namor 0.1.0 → 0.2.0

data/lib/namor/namor.rb

@@ -7,13 +7,25 @@ class Namor::Namor
     @config = opts
   end
 
-  def extract(name)
-    return [] if name.nil?
-
+  # clean up a single name component
+  # * output all converted to uppercase
+  # * strip leading ZZ+ or XX+ (frequently used as invalid-account prefixes)
+  # * remove any words that are in the user-provided suppression list
+  # * remove words from list of common suffixes (Jr, Sr etc)
+  # * remove anything inside parenthesis
+  # * remove punctuation
+  # * squeeze whitespace & trim spaces from ends
+  def scrub(name, opts = {})
     suppression_list = @config[:suppress] || []
-    suppression_re = suppression_list.join('|')
+    suppression_re = (suppression_list + (opts[:suppress]||[])).compact.map(&:upcase).join('|')
+
+    name && name.upcase.gsub(/^[ZX]{2,}/, '').gsub(/\b(#{suppression_re})\b/i, '').gsub(/\b(JR|SR|II|III|IV)\b/i, '').gsub(/\([^\(]*\)/, '').gsub(/\./, ' ').gsub(/[_'-]/, '').gsub(/,\s*$/, '').gsub(/ +/, ' ').strip
+  end
+
+  def extract(name, opts = {})
+    return [] if name.nil?
 
-    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
+    detitled_name = scrub(name, opts)
 
     if detitled_name =~ /,/
       # "last, first[ middle]"

data/lib/namor/version.rb

@@ -1,3 +1,3 @@
 module Namor
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/spec/lib/namor_spec.rb

@@ -5,7 +5,7 @@ require "spec_helper"
 describe "name extract" do
   before(:all) do
     @namor = Namor::Namor.new
-    @namor.config(:suppress => ['MD', 'DDS'])
+    @namor.config(:suppress => ['MD', 'dds'])
   end
 
   it "should handle 2-part names without commas" do
@@ -69,6 +69,9 @@ describe "name extract" do
     @namor.extract("Smith,Anne-Marie").should == ['ANNEMARIE', nil, 'SMITH', 'SMITH,ANNEMARIE']
   end
 
+  it "should treat some cases with periods as first.last" do
+    @namor.extract("john.smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
+  end
 end
 
 describe "with cluster coding" do
@@ -101,4 +104,25 @@ describe "name componentization" do
     @namor.components("john smith esk.").should == ['ESK', 'JOHN', 'SMITH']
     @namor.components("john smith esq.").should == ['JOHN', 'SMITH']
   end
+
+  it "should scrub individual name components of punctuation and titles" do
+    @namor.scrub('Foxworthy-Smythe, ESQ.').should == 'FOXWORTHYSMYTHE'
+  end
+
+  it "should delete strings inside parens" do
+    @namor.scrub("O'Hara (Morrison)").should == 'OHARA'
+    @namor.scrub("  Smith  (Brown) ").should == 'SMITH'
+  end
+
+  it "should deal with periods in names" do
+    @namor.scrub("G. Gordon").should == 'G GORDON'
+  end
+
+  it "should remove junk prefixing" do
+    @namor.scrub("ZZJOHN SMITH").should == 'JOHN SMITH'
+  end
+
+  it "should allow case-specific word suppression" do
+    @namor.scrub("Amazing Magician", :suppress => ['magician', nil, 'conjuror']).should == 'AMAZING'
+  end
 end

data/spec/spec_helper.rb

@@ -1,35 +1,9 @@
-# require File.expand_path("../../config/environment", __FILE__)
-# require 'rspec/rails'
 require 'rspec/autorun'
-# require 'capybara/rspec'
-require "tempfile"
 
 # Requires supporting ruby files with custom matchers and macros, etc,
 # in spec/support/ and its subdirectories.
-# Dir[Rails.root.join("spec/support/**/*.rb")].each {|f| require f}
 
 require File.expand_path('../../lib/namor', __FILE__)
 
 RSpec.configure do |config|
-  # ## Mock Framework
-  #
-  # If you prefer to use mocha, flexmock or RR, uncomment the appropriate line:
-  #
-  # config.mock_with :mocha
-  # config.mock_with :flexmock
-  # config.mock_with :rr
-
-  # Remove this line if you're not using ActiveRecord or ActiveRecord fixtures
-  # config.fixture_path = "#{::Rails.root}/spec/fixtures"
-
-  # If you're not using ActiveRecord, or you'd prefer not to run each of your
-  # examples within a transaction, remove the following line or assign false
-  # instead of true.
-  # config.use_transactional_fixtures = true
-  # config.use_instantiated_fixtures  = false
-
-  # If true, the base class of anonymous controllers will be inferred
-  # automatically. This will be the default behavior in future versions of
-  # rspec-rails.
-  # config.infer_base_class_for_anonymous_controllers = false
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: namor
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-08-30 00:00:00.000000000 Z
+date: 2012-08-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -108,7 +108,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 52459653516907226
+      hash: -1410144287652690285
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -117,7 +117,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 52459653516907226
+      hash: -1410144287652690285
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24