stringex 1.5.1 → 2.0.0

data/lib/stringex/unidecoder.rb

@@ -1,5 +1,4 @@
 # encoding: UTF-8
-require "yaml"
 
 module Stringex
   module Unidecoder
@@ -7,15 +6,14 @@ module Stringex
     CODEPOINTS = Hash.new{|h, k|
       h[k] = YAML.load_file(File.join(File.expand_path(File.dirname(__FILE__)), "unidecoder_data", "#{k}.yml"))
     } unless defined?(CODEPOINTS)
-    LOCAL_CODEPOINTS = Hash.new unless defined?(LOCAL_CODEPOINTS)
 
     class << self
       # Returns string with its UTF-8 characters transliterated to ASCII ones
       #
       # You're probably better off just using the added String#to_ascii
       def decode(string)
-        string.gsub(/[^\x00-\x7f]/u) do |codepoint|
-          if localized = local_codepoint(codepoint)
+        string.gsub(/[^\x00-\x00]/u) do |codepoint|
+          if localized = translate(codepoint)
             localized
           else
             begin
@@ -47,66 +45,12 @@ module Stringex
         "#{code_group(unpacked)}.yml (line #{grouped_point(unpacked) + 2})"
       end
 
-      # Adds localized transliterations to Unidecoder
-      def localize_from(hash_or_path_to_file)
-        hash = if hash_or_path_to_file.is_a?(Hash)
-          hash_or_path_to_file
-        else
-          YAML.load_file(hash_or_path_to_file)
-        end
-        verify_local_codepoints hash
-      end
-
-      # Returns locale for localized transliterations
-      def locale
-        if @locale
-          @locale
-        elsif defined?(I18n)
-          I18n.locale
-        else
-          default_locale
-        end
-      end
-
-      # Sets locale for localized transliterations
-      def locale=(new_locale)
-        @locale = new_locale
-      end
-
-      # Returns default locale for localized transliterations. NOTE: Will set @locale as well.
-      def default_locale
-        @default_locale ||= "en"
-        @locale = @default_locale
-      end
-
-      # Sets the default locale for localized transliterations. NOTE: Will set @locale as well.
-      def default_locale=(new_locale)
-        @default_locale = new_locale
-        # Seems logical that @locale should be the new default
-        @locale = new_locale
-      end
-
-      # Returns the localized transliteration for a codepoint
-      def local_codepoint(codepoint)
-        locale_hash = LOCAL_CODEPOINTS[locale] || LOCAL_CODEPOINTS[locale.is_a?(Symbol) ? locale.to_s : locale.to_sym]
-        locale_hash && locale_hash[codepoint]
-      end
-
-      # Runs a block with a temporary locale setting, returning the locale to the original state when complete
-      def with_locale(new_locale, &block)
-        new_locale = default_locale if new_locale == :default
-        original_locale = locale
-        self.locale = new_locale
-        block.call
-        self.locale = original_locale
-      end
+    private
 
-      # Runs a block with default locale
-      def with_default_locale(&block)
-        with_locale default_locale, &block
+      def translate(codepoint)
+        Localization.translate(:transliterations, codepoint)
       end
 
-    private
       # Returns the Unicode codepoint grouping for the given character
       def code_group(unpacked_character)
         "x%02x" % (unpacked_character >> 8)
@@ -116,51 +60,12 @@ module Stringex
       def grouped_point(unpacked_character)
         unpacked_character & 255
       end
-
-      # Checks LOCAL_CODEPOINTS's Hash is in the format we expect before assigning it and raises
-      # instructive exception if not
-      def verify_local_codepoints(hash)
-        if !pass_check(hash)
-          raise ArgumentError, "LOCAL_CODEPOINTS is not correctly defined. Please see the README for more information on how to correctly format this data."
-        end
-        hash.each{|k, v| LOCAL_CODEPOINTS[k] = v}
-      end
-
-      def pass_check(hash)
-        return false if !hash.is_a?(Hash)
-        hash.all?{|key, value| pass_check_key_and_value_test(key, value) }
-      end
-
-      def pass_check_key_and_value_test(key, value)
-        # Fuck a duck, eh?
-        return false unless [Symbol, String].include?(key.class)
-        return false unless value.is_a?(Hash)
-        value.all?{|k, v| k.is_a?(String) && v.is_a?(String)}
-      end
-    end
-  end
-
-  # Provide a simpler interface for localization implementations
-  class << self
-    %w{
-      localize_from
-      locale
-      locale=
-      default_locale
-      default_locale=
-      local_codepoint
-      with_locale
-      with_default_locale
-    }.each do |name|
-      define_method name do |*args, &block|
-        Unidecoder.send name, *args, &block
-      end
     end
   end
 end
 
 module Stringex
-  module StringExtensions
+  module StringExtensions::PublicInstanceMethods
     # Returns string with its UTF-8 characters transliterated to ASCII ones. Example:
     #
     #   "⠋⠗⠁⠝⠉⠑".to_ascii #=> "france"

data/lib/stringex/unidecoder_data/x00.yml

@@ -95,7 +95,7 @@
 - ']'
 - '^'
 - _
-- '`'
+- "'"
 - a
 - b
 - c

data/lib/stringex/unidecoder_data/x02.yml

@@ -186,10 +186,10 @@
 - y
 - "'"
 - '"'
-- '`'
 - "'"
-- '`'
-- '`'
+- "'"
+- "'"
+- "'"
 - "'"
 - '?'
 - '?'
@@ -202,14 +202,14 @@
 - "'"
 - '-'
 - /
-- '`'
+- "'"
 - ','
 - _
 - \
 - /
 - ':'
 - .
-- '`'
+- "'"
 - "'"
 - '^'
 - V

data/lib/stringex/unidecoder_data/x05.yml

@@ -225,7 +225,7 @@
 - n
 - n
 - s
-- '`'
+- "'"
 - p
 - p
 - ts

data/lib/stringex/unidecoder_data/x06.yml

@@ -56,7 +56,7 @@
 - D
 - T
 - Z
-- '`'
+- "'"
 - G
 - '[?]'
 - '[?]'

data/lib/stringex/unidecoder_data/x07.yml

@@ -36,7 +36,7 @@
 - n
 - s
 - s
-- '`'
+- "'"
 - p
 - p
 - S
@@ -64,7 +64,7 @@
 - u
 - o
 - ''
-- '`'
+- "'"
 - "'"
 - ''
 - ''
@@ -161,7 +161,7 @@
 - d
 - t
 - z
-- '`'
+- "'"
 - gh
 - q
 - w

data/lib/stringex/unidecoder_data/x09.yml

@@ -82,7 +82,7 @@
 - AUM
 - "'"
 - "'"
-- '`'
+- "'"
 - "'"
 - '[?]'
 - '[?]'

data/lib/stringex/unidecoder_data/x0e.yml

@@ -44,7 +44,7 @@
 - s
 - h
 - l
-- '`'
+- "'"
 - h
 - '~'
 - a
@@ -172,7 +172,7 @@
 - s
 - h
 - '[?]'
-- '`'
+- "'"
 - ''
 - '~'
 - a

data/lib/stringex/unidecoder_data/x1f.yml

@@ -238,7 +238,7 @@
 - R
 - '"`'
 - "\"'"
-- '`'
+- "'"
 - '[?]'
 - '[?]'
 - o
@@ -253,4 +253,4 @@
 - O
 - O
 - "'"
-- '`'
+- "'"

data/lib/stringex/unidecoder_data/x20.yml

@@ -52,7 +52,7 @@
 - "'"
 - '"'
 - "'''"
-- '`'
+- "'"
 - '``'
 - '```'
 - '^'

data/lib/stringex/unidecoder_data/xfb.yml

@@ -31,7 +31,7 @@
 - yi
 - ''
 - ay
-- '`'
+- "'"
 - ''
 - d
 - h

data/lib/stringex/unidecoder_data/xff.yml

@@ -63,7 +63,7 @@
 - ']'
 - '^'
 - _
-- '`'
+- "'"
 - a
 - b
 - c

data/lib/stringex/version.rb

@@ -0,0 +1,8 @@
+module Stringex
+  module Version
+    MAJOR = 1
+    MINOR = 5
+    PATCH = 0
+    STRING = "#{MAJOR}.#{MINOR}.#{PATCH}"
+  end
+end

data/locales/da.yml

@@ -0,0 +1,73 @@
+# NOTE: Some translation keys make use of matches from regular expressions
+# to manipulate whitespace and order. Please consult the source code for
+# Stringex::Localization::ConversionExpressions to see what those
+# regular expressions look like if you need to manipulate the order
+# differently than the usage below.
+da:
+  stringex:
+    characters:
+      and: og
+      at: snabel-a
+      divide: divideret med
+      degrees: grader
+      dot: \1 punktum \2
+      ellipsis: prik prik prik
+      equals: lig med
+      number: nummer
+      percent: procent
+      plus: plus
+      slash: skråstreg
+      star: stjerne
+    currencies:
+      dollars: \1 dollars
+      dollars_cents: \1 dollars \2 cents
+      pounds: \1 pund
+      pounds_pence: \1 pund \2 pence
+      euros: \1 euro
+      euros_cents: \1 euro \2 cent
+      yen: \1 yen
+    html_entities:
+      amp: and
+      cent: " cents"
+      copy: (c)
+      deg: " grader "
+      divide: " divideret med "
+      double_quote: '"'
+      ellipsis: "..."
+      en_dash: "-"
+      em_dash: "--"
+      frac14: en fjerdedel
+      frac12: halv
+      frac34: tre fjerdedele
+      gt: ">"
+      lt: <
+      nbsp: " "
+      pound: " pund "
+      reg: (r)
+      single_quote: "'"
+      times: x
+      trade: (tm)
+      yen: " yen "
+    vulgar_fractions:
+      half: halv
+      one_third: en tredjedel
+      two_thirds: to tredjedele
+      one_fourth: en fjerdedel
+      three_fourths: tre fjerdedele
+      one_fifth: en femtedel
+      two_fifths: to femtedele
+      three_fifths: tre femtedele
+      four_fifths: fire femtedele
+      one_sixth: en sjettedel
+      five_sixths: fem sjettedele
+      one_eighth: en ottendedel
+      three_eighths: tre ottendedele
+      five_eighths: fem ottendedele
+      seven_eighths: syv ottendedele
+    transliterations:
+      Æ: AE
+      Ø: OE
+      Å: AA
+      æ: ae
+      ø: oe
+      å: aa

data/locales/en.yml

@@ -0,0 +1,66 @@
+# NOTE: Some translation keys make use of matches from regular expressions
+# to manipulate whitespace and order. Please consult the source code for
+# Stringex::Localization::ConversionExpressions to see what those
+# regular expressions look like if you need to manipulate the order
+# differently than the usage below.
+en:
+  stringex:
+    characters:
+      and: and
+      at: at
+      divide: divided by
+      degrees: degrees
+      dot: \1 dot \2
+      ellipsis: dot dot dot
+      equals: equals
+      number: number
+      percent: percent
+      plus: plus
+      slash: slash
+      star: star
+    currencies:
+      dollars: \1 dollars
+      dollars_cents: \1 dollars \2 cents
+      pounds: \1 pounds
+      pounds_pence: \1 pounds \2 pence
+      euros: \1 euros
+      euros_cents: \1 euros \2 cents
+      yen: \1 yen
+    html_entities:
+      amp: and
+      cent: " cents"
+      copy: (c)
+      deg: " degrees "
+      divide: " divided by "
+      double_quote: '"'
+      ellipsis: "..."
+      en_dash: "-"
+      em_dash: "--"
+      frac14: one fourth
+      frac12: half
+      frac34: three fourths
+      gt: ">"
+      lt: <
+      nbsp: " "
+      pound: " pounds "
+      reg: (r)
+      single_quote: "'"
+      times: x
+      trade: (tm)
+      yen: " yen "
+    vulgar_fractions:
+      half: half
+      one_third: one third
+      two_thirds: two thirds
+      one_fourth: one fourth
+      three_fourths: three fourths
+      one_fifth: one fifth
+      two_fifths: two fifths
+      three_fifths: three fifths
+      four_fifths: four fifths
+      one_sixth: one sixth
+      five_sixths: five sixths
+      one_eighth: one eighth
+      three_eighths: three eighths
+      five_eighths: five eighths
+      seven_eighths: seven eighths