From ec1e6ea4e61a0b509a0044bc5c41d96f7677c2c8 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:10:30 +0200 Subject: [PATCH 01/12] UnicodeData.txt from L2/22-151R --- unicodetools/data/ucd/dev/UnicodeData.txt | 44 +++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index 8f88960db..fb08799ca 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,3 +1,47 @@ +1E5D0;OL ONAL LETTER O;Lo;0;L;;;;;N;;;;; +1E5D1;OL ONAL LETTER OM;Lo;0;L;;;;;N;;;;; +1E5D2;OL ONAL LETTER ONG;Lo;0;L;;;;;N;;;;; +1E5D3;OL ONAL LETTER ORR;Lo;0;L;;;;;N;;;;; +1E5D4;OL ONAL LETTER OO;Lo;0;L;;;;;N;;;;; +1E5D5;OL ONAL LETTER OY;Lo;0;L;;;;;N;;;;; +1E5D6;OL ONAL LETTER A;Lo;0;L;;;;;N;;;;; +1E5D7;OL ONAL LETTER AD;Lo;0;L;;;;;N;;;;; +1E5D8;OL ONAL LETTER AB;Lo;0;L;;;;;N;;;;; +1E5D9;OL ONAL LETTER AH;Lo;0;L;;;;;N;;;;; +1E5DA;OL ONAL LETTER AL;Lo;0;L;;;;;N;;;;; +1E5DB;OL ONAL LETTER AW;Lo;0;L;;;;;N;;;;; +1E5DC;OL ONAL LETTER I;Lo;0;L;;;;;N;;;;; +1E5DD;OL ONAL LETTER IT;Lo;0;L;;;;;N;;;;; +1E5DE;OL ONAL LETTER IP;Lo;0;L;;;;;N;;;;; +1E5DF;OL ONAL LETTER ITT;Lo;0;L;;;;;N;;;;; +1E5E0;OL ONAL LETTER ID;Lo;0;L;;;;;N;;;;; +1E5E1;OL ONAL LETTER IN;Lo;0;L;;;;;N;;;;; +1E5E2;OL ONAL LETTER U;Lo;0;L;;;;;N;;;;; +1E5E3;OL ONAL LETTER UK;Lo;0;L;;;;;N;;;;; +1E5E4;OL ONAL LETTER UDD;Lo;0;L;;;;;N;;;;; +1E5E5;OL ONAL LETTER UJ;Lo;0;L;;;;;N;;;;; +1E5E6;OL ONAL LETTER UNY;Lo;0;L;;;;;N;;;;; +1E5E7;OL ONAL LETTER UR;Lo;0;L;;;;;N;;;;; +1E5E8;OL ONAL LETTER E;Lo;0;L;;;;;N;;;;; +1E5E9;OL ONAL LETTER ES;Lo;0;L;;;;;N;;;;; +1E5EA;OL ONAL LETTER EH;Lo;0;L;;;;;N;;;;; +1E5EB;OL ONAL LETTER EC;Lo;0;L;;;;;N;;;;; +1E5EC;OL ONAL LETTER ENN;Lo;0;L;;;;;N;;;;; +1E5ED;OL ONAL LETTER EG;Lo;0;L;;;;;N;;;;; +1E5EE;OL ONAL SIGN MU;Mn;230;NSM;;;;;N;;;;; +1E5EF;OL ONAL SIGN IKIR;Mn;220;NSM;;;;;N;;;;; +1E5F0;OL ONAL SIGN HODDOND;Lo;0;L;;;;;N;;;;; +1E5F1;OL ONAL DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +1E5F2;OL ONAL DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +1E5F3;OL ONAL DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +1E5F4;OL ONAL DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +1E5F5;OL ONAL DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +1E5F6;OL ONAL DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +1E5F7;OL ONAL DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +1E5F8;OL ONAL DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +1E5F9;OL ONAL DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +1E5FA;OL ONAL DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +1E5FF;OL ONAL ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; From a5e4b2abb2943ee4aea58a46f64c0aa96e0cc0b7 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:14:02 +0200 Subject: [PATCH 02/12] LineBreak.txt from L2/22-151R --- unicodetools/data/ucd/dev/LineBreak.txt | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index f0b1a9b41..46ee99a04 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,3 +1,8 @@ +1E5D0..1E5ED;AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF;CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0;AL # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA;NU # Nd [10] OL ONAL DIGIT ZERO..ON ONAL DIGIT NINE +1E5FF;AL # Po OL ONAL ABBREVIATION SIGN # LineBreak-16.0.0.txt # Date: 2023-10-02, 12:16:34 GMT # © 2023 Unicode®, Inc. From ef60a9f43f0a3662d9619f32ed62394714900733 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:15:24 +0200 Subject: [PATCH 03/12] Scripts.txt --- unicodetools/data/ucd/dev/Scripts.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 13e7f6299..13ecda6cb 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,3 +1,4 @@ +1E5D0..1E5FF; Ol_Onal # Scripts-16.0.0.txt # Date: 2023-10-02, 12:17:02 GMT # © 2023 Unicode®, Inc. From d8fc471623791d7201f7d9a0520640e771b8084b Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:16:37 +0200 Subject: [PATCH 04/12] ShortBlockNames.txt, Blocks.txt --- unicodetools/data/ucd/dev/Blocks.txt | 1 + .../src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt | 1 + 2 files changed, 2 insertions(+) diff --git a/unicodetools/data/ucd/dev/Blocks.txt b/unicodetools/data/ucd/dev/Blocks.txt index 8fa3eaad0..825fb922b 100644 --- a/unicodetools/data/ucd/dev/Blocks.txt +++ b/unicodetools/data/ucd/dev/Blocks.txt @@ -325,6 +325,7 @@ FFF0..FFFF; Specials 1E290..1E2BF; Toto 1E2C0..1E2FF; Wancho 1E4D0..1E4FF; Nag Mundari +1E5D0..1E5FF; Ol Onal 1E7E0..1E7FF; Ethiopic Extended-B 1E800..1E8DF; Mende Kikakui 1E900..1E95F; Adlam diff --git a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt index 32a6ce8cc..b45dc2cf9 100644 --- a/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt +++ b/unicodetools/src/main/resources/org/unicode/text/UCD/ShortBlockNames.txt @@ -226,6 +226,7 @@ Nushu ; Nushu Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong Ogham ; Ogham Ol_Chiki ; Ol_Chiki +Ol_Onal ; Ol_Onal Old_Italic ; Old_Italic Old_Hungarian ; Old_Hungarian Old_North_Arabian ; Old_North_Arabian From ba5f025637f9ccd607648dfc8ff85ca531543d30 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:20:58 +0200 Subject: [PATCH 05/12] scx --- unicodetools/data/ucd/dev/ScriptExtensions.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 23141fb82..48ea67776 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -620,7 +620,7 @@ A830..A832 ; Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Mlym Modi Nand Shrd Sind # Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh -0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DANDA +0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh Onao # Po DEVANAGARI DANDA # Total code points: 1 @@ -628,7 +628,7 @@ A830..A832 ; Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Mlym Modi Nand Shrd Sind # Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh -0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DOUBLE DANDA +0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh Onao # Po DEVANAGARI DOUBLE DANDA # Total code points: 1 From 80ae3945ed56b9dacb84829bbca9b336eaed6725 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:22:14 +0200 Subject: [PATCH 06/12] Regenerate UCD --- unicodetools/data/ucd/dev/DerivedAge.txt | 6 +- .../data/ucd/dev/DerivedCoreProperties.txt | 41 ++++++--- unicodetools/data/ucd/dev/EastAsianWidth.txt | 7 +- unicodetools/data/ucd/dev/LineBreak.txt | 12 +-- .../data/ucd/dev/NormalizationTest.txt | 6 +- .../data/ucd/dev/PropertyValueAliases.txt | 6 +- .../data/ucd/dev/ScriptExtensions.txt | 12 +-- unicodetools/data/ucd/dev/Scripts.txt | 14 ++- unicodetools/data/ucd/dev/UnicodeData.txt | 88 +++++++++---------- .../data/ucd/dev/VerticalOrientation.txt | 7 +- .../dev/auxiliary/GraphemeBreakProperty.txt | 5 +- .../dev/auxiliary/SentenceBreakProperty.txt | 12 ++- .../ucd/dev/auxiliary/WordBreakProperty.txt | 12 ++- .../ucd/dev/extracted/DerivedBidiClass.txt | 13 ++- .../dev/extracted/DerivedCombiningClass.txt | 16 ++-- .../dev/extracted/DerivedEastAsianWidth.txt | 9 +- .../dev/extracted/DerivedGeneralCategory.txt | 21 +++-- .../ucd/dev/extracted/DerivedJoiningType.txt | 5 +- .../ucd/dev/extracted/DerivedLineBreak.txt | 17 ++-- .../data/ucd/dev/extracted/DerivedName.txt | 48 +++++++++- .../ucd/dev/extracted/DerivedNumericType.txt | 7 +- .../dev/extracted/DerivedNumericValues.txt | 34 ++++--- 22 files changed, 270 insertions(+), 128 deletions(-) diff --git a/unicodetools/data/ucd/dev/DerivedAge.txt b/unicodetools/data/ucd/dev/DerivedAge.txt index 0572b7be6..0f5af1e02 100644 --- a/unicodetools/data/ucd/dev/DerivedAge.txt +++ b/unicodetools/data/ucd/dev/DerivedAge.txt @@ -1,5 +1,5 @@ # DerivedAge-16.0.0.txt -# Date: 2023-10-02, 12:16:00 GMT +# Date: 2023-10-09, 13:21:29 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2011,7 +2011,9 @@ FDFE..FDFF ; 14.0 # [2] ARABIC LIGATURE SUBHAANAHU WA TAAALAA..ARABIC LIGAT 0897 ; 16.0 # ARABIC PEPET 10EC2..10EC4 ; 16.0 # [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +1E5D0..1E5FA ; 16.0 # [43] OL ONAL LETTER O..OL ONAL DIGIT NINE +1E5FF ; 16.0 # OL ONAL ABBREVIATION SIGN -# Total code points: 4 +# Total code points: 48 # EOF diff --git a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt index 21cf3645d..215fdf43d 100644 --- a/unicodetools/data/ucd/dev/DerivedCoreProperties.txt +++ b/unicodetools/data/ucd/dev/DerivedCoreProperties.txt @@ -1,5 +1,5 @@ # DerivedCoreProperties-16.0.0.txt -# Date: 2023-10-02, 12:41:01 GMT +# Date: 2023-10-09, 13:21:49 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1349,6 +1349,8 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 1E2C0..1E2EB ; Alphabetic # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; Alphabetic # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; Alphabetic # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; Alphabetic # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; Alphabetic # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; Alphabetic # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Alphabetic # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Alphabetic # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1403,7 +1405,7 @@ FFDA..FFDC ; Alphabetic # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG 30000..3134A ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 138390 +# Total code points: 138421 # ================================================ @@ -3433,6 +3435,7 @@ FFF9..FFFB ; Case_Ignorable # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI 1E2EC..1E2EF ; Case_Ignorable # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EB ; Case_Ignorable # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; Case_Ignorable # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Case_Ignorable # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Case_Ignorable # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Case_Ignorable # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; Case_Ignorable # Lm ADLAM NASALIZATION MARK @@ -3441,7 +3444,7 @@ E0001 ; Case_Ignorable # Cf LANGUAGE TAG E0020..E007F ; Case_Ignorable # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2708 +# Total code points: 2710 # ================================================ @@ -6811,6 +6814,8 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; ID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; ID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; ID_Start # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; ID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; ID_Start # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; ID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -6861,7 +6866,7 @@ FFDA..FFDC ; ID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136970 +# Total code points: 137001 # ================================================ @@ -8166,6 +8171,10 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 1E4EB ; ID_Continue # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; ID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; ID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; ID_Continue # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; ID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; ID_Continue # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; ID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E7E0..1E7E6 ; ID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8221,7 +8230,7 @@ FFDA..FFDC ; ID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN 31350..323AF ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140112 +# Total code points: 140155 # ================================================ @@ -8927,6 +8936,8 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 1E2C0..1E2EB ; XID_Start # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; XID_Start # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; XID_Start # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; XID_Start # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; XID_Start # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; XID_Start # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Start # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Start # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -8977,7 +8988,7 @@ FFDA..FFDC ; XID_Start # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU 30000..3134A ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 136947 +# Total code points: 136978 # ================================================ @@ -10283,6 +10294,10 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 1E4EB ; XID_Continue # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; XID_Continue # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; XID_Continue # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; XID_Continue # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; XID_Continue # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; XID_Continue # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; XID_Continue # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E7E0..1E7E6 ; XID_Continue # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; XID_Continue # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; XID_Continue # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -10338,7 +10353,7 @@ FFDA..FFDC ; XID_Continue # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA 31350..323AF ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF E0100..E01EF ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 140093 +# Total code points: 140136 # ================================================ @@ -10770,12 +10785,13 @@ FF9E..FF9F ; Grapheme_Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK. 1E2AE ; Grapheme_Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Grapheme_Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Grapheme_Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Grapheme_Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Grapheme_Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Grapheme_Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Grapheme_Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Grapheme_Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2126 +# Total code points: 2128 # ================================================ @@ -12427,6 +12443,10 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 1E4D0..1E4EA ; Grapheme_Base # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; Grapheme_Base # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; Grapheme_Base # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; Grapheme_Base # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; Grapheme_Base # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; Grapheme_Base # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; Grapheme_Base # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; Grapheme_Base # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Grapheme_Base # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Grapheme_Base # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -12529,7 +12549,7 @@ FFFC..FFFD ; Grapheme_Base # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEME 30000..3134A ; Grapheme_Base # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Grapheme_Base # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 147616 +# Total code points: 147658 # ================================================ @@ -12830,9 +12850,10 @@ FE20..FE2F ; InCB; Extend # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING 1E2AE ; InCB; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; InCB; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; InCB; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; InCB; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; InCB; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; InCB; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA -# Total code points: 885 +# Total code points: 887 # EOF diff --git a/unicodetools/data/ucd/dev/EastAsianWidth.txt b/unicodetools/data/ucd/dev/EastAsianWidth.txt index e40596ac2..bc47c0a65 100644 --- a/unicodetools/data/ucd/dev/EastAsianWidth.txt +++ b/unicodetools/data/ucd/dev/EastAsianWidth.txt @@ -1,5 +1,5 @@ # EastAsianWidth-16.0.0.txt -# Date: 2023-10-02, 12:16:33 GMT +# Date: 2023-10-09, 13:21:54 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2432,6 +2432,11 @@ FFFD ; A # So REPLACEMENT CHARACTER 1E4EB ; N # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; N # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; N # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; N # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; N # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; N # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; N # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; N # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE diff --git a/unicodetools/data/ucd/dev/LineBreak.txt b/unicodetools/data/ucd/dev/LineBreak.txt index 46ee99a04..eccbe455e 100644 --- a/unicodetools/data/ucd/dev/LineBreak.txt +++ b/unicodetools/data/ucd/dev/LineBreak.txt @@ -1,10 +1,5 @@ -1E5D0..1E5ED;AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG -1E5EE..1E5EF;CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR -1E5F0;AL # Lo OL ONAL SIGN HODDOND -1E5F1..1E5FA;NU # Nd [10] OL ONAL DIGIT ZERO..ON ONAL DIGIT NINE -1E5FF;AL # Po OL ONAL ABBREVIATION SIGN # LineBreak-16.0.0.txt -# Date: 2023-10-02, 12:16:34 GMT +# Date: 2023-10-09, 13:21:55 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3343,6 +3338,11 @@ FFFD ; AI # So REPLACEMENT CHARACTER 1E4EB ; AL # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; AL # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; NU # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; AL # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE diff --git a/unicodetools/data/ucd/dev/NormalizationTest.txt b/unicodetools/data/ucd/dev/NormalizationTest.txt index 757d8f5de..a42521df0 100644 --- a/unicodetools/data/ucd/dev/NormalizationTest.txt +++ b/unicodetools/data/ucd/dev/NormalizationTest.txt @@ -1,5 +1,5 @@ # NormalizationTest-16.0.0.txt -# Date: 2023-10-02, 12:41:11 GMT +# Date: 2023-10-09, 13:21:56 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -18920,6 +18920,10 @@ FFEE;FFEE;FFEE;25CB;25CB; # (￮; ￮; ￮; ○; ○; ) HALFWIDTH WHITE CIRCLE 0061 1E4EE 059A 0316 1DFA 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062;0061 1DFA 1E4EE 0316 059A 0062; # (a◌𞓮◌֚◌̖◌᷺b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; a◌᷺◌𞓮◌̖◌֚b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN IKIR, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 0315 0300 05AE 1E4EF 0062;00E0 05AE 1E4EF 0315 0062;0061 05AE 0300 1E4EF 0315 0062;00E0 05AE 1E4EF 0315 0062;0061 05AE 0300 1E4EF 0315 0062; # (a◌̕◌̀◌֮◌𞓯b; à◌֮◌𞓯◌̕b; a◌֮◌̀◌𞓯◌̕b; à◌֮◌𞓯◌̕b; a◌֮◌̀◌𞓯◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, NAG MUNDARI SIGN SUTUH, LATIN SMALL LETTER B 0061 1E4EF 0315 0300 05AE 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062;0061 05AE 1E4EF 0300 0315 0062; # (a◌𞓯◌̕◌̀◌֮b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; a◌֮◌𞓯◌̀◌̕b; ) LATIN SMALL LETTER A, NAG MUNDARI SIGN SUTUH, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 0315 0300 05AE 1E5EE 0062;00E0 05AE 1E5EE 0315 0062;0061 05AE 0300 1E5EE 0315 0062;00E0 05AE 1E5EE 0315 0062;0061 05AE 0300 1E5EE 0315 0062; # (a◌̕◌̀◌֮◌𞗮b; à◌֮◌𞗮◌̕b; a◌֮◌̀◌𞗮◌̕b; à◌֮◌𞗮◌̕b; a◌֮◌̀◌𞗮◌̕b; ) LATIN SMALL LETTER A, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, OL ONAL SIGN MU, LATIN SMALL LETTER B +0061 1E5EE 0315 0300 05AE 0062;0061 05AE 1E5EE 0300 0315 0062;0061 05AE 1E5EE 0300 0315 0062;0061 05AE 1E5EE 0300 0315 0062;0061 05AE 1E5EE 0300 0315 0062; # (a◌𞗮◌̕◌̀◌֮b; a◌֮◌𞗮◌̀◌̕b; a◌֮◌𞗮◌̀◌̕b; a◌֮◌𞗮◌̀◌̕b; a◌֮◌𞗮◌̀◌̕b; ) LATIN SMALL LETTER A, OL ONAL SIGN MU, COMBINING COMMA ABOVE RIGHT, COMBINING GRAVE ACCENT, HEBREW ACCENT ZINOR, LATIN SMALL LETTER B +0061 059A 0316 1DFA 1E5EF 0062;0061 1DFA 0316 1E5EF 059A 0062;0061 1DFA 0316 1E5EF 059A 0062;0061 1DFA 0316 1E5EF 059A 0062;0061 1DFA 0316 1E5EF 059A 0062; # (a◌֚◌̖◌᷺◌𞗯b; a◌᷺◌̖◌𞗯◌֚b; a◌᷺◌̖◌𞗯◌֚b; a◌᷺◌̖◌𞗯◌֚b; a◌᷺◌̖◌𞗯◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, OL ONAL SIGN IKIR, LATIN SMALL LETTER B +0061 1E5EF 059A 0316 1DFA 0062;0061 1DFA 1E5EF 0316 059A 0062;0061 1DFA 1E5EF 0316 059A 0062;0061 1DFA 1E5EF 0316 059A 0062;0061 1DFA 1E5EF 0316 059A 0062; # (a◌𞗯◌֚◌̖◌᷺b; a◌᷺◌𞗯◌̖◌֚b; a◌᷺◌𞗯◌̖◌֚b; a◌᷺◌𞗯◌̖◌֚b; a◌᷺◌𞗯◌̖◌֚b; ) LATIN SMALL LETTER A, OL ONAL SIGN IKIR, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 1E8D0 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062;0061 1DFA 0316 1E8D0 059A 0062; # (a◌֚◌̖◌᷺◌𞣐b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; a◌᷺◌̖◌𞣐◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, MENDE KIKAKUI COMBINING NUMBER TEENS, LATIN SMALL LETTER B 0061 1E8D0 059A 0316 1DFA 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062;0061 1DFA 1E8D0 0316 059A 0062; # (a◌𞣐◌֚◌̖◌᷺b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; a◌᷺◌𞣐◌̖◌֚b; ) LATIN SMALL LETTER A, MENDE KIKAKUI COMBINING NUMBER TEENS, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, LATIN SMALL LETTER B 0061 059A 0316 1DFA 1E8D1 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062;0061 1DFA 0316 1E8D1 059A 0062; # (a◌֚◌̖◌᷺◌𞣑b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; a◌᷺◌̖◌𞣑◌֚b; ) LATIN SMALL LETTER A, HEBREW ACCENT YETIV, COMBINING GRAVE ACCENT BELOW, COMBINING DOT BELOW LEFT, MENDE KIKAKUI COMBINING NUMBER TENS, LATIN SMALL LETTER B diff --git a/unicodetools/data/ucd/dev/PropertyValueAliases.txt b/unicodetools/data/ucd/dev/PropertyValueAliases.txt index 9039e9eb2..b3f9e6878 100644 --- a/unicodetools/data/ucd/dev/PropertyValueAliases.txt +++ b/unicodetools/data/ucd/dev/PropertyValueAliases.txt @@ -1,5 +1,5 @@ -# PropertyValueAliases-15.1.0.txt -# Date: 2023-08-07, 15:21:34 GMT +# PropertyValueAliases-16.0.0.txt +# Date: 2023-10-09, 13:21:58 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -381,6 +381,7 @@ blk; Nyiakeng_Puachue_Hmong ; Nyiakeng_Puachue_Hmong blk; OCR ; Optical_Character_Recognition blk; Ogham ; Ogham blk; Ol_Chiki ; Ol_Chiki +blk; Ol_Onal ; Ol_Onal blk; Old_Hungarian ; Old_Hungarian blk; Old_Italic ; Old_Italic blk; Old_North_Arabian ; Old_North_Arabian @@ -1393,6 +1394,7 @@ sc ; Nkoo ; Nko sc ; Nshu ; Nushu sc ; Ogam ; Ogham sc ; Olck ; Ol_Chiki +sc ; Onao ; Ol_Onal sc ; Orkh ; Old_Turkic sc ; Orya ; Oriya sc ; Osge ; Osage diff --git a/unicodetools/data/ucd/dev/ScriptExtensions.txt b/unicodetools/data/ucd/dev/ScriptExtensions.txt index 48ea67776..4f46be8e7 100644 --- a/unicodetools/data/ucd/dev/ScriptExtensions.txt +++ b/unicodetools/data/ucd/dev/ScriptExtensions.txt @@ -1,5 +1,5 @@ -# ScriptExtensions-15.1.0.txt -# Date: 2023-02-01, 23:02:24 GMT +# ScriptExtensions-16.0.0.txt +# Date: 2023-10-09, 13:22:09 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -618,17 +618,17 @@ A830..A832 ; Deva Dogr Gujr Guru Khoj Knda Kthi Mahj Mlym Modi Nand Shrd Sind # ================================================ -# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh +# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh -0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh Onao # Po DEVANAGARI DANDA +0964 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DANDA # Total code points: 1 # ================================================ -# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh +# Script_Extensions=Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh -0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Orya Sind Sinh Sylo Takr Taml Telu Tirh Onao # Po DEVANAGARI DOUBLE DANDA +0965 ; Beng Deva Dogr Gong Gonm Gran Gujr Guru Knda Limb Mahj Mlym Nand Onao Orya Sind Sinh Sylo Takr Taml Telu Tirh # Po DEVANAGARI DOUBLE DANDA # Total code points: 1 diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 13ecda6cb..01e5bf32c 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,6 +1,5 @@ -1E5D0..1E5FF; Ol_Onal # Scripts-16.0.0.txt -# Date: 2023-10-02, 12:17:02 GMT +# Date: 2023-10-09, 13:22:09 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3032,4 +3031,15 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI # Total code points: 42 +# ================================================ + +1E5D0..1E5ED ; Ol_Onal # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; Ol_Onal # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; Ol_Onal # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; Ol_Onal # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FB..1E5FE ; Ol_Onal # Cn [4] .. +1E5FF ; Ol_Onal # Po OL ONAL ABBREVIATION SIGN + +# Total code points: 48 + # EOF diff --git a/unicodetools/data/ucd/dev/UnicodeData.txt b/unicodetools/data/ucd/dev/UnicodeData.txt index fb08799ca..834919f0f 100644 --- a/unicodetools/data/ucd/dev/UnicodeData.txt +++ b/unicodetools/data/ucd/dev/UnicodeData.txt @@ -1,47 +1,3 @@ -1E5D0;OL ONAL LETTER O;Lo;0;L;;;;;N;;;;; -1E5D1;OL ONAL LETTER OM;Lo;0;L;;;;;N;;;;; -1E5D2;OL ONAL LETTER ONG;Lo;0;L;;;;;N;;;;; -1E5D3;OL ONAL LETTER ORR;Lo;0;L;;;;;N;;;;; -1E5D4;OL ONAL LETTER OO;Lo;0;L;;;;;N;;;;; -1E5D5;OL ONAL LETTER OY;Lo;0;L;;;;;N;;;;; -1E5D6;OL ONAL LETTER A;Lo;0;L;;;;;N;;;;; -1E5D7;OL ONAL LETTER AD;Lo;0;L;;;;;N;;;;; -1E5D8;OL ONAL LETTER AB;Lo;0;L;;;;;N;;;;; -1E5D9;OL ONAL LETTER AH;Lo;0;L;;;;;N;;;;; -1E5DA;OL ONAL LETTER AL;Lo;0;L;;;;;N;;;;; -1E5DB;OL ONAL LETTER AW;Lo;0;L;;;;;N;;;;; -1E5DC;OL ONAL LETTER I;Lo;0;L;;;;;N;;;;; -1E5DD;OL ONAL LETTER IT;Lo;0;L;;;;;N;;;;; -1E5DE;OL ONAL LETTER IP;Lo;0;L;;;;;N;;;;; -1E5DF;OL ONAL LETTER ITT;Lo;0;L;;;;;N;;;;; -1E5E0;OL ONAL LETTER ID;Lo;0;L;;;;;N;;;;; -1E5E1;OL ONAL LETTER IN;Lo;0;L;;;;;N;;;;; -1E5E2;OL ONAL LETTER U;Lo;0;L;;;;;N;;;;; -1E5E3;OL ONAL LETTER UK;Lo;0;L;;;;;N;;;;; -1E5E4;OL ONAL LETTER UDD;Lo;0;L;;;;;N;;;;; -1E5E5;OL ONAL LETTER UJ;Lo;0;L;;;;;N;;;;; -1E5E6;OL ONAL LETTER UNY;Lo;0;L;;;;;N;;;;; -1E5E7;OL ONAL LETTER UR;Lo;0;L;;;;;N;;;;; -1E5E8;OL ONAL LETTER E;Lo;0;L;;;;;N;;;;; -1E5E9;OL ONAL LETTER ES;Lo;0;L;;;;;N;;;;; -1E5EA;OL ONAL LETTER EH;Lo;0;L;;;;;N;;;;; -1E5EB;OL ONAL LETTER EC;Lo;0;L;;;;;N;;;;; -1E5EC;OL ONAL LETTER ENN;Lo;0;L;;;;;N;;;;; -1E5ED;OL ONAL LETTER EG;Lo;0;L;;;;;N;;;;; -1E5EE;OL ONAL SIGN MU;Mn;230;NSM;;;;;N;;;;; -1E5EF;OL ONAL SIGN IKIR;Mn;220;NSM;;;;;N;;;;; -1E5F0;OL ONAL SIGN HODDOND;Lo;0;L;;;;;N;;;;; -1E5F1;OL ONAL DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; -1E5F2;OL ONAL DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; -1E5F3;OL ONAL DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; -1E5F4;OL ONAL DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; -1E5F5;OL ONAL DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; -1E5F6;OL ONAL DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; -1E5F7;OL ONAL DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; -1E5F8;OL ONAL DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; -1E5F9;OL ONAL DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; -1E5FA;OL ONAL DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; -1E5FF;OL ONAL ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 0000;;Cc;0;BN;;;;;N;NULL;;;; 0001;;Cc;0;BN;;;;;N;START OF HEADING;;;; 0002;;Cc;0;BN;;;;;N;START OF TEXT;;;; @@ -30923,6 +30879,50 @@ FFFD;REPLACEMENT CHARACTER;So;0;ON;;;;;N;;;;; 1E4F7;NAG MUNDARI DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; 1E4F8;NAG MUNDARI DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; 1E4F9;NAG MUNDARI DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +1E5D0;OL ONAL LETTER O;Lo;0;L;;;;;N;;;;; +1E5D1;OL ONAL LETTER OM;Lo;0;L;;;;;N;;;;; +1E5D2;OL ONAL LETTER ONG;Lo;0;L;;;;;N;;;;; +1E5D3;OL ONAL LETTER ORR;Lo;0;L;;;;;N;;;;; +1E5D4;OL ONAL LETTER OO;Lo;0;L;;;;;N;;;;; +1E5D5;OL ONAL LETTER OY;Lo;0;L;;;;;N;;;;; +1E5D6;OL ONAL LETTER A;Lo;0;L;;;;;N;;;;; +1E5D7;OL ONAL LETTER AD;Lo;0;L;;;;;N;;;;; +1E5D8;OL ONAL LETTER AB;Lo;0;L;;;;;N;;;;; +1E5D9;OL ONAL LETTER AH;Lo;0;L;;;;;N;;;;; +1E5DA;OL ONAL LETTER AL;Lo;0;L;;;;;N;;;;; +1E5DB;OL ONAL LETTER AW;Lo;0;L;;;;;N;;;;; +1E5DC;OL ONAL LETTER I;Lo;0;L;;;;;N;;;;; +1E5DD;OL ONAL LETTER IT;Lo;0;L;;;;;N;;;;; +1E5DE;OL ONAL LETTER IP;Lo;0;L;;;;;N;;;;; +1E5DF;OL ONAL LETTER ITT;Lo;0;L;;;;;N;;;;; +1E5E0;OL ONAL LETTER ID;Lo;0;L;;;;;N;;;;; +1E5E1;OL ONAL LETTER IN;Lo;0;L;;;;;N;;;;; +1E5E2;OL ONAL LETTER U;Lo;0;L;;;;;N;;;;; +1E5E3;OL ONAL LETTER UK;Lo;0;L;;;;;N;;;;; +1E5E4;OL ONAL LETTER UDD;Lo;0;L;;;;;N;;;;; +1E5E5;OL ONAL LETTER UJ;Lo;0;L;;;;;N;;;;; +1E5E6;OL ONAL LETTER UNY;Lo;0;L;;;;;N;;;;; +1E5E7;OL ONAL LETTER UR;Lo;0;L;;;;;N;;;;; +1E5E8;OL ONAL LETTER E;Lo;0;L;;;;;N;;;;; +1E5E9;OL ONAL LETTER ES;Lo;0;L;;;;;N;;;;; +1E5EA;OL ONAL LETTER EH;Lo;0;L;;;;;N;;;;; +1E5EB;OL ONAL LETTER EC;Lo;0;L;;;;;N;;;;; +1E5EC;OL ONAL LETTER ENN;Lo;0;L;;;;;N;;;;; +1E5ED;OL ONAL LETTER EG;Lo;0;L;;;;;N;;;;; +1E5EE;OL ONAL SIGN MU;Mn;230;NSM;;;;;N;;;;; +1E5EF;OL ONAL SIGN IKIR;Mn;220;NSM;;;;;N;;;;; +1E5F0;OL ONAL SIGN HODDOND;Lo;0;L;;;;;N;;;;; +1E5F1;OL ONAL DIGIT ZERO;Nd;0;L;;0;0;0;N;;;;; +1E5F2;OL ONAL DIGIT ONE;Nd;0;L;;1;1;1;N;;;;; +1E5F3;OL ONAL DIGIT TWO;Nd;0;L;;2;2;2;N;;;;; +1E5F4;OL ONAL DIGIT THREE;Nd;0;L;;3;3;3;N;;;;; +1E5F5;OL ONAL DIGIT FOUR;Nd;0;L;;4;4;4;N;;;;; +1E5F6;OL ONAL DIGIT FIVE;Nd;0;L;;5;5;5;N;;;;; +1E5F7;OL ONAL DIGIT SIX;Nd;0;L;;6;6;6;N;;;;; +1E5F8;OL ONAL DIGIT SEVEN;Nd;0;L;;7;7;7;N;;;;; +1E5F9;OL ONAL DIGIT EIGHT;Nd;0;L;;8;8;8;N;;;;; +1E5FA;OL ONAL DIGIT NINE;Nd;0;L;;9;9;9;N;;;;; +1E5FF;OL ONAL ABBREVIATION SIGN;Po;0;L;;;;;N;;;;; 1E7E0;ETHIOPIC SYLLABLE HHYA;Lo;0;L;;;;;N;;;;; 1E7E1;ETHIOPIC SYLLABLE HHYU;Lo;0;L;;;;;N;;;;; 1E7E2;ETHIOPIC SYLLABLE HHYI;Lo;0;L;;;;;N;;;;; diff --git a/unicodetools/data/ucd/dev/VerticalOrientation.txt b/unicodetools/data/ucd/dev/VerticalOrientation.txt index 89e03f3c2..771b44040 100644 --- a/unicodetools/data/ucd/dev/VerticalOrientation.txt +++ b/unicodetools/data/ucd/dev/VerticalOrientation.txt @@ -1,5 +1,5 @@ # VerticalOrientation-16.0.0.txt -# Date: 2023-10-02, 12:17:09 GMT +# Date: 2023-10-09, 13:22:12 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -2288,6 +2288,11 @@ FFFC..FFFD ; U # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARA 1E4EB ; R # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; R # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; R # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; R # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; R # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; R # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; R # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; R # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; R # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; R # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; R # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE diff --git a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt index a33745533..787bb8dee 100644 --- a/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/GraphemeBreakProperty.txt @@ -1,5 +1,5 @@ # GraphemeBreakProperty-16.0.0.txt -# Date: 2023-10-02, 12:16:33 GMT +# Date: 2023-10-09, 13:21:54 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -453,13 +453,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2131 +# Total code points: 2133 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt index 04638c600..d1937c3c8 100644 --- a/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt +++ b/unicodetools/data/ucd/dev/auxiliary/SentenceBreakProperty.txt @@ -1,5 +1,5 @@ # SentenceBreakProperty-16.0.0.txt -# Date: 2023-10-02, 12:17:03 GMT +# Date: 2023-10-09, 13:22:10 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -562,12 +562,13 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2551 +# Total code points: 2553 # ================================================ @@ -2488,6 +2489,8 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; OLetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; OLetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; OLetter # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; OLetter # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; OLetter # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; OLetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; OLetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; OLetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2537,7 +2540,7 @@ FFDA..FFDC ; OLetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 30000..3134A ; OLetter # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; OLetter # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132661 +# Total code points: 132692 # ================================================ @@ -2610,10 +2613,11 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; Numeric # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 694 +# Total code points: 704 # ================================================ diff --git a/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt b/unicodetools/data/ucd/dev/auxiliary/WordBreakProperty.txt index 870eb1937..9446b5480 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: 2023-10-02, 12:17:10 GMT +# Date: 2023-10-09, 13:22:12 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -598,13 +598,14 @@ FF9E..FF9F ; Extend # Lm [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT 1E2AE ; Extend # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Extend # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Extend # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Extend # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Extend # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Extend # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1F3FB..1F3FF ; Extend # Sk [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6 E0020..E007F ; Extend # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2555 +# Total code points: 2557 # ================================================ @@ -1270,6 +1271,8 @@ FFDA..FFDC ; ALetter # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL 1E2C0..1E2EB ; ALetter # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; ALetter # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; ALetter # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; ALetter # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; ALetter # Lo OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; ALetter # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; ALetter # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; ALetter # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1314,7 +1317,7 @@ 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: 29493 +# Total code points: 29524 # ================================================ @@ -1432,10 +1435,11 @@ FF10..FF19 ; Numeric # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Numeric # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Numeric # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Numeric # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; Numeric # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Numeric # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Numeric # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 693 +# Total code points: 703 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt index 425000246..ff59968d6 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedBidiClass.txt @@ -1,5 +1,5 @@ # DerivedBidiClass-16.0.0.txt -# Date: 2023-10-02, 12:16:21 GMT +# Date: 2023-10-09, 13:21:47 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1159,6 +1159,10 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER 1E4D0..1E4EA ; L # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; L # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; L # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; L # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; L # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; L # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; L # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; L # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; L # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; L # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1182,8 +1186,8 @@ FFDA..FFDC ; L # Lo [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER F0000..FFFFD ; L # Co [65534] .. 100000..10FFFD; L # Co [65534] .. -# The above property value applies to 820462 code points not listed here. -# Total code points: 1096267 +# The above property value applies to 820418 code points not listed here. +# Total code points: 1096265 # ================================================ @@ -2344,11 +2348,12 @@ FE20..FE2F ; NSM # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC 1E2AE ; NSM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; NSM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; NSM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; NSM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; NSM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; NSM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1994 +# Total code points: 1996 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt index d2888c80d..231e213f2 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedCombiningClass.txt @@ -1,5 +1,5 @@ # DerivedCombiningClass-16.0.0.txt -# Date: 2023-10-02, 12:41:00 GMT +# Date: 2023-10-09, 13:21:48 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1899,6 +1899,10 @@ FFFC..FFFD ; 0 # So [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER 1E4D0..1E4EA ; 0 # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; 0 # Lm NAG MUNDARI SIGN OJOD 1E4F0..1E4F9 ; 0 # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; 0 # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; 0 # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; 0 # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; 0 # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; 0 # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; 0 # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; 0 # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2006,8 +2010,8 @@ E0100..E01EF ; 0 # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 F0000..FFFFD ; 0 # Co [65534] .. 100000..10FFFD; 0 # Co [65534] .. -# The above property value applies to 826762 code points not listed here. -# Total code points: 1113189 +# The above property value applies to 826718 code points not listed here. +# Total code points: 1113187 # ================================================ @@ -2566,9 +2570,10 @@ FE27..FE2D ; 220 # Mn [7] COMBINING LIGATURE LEFT HALF BELOW..COMBINING CON 1D17B..1D182 ; 220 # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE 1D18A..1D18B ; 220 # Mn [2] MUSICAL SYMBOL COMBINING DOUBLE TONGUE..MUSICAL SYMBOL COMBINING TRIPLE TONGUE 1E4EE ; 220 # Mn NAG MUNDARI SIGN IKIR +1E5EF ; 220 # Mn OL ONAL SIGN IKIR 1E8D0..1E8D6 ; 220 # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS -# Total code points: 181 +# Total code points: 182 # ================================================ @@ -2740,9 +2745,10 @@ FE2E..FE2F ; 230 # Mn [2] COMBINING CYRILLIC TITLO LEFT HALF..COMBINING CYR 1E2AE ; 230 # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; 230 # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EF ; 230 # Mn NAG MUNDARI SIGN SUTUH +1E5EE ; 230 # Mn OL ONAL SIGN MU 1E944..1E949 ; 230 # Mn [6] ADLAM ALIF LENGTHENER..ADLAM GEMINATE CONSONANT MODIFIER -# Total code points: 511 +# Total code points: 512 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt b/unicodetools/data/ucd/dev/extracted/DerivedEastAsianWidth.txt index 6776cd4c8..c5d87ef17 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: 2023-10-02, 12:16:27 GMT +# Date: 2023-10-09, 13:21:50 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1935,6 +1935,11 @@ FFFC ; N # So OBJECT REPLACEMENT CHARACTER 1E4EB ; N # Lm NAG MUNDARI SIGN OJOD 1E4EC..1E4EF ; N # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH 1E4F0..1E4F9 ; N # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5D0..1E5ED ; N # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5EE..1E5EF ; N # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E5F0 ; N # Lo OL ONAL SIGN HODDOND +1E5F1..1E5FA ; N # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE +1E5FF ; N # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; N # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; N # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; N # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2044,7 +2049,7 @@ 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 766280 code points not listed here. +# The above property value applies to 766236 code points not listed here. # Total code points: 792618 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt index b75457c76..dcf60c6bb 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedGeneralCategory.txt @@ -1,5 +1,5 @@ # DerivedGeneralCategory-16.0.0.txt -# Date: 2023-10-02, 12:16:28 GMT +# Date: 2023-10-09, 13:21:50 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -626,7 +626,9 @@ FFFE..FFFF ; Cn # [2] .. 1E2AF..1E2BF ; Cn # [17] .. 1E2FA..1E2FE ; Cn # [5] .. 1E300..1E4CF ; Cn # [464] .. -1E4FA..1E7DF ; Cn # [742] .. +1E4FA..1E5CF ; Cn # [214] .. +1E5FB..1E5FE ; Cn # [4] .. +1E600..1E7DF ; Cn # [480] .. 1E7E7 ; Cn # 1E7EC ; Cn # 1E7EF ; Cn # @@ -724,7 +726,7 @@ E01F0..EFFFF ; Cn # [65040] .. FFFFE..FFFFF ; Cn # [2] .. 10FFFE..10FFFF; Cn # [2] .. -# Total code points: 824714 +# Total code points: 824670 # ================================================ @@ -2608,6 +2610,8 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 1E290..1E2AD ; Lo # [30] TOTO LETTER PA..TOTO LETTER A 1E2C0..1E2EB ; Lo # [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; Lo # [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL +1E5D0..1E5ED ; Lo # [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; Lo # OL ONAL SIGN HODDOND 1E7E0..1E7E6 ; Lo # [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; Lo # [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; Lo # [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -2656,7 +2660,7 @@ FFDA..FFDC ; Lo # [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I 30000..3134A ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A 31350..323AF ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF -# Total code points: 132237 +# Total code points: 132268 # ================================================ @@ -3005,11 +3009,12 @@ FE20..FE2F ; Mn # [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL 1E2AE ; Mn # TOTO SIGN RISING TONE 1E2EC..1E2EF ; Mn # [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; Mn # [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; Mn # [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Mn # [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; Mn # [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0100..E01EF ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 1986 +# Total code points: 1988 # ================================================ @@ -3278,10 +3283,11 @@ FF10..FF19 ; Nd # [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Nd # [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Nd # [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Nd # [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; Nd # [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Nd # [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Nd # [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 680 +# Total code points: 690 # ================================================ @@ -3864,9 +3870,10 @@ FF64..FF65 ; Po # [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL 16FE2 ; Po # OLD CHINESE HOOK MARK 1BC9F ; Po # DUPLOYAN PUNCTUATION CHINOOK FULL STOP 1DA87..1DA8B ; Po # [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS +1E5FF ; Po # OL ONAL ABBREVIATION SIGN 1E95E..1E95F ; Po # [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK -# Total code points: 628 +# Total code points: 629 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt index 082e7a262..e52030697 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedJoiningType.txt @@ -1,5 +1,5 @@ # DerivedJoiningType-16.0.0.txt -# Date: 2023-10-02, 12:16:29 GMT +# Date: 2023-10-09, 13:21:51 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -563,6 +563,7 @@ FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATI 1E2AE ; T # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; T # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA 1E94B ; T # Lm ADLAM NASALIZATION MARK @@ -570,6 +571,6 @@ E0001 ; T # Cf LANGUAGE TAG E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2151 +# Total code points: 2153 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt index c2f084c5f..6a091ac1f 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedLineBreak.txt @@ -1,5 +1,5 @@ # DerivedLineBreak-16.0.0.txt -# Date: 2023-10-02, 12:16:29 GMT +# Date: 2023-10-09, 13:21:51 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -68,8 +68,8 @@ E000..F8FF ; XX # Co [6400] .. F0000..FFFFD ; XX # Co [65534] .. 100000..10FFFD; XX # Co [65534] .. -# The above property value applies to 762721 code points not listed here. -# Total code points: 900189 +# The above property value applies to 762677 code points not listed here. +# Total code points: 900145 # ================================================ @@ -543,10 +543,11 @@ ABF0..ABF9 ; NU # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DIGIT NINE 1E140..1E149 ; NU # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; NU # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; NU # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; NU # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; NU # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; NU # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 624 +# Total code points: 634 # ================================================ @@ -1504,6 +1505,9 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1E2C0..1E2EB ; AL # Lo [44] WANCHO LETTER AA..WANCHO LETTER YIH 1E4D0..1E4EA ; AL # Lo [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL 1E4EB ; AL # Lm NAG MUNDARI SIGN OJOD +1E5D0..1E5ED ; AL # Lo [30] OL ONAL LETTER O..OL ONAL LETTER EG +1E5F0 ; AL # Lo OL ONAL SIGN HODDOND +1E5FF ; AL # Po OL ONAL ABBREVIATION SIGN 1E7E0..1E7E6 ; AL # Lo [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO 1E7E8..1E7EB ; AL # Lo [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE 1E7ED..1E7EE ; AL # Lo [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE @@ -1581,7 +1585,7 @@ FFED..FFEE ; AL # So [2] HALFWIDTH BLACK SQUARE..HALFWIDTH WHITE CIRCLE 1FB00..1FB92 ; AL # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK 1FB94..1FBCA ; AL # So [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON -# Total code points: 21732 +# Total code points: 21764 # ================================================ @@ -2331,13 +2335,14 @@ FFF9..FFFB ; CM # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTAT 1E2AE ; CM # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; CM # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI 1E4EC..1E4EF ; CM # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; CM # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; CM # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E94A ; CM # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA E0001 ; CM # Cf LANGUAGE TAG E0020..E007F ; CM # Cf [96] TAG SPACE..CANCEL TAG E0100..E01EF ; CM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 -# Total code points: 2430 +# Total code points: 2432 # ================================================ diff --git a/unicodetools/data/ucd/dev/extracted/DerivedName.txt b/unicodetools/data/ucd/dev/extracted/DerivedName.txt index 080ce3711..4bf9e01c0 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedName.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedName.txt @@ -1,5 +1,5 @@ # DerivedName-16.0.0.txt -# Date: 2023-10-02, 12:16:30 GMT +# Date: 2023-10-09, 13:21:52 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -40678,6 +40678,50 @@ FFFD ; REPLACEMENT CHARACTER 1E4F7 ; NAG MUNDARI DIGIT SEVEN 1E4F8 ; NAG MUNDARI DIGIT EIGHT 1E4F9 ; NAG MUNDARI DIGIT NINE +1E5D0 ; OL ONAL LETTER O +1E5D1 ; OL ONAL LETTER OM +1E5D2 ; OL ONAL LETTER ONG +1E5D3 ; OL ONAL LETTER ORR +1E5D4 ; OL ONAL LETTER OO +1E5D5 ; OL ONAL LETTER OY +1E5D6 ; OL ONAL LETTER A +1E5D7 ; OL ONAL LETTER AD +1E5D8 ; OL ONAL LETTER AB +1E5D9 ; OL ONAL LETTER AH +1E5DA ; OL ONAL LETTER AL +1E5DB ; OL ONAL LETTER AW +1E5DC ; OL ONAL LETTER I +1E5DD ; OL ONAL LETTER IT +1E5DE ; OL ONAL LETTER IP +1E5DF ; OL ONAL LETTER ITT +1E5E0 ; OL ONAL LETTER ID +1E5E1 ; OL ONAL LETTER IN +1E5E2 ; OL ONAL LETTER U +1E5E3 ; OL ONAL LETTER UK +1E5E4 ; OL ONAL LETTER UDD +1E5E5 ; OL ONAL LETTER UJ +1E5E6 ; OL ONAL LETTER UNY +1E5E7 ; OL ONAL LETTER UR +1E5E8 ; OL ONAL LETTER E +1E5E9 ; OL ONAL LETTER ES +1E5EA ; OL ONAL LETTER EH +1E5EB ; OL ONAL LETTER EC +1E5EC ; OL ONAL LETTER ENN +1E5ED ; OL ONAL LETTER EG +1E5EE ; OL ONAL SIGN MU +1E5EF ; OL ONAL SIGN IKIR +1E5F0 ; OL ONAL SIGN HODDOND +1E5F1 ; OL ONAL DIGIT ZERO +1E5F2 ; OL ONAL DIGIT ONE +1E5F3 ; OL ONAL DIGIT TWO +1E5F4 ; OL ONAL DIGIT THREE +1E5F5 ; OL ONAL DIGIT FOUR +1E5F6 ; OL ONAL DIGIT FIVE +1E5F7 ; OL ONAL DIGIT SIX +1E5F8 ; OL ONAL DIGIT SEVEN +1E5F9 ; OL ONAL DIGIT EIGHT +1E5FA ; OL ONAL DIGIT NINE +1E5FF ; OL ONAL ABBREVIATION SIGN 1E7E0 ; ETHIOPIC SYLLABLE HHYA 1E7E1 ; ETHIOPIC SYLLABLE HHYU 1E7E2 ; ETHIOPIC SYLLABLE HHYI @@ -44180,6 +44224,6 @@ E01ED ; VARIATION SELECTOR-254 E01EE ; VARIATION SELECTOR-255 E01EF ; VARIATION SELECTOR-256 -# Total code points: 149817 +# Total code points: 149861 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt index 062f4fbe5..25a128ce4 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericType.txt @@ -1,5 +1,5 @@ -# DerivedNumericType-15.1.0.txt -# Date: 2023-01-05, 20:34:41 GMT +# DerivedNumericType-16.0.0.txt +# Date: 2023-10-09, 13:21:53 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -283,9 +283,10 @@ FF10..FF19 ; Decimal # Nd [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE 1E140..1E149 ; Decimal # Nd [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F0..1E2F9 ; Decimal # Nd [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE 1E4F0..1E4F9 ; Decimal # Nd [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE +1E5F1..1E5FA ; Decimal # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E950..1E959 ; Decimal # Nd [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE 1FBF0..1FBF9 ; Decimal # Nd [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE -# Total code points: 680 +# Total code points: 690 # EOF diff --git a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt index e67164682..1438d395b 100644 --- a/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt +++ b/unicodetools/data/ucd/dev/extracted/DerivedNumericValues.txt @@ -1,5 +1,5 @@ -# DerivedNumericValues-15.1.0.txt -# Date: 2023-01-05, 20:34:41 GMT +# DerivedNumericValues-16.0.0.txt +# Date: 2023-10-09, 13:21:54 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -121,12 +121,13 @@ FF10 ; 0.0 ; ; 0 # Nd FULLWIDTH DIGIT ZERO 1E140 ; 0.0 ; ; 0 # Nd NYIAKENG PUACHUE HMONG DIGIT ZERO 1E2F0 ; 0.0 ; ; 0 # Nd WANCHO DIGIT ZERO 1E4F0 ; 0.0 ; ; 0 # Nd NAG MUNDARI DIGIT ZERO +1E5F1 ; 0.0 ; ; 0 # Nd OL ONAL DIGIT ZERO 1E950 ; 0.0 ; ; 0 # Nd ADLAM DIGIT ZERO 1F100..1F101 ; 0.0 ; ; 0 # No [2] DIGIT ZERO FULL STOP..DIGIT ZERO COMMA 1F10B..1F10C ; 0.0 ; ; 0 # No [2] DINGBAT CIRCLED SANS-SERIF DIGIT ZERO..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO 1FBF0 ; 0.0 ; ; 0 # Nd SEGMENTED DIGIT ZERO -# Total code points: 88 +# Total code points: 89 # ================================================ @@ -543,6 +544,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1E141 ; 1.0 ; ; 1 # Nd NYIAKENG PUACHUE HMONG DIGIT ONE 1E2F1 ; 1.0 ; ; 1 # Nd WANCHO DIGIT ONE 1E4F1 ; 1.0 ; ; 1 # Nd NAG MUNDARI DIGIT ONE +1E5F2 ; 1.0 ; ; 1 # Nd OL ONAL DIGIT ONE 1E8C7 ; 1.0 ; ; 1 # No MENDE KIKAKUI DIGIT ONE 1E951 ; 1.0 ; ; 1 # Nd ADLAM DIGIT ONE 1EC71 ; 1.0 ; ; 1 # No INDIC SIYAQ NUMBER ONE @@ -553,7 +555,7 @@ FF11 ; 1.0 ; ; 1 # Nd FULLWIDTH DIGIT ONE 1FBF1 ; 1.0 ; ; 1 # Nd SEGMENTED DIGIT ONE 2092A ; 1.0 ; ; 1 # Lo CJK UNIFIED IDEOGRAPH-2092A -# Total code points: 144 +# Total code points: 145 # ================================================ @@ -696,6 +698,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1E142 ; 2.0 ; ; 2 # Nd NYIAKENG PUACHUE HMONG DIGIT TWO 1E2F2 ; 2.0 ; ; 2 # Nd WANCHO DIGIT TWO 1E4F2 ; 2.0 ; ; 2 # Nd NAG MUNDARI DIGIT TWO +1E5F3 ; 2.0 ; ; 2 # Nd OL ONAL DIGIT TWO 1E8C8 ; 2.0 ; ; 2 # No MENDE KIKAKUI DIGIT TWO 1E952 ; 2.0 ; ; 2 # Nd ADLAM DIGIT TWO 1EC72 ; 2.0 ; ; 2 # No INDIC SIYAQ NUMBER TWO @@ -707,7 +710,7 @@ FF12 ; 2.0 ; ; 2 # Nd FULLWIDTH DIGIT TWO 1FBF2 ; 2.0 ; ; 2 # Nd SEGMENTED DIGIT TWO 22390 ; 2.0 ; ; 2 # Lo CJK UNIFIED IDEOGRAPH-22390 -# Total code points: 146 +# Total code points: 147 # ================================================ @@ -842,6 +845,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 1E143 ; 3.0 ; ; 3 # Nd NYIAKENG PUACHUE HMONG DIGIT THREE 1E2F3 ; 3.0 ; ; 3 # Nd WANCHO DIGIT THREE 1E4F3 ; 3.0 ; ; 3 # Nd NAG MUNDARI DIGIT THREE +1E5F4 ; 3.0 ; ; 3 # Nd OL ONAL DIGIT THREE 1E8C9 ; 3.0 ; ; 3 # No MENDE KIKAKUI DIGIT THREE 1E953 ; 3.0 ; ; 3 # Nd ADLAM DIGIT THREE 1EC73 ; 3.0 ; ; 3 # No INDIC SIYAQ NUMBER THREE @@ -855,7 +859,7 @@ FF13 ; 3.0 ; ; 3 # Nd FULLWIDTH DIGIT THREE 22998 ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-22998 23B1B ; 3.0 ; ; 3 # Lo CJK UNIFIED IDEOGRAPH-23B1B -# Total code points: 144 +# Total code points: 145 # ================================================ @@ -984,6 +988,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 1E144 ; 4.0 ; ; 4 # Nd NYIAKENG PUACHUE HMONG DIGIT FOUR 1E2F4 ; 4.0 ; ; 4 # Nd WANCHO DIGIT FOUR 1E4F4 ; 4.0 ; ; 4 # Nd NAG MUNDARI DIGIT FOUR +1E5F5 ; 4.0 ; ; 4 # Nd OL ONAL DIGIT FOUR 1E8CA ; 4.0 ; ; 4 # No MENDE KIKAKUI DIGIT FOUR 1E954 ; 4.0 ; ; 4 # Nd ADLAM DIGIT FOUR 1EC74 ; 4.0 ; ; 4 # No INDIC SIYAQ NUMBER FOUR @@ -996,7 +1001,7 @@ FF14 ; 4.0 ; ; 4 # Nd FULLWIDTH DIGIT FOUR 200E2 ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-200E2 2626D ; 4.0 ; ; 4 # Lo CJK UNIFIED IDEOGRAPH-2626D -# Total code points: 135 +# Total code points: 136 # ================================================ @@ -1129,6 +1134,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1E145 ; 5.0 ; ; 5 # Nd NYIAKENG PUACHUE HMONG DIGIT FIVE 1E2F5 ; 5.0 ; ; 5 # Nd WANCHO DIGIT FIVE 1E4F5 ; 5.0 ; ; 5 # Nd NAG MUNDARI DIGIT FIVE +1E5F6 ; 5.0 ; ; 5 # Nd OL ONAL DIGIT FIVE 1E8CB ; 5.0 ; ; 5 # No MENDE KIKAKUI DIGIT FIVE 1E955 ; 5.0 ; ; 5 # Nd ADLAM DIGIT FIVE 1EC75 ; 5.0 ; ; 5 # No INDIC SIYAQ NUMBER FIVE @@ -1139,7 +1145,7 @@ FF15 ; 5.0 ; ; 5 # Nd FULLWIDTH DIGIT FIVE 1FBF5 ; 5.0 ; ; 5 # Nd SEGMENTED DIGIT FIVE 20121 ; 5.0 ; ; 5 # Lo CJK UNIFIED IDEOGRAPH-20121 -# Total code points: 133 +# Total code points: 134 # ================================================ @@ -1257,6 +1263,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1E146 ; 6.0 ; ; 6 # Nd NYIAKENG PUACHUE HMONG DIGIT SIX 1E2F6 ; 6.0 ; ; 6 # Nd WANCHO DIGIT SIX 1E4F6 ; 6.0 ; ; 6 # Nd NAG MUNDARI DIGIT SIX +1E5F7 ; 6.0 ; ; 6 # Nd OL ONAL DIGIT SIX 1E8CC ; 6.0 ; ; 6 # No MENDE KIKAKUI DIGIT SIX 1E956 ; 6.0 ; ; 6 # Nd ADLAM DIGIT SIX 1EC76 ; 6.0 ; ; 6 # No INDIC SIYAQ NUMBER SIX @@ -1267,7 +1274,7 @@ FF16 ; 6.0 ; ; 6 # Nd FULLWIDTH DIGIT SIX 1FBF6 ; 6.0 ; ; 6 # Nd SEGMENTED DIGIT SIX 20AEA ; 6.0 ; ; 6 # Lo CJK UNIFIED IDEOGRAPH-20AEA -# Total code points: 117 +# Total code points: 118 # ================================================ @@ -1383,6 +1390,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1E147 ; 7.0 ; ; 7 # Nd NYIAKENG PUACHUE HMONG DIGIT SEVEN 1E2F7 ; 7.0 ; ; 7 # Nd WANCHO DIGIT SEVEN 1E4F7 ; 7.0 ; ; 7 # Nd NAG MUNDARI DIGIT SEVEN +1E5F8 ; 7.0 ; ; 7 # Nd OL ONAL DIGIT SEVEN 1E8CD ; 7.0 ; ; 7 # No MENDE KIKAKUI DIGIT SEVEN 1E957 ; 7.0 ; ; 7 # Nd ADLAM DIGIT SEVEN 1EC77 ; 7.0 ; ; 7 # No INDIC SIYAQ NUMBER SEVEN @@ -1393,7 +1401,7 @@ FF17 ; 7.0 ; ; 7 # Nd FULLWIDTH DIGIT SEVEN 1FBF7 ; 7.0 ; ; 7 # Nd SEGMENTED DIGIT SEVEN 20001 ; 7.0 ; ; 7 # Lo CJK UNIFIED IDEOGRAPH-20001 -# Total code points: 117 +# Total code points: 118 # ================================================ @@ -1506,6 +1514,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1E148 ; 8.0 ; ; 8 # Nd NYIAKENG PUACHUE HMONG DIGIT EIGHT 1E2F8 ; 8.0 ; ; 8 # Nd WANCHO DIGIT EIGHT 1E4F8 ; 8.0 ; ; 8 # Nd NAG MUNDARI DIGIT EIGHT +1E5F9 ; 8.0 ; ; 8 # Nd OL ONAL DIGIT EIGHT 1E8CE ; 8.0 ; ; 8 # No MENDE KIKAKUI DIGIT EIGHT 1E958 ; 8.0 ; ; 8 # Nd ADLAM DIGIT EIGHT 1EC78 ; 8.0 ; ; 8 # No INDIC SIYAQ NUMBER EIGHT @@ -1515,7 +1524,7 @@ FF18 ; 8.0 ; ; 8 # Nd FULLWIDTH DIGIT EIGHT 1F109 ; 8.0 ; ; 8 # No DIGIT EIGHT COMMA 1FBF8 ; 8.0 ; ; 8 # Nd SEGMENTED DIGIT EIGHT -# Total code points: 112 +# Total code points: 113 # ================================================ @@ -1631,6 +1640,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1E149 ; 9.0 ; ; 9 # Nd NYIAKENG PUACHUE HMONG DIGIT NINE 1E2F9 ; 9.0 ; ; 9 # Nd WANCHO DIGIT NINE 1E4F9 ; 9.0 ; ; 9 # Nd NAG MUNDARI DIGIT NINE +1E5FA ; 9.0 ; ; 9 # Nd OL ONAL DIGIT NINE 1E8CF ; 9.0 ; ; 9 # No MENDE KIKAKUI DIGIT NINE 1E959 ; 9.0 ; ; 9 # Nd ADLAM DIGIT NINE 1EC79 ; 9.0 ; ; 9 # No INDIC SIYAQ NUMBER NINE @@ -1641,7 +1651,7 @@ FF19 ; 9.0 ; ; 9 # Nd FULLWIDTH DIGIT NINE 1FBF9 ; 9.0 ; ; 9 # Nd SEGMENTED DIGIT NINE 2F890 ; 9.0 ; ; 9 # Lo CJK COMPATIBILITY IDEOGRAPH-2F890 -# Total code points: 118 +# Total code points: 119 # ================================================ From 57928c4cf9ca51e344db5fd3d015f4b3f0f39c1d Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:22:59 +0200 Subject: [PATCH 07/12] GenerateEnums --- .../src/main/java/org/unicode/props/UcdPropertyValues.java | 2 ++ 1 file changed, 2 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java index c5eb7e092..a32556983 100644 --- a/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java +++ b/unicodetools/src/main/java/org/unicode/props/UcdPropertyValues.java @@ -406,6 +406,7 @@ public enum Block_Values implements Named { Optical_Character_Recognition("OCR"), Ogham("Ogham"), Ol_Chiki("Ol_Chiki"), + Ol_Onal("Ol_Onal"), Old_Hungarian("Old_Hungarian"), Old_Italic("Old_Italic"), Old_North_Arabian("Old_North_Arabian"), @@ -1802,6 +1803,7 @@ public enum Script_Values implements Named { Nushu("Nshu"), Ogham("Ogam"), Ol_Chiki("Olck"), + Ol_Onal("Onao"), Old_Turkic("Orkh"), Oriya("Orya"), Osage("Osge"), From fe361c0c8e335c99df743b240b904a678a4087e9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:50:16 +0200 Subject: [PATCH 08/12] No script for the hole --- unicodetools/data/ucd/dev/Scripts.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index 01e5bf32c..aba9fc2c7 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -3037,7 +3037,6 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 1E5EE..1E5EF ; Ol_Onal # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E5F0 ; Ol_Onal # Lo OL ONAL SIGN HODDOND 1E5F1..1E5FA ; Ol_Onal # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE -1E5FB..1E5FE ; Ol_Onal # Cn [4] .. 1E5FF ; Ol_Onal # Po OL ONAL ABBREVIATION SIGN # Total code points: 48 From 9a571031801eba816e264169a054b20561ab908f Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 9 Oct 2023 15:51:32 +0200 Subject: [PATCH 09/12] Regenerate UCD --- unicodetools/data/ucd/dev/Scripts.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/Scripts.txt b/unicodetools/data/ucd/dev/Scripts.txt index aba9fc2c7..fb12ba726 100644 --- a/unicodetools/data/ucd/dev/Scripts.txt +++ b/unicodetools/data/ucd/dev/Scripts.txt @@ -1,5 +1,5 @@ # Scripts-16.0.0.txt -# Date: 2023-10-09, 13:22:09 GMT +# Date: 2023-10-09, 13:51:26 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -3039,6 +3039,6 @@ ABF0..ABF9 ; Meetei_Mayek # Nd [10] MEETEI MAYEK DIGIT ZERO..MEETEI MAYEK DI 1E5F1..1E5FA ; Ol_Onal # Nd [10] OL ONAL DIGIT ZERO..OL ONAL DIGIT NINE 1E5FF ; Ol_Onal # Po OL ONAL ABBREVIATION SIGN -# Total code points: 48 +# Total code points: 44 # EOF From e495f62e6f1ba19ae52c262c9804b458beb53931 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 14:50:10 +0200 Subject: [PATCH 10/12] A guess at alpha dia ext --- unicodetools/data/ucd/dev/PropList.txt | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 777e8a288..414ccbc30 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,3 +1,7 @@ +1E5EE; Diacritic +1E5EF; Diacritic +1E5EF; Extender + # PropList-15.1.0.txt # Date: 2023-08-01, 21:56:53 GMT # © 2023 Unicode®, Inc. From fb0ea31c25bb1dcb80dfde9251399e4265090cd9 Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Mon, 23 Oct 2023 15:03:37 +0200 Subject: [PATCH 11/12] Regenerate UCD --- unicodetools/data/ucd/dev/PropList.txt | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/unicodetools/data/ucd/dev/PropList.txt b/unicodetools/data/ucd/dev/PropList.txt index 414ccbc30..f847a9445 100644 --- a/unicodetools/data/ucd/dev/PropList.txt +++ b/unicodetools/data/ucd/dev/PropList.txt @@ -1,9 +1,5 @@ -1E5EE; Diacritic -1E5EF; Diacritic -1E5EF; Extender - -# PropList-15.1.0.txt -# Date: 2023-08-01, 21:56:53 GMT +# PropList-16.0.0.txt +# Date: 2023-10-23, 13:03:16 GMT # © 2023 Unicode®, Inc. # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # For terms of use, see https://www.unicode.org/terms_of_use.html @@ -1103,11 +1099,12 @@ FFE3 ; Diacritic # Sk FULLWIDTH MACRON 1E130..1E136 ; Diacritic # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D 1E2AE ; Diacritic # Mn TOTO SIGN RISING TONE 1E2EC..1E2EF ; Diacritic # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E5EE..1E5EF ; Diacritic # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR 1E8D0..1E8D6 ; Diacritic # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS 1E944..1E946 ; Diacritic # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK 1E948..1E94A ; Diacritic # Mn [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA -# Total code points: 1144 +# Total code points: 1146 # ================================================ @@ -1143,9 +1140,10 @@ FF70 ; Extender # Lm HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND 16FE0..16FE1 ; Extender # Lm [2] TANGUT ITERATION MARK..NUSHU ITERATION MARK 16FE3 ; Extender # Lm OLD CHINESE ITERATION MARK 1E13C..1E13D ; Extender # Lm [2] NYIAKENG PUACHUE HMONG SIGN XW XW..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER +1E5EF ; Extender # Mn OL ONAL SIGN IKIR 1E944..1E946 ; Extender # Mn [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK -# Total code points: 50 +# Total code points: 51 # ================================================ From 39fd292beb195fa31d8e0271b1a594bb78d90e7e Mon Sep 17 00:00:00 2001 From: Robin Leroy Date: Tue, 24 Oct 2023 23:01:52 +0200 Subject: [PATCH 12/12] Ignore conflict markers in ScriptExtensions --- .../src/main/java/org/unicode/jsp/FileUtilities.java | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/unicodetools/src/main/java/org/unicode/jsp/FileUtilities.java b/unicodetools/src/main/java/org/unicode/jsp/FileUtilities.java index 366627e50..a0c4d2bb0 100644 --- a/unicodetools/src/main/java/org/unicode/jsp/FileUtilities.java +++ b/unicodetools/src/main/java/org/unicode/jsp/FileUtilities.java @@ -76,6 +76,11 @@ public SemiFileReader process(BufferedReader in, String fileName) { if (line == null) { break; } + if (line.startsWith("<<<<<<<") + || line.startsWith("=======") + || line.startsWith(">>>>>>>")) { + continue; + } final int comment = line.indexOf("#"); if (comment >= 0) { processComment(line, comment);