alphabets 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 2679f375c1118915625e06811cf773a4d59707a6
+  data.tar.gz: 5375336c3b4d0002923547f5a9d41498d629722f
+SHA512:
+  metadata.gz: 3ff7470fe10524e8b0080cc36c9eb7a2534f70f75a4f47ca1cf46698bb2cf68a8845b45a364c01a65469bfa3d42f7865172aff8217103766043675b30924bf7a
+  data.tar.gz: '018796bf5c80bc970458716cf297f53616fb2ee1a031e91fa184d5351483564760a688e283368d760838832350b683d6951c4ce857eaa168177269ae451c10dd'

data/HISTORY.md

@@ -0,0 +1,3 @@
+### 0.0.1 / 2019-08-13
+
+* Everything is new. First release.

data/Manifest.txt

@@ -0,0 +1,13 @@
+HISTORY.md
+Manifest.txt
+NOTES.md
+README.md
+Rakefile
+lib/alphabets.rb
+lib/alphabets/alphabets.rb
+lib/alphabets/variants.rb
+lib/alphabets/version.rb
+test/helper.rb
+test/test_downcase.rb
+test/test_unaccent.rb
+test/test_variants.rb

data/NOTES.md

@@ -0,0 +1,3 @@
+# Notes
+
+## Todos

data/README.md

@@ -0,0 +1,26 @@
+# alphabets -
+
+
+* home  :: [github.com/sportdb/sport.db](https://github.com/sportdb/sport.db)
+* bugs  :: [github.com/sportdb/sport.db/issues](https://github.com/sportdb/sport.db/issues)
+* gem   :: [rubygems.org/gems/alphabets](https://rubygems.org/gems/alphabets)
+* rdoc  :: [rubydoc.info/gems/alphabets](http://rubydoc.info/gems/alphabets)
+* forum :: [opensport](http://groups.google.com/group/opensport)
+
+
+## Usage
+
+To be done
+
+
+## License
+
+The `alphabets` scripts are dedicated to the public domain.
+Use it as you please with no restrictions whatsoever.
+
+
+## Questions? Comments?
+
+Send them along to the
+[Open Sports & Friends Forum/Mailing List](http://groups.google.com/group/opensport).
+Thanks!

data/Rakefile

@@ -0,0 +1,28 @@
+require 'hoe'
+require './lib/alphabets/version.rb'
+
+Hoe.spec 'alphabets' do
+
+  self.version = Alphabet::VERSION
+
+  self.summary = "alphabets - "
+  self.description = summary
+
+  self.urls = ['https://github.com/sportdb/sport.db']
+
+  self.author = 'Gerald Bauer'
+  self.email = 'opensport@googlegroups.com'
+
+  # switch extension to .markdown for gihub formatting
+  self.readme_file = 'README.md'
+  self.history_file = 'HISTORY.md'
+
+  self.licenses = ['Public Domain']
+
+  self.extra_deps = []
+
+  self.spec_extras = {
+   :required_ruby_version => '>= 2.2.2'
+  }
+
+end

data/lib/alphabets.rb

@@ -0,0 +1,34 @@
+# encoding: utf-8
+
+require 'pp'
+
+
+###
+# our own code
+require 'alphabets/version' # let version always go first
+require 'alphabets/alphabets'
+require 'alphabets/variants'
+
+
+
+## add "global" convenience helper
+def downcase_i18n( name )
+  Alphabet.downcase_i18n( name )
+end
+
+def unaccent( name )
+  Alphabet.unaccent( name )   ## using "default" language character mapping / table
+end
+
+def variants( name )    ## todo/check: rename to unaccent_variants or unaccent_names - why? why not?
+  Variant.find( name )
+end
+
+
+## add convenience aliases - also add Alpha - why? why not?
+Abc       = Alphabet
+Alphabets = Alphabet
+Alpha     = Alphabet
+
+
+puts Alphabet.banner   # say hello

data/lib/alphabets/alphabets.rb

@@ -0,0 +1,186 @@
+# encoding: utf-8
+
+class Alphabet   ## todo/fix: add alias Abc  and Alpha too? why? why not?
+  def self.frequency_table( name )   ## todo/check: use/rename to char_frequency_table
+    ## calculate the frequency table of letters, digits, etc.
+    freq = Hash.new(0)
+    name.each_char do |ch|
+       freq[ch] += 1
+    end
+    freq
+  end
+
+
+  def self.count( freq, mapping_or_chars )
+    chars = if mapping_or_chars.is_a?( Hash )
+              mapping_or_chars.keys
+            else   ## todo/fix: check for is_a? Array and if is String split into Array (on char at a time?) - why? why not?
+              mapping_or_chars  ## assume it's an array/list of characters
+            end
+
+    chars.reduce(0) do |count,ch|
+      count += freq[ch]
+      count
+    end
+  end
+
+
+  def self.tr( name, mapping )
+    buf = String.new
+    name.each_char do |ch|
+      buf << if mapping[ch]
+                mapping[ch]
+              else
+                ch
+              end
+    end
+    buf
+  end
+
+
+  class Unaccenter #Worker    ## todo/change - find a better name - why? why not?
+    def initialize( mapping )
+      @mapping = mapping
+    end
+
+    def count( name )      Alphabet.count( name, @mapping ); end
+    def unaccent( name )   Alphabet.tr( name, @mapping );    end
+  end  # class Unaccent Worker
+
+
+  def self.find_unaccenter( key )
+    if key == :de
+      @de ||= Unaccenter.new( UNACCENT_DE )
+      @de
+    else
+      ## use uni(versal) or unicode or something - why? why not?
+      ##  use all or int'l (international) - why? why not?
+      ##  use en  (english) - why? why not?
+      @default ||= Unaccenter.new( UNACCENT )
+      @default
+    end
+  end
+
+  def self.unaccent( name )
+    @default ||= Unaccenter.new( UNACCENT )
+    @default.unaccent( name )
+  end
+
+
+  def self.downcase_i18n( name )    ## our very own downcase for int'l characters / letters
+    tr( name, DOWNCASE )
+  end
+  ## add downcase_uni  - univeral/unicode - why? why not?
+
+
+  ##  "simple" unaccent (remove accents/diacritics and unfold ligatures) translation table / mapping
+  UNACCENT = {
+    'Ä'=>'A',  'ä'=>'a',
+    'Á'=>'A',  'á'=>'a',
+               'à'=>'a',
+               'ã'=>'a',
+               'â'=>'a',
+    'Å'=>'A',  'å'=>'a',
+               'æ'=>'ae',
+               'ā'=>'a',
+               'ă'=>'a',
+               'ą'=>'a',
+
+    'Ç' =>'C', 'ç'=>'c',
+               'ć'=>'c',
+    'Č'=>'C',  'č'=>'c',
+
+    'É'=>'E',  'é'=>'e',
+               'è'=>'e',
+               'ê'=>'e',
+               'ë'=>'e',
+               'ė'=>'e',
+               'ę'=>'e',
+
+               'ğ'=>'g',
+
+    'İ'=>'I',
+    'Í'=>'I',  'í'=>'i',
+               'î'=>'i',
+               'ī'=>'i',
+               'ı'=>'i',
+
+    'Ł'=>'L', 'ł'=>'l',
+
+               'ñ'=>'n',
+               'ń'=>'n',
+               'ň'=>'n',
+
+    'Ö'=>'O',  'ö'=>'o',
+               'ó'=>'o',
+               'õ'=>'o',
+               'ô'=>'o',
+               'ø'=>'o',
+               'ő'=>'o',
+
+                'ř'=>'r',
+
+    'Ś'=>'S',
+    'Ş'=>'S',  'ş'=>'s',
+    'Š'=>'S',  'š'=>'s',
+               'ș'=>'s',  ## U+0219
+               'ß'=>'ss',
+
+               'ţ'=>'t',  ## U+0163
+               'ț'=>'t',  ## U+021B
+               'þ'=>'th',   #### fix!!!! use p - why? why not?
+
+    'Ü'=>'U',  'ü'=>'u',
+    'Ú'=>'U',  'ú'=>'u',
+               'ū'=>'u',
+
+               'ý'=>'y',
+
+               'ź'=>'z',
+               'ż'=>'z',
+    'Ž'=>'Z',  'ž'=>'z',
+  }
+
+
+  ##  de,at,ch translation for umlauts
+  UNACCENT_DE = {
+    'Ä'=>'Ae',  'ä'=>'ae',  ### Use AE, OE, UE and NOT Ae, Oe, Ue - why? why not? e.g.VÖST => VOEST or Ö => OE
+    'Ö'=>'Oe',  'ö'=>'oe',
+    'Ü'=>'Ue',  'ü'=>'ue',
+                'ß'=>'ss',
+  }
+
+  ## add UNACCENT_ES - why? why not?  is Espanyol catalan spelling or spanish (castillian)?
+  # 'ñ'=>'ny',    ## e.g. Español => Espanyol
+
+  DOWNCASE = %w[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z].reduce({}) do |h,ch|
+    h[ch] = ch.downcase
+    h
+  end.merge(
+    'Ä'=>'ä',
+    'Á'=>'á',
+    'Å'=>'å',
+
+    'Ç'=>'ç',
+    'Č'=>'č',
+
+    'É'=>'é',
+
+    'İ'=>'?',   ## fix - add lowercase
+    'Í'=>'í',
+
+    'Ł'=>'ł',
+
+    'Ö'=>'ö',
+
+    'Ś'=>'?',   ## fix - add lowercase
+    'Ş'=>'ş',
+    'Š'=>'š',
+
+    'Ü'=>'ü',
+    'Ú'=>'ú',
+
+    'Ž'=>'ž',
+  )
+
+end  # class Alphabet

data/lib/alphabets/variants.rb

@@ -0,0 +1,72 @@
+# encoding: utf-8
+
+
+class Variant    ## (spelling) variant finder / builder for names
+
+  EN_UNACCENTER = Alphabet.find_unaccenter( :en ) ## assume english (en) as default for know - change to universal/int'l/default or something - why? why not?
+  DE_UNACCENTER = Alphabet.find_unaccenter( :de )
+
+def self.find( name )
+  alt_names = []
+
+  freq = Alphabet.frequency_table( name )
+
+  en = EN_UNACCENTER
+  if en.count( freq ) > 0    # check if includes äöü (that is, character with accents or diacritics) etc.
+    alt_names <<  en.unaccent( name )
+  end
+
+  de = DE_UNACCENTER
+  if de.count( freq ) > 0
+    alt_names <<  de.unaccent( name )
+  end
+
+  ## todo - make uniq  e.g. Preußen is Preussen, Preussen 2x
+  alt_names = alt_names.uniq
+  alt_names
+end
+
+end  # class Variant
+
+
+
+######################################
+#  expiremental class - use (just) Name or NameQ or NameVariant or NameAnalyzer/Query or similar - why? why not?
+##   let's wait for now with usage - let's add more methods as we go along and find more - why? why not?
+class NameQuery
+  def initialize( name )
+    @name = name
+  end
+
+  def frequency_table
+    @freq ||= Alphabet.frequency_table( @name )
+  end
+
+  def variants
+    @variants ||= find_variants
+  end
+
+private
+  EN_UNACCENTER = Alphabet.find_unaccenter( :en ) ## assume english (en) as default for know - change to universal/int'l/default or something - why? why not?
+  DE_UNACCENTER = Alphabet.find_unaccenter( :de )
+
+  def find_variants
+    alt_names = []
+
+    freq = frequency_table
+
+    en = EN_UNACCENTER
+    if en.count( freq ) > 0    # check if includes äöü (that is, character with accents or diacritics) etc.
+      alt_names <<  en.unaccent( @name )
+    end
+
+    de = DE_UNACCENTER
+    if de.count( freq ) > 0
+      alt_names <<  de.unaccent( @name )
+    end
+
+    ## todo - make uniq  e.g. Preußen is Preussen, Preussen 2x
+    alt_names = alt_names.uniq
+    alt_names
+  end
+end  ## class VariantName

data/lib/alphabets/version.rb

@@ -0,0 +1,23 @@
+# encoding: utf-8
+
+
+## todo/check: use a module Alphabets with s to keep version and banner separate - why? why not?
+
+class Alphabet
+  MAJOR = 0    ## todo: namespace inside version or something - why? why not??
+  MINOR = 0
+  PATCH = 1
+  VERSION = [MAJOR,MINOR,PATCH].join('.')
+
+  def self.version
+    VERSION
+  end
+
+  def self.banner
+    "alphabets/#{VERSION} on Ruby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE}) [#{RUBY_PLATFORM}]"
+  end
+
+  def self.root
+    File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
+  end
+end # class Alphabet

data/test/helper.rb

@@ -0,0 +1,10 @@
+## $:.unshift(File.dirname(__FILE__))
+
+## minitest setup
+
+require 'minitest/autorun'
+
+
+## our own code
+
+require 'alphabets'

data/test/test_downcase.rb

@@ -0,0 +1,18 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_downcase.rb
+
+
+require 'helper'
+
+class TestDowncase < MiniTest::Test
+
+  def test_downcase_i18n
+    assert_equal 'abcdefghijklmnopqrstuvwxyz',  downcase_i18n( 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' )
+    assert_equal 'äöü',  downcase_i18n( 'ÄÖÜ' )
+    assert_equal 'köln', downcase_i18n( 'KÖLN' )
+  end
+
+end # class TestDowncase

data/test/test_unaccent.rb

@@ -0,0 +1,36 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_unaccent.rb
+
+
+require 'helper'
+
+class TestUnaccent < MiniTest::Test
+
+  def test_de
+    assert_equal 'Augsburg',             unaccent( 'Augsburg' )
+
+    assert_equal 'Koln',                 unaccent( 'Köln' )
+    assert_equal '1. FC Koln',           unaccent( '1. FC Köln' )
+
+    assert_equal 'Bayern Munchen',       unaccent( 'Bayern München' )
+    assert_equal 'F. Dusseldorf',        unaccent( 'F. Düsseldorf' )
+    assert_equal 'Preussen',             unaccent( 'Preußen' )
+    assert_equal 'Munster Preussen',     unaccent( 'Münster Preußen' )
+    assert_equal 'Rot-Weiss Oberhausen', unaccent( 'Rot-Weiß Oberhausen' )
+
+    assert_equal 'St. Polten',           unaccent( 'St. Pölten' )
+  end
+
+  def test_es
+    assert_equal 'Madrid',               unaccent( 'Madrid' )
+
+    assert_equal 'Atletico Madrid',      unaccent( 'Atlético Madrid' )
+    assert_equal 'Ecija Balompie',       unaccent( 'Écija Balompié' )
+    assert_equal 'La Coruna',            unaccent( 'La Coruña' )
+    assert_equal 'Almeria',              unaccent( 'Almería' )
+  end
+
+end # class TestUnaccent

data/test/test_variants.rb

@@ -0,0 +1,36 @@
+# encoding: utf-8
+
+###
+#  to run use
+#     ruby -I ./lib -I ./test test/test_variants.rb
+
+
+require 'helper'
+
+class TestVariants < MiniTest::Test
+
+  def test_de
+    assert_equal [],                             variants( 'Augsburg' )
+
+    assert_equal ['Koln', 'Koeln'],              variants( 'Köln' )
+    assert_equal ['1. FC Koln', '1. FC Koeln'],  variants( '1. FC Köln' )
+
+    assert_equal ['Bayern Munchen', 'Bayern Muenchen'], variants( 'Bayern München' )
+    assert_equal ['F. Dusseldorf', 'F. Duesseldorf'],   variants( 'F. Düsseldorf' )
+    assert_equal ['Preussen'], variants( 'Preußen' )
+    assert_equal ['Munster Preussen', 'Muenster Preussen'], variants( 'Münster Preußen' )
+    assert_equal ['Rot-Weiss Oberhausen'], variants( 'Rot-Weiß Oberhausen' )
+
+    assert_equal ['St. Polten', 'St. Poelten'], variants( 'St. Pölten' )
+  end
+
+  def test_es
+    assert_equal [],                   variants( 'Madrid' )
+
+    assert_equal ['Atletico Madrid'],  variants( 'Atlético Madrid' )
+    assert_equal ['Ecija Balompie'],   variants( 'Écija Balompié' )
+    assert_equal ['La Coruna'],        variants( 'La Coruña' )
+    assert_equal ['Almeria'],          variants( 'Almería' )
+  end
+
+end # class TestVariants

metadata

@@ -0,0 +1,90 @@
+--- !ruby/object:Gem::Specification
+name: alphabets
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Gerald Bauer
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-08-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.0'
+- !ruby/object:Gem::Dependency
+  name: hoe
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.16'
+description: 'alphabets - '
+email: opensport@googlegroups.com
+executables: []
+extensions: []
+extra_rdoc_files:
+- HISTORY.md
+- Manifest.txt
+- NOTES.md
+- README.md
+files:
+- HISTORY.md
+- Manifest.txt
+- NOTES.md
+- README.md
+- Rakefile
+- lib/alphabets.rb
+- lib/alphabets/alphabets.rb
+- lib/alphabets/variants.rb
+- lib/alphabets/version.rb
+- test/helper.rb
+- test/test_downcase.rb
+- test/test_unaccent.rb
+- test/test_variants.rb
+homepage: https://github.com/sportdb/sport.db
+licenses:
+- Public Domain
+metadata: {}
+post_install_message: 
+rdoc_options:
+- "--main"
+- README.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.2.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.5.2
+signing_key: 
+specification_version: 4
+summary: alphabets -
+test_files: []