namor 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +2 -0
- data/lib/namor.rb +50 -0
- data/lib/namor/version.rb +3 -0
- data/namor.gemspec +22 -0
- data/spec/lib/namor_spec.rb +63 -0
- data/spec/spec_helper.rb +35 -0
- metadata +102 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Jason May
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# Namor
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'namor'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install namor
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/lib/namor.rb
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
require "namor/version"
|
2
|
+
|
3
|
+
module Namor
|
4
|
+
def self.extract(name, args = {})
|
5
|
+
return [] if name.nil?
|
6
|
+
|
7
|
+
suppression_list = args[:suppress] || []
|
8
|
+
suppression_re = suppression_list.join('|')
|
9
|
+
|
10
|
+
detitled_name = name.upcase.gsub(/\b(#{suppression_re})\b/i, '').gsub(/\b(MD|JR|SR|I+|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/[_.'-]/, '').gsub(/,\s*$/, '').gsub(/ +/, ' ').strip
|
11
|
+
|
12
|
+
if detitled_name =~ /,/
|
13
|
+
# "last, first[ middle]"
|
14
|
+
lastname, firstname = detitled_name.split(/\s*,\s*/)
|
15
|
+
lastname.gsub!(/ /, '')
|
16
|
+
middlename = nil
|
17
|
+
if firstname && firstname =~ / /
|
18
|
+
pieces = firstname.split(/ +/)
|
19
|
+
firstname = pieces.shift
|
20
|
+
middlename = pieces.join if pieces.any?
|
21
|
+
end
|
22
|
+
else
|
23
|
+
# "first [middle ]last"
|
24
|
+
pieces = detitled_name.split(' ')
|
25
|
+
firstname = pieces.shift
|
26
|
+
middlename = nil
|
27
|
+
if pieces.count > 1 && pieces.first.length == 1
|
28
|
+
# assume this is a middle initial
|
29
|
+
middlename = pieces.shift
|
30
|
+
end
|
31
|
+
|
32
|
+
lastname = pieces.join
|
33
|
+
end
|
34
|
+
|
35
|
+
firstname = nil if firstname.empty?
|
36
|
+
middlename = nil if middlename && middlename.empty?
|
37
|
+
lastname = nil if lastname.empty?
|
38
|
+
|
39
|
+
fm = [firstname, middlename].compact.join(' ')
|
40
|
+
fullname = [lastname, fm].compact.join(',')
|
41
|
+
|
42
|
+
[firstname, middlename, lastname, fullname]
|
43
|
+
end
|
44
|
+
|
45
|
+
def self.extract_with_cluster(name, args = {})
|
46
|
+
ary = extract(name, args)
|
47
|
+
return [] if ary.empty?
|
48
|
+
ary << ary.last.gsub(/\W/, '_')
|
49
|
+
end
|
50
|
+
end
|
data/namor.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/namor/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Jason May"]
|
6
|
+
gem.email = ["jmay@pobox.com"]
|
7
|
+
gem.description = %q{Munging English names}
|
8
|
+
gem.summary = %q{Parse & extract pieces of names}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "namor"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = Namor::VERSION
|
17
|
+
|
18
|
+
gem.add_development_dependency "rake", "~> 0.9.2"
|
19
|
+
gem.add_development_dependency "rspec", "~> 2.9.0"
|
20
|
+
gem.add_development_dependency "guard-rspec", "~> 0.7.0"
|
21
|
+
gem.add_development_dependency "ruby_gntp", "~> 0.3.4"
|
22
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# spec for name component extraction
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
describe "name extract" do
|
6
|
+
it "should handle 2-part names without commas" do
|
7
|
+
Namor::extract("john smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
|
8
|
+
end
|
9
|
+
|
10
|
+
it "should handle 2-part names with commas" do
|
11
|
+
Namor::extract("SMITH, JOHN").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
|
12
|
+
end
|
13
|
+
|
14
|
+
it "should handle 2-part names with commas and middle initials" do
|
15
|
+
Namor::extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
16
|
+
end
|
17
|
+
|
18
|
+
it "should handle 2-part names with commas and middle initials" do
|
19
|
+
Namor::extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
20
|
+
end
|
21
|
+
|
22
|
+
it "should strip elements within parentheses" do
|
23
|
+
Namor::extract("SMITH, JOHN (Jacko) R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
24
|
+
end
|
25
|
+
|
26
|
+
it "should drop periods" do
|
27
|
+
Namor::extract("John R. Smith").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
|
28
|
+
end
|
29
|
+
|
30
|
+
it "should drop spaces in last name (only when input has a comma)" do
|
31
|
+
Namor::extract("Smith Jones, Mary").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
|
32
|
+
end
|
33
|
+
|
34
|
+
it "should drop dashes & apostrophes" do
|
35
|
+
Namor::extract("Mary Smith-Jones").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
|
36
|
+
Namor::extract("Mary S. O'Keefe").should == ['MARY', 'S', 'OKEEFE', 'OKEEFE,MARY S']
|
37
|
+
Namor::extract("Jean-Michel Claude").should == ['JEANMICHEL', nil, 'CLAUDE', 'CLAUDE,JEANMICHEL']
|
38
|
+
end
|
39
|
+
|
40
|
+
it "should concatenate extract name pieces" do
|
41
|
+
Namor::extract("rajesh kumar vishnu garuda").should == ['RAJESH', nil, 'KUMARVISHNUGARUDA', 'KUMARVISHNUGARUDA,RAJESH']
|
42
|
+
Namor::extract("Kumar, Rajesh Vishnu Garuda").should == ['RAJESH', 'VISHNUGARUDA', 'KUMAR', 'KUMAR,RAJESH VISHNUGARUDA']
|
43
|
+
end
|
44
|
+
|
45
|
+
it "should excise suffixes like 'Jr.' from lastnames" do
|
46
|
+
Namor::extract("Smith Jr, Edward M").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
|
47
|
+
end
|
48
|
+
|
49
|
+
it "should excise terms from optional suppression list" do
|
50
|
+
Namor::extract("Smith Jr, Edward M MD DDS", :suppress => ['MD', 'DDS']).should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
|
51
|
+
Namor::extract("Smith Jr, Edward III MD PHD", :suppress => ['MD', 'DDS']).should == ['EDWARD', 'PHD', 'SMITH', 'SMITH,EDWARD PHD']
|
52
|
+
end
|
53
|
+
|
54
|
+
it "should handle pathological cases" do
|
55
|
+
Namor::extract(", Mary Smith").should == ['MARY', 'SMITH', nil, 'MARY SMITH']
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
describe "with cluster coding" do
|
60
|
+
it "should generate cluster labels" do
|
61
|
+
Namor::extract_with_cluster("Smith Jr, Edward III MD PHD", :suppress => ['MD', 'DDS']).last.should == 'SMITH_EDWARD_PHD'
|
62
|
+
end
|
63
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# require File.expand_path("../../config/environment", __FILE__)
|
2
|
+
# require 'rspec/rails'
|
3
|
+
require 'rspec/autorun'
|
4
|
+
# require 'capybara/rspec'
|
5
|
+
require "tempfile"
|
6
|
+
|
7
|
+
# Requires supporting ruby files with custom matchers and macros, etc,
|
8
|
+
# in spec/support/ and its subdirectories.
|
9
|
+
# Dir[Rails.root.join("spec/support/**/*.rb")].each {|f| require f}
|
10
|
+
|
11
|
+
require File.expand_path('../../lib/namor', __FILE__)
|
12
|
+
|
13
|
+
RSpec.configure do |config|
|
14
|
+
# ## Mock Framework
|
15
|
+
#
|
16
|
+
# If you prefer to use mocha, flexmock or RR, uncomment the appropriate line:
|
17
|
+
#
|
18
|
+
# config.mock_with :mocha
|
19
|
+
# config.mock_with :flexmock
|
20
|
+
# config.mock_with :rr
|
21
|
+
|
22
|
+
# Remove this line if you're not using ActiveRecord or ActiveRecord fixtures
|
23
|
+
# config.fixture_path = "#{::Rails.root}/spec/fixtures"
|
24
|
+
|
25
|
+
# If you're not using ActiveRecord, or you'd prefer not to run each of your
|
26
|
+
# examples within a transaction, remove the following line or assign false
|
27
|
+
# instead of true.
|
28
|
+
# config.use_transactional_fixtures = true
|
29
|
+
# config.use_instantiated_fixtures = false
|
30
|
+
|
31
|
+
# If true, the base class of anonymous controllers will be inferred
|
32
|
+
# automatically. This will be the default behavior in future versions of
|
33
|
+
# rspec-rails.
|
34
|
+
# config.infer_base_class_for_anonymous_controllers = false
|
35
|
+
end
|
metadata
ADDED
@@ -0,0 +1,102 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: namor
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jason May
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-08-08 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rake
|
16
|
+
requirement: &2152651100 !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ~>
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 0.9.2
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: *2152651100
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: rspec
|
27
|
+
requirement: &2152661440 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ~>
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 2.9.0
|
33
|
+
type: :development
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *2152661440
|
36
|
+
- !ruby/object:Gem::Dependency
|
37
|
+
name: guard-rspec
|
38
|
+
requirement: &2152659940 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ~>
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: 0.7.0
|
44
|
+
type: :development
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: *2152659940
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: ruby_gntp
|
49
|
+
requirement: &2152658740 !ruby/object:Gem::Requirement
|
50
|
+
none: false
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 0.3.4
|
55
|
+
type: :development
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *2152658740
|
58
|
+
description: Munging English names
|
59
|
+
email:
|
60
|
+
- jmay@pobox.com
|
61
|
+
executables: []
|
62
|
+
extensions: []
|
63
|
+
extra_rdoc_files: []
|
64
|
+
files:
|
65
|
+
- .gitignore
|
66
|
+
- Gemfile
|
67
|
+
- LICENSE
|
68
|
+
- README.md
|
69
|
+
- Rakefile
|
70
|
+
- lib/namor.rb
|
71
|
+
- lib/namor/version.rb
|
72
|
+
- namor.gemspec
|
73
|
+
- spec/lib/namor_spec.rb
|
74
|
+
- spec/spec_helper.rb
|
75
|
+
homepage: ''
|
76
|
+
licenses: []
|
77
|
+
post_install_message:
|
78
|
+
rdoc_options: []
|
79
|
+
require_paths:
|
80
|
+
- lib
|
81
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
82
|
+
none: false
|
83
|
+
requirements:
|
84
|
+
- - ! '>='
|
85
|
+
- !ruby/object:Gem::Version
|
86
|
+
version: '0'
|
87
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
88
|
+
none: false
|
89
|
+
requirements:
|
90
|
+
- - ! '>='
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
requirements: []
|
94
|
+
rubyforge_project:
|
95
|
+
rubygems_version: 1.8.10
|
96
|
+
signing_key:
|
97
|
+
specification_version: 3
|
98
|
+
summary: Parse & extract pieces of names
|
99
|
+
test_files:
|
100
|
+
- spec/lib/namor_spec.rb
|
101
|
+
- spec/spec_helper.rb
|
102
|
+
has_rdoc:
|