iso-codes 0.1.0 → 0.2.0

data/README.rdoc

@@ -68,6 +68,6 @@ For an individual language the macrolanguage, if any, can be found.
 If you feel like implementing any of this, please fork the project on
 github.
 
-= Copyright
+== Copyright
 
-Copyright (c) 2010 Marius L. Jøhndal.
+Copyright (c) 2010, 2011 Marius L. Jøhndal.

data/TODO

@@ -0,0 +1,49 @@
+= iso-codes
+
+These files may be used to download the list of language codes with their language names, for example into a database. To read the files, please note that one line of text contains one entry. An alpha-3 (bibliographic) code, an alpha-3 (terminologic) code (when given), an alpha-2 code (when given), an English name, and a French name of a language are all separated by pipe (|) characters. If one of these elements is not applicable to the entry, the field is left empty, i.e., a pipe (|) character immediately follows the preceding entry. The Line terminator is the LF character.
+
+A comprehensive database of ISO codes.
+
+
+While most languages are given one code by the standard, twenty of the languages described have two three-letter codes, a "bibliographic" code (ISO 639-2/B), which is derived from the English name for the language and was a necessary legacy feature, and a "terminological" code (ISO 639-2/T), which is derived from the native name for the language. Each of these twenty languages is also included in the ISO 639-1 standard. (There were 22 B codes; scc and scr are now deprecated.)
+
+In addition, there are codes for special situations:
+
+    * mis is listed as "uncoded languages"
+    * mul (for multiple languages) is applied when several languages are used and it is not practical to specify all the appropriate language codes
+    * The interval from qaa to qtz is reserved and is not used in the standard
+    * und (for undetermined) is used in situations in which a language or languages must be indicated but the language cannot be identified.
+    * zxx is listed in the code list as "no linguistic content" (added 2006-01-11)
+
+Some ISO 639-2 codes that are commonly used for languages do not precisely represent a particular language or some related languages (as the above macrolanguages). They are regarded as collective languages (or collectives) and are excluded from ISO 639-3.
+
+
+CREATE TABLE ISO_639-3_Names (
+   Id             char(3)     NOT NULL,  -- The three-letter 639-3 identifier
+   Print_Name     varchar(75) NOT NULL,  -- One of the names associated with this identifier 
+   Inverted_Name  varchar(75) NOT NULL)  -- The inverted form of this Print_Name form   
+
+CREATE TABLE ISO_639-3_Macrolanguages (
+   M_Id      char(3) NOT NULL,  -- The identifier for a macrolanguage
+   I_Id      char(3) NOT NULL,  -- The identifier for an individual language
+                                -- that is a member of the macrolanguage
+   I_Status  char(1) NOT NULL)  -- A (active) or R (retired) indicating the
+                                -- status of the individual code element
+
+* countries and regions: 
+
+  - ISO 3166-1 Codes for the representation of names of countries and their subdivisions – Part 1: Country codes,
+    ISO 3166-2 Codes for the representation of names of countries and their subdivisions – Part 2: Country subdivision codes,
+    ISO 3166-3 Codes for the representation of names of countries and their subdivisions – Part 3: Code for formerly used names of countries
+
+    Maintenance agency: http://www.iso.org/iso/country_codes
+    Last update: 2008-04-25 (http://www.iso.org/iso/country_codes/check_what_s_new.htm)
+
+* currencies:
+
+  - ISO 4217:2008 Codes for the representation of currencies and funds
+    ISO 4217:2001 Codes for the representation of currencies and funds
+
+    Maintenance agency: http://www.bsi-global.com/en/Standards-and-Publications/Industry-Sectors/Services/BSI-Currency-Code-Service/
+
+                                

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.0

data/lib/iso_codes.rb

@@ -1,41 +1,41 @@
 #
 # iso_codes.rb - A comprehensive database of ISO codes
 #
-# Written by Marius L. Jøhndal, 2008, 2010.
+# Written by Marius L. Jøhndal, 2008, 2010, 2011.
 #
 require 'zlib'
 
 module ISOCodes
-  # Version of the ISO 639-3 code set (see
+  # Version of the ISO 639-3 code set supported (see
   # http://www.sil.org/iso639-3/download.asp).
-  ISO_639_3_VERSION = '20100330'
+  ISO_639_3_VERSION = '20100707'
 
-  # Version of the ISO 639-3 macrolanguage mappings (see
+  # Version of the ISO 639-3 macrolanguage mappings supported (see
   # http://www.sil.org/iso639-3/download.asp).
   ISO_639_3_MACROLANGUAGE_MAPPINGS_VERSION = '20100128'
 
   class Language
-    # Returns the ISO 639-3 identifier.
+    # ISO 639-3 identifier for the language, or +nil+ if none is defined.
     attr_reader :identifier
 
-    # Returns the equivalent ISO 639-2 identifier of the bibliographic applications code set, or
-    # +nil+ if none is defined.
+    # ISO 639-2 identifier of the bibliographic applications code set for
+    # the language, or +nil+ if none is defined.
     attr_reader :alpha3_bibliographic
 
-    # Returns the equivalent ISO 639-2 identifier of the terminology applications code set, or
-    # +nil+ if none is defined.
+    # ISO 639-2 identifier of the terminology applications code set for the
+    # language, or +nil+ if none is defined.
     attr_reader :alpha3_terminology
 
-    # Returns the equivalent ISO 639-1 identifier, or +nil+ if none is defined.
+    # ISO 639-1 identifier for the language, or +nil+ if none is defined.
     attr_reader :alpha2
 
-    # Returns the language type. Language type is either <tt>:living</tt>,
-    # <tt>:extinct</tt>, <tt>:ancient</tt>, <tt>:historic</tt>,
-    # <tt>:constructed</tt>, or <tt>:special</tt>. See http://www.sil.org/iso639-3/types.asp
-    # for a description of these.
+    # Language type for the language. Language type is either
+    # <tt>:living</tt>, <tt>:extinct</tt>, <tt>:ancient</tt>,
+    # <tt>:historic</tt>, <tt>:constructed</tt>, or <tt>:special</tt>. See
+    # http://www.sil.org/iso639-3/types.asp for a description.
     attr_reader :language_type
 
-    # Returns the reference language name.
+    # Reference name for the language.
     attr_reader :reference_name
 
     def initialize(identifier, part2b, part2t, part1, language_type, ref_name)
@@ -56,8 +56,8 @@ module ISOCodes
       @macrolanguage = macrolanguage
     end
 
-    # Returns the macrolanguage it is part of or +nil+ if not part of any
-    # macrolanguage.
+    # Returns the macrolanguage the language belongs to or +nil+ if not
+    # part of any macrolanguage.
     def macrolanguage
       ISOCodes::find_iso_639_3_language(@macrolanguage)
     end
@@ -71,7 +71,8 @@ module ISOCodes
       @individual_languages = individual_languages
     end
 
-    # Returns an array of individual languages, otherwise an empty array.
+    # Returns an array of individual languages or an empty array if no
+    # individual languages are defined.
     def individual_languages
       @individual_languages.map { |c| ISOCodes::find_iso_639_3_language(c) }
     end
@@ -79,13 +80,13 @@ module ISOCodes
 
   class << self
     # Returns an object describing the language identified by the language
-    # code.
+    # code +code+.
     def find_language(code)
       find_iso_639_3_language(code)
     end
 
-    # Returns an object describing the language identified by an ISO 639-3
-    # identifier.
+    # Returns an object describing the language identified by the ISO 639-3
+    # identifier +code+.
     def find_iso_639_3_language(code)
       if @@iso_639_3.has_key?(code)
         klass, *rest = @@iso_639_3[code]
@@ -98,15 +99,6 @@ module ISOCodes
 
   private
 
-  LANGUAGE_TYPES = {
-    'L' => :living,
-    'E' => :extinct,
-    'A' => :ancient,
-    'H' => :historic,
-    'C' => :constructed,
-    'S' => :special,
-  }.freeze
-
   DATA_PATH = File.expand_path(File.dirname(__FILE__))
 
   class << self
@@ -114,7 +106,7 @@ module ISOCodes
       File.join(DATA_PATH, filename)
     end
 
-    def read_data_file(filename, field_count, delimiter = /,\s*/, skip_first = false)
+    def read_data_file(filename, field_count, delimiter, skip_first)
       Zlib::GzipReader.open(get_data_filename(filename)).each_line do |l|
         if skip_first
           skip_first = false
@@ -135,16 +127,26 @@ module ISOCodes
         raise ArgumentError, "missing identifier" if identifier.nil?
         raise ArgumentError, "missing reference name" if ref_name.nil?
 
-        case scope
-        when 'I': klass = IndividualLanguage
-        when 'M': klass = Macrolanguage
-        when 'S': klass = nil # FIXME
-        else
-          raise ArgumentError, "invalid scope"
-        end
-
-        language_type = LANGUAGE_TYPES[language_type]
-        raise ArgumentError, "invalid language type" if language_type.nil?
+        klass =
+          case scope
+          when 'I': IndividualLanguage
+          when 'M': Macrolanguage
+          when 'S': nil # FIXME
+          else
+            raise ArgumentError, "invalid scope"
+          end
+
+        language_type =
+          case language_type
+          when 'L': :living
+          when 'E': :extinct
+          when 'A': :ancient
+          when 'H': :historic
+          when 'C': :constructed
+          when 'S': :special
+          else
+            raise ArgumentError, "invalid language type"
+          end
 
         data[identifier] = [klass, nil, nil, identifier, part2b, part2t, part1, language_type, ref_name]
       end

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: iso-codes
 version: !ruby/object:Gem::Version 
+  hash: 23
   prerelease: false
   segments: 
   - 0
-  - 1
+  - 2
   - 0
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - "Marius L. J\xC3\xB8hndal"
@@ -14,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-06-29 00:00:00 +01:00
+date: 2011-01-19 00:00:00 +00:00
 default_executable: 
 dependencies: []
 
@@ -27,45 +28,50 @@ extensions: []
 extra_rdoc_files: 
 - README.rdoc
 - README.todo
+- TODO
 files: 
-- .gitignore
 - CHANGELOG
 - README.rdoc
 - Rakefile
 - VERSION
 - iso-codes.gemspec
 - lib/iso-639-3-macrolanguages_20100128.tab.gz
-- lib/iso-639-3_20100330.tab.gz
+- lib/iso-639-3_20100707.tab.gz
 - lib/iso_codes.rb
 - test/test_iso_codes.rb
 - README.todo
+- TODO
 has_rdoc: true
 homepage: http://github.com/mlj/iso-codes
 licenses: []
 
 post_install_message: 
-rdoc_options: 
-- --charset=UTF-8
+rdoc_options: []
+
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: iso-codes
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: ISO language and script code support

data/.gitignore

@@ -1,2 +0,0 @@
-pkg
-doc