namae 0.7.1 → 0.8.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2a99f6d608d0f0a94a3235e2a00e1bd8403913c5
+  data.tar.gz: f9efce4cd6dbcfc5c0b7d6d7a29a058a2849ec58
+SHA512:
+  metadata.gz: 87611448553830c290b1ff250d65390b17ac4a7217e9e12f71f30a14866b82a46bd79650d4810dc21cdb90a219fccc471ffd2025de8e640d0d1ecbb098937877
+  data.tar.gz: 6310b836f15d5b09df3ed821d39d9e558a463476fa7b6fecde76dd3b1a20305d653776a2923e01d0c890c4c75273de2671f7d6b48c010111e60c3bc082f30808

data/.travis.yml

@@ -1,6 +1,7 @@
 language: ruby
 bundler_args: --without debug osx development
 rvm:
+  - 2.0.0
   - 1.9.2
   - 1.9.3
   - jruby

data/AGPL

@@ -629,8 +629,9 @@ to attach them to the start of each source file to most effectively
 state the exclusion of warranty; and each file should have at least
 the "copyright" line and a pointer to where the full notice is found.
 
-    Namae. A personal name parser
+    Namae. A personal name parser.
     Copyright (C) 2012 President and Fellows of Harvard College
+    Copyright (C) 2013 Sylvester Keil
 
     This program is free software: you can redistribute it and/or modify
     it under the terms of the GNU Affero General Public License as published by

data/BSDL

@@ -1,5 +1,6 @@
-Namae. A personal name parser
+Namae. A personal name parser.
 Copyright (C) 2012 President and Fellows of Harvard College
+Copyright (C) 2013 Sylvester Keil
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

data/Gemfile

@@ -1,24 +1,23 @@
-source :rubygems
+source 'https://rubygems.org'
 
 group :test do
-  gem 'rspec', '~> 2.10.0'
-  gem 'rake', '~> 0.9.2'
-  gem 'cucumber', '~> 1.2.0'
-  gem 'yard', '~> 0.7'
+  gem 'rspec'
+  gem 'rake'
+  gem 'cucumber'
 end
 
 group :development do
-  gem 'racc', '~> 1.4.8', :platform => [:mri_19, :mri_18, :rbx]
-  gem 'bundler', '~> 1.1'
+  gem 'racc', '~> 1.4.8', :platform => [:ruby_20, :ruby_19, :ruby_18]
   gem 'simplecov', :require => false
-  gem 'ZenTest', '~> 4.8.0'
+  gem 'ZenTest'
   gem 'jeweler', '~> 1.8.3'
+  gem 'yard'
 end
 
 group :debug do
-  gem 'debugger', '~> 1.1.3', :platform => :mri_19
+  gem 'debugger', '~> 1.1.3', :platform => [:mri_19]
 end
 
 group :osx do
   gem 'autotest-fsevent'
-end
+end

data/README.md

@@ -90,6 +90,15 @@ names are written in display-order:
     Namae.parse 'Prof. Donald Ervin Knuth'
     #-> [#<Name family="Knuth" given="Donald Ervin" title="Prof.">]
     
+    Namae.parse 'Ms. Sofia Kovaleskaya'
+    #-> [#<Name family="Kovaleskaya" given="Sofia" appellation="Ms.">]
+
+    Namae.parse 'Countess Ada Lovelace'
+    #-> [#<Name family="Lovelace" given="Ada" title="Countess">]
+
+    Namae.parse 'Ken Griffey Jr.'
+    #-> [#<Name family="Griffey" given="Ken" suffix="Jr.">]
+
 Or in sort-order:
 
     Namae.parse 'Turing, Alan M.'
@@ -153,8 +162,13 @@ Contributors
 * [Sylvester Keil](http://sylvester.keil.or.at)
 * Dan Collis-Puro
 
+Credits
+-------
+Namae was written as a part of a Google Summer of Code project. Thanks Google!
+
 Copyright
 ---------
 Copyright (c) 2012 President and Fellows of Harvard College.
+Copyright (c) 2013 Sylvester Keil
 
 Namae is dual licensed under the AGPL and a BSD-style license.

data/Rakefile

@@ -58,5 +58,9 @@ Cucumber::Rake::Task.new(:features)
 
 task :default => [:spec, :features]
 
-require 'yard'
-YARD::Rake::YardocTask.new
+begin
+  require 'yard'
+  YARD::Rake::YardocTask.new
+rescue LoadError => e
+  # ignore
+end

data/features/bibtex.feature

@@ -40,9 +40,9 @@ Feature: Parse BibTeX-style names
     | bb CC dd EE, AA | AA         | bb CC dd   | EE      |    |
     | bb, AA          | AA         |            | bb      |    |
     | BB,             |            |            | BB      |    |
-    | bb CC,XX, AA    | AA         | bb         | CC      | XX |
-    | bb CC,xx, AA    | AA         | bb         | CC      | xx |
-    | BB,, AA         | AA         |            | BB      |    |
+    | bb CC,II, AA    | AA         | bb         | CC      | II |
+    | bb CC,jr, AA    | AA         | bb         | CC      | jr |
+#    | BB,, AA         | AA         |            | BB      |    |
     | CC dd BB, AA    | AA         | CC dd      | BB      |    |
     | BB, AA          | AA         |            | BB      |    |
 

data/features/examples.feature

@@ -10,13 +10,16 @@ Feature: Parse the names in the Readme file
 
     @readme @display
     Scenarios: Readme examples (display-order)
-      | name                         | given        | particle | family    | suffix | title | appellation | nick |
-      | Charles Babbage              | Charles      |          | Babbage   |        |       |             |      |
-      | Mr. Alan M. Turing           | Alan M.      |          | Turing    |        |       | Mr.         |      |
-      | Yukihiro "Matz" Matsumoto    | Yukihiro     |          | Matsumoto |        |       |             | Matz |
-      | Sir Isaac Newton             | Isaac        |          | Newton    |        | Sir   |             |      |
-      | Prof. Donald Ervin Knuth     | Donald Ervin |          | Knuth     |        | Prof. |             |      |
-      | Lord Byron                   |              |          | Byron     |        | Lord  |             |      |
+      | name                         | given        | particle | family       | suffix | title     | appellation | nick |
+      | Charles Babbage              | Charles      |          | Babbage      |        |           |             |      |
+      | Mr. Alan M. Turing           | Alan M.      |          | Turing       |        |           | Mr.         |      |
+      | Yukihiro "Matz" Matsumoto    | Yukihiro     |          | Matsumoto    |        |           |             | Matz |
+      | Sir Isaac Newton             | Isaac        |          | Newton       |        | Sir       |             |      |
+      | Prof. Donald Ervin Knuth     | Donald Ervin |          | Knuth        |        | Prof.     |             |      |
+      | Lord Byron                   |              |          | Byron        |        | Lord      |             |      |
+      | Ms. Sofia Kovalevskaya       | Sofia        |          | Kovalevskaya |        |           | Ms.         |      |
+      | Countess Ada Lovelace        | Ada          |          | Lovelace     |        | Countess  |             |      |
+      | Augusta Ada King             | Augusta Ada  |          | King         |        |           |             |      |
 
     @readme @sort
     Scenarios: Readme examples (sort-order)

data/features/suffix.feature

@@ -9,34 +9,34 @@ Feature: Parse names with a suffix
       | given      | family  | suffix  |
       | Ken        | Griffey | Jr.     |
 
-  # @names @suffix
-  # Scenario: Names with a suffix in display-order
-  #   When I parse the names "Ken Griffey, Jr."
-  #   Then the names should be:
-  #     | given      | family  | suffix  |
-  #     | Ken        | Griffey | Jr.     |
-  # 
-  # @names @suffix
-  # Scenario: Names with a suffix in sort-order chicago style
-  #   When I parse the names "Griffey, Ken, Jr."
-  #   Then the names should be:
-  #     | given      | family  | suffix  |
-  #     | Ken        | Griffey | Jr.     |
-  # 
-  # @names @suffix
-  # Scenario: Names with a suffix in display-order no comma
-  #   When I parse the names "Ken Griffey Jr."
-  #   Then the names should be:
-  #     | given      | family  | suffix  |
-  #     | Ken        | Griffey | Jr.     |
-  # 
-  # 
-  # @names @suffix @list
-  # Scenario: Names with a suffix
-  #   When I parse the names "Griffey, Jr., Ken and Ken Griffey, Jr. and Griffey, Ken, Jr. and Ken Griffey Jr."
-  #   Then the names should be:
-  #     | given      | family  | suffix  |
-  #     | Ken        | Griffey | Jr.     |
-  #     | Ken        | Griffey | Jr.     |
-  #     | Ken        | Griffey | Jr.     |
-  #     | Ken        | Griffey | Jr.     |
+  @names @suffix
+  Scenario: Names with a suffix in display-order
+    When I parse the names "Ken Griffey, Jr."
+    Then the names should be:
+      | given      | family  | suffix  |
+      | Ken        | Griffey | Jr.     |
+  
+  @names @suffix
+  Scenario: Names with a suffix in sort-order chicago style
+    When I parse the names "Griffey, Ken, Jr."
+    Then the names should be:
+      | given      | family  | suffix  |
+      | Ken        | Griffey | Jr.     |
+  
+  @names @suffix
+  Scenario: Names with a suffix in display-order no comma
+    When I parse the names "Ken Griffey Jr."
+    Then the names should be:
+      | given      | family  | suffix  |
+      | Ken        | Griffey | Jr.     |
+  
+  
+  @names @suffix @list
+  Scenario: Names with a suffix
+    When I parse the names "Griffey, Jr., Ken and Ken Griffey, Jr. and Griffey, Ken, Jr. and Ken Griffey Jr."
+    Then the names should be:
+      | given      | family  | suffix  |
+      | Ken        | Griffey | Jr.     |
+      | Ken        | Griffey | Jr.     |
+      | Ken        | Griffey | Jr.     |
+      | Ken        | Griffey | Jr.     |

data/lib/namae/name.rb

@@ -46,10 +46,22 @@ module Namae
 
     
     # @param attributes [Hash] the individual parts of the name
+    # @param sanitize [Boolean] whether or not to apply extra
+    #   sanitation rules
     # @example
     #   Name.new(:family => 'Matsumoto')
-    def initialize(attributes = {})
+    def initialize(attributes = {}, sanitize = false)
       super(*attributes.values_at(*Name.parts))
+
+      if sanitize && suffix && !given && family
+        tokens = family.split(/\s+/)
+
+        # Display-order plus comma suffix special case
+        if tokens.length > 1
+          self.family = tokens.pop
+          self.given = tokens.join(' ')
+        end
+      end
     end
   
     # @return [String] the name in sort order
@@ -142,4 +154,4 @@ module Namae
     end
 
   end
-end
+end

data/lib/namae/parser.rb

@@ -12,7 +12,7 @@ require 'strscan'
 module Namae
   class Parser < Racc::Parser
 
-module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
+module_eval(<<'...end parser.y/module_eval...', 'parser.y', 97)
 
   include Singleton
     
@@ -24,8 +24,8 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
       :prefer_comma_as_separator => false,
       :comma => ',',
       :separator => /\s*(\band\b|\&)\s*/i,
-      :title => /\s*\b(sir|lord|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
-      :suffix => /\s*\b(jr|sr|[ivx]{2,})\.?\s*/i,
+      :title => /\s*\b(sir|lord|count(ess)?|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
+      :suffix => /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/,
       :appellation => /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
     }
   end
@@ -77,7 +77,7 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
   end
   
   def reset
-    @commas, @words, @initials, @yydebug = 0, 0, 0, debug?   
+    @commas, @words, @initials, @suffices, @yydebug = 0, 0, 0, 0, debug?   
     self
   end
 
@@ -93,7 +93,7 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
   
   def consume_separator
     return next_token if seen_separator?
-    @commas, @words, @initials = 0, 0, 0
+    @commas, @words, @initials, @suffices = 0, 0, 0, 0
     [:AND, :AND]
   end
   
@@ -104,7 +104,14 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
 
   def consume_word(type, word)
     @words += 1
-    @initials += 1 if type == :UWORD && word =~ /^\s*[[:alpha:]]\.\s*$/
+
+    case type
+    when :UWORD
+      @initials += 1 if word =~ /^\s*[[:alpha:]]\.\s*$/
+    when :SUFFIX
+      @suffices += 1
+    end
+
     [type, word]
   end
 
@@ -113,12 +120,7 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
   end
 
   def suffix?
-    seen_suffix? || will_see_suffix?
-  end
-  
-  def seen_suffix?
-    return false unless stack.length > 1
-    last_token == :COMMA || last_token =~ suffix
+    !@suffices.zero? || will_see_suffix?
   end
   
   def will_see_suffix?
@@ -130,7 +132,8 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
   end
 
   def seen_full_name?
-    prefer_comma_as_separator? && @words > 1 && (@initials > 0 || !will_see_initial?)
+    prefer_comma_as_separator? && @words > 1 &&
+      (@initials > 0 || !will_see_initial?) && !will_see_suffix?
   end
 
   def next_token
@@ -149,6 +152,8 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
       next_token
     when input.scan(title)
       consume_word(:TITLE, input.matched.strip)
+    when input.scan(suffix)
+      consume_word(:SUFFIX, input.matched.strip)
     when input.scan(appellation)
       [:APPELLATION, input.matched.strip]
     when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{comma}]*/)
@@ -177,105 +182,121 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 90)
 ##### State transition tables begin ###
 
 racc_action_table = [
-   -34,    16,   -22,   -36,   -22,   -35,   -22,   -34,    17,   -22,
-   -36,   -22,   -35,   -34,    53,   -22,    14,    12,    15,    55,
-   -34,     7,     8,    14,    12,    15,    42,    33,     7,     8,
-    14,    22,    15,    24,    14,    22,    15,    24,    30,    28,
-    31,    30,    28,    31,    49,    48,    50,    30,    39,    31,
-    49,    48,    50,    49,    48,    50,    30,    28,    31,    30,
-    43,    31,    49,    48,    50,    30,    28,    31,    49,    48,
-    50,    14,    22,    15,    30,    32,    31,    30,    28,    31 ]
+   -36,   -38,   -37,    58,    30,    62,    31,   -36,   -38,   -37,
+   -36,   -38,   -37,    56,   -22,    56,   -22,    53,    52,    54,
+   -36,   -22,   -22,   -22,    39,    16,    39,   -36,    33,    39,
+   -22,    32,    17,    53,    52,    54,    53,    52,    54,    56,
+    39,    45,   nil,    39,    14,    12,    15,   nil,   nil,     7,
+     8,    14,    12,    15,   nil,   nil,     7,     8,    14,    22,
+    15,    24,    60,    53,    52,    54,    14,    22,    15,    24,
+    30,    46,    31,    53,    52,    54,    30,    28,    31,    30,
+    28,    31,    30,    42,    31,    30,    28,    31,    30,    28,
+    31,    30,    28,    31,    14,    22,    15,    53,    52,    54 ]
 
 racc_action_check = [
-    22,     1,    39,    15,    28,    14,    28,    22,     1,    39,
-    15,    28,    14,    12,    41,    12,     0,     0,     0,    45,
-    12,     0,     0,    17,    17,    17,    27,    16,    17,    17,
-    20,    20,    20,    20,     9,     9,     9,     9,    25,    25,
-    25,    21,    21,    21,    55,    55,    55,    24,    24,    24,
-    53,    53,    53,    47,    47,    47,    10,    10,    10,    29,
-    29,    29,    32,    32,    32,    35,    35,    35,    42,    42,
-    42,     5,     5,     5,    40,    11,    40,    38,    38,    38 ]
+    22,    15,    14,    44,    43,    50,    43,    22,    15,    14,
+    22,    15,    14,    50,    28,    38,    28,    32,    32,    32,
+    12,    28,    12,    42,    32,     1,    23,    12,    16,    60,
+    42,    11,     1,    58,    58,    58,    45,    45,    45,    64,
+    58,    27,   nil,    45,     0,     0,     0,   nil,   nil,     0,
+     0,    17,    17,    17,   nil,   nil,    17,    17,    20,    20,
+    20,    20,    49,    49,    49,    49,     9,     9,     9,     9,
+    29,    29,    29,    62,    62,    62,    10,    10,    10,    25,
+    25,    25,    24,    24,    24,    35,    35,    35,    21,    21,
+    21,    41,    41,    41,     5,     5,     5,    65,    65,    65 ]
 
 racc_action_pointer = [
-    13,     1,   nil,   nil,   nil,    68,   nil,   nil,   nil,    31,
-    53,    73,    13,   nil,     5,     3,    27,    20,   nil,   nil,
-    27,    38,     0,   nil,    44,    35,   nil,    24,     4,    56,
-   nil,   nil,    59,   nil,   nil,    62,   nil,   nil,    74,     2,
-    71,    12,    65,   nil,   nil,    17,   nil,    50,   nil,   nil,
-   nil,   nil,   nil,    47,   nil,    41,   nil,   nil,   nil ]
+    41,    25,   nil,   nil,   nil,    91,   nil,   nil,   nil,    63,
+    73,    29,    20,   nil,     2,     1,    28,    48,   nil,   nil,
+    55,    85,     0,    16,    79,    76,   nil,    39,    14,    67,
+   nil,   nil,    14,   nil,   nil,    82,   nil,   nil,     5,   nil,
+   nil,    88,    23,     1,     1,    33,   nil,   nil,   nil,    60,
+     3,   nil,   nil,   nil,   nil,   nil,   nil,   nil,    30,   nil,
+    19,   nil,    70,   nil,    29,    94 ]
 
 racc_action_default = [
-    -1,   -37,    -2,    -4,    -5,   -37,    -8,    -9,   -10,   -23,
-   -37,   -37,   -19,   -26,   -28,   -29,   -37,   -37,    -6,    -7,
-   -37,   -37,   -19,   -11,   -37,   -37,   -27,   -15,   -20,   -23,
-   -28,   -29,   -32,    59,    -3,   -37,   -15,   -12,   -37,   -19,
-   -23,   -14,   -32,   -21,   -16,   -24,   -30,   -33,   -34,   -35,
-   -36,   -14,   -13,   -32,   -17,   -32,   -31,   -18,   -25 ]
+    -1,   -43,    -2,    -4,    -5,   -43,    -8,    -9,   -10,   -23,
+   -43,   -43,   -19,   -28,   -30,   -31,   -43,   -43,    -6,    -7,
+   -43,   -43,   -19,   -39,   -43,   -43,   -29,   -15,   -20,   -23,
+   -30,   -31,   -34,    66,    -3,   -43,   -15,   -11,   -40,   -41,
+   -12,   -43,   -19,   -23,   -14,   -34,   -21,   -16,   -24,   -35,
+   -26,   -32,   -36,   -37,   -38,   -14,   -42,   -13,   -34,   -17,
+   -43,   -33,   -43,   -18,   -25,   -27 ]
 
 racc_goto_table = [
-     3,    26,    19,    44,    58,    18,     1,   nil,    27,    23,
-     9,     2,    26,    54,   nil,    20,   nil,     3,   nil,    36,
-    23,    26,    37,    41,    57,    21,   nil,     9,    34,    25,
-   nil,   nil,    26,    51,    40,   nil,    52,   nil,   nil,   nil,
-    35,   nil,   nil,   nil,    38,   nil,   nil,    56 ]
+     3,    38,    26,    65,    27,    18,     9,     2,    47,    23,
+    37,    20,    21,    26,    19,    36,    25,     3,    40,    44,
+    23,    59,    26,     9,    34,     1,   nil,    35,   nil,    55,
+    43,    41,   nil,   nil,    63,    57,    26,   nil,    64,   nil,
+   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,    61,
+   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,
+   nil,   nil,   nil,   nil,   nil,    61 ]
 
 racc_goto_check = [
-     3,    12,     4,    10,    11,     3,     1,   nil,     8,     3,
-     7,     2,    12,    10,   nil,     7,   nil,     3,   nil,     8,
-     3,    12,     8,     8,    10,     9,   nil,     7,     2,     9,
-   nil,   nil,    12,     8,     7,   nil,     8,   nil,   nil,   nil,
-     9,   nil,   nil,   nil,     9,   nil,   nil,     3 ]
+     3,    14,    15,    13,     9,     3,     7,     2,    11,     3,
+     8,     7,    10,    15,     4,     9,    10,     3,     9,     9,
+     3,    11,    15,     7,     2,     1,   nil,    10,   nil,     9,
+     7,    10,   nil,   nil,    11,     9,    15,   nil,    14,   nil,
+   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,     3,
+   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,   nil,
+   nil,   nil,   nil,   nil,   nil,     3 ]
 
 racc_goto_pointer = [
-   nil,     6,    11,     0,    -3,   nil,   nil,    10,    -2,    20,
-   -29,   -51,    -8,   nil ]
+   nil,    25,     7,     0,     9,   nil,   nil,     6,   -13,    -6,
+     7,   -24,   nil,   -59,   -22,    -7 ]
 
 racc_goto_default = [
-   nil,   nil,   nil,    46,     4,     5,     6,    29,    11,    10,
-   nil,    45,    13,    47 ]
+   nil,   nil,   nil,    51,     4,     5,     6,    29,   nil,    11,
+    10,   nil,    48,    49,    50,    13 ]
 
 racc_reduce_table = [
   0, 0, :racc_error,
-  0, 11, :_reduce_1,
-  1, 11, :_reduce_2,
-  3, 11, :_reduce_3,
-  1, 12, :_reduce_4,
-  1, 12, :_reduce_none,
-  2, 12, :_reduce_6,
-  2, 12, :_reduce_7,
-  1, 12, :_reduce_none,
-  1, 15, :_reduce_9,
-  1, 15, :_reduce_10,
-  2, 14, :_reduce_11,
-  3, 14, :_reduce_12,
-  4, 14, :_reduce_13,
-  3, 14, :_reduce_14,
-  2, 14, :_reduce_15,
-  3, 16, :_reduce_16,
-  4, 16, :_reduce_17,
-  5, 16, :_reduce_18,
-  1, 19, :_reduce_none,
-  2, 19, :_reduce_20,
-  3, 19, :_reduce_21,
-  1, 18, :_reduce_none,
-  1, 18, :_reduce_none,
-  1, 20, :_reduce_24,
-  3, 20, :_reduce_25,
-  1, 17, :_reduce_none,
-  2, 17, :_reduce_27,
-  1, 22, :_reduce_none,
-  1, 22, :_reduce_none,
-  1, 23, :_reduce_none,
-  2, 23, :_reduce_31,
-  0, 21, :_reduce_none,
-  1, 21, :_reduce_none,
+  0, 12, :_reduce_1,
+  1, 12, :_reduce_2,
+  3, 12, :_reduce_3,
+  1, 13, :_reduce_4,
   1, 13, :_reduce_none,
+  2, 13, :_reduce_6,
+  2, 13, :_reduce_7,
   1, 13, :_reduce_none,
-  1, 13, :_reduce_none ]
+  1, 16, :_reduce_9,
+  1, 16, :_reduce_10,
+  3, 15, :_reduce_11,
+  3, 15, :_reduce_12,
+  4, 15, :_reduce_13,
+  3, 15, :_reduce_14,
+  2, 15, :_reduce_15,
+  3, 17, :_reduce_16,
+  4, 17, :_reduce_17,
+  5, 17, :_reduce_18,
+  1, 21, :_reduce_none,
+  2, 21, :_reduce_20,
+  3, 21, :_reduce_21,
+  1, 20, :_reduce_none,
+  1, 20, :_reduce_none,
+  1, 22, :_reduce_24,
+  3, 22, :_reduce_25,
+  1, 22, :_reduce_26,
+  3, 22, :_reduce_27,
+  1, 18, :_reduce_none,
+  2, 18, :_reduce_29,
+  1, 26, :_reduce_none,
+  1, 26, :_reduce_none,
+  1, 24, :_reduce_none,
+  2, 24, :_reduce_33,
+  0, 23, :_reduce_none,
+  1, 23, :_reduce_none,
+  1, 14, :_reduce_none,
+  1, 14, :_reduce_none,
+  1, 14, :_reduce_none,
+  0, 19, :_reduce_none,
+  1, 19, :_reduce_none,
+  1, 25, :_reduce_none,
+  2, 25, :_reduce_42 ]
 
-racc_reduce_n = 37
+racc_reduce_n = 43
 
-racc_shift_n = 59
+racc_shift_n = 66
 
 racc_token_table = {
   false => 0,
@@ -287,9 +308,10 @@ racc_token_table = {
   :NICK => 6,
   :AND => 7,
   :APPELLATION => 8,
-  :TITLE => 9 }
+  :TITLE => 9,
+  :SUFFIX => 10 }
 
-racc_nt_base = 10
+racc_nt_base = 11
 
 racc_use_result_var = true
 
@@ -320,6 +342,7 @@ Racc_token_to_s_table = [
   "AND",
   "APPELLATION",
   "TITLE",
+  "SUFFIX",
   "$start",
   "names",
   "name",
@@ -328,12 +351,14 @@ Racc_token_to_s_table = [
   "honorific",
   "sort_order",
   "u_words",
+  "opt_suffices",
   "last",
   "von",
   "first",
   "opt_words",
-  "u_word",
-  "words" ]
+  "words",
+  "suffices",
+  "u_word" ]
 
 Racc_debug_parser = false
 
@@ -403,7 +428,7 @@ module_eval(<<'.,.,', 'parser.y', 21)
 
 module_eval(<<'.,.,', 'parser.y', 25)
   def _reduce_11(val, _values, result)
-             result = Name.new(:given => val[0], :family => val[1])
+             result = Name.new(:given => val[0], :family => val[1], :suffix => val[2])
        
     result
   end
@@ -445,8 +470,8 @@ module_eval(<<'.,.,', 'parser.y', 43)
 
 module_eval(<<'.,.,', 'parser.y', 48)
   def _reduce_16(val, _values, result)
-             result = Name.new(:family => val[0], :suffix => val[2][0],
-           :given => val[2][1])
+             result = Name.new({ :family => val[0], :suffix => val[2][0],
+           :given => val[2][1] }, !!val[2][0])
        
     result
   end
@@ -454,8 +479,8 @@ module_eval(<<'.,.,', 'parser.y', 48)
 
 module_eval(<<'.,.,', 'parser.y', 53)
   def _reduce_17(val, _values, result)
-             result = Name.new(:particle => val[0], :family => val[1],
-           :suffix => val[3][0], :given => val[3][1])
+             result = Name.new({ :particle => val[0], :family => val[1],
+           :suffix => val[3][0], :given => val[3][1] }, !!val[3][0])
        
     result
   end
@@ -463,8 +488,8 @@ module_eval(<<'.,.,', 'parser.y', 53)
 
 module_eval(<<'.,.,', 'parser.y', 58)
   def _reduce_18(val, _values, result)
-             result = Name.new(:particle => val[0,2].join(' '), :family => val[2],
-           :suffix => val[4][0], :given => val[4][1])
+             result = Name.new({ :particle => val[0,2].join(' '), :family => val[2],
+           :suffix => val[4][0], :given => val[4][1] }, !!val[4][0])
        
     result
   end
@@ -499,36 +524,46 @@ module_eval(<<'.,.,', 'parser.y', 69)
 
 module_eval(<<'.,.,', 'parser.y', 70)
   def _reduce_25(val, _values, result)
-     result = [val[0],val[2]] 
+     result = [val[2],val[0]] 
     result
   end
 .,.,
 
-# reduce 26 omitted
+module_eval(<<'.,.,', 'parser.y', 71)
+  def _reduce_26(val, _values, result)
+     result = [val[0],nil] 
+    result
+  end
+.,.,
 
-module_eval(<<'.,.,', 'parser.y', 73)
+module_eval(<<'.,.,', 'parser.y', 72)
   def _reduce_27(val, _values, result)
-     result = val.join(' ') 
+     result = [val[0],val[2]] 
     result
   end
 .,.,
 
 # reduce 28 omitted
 
-# reduce 29 omitted
-
-# reduce 30 omitted
-
-module_eval(<<'.,.,', 'parser.y', 78)
-  def _reduce_31(val, _values, result)
+module_eval(<<'.,.,', 'parser.y', 75)
+  def _reduce_29(val, _values, result)
      result = val.join(' ') 
     result
   end
 .,.,
 
+# reduce 30 omitted
+
+# reduce 31 omitted
+
 # reduce 32 omitted
 
-# reduce 33 omitted
+module_eval(<<'.,.,', 'parser.y', 80)
+  def _reduce_33(val, _values, result)
+     result = val.join(' ') 
+    result
+  end
+.,.,
 
 # reduce 34 omitted
 
@@ -536,6 +571,23 @@ module_eval(<<'.,.,', 'parser.y', 78)
 
 # reduce 36 omitted
 
+# reduce 37 omitted
+
+# reduce 38 omitted
+
+# reduce 39 omitted
+
+# reduce 40 omitted
+
+# reduce 41 omitted
+
+module_eval(<<'.,.,', 'parser.y', 89)
+  def _reduce_42(val, _values, result)
+     result = val.join(' ') 
+    result
+  end
+.,.,
+
 def _reduce_none(val, _values, result)
   val[0]
 end

data/lib/namae/parser.y

@@ -1,8 +1,8 @@
-# -*- racc -*-
+# -*- ruby -*-
 
 class Namae::Parser
 
-token COMMA UWORD LWORD PWORD NICK AND APPELLATION TITLE
+token COMMA UWORD LWORD PWORD NICK AND APPELLATION TITLE SUFFIX
 
 expect 0
 
@@ -21,9 +21,9 @@ rule
   honorific : APPELLATION { result = Name.new(:appellation => val[0]) }
             | TITLE       { result = Name.new(:title => val[0]) }
             
-  display_order : u_words word
+  display_order : u_words word opt_suffices
        {
-         result = Name.new(:given => val[0], :family => val[1])
+         result = Name.new(:given => val[0], :family => val[1], :suffix => val[2])
        }
        | u_words NICK last
        {
@@ -46,18 +46,18 @@ rule
        
   sort_order : last COMMA first
        {
-         result = Name.new(:family => val[0], :suffix => val[2][0],
-           :given => val[2][1])
+         result = Name.new({ :family => val[0], :suffix => val[2][0],
+           :given => val[2][1] }, !!val[2][0])
        }
        | von last COMMA first
        {
-         result = Name.new(:particle => val[0], :family => val[1],
-           :suffix => val[3][0], :given => val[3][1])
+         result = Name.new({ :particle => val[0], :family => val[1],
+           :suffix => val[3][0], :given => val[3][1] }, !!val[3][0])
        }
        | u_words von last COMMA first
        {
-         result = Name.new(:particle => val[0,2].join(' '), :family => val[2],
-           :suffix => val[4][0], :given => val[4][1])
+         result = Name.new({ :particle => val[0,2].join(' '), :family => val[2],
+           :suffix => val[4][0], :given => val[4][1] }, !!val[4][0])
        }
        ;
 
@@ -67,8 +67,10 @@ rule
 
   last : LWORD | u_words
 
-  first : opt_words                 { result = [nil,val[0]] }
-        | opt_words COMMA opt_words { result = [val[0],val[2]] }
+  first : opt_words             { result = [nil,val[0]] }
+        | words COMMA suffices  { result = [val[2],val[0]] }
+        | suffices              { result = [val[0],nil] }
+        | suffices COMMA words  { result = [val[0],val[2]] }
 
   u_words : u_word
           | u_words u_word { result = val.join(' ') }
@@ -82,6 +84,11 @@ rule
 
   word : LWORD | UWORD | PWORD
 
+  opt_suffices : /* empty */ | suffices
+
+  suffices : SUFFIX
+           | suffices SUFFIX { result = val.join(' ') }
+
 ---- header
 require 'singleton'
 require 'strscan'
@@ -98,8 +105,8 @@ require 'strscan'
       :prefer_comma_as_separator => false,
       :comma => ',',
       :separator => /\s*(\band\b|\&)\s*/i,
-      :title => /\s*\b(sir|lord|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
-      :suffix => /\s*\b(jr|sr|[ivx]{2,})\.?\s*/i,
+      :title => /\s*\b(sir|lord|count(ess)?|(prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
+      :suffix => /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/,
       :appellation => /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
     }
   end
@@ -151,7 +158,7 @@ require 'strscan'
   end
   
   def reset
-    @commas, @words, @initials, @yydebug = 0, 0, 0, debug?   
+    @commas, @words, @initials, @suffices, @yydebug = 0, 0, 0, 0, debug?   
     self
   end
 
@@ -167,7 +174,7 @@ require 'strscan'
   
   def consume_separator
     return next_token if seen_separator?
-    @commas, @words, @initials = 0, 0, 0
+    @commas, @words, @initials, @suffices = 0, 0, 0, 0
     [:AND, :AND]
   end
   
@@ -178,7 +185,14 @@ require 'strscan'
 
   def consume_word(type, word)
     @words += 1
-    @initials += 1 if type == :UWORD && word =~ /^\s*[[:alpha:]]\.\s*$/
+
+    case type
+    when :UWORD
+      @initials += 1 if word =~ /^\s*[[:alpha:]]\.\s*$/
+    when :SUFFIX
+      @suffices += 1
+    end
+
     [type, word]
   end
 
@@ -187,12 +201,7 @@ require 'strscan'
   end
 
   def suffix?
-    seen_suffix? || will_see_suffix?
-  end
-  
-  def seen_suffix?
-    return false unless stack.length > 1
-    last_token == :COMMA || last_token =~ suffix
+    !@suffices.zero? || will_see_suffix?
   end
   
   def will_see_suffix?
@@ -204,7 +213,8 @@ require 'strscan'
   end
 
   def seen_full_name?
-    prefer_comma_as_separator? && @words > 1 && (@initials > 0 || !will_see_initial?)
+    prefer_comma_as_separator? && @words > 1 &&
+      (@initials > 0 || !will_see_initial?) && !will_see_suffix?
   end
 
   def next_token
@@ -223,6 +233,8 @@ require 'strscan'
       next_token
     when input.scan(title)
       consume_word(:TITLE, input.matched.strip)
+    when input.scan(suffix)
+      consume_word(:SUFFIX, input.matched.strip)
     when input.scan(appellation)
       [:APPELLATION, input.matched.strip]
     when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{comma}]*/)
@@ -246,4 +258,4 @@ require 'strscan'
     
   attr_reader :input
 
-# -*- racc -*-
+# -*- racc -*-

data/lib/namae/version.rb

@@ -1,10 +1,10 @@
 module Namae
   module Version
     MAJOR = 0
-    MINOR = 7
-    PATCH = 1
+    MINOR = 8
+    PATCH = 0
     BUILD = nil
 
     STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze
   end
-end
+end

data/namae.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "namae"
-  s.version = "0.7.1"
+  s.version = "0.8.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Sylvester Keil", "Dan Collis-Puro"]
-  s.date = "2012-11-08"
+  s.date = "2013-08-23"
   s.description = " Namae (\u{540d}\u{524d}) is a parser for human names. It recognizes personal names of various cultural backgrounds and tries to split them into their component parts (e.g., given and family names, honorifics etc.). "
   s.email = ["sylvester@keil.or.at", "dan@collispuro.com"]
   s.extra_rdoc_files = [
@@ -49,31 +49,31 @@ Gem::Specification.new do |s|
   s.homepage = "https://github.com/berkmancenter/namae"
   s.licenses = ["AGPL"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "1.8.24"
+  s.rubygems_version = "2.0.3"
   s.summary = "Namae (\u{540d}\u{524d}) parses personal names and splits them into their component parts."
 
   if s.respond_to? :specification_version then
-    s.specification_version = 3
+    s.specification_version = 4
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_development_dependency(%q<racc>, ["~> 1.4.8"])
-      s.add_development_dependency(%q<bundler>, ["~> 1.1"])
       s.add_development_dependency(%q<simplecov>, [">= 0"])
-      s.add_development_dependency(%q<ZenTest>, ["~> 4.8.0"])
+      s.add_development_dependency(%q<ZenTest>, [">= 0"])
       s.add_development_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_development_dependency(%q<yard>, [">= 0"])
     else
       s.add_dependency(%q<racc>, ["~> 1.4.8"])
-      s.add_dependency(%q<bundler>, ["~> 1.1"])
       s.add_dependency(%q<simplecov>, [">= 0"])
-      s.add_dependency(%q<ZenTest>, ["~> 4.8.0"])
+      s.add_dependency(%q<ZenTest>, [">= 0"])
       s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+      s.add_dependency(%q<yard>, [">= 0"])
     end
   else
     s.add_dependency(%q<racc>, ["~> 1.4.8"])
-    s.add_dependency(%q<bundler>, ["~> 1.1"])
     s.add_dependency(%q<simplecov>, [">= 0"])
-    s.add_dependency(%q<ZenTest>, ["~> 4.8.0"])
+    s.add_dependency(%q<ZenTest>, [">= 0"])
     s.add_dependency(%q<jeweler>, ["~> 1.8.3"])
+    s.add_dependency(%q<yard>, [">= 0"])
   end
 end
 

data/spec/namae/parser_spec.rb

@@ -60,6 +60,19 @@ module Namae
           end
         end
 
+        %w{Jr. Jr Sr. Sr II II. VII IX}.each do |suffix|
+          describe "the next token is #{suffix.inspect}" do
+            before { parser.send(:input).string = suffix }
+            it 'returns an SUFFIX token' do
+              parser.send(:next_token).should == [:SUFFIX, suffix]
+            end
+
+            it 'the input matches the suffix pattern' do
+              parser.suffix.should match(suffix)
+            end
+          end
+        end
+
       end
 
       describe '#parse!' do
@@ -103,9 +116,18 @@ module Namae
             end
           end
 
+          it 'parses common Jr. as a suffix in sort order' do
+            parser.parse!('Griffey, Jr., Ken')[0].values_at(:given, :family, :suffix).should == ['Ken', 'Griffey', 'Jr.']
+            parser.parse!('Griffey, Ken, Jr.')[0].values_at(:given, :family, :suffix).should == ['Ken', 'Griffey', 'Jr.']
+          end
+
+          it 'parses common Jr. as a suffix in display order' do
+            parser.parse!('Ken Griffey Jr.')[0].values_at(:given, :family, :suffix).should == ['Ken', 'Griffey', 'Jr.']
+          end
+
         end
       end
 
     end
   end
-end
+end

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: namae
 version: !ruby/object:Gem::Version
-  version: 0.7.1
-  prerelease: 
+  version: 0.8.0
 platform: ruby
 authors:
 - Sylvester Keil
@@ -10,12 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-08 00:00:00.000000000 Z
+date: 2013-08-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: racc
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -23,76 +21,67 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
         version: 1.4.8
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: simplecov
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - '>='
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - '>='
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '0'
 - !ruby/object:Gem::Dependency
-  name: simplecov
+  name: ZenTest
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: ZenTest
+  name: jeweler
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 4.8.0
+        version: 1.8.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 4.8.0
+        version: 1.8.3
 - !ruby/object:Gem::Dependency
-  name: jeweler
+  name: yard
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - '>='
       - !ruby/object:Gem::Version
-        version: 1.8.3
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ~>
+    - - '>='
       - !ruby/object:Gem::Version
-        version: 1.8.3
-description: ! ' Namae (名前) is a parser for human names. It recognizes personal names
+        version: '0'
+description: ' Namae (名前) is a parser for human names. It recognizes personal names
   of various cultural backgrounds and tries to split them into their component parts
   (e.g., given and family names, honorifics etc.). '
 email:
@@ -135,29 +124,25 @@ files:
 homepage: https://github.com/berkmancenter/namae
 licenses:
 - AGPL
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -3595872270413772674
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Namae (名前) parses personal names and splits them into their component parts.
 test_files: []