list_matcher 1.0.7 → 1.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0f79c113982bca292d38166efef13f34dad0e94c
-  data.tar.gz: 57d959f68c59bcb5e46d845bbc91fc6c886938ea
+  metadata.gz: 7cd4faa0dd3bafd7a1933d14d325056175c28886
+  data.tar.gz: 895da5871b03ba84b0d41bade4ed9aaa45231b0c
 SHA512:
-  metadata.gz: 60928c05f29c22d7c35dd185754ac15e00c67241371b63a8ec49623cbbd4f4d56039ccceba89ee7bfabf8fd42d48d61032b6fb04fade09c46e955fc671c5a59d
-  data.tar.gz: 5833bb49787f30342f8217fdce788b8ba1e60cae48e4cef83c90346168112c2a3d1ac0581a3261328d9537e06bc7fd0664feff39eda097cd042183b4a74c9072
+  metadata.gz: 944331095b454a924a047f7c1f96bae2c8254b4e092622e185de66e35063a6f698e1e8c3a45f99cebe7c4e2077203987cb94bb53d4ffb2720eb601f7a055a032
+  data.tar.gz: eb3ad634394d9fa378f206117e47b553e3f21c032a95cd284b5591c81893374cdc69330c2f48f9e0e1f2693e13e96b391c45eb71b470567527d636b7e25aeaa6

data/README.md

@@ -401,6 +401,18 @@ List::Matcher.pattern [ 'cat and dog', '# is sometimes called the pound symbol'
 
 Note that `List::Matcher` will continue to quote other white space characters.
 
+### encoding
+
+```ruby
+default: Encoding::UTF_8
+```
+
+`List::Matcher` converts characters into integers during the construction of character classes and then
+must convert the integers back into characters. In order to do this with characters whose code point is
+above 255 we must give `chr` a character encoding. This is all that this is. Most likely you will never
+need to change this default, but if it causes you trouble this parameters is provided so you can fix
+it without having to fork the code.
+
 ## Benchmarks
 
 Efficiency isn't the principle purpose of List::Matcher, but in almost all cases List::Matcher

data/lib/list_matcher.rb

@@ -3,7 +3,8 @@ require "list_matcher/version"
 module List
   class Matcher
     attr_reader :atomic, :backtracking, :bound, :case_insensitive, :strip, :left_bound,
-      :right_bound, :word_test, :normalize_whitespace, :multiline, :name, :vet, :not_extended
+      :right_bound, :word_test, :normalize_whitespace, :multiline, :name, :vet, :not_extended,
+      :encoding
 
     # a special exception class for List::Matcher
     class Error < ::StandardError; end
@@ -33,7 +34,8 @@ module List
           normalize_whitespace: false,
           symbols:              {},
           name:                 false,
-          vet:                  false
+          vet:                  false,
+          encoding:             Encoding::UTF_8
         )
       @atomic               = atomic
       @backtracking         = backtracking
@@ -46,6 +48,7 @@ module List
       @bound                = !!bound
       @normalize_whitespace = normalize_whitespace
       @vet                  = vet
+      @encoding             = encoding
       if name
         raise Error, "name must be a string or symbol" unless name.is_a?(String) || name.is_a?(Symbol)
         begin
@@ -354,7 +357,7 @@ module List
               s == 0 ? a.to_s <=> b.to_s : s
             end
           end.each do |var, opts|
-            c = ( max += 1 ).chr
+            c = ( max += 1 ).chr(engine.encoding)
             sp = if opts.is_a? Hash
               pat = opts.delete :pattern
               raise Error, "symbol #{var} requires a pattern" unless pat || var.is_a?(Regexp)
@@ -372,12 +375,12 @@ module List
         end
         if engine.bound
           if engine.left_bound
-            c = ( max += 1 ).chr
+            c = ( max += 1 ).chr(engine.encoding)
             @left = SymbolPattern.new engine, c, c, engine.left_bound
             @specials << @left
           end
           if engine.right_bound
-            c = ( max += 1 ).chr
+            c = ( max += 1 ).chr(engine.encoding)
             @right = SymbolPattern.new engine, c, c, engine.right_bound
             @specials << @right
           end
@@ -684,15 +687,15 @@ module List
         else
           rs = ranges(chars)
           if rs.size == 1 && rs[0][0] == rs[0][1]
-            cc_quote rs[0][0].chr
+            cc_quote rs[0][0].chr(engine.encoding)
           else
             mid = rs.map do |s, e|
               if s == e
-                cc_quote s.chr
+                cc_quote s.chr(engine.encoding)
               elsif e == s + 1
-                "#{ cc_quote s.chr }#{ cc_quote e.chr }"
+                "#{ cc_quote s.chr(engine.encoding) }#{ cc_quote e.chr(engine.encoding) }"
               else
-                "#{ cc_quote s.chr }-#{ cc_quote e.chr }"
+                "#{ cc_quote s.chr(engine.encoding) }-#{ cc_quote e.chr(engine.encoding) }"
               end
             end.join
           end

data/lib/list_matcher/version.rb

@@ -1,3 +1,3 @@
 module ListMatcher
-  VERSION = "1.0.7"
+  VERSION = "1.1.8"
 end

data/list_matcher.gemspec

@@ -9,7 +9,10 @@ Gem::Specification.new do |spec|
   spec.authors               = ["dfhoughton"]
   spec.email                 = ["dfhoughton@gmail.com"]
   spec.summary               = %q{List::Matcher automates the generation of efficient regular expressions.}
-  spec.description           = spec.summary
+  spec.description           = <<-END
+    List::Matcher automates the creation of regular expressions from lists, including lists of other regular
+    expressions. The expressions it generates from lists of strings are non-backtracking and compact.
+  END
   spec.homepage              = "https://github.com/dfhoughton/list_matcher"
   spec.license               = "MIT"
 
@@ -21,5 +24,5 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.7"
   spec.add_development_dependency "rake", "~> 10.0"
-  spec.add_development_dependency "minitest"
+  spec.add_development_dependency "minitest", "~> 5"
 end

data/test/basic_test.rb

@@ -31,6 +31,14 @@ class BasicTest < Minitest::Test
     end
   end
 
+  def test_fat_chars
+    doublewides = (256...1000).map{ |i| i.chr(Encoding::UTF_8) }
+    rx = List::Matcher.rx doublewides
+    doublewides.each do |word|
+      assert rx === word, "can match #{word}"
+    end
+  end
+
   def test_word_chars_case_insensitive
     word = (1..255).map(&:chr).select{ |c| /\w/ === c }
     chars = word + ['+']

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: list_matcher
 version: !ruby/object:Gem::Version
-  version: 1.0.7
+  version: 1.1.8
 platform: ruby
 authors:
 - dfhoughton
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-01-19 00:00:00.000000000 Z
+date: 2017-12-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -42,17 +42,19 @@ dependencies:
   name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
-description: List::Matcher automates the generation of efficient regular expressions.
+        version: '5'
+description: |2
+      List::Matcher automates the creation of regular expressions from lists, including lists of other regular
+      expressions. The expressions it generates from lists of strings are non-backtracking and compact.
 email:
 - dfhoughton@gmail.com
 executables: []