babosa 0.3.10 → 1.0.4

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 7878565d1bfb436b7110d42e81dff1eb589f86e10e0919ded4b2de695784fae3
+  data.tar.gz: f6f3e7cc2b4876a940ec66fa1895f9cd3390526c62cebc888110494b72d77fe5
+SHA512:
+  metadata.gz: 6ea0ff964d688d9ca29710da13207c12d49509c13d72f8198a33d38141f7f6ad39b5792f5937a94a44b3976dcd68b24233c11b3418dc9d100a170caa799404ed
+  data.tar.gz: 1b37fd01a1907f244e112171da5dd942105181b860e6dc05ede3e1798bfdf1e50e8543b69757109dc9bd7dfddecb6ba2fbec2b59f38843223052c559f085490e

data/Changelog.md

@@ -0,0 +1,107 @@
+# Babosa Changelog
+
+## 1.0.4
+
+* Fix nil being cast to frozen string (https://github.com/norman/babosa/pull/52)
+
+## 1.0.3
+
+* Fix Active Support 6 deprecations (https://github.com/norman/babosa/pull/50)
+
+## 1.0.2
+
+* Fix regression in ActiveSupport UTF8 proxy.
+
+## 1.0.1
+
+* Fix error with tidy_bytes on Rubinius.
+* Simplify Active Support UTF8 proxy.
+* Fix `allow_bangs` argument to to_ruby_method being silently ignored.
+* Raise error when generating an impossible Ruby method name.
+
+## 1.0.0
+
+* Adopt semantic versioning.
+* When using Active Support, require 3.2 or greater.
+* Require Ruby 2.0 or greater.
+* Fix Ruby warnings.
+* Improve support for Ukrainian.
+* Support some additional punctuation characters used by Chinese and others.
+* Add Polish spec.
+* Use native Unicode normalization on Ruby 2.2 in UTF8::DumbProxy.
+* Invoke Ruby-native upcase/downcase in UTF8::DumbProxy.
+* Proxy `tidy_bytes` method to Active Support when possible.
+* Remove SlugString constant.
+
+## 0.3.11
+
+*  Add support for Vietnamese.
+
+## 0.3.10
+
+*  Fix Macedonian "S/S". Don't `include JRuby` unnecessarily.
+
+## 0.3.9
+
+* Add missing Greek vowels with diaeresis.
+
+## 0.3.8
+
+* Correct and improve Macedonian support.
+
+## 0.3.7
+
+* Fix compatibility with Ruby 1.8.7.
+* Add Swedish support.
+
+## 0.3.6
+
+* Allow multiple transliterators.
+* Add Greek support.
+
+## 0.3.5
+
+* Don't strip underscores from identifiers.
+
+## 0.3.4
+
+* Add Romanian support.
+
+## 0.3.3
+
+* Add Norwegian support.
+
+## 0.3.2
+
+* Improve Macedonian support.
+
+## 0.3.1
+
+* Small fixes to Cyrillic.
+
+## 0.3.0
+
+* Cyrillic support.
+* Improve support for various Unicode spaces and dashes.
+
+## 0.2.2
+
+* Fix for "smart" quote handling.
+
+## 0.2.1
+
+* Implement #empty? for compatiblity with Active Support's #blank?.
+
+## 0.2.0
+
+* Add support for Danish.
+* Add method to generate Ruby identifiers.
+* Improve performance.
+
+## 0.1.1
+
+* Add support for Serbian.
+
+## 0.1.0
+
+* Initial extraction from FriendlyId.

data/README.md

@@ -218,8 +218,8 @@ Babosa can be installed via Rubygems:
 
 You can get the source code from its [Github repository](http://github.com/norman/babosa).
 
-Babosa is tested to be compatible with Ruby 1.8.7-2.0.0, JRuby 1.4+, and
-Rubinius 1.0+ It's probably compatible with other Rubies as well.
+Babosa is tested to be compatible with Ruby 2.x, JRuby 1.7+, and
+Rubinius 2.x It's probably compatible with other Rubies as well.
 
 ## Reporting bugs
 
@@ -239,6 +239,8 @@ tracker](http://github.com/norman/babosa/issues).
 
 Many thanks to the following people for their help:
 
+* [Dmitry A. Ilyashevich](https://github.com/dmitry-ilyashevich) - Deprecation fixes
+* [anhkind](https://github.com/anhkind) - Vietnamese support
 * [Martins Zakis](https://github.com/martins) - Bug fixes
 * [Vassilis Rodokanakis](https://github.com/vrodokanakis) - Greek support
 * [Peco Danajlovski](https://github.com/Vortex) - Macedonian support
@@ -254,26 +256,6 @@ Many thanks to the following people for their help:
 * [Molte Emil Strange Andersen](https://github.com/molte) - Danish support
 * [Milan Dobrota](https://github.com/milandobrota) - Serbian support
 
-
-## Changelog
-
-* 0.3.10 - Fixed Macedonian "S/S". Don't `include JRuby` unnecessarily.
-* 0.3.9 - Added missing Greek vowels with diaeresis.
-* 0.3.8 - Correct and improve Macedonian support.
-* 0.3.7 - Fix compatibility with Ruby 1.8.7. Add Swedish support.
-* 0.3.6 - Allow multiple transliterators. Add Greek support.
-* 0.3.5 - Don't strip underscores from identifiers.
-* 0.3.4 - Add Romanian support.
-* 0.3.3 - Add Norwegian support.
-* 0.3.2 - Improve Macedonian support.
-* 0.3.1 - Small fixes to Cyrillic.
-* 0.3.0 - Cyrillic support. Improve support for various Unicode spaces and dashes.
-* 0.2.2 - Fix for "smart" quote handling.
-* 0.2.1 - Implement #empty? for compatiblity with Active Support's #blank?.
-* 0.2.0 - Added support for Danish. Added method to generate Ruby identifiers. Improved performance.
-* 0.1.1 - Added support for Serbian.
-* 0.1.0 - Initial extraction from FriendlyId.
-
 ## Copyright
 
 Copyright (c) 2010-2013 Norman Clarke
@@ -294,4 +276,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+SOFTWARE.

data/lib/babosa.rb

@@ -9,23 +9,6 @@ class String
     Babosa::Identifier.new self
   end
   alias to_slug to_identifier
-
-  # Compatibility with 1.8.6
-  if !public_method_defined? :bytesize
-    def bytesize
-      unpack("C*").length
-    end
-  end
-
-  # Define unless Active Support has already added this method.
-  if !public_method_defined? :classify
-    # Convert from underscores to class name. E.g.:
-    #     hello_world => HelloWorld
-    def classify
-      split("_").map {|a| a.gsub(/\b('?[a-z])/) { $1.upcase }}.join
-    end
-  end
-
 end
 
 require "babosa/transliterator/base"

data/lib/babosa/identifier.rb

@@ -30,12 +30,14 @@ module Babosa
   # @see http://www.utf8-chartable.de/unicode-utf8-table.pl?utf8=dec Unicode character table
   class Identifier
 
+    Error = Class.new(StandardError)
+
     attr_reader :wrapped_string
     alias to_s wrapped_string
 
     @@utf8_proxy = if Babosa.jruby15?
       UTF8::JavaProxy
-    elsif defined? Unicode
+    elsif defined? Unicode::VERSION
       UTF8::UnicodeProxy
     elsif defined? ActiveSupport
       UTF8::ActiveSupportProxy
@@ -44,13 +46,13 @@ module Babosa
     end
 
     # Return the proxy used for UTF-8 support.
-    # @see Babosa::UTF8::UTF8Proxy
+    # @see Babosa::UTF8::Proxy
     def self.utf8_proxy
       @@utf8_proxy
     end
 
     # Set a proxy object used for UTF-8 support.
-    # @see Babosa::UTF8::UTF8Proxy
+    # @see Babosa::UTF8::Proxy
     def self.utf8_proxy=(obj)
       @@utf8_proxy = obj
     end
@@ -100,16 +102,17 @@ module Babosa
     #   string.transliterate                 # => "¡Feliz ano!"
     #   string.transliterate :spanish        # => "¡Feliz anio!"
     #
-    # You can modify the built-in approximations, or add your own:
+    # The approximations are an array, which you can modify if you choose:
     #
     #   # Make Spanish use "nh" rather than "nn"
-    #   Babosa::Characters.add_approximations(:spanish, "ñ" => "nh")
+    #   Babosa::Transliterator::Spanish::APPROXIMATIONS["ñ"] = "nh"
     #
     # Notice that this method does not simply convert to ASCII; if you want
     # to remove non-ASCII characters such as "¡" and "¿", use {#to_ascii!}:
     #
     #   string.transliterate!(:spanish)       # => "¡Feliz anio!"
     #   string.transliterate!                 # => "¡Feliz anio!"
+    #
     # @param *args <Symbol>
     # @return String
     def transliterate!(*kinds)
@@ -142,13 +145,8 @@ module Babosa
     # @param Options
     # @return String
     def normalize!(options = nil)
-      # Handle deprecated usage
-      if options == true
-        warn "#normalize! now takes a hash of options rather than a boolean"
-        options = default_normalize_options.merge(:to_ascii => true)
-      else
-        options = default_normalize_options.merge(options || {})
-      end
+      options = default_normalize_options.merge(options || {})
+
       if translit_option = options[:transliterate]
         if translit_option != true
           transliterate!(*translit_option)
@@ -168,10 +166,14 @@ module Babosa
     # Normalize a string so that it can safely be used as a Ruby method name.
     def to_ruby_method!(allow_bangs = true)
       leader, trailer = @wrapped_string.strip.scan(/\A(.+)(.)\z/).flatten
+      leader          = leader.to_s.dup
+      trailer         = trailer.to_s.dup
       if allow_bangs
-        trailer.downcase.gsub!(/[^a-z0-9!=\\\\?]/, '')
+        trailer.downcase!
+        trailer.gsub!(/[^a-z0-9!=\\?]/, '')
       else
-        trailer.downcase.gsub!(/[^a-z0-9]/, '')
+        trailer.downcase!
+        trailer.gsub!(/[^a-z0-9]/, '')
       end
       id = leader.to_identifier
       id.transliterate!
@@ -180,6 +182,9 @@ module Babosa
       id.word_chars!
       id.clean!
       @wrapped_string = id.to_s + trailer
+      if @wrapped_string == ""
+        raise Error, "Input generates impossible Ruby method name"
+      end
       with_separators!("_")
     end
 
@@ -285,7 +290,4 @@ module Babosa
       id
     end
   end
-
-  # Identifier is aliased as SlugString to support older versions of FriendlyId.
-  SlugString = Identifier
 end

data/lib/babosa/transliterator/base.rb

@@ -10,6 +10,7 @@ module Babosa
     autoload :Cyrillic,   "babosa/transliterator/cyrillic"
     autoload :Danish,     "babosa/transliterator/danish"
     autoload :German,     "babosa/transliterator/german"
+    autoload :Hindi,      "babosa/transliterator/hindi"
     autoload :Latin,      "babosa/transliterator/latin"
     autoload :Macedonian, "babosa/transliterator/macedonian"
     autoload :Norwegian,  "babosa/transliterator/norwegian"
@@ -20,13 +21,15 @@ module Babosa
     autoload :Swedish,    "babosa/transliterator/swedish"
     autoload :Ukrainian,  "babosa/transliterator/ukrainian"
     autoload :Greek,      "babosa/transliterator/greek"
+    autoload :Vietnamese, "babosa/transliterator/vietnamese"
+    autoload :Turkish,    "babosa/transliterator/turkish"
 
     def self.get(symbol)
-      const_get(symbol.to_s.classify)
+      class_name = symbol.to_s.split("_").map {|a| a.gsub(/\b('?[a-z])/) { $1.upcase }}.join
+      const_get(class_name)
     end
 
     class Base
-
       include Singleton
 
       APPROXIMATIONS = {
@@ -38,7 +41,6 @@ module Babosa
         "–" => "-",
         "—" => "-",
         "―" => "-",
-        "―" => "-",
         "‘" => "'",
         "‛" => "'",
         "“" => '"',
@@ -46,6 +48,19 @@ module Babosa
         "„" => '"',
         "‟" => '"',
         '’' => "'",
+        '，' => ",",
+        '。' => ".",
+        '！' => "!",
+        '？' => '?',
+        '、' => ',',
+        '（' => '(',
+        '）' => ')',
+        '【' => '[',
+        '】' => ']',
+        '；' => ';',
+        '：' => ':',
+        '《' => '<',
+        '》' => '>',
         # various kinds of space characters
         "\xc2\xa0"     => " ",
         "\xe2\x80\x80" => " ",
@@ -86,6 +101,7 @@ module Babosa
         @approximations[codepoint]
       end
 
+      # Transliterates a string.
       def transliterate(string)
         string.unpack("U*").map {|char| self[char] || char}.flatten.pack("U*")
       end

data/lib/babosa/transliterator/hindi.rb

@@ -0,0 +1,137 @@
+# encoding: utf-8
+module Babosa
+  module Transliterator
+    class Hindi < Base
+      APPROXIMATIONS = {
+        "ऀ" => "n",
+        "ँ" => "n",
+        "ं" => "n",
+        "ः" => "h",
+        "ऄ" => "a",
+        "अ" => "a",
+        "आ" => "aa",
+        "इ" => "i",
+        "ई" => "ii",
+        "उ" => "u",
+        "ऊ" => "uu",
+        "ऋ" => "ri",
+        "ऌ" => "lri",
+        "ऍ" => "e",
+        "ऎ" => "e",
+        "ए" => "e",
+        "ऐ" => "ei",
+        "ऑ" => "o",
+        "ऒ" => "o",
+        "ओ" => "o",
+        "औ" => "ou",
+        "क" => "k",
+        "ख" => "kh",
+        "ग" => "g",
+        "घ" => "gh",
+        "ङ" => "d",
+        "च" => "ch",
+        "छ" => "chh",
+        "ज" => "j",
+        "झ" => "jh",
+        "ञ" => "ny",
+        "ट" => "tt",
+        "ठ" => "tth",
+        "ड" => "dd",
+        "ढ" => "ddh",
+        "ण" => "nn",
+        "त" => "t",
+        "थ" => "th",
+        "द" => "d",
+        "ध" => "dh",
+        "न" => "n",
+        "ऩ" => "nnn",
+        "प" => "p",
+        "फ" => "ph",
+        "ब" => "b",
+        "भ" => "bh",
+        "म" => "m",
+        "य" => "y",
+        "र" => "r",
+        "ऱ" => "rr",
+        "ल" => "l",
+        "ळ" => "ll",
+        "ऴ" => "ll",
+        "व" => "v",
+        "श" => "sh",
+        "ष" => "ss",
+        "स" => "s",
+        "ह" => "h",
+        "ऺ" => "oe",
+        "ऻ" => "ooe",
+        "़" => "",
+        "ऽ" => "-",
+        "ा" => "aa",
+        "ि" => "i",
+        "ी" => "ii",
+        "ु" => "u",
+        "ू" => "uu",
+        "ृ" => "r",
+        "ॄ" => "rr",
+        "ॅ" => "e",
+        "ॆ" => "e",
+        "े" => "e",
+        "ै" => "ai",
+        "ॉ" => "o",
+        "ॊ" => "o",
+        "ो" => "o",
+        "ौ" => "au",
+        "्" => "",
+        "ॎ" => "e",
+        "ॏ" => "aw",
+        "ॐ" => "om",
+        "॑" => "",
+        "॒" => "_",
+        "॓" => "",
+        "॔" => "",
+        "ॕ" => "ee",
+        "ॖ" => "ue",
+        "ॗ" => "uue",
+        "क़" => "q",
+        "ख़" => "khh",
+        "ग़" => "ghh",
+        "ज़" => "za",
+        "ड़" => "dddh",
+        "ढ़" => "rh",
+        "फ़" => "f",
+        "य़" => "yy",
+        "ॠ" => "rri",
+        "ॡ" => "lr",
+        "ॢ" => "l",
+        "ॣ" => "l",
+        "।" => ".",
+        "॥" => "..",
+        "०" => "0",
+        "१" => "1",
+        "२" => "2",
+        "३" => "3",
+        "४" => "4",
+        "५" => "5",
+        "६" => "6",
+        "७" => "7",
+        "८" => "8",
+        "९" => "9",
+        "॰" => ".",
+        "ॱ" => ".",
+        "ॲ" => "a",
+        "ॳ" => "oe",
+        "ॴ" => "ooe",
+        "ॵ" => "aw",
+        "ॶ" => "ue",
+        "ॷ" => "uue",
+        "ॸ" => "dd",
+        "ॹ" => "zh",
+        "ॺ" => "y",
+        "ॻ" => "gg",
+        "ॼ" => "jj",
+        "ॽ" => "?",
+        "ॾ" => "ddd",
+        "ॿ" => "bb"
+      }
+    end
+  end
+end