namae 0.9.3 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9c35acb2595cb60e9256141f209a97ebe717c5fd
-  data.tar.gz: ce3c39facdf1b12051b56edb8330376f777eb2d8
+  metadata.gz: 7e3498b418afe338293a9fe9c7b4c8747ee014b2
+  data.tar.gz: cac2386cd67b385330b50a8d722429100020b2e6
 SHA512:
-  metadata.gz: e3e158d44f41686c75eadb19b9a4ef984db05b57d7e2be63aa4db7b8c62bb119216ddbd6a7a1c2bc28d6068f6a7df7a7cbb2cb8f176903b43e54e2af07df21f5
-  data.tar.gz: e440237a7f090dc85cbb1e68f1388831147823794b305fcc0e6ae131fe4cb26692d841ca0f9a2facf3bcf65f5ab6ac79fe0ec492a2adeb9e8cb6eac427435eb8
+  metadata.gz: a2001bf45ca48aa8d9d1a8f31143a3687f5013ffa4e8be7837c7efa08a5acb9257cd8e7685a0ee19f89a49d8e4bf841a596cc99e734087d6bb32828c025b0e34
+  data.tar.gz: e7b62fc3a1278938f42e5fcee152cf47ba06e5378f3bedef6bc238d3983a11d2ffc25bc7ec6c8dd90655dc6ca29f976d62e2c3dd710d6cd0700056481244f1d3

data/.travis.yml

@@ -1,7 +1,12 @@
 language: ruby
 bundler_args: --without debug osx optional
 script: bundle exec rake test_with_coveralls
+
+sudo: false
+cache: bundler
+
 rvm:
+  - 2.2.0
   - 2.1.0
   - 2.0.0
   - 1.9.3

data/Gemfile

@@ -21,8 +21,8 @@ group :optional do
 end
 
 group :debug do
-  gem 'debugger', '~>1.6', :platform => [:mri_20, :mri_19]
-  gem 'byebug', '~>3.5', :platform => [:mri_21, :mri_22]
+  gem 'debugger', '~>1.6', :platform => [:mri_19]
+  gem 'byebug', '~>3.5', :platform => :mri if RUBY_VERSION > '2.0'
   gem 'rubinius-compiler', '~>2.0', :platform => :rbx
   gem 'rubinius-debugger', '~>2.0', :platform => :rbx
 end

data/features/lists.feature

@@ -30,6 +30,22 @@ Feature: Parse a list of names
       | Dennis | Ritchie   |
       | Donald | Knuth     |
 
+  @list
+  Scenario: A list of names separated by semicolons
+    When I parse the names "John D. Smith; Jack R. Johnson; Emily Tanner"
+    Then there should be 3 names
+    And the names should be:
+      | given   | family  |
+      | John D. | Smith   |
+      | Jack R. | Johnson |
+      | Emily   | Tanner  |
+    When I parse the names "Smith, John D.; Johnson, Jack R.; Tanner, Emily"
+    Then there should be 3 names
+    And the names should be:
+      | given   | family  |
+      | John D. | Smith   |
+      | Jack R. | Johnson |
+      | Emily   | Tanner  |
 
   @list
   Scenario: A list of sort-order names with initials separated by commas
@@ -51,6 +67,24 @@ Feature: Parse a list of names
       | Dennis | Ritchie   |
       | Donald | Knuth     |
 
+  @list
+  Scenario: A list of mixed names separated by semicolons, commas and 'and'
+    Given a parser that prefers commas as separators
+    When I parse the names "John D. Smith, Jack R. Johnson & Emily Tanner"
+    Then there should be 3 names
+    And the names should be:
+      | given   | family  |
+      | John D. | Smith   |
+      | Jack R. | Johnson |
+      | Emily   | Tanner  |
+    When I parse the names "C. Foster; C. Hamel, C. Desroches"
+    Then there should be 3 names
+    And the names should be:
+      | given | family    |
+      | C.    | Foster    |
+      | C.    | Hamel     |
+      | C.    | Desroches |
+
   @list
   Scenario: A list of display-order names separated by commas and 'and'
     Given a parser that prefers commas as separators
@@ -64,7 +98,7 @@ Feature: Parse a list of names
 
   @list @wip
   Scenario: A list of names separated by commas
-  	Given a parser that prefers commas as separators
+    Given a parser that prefers commas as separators
     When I parse the names "G. Proctor, M. Cooper, P. Sanders & B. Malcom"
     Then the names should be:
       | given | family  |
@@ -81,7 +115,7 @@ Feature: Parse a list of names
       | B     | Malcom  |
 
   Scenario: A list of names with particles separated by commas
-  	Given a parser that prefers commas as separators
+    Given a parser that prefers commas as separators
     When I parse the names "Di Proctor, M., von Cooper, P."
     Then the names should be:
       | given | family     |

data/lib/namae/parser.rb

@@ -23,7 +23,8 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
       :debug => false,
       :prefer_comma_as_separator => false,
       :comma => ',',
-      :separator => /\s*(\band\b|\&)\s*/i,
+      :stops => ',;',
+      :separator => /\s*(\band\b|\&|;)\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
@@ -42,6 +43,10 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
     options[:comma]
   end
 
+  def stops
+    options[:stops]
+  end
+
   def title
     options[:title]
   end
@@ -142,7 +147,7 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
       nil
     when input.scan(separator)
       consume_separator
-    when input.scan(/\s*,\s*/)
+    when input.scan(/\s*#{comma}\s*/)
       if @commas.zero? && !seen_full_name? || @commas == 1 && suffix?
         consume_comma
       else
@@ -156,11 +161,11 @@ module_eval(<<'...end parser.y/module_eval...', 'parser.y', 107)
       consume_word(:SUFFIX, input.matched.strip)
     when input.scan(appellation)
       [:APPELLATION, input.matched.strip]
-    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{comma}]*/)
+    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{stops}]*/)
       consume_word(:UWORD, input.matched)
-    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{comma}]*/)
+    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{stops}]*/)
       consume_word(:LWORD, input.matched)
-    when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{comma}]*/)
+    when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{stops}]*/)
       consume_word(:PWORD, input.matched)
     when input.scan(/('[^'\n]+')|("[^"\n]+")/)
       consume_word(:NICK, input.matched[1...-1])

data/lib/namae/parser.y

@@ -114,7 +114,8 @@ require 'strscan'
       :debug => false,
       :prefer_comma_as_separator => false,
       :comma => ',',
-      :separator => /\s*(\band\b|\&)\s*/i,
+      :stops => ',;',
+      :separator => /\s*(\band\b|\&|;)\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
@@ -133,6 +134,10 @@ require 'strscan'
     options[:comma]
   end
 
+  def stops
+    options[:stops]
+  end
+
   def title
     options[:title]
   end
@@ -233,7 +238,7 @@ require 'strscan'
       nil
     when input.scan(separator)
       consume_separator
-    when input.scan(/\s*,\s*/)
+    when input.scan(/\s*#{comma}\s*/)
       if @commas.zero? && !seen_full_name? || @commas == 1 && suffix?
         consume_comma
       else
@@ -247,11 +252,11 @@ require 'strscan'
       consume_word(:SUFFIX, input.matched.strip)
     when input.scan(appellation)
       [:APPELLATION, input.matched.strip]
-    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{comma}]*/)
+    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{stops}]*/)
       consume_word(:UWORD, input.matched)
-    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{comma}]*/)
+    when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{stops}]*/)
       consume_word(:LWORD, input.matched)
-    when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{comma}]*/)
+    when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{stops}]*/)
       consume_word(:PWORD, input.matched)
     when input.scan(/('[^'\n]+')|("[^"\n]+")/)
       consume_word(:NICK, input.matched[1...-1])

data/lib/namae/version.rb

@@ -1,8 +1,8 @@
 module Namae
   module Version
     MAJOR = 0
-    MINOR = 9
-    PATCH = 3
+    MINOR = 10
+    PATCH = 0
     BUILD = nil
 
     STRING = [MAJOR, MINOR, PATCH, BUILD].compact.join('.').freeze

data/namae.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: namae 0.9.3 ruby lib
+# stub: namae 0.10.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "namae"
-  s.version = "0.9.3"
+  s.version = "0.10.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Sylvester Keil", "Dan Collis-Puro"]
-  s.date = "2015-01-19"
+  s.date = "2015-04-26"
   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 = [

data/spec/namae/parser_spec.rb

@@ -44,6 +44,27 @@ module Namae
           end
         end
 
+        describe 'when the next input is ", "' do
+          before { parser.send(:input).string = ', ' }
+          it 'returns a COMMA token' do
+            expect(parser.send(:next_token)).to eq([:COMMA, :COMMA])
+          end
+        end
+
+        describe 'when the next input is "; "' do
+          before { parser.send(:input).string = '; ' }
+          it 'returns an AND token' do
+            expect(parser.send(:next_token)).to eq([:AND, :AND])
+          end
+        end
+
+        describe 'when the next input is "foo;"' do
+          before { parser.send(:input).string = 'foo;' }
+          it 'returns an LWORD token "foo"' do
+            expect(parser.send(:next_token)).to eq([:LWORD, 'foo'])
+          end
+        end
+
         describe 'when the next input is " \'foo bar\' "' do
           before { parser.send(:input).string = " 'foo bar' " }
           it 'returns a NICK token' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: namae
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 0.10.0
 platform: ruby
 authors:
 - Sylvester Keil
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-01-19 00:00:00.000000000 Z
+date: 2015-04-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: simplecov
@@ -134,3 +134,4 @@ signing_key:
 specification_version: 4
 summary: Namae (名前) parses personal names and splits them into their component parts.
 test_files: []
+has_rdoc: