unicode 0.4.3 → 0.4.3.1

data/Rakefile

@@ -0,0 +1,23 @@
+require "rake/clean"
+require "rake/extensiontask"
+require "rubygems/package_task"
+
+CLEAN << "pkg" << "tmp" << "lib/unicode"
+
+gem_spec = eval(File.read(File.expand_path("../unicode.gemspec", __FILE__)))
+
+Gem::PackageTask.new(gem_spec) {|pkg|}
+
+Rake::ExtensionTask.new('unicode_native', gem_spec) do |ext|
+  ext.cross_compile = true
+  ext.cross_platform = ['x86-mingw32', 'x86-mswin32-60']
+  ext.ext_dir = "ext/unicode"
+  ext.lib_dir = "lib/unicode"
+end
+
+desc "Build native gems for Windows"
+task :windows_gem => :clean do
+  ENV["RUBY_CC_VERSION"] = "1.8.7:1.9.3"
+  sh "rake cross compile"
+  sh "rake cross native gem"
+end

data/ext/unicode/extconf.rb

@@ -0,0 +1,3 @@
+require 'mkmf'
+
+create_makefile("unicode/unicode_native")

data/{unicode.c → ext/unicode/unicode.c}

@@ -1230,7 +1230,7 @@ unicode_get_text_elements(VALUE obj, VALUE str)
 }
 
 void
-Init_unicode()
+Init_unicode_native()
 {
   int i;
 

data/lib/unicode.rb

@@ -0,0 +1,6 @@
+begin
+  RUBY_VERSION =~ /(\d+.\d+)/
+  require "unicode/#{$1}/unicode_native"
+rescue LoadError
+  require 'unicode/unicode_native'
+end

data/test/test.rb

@@ -0,0 +1,69 @@
+#! /usr/local/bin/ruby -KU
+# -*- coding: utf-8 -*-
+
+require 'unicode'
+
+## dump Unicode string
+class String
+  def udump
+    ustr = self.unpack("U*")
+    ret = []
+    ustr.each do |e|
+      if e.is_a?(Integer)
+        ret << "U+%04X" % e
+      else
+        ret << e
+      end
+    end
+    ret
+  end
+end
+
+
+print "Canonical decomposition vs compatibility decomposition\n"
+p Unicode::decompose("⑽ o\xef\xac\x83ce").udump
+p Unicode::decompose_compat("⑽ o\xef\xac\x83ce")
+
+print "Canonical equivalent vs Compatibility equivalent\n"
+p Unicode::strcmp("ｶﾞ", "ガ")
+p Unicode::strcmp("ガ", "ｶﾞ")
+p Unicode::strcmp_compat("ｶﾞ", "ガ")
+
+print "Decomposition/composition\n"
+p Unicode::normalize_D([0x63, 0x301, 0x327].pack("U*")).udump
+p Unicode::normalize_D([0x63, 0x327, 0x301].pack("U*")).udump
+p Unicode::normalize_D([0x107, 0x327].pack("U*")).udump
+p Unicode::normalize_D([0xe7, 0x301].pack("U*")).udump
+p Unicode::normalize_C([0x63, 0x301, 0x327].pack("U*")).udump
+p Unicode::normalize_C([0x63, 0x327, 0x301].pack("U*")).udump
+p Unicode::normalize_C([0x107, 0x327].pack("U*")).udump
+p Unicode::normalize_C([0xe7, 0x301].pack("U*")).udump
+
+print "Kana Normalization\n"
+p Unicode::normalize_D("ｶﾞガ").udump
+p Unicode::normalize_C("ｶﾞガ").udump
+p Unicode::normalize_KD("ｶﾞガ").udump
+p Unicode::normalize_KC("ｶﾞガ").udump
+
+print "Hangul\n"
+p "요시담".udump
+p Unicode::normalize_D("요시담").udump
+p Unicode::normalize_C("요시담").udump
+
+print "Composition Exclusion\n"
+print "   ANGSTROM SIGN [U+212B]\n"
+p Unicode::normalize_D([0x212b].pack("U")).udump
+p Unicode::normalize_C([0x212b].pack("U")).udump
+print "   LATIN CAPITAL LETTER A WITH RING ABOVE [U+00C5]\n"
+p Unicode::normalize_D([0x00c5].pack("U")).udump
+p Unicode::normalize_C([0x00c5].pack("U")).udump
+
+print "Case conversion\n"
+p Unicode::normalize_C(Unicode::upcase([0x63, 0x301, 0x327, 0xff41].pack("U*"))).udump
+p Unicode::normalize_C(Unicode::downcase([0x43, 0x301, 0x327, 0xff21].pack("U*"))).udump
+p Unicode::capitalize([0x1f1, 0x41, 0x61, 0xff21].pack("U*")).udump
+
+
+## Local variables:
+## coding: utf-8
+## End:

data/unicode.gemspec

@@ -0,0 +1,29 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{unicode}
+  s.version = "0.4.3.1"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = [%q{Yoshida Masato}]
+  s.date = %q{2012-08-07}
+  s.email = %q{yoshidam@yoshidam.net}
+  s.extensions = %w[ext/unicode/extconf.rb]
+  s.extra_rdoc_files = %w[README]
+  s.files = %w[
+    README Rakefile unicode.gemspec lib/unicode.rb
+    test/test.rb tools/README tools/mkunidata.rb tools/normtest.rb
+    ext/unicode/extconf.rb ext/unicode/unicode.c ext/unicode/unidata.map
+    ext/unicode/ustring.c ext/unicode/ustring.h ext/unicode/wstring.c ext/unicode/wstring.h
+  ]
+  s.homepage = %q{http://www.yoshidam.net/Ruby.html#unicode}
+  s.require_paths = %w[lib]
+  s.rubygems_version = %q{1.8.6}
+  s.summary = %q{Unicode normalization library.}
+  s.description = %q{Unicode normalization library.}
+
+  if s.respond_to? :specification_version then
+    s.specification_version = 3
+  end
+end
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unicode
 version: !ruby/object:Gem::Version
-  version: 0.4.3
+  version: 0.4.3.1
   prerelease: 
 platform: ruby
 authors:
@@ -15,27 +15,31 @@ description: Unicode normalization library.
 email: yoshidam@yoshidam.net
 executables: []
 extensions:
-- extconf.rb
+- ext/unicode/extconf.rb
 extra_rdoc_files:
 - README
 files:
-- extconf.rb
-- unicode.c
-- ustring.c
-- ustring.h
-- wstring.c
-- wstring.h
 - README
+- Rakefile
+- unicode.gemspec
+- lib/unicode.rb
+- test/test.rb
+- tools/README
 - tools/mkunidata.rb
 - tools/normtest.rb
-- tools/README
-- unidata.map
+- ext/unicode/extconf.rb
+- ext/unicode/unicode.c
+- ext/unicode/unidata.map
+- ext/unicode/ustring.c
+- ext/unicode/ustring.h
+- ext/unicode/wstring.c
+- ext/unicode/wstring.h
 homepage: http://www.yoshidam.net/Ruby.html#unicode
 licenses: []
 post_install_message: 
 rdoc_options: []
 require_paths:
-- .
+- lib
 required_ruby_version: !ruby/object:Gem::Requirement
   none: false
   requirements:

data/extconf.rb

@@ -1,3 +0,0 @@
-require 'mkmf'
-
-create_makefile("unicode")