Regexp supports Unicoe 9.0.0's \X

* meta character \X matches Unicode 9.0.0 characters with some workarounds
  for UTR #51 Unicode Emoji, Version 4.0 emoji zwj sequences.
  [Feature #12831] [ruby-core:77586]

The term "character" can have many meanings bytes, codepoints, combined
characters, and so on. "grapheme cluster" is highest one of such words,
which means user-perceived characters.
Unicode Standard Annex #29 UNICODE TEXT SEGMENTATION specifies how to
handle grapheme clusters (extended grapheme cluster).
But some specs aren't updated to current situation because Unicode Emoji
is rapidly extended without well definition.
It breaks the precondition of UTR#29 "Grapheme cluster boundaries can be
easily tested by looking at immediately adjacent characters". (the
sentence will be removed in the next version)
Though some of its detail are described in Unicode Technical Report #51
UNICODE EMOJI but it is not merged into UTR#29 yet.

http://unicode.org/reports/tr29/
http://unicode.org/reports/tr51/
http://unicode.org/Public/emoji/4.0/

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@56949 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 33 insertions, 3 deletions

diff --git a/tool/enc-unicode.rb b/tool/enc-unicode.rb
index 83bbe352e1..0e3ba474f7 100755
--- a/tool/enc-unicode.rb
+++ b/tool/enc-unicode.rb
@@ -144,7 +144,7 @@ def parse_scripts(data, categories)
         categories[current] = file[:title]
         (names[file[:title]] ||= []) << current
         cps = []
-      elsif /^([0-9a-fA-F]+)(?:..([0-9a-fA-F]+))?\s*;\s*(\w+)/ =~ line
+      elsif /^([0-9a-fA-F]+)(?:\.\.([0-9a-fA-F]+))?\s*;\s*(\w+)/ =~ line
         current = $3
         $2 ? cps.concat(($1.to_i(16)..$2.to_i(16)).to_a) : cps.push($1.to_i(16))
       end
@@ -199,7 +199,26 @@ def parse_age(data)
       ages << current
       last_constname = constname
       cps = []
-    elsif /^([0-9a-fA-F]+)(?:..([0-9a-fA-F]+))?\s*;\s*(\d+\.\d+)/ =~ line
+    elsif /^([0-9a-fA-F]+)(?:\.\.([0-9a-fA-F]+))?\s*;\s*(\d+\.\d+)/ =~ line
+      current = $3
+      $2 ? cps.concat(($1.to_i(16)..$2.to_i(16)).to_a) : cps.push($1.to_i(16))
+    end
+  end
+  ages
+end
+
+def parse_GraphemeBreakProperty(data)
+  current = nil
+  cps = []
+  ages = []
+  data_foreach('GraphemeBreakProperty.txt') do |line|
+    if /^# Total code points: / =~ line
+      constname = constantize_Grapheme_Cluster_Break(current)
+      data[constname] = cps
+      make_const(constname, cps, "Grapheme_Cluster_Break=#{current}")
+      ages << current
+      cps = []
+    elsif /^([0-9a-fA-F]+)(?:\.\.([0-9a-fA-F]+))?\s*;\s*(\w+)/ =~ line
       current = $3
       $2 ? cps.concat(($1.to_i(16)..$2.to_i(16)).to_a) : cps.push($1.to_i(16))
     end
@@ -209,7 +228,6 @@ end
 
 def parse_block(data)
   current = nil
-  last_constname = nil
   cps = []
   blocks = []
   data_foreach('Blocks.txt') do |line|
@@ -269,6 +287,10 @@ def constantize_agename(name)
   "Age_#{name.sub(/\./, '_')}"
 end
 
+def constantize_Grapheme_Cluster_Break(name)
+  "Grapheme_Cluster_Break_#{name}"
+end
+
 def constantize_blockname(name)
   "In_#{name.gsub(/\W/, '_')}"
 end
@@ -381,6 +403,7 @@ end
 output.ifdef :USE_UNICODE_AGE_PROPERTIES
 ages = parse_age(data)
 output.endif :USE_UNICODE_AGE_PROPERTIES
+graphemeBreaks = parse_GraphemeBreakProperty(data)
 blocks = parse_block(data)
 output.endif :USE_UNICODE_PROPERTIES
 puts(<<'__HEREDOC')
@@ -393,6 +416,7 @@ props.each{|name| puts"  CR_#{name},"}
 output.ifdef :USE_UNICODE_AGE_PROPERTIES
 ages.each{|name|  puts"  CR_#{constantize_agename(name)},"}
 output.endif :USE_UNICODE_AGE_PROPERTIES
+graphemeBreaks.each{|name|  puts"  CR_#{constantize_Grapheme_Cluster_Break(name)},"}
 blocks.each{|name|puts"  CR_#{name},"}
 output.endif :USE_UNICODE_PROPERTIES
 
@@ -437,6 +461,12 @@ ages.each do |name|
   puts "%-40s %3d" % [name + ',', i]
 end
 output.endif :USE_UNICODE_AGE_PROPERTIES
+graphemeBreaks.each do |name|
+  i += 1
+  name = "graphemeclusterbreak=#{name.delete('_').downcase}"
+  name_to_index[name] = i
+  puts "%-40s %3d" % [name + ',', i]
+end
 blocks.each do |name|
   i += 1
   name = normalize_propname(name)