From 70c3e9595fcf0c2b79f6eee0d4b44755dd6d2fd9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Sat, 8 Jun 2024 03:52:57 +0200 Subject: [PATCH] Regenerate UCD --- unicodetools/data/ucd/dev/PropList.txt | 5 +++-- .../data/ucd/dev/auxiliary/WordBreakProperty.txt | 5 ++--- .../data/ucd/dev/extracted/DerivedEastAsianWidth.txt | 9 ++++----- 3 files changed, 9 insertions(+), 10 deletions(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 395aa448d..8f75dfa66 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,5 +1,5 @@ # PropList-16.0.0.txt -# Date: 2024-05-08, 03:40:06 GMT +# Date: 2024-06-08, 01:51:32 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -874,6 +874,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 17000..187F7 ; Ideographic # Lo [6136] TANGUT IDEOGRAPH-17000..TANGUT IDEOGRAPH-187F7 18800..18CD5 ; Ideographic # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CFF..18D08 ; Ideographic # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 +18D82..18DF2 ; Ideographic # Lo [113] TANGUT COMPONENT-771..TANGUT COMPONENT-883 1B170..1B2FB ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB 20000..2A6DF ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF 2A700..2B739 ; Ideographic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739 @@ -885,7 +886,7 @@ FA70..FAD9 ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM 30000..3134A ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 106477 +# Total code points: 106590 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 6acbe0645..9b2f95a9b 100644 --- a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt @@ -1,5 +1,5 @@ # WordBreakProperty-16.0.0.txt -# Date: 2024-06-07, 20:44:43 GMT +# Date: 2024-06-08, 01:52:01 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -1263,7 +1263,6 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 16F93..16F9F ; ALetter # Lm [13] MIAO LETTER TONE-2..MIAO LETTER REFORMED TONE-8 16FE0..16FE1 ; ALetter # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; ALetter # Lm OLD CHINESE ITERATION MARK -18D82..18DF2 ; ALetter # Lo [113] TANGUT COMPONENT-771..TANGUT COMPONENT-883 1BC00..1BC6A ; ALetter # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M 1BC70..1BC7C ; ALetter # Lo [13] DUPLOYAN AFFIX LEFT HORIZONTAL SECANT..DUPLOYAN AFFIX ATTACHED TANGENT HOOK 1BC80..1BC88 ; ALetter # Lo [9] DUPLOYAN AFFIX HIGH ACUTE..DUPLOYAN AFFIX HIGH VERTICAL @@ -1356,7 +1355,7 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1F150..1F169 ; ALetter # So [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z 1F170..1F189 ; ALetter # So [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z -# Total code points: 33904 +# Total code points: 33791 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index a3fa94903..dbf1dcc49 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt @@ -1,5 +1,5 @@ # DerivedEastAsianWidth-16.0.0.txt -# Date: 2024-06-07, 20:44:11 GMT +# Date: 2024-06-08, 01:51:20 GMT # © 2024 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use and license, see https://www.unicode.org/terms_of_use.html @@ -2103,8 +2103,8 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER E0001 ; N # Cf LANGUAGE TAG E0020..E007F ; N # Cf [96] TAG SPACE..CANCEL TAG -# The above property value applies to 760985 code points not listed here. -# Total code points: 792306 +# The above property value applies to 760986 code points not listed here. +# Total code points: 792307 # ================================================ @@ -2512,7 +2512,6 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 18800..18CD5 ; W # Lo [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5 18CFF..18D08 ; W # Lo [10] KHITAN SMALL SCRIPT CHARACTER-18CFF..TANGUT IDEOGRAPH-18D08 18D82..18DF2 ; W # Lo [113] TANGUT COMPONENT-771..TANGUT COMPONENT-883 -18DF3 ; W # Cn 1AFF0..1AFF3 ; W # Lm [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5 1AFF5..1AFFB ; W # Lm [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5 1AFFD..1AFFE ; W # Lm [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8 @@ -2582,7 +2581,7 @@ FE6A..FE6B ; W # Po [2] SMALL PERCENT SIGN..SMALL COMMERCIAL AT 31350..323AF ; W # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF # The above property value applies to 60482 code points not listed here. -# Total code points: 182729 +# Total code points: 182728 # ================================================