iso-639 0.1.0 → 0.2.0

data/Gemfile

@@ -6,8 +6,8 @@ source "http://rubygems.org"
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 group :development, :test do
-  gem "jeweler", "~> 1.8.4"
   gem "mocha", ">= 0"
   gem "rdoc", "~> 3.12"
   gem "shoulda", ">= 0"
-end
+  gem "rake"
+end

data/Gemfile.lock

@@ -4,13 +4,7 @@ GEM
     activesupport (3.2.8)
       i18n (~> 0.6)
       multi_json (~> 1.0)
-    git (1.2.5)
     i18n (0.6.1)
-    jeweler (1.8.4)
-      bundler (~> 1.0)
-      git (>= 1.2.5)
-      rake
-      rdoc
     json (1.7.5)
     metaclass (0.0.1)
     mocha (0.12.7)
@@ -30,7 +24,7 @@ PLATFORMS
   ruby
 
 DEPENDENCIES
-  jeweler (~> 1.8.4)
   mocha
+  rake
   rdoc (~> 3.12)
   shoulda

data/README.markdown

@@ -10,8 +10,6 @@ The [ISO 639-1](http://en.wikipedia.org/wiki/ISO_639-1) specification uses a two
 
 The [ISO 639-2](http://www.loc.gov/standards/iso639-2/) ([Wikipedia](http://en.wikipedia.org/wiki/ISO_639-2)) specification uses a three-letter code, is used primarily in bibliography and terminology and covers many more languages than the ISO 639-1 specification.
 
-The other ISO 639 standards are considered beyond the scope of this library.
-
 ## Usage
 
     require 'iso-639'
@@ -27,6 +25,13 @@ To find a language entry:
     # by French name
     ISO_639.find_by_french_name("français")
 
+The `ISO_639.search` class method searches across all fields and will
+match names in cases where a record has multiple names. This method
+always returns an array of 0 or more results. For example:
+
+    ISO_639.search("spanish")
+    # => [["spa", "", "es", "Spanish; Castilian", "espagnol; castillan"]]
+
 Entries are arrays with convenience methods for accessing fields:
     
     @entry = ISO_639.find("slo")

data/Rakefile

@@ -11,20 +11,6 @@ rescue Bundler::BundlerError => e
 end
 require 'rake'
 
-require 'jeweler'
-Jeweler::Tasks.new do |gem|
-  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
-  gem.name = "iso-639"
-  gem.homepage = "http://github.com/alphabetum/pandoc-ruby"
-  gem.license = "MIT"
-  gem.summary = %Q{ISO 639-1 and ISO 639-2 language code entries and convenience methods}
-  gem.description = %Q{ISO 639-1 and ISO 639-2 language code entries and convenience methods}
-  gem.email = "hi@williammelody.com"
-  gem.authors = ["William Melody"]
-  # dependencies defined in Gemfile
-end
-Jeweler::RubygemsDotOrgTasks.new
-
 require 'rake/testtask'
 Rake::TestTask.new(:test) do |test|
   test.libs << 'lib' << 'test'

data/iso-639.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = "iso-639"
-  s.version = "0.1.0"
+  s.version = "0.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["William Melody"]
@@ -23,7 +23,6 @@ Gem::Specification.new do |s|
     "LICENSE",
     "README.markdown",
     "Rakefile",
-    "VERSION",
     "iso-639.gemspec",
     "lib/iso-639.rb",
     "test/helper.rb",
@@ -39,18 +38,15 @@ Gem::Specification.new do |s|
     s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
-      s.add_development_dependency(%q<jeweler>, ["~> 1.8.4"])
       s.add_development_dependency(%q<mocha>, [">= 0"])
       s.add_development_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_development_dependency(%q<shoulda>, [">= 0"])
     else
-      s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
       s.add_dependency(%q<mocha>, [">= 0"])
       s.add_dependency(%q<rdoc>, ["~> 3.12"])
       s.add_dependency(%q<shoulda>, [">= 0"])
     end
   else
-    s.add_dependency(%q<jeweler>, ["~> 1.8.4"])
     s.add_dependency(%q<mocha>, [">= 0"])
     s.add_dependency(%q<rdoc>, ["~> 3.12"])
     s.add_dependency(%q<shoulda>, [">= 0"])

data/lib/iso-639.rb

@@ -497,6 +497,28 @@ class ISO_639 < Array
     self["zxx", "", "", "No linguistic content; Not applicable", "pas de contenu linguistique; non applicable"],
     self["zza", "", "", "Zaza; Dimili; Dimli; Kirdki; Kirmanjki; Zazaki", "zaza; dimili; dimli; kirdki; kirmanjki; zazaki"]
   ]
+
+  # A reverse index generated from the ISO_639_2 data. Used for searching
+  # all words and codes in all fields.
+  REVERSE_INDEX = lambda {
+    index = {}
+    ISO_639_2.each_with_index do |record, i|
+      record.each do |field|
+        downcased = field.downcase
+        words = (
+          downcased.split(/[[:blank:]]|\(|\)|,|;/) +
+          downcased.split(/;/)
+        )
+        words.each do |word|
+          unless word.empty?
+            index[word] ||= []
+            index[word] << i
+          end
+        end
+      end
+    end
+    return index
+  }.call
   
   # The ISO 639-1 dataset as an array of entries. Each entry is an array with
   # the following format:
@@ -530,6 +552,15 @@ class ISO_639 < Array
     def find_by_french_name(name)
       ISO_639_2.detect { |entry| entry if entry.french_name == name }
     end
+
+    # Returns an array of matches for the search term. The term can be a code
+    # of any kind, or it can be one of the words contained in the English or
+    # French name field.
+    def search(term)
+      normalized_term = term.downcase.strip
+      indexes         = REVERSE_INDEX[normalized_term]
+      indexes ? ISO_639_2.values_at(*indexes).uniq : []
+    end
   end
   
   # The entry's alpha-3 bibliotigraphic code.
@@ -544,4 +575,4 @@ class ISO_639 < Array
   # The entry's french name.
   def french_name;          self[4] end
   
-end
+end

data/test/test_ISO_639.rb

@@ -1,3 +1,4 @@
+# encoding: UTF-8
 require 'helper'
 
 class TestISO639 < Test::Unit::TestCase
@@ -37,5 +38,42 @@ class TestISO639 < Test::Unit::TestCase
       assert_equal ["eng", "eng", "", "en", "English", "anglais"][i], @entry.send(m)
     end
   end
+
+  should "return single record array by searching a unique code" do
+    assert_equal(
+      [["spa", "", "es", "Spanish; Castilian", "espagnol; castillan"]],
+      ISO_639.search("es")
+    )
+  end
+
+  should "return single record array by searching a unique term" do
+    assert_equal(
+      [["spa", "", "es", "Spanish; Castilian", "espagnol; castillan"]],
+      ISO_639.search("spanish")
+    )
+  end
+
+  should "return multiple record array by searching a common term" do
+    assert_equal(
+      [
+        ["egy", "", "", "Egyptian (Ancient)", "égyptien"],
+        ["grc", "", "", "Greek, Ancient (to 1453)", "grec ancien (jusqu'à 1453)"]
+      ],
+      ISO_639.search("ancient")
+    )
+  end
+
+  should "return empty array when searching a non-existent term" do
+    assert_equal(
+      [], ISO_639.search("bad term")
+    )
+  end
+
+  should "return single record array by searching a unique multi-word term" do
+    assert_equal(
+      [["ypk", "", "", "Yupik languages", "yupik, langues"]],
+      ISO_639.search("yupik, langues")
+    )
+  end
   
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: iso-639
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
   prerelease: 
 platform: ruby
 authors:
@@ -11,22 +11,6 @@ bindir: bin
 cert_chain: []
 date: 2012-11-01 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: jeweler
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.8.4
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.8.4
 - !ruby/object:Gem::Dependency
   name: mocha
   requirement: !ruby/object:Gem::Requirement
@@ -89,7 +73,6 @@ files:
 - LICENSE
 - README.markdown
 - Rakefile
-- VERSION
 - iso-639.gemspec
 - lib/iso-639.rb
 - test/helper.rb
@@ -107,9 +90,6 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: 2442761226781882380
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:

data/VERSION

@@ -1 +0,0 @@
-0.1.0