update to Unicode Version 12.1.0 (beta)

Unicode Version 12.1.0 adds one single character, U+32FF SQUARE ERA NAME REIWA,
for the new Japanese era starting on May 1st. 12.1.0 will be finalized only on
May 7th, so we go with the beta version because further changes in the data we
need are highly unlikely, and we want to make sure Ruby is ready for the new era.

* common.mk: change UNICODE_VERSION to 12.1.0, UNICODE_BETA to YES

* enc/unicode/12.1.0, enc/unicode/12.1.0/casefold.h, enc/unicode/12.1.0/name2ctype.h:
  add directory and generated data files for new version

* lib/unicode_normalize/tables.rb: update for new character

* test/ruby/test_regexp.rb: add test for character property age=12.1

* test/test_unicode_normalize.rb: add test for NFKC decomposition of new character

This (mostly) completes issue #15195.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@67441 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

common.mk

@@ -15,9 +15,9 @@ mflags = $(MFLAGS)
 gnumake_recursive =
 enable_shared = $(ENABLE_SHARED:no=)
 
-UNICODE_VERSION = 12.0.0
+UNICODE_VERSION = 12.1.0
 UNICODE_EMOJI_VERSION = 12.0
-UNICODE_BETA = NO
+UNICODE_BETA = YES
 
 ### set the following environment variable or uncomment the line if
 ### the Unicode data files should be updated completely on every update ('make up',...).

lib/unicode_normalize/tables.rb

@@ -1388,8 +1388,7 @@ module UnicodeNormalize  # :nodoc:
     "\u3200-\u321E" \
     "\u3220-\u3247" \
     "\u3250-\u327E" \
-    "\u3280-\u32FE" \
-    "\u3300-\u33FF" \
+    "\u3280-\u33FF" \
     "\uA69C\uA69D" \
     "\uA770" \
     "\uA7F8\uA7F9" \
@@ -5493,6 +5492,7 @@ module UnicodeNormalize  # :nodoc:
     "\u32FC"=>"\u30F0",
     "\u32FD"=>"\u30F1",
     "\u32FE"=>"\u30F2",
+    "\u32FF"=>"\u4EE4\u548C",
     "\u3300"=>"\u30A2\u30D1\u30FC\u30C8",
     "\u3301"=>"\u30A2\u30EB\u30D5\u30A1",
     "\u3302"=>"\u30A2\u30F3\u30DA\u30A2",

test/ruby/test_regexp.rb

@@ -1075,6 +1075,9 @@ class TestRegexp < Test::Unit::TestCase
     assert_no_match(/^\p{age=3.0}$/u, "\u2754")
     assert_no_match(/^\p{age=2.0}$/u, "\u2754")
     assert_no_match(/^\p{age=1.1}$/u, "\u2754")
+
+    assert_no_match(/^\p{age=12.0}$/u, "\u32FF")
+    assert_match(/^\p{age=12.1}$/u, "\u32FF")
   end
 
   MatchData_A = eval("class MatchData_\u{3042} < MatchData; self; end")

test/test_unicode_normalize.rb

@@ -187,6 +187,10 @@ class TestUnicodeNormalize
     assert_raise(Encoding::CompatibilityError) { "abc".force_encoding('ISO-8859-1').unicode_normalized? }
   end
 
+  def test_reiwa
+    assert_equal "\u4EE4\u548C", "\u32FF".unicode_normalize(:nfkc)
+  end
+
   def test_us_ascii
     ascii_string = 'abc'.encode('US-ASCII')