namae 1.1.0 → 1.2.0

data/lib/namae/parser.y

@@ -24,32 +24,24 @@ rule
 
   display_order : u_words word opt_suffices opt_titles
        {
-         result = Name.new(:given => val[0], :family => val[1],
-           :suffix => val[2], :title => val[3])
+         result = Name.new(
+           :given => val[0], :family => val[1], :suffix => val[2], :title => val[3]
+         )
        }
        | u_words NICK last opt_suffices opt_titles
        {
-         result = Name.new(:given => val[0], :nick => val[1],
-           :family => val[2], :suffix => val[3], :title => val[4])
+         result = Name.new(
+           :given => val[0], :nick => val[1], :family => val[2], :suffix => val[3], :title => val[4]
+         )
        }
        | u_words NICK von last opt_suffices opt_titles
        {
-         result = Name.new(:given => val[0], :nick => val[1],
-           :particle => val[2], :family => val[3],
-           :suffix => val[4], :title => val[5])
+         result = Name.new(
+           :given => val[0], :nick => val[1], :particle => val[2], :family => val[3], :suffix => val[4], :title => val[5])
        }
        | u_words von last
        {
-         result = Name.new(:given => val[0], :particle => val[1],
-          :family => val[2])
-       }
-       | u_words UPARTICLE last
-       {
-          result = if include_particle_in_family?
-                    Name.new(:given => val[0], :family => val[1,2].join(' '))
-                   else
-                     Name.new(:given => val[0], :particle => val[1], :family => val[2])
-                   end
+         result = Name.new(:given => val[0], :particle => val[1], :family => val[2])
        }
        | von last
        {
@@ -58,32 +50,29 @@ rule
 
   sort_order : last COMMA first
        {
-         result = Name.new({ :family => val[0], :suffix => val[2][0],
-           :given => val[2][1] }, !!val[2][0])
-       }
-       | UPARTICLE last COMMA first
-       {
-         result = if include_particle_in_family?
-                    Name.new({ :family => val[0,2].join(' '), :suffix => val[3][0], :given => val[3][1] }, !!val[3][0])
-                  else
-                    Name.new({ :particle => val[0], :family => val[1], :suffix => val[3][0], :given => val[3][1] }, !!val[3][0])
-                  end
+         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] }, !!val[3][0])
+         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] }, !!val[4][0])
+         result = Name.new({
+           :particle => val[0,2].join(' '), :family => val[2], :suffix => val[4][0], :given => val[4][1]
+         }, !!val[4][0])
        }
        ;
 
-  von : LWORD
-      | von LWORD         { result = val.join(' ') }
-      | von u_words LWORD { result = val.join(' ') }
+  von : particle
+      | von particle         { result = val.join(' ') }
+      | von u_words particle { result = val.join(' ') }
+
+  particle : LWORD | UPARTICLE
 
   last : LWORD | u_words
 
@@ -103,7 +92,7 @@ rule
   opt_comma : /* empty */ | COMMA
   opt_words : /* empty */ | words
 
-  word : LWORD | UWORD | PWORD
+  word : LWORD | UWORD | PWORD | UPARTICLE
 
   opt_suffices : /* empty */ | suffices
 
@@ -130,7 +119,7 @@ require 'strscan'
     :title => /\s*\b(sir|lord|count(ess)?|(gen|adm|col|maj|capt|cmdr|lt|sgt|cpl|pvt|pastor|pr|reverend|rev|elder|deacon|deaconess|father|fr|rabbi|cantor|vicar|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,
-    :uppercase_particle => /\s*\b((Da|De|Di|De\sLa|Du|Der|Des|Da|St|Saint|Les|Van)\.?)(\s+|$)/
+    :uppercase_particle => /\s*\b(D[aiu]|De[rs]?|St\.?|Saint|La|Les|V[ao]n)(\s+|$)/
   }
 
   class << self
@@ -197,7 +186,9 @@ require 'strscan'
   def parse!(string)
     @input = StringScanner.new(normalize(string))
     reset
-    do_parse
+    names = do_parse
+    names.map(&:merge_particles!) if include_particle_in_family?
+    names
   end
 
   def normalize(string)

data/lib/namae/version.rb

@@ -1,7 +1,7 @@
 module Namae
   module Version
     MAJOR = 1
-    MINOR = 1
+    MINOR = 2
     PATCH = 0
     BUILD = nil
 

data/lib/namae.rb

@@ -2,4 +2,4 @@ require 'namae/version'
 
 require 'namae/name'
 require 'namae/parser'
-require 'namae/utility'
+require 'namae/utility'

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: namae
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.2.0
 platform: ruby
 authors:
 - Sylvester Keil
-- Dan Collis-Puro
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-03-12 00:00:00.000000000 Z
+date: 2024-01-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: racc
@@ -17,64 +16,49 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.4'
-  type: :development
+        version: '1.7'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.4'
+        version: '1.7'
 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:
 - sylvester@keil.or.at
-- dan@collispuro.com
 executables: []
 extensions: []
 extra_rdoc_files:
 - README.md
+- AGPL
 files:
-- ".codeclimate.yml"
-- ".coveralls.yml"
-- ".document"
-- ".rspec"
-- ".rubocop.yml"
-- ".simplecov"
-- ".travis.yml"
-- ".yardopts"
 - AGPL
 - BSDL
-- Gemfile
 - README.md
-- Rakefile
-- cucumber.yml
-- features/bibtex.feature
-- features/examples.feature
-- features/lists.feature
-- features/step_definitions/namae_steps.rb
-- features/suffix.feature
-- features/support/env.rb
-- features/title.feature
 - lib/namae.rb
 - lib/namae/name.rb
 - lib/namae/parser.rb
 - lib/namae/parser.y
 - lib/namae/utility.rb
 - lib/namae/version.rb
-- namae.gemspec
-- spec/namae/name_spec.rb
-- spec/namae/parser_spec.rb
-- spec/namae/utility_spec.rb
-- spec/spec_helper.rb
-- spec/thread_safety_spec.rb
 homepage: https://github.com/berkmancenter/namae
 licenses:
 - AGPL-3.0
+- BSD-2-Clause
 metadata: {}
 post_install_message:
-rdoc_options: []
+rdoc_options:
+- "--line-numbers"
+- "--inline-source"
+- "--title"
+- "'Namae'"
+- "--main"
+- README.md
+- "--exclude"
+- lib/namae/parser.rb
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
@@ -88,7 +72,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
+rubygems_version: 3.5.3
 signing_key:
 specification_version: 4
 summary: Namae (名前) parses personal names and splits them into their component parts.

data/.codeclimate.yml

@@ -1,16 +0,0 @@
----
-endinges:
-  duplication:
-    enabled: true
-    config:
-      languages:
-        - ruby
-  fixme:
-    enabled: true
-  rubocop:
-    enabled: true
-ratings:
-  paths:
-    - '**.rb'
-exclude_paths:
-  - lib/namae/parser.rb

data/.coveralls.yml

@@ -1 +0,0 @@
-service_name: travis-ci

data/.document

@@ -1,7 +0,0 @@
-lib/**/*.rb
-bin/*
-- 
-features/**/*.feature
-AGPL
-BSDL
-README.md

data/.rspec

@@ -1,2 +0,0 @@
---require ./spec/spec_helper.rb
---color