regexp_optimized_union 0.1.2 → 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 45abdaf8017a48216c2d3de78c008aef03e54a64
+  data.tar.gz: 90f26948c74bdcbc769f3f827fb0d601b533999b
+SHA512:
+  metadata.gz: 600fdd924917e83e8ce77067d3e28f83a1f219820c4a91967beb46854ac26d1c92cde44aca97c3d1ae19119d496be5e6a0e47089fcc42deb596bc1f26e3ebc75
+  data.tar.gz: 000e8b87b88482f6d7b3309ca85322f13dd4bce5c39b948680a7e38fd962bbbf64512fc4dbae99d47b95d3006fbb22fcb1b05761a272b73cf07f3ae9e6908d41

data/changes

@@ -0,0 +1,3 @@
+0.2.0
+  - Fix error for UTF-8 string
+  - Drop support for Ruby <= 1.8

data/lib/regexp_optimized_union.rb

@@ -1,13 +1,4 @@
-if RUBY_VERSION < '1.9'
-  require 'enumerator'
-  class String
-    unless defined?(ord)
-      def ord
-        unpack('C').first
-      end
-    end
-  end
-end
+# coding: UTF-8
 
 class Regexp
   # trie for optimization
@@ -75,11 +66,7 @@ class Regexp
     def build_char_group chars
       return chars.first if chars.size == 1
 
-      if RUBY_VERSION < '1.9'
-        chars, mb_chars = chars.partition{|c| c.bytesize == 1}
-      else
-        mb_chars = []
-      end
+      mb_chars = []
 
       chars = chars.map(&:ord)
       chars.sort!
@@ -93,18 +80,18 @@ class Regexp
         end
       end
 
-      groups.map! do |range|
+      groups = groups.flat_map do |range|
         # only apply range to >= 4 contiguous chars
         if range.end >= range.begin + 3
-          "#{range.begin.chr}-#{range.end.chr}"
+          [range.begin, '-'.ord, range.end]
         elsif range.end > range.begin
-          range.map(&:chr).join
+          range.to_a
         else
-          range.begin.chr
+          [range.begin]
         end
       end
 
-      "[#{groups.join}#{mb_chars.join}]"
+      "[#{groups.pack 'U*'}#{mb_chars.join}]"
     end
 
     def to_re_src
@@ -148,6 +135,7 @@ class Regexp
     # build trie
     a.each do |s|
       next if s.empty?
+      s = s.encode 'utf-8'
       t = trie
       s.chars.each do |c|
         c = Regexp.escape c
@@ -193,7 +181,10 @@ if __FILE__ == $PROGRAM_NAME
     %w[foobar fooabar foogabar] => /foo(?:|a|ga)bar/,
     %w[vax vcx vbx vdx]         => /v[a-d]x/,
     %w[vax vcx vbx]             => /v[abc]x/,
-    %w[xa xc xb x]              => /x[abc]?/
+    %w[xa xc xb x]              => /x[abc]?/,
+    %w[一郎 二郎 三郎 四郎]        => /[一三二四]郎/,
+    # caveats: escape chars can not be turned into char group
+    %w[a^ a- a*]                => /a(?:\^|\-|\*)/,
   }.each do |a, r|
     l = Regexp.optimized_union a
     a.each do |s|

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: regexp_optimized_union
 version: !ruby/object:Gem::Version
-  version: 0.1.2
-  prerelease: 
+  version: 0.2.0
 platform: ruby
 authors:
 - luikore
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-14 00:00:00.000000000 Z
+date: 2016-07-11 00:00:00.000000000 Z
 dependencies: []
 description: Regexp.optimized_union(word_list, regexp_options) generates optimized
   regexp for matching union of word list
@@ -18,32 +17,33 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- changes
 - lib/regexp_optimized_union.rb
 - readme.md
 homepage: https://github.com/luikore/regexp_optimized_union
 licenses:
 - WTFPL
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: 1.3.6
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.5.1
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Regexp.optimized_union(word_list, regexp_options) generates optimized regexp
   for matching union of word list
 test_files: []
+has_rdoc: