namor 0.3.0 → 0.3.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/namor/namor.rb +33 -9
- data/lib/namor/version.rb +1 -1
- data/spec/lib/namor_spec.rb +28 -24
- metadata +3 -3
data/lib/namor/namor.rb
CHANGED
@@ -19,7 +19,28 @@ class Namor::Namor
|
|
19
19
|
suppression_list = @config[:suppress] || []
|
20
20
|
suppression_re = Regexp.new('\b?' + (suppression_list + (opts[:suppress]||[])).compact.map(&:upcase).join('|') + '\b?')
|
21
21
|
|
22
|
-
name && name.upcase.gsub(/^[ZX]{2,}/, '').gsub(suppression_re, '').gsub(/\b(JR|SR|II|III|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/\./, ' ').gsub(/[_'
|
22
|
+
name && name.upcase.gsub(/^[ZX]{2,}/, '').gsub(suppression_re, '').gsub(/\b(JR|SR|II|III|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/\./, ' ').gsub(/[_'\&]/, '').gsub(/,\s*$/, '').gsub(/ +/, ' ').strip
|
23
|
+
end
|
24
|
+
|
25
|
+
def fullscrub(name)
|
26
|
+
final_cleaning(scrub(name))
|
27
|
+
end
|
28
|
+
|
29
|
+
def demaiden(lastname)
|
30
|
+
return [nil,nil] unless lastname && !lastname.empty?
|
31
|
+
if lastname =~ /\-/
|
32
|
+
[lastname.gsub(/ /, ''), lastname.split(/\-/).last.gsub(/ /, '')]
|
33
|
+
else
|
34
|
+
[lastname.gsub(/ /, ''), lastname.split(/ /).last]
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
def final_cleaning(name)
|
39
|
+
if name && !name.empty?
|
40
|
+
name.gsub(/\-/, '')
|
41
|
+
else
|
42
|
+
nil
|
43
|
+
end
|
23
44
|
end
|
24
45
|
|
25
46
|
def extract(name, opts = {})
|
@@ -30,7 +51,7 @@ class Namor::Namor
|
|
30
51
|
if detitled_name =~ /,/
|
31
52
|
# "last, first[ middle]"
|
32
53
|
lastname, firstname = detitled_name.split(/\s*,\s*/)
|
33
|
-
lastname
|
54
|
+
lastname, de_maidened_last = demaiden(lastname)
|
34
55
|
middlename = nil
|
35
56
|
if firstname && firstname =~ / /
|
36
57
|
pieces = firstname.split(/ +/)
|
@@ -38,26 +59,29 @@ class Namor::Namor
|
|
38
59
|
middlename = pieces.join if pieces.any?
|
39
60
|
end
|
40
61
|
else
|
41
|
-
# "first [middle ]last"
|
62
|
+
# "first [middle-initial ]last" or "first everything-else-is-the-lastname"
|
42
63
|
pieces = detitled_name.split(' ')
|
43
64
|
firstname = pieces.shift
|
44
|
-
middlename = nil
|
45
65
|
if pieces.count > 1 && pieces.first.length == 1
|
46
66
|
# assume this is a middle initial
|
47
67
|
middlename = pieces.shift
|
68
|
+
else
|
69
|
+
middlename = nil
|
48
70
|
end
|
49
71
|
|
50
|
-
lastname = pieces.join
|
72
|
+
lastname, de_maidened_last = demaiden(pieces.join(' '))
|
51
73
|
end
|
52
74
|
|
53
|
-
firstname =
|
54
|
-
middlename =
|
55
|
-
lastname =
|
75
|
+
firstname = final_cleaning(firstname)
|
76
|
+
middlename = final_cleaning(middlename)
|
77
|
+
lastname = final_cleaning(lastname)
|
78
|
+
de_maidened_last = final_cleaning(de_maidened_last)
|
56
79
|
|
57
80
|
fm = [firstname, middlename].compact.join(' ')
|
58
81
|
fullname = [lastname, fm].compact.join(',')
|
82
|
+
nee_fullname = [de_maidened_last, fm].compact.join(',')
|
59
83
|
|
60
|
-
[firstname, middlename, lastname, fullname]
|
84
|
+
[firstname, middlename, lastname, fullname, nee_fullname]
|
61
85
|
end
|
62
86
|
|
63
87
|
def extract_with_cluster(name, opts = {})
|
data/lib/namor/version.rb
CHANGED
data/spec/lib/namor_spec.rb
CHANGED
@@ -9,71 +9,75 @@ describe "name extract" do
|
|
9
9
|
end
|
10
10
|
|
11
11
|
it "should handle 2-part names without commas" do
|
12
|
-
@namor.extract("john smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
|
12
|
+
@namor.extract("john smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
|
13
13
|
end
|
14
14
|
|
15
15
|
it "should handle 2-part names with commas" do
|
16
|
-
@namor.extract("SMITH, JOHN").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
|
16
|
+
@namor.extract("SMITH, JOHN").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
|
17
17
|
end
|
18
18
|
|
19
19
|
it "should handle 2-part names with commas and middle initials" do
|
20
|
-
@namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
20
|
+
@namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
|
21
21
|
end
|
22
22
|
|
23
23
|
it "should handle 2-part names with commas and middle initials" do
|
24
|
-
@namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
24
|
+
@namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
|
25
25
|
end
|
26
26
|
|
27
27
|
it "should strip elements within parentheses" do
|
28
|
-
@namor.extract("SMITH, JOHN (Jacko) R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
28
|
+
@namor.extract("SMITH, JOHN (Jacko) R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
|
29
29
|
end
|
30
30
|
|
31
31
|
it "should drop periods" do
|
32
|
-
@namor.extract("John R. Smith").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
32
|
+
@namor.extract("John R. Smith").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
|
33
33
|
end
|
34
34
|
|
35
35
|
it "should drop spaces in last name (only when input has a comma)" do
|
36
|
-
@namor.extract("Smith Jones, Mary").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
|
36
|
+
@namor.extract("Smith Jones, Mary").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY', 'JONES,MARY']
|
37
37
|
end
|
38
38
|
|
39
39
|
it "should drop dashes, apostrophes, ampersands" do
|
40
|
-
@namor.extract("Mary Smith-Jones").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
|
41
|
-
@namor.extract("Mary S. O'Keefe").should == ['MARY', 'S', 'OKEEFE', 'OKEEFE,MARY S']
|
42
|
-
@namor.extract("Jean-Michel Claude").should == ['JEANMICHEL', nil, 'CLAUDE', 'CLAUDE,JEANMICHEL']
|
43
|
-
@namor.extract("Smith, Bob & Sue").should == ['BOB', 'SUE', 'SMITH', 'SMITH,BOB SUE']
|
44
|
-
@namor.extract("Research & Development").should == ['RESEARCH', nil, 'DEVELOPMENT', 'DEVELOPMENT,RESEARCH']
|
40
|
+
@namor.extract("Mary Smith-Jones").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY', 'JONES,MARY']
|
41
|
+
@namor.extract("Mary S. O'Keefe").should == ['MARY', 'S', 'OKEEFE', 'OKEEFE,MARY S', 'OKEEFE,MARY S']
|
42
|
+
@namor.extract("Jean-Michel Claude").should == ['JEANMICHEL', nil, 'CLAUDE', 'CLAUDE,JEANMICHEL', 'CLAUDE,JEANMICHEL']
|
43
|
+
@namor.extract("Smith, Bob & Sue").should == ['BOB', 'SUE', 'SMITH', 'SMITH,BOB SUE', 'SMITH,BOB SUE']
|
44
|
+
@namor.extract("Research & Development").should == ['RESEARCH', nil, 'DEVELOPMENT', 'DEVELOPMENT,RESEARCH', 'DEVELOPMENT,RESEARCH']
|
45
45
|
end
|
46
46
|
|
47
47
|
it "should concatenate extract name pieces" do
|
48
|
-
@namor.extract("rajesh kumar vishnu garuda").should == ['RAJESH', nil, 'KUMARVISHNUGARUDA', 'KUMARVISHNUGARUDA,RAJESH']
|
49
|
-
@namor.extract("Kumar, Rajesh Vishnu Garuda").should == ['RAJESH', 'VISHNUGARUDA', 'KUMAR', 'KUMAR,RAJESH VISHNUGARUDA']
|
48
|
+
@namor.extract("rajesh kumar vishnu garuda").should == ['RAJESH', nil, 'KUMARVISHNUGARUDA', 'KUMARVISHNUGARUDA,RAJESH', 'GARUDA,RAJESH']
|
49
|
+
@namor.extract("Kumar, Rajesh Vishnu Garuda").should == ['RAJESH', 'VISHNUGARUDA', 'KUMAR', 'KUMAR,RAJESH VISHNUGARUDA', 'KUMAR,RAJESH VISHNUGARUDA']
|
50
50
|
end
|
51
51
|
|
52
52
|
it "should excise suffixes like 'Jr.' from lastnames" do
|
53
|
-
@namor.extract("Smith Jr, Edward M").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
|
53
|
+
@namor.extract("Smith Jr, Edward M").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
|
54
54
|
end
|
55
55
|
|
56
56
|
it "should excise terms from optional suppression list" do
|
57
|
-
@namor.extract("Smith Jr, Edward M MD DDS").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
|
58
|
-
@namor.extract("Smith Jr, Edward M M.D.").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
|
59
|
-
@namor.extract("Smith Jr, Edward III MD PHD").should == ['EDWARD', 'PHD', 'SMITH', 'SMITH,EDWARD PHD']
|
57
|
+
@namor.extract("Smith Jr, Edward M MD DDS").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
|
58
|
+
@namor.extract("Smith Jr, Edward M M.D.").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
|
59
|
+
@namor.extract("Smith Jr, Edward III MD PHD").should == ['EDWARD', 'PHD', 'SMITH', 'SMITH,EDWARD PHD', 'SMITH,EDWARD PHD']
|
60
60
|
end
|
61
61
|
|
62
62
|
it "should handle pathological cases" do
|
63
|
-
@namor.extract(", Mary Smith").should == ['MARY', 'SMITH', nil, 'MARY SMITH']
|
63
|
+
@namor.extract(", Mary Smith").should == ['MARY', 'SMITH', nil, 'MARY SMITH', 'MARY SMITH']
|
64
64
|
end
|
65
65
|
|
66
66
|
it "should squash multi-part last names" do
|
67
|
-
@namor.extract("Al Hassan, Bashar").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR']
|
68
|
-
@namor.extract("Bashar Al-Hassan").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR']
|
67
|
+
@namor.extract("Al Hassan, Bashar").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR', 'HASSAN,BASHAR']
|
68
|
+
@namor.extract("Bashar Al-Hassan").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR', 'HASSAN,BASHAR']
|
69
69
|
end
|
70
70
|
|
71
71
|
it "should squash hyphenated first names" do
|
72
|
-
@namor.extract("Smith,Anne-Marie").should == ['ANNEMARIE', nil, 'SMITH', 'SMITH,ANNEMARIE']
|
72
|
+
@namor.extract("Smith,Anne-Marie").should == ['ANNEMARIE', nil, 'SMITH', 'SMITH,ANNEMARIE', 'SMITH,ANNEMARIE']
|
73
73
|
end
|
74
74
|
|
75
75
|
it "should treat some cases with periods as first.last" do
|
76
|
-
@namor.extract("john.smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
|
76
|
+
@namor.extract("john.smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
|
77
|
+
end
|
78
|
+
|
79
|
+
it "should generate estimated maiden names" do
|
80
|
+
@namor.extract("Jones-De Quento, Maria").should == ['MARIA', nil, 'JONESDEQUENTO', 'JONESDEQUENTO,MARIA', 'DEQUENTO,MARIA']
|
77
81
|
end
|
78
82
|
end
|
79
83
|
|
@@ -109,7 +113,7 @@ describe "name componentization" do
|
|
109
113
|
end
|
110
114
|
|
111
115
|
it "should scrub individual name components of punctuation and titles" do
|
112
|
-
@namor.
|
116
|
+
@namor.fullscrub('Foxworthy-Smythe, ESQ.').should == 'FOXWORTHYSMYTHE'
|
113
117
|
end
|
114
118
|
|
115
119
|
it "should delete strings inside parens" do
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: namor
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.1
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -108,7 +108,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
108
108
|
version: '0'
|
109
109
|
segments:
|
110
110
|
- 0
|
111
|
-
hash:
|
111
|
+
hash: 3235644830650956760
|
112
112
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
113
113
|
none: false
|
114
114
|
requirements:
|
@@ -117,7 +117,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
117
117
|
version: '0'
|
118
118
|
segments:
|
119
119
|
- 0
|
120
|
-
hash:
|
120
|
+
hash: 3235644830650956760
|
121
121
|
requirements: []
|
122
122
|
rubyforge_project:
|
123
123
|
rubygems_version: 1.8.24
|