[Feature #21275] Bump Unicode version to 17.0.0

This commit is contained in:
Mari Imaizumi 2025-11-13 19:02:10 +09:00
parent e39385bf84
commit cb3bc8ae3f
Notes: git 2025-11-14 03:28:06 +00:00
8 changed files with 8948 additions and 7503 deletions

View File

@ -134,8 +134,8 @@ Note: We're only listing outstanding class updates.
* String
* Update Unicode to Version 16.0.0 and Emoji Version 16.0.
[[Feature #19908]][[Feature #20724]] (also applies to Regexp)
* Update Unicode to Version 17.0.0 and Emoji Version 17.0.
[[Feature #19908]][[Feature #20724]][[Feature #21275]] (also applies to Regexp)
* Thread

View File

@ -21,7 +21,7 @@ gnumake_recursive =
sequential = $(gnumake:yes=-sequential)
enable_shared = $(ENABLE_SHARED:no=)
UNICODE_VERSION = 16.0.0
UNICODE_VERSION = 17.0.0
UNICODE_EMOJI_VERSION_0 = $(UNICODE_VERSION)///
UNICODE_EMOJI_VERSION_1 = $(UNICODE_EMOJI_VERSION_0:.0///=)
UNICODE_EMOJI_VERSION = $(UNICODE_EMOJI_VERSION_1:///=)

View File

@ -146,6 +146,7 @@ Older versions may not support all of these.
- <tt>\p{Bassa_Vah}</tt>, <tt>\p{Bass}</tt>
- <tt>\p{Batak}</tt>, <tt>\p{Batk}</tt>
- <tt>\p{Bengali}</tt>, <tt>\p{Beng}</tt>
- <tt>\p{Beria_Erfe}</tt>, <tt>\p{Berf}</tt>
- <tt>\p{Bhaiksuki}</tt>, <tt>\p{Bhks}</tt>
- <tt>\p{Bopomofo}</tt>, <tt>\p{Bopo}</tt>
- <tt>\p{Brahmi}</tt>, <tt>\p{Brah}</tt>
@ -270,6 +271,7 @@ Older versions may not support all of these.
- <tt>\p{Sharada}</tt>, <tt>\p{Shrd}</tt>
- <tt>\p{Shavian}</tt>, <tt>\p{Shaw}</tt>
- <tt>\p{Siddham}</tt>, <tt>\p{Sidd}</tt>
- <tt>\p{Sidetic}</tt>, <tt>\p{Sidt}</tt>
- <tt>\p{SignWriting}</tt>, <tt>\p{Sgnw}</tt>
- <tt>\p{Sinhala}</tt>, <tt>\p{Sinh}</tt>
- <tt>\p{Sogdian}</tt>, <tt>\p{Sogd}</tt>
@ -284,6 +286,7 @@ Older versions may not support all of these.
- <tt>\p{Tai_Le}</tt>, <tt>\p{Tale}</tt>
- <tt>\p{Tai_Tham}</tt>, <tt>\p{Lana}</tt>
- <tt>\p{Tai_Viet}</tt>, <tt>\p{Tavt}</tt>
- <tt>\p{Tai_Yo}</tt>, <tt>\p{Tayo}</tt>
- <tt>\p{Takri}</tt>, <tt>\p{Takr}</tt>
- <tt>\p{Tamil}</tt>, <tt>\p{Taml}</tt>
- <tt>\p{Tangsa}</tt>, <tt>\p{Tnsa}</tt>
@ -295,6 +298,7 @@ Older versions may not support all of these.
- <tt>\p{Tifinagh}</tt>, <tt>\p{Tfng}</tt>
- <tt>\p{Tirhuta}</tt>, <tt>\p{Tirh}</tt>
- <tt>\p{Todhri}</tt>, <tt>\p{Todr}</tt>
- <tt>\p{Tolong_Siki}</tt>, <tt>\p{Tols}</tt>
- <tt>\p{Toto}</tt>
- <tt>\p{Tulu_Tigalari}</tt>, <tt>\p{Tutg}</tt>
- <tt>\p{Ugaritic}</tt>, <tt>\p{Ugar}</tt>
@ -336,6 +340,7 @@ Older versions may not support all of these.
- <tt>\p{In_Bassa_Vah}</tt>
- <tt>\p{In_Batak}</tt>
- <tt>\p{In_Bengali}</tt>
- <tt>\p{In_Beria_Erfe}</tt>
- <tt>\p{In_Bhaiksuki}</tt>
- <tt>\p{In_Block_Elements}</tt>
- <tt>\p{In_Bopomofo}</tt>
@ -363,6 +368,7 @@ Older versions may not support all of these.
- <tt>\p{In_CJK_Unified_Ideographs_Extension_G}</tt>
- <tt>\p{In_CJK_Unified_Ideographs_Extension_H}</tt>
- <tt>\p{In_CJK_Unified_Ideographs_Extension_I}</tt>
- <tt>\p{In_CJK_Unified_Ideographs_Extension_J}</tt>
- <tt>\p{In_Carian}</tt>
- <tt>\p{In_Caucasian_Albanian}</tt>
- <tt>\p{In_Chakma}</tt>
@ -516,6 +522,7 @@ Older versions may not support all of these.
- <tt>\p{In_Miscellaneous_Mathematical_Symbols_A}</tt>
- <tt>\p{In_Miscellaneous_Mathematical_Symbols_B}</tt>
- <tt>\p{In_Miscellaneous_Symbols}</tt>
- <tt>\p{In_Miscellaneous_Symbols_Supplement}</tt>
- <tt>\p{In_Miscellaneous_Symbols_and_Arrows}</tt>
- <tt>\p{In_Miscellaneous_Symbols_and_Pictographs}</tt>
- <tt>\p{In_Miscellaneous_Technical}</tt>
@ -575,9 +582,11 @@ Older versions may not support all of these.
- <tt>\p{In_Samaritan}</tt>
- <tt>\p{In_Saurashtra}</tt>
- <tt>\p{In_Sharada}</tt>
- <tt>\p{In_Sharada_Supplement}</tt>
- <tt>\p{In_Shavian}</tt>
- <tt>\p{In_Shorthand_Format_Controls}</tt>
- <tt>\p{In_Siddham}</tt>
- <tt>\p{In_Sidetic}</tt>
- <tt>\p{In_Sinhala}</tt>
- <tt>\p{In_Sinhala_Archaic_Numbers}</tt>
- <tt>\p{In_Small_Form_Variants}</tt>
@ -613,12 +622,14 @@ Older versions may not support all of these.
- <tt>\p{In_Tai_Tham}</tt>
- <tt>\p{In_Tai_Viet}</tt>
- <tt>\p{In_Tai_Xuan_Jing_Symbols}</tt>
- <tt>\p{In_Tai_Yo}</tt>
- <tt>\p{In_Takri}</tt>
- <tt>\p{In_Tamil}</tt>
- <tt>\p{In_Tamil_Supplement}</tt>
- <tt>\p{In_Tangsa}</tt>
- <tt>\p{In_Tangut}</tt>
- <tt>\p{In_Tangut_Components}</tt>
- <tt>\p{In_Tangut_Components_Supplement}</tt>
- <tt>\p{In_Tangut_Supplement}</tt>
- <tt>\p{In_Telugu}</tt>
- <tt>\p{In_Thaana}</tt>
@ -627,6 +638,7 @@ Older versions may not support all of these.
- <tt>\p{In_Tifinagh}</tt>
- <tt>\p{In_Tirhuta}</tt>
- <tt>\p{In_Todhri}</tt>
- <tt>\p{In_Tolong_Siki}</tt>
- <tt>\p{In_Toto}</tt>
- <tt>\p{In_Transport_and_Map_Symbols}</tt>
- <tt>\p{In_Tulu_Tigalari}</tt>
@ -685,6 +697,7 @@ Older versions may not support all of these.
- <tt>\p{Age_15_0}</tt>
- <tt>\p{Age_15_1}</tt>
- <tt>\p{Age_16_0}</tt>
- <tt>\p{Age_17_0}</tt>
- <tt>\p{Age_1_1}</tt>
- <tt>\p{Age_2_0}</tt>
- <tt>\p{Age_2_1}</tt>

File diff suppressed because it is too large Load Diff

View File

@ -1,8 +1,8 @@
# coding: us-ascii
# frozen_string_literal: true
Encoding::UNICODE_VERSION == "16.0.0" or
raise "Unicode version mismatch: 16.0.0 expected but #{Encoding::UNICODE_VERSION}"
Encoding::UNICODE_VERSION == "17.0.0" or
raise "Unicode version mismatch: 17.0.0 expected but #{Encoding::UNICODE_VERSION}"
# automatically generated by template/unicode_norm_gen.tmpl
@ -99,7 +99,8 @@ module UnicodeNormalize # :nodoc:
"\u1A75-\u1A7C" \
"\u1A7F" \
"\u1AB0-\u1ABD" \
"\u1ABF-\u1ACE" \
"\u1ABF-\u1ADD" \
"\u1AE0-\u1AEB" \
"\u1B34\u1B35" \
"\u1B44" \
"\u1B6B-\u1B73" \
@ -154,6 +155,7 @@ module UnicodeNormalize # :nodoc:
"\u{10D24}-\u{10D27}" \
"\u{10D69}-\u{10D6D}" \
"\u{10EAB}\u{10EAC}" \
"\u{10EFA}\u{10EFB}" \
"\u{10EFD}-\u{10EFF}" \
"\u{10F46}-\u{10F50}" \
"\u{10F82}-\u{10F85}" \
@ -230,6 +232,10 @@ module UnicodeNormalize # :nodoc:
"\u{1E2EC}-\u{1E2EF}" \
"\u{1E4EC}-\u{1E4EF}" \
"\u{1E5EE}\u{1E5EF}" \
"\u{1E6E3}" \
"\u{1E6E6}" \
"\u{1E6EE}\u{1E6EF}" \
"\u{1E6F5}" \
"\u{1E8D0}-\u{1E8D6}" \
"\u{1E944}-\u{1E94A}" \
"]"
@ -1460,7 +1466,7 @@ module UnicodeNormalize # :nodoc:
"\u3280-\u33FF" \
"\uA69C\uA69D" \
"\uA770" \
"\uA7F2-\uA7F4" \
"\uA7F1-\uA7F4" \
"\uA7F8\uA7F9" \
"\uAB5C-\uAB5F" \
"\uAB69" \
@ -2019,6 +2025,33 @@ module UnicodeNormalize # :nodoc:
"\u1ACC"=>230,
"\u1ACD"=>230,
"\u1ACE"=>230,
"\u1ACF"=>230,
"\u1AD0"=>230,
"\u1AD1"=>230,
"\u1AD2"=>230,
"\u1AD3"=>230,
"\u1AD4"=>230,
"\u1AD5"=>230,
"\u1AD6"=>230,
"\u1AD7"=>230,
"\u1AD8"=>230,
"\u1AD9"=>230,
"\u1ADA"=>230,
"\u1ADB"=>230,
"\u1ADC"=>230,
"\u1ADD"=>220,
"\u1AE0"=>230,
"\u1AE1"=>230,
"\u1AE2"=>230,
"\u1AE3"=>230,
"\u1AE4"=>230,
"\u1AE5"=>230,
"\u1AE6"=>220,
"\u1AE7"=>230,
"\u1AE8"=>230,
"\u1AE9"=>230,
"\u1AEA"=>230,
"\u1AEB"=>234,
"\u1B34"=>7,
"\u1B44"=>9,
"\u1B6B"=>230,
@ -2293,6 +2326,8 @@ module UnicodeNormalize # :nodoc:
"\u{10D6D}"=>230,
"\u{10EAB}"=>230,
"\u{10EAC}"=>230,
"\u{10EFA}"=>220,
"\u{10EFB}"=>220,
"\u{10EFD}"=>220,
"\u{10EFE}"=>220,
"\u{10EFF}"=>220,
@ -2479,6 +2514,11 @@ module UnicodeNormalize # :nodoc:
"\u{1E4EF}"=>230,
"\u{1E5EE}"=>230,
"\u{1E5EF}"=>220,
"\u{1E6E3}"=>230,
"\u{1E6E6}"=>230,
"\u{1E6EE}"=>230,
"\u{1E6EF}"=>230,
"\u{1E6F5}"=>230,
"\u{1E8D0}"=>220,
"\u{1E8D1}"=>220,
"\u{1E8D2}"=>220,
@ -5922,6 +5962,7 @@ module UnicodeNormalize # :nodoc:
"\uA69C"=>"\u044A",
"\uA69D"=>"\u044C",
"\uA770"=>"\uA76F",
"\uA7F1"=>"S",
"\uA7F2"=>"C",
"\uA7F3"=>"F",
"\uA7F4"=>"Q",

View File

@ -9,9 +9,9 @@ describe "RbConfig::CONFIG['UNICODE_EMOJI_VERSION']" do
end
# Caution: ruby_version_is means is_or_later
ruby_version_is "3.5" do
it "is 16.0" do
RbConfig::CONFIG['UNICODE_EMOJI_VERSION'].should == "16.0"
ruby_version_is "4.0" do
it "is 17.0" do
RbConfig::CONFIG['UNICODE_EMOJI_VERSION'].should == "17.0"
end
end
end

View File

@ -9,9 +9,9 @@ describe "RbConfig::CONFIG['UNICODE_VERSION']" do
end
# Caution: ruby_version_is means is_or_later
ruby_version_is "3.5" do
it "is 16.0.0" do
RbConfig::CONFIG['UNICODE_VERSION'].should == "16.0.0"
ruby_version_is "4.0" do
it "is 17.0.0" do
RbConfig::CONFIG['UNICODE_VERSION'].should == "17.0.0"
end
end
end