alphabets 0.1.3 → 1.0.1

data/lib/alphabets/alphabets.rb

@@ -1,184 +1,186 @@
-
-class Alphabet
-
-##  "simple" unaccent (remove accents/diacritics and unfold ligatures) translation table / mapping
-UNACCENT = Reader.parse( <<TXT )
-    Ä A   ä a
-    Á A   á a
-    À A   à a
-    Ã A   ã a
-    Â A   â a
-    Å A   å a
-    Æ AE  æ ae   # ae ligature
-          ā a
-          ă a
-    Ą A   ą a    # ą - U+0105 (261) - LATIN SMALL LETTER A WITH OGONEK
-
-    Ç C   ç c    # ç - U+00E7 (231) - LATIN SMALL LETTER C WITH CEDILLA
-    Ć C   ć c
-    Č C   č c
-
-    Ď D   ď d
-    Ð D   ð d    # iceland - d
-
-    É E   é e
-    È E   è e
-    Ê E   ê e
-    Ë E   ë e
-          ė e
-    Ę E   ę e
-    Ě E   ě e
-
-          ğ g
-
-    İ I
-    Í I   í i
-    Ì I   ì i
-    Î I   î i
-          ī i
-          ı i    # ı - U+0131 (305) - LATIN SMALL LETTER DOTLESS I
-    Ï I   ï i
-
-    Ł L   ł l
-
-    Ñ N   ñ n
-    Ń N   ń n
-    Ň N   ň n
-
-    Ö O   ö o
-    Ő O   ő o    # hungarian - use OE/oe  - why? (it's not a ligature) why not?
-    Ó O   ó o
-    Ò O   ò o
-    Õ O   õ o
-    Ô O   ô o
-          ø o
-    Œ OE  œ oe   # oe ligature
-
-    Ř R   ř r
-
-    Ś S   ś s
-    Ş S   ş s   # ş - U+015F (351) - LATIN SMALL LETTER S WITH CEDILLA
-    Ș S   ș s   # ș - U+0219 (537) - LATIN SMALL LETTER S WITH COMMA BELOW
-    Š S   š s
-          ß ss  # ß - U+00DF (223) - LATIN SMALL LETTER SHARP S
-
-    Ţ T   ţ t   # ţ - U+0163 (355) - LATIN SMALL LETTER T WITH CEDILLA
-    Ț T   ț t   # ț - U+021B (539) - LATIN SMALL LETTER T WITH COMMA BELOW
-    Ť T   ť t
-
-    Þ P   þ p   # þ - U+00FE (254) - LATIN SMALL LETTER THORN
-                #### fix/check!!!! icelandic - use p is p or th - why? why not?
-
-    Ü U   ü u
-    Ú U   ú u
-    Ù U   ù u
-          ū u
-    Ů U   ů u
-    Û U   û u
-
-    Ý Y   ý y
-    Ÿ Y   ÿ y
-
-    Ź Z   ź z
-    Ż Z   ż z
-    Ž Z   ž z
-TXT
-
-##
-# Notes:
-#  Romanian did NOT initially get its Ș/ș and Ț/ț (with comma) letters,
-#  because these letters were initially unified with Ş/ş and Ţ/ţ (with cedilla)
-#  by the Unicode Consortium, considering the shapes with comma beneath
-#  to be glyph variants of the shapes with cedilla.
-#  However, the letters with explicit comma below were later added to the Unicode standard and are also in ISO 8859-16.
-
-
-##  de,at,ch translation for umlauts
-UNACCENT_DE = Reader.parse( <<TXT )
-    Ä AE  ä ae    ### note: Use upcase AE, OE, UE and NOT titlecase Ae, Oe, Ue - why? why not? e.g.VÖST => VOEST or Ö => OE
-    Ö OE  ö oe
-    Ü UE  ü ue
-          ß ss
-TXT
-
-
-## 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( Reader.parse( <<TXT ) )
-    Ä ä
-    Á á
-    À à
-    Â â
-    Å å
-    Æ æ   # LATIN LETTER AE  - ae ligature
-    Ą ą
-    Ã ã
-
-    Ç ç   # LATIN LETTER C WITH CEDILLA
-    Č č
-    Ć ć
-
-    Ď ď
-
-    Ð ð    # iceland - d
-
-    É é
-    È è
-    Ë ë
-    Ê ê
-    Ę ę
-    Ě ě
-
-    İ i
-    Í í
-    Ì ì
-    Ï ï
-    Î î
-
-    Ł ł
-
-    Ń ń
-    Ň ň
-    Ñ ñ
-
-    Ö ö
-    Ő ő
-    Œ œ   # LATIN LIGATURE OE
-    Ó ó
-    Ò ò
-    Ô ô
-    Õ õ
-
-    Þ þ    # iceland - p
-
-    Ř ř
-
-    Ś ś
-    Ş ş   # LATIN LETTER S WITH CEDILLA
-    Ș ș   # LATIN LETTER S WITH COMMA BELOW
-    Š š
-
-    Ţ ţ   # LATIN LETTER T WITH CEDILLA
-    Ț ț   # LATIN LETTER T WITH COMMA BELOW
-    Ť ť
-
-    Ü ü
-    Ú ú
-    Ù ù
-    Ů ů
-    Û û
-
-    Ý ý
-    Ÿ ÿ
-
-    Ž ž
-    Ż ż
-    Ź ź
-TXT
-
-end  # class Alphabet
+
+class Alphabet
+
+##  "simple" unaccent (remove accents/diacritics and unfold ligatures) translation table / mapping
+UNACCENT = Reader.parse( <<TXT )
+    Ä A   ä a
+    Á A   á a
+    À A   à a
+    Ã A   ã a
+    Â A   â a
+    Å A   å a
+    Æ AE  æ ae   # ae ligature
+          ā a
+          ă a
+    Ą A   ą a    # ą - U+0105 (261) - LATIN SMALL LETTER A WITH OGONEK
+
+    Ç C   ç c    # ç - U+00E7 (231) - LATIN SMALL LETTER C WITH CEDILLA
+    Ć C   ć c
+    Č C   č c
+
+    Ď D   ď d
+    Ð D   ð d    # iceland - d
+
+    É E   é e
+    È E   è e
+    Ê E   ê e
+    Ë E   ë e
+          ė e
+    Ę E   ę e
+    Ě E   ě e
+
+          ğ g
+
+    İ I
+    Í I   í i
+    Ì I   ì i
+    Î I   î i
+          ī i
+          ı i    # ı - U+0131 (305) - LATIN SMALL LETTER DOTLESS I
+    Ï I   ï i
+
+    Ł L   ł l
+
+    Ñ N   ñ n
+    Ń N   ń n
+    Ň N   ň n
+    Ņ N   ņ n        # N/n with cedilla U+0145 / U+0146 (capital / small)
+
+    Ö O   ö o
+    Ő O   ő o    # hungarian - use OE/oe  - why? (it's not a ligature) why not?
+    Ó O   ó o
+    Ò O   ò o
+    Õ O   õ o
+    Ô O   ô o
+          ø o
+    Œ OE  œ oe   # oe ligature
+
+    Ř R   ř r
+
+    Ś S   ś s
+    Ş S   ş s   # ş - U+015F (351) - LATIN SMALL LETTER S WITH CEDILLA
+    Ș S   ș s   # ș - U+0219 (537) - LATIN SMALL LETTER S WITH COMMA BELOW
+    Š S   š s
+          ß ss  # ß - U+00DF (223) - LATIN SMALL LETTER SHARP S
+
+    Ţ T   ţ t   # ţ - U+0163 (355) - LATIN SMALL LETTER T WITH CEDILLA
+    Ț T   ț t   # ț - U+021B (539) - LATIN SMALL LETTER T WITH COMMA BELOW
+    Ť T   ť t
+
+    Þ P   þ p   # þ - U+00FE (254) - LATIN SMALL LETTER THORN
+                #### fix/check!!!! icelandic - use p is p or th - why? why not?
+
+    Ü U   ü u
+    Ú U   ú u
+    Ù U   ù u
+          ū u
+    Ů U   ů u
+    Û U   û u
+
+    Ý Y   ý y
+    Ÿ Y   ÿ y
+
+    Ź Z   ź z
+    Ż Z   ż z
+    Ž Z   ž z
+TXT
+
+##
+# Notes:
+#  Romanian did NOT initially get its Ș/ș and Ț/ț (with comma) letters,
+#  because these letters were initially unified with Ş/ş and Ţ/ţ (with cedilla)
+#  by the Unicode Consortium, considering the shapes with comma beneath
+#  to be glyph variants of the shapes with cedilla.
+#  However, the letters with explicit comma below were later added to the Unicode standard and are also in ISO 8859-16.
+
+
+##  de,at,ch translation for umlauts
+UNACCENT_DE = Reader.parse( <<TXT )
+    Ä AE  ä ae    ### note: Use upcase AE, OE, UE and NOT titlecase Ae, Oe, Ue - why? why not? e.g.VÖST => VOEST or Ö => OE
+    Ö OE  ö oe
+    Ü UE  ü ue
+          ß ss
+TXT
+
+
+## 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( Reader.parse( <<TXT ) )
+    Ä ä
+    Á á
+    À à
+    Â â
+    Å å
+    Æ æ   # LATIN LETTER AE  - ae ligature
+    Ą ą
+    Ã ã
+
+    Ç ç   # LATIN LETTER C WITH CEDILLA
+    Č č
+    Ć ć
+
+    Ď ď
+
+    Ð ð    # iceland - d
+
+    É é
+    È è
+    Ë ë
+    Ê ê
+    Ę ę
+    Ě ě
+
+    İ i
+    Í í
+    Ì ì
+    Ï ï
+    Î î
+
+    Ł ł
+
+    Ń ń
+    Ň ň
+    Ñ ñ
+    Ņ ņ
+
+    Ö ö
+    Ő ő
+    Œ œ   # LATIN LIGATURE OE
+    Ó ó
+    Ò ò
+    Ô ô
+    Õ õ
+
+    Þ þ    # iceland - p
+
+    Ř ř
+
+    Ś ś
+    Ş ş   # LATIN LETTER S WITH CEDILLA
+    Ș ș   # LATIN LETTER S WITH COMMA BELOW
+    Š š
+
+    Ţ ţ   # LATIN LETTER T WITH CEDILLA
+    Ț ț   # LATIN LETTER T WITH COMMA BELOW
+    Ť ť
+
+    Ü ü
+    Ú ú
+    Ù ù
+    Ů ů
+    Û û
+
+    Ý ý
+    Ÿ ÿ
+
+    Ž ž
+    Ż ż
+    Ź ź
+TXT
+
+end  # class Alphabet

data/lib/alphabets/variants.rb

@@ -1,72 +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
+# 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

@@ -1,23 +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 = 1
-  PATCH = 3
-  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
+# encoding: utf-8
+
+
+## todo/check: use a module Alphabets with s to keep version and banner separate - why? why not?
+
+class Alphabet
+  MAJOR = 1    ## 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}] in (#{root})"
+  end
+
+  def self.root
+    File.expand_path( File.dirname(File.dirname(File.dirname(__FILE__))) )
+  end
+end # class Alphabet

data/lib/alphabets.rb

@@ -1,40 +1,46 @@
-# encoding: utf-8
-
-require 'pp'
-
-
-###
-# our own code
-require 'alphabets/version' # let version always go first
-require 'alphabets/reader'
-require 'alphabets/alphabets'
-require 'alphabets/utils'
-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 undiacritic( name ) unaccent( name ); end    ## alias for unaccent
-
-
-
-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
+
+## note - pp now part of ruby core since version ???
+###           check no longer required!!!
+require 'pp'
+
+
+###
+# our own code
+require_relative 'alphabets/version' # let version always go first
+require_relative 'alphabets/reader'
+require_relative 'alphabets/alphabets'
+require_relative 'alphabets/utils'
+require_relative 'alphabets/variants'
+
+
+##
+##  add globals inside Kernel ??
+##    lets us use alias_method 
+##    what else?   why? why not?
+
+
+## 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 undiacritic( name ) unaccent( name ); end    ## alias for unaccent
+
+
+
+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/test/helper.rb

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