN' => :india, 'IS' => :iceland,
|
21
25
|
'IT' => :italy, 'JP' => :japan, 'KP' => :korea, 'KR' => :korea,
|
22
|
-
'KZ' => :the_stans, 'LT' => :lithuania, 'LU' => :luxembourg,
|
23
|
-
'
|
24
|
-
'
|
25
|
-
'
|
26
|
-
'
|
27
|
-
'
|
28
|
-
'UZ' => :the_stans, 'VN' => :vietnam
|
29
|
-
}
|
26
|
+
'KZ' => :the_stans, 'LT' => :lithuania, 'LU' => :luxembourg,
|
27
|
+
'LV' => :latvia, 'MD' => :moldova, 'ME' => :montenegro, 'MK' => :macedonia,
|
28
|
+
'MT' => :malta, 'NL' => :the_netherlands, 'NO' => :norway, 'PL' => :poland,
|
29
|
+
'PT' => :portugal, 'QA' => :arabia, 'RO' => :romania, 'RS' => :serbia,
|
30
|
+
'RU' => :russia, 'SA' => :arabia, 'SE' => :sweden, 'SI' => :slovenia,
|
31
|
+
'SK' => :slovakia, 'TR' => :turkey, 'TW' => :china, 'UA' => :ukraine,
|
32
|
+
'US' => :usa, 'UZ' => :the_stans, 'VN' => :vietnam
|
33
|
+
}.freeze
|
30
34
|
|
31
35
|
def initialize(opts = {})
|
36
|
+
relpath = '../gender_detector/data/nam_dict.txt'
|
32
37
|
opts = {
|
33
|
-
:
|
34
|
-
:
|
35
|
-
:
|
38
|
+
filename: File.expand_path(relpath, __FILE__),
|
39
|
+
case_sensitive: true,
|
40
|
+
unknown_value: :andy
|
36
41
|
}.merge(opts)
|
37
42
|
@filename = opts[:filename]
|
38
43
|
@case_sensitive = opts[:case_sensitive]
|
@@ -42,31 +47,31 @@ class GenderDetector
|
|
42
47
|
|
43
48
|
def parse(fname)
|
44
49
|
@names = {}
|
45
|
-
open(fname,
|
46
|
-
f.each_line
|
50
|
+
open(fname, 'r:iso8859-1:utf-8') do |f|
|
51
|
+
f.each_line do |line|
|
47
52
|
eat_name_line line
|
48
|
-
|
49
|
-
|
53
|
+
end
|
54
|
+
end
|
50
55
|
end
|
51
56
|
|
52
57
|
def knows_country?(country)
|
53
|
-
COUNTRIES.include?(country)
|
58
|
+
COUNTRIES.include?(country) || ISO_3166_MAPPING.include?(country)
|
54
59
|
end
|
55
60
|
|
56
61
|
def name_exists?(name)
|
57
|
-
name =
|
58
|
-
@names.
|
62
|
+
name = downcase(name) unless @case_sensitive
|
63
|
+
@names.key?(name) ? name : false
|
59
64
|
end
|
60
65
|
|
61
66
|
def get_gender(name, country = nil)
|
62
|
-
name =
|
67
|
+
name = downcase(name) unless @case_sensitive
|
63
68
|
|
64
|
-
if
|
69
|
+
if !name_exists?(name)
|
65
70
|
@unknown_value
|
66
71
|
elsif country.nil?
|
67
|
-
most_popular_gender(name)
|
68
|
-
country_values.split(
|
69
|
-
|
72
|
+
most_popular_gender(name) do |country_values|
|
73
|
+
country_values.split('').select { |l| l.strip != '' }.length
|
74
|
+
end
|
70
75
|
elsif COUNTRIES.include?(country)
|
71
76
|
most_popular_gender_in_country(name, country)
|
72
77
|
elsif ISO_3166_MAPPING.include?(country)
|
@@ -77,57 +82,69 @@ class GenderDetector
|
|
77
82
|
end
|
78
83
|
|
79
84
|
def inspect
|
80
|
-
"#<#{self.class.name} filename=\"#{@filename}\"
|
85
|
+
"#<#{self.class.name} filename=\"#{@filename}\" " \
|
86
|
+
" case_sensitive=#{@case_sensitive} unknown_value=#{@unknown_value}>"
|
81
87
|
end
|
82
88
|
|
83
89
|
private
|
90
|
+
|
84
91
|
def most_popular_gender_in_country(name, country)
|
85
92
|
index = COUNTRIES.index(country)
|
86
|
-
most_popular_gender(name)
|
93
|
+
most_popular_gender(name) do |country_values|
|
87
94
|
country_values[index].ord
|
88
|
-
|
95
|
+
end
|
89
96
|
end
|
90
97
|
|
91
98
|
def eat_name_line(line)
|
92
|
-
return if line.start_with?(
|
99
|
+
return if line.start_with?('#', '=')
|
93
100
|
|
94
|
-
parts = line.split(
|
101
|
+
parts = line.split(' ').select { |p| p.strip != '' }
|
95
102
|
country_values = line.slice(30, line.length)
|
96
|
-
name = @case_sensitive ? parts[1] :
|
103
|
+
name = @case_sensitive ? parts[1] : downcase(parts[1])
|
97
104
|
|
98
105
|
case parts[0]
|
99
|
-
when
|
100
|
-
when
|
101
|
-
when
|
102
|
-
when
|
103
|
-
when
|
106
|
+
when 'M' then set(name, :male, country_values)
|
107
|
+
when '1M', '?M' then set(name, :mostly_male, country_values)
|
108
|
+
when 'F' then set(name, :female, country_values)
|
109
|
+
when '1F', '?F' then set(name, :mostly_female, country_values)
|
110
|
+
when '?' then set(name, :andy, country_values)
|
104
111
|
else raise "Not sure what to do with a gender of #{parts[0]}"
|
105
112
|
end
|
106
113
|
end
|
107
114
|
|
108
115
|
def most_popular_gender(name)
|
109
|
-
return @unknown_value unless @names.
|
116
|
+
return @unknown_value unless @names.key?(name)
|
110
117
|
|
111
118
|
max = 0
|
112
119
|
best = @names[name].keys.first
|
113
|
-
@names[name].each
|
120
|
+
@names[name].each do |gender, country_values|
|
114
121
|
count = yield country_values
|
115
122
|
if count > max
|
116
123
|
max = count
|
117
124
|
best = gender
|
118
125
|
end
|
119
|
-
|
126
|
+
end
|
120
127
|
best
|
121
128
|
end
|
122
129
|
|
123
130
|
def set(name, gender, country_values)
|
124
|
-
if name.include?
|
125
|
-
[
|
126
|
-
set name.gsub(
|
127
|
-
|
131
|
+
if name.include? '+'
|
132
|
+
['', '-', ' '].each do |replacement|
|
133
|
+
set name.gsub('+', replacement), gender, country_values
|
134
|
+
end
|
128
135
|
else
|
129
136
|
@names[name] ||= {}
|
130
137
|
@names[name][gender] = country_values
|
131
138
|
end
|
132
139
|
end
|
140
|
+
|
141
|
+
def downcase(name)
|
142
|
+
if defined?(UnicodeUtils)
|
143
|
+
UnicodeUtils.downcase(name)
|
144
|
+
elsif defined?(ActiveSupport::Multibyte::Chars)
|
145
|
+
name.mb_chars.downcase.to_s
|
146
|
+
else
|
147
|
+
name.downcase
|
148
|
+
end
|
149
|
+
end
|
133
150
|
end
|
metadata
CHANGED
@@ -1,112 +1,132 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: gender_detector
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
5
|
-
prerelease:
|
4
|
+
version: 1.0.0
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Brian Muller
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date:
|
11
|
+
date: 2016-08-25 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
|
-
name:
|
14
|
+
name: rubocop
|
16
15
|
requirement: !ruby/object:Gem::Requirement
|
17
|
-
none: false
|
18
16
|
requirements:
|
19
|
-
- -
|
17
|
+
- - "~>"
|
20
18
|
- !ruby/object:Gem::Version
|
21
|
-
version:
|
22
|
-
type: :
|
19
|
+
version: '0.42'
|
20
|
+
type: :development
|
23
21
|
prerelease: false
|
24
22
|
version_requirements: !ruby/object:Gem::Requirement
|
25
|
-
none: false
|
26
23
|
requirements:
|
27
|
-
- -
|
24
|
+
- - "~>"
|
28
25
|
- !ruby/object:Gem::Version
|
29
|
-
version:
|
26
|
+
version: '0.42'
|
30
27
|
- !ruby/object:Gem::Dependency
|
31
28
|
name: minitest
|
32
29
|
requirement: !ruby/object:Gem::Requirement
|
33
|
-
none: false
|
34
30
|
requirements:
|
35
|
-
- -
|
31
|
+
- - "~>"
|
36
32
|
- !ruby/object:Gem::Version
|
37
|
-
version: '
|
33
|
+
version: '5.9'
|
38
34
|
type: :development
|
39
35
|
prerelease: false
|
40
36
|
version_requirements: !ruby/object:Gem::Requirement
|
41
|
-
none: false
|
42
37
|
requirements:
|
43
|
-
- -
|
38
|
+
- - "~>"
|
44
39
|
- !ruby/object:Gem::Version
|
45
|
-
version: '
|
40
|
+
version: '5.9'
|
46
41
|
- !ruby/object:Gem::Dependency
|
47
42
|
name: rake
|
48
43
|
requirement: !ruby/object:Gem::Requirement
|
49
|
-
none: false
|
50
44
|
requirements:
|
51
|
-
- -
|
45
|
+
- - "~>"
|
52
46
|
- !ruby/object:Gem::Version
|
53
47
|
version: '0'
|
54
48
|
type: :development
|
55
49
|
prerelease: false
|
56
50
|
version_requirements: !ruby/object:Gem::Requirement
|
57
|
-
none: false
|
58
51
|
requirements:
|
59
|
-
- -
|
52
|
+
- - "~>"
|
60
53
|
- !ruby/object:Gem::Version
|
61
54
|
version: '0'
|
62
55
|
- !ruby/object:Gem::Dependency
|
63
|
-
name:
|
56
|
+
name: minitest-stub-const
|
64
57
|
requirement: !ruby/object:Gem::Requirement
|
65
|
-
none: false
|
66
58
|
requirements:
|
67
|
-
- -
|
59
|
+
- - "~>"
|
68
60
|
- !ruby/object:Gem::Version
|
69
|
-
version: '0'
|
61
|
+
version: '0.5'
|
70
62
|
type: :development
|
71
63
|
prerelease: false
|
72
64
|
version_requirements: !ruby/object:Gem::Requirement
|
73
|
-
none: false
|
74
65
|
requirements:
|
75
|
-
- -
|
66
|
+
- - "~>"
|
76
67
|
- !ruby/object:Gem::Version
|
77
|
-
version: '0'
|
78
|
-
|
68
|
+
version: '0.5'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: unicode_utils
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.3'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '1.3'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: activesupport
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '5.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '5.0'
|
97
|
+
description: Guess gender from first name, with multilingual support.
|
79
98
|
email:
|
80
99
|
- bamuller@gmail.com
|
81
100
|
executables: []
|
82
101
|
extensions: []
|
83
102
|
extra_rdoc_files: []
|
84
103
|
files:
|
85
|
-
- lib/gender_detector/version.rb
|
86
104
|
- lib/gender_detector.rb
|
87
105
|
- lib/gender_detector/data/nam_dict.txt
|
106
|
+
- lib/gender_detector/version.rb
|
88
107
|
homepage: https://github.com/bmuller/gender_detector
|
89
|
-
licenses:
|
90
|
-
|
108
|
+
licenses:
|
109
|
+
- MIT
|
110
|
+
metadata: {}
|
111
|
+
post_install_message: For unicode support you'll need to also install the unicode_utils
|
112
|
+
or activesupport gem
|
91
113
|
rdoc_options: []
|
92
114
|
require_paths:
|
93
115
|
- lib
|
94
116
|
required_ruby_version: !ruby/object:Gem::Requirement
|
95
|
-
none: false
|
96
117
|
requirements:
|
97
|
-
- -
|
118
|
+
- - ">="
|
98
119
|
- !ruby/object:Gem::Version
|
99
120
|
version: 1.9.0
|
100
121
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
101
|
-
none: false
|
102
122
|
requirements:
|
103
|
-
- -
|
123
|
+
- - ">="
|
104
124
|
- !ruby/object:Gem::Version
|
105
125
|
version: '0'
|
106
126
|
requirements: []
|
107
127
|
rubyforge_project:
|
108
|
-
rubygems_version:
|
128
|
+
rubygems_version: 2.5.1
|
109
129
|
signing_key:
|
110
|
-
specification_version:
|
130
|
+
specification_version: 4
|
111
131
|
summary: Get gender from first name.
|
112
132
|
test_files: []
|