namor 0.3.0 → 0.3.1

data/lib/namor/namor.rb

@@ -19,7 +19,28 @@ class Namor::Namor
     suppression_list = @config[:suppress] || []
     suppression_re = Regexp.new('\b?' + (suppression_list + (opts[:suppress]||[])).compact.map(&:upcase).join('|') + '\b?')
 
-    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
+    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
+  end
+
+  def fullscrub(name)
+    final_cleaning(scrub(name))
+  end
+
+  def demaiden(lastname)
+    return [nil,nil] unless lastname && !lastname.empty?
+    if lastname =~ /\-/
+      [lastname.gsub(/ /, ''), lastname.split(/\-/).last.gsub(/ /, '')]
+    else
+      [lastname.gsub(/ /, ''), lastname.split(/ /).last]
+    end
+  end
+
+  def final_cleaning(name)
+    if name && !name.empty?
+      name.gsub(/\-/, '')
+    else
+      nil
+    end
   end
 
   def extract(name, opts = {})
@@ -30,7 +51,7 @@ class Namor::Namor
     if detitled_name =~ /,/
       # "last, first[ middle]"
       lastname, firstname = detitled_name.split(/\s*,\s*/)
-      lastname.gsub!(/ /, '')
+      lastname, de_maidened_last = demaiden(lastname)
       middlename = nil
       if firstname && firstname =~ / /
         pieces = firstname.split(/ +/)
@@ -38,26 +59,29 @@ class Namor::Namor
         middlename = pieces.join if pieces.any?
       end
     else
-      # "first [middle ]last"
+      # "first [middle-initial ]last" or "first everything-else-is-the-lastname"
       pieces = detitled_name.split(' ')
       firstname = pieces.shift
-      middlename = nil
       if pieces.count > 1 && pieces.first.length == 1
         # assume this is a middle initial
         middlename = pieces.shift
+      else
+        middlename = nil
       end
 
-      lastname = pieces.join
+      lastname, de_maidened_last = demaiden(pieces.join(' '))
     end
 
-    firstname = nil if firstname.empty?
-    middlename = nil if middlename && middlename.empty?
-    lastname = nil if lastname.empty?
+    firstname = final_cleaning(firstname)
+    middlename = final_cleaning(middlename)
+    lastname = final_cleaning(lastname)
+    de_maidened_last = final_cleaning(de_maidened_last)
 
     fm = [firstname, middlename].compact.join(' ')
     fullname = [lastname, fm].compact.join(',')
+    nee_fullname = [de_maidened_last, fm].compact.join(',')
 
-    [firstname, middlename, lastname, fullname]
+    [firstname, middlename, lastname, fullname, nee_fullname]
   end
 
   def extract_with_cluster(name, opts = {})

data/lib/namor/version.rb

@@ -1,3 +1,3 @@
 module Namor
-  VERSION = "0.3.0"
+  VERSION = "0.3.1"
 end

data/spec/lib/namor_spec.rb

@@ -9,71 +9,75 @@ describe "name extract" do
   end
 
   it "should handle 2-part names without commas" do
-    @namor.extract("john smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
+    @namor.extract("john smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
   end
 
   it "should handle 2-part names with commas" do
-    @namor.extract("SMITH, JOHN").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
+    @namor.extract("SMITH, JOHN").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
   end
 
   it "should handle 2-part names with commas and middle initials" do
-    @namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
+    @namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
   end
 
   it "should handle 2-part names with commas and middle initials" do
-    @namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
+    @namor.extract("SMITH, JOHN R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
   end
 
   it "should strip elements within parentheses" do
-    @namor.extract("SMITH, JOHN (Jacko) R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
+    @namor.extract("SMITH, JOHN (Jacko) R").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
   end
 
   it "should drop periods" do
-    @namor.extract("John R. Smith").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R']
+    @namor.extract("John R. Smith").should == ['JOHN', 'R', 'SMITH', 'SMITH,JOHN R', 'SMITH,JOHN R']
   end
 
   it "should drop spaces in last name (only when input has a comma)" do
-    @namor.extract("Smith Jones, Mary").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
+    @namor.extract("Smith Jones, Mary").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY', 'JONES,MARY']
   end
 
   it "should drop dashes, apostrophes, ampersands" do
-    @namor.extract("Mary Smith-Jones").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY']
-    @namor.extract("Mary S. O'Keefe").should == ['MARY', 'S', 'OKEEFE', 'OKEEFE,MARY S']
-    @namor.extract("Jean-Michel Claude").should == ['JEANMICHEL', nil, 'CLAUDE', 'CLAUDE,JEANMICHEL']
-    @namor.extract("Smith, Bob & Sue").should == ['BOB', 'SUE', 'SMITH', 'SMITH,BOB SUE']
-    @namor.extract("Research & Development").should == ['RESEARCH', nil, 'DEVELOPMENT', 'DEVELOPMENT,RESEARCH']
+    @namor.extract("Mary Smith-Jones").should == ['MARY', nil, 'SMITHJONES', 'SMITHJONES,MARY', 'JONES,MARY']
+    @namor.extract("Mary S. O'Keefe").should == ['MARY', 'S', 'OKEEFE', 'OKEEFE,MARY S', 'OKEEFE,MARY S']
+    @namor.extract("Jean-Michel Claude").should == ['JEANMICHEL', nil, 'CLAUDE', 'CLAUDE,JEANMICHEL', 'CLAUDE,JEANMICHEL']
+    @namor.extract("Smith, Bob & Sue").should == ['BOB', 'SUE', 'SMITH', 'SMITH,BOB SUE', 'SMITH,BOB SUE']
+    @namor.extract("Research & Development").should == ['RESEARCH', nil, 'DEVELOPMENT', 'DEVELOPMENT,RESEARCH', 'DEVELOPMENT,RESEARCH']
   end
 
   it "should concatenate extract name pieces" do
-    @namor.extract("rajesh kumar vishnu garuda").should == ['RAJESH', nil, 'KUMARVISHNUGARUDA', 'KUMARVISHNUGARUDA,RAJESH']
-    @namor.extract("Kumar, Rajesh Vishnu Garuda").should == ['RAJESH', 'VISHNUGARUDA', 'KUMAR', 'KUMAR,RAJESH VISHNUGARUDA']
+    @namor.extract("rajesh kumar vishnu garuda").should == ['RAJESH', nil, 'KUMARVISHNUGARUDA', 'KUMARVISHNUGARUDA,RAJESH', 'GARUDA,RAJESH']
+    @namor.extract("Kumar, Rajesh Vishnu Garuda").should == ['RAJESH', 'VISHNUGARUDA', 'KUMAR', 'KUMAR,RAJESH VISHNUGARUDA', 'KUMAR,RAJESH VISHNUGARUDA']
   end
 
   it "should excise suffixes like 'Jr.' from lastnames" do
-    @namor.extract("Smith Jr, Edward M").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
+    @namor.extract("Smith Jr, Edward M").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
   end
 
   it "should excise terms from optional suppression list" do
-    @namor.extract("Smith Jr, Edward M MD DDS").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
-    @namor.extract("Smith Jr, Edward M M.D.").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M']
-    @namor.extract("Smith Jr, Edward III MD PHD").should == ['EDWARD', 'PHD', 'SMITH', 'SMITH,EDWARD PHD']
+    @namor.extract("Smith Jr, Edward M MD DDS").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
+    @namor.extract("Smith Jr, Edward M M.D.").should == ['EDWARD', 'M', 'SMITH', 'SMITH,EDWARD M', 'SMITH,EDWARD M']
+    @namor.extract("Smith Jr, Edward III MD PHD").should == ['EDWARD', 'PHD', 'SMITH', 'SMITH,EDWARD PHD', 'SMITH,EDWARD PHD']
   end
 
   it "should handle pathological cases" do
-    @namor.extract(", Mary Smith").should == ['MARY', 'SMITH', nil, 'MARY SMITH']
+    @namor.extract(", Mary Smith").should == ['MARY', 'SMITH', nil, 'MARY SMITH', 'MARY SMITH']
   end
 
   it "should squash multi-part last names" do
-    @namor.extract("Al Hassan, Bashar").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR']
-    @namor.extract("Bashar Al-Hassan").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR']
+    @namor.extract("Al Hassan, Bashar").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR', 'HASSAN,BASHAR']
+    @namor.extract("Bashar Al-Hassan").should == ['BASHAR', nil, 'ALHASSAN', 'ALHASSAN,BASHAR', 'HASSAN,BASHAR']
   end
 
   it "should squash hyphenated first names" do
-    @namor.extract("Smith,Anne-Marie").should == ['ANNEMARIE', nil, 'SMITH', 'SMITH,ANNEMARIE']
+    @namor.extract("Smith,Anne-Marie").should == ['ANNEMARIE', nil, 'SMITH', 'SMITH,ANNEMARIE', 'SMITH,ANNEMARIE']
   end
 
   it "should treat some cases with periods as first.last" do
-    @namor.extract("john.smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN']
+    @namor.extract("john.smith").should == ['JOHN', nil, 'SMITH', 'SMITH,JOHN', 'SMITH,JOHN']
+  end
+
+  it "should generate estimated maiden names" do
+    @namor.extract("Jones-De Quento, Maria").should == ['MARIA', nil, 'JONESDEQUENTO', 'JONESDEQUENTO,MARIA', 'DEQUENTO,MARIA']
   end
 end
 
@@ -109,7 +113,7 @@ describe "name componentization" do
   end
 
   it "should scrub individual name components of punctuation and titles" do
-    @namor.scrub('Foxworthy-Smythe, ESQ.').should == 'FOXWORTHYSMYTHE'
+    @namor.fullscrub('Foxworthy-Smythe, ESQ.').should == 'FOXWORTHYSMYTHE'
   end
 
   it "should delete strings inside parens" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: namor
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
   prerelease: 
 platform: ruby
 authors:
@@ -108,7 +108,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 236992470015496114
+      hash: 3235644830650956760
 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: 236992470015496114
+      hash: 3235644830650956760
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24