forkforge 0.0.3

data/features/unicode_org.feature

@@ -0,0 +1,500 @@
+# encoding: utf-8
+
+Feature: UnicodeData.txt file is to be used locally until it’s absent
+	Scenario: Get all composed symbols
+		When we call all_character_decomposition_mapping on Forkforge::UnicodeData
+		Then the result count equals to 5721
+
+###############################################################################
+	@camel
+  Scenario: Camel to underscore function works
+    Given we have a string "CamelCasedString"
+    When we call "camel_to_underscore" method on Forkforge::Unicode
+    Then the result is "camel_cased_string"
+
+	@camel
+  Scenario: Underscore to camel function works
+    Given we have a string "underscore_old_school_string"
+    When we call "underscore_to_camel" method on Forkforge::Unicode
+    Then the result is "UnderscoreOldSchoolString"
+
+###############################################################################
+
+	@letter
+  Scenario: Get all specific letter: uppercase
+    When we call "uppercase" method on Forkforge::Letter
+    Then the result count equals to 1490
+     And the first item equals to "A"
+
+	@letter
+	Scenario: Get all specific letter: lowercase
+		When we call "lowercase" method on Forkforge::Letter
+		Then the result count equals to 1841
+		 And the first item equals to "a"
+
+	@letter
+	Scenario: Get all specific letter: titlecase
+		When we call "titlecase" method on Forkforge::Letter
+		Then the result count equals to 31
+		 And the first item equals to "Dž"
+
+	@letter
+	Scenario: Get all specific letter: modifier
+		When we call "modifier" method on Forkforge::Letter
+		Then the result count equals to 248
+		 And the first item equals to "ʰ"
+
+	@letter
+	Scenario: Get all specific letter: others
+		When we call "other" method on Forkforge::Letter
+		Then the result count equals to 13350
+		 And the first item equals to "ª"
+
+	@letter
+	Scenario: Get all codepoints for uppercased letters
+	  When we call uppercase_code_point on Forkforge::Letter
+	  Then we print first 10 results
+
+###############################################################################
+
+	@mark
+	Scenario: Get all specific marks: non-spacing
+		When we call "non_spacing" method on Forkforge::Mark
+		Then the result count equals to 1418
+		 And the first item equals to "̀"
+
+	@mark
+	Scenario: Get all specific marks: spacing combining
+		When we call "spacing_combining" method on Forkforge::Mark
+		Then the result count equals to 399
+		 And the first item equals to "ः"
+
+	@mark
+	Scenario: Get all specific marks: enclosing
+		When we call "enclosing" method on Forkforge::Mark
+		Then the result count equals to 13
+		 And the first item equals to "҈"
+
+###############################################################################
+
+	@number
+	Scenario: Get all specific numbers: decimal digit
+		When we call "decimal_digit" method on Forkforge::Number
+		Then the result count equals to 540
+		 And the first item equals to "0"
+
+	@number
+	Scenario: Get all specific numbers: letter
+		When we call "letter" method on Forkforge::Number
+		Then the result count equals to 236
+		 And the first item equals to "ᛮ"
+
+	@number
+	Scenario: Get all specific numbers: other
+		When we call "other" method on Forkforge::Number
+		Then the result count equals to 570
+		 And the first item equals to "²"
+
+###############################################################################
+
+	@punctuation
+	Scenario: Get all specific punctuation: connectors
+		When we call "connector" method on Forkforge::Punctuation
+		Then the result count equals to 10
+		 And the first item equals to "_"
+
+	@punctuation
+	Scenario: Get all specific punctuation: dashes
+		When we call "dash" method on Forkforge::Punctuation
+		Then the result count equals to 24
+		 And the first item equals to "-"
+
+	@punctuation
+	Scenario: Get all specific punctuation: opens
+		When we call "open" method on Forkforge::Punctuation
+		Then the result count equals to 75
+		 And the first item equals to "("
+
+	@punctuation
+	Scenario: Get all specific punctuation: closes
+		When we call "close" method on Forkforge::Punctuation
+		Then the result count equals to 73
+		 And the first item equals to ")"
+
+	@punctuation
+	Scenario: Get all specific punctuation: initial_quotes
+		When we call "initial_quote" method on Forkforge::Punctuation
+		Then the result count equals to 12
+		 And the first item equals to "«"
+
+	@punctuation
+	Scenario: Get all specific punctuation: final_quotes
+		When we call "final_quote" method on Forkforge::Punctuation
+		Then the result count equals to 10
+		 And the first item equals to "»"
+
+	@punctuation
+	Scenario: Get all specific punctuation: others
+		When we call "other" method on Forkforge::Punctuation
+		Then the result count equals to 484
+		 And the first item equals to "!"
+
+###############################################################################
+
+	@symbol
+	Scenario: Get all specific symbols: math
+		When we call "math" method on Forkforge::Symbol
+		Then the result count equals to 948
+		 And the first item equals to "+"
+
+	@symbol
+	Scenario: Get all specific symbols: currency
+		When we call "currency" method on Forkforge::Symbol
+		Then the result count equals to 52
+		 And the first item equals to "$"
+
+	@symbol
+	Scenario: Get all specific symbols: modifier
+		When we call "modifier" method on Forkforge::Symbol
+		Then the result count equals to 116
+		 And the first item equals to "^"
+
+	@symbol
+	Scenario: Get all specific symbols: other
+		When we call "other" method on Forkforge::Symbol
+		Then the result count equals to 5082
+		 And the first item equals to "¦"
+
+###############################################################################
+
+	@separator
+	Scenario: Get all specific separators: space
+		When we call "space" method on Forkforge::Separator
+		Then the result count equals to 17
+		 And the first item equals to " "
+
+	@separator
+	Scenario: Get all specific separators: line
+		When we call "line" method on Forkforge::Separator
+		Then the result count equals to 1
+		 And we print results
+
+	@separator
+	Scenario: Get all specific separators: paragraph
+		When we call "paragraph" method on Forkforge::Separator
+		Then the result count equals to 1
+		 And we print results
+
+###############################################################################
+
+	@other
+	Scenario: Get all specific others: control
+		When we call "control" method on Forkforge::Other
+		Then the result count equals to 65
+
+	@other
+	Scenario: Get all specific others: format
+		When we call "format" method on Forkforge::Other
+		Then the result count equals to 150
+		 And the first item equals to "­"
+
+	@other
+	Scenario: Get all specific others: surrogate
+		When we call "surrogate" method on Forkforge::Other
+		Then the result count equals to 6
+		 And we print results
+
+	@other
+	Scenario: Get all specific others: private use
+		When we call "private_use" method on Forkforge::Other
+		Then the result count equals to 6
+		 And we print results
+
+	@other
+	Scenario: Get all specific others: not assigned
+		When we call "not_assigned" method on Forkforge::Other
+		Then the result count equals to 0
+
+###############################################################################
+
+	@punctuation @connector
+	Scenario: Get all connectors with their names
+		When we call "connector_character_name" method on Forkforge::Punctuation
+		Then the result count equals to 10
+		 And the first item’s value equals to "LOW LINE"
+
+	@punctuation @connector
+	Scenario: Get all dashes with their names
+		When we call "dash_character_name" method on Forkforge::Punctuation
+		Then the result count equals to 24
+		 And the first item’s value equals to "HYPHEN-MINUS"
+
+###############################################################################
+
+  @languages
+	Scenario: Upcase function works properly on cyrillics
+    Given we have a cyrillic string "МАМА мыла РАМУ"
+    When the string is upcased
+    Then the result is "МАМА МЫЛА РАМУ"
+
+  # titlecase titleize every funcking letter!!
+  @languages
+	Scenario: Titlecase function works properly on cyrillics
+    Given we have a cyrillic string "МАМА мыла РАМУ"
+    When the string is titlecased
+    Then the result is "МАМА МЫЛА РАМУ"
+
+  @languages
+	Scenario: Downcase function works properly on cyrillics
+    Given we have a cyrillic string "МАМА мыла РАМУ"
+    When the string is downcased
+    Then the result is "мама мыла раму"
+
+	@languages
+  Scenario: Upcase function works properly on combined
+    Given we have a cyrillic string "naïve Álto Pàlo"
+    When the string is upcased
+    Then the result is "NAÏVE ÁLTO PÀLO"
+
+  @languages
+	Scenario: Upcase function works properly with Turkic (CAPITAL I WITH DOT)
+    Given we have a string "naïve istanbul"
+    When the string is upcased with language set to "tr"
+    Then the result is "NAİ̈VE İSTANBUL"
+
+  @languages
+	Scenario: Upcase function works properly with generic (CAPITAL I WITHOUT DOT)
+    Given we have a string "naïve istanbul"
+    When the string is upcased with language set to ""
+    Then the result is "NAÏVE ISTANBUL"
+
+  @languages
+	Scenario: Downcase function works properly with generic (SMALL I WITH DOT)
+    Given we have a string "NAÏVE ISTANBUL"
+    When the string is downcased with language set to ""
+    Then the result is "naïve istanbul"
+
+  @languages
+	Scenario: Print out known conditions
+    When we ask to print known conditions
+    Then we print results
+
+###############################################################################
+
+	@lookup
+	Scenario: Lookup symbols by name
+	  Given we have a pattern "RiNg AbOvE"
+	   When lookup is done with this pattern
+	   Then we print results
+
+	@lookup
+	Scenario: Lookup symbols by name
+	  Given we have a pattern "RING ABOVE"
+	   When lookup using all_character_name is done with this pattern
+	   Then we print first 2 results
+
+	@lookup
+	Scenario: Lookup symbols with tagged character_name
+	  Given we have a pattern looking like a tag
+	   When lookup using all_character_name is done with this pattern
+	   Then we print first 1 results
+
+	@lookup
+	Scenario: Lookup tag names using character_name
+	  Given we have a pattern looking like a tag
+	   When result is filtered to show tags
+		 Then the result count equals to 25
+	    And we print first 21 results
+
+	@lookup
+	Scenario: Lookup tags using character_name
+	  Given we have a pattern looking like a tag
+	   When result is filtered to show tagged characters
+		 Then the result count equals to 25
+	    And the result’s first element nested count is "65"
+
+	@lookup
+	Scenario: Lookup tags using meta method
+	  Given we have a pattern looking like a tag
+	   When result is set to response from "control" function call
+		 Then the result count equals to 65
+	    And we print first 1 results
+
+	@lookup
+	Scenario: Print info on symbol
+	  Given we have a symbol "〷"
+	   When we retrieve it’s info
+		 Then we print results
+		  And the result is "IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL"
+
+	@lookup
+	Scenario: Print info on symbol on it’s codebase
+	  Given we have a symbol with codebase "0x3037"
+	   When we retrieve it’s info
+		 Then we print results
+			And the result is "IDEOGRAPHIC TELEGRAPH LINE FEED SEPARATOR SYMBOL"
+
+###############################################################################
+
+  @tag
+	Scenario: Tag class accepts strings with tag delimiters properly
+    Given we have a string "<font>"
+     When we construct Tag object against it
+     Then both sym and tag have correct values
+
+  @tag
+	Scenario: Tag class accepts strings without tag delimiters properly
+    Given we have a string "font"
+     When we construct Tag object against it
+     Then both sym and tag have correct values
+
+  @tag
+	Scenario: Tag class rejects strings with improper tags
+    Given we have a string "ghgh"
+     When we construct Tag object against it
+     Then both sym and tag have nil values
+
+	@tag
+  Scenario: Decompose symbols
+    Given we have a string "Barçelona Niños"
+     When we decompose it
+     Then we print results
+		  And the result is "Barçelona Niños"
+
+  @tag
+	Scenario: Decompose symbols with <font>
+    Given we have a string "ℂool"
+     When we decompose it
+     Then we print results
+			And the result is "Cool"
+
+  @tag
+	Scenario: Decompose symbols with <font>
+    Given we have a string "ℂool"
+     When we decompose it with circle tag only
+     Then we print results
+			And the result is "ℂool"
+
+  @tag
+	Scenario: Add custom decomposition symbols
+    Given we have a string "Мáма"
+     When we add custom decomposition rule
+      And we decompose it
+     Then we print results
+
+###############################################################################
+
+  @compose
+	Scenario: Composing digit with circle
+    Given we have a string "1"
+     When we compose input to "circle"
+     Then the result is "①"
+      And we print results
+
+	@compose
+  Scenario: Composing letter with font
+    Given we have a string "a"
+     When we compose input to "font"
+     Then the result is "𝐚,𝑎,𝒂,𝒶,𝓪,𝔞,𝕒,𝖆,𝖺,𝗮,𝘢,𝙖,𝚊"
+      And we print results
+
+  @compose
+	Scenario: Composing letter with wide
+    Given we have a string "a"
+     When we compose input to "wide"
+     Then the result is "ａ"
+      And we print results
+
+  @compose
+	Scenario: Composing letter with super
+    Given we have a string "a"
+     When we compose input to "super"
+     Then we print results
+      And the result is "ª,ᵃ"
+
+  @compose
+	Scenario: Composing letter with sub
+    Given we have a string "a"
+     When we compose input to "sub"
+     Then we print results
+      And the result is "ₐ"
+
+  @compose
+	Scenario: Composing letter with vertical
+    Given we have a string "?"
+     When we compose input to "vertical"
+     Then we print results
+      And the result is "︖"
+
+  @compose
+	Scenario: Composing letter with small
+    Given we have a string "?"
+     When we compose input to "small"
+     Then we print results
+      And the result is "﹖"
+
+  @compose
+	Scenario: Composing letter with compat
+    Given we have a string "µ"
+     When we compose input to "compat"
+     Then we print results
+      And the result is "µ"
+
+###############################################################################
+
+	@compose @complex
+	Scenario: Composing text with wide
+		Given we have a string "Hola, Barçelona!"
+		When we compose input to "wide"
+		Then we print results
+			And the result is "Ｈ,ｏ,ｌ,ａ,，,　,Ｂ,ａ,ｒ,ç,ｅ,ｌ,ｏ,ｎ,ａ,！"
+
+	@compose @complex
+	Scenario: Composing text with wide (direct call)
+		Given we have a string "Hola, Barçelona!"
+		When we widify input
+		Then we print results
+			And the result is "Ｈｏｌａ，　Ｂａｒｃ̧ｅｌｏｎａ！"
+
+	@compose @complex
+	Scenario: Composing text with circle (direct call)
+		Given we have a string "Hola, Barçelona!"
+		When we circlefy input
+		Then we print results
+			And the result is "Ⓗⓞⓛⓐ, Ⓑⓐⓡⓒ̧ⓔⓛⓞⓝⓐ!"
+
+###############################################################################
+
+  @lookup @complex
+	Scenario: Code points method missing works on latin letters
+    When we call "math" method on Forkforge::CodePoints for "b"
+    Then we print results
+     And the result to string is "𝐛𝑏𝒃𝒷𝓫𝔟𝕓𝖇𝖻𝗯𝘣𝙗𝚋"
+
+	@lookup @complex
+  Scenario: Code points method missing works on strings
+    When we call "math" method on Forkforge::CodePoints for "abc"
+    Then we print results
+     And the result to string is "𝐚𝐛𝐜𝑎𝑏𝑐𝒂𝒃𝒄𝒶𝒷𝒸𝓪𝓫𝓬𝔞𝔟𝔠𝕒𝕓𝕔𝖆𝖇𝖈𝖺𝖻𝖼𝗮𝗯𝗰𝘢𝘣𝘤𝙖𝙗𝙘𝚊𝚋𝚌"
+
+	@lookup @complex
+	Scenario: Code points method missing chained works on strings
+    When we call "math_fraktur_bold" method on Forkforge::CodePoints for "abc"
+    Then we print results
+     And the result to string is "𝖆𝖇𝖈"
+
+###############################################################################
+
+	@monkey
+	Scenario: String monkeypatches (wide)
+		Given we have a string "CamelCasedString"
+		When the string is directly widefied
+		Then the result is "ＣａｍｅｌＣａｓｅｄＳｔｒｉｎｇ"
+
+	@monkey
+	Scenario: String monkeypatches (upcase on cyrillics)
+		Given we have a string "МАМА мыла РАМУ"
+		When the string is directly upcased
+		Then the result is "МАМА МЫЛА РАМУ"
+
+###############################################################################

data/forkforge.gemspec

@@ -0,0 +1,33 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'forkforge/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "forkforge"
+  spec.version       = Forkforge::VERSION
+  spec.authors       = ["Alexei Matyushkin"]
+  spec.email         = ["am@mudasobwa.ru"]
+  spec.summary       = %q{Unicode handling library}
+  spec.description   = %Q{
+    Pure ruby implementation of Unicode manipulations as by Consortium.
+    Includes: languages-specific uppercase/lowercase, composition, decomposition and more.
+  }
+  spec.homepage      = "http://forkforge.com"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.5"
+  spec.add_development_dependency "rake", '~> 0'
+  spec.add_development_dependency "pry", '~> 0'
+  spec.add_development_dependency "pry-rescue", '~> 0'
+  spec.add_development_dependency "awesome_print", '~> 0'
+  spec.add_development_dependency "rspec", '~> 0'
+  spec.add_development_dependency 'yard', '~> 0'
+  spec.add_development_dependency 'cucumber', '~> 0'
+  spec.add_development_dependency 'yard-cucumber', '~> 0'
+end

data/lib/forkforge/category.rb

@@ -0,0 +1,165 @@
+# encoding: utf-8
+
+require 'forkforge/internal/code_point'
+require 'forkforge/internal/unicode_data'
+
+module Forkforge
+  module Category
+    # Letter::all_raw | Letter::uppercase_raw | Letter::uppercase 'Alexei' # ⇒ 'A'
+    # Letter::uppercase_code_point | Mark::non_spacing_bidirectional_category
+    def self.included base
+      base.const_get(:TYPES).each { |type|
+        base.class_eval %Q{
+          def #{type.last}_raw
+            @@#{type.last} ||= Forkforge::UnicodeData::all_general_category /#{type.first}/
+          end
+          def is_#{type.last} s
+            UnicodeData::infos(s).inject(true) { |memo, kv|
+              memo &&= kv[:general_category] == "#{type.first}"
+            }
+          end
+          def #{type.last} s = nil
+            @@#{type.last}_array ||= #{type.last}_raw.map { |k, v| Forkforge::UnicodeData::to_char k }
+            s.respond_to?(:scan) ? s.scan(Regexp.new(@@#{type.last}_array.join '|')) : @@#{type.last}_array
+          end
+        }
+        CodePoint::UNICODE_FIELDS.each { |method|
+          base.class_eval %Q{
+            def #{type.last}_#{method}
+              @@#{type.last}_#{method} ||= #{type.last}_raw.map { |k, v|
+                [ Forkforge::UnicodeData::to_char(k), Forkforge::UnicodeData::get_#{method}(k) ]
+              }.to_h
+            end
+          }
+        }
+      }
+      base.extend base
+    end
+  end
+
+=begin
+  Lu  Letter, Uppercase
+  Ll  Letter, Lowercase
+  Lt  Letter, Titlecase
+  Lm  Letter, Modifier
+  Lo  Letter, Other
+  LC  Letter, Cased (combining)
+=end
+  module Letter
+    TYPES = [
+      ['L.?', :all],
+      ['Lu', :uppercase],
+      ['Ll', :lowercase],
+      ['Lt', :titlecase],
+      ['Lm', :modifier],
+      ['Lo', :other],
+      ['L[Cult]', :cased]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Mn  Mark, Non-Spacing
+  Mc  Mark, Spacing Combining
+  Me  Mark, Enclosing
+=end
+  module Mark
+    TYPES = [
+      ['M.?', :all],
+      ['Mn', :non_spacing],
+      ['Mc', :spacing_combining],
+      ['Me', :enclosing]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Nd  Number, Decimal Digit
+  Nl  Number, Letter
+  No  Number, Other
+=end
+  module Number
+    TYPES = [
+      ['N.?', :all],
+      ['Nd', :decimal_digit],
+      ['Nl', :letter],
+      ['No', :other]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Pc  Punctuation, Connector
+  Pd  Punctuation, Dash
+  Ps  Punctuation, Open
+  Pe  Punctuation, Close
+  Pi  Punctuation, Initial quote (may behave like Ps or Pe depending on usage)
+  Pf  Punctuation, Final quote (may behave like Ps or Pe depending on usage)
+  Po  Punctuation, Other
+=end
+  module Punctuation
+    TYPES = [
+      ['P.?', :all],
+      ['Pc', :connector],
+      ['Pd', :dash],
+      ['Ps', :open],
+      ['Pe', :close],
+      ['Pi', :initial_quote], # (may behave like Ps or Pe depending on usage)
+      ['Pf', :final_quote], # (may behave like Ps or Pe depending on usage)
+      ['Po', :other]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Sm  Symbol, Math
+  Sc  Symbol, Currency
+  Sk  Symbol, Modifier
+  So  Symbol, Other
+=end
+  module Symbol
+    TYPES = [
+      ['S.?', :all],
+      ['Sm', :math],
+      ['Sc', :currency],
+      ['Sk', :modifier],
+      ['So', :other]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Zs  Separator, Space
+  Zl  Separator, Line
+  Zp  Separator, Paragraph
+=end
+  module Separator
+    TYPES = [
+      ['Z.?', :all],
+      ['Zs', :space],
+      ['Zl', :line],
+      ['Zp', :paragraph]
+    ]
+    include Forkforge::Category
+  end
+
+=begin
+  Cc  Other, Control
+  Cf  Other, Format
+  Cs  Other, Surrogate
+  Co  Other, Private Use
+  Cn  Other, Not Assigned (no characters in the file have this property)
+=end
+  module Other
+    TYPES = [
+      ['C.?', :all],
+      ['Cc', :control],
+      ['Cf', :format],
+      ['Cs', :surrogate],
+      ['Co', :private_use],
+      ['Cn', :not_assigned] # no characters in the file have this property
+    ]
+    include Forkforge::Category
+  end
+
+end