From dd57a1d762bf658313d4d01df9418c17c476017b Mon Sep 17 00:00:00 2001 From: Markus Scherer Date: Fri, 17 Nov 2023 15:52:48 -0800 Subject: [PATCH] U+19DA is DISALLOWED because XV8 --- unicodetools/data/idna/idna2008derived/Idna2008-10.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-11.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-12.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-12.1.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-13.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-14.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-15.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-15.1.0.txt | 5 +++-- unicodetools/data/idna/idna2008derived/Idna2008-7.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-8.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/Idna2008-9.0.0.txt | 7 ++++--- unicodetools/data/idna/idna2008derived/ReadMe.txt | 6 ++++++ 12 files changed, 49 insertions(+), 32 deletions(-) diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-10.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-10.0.0.txt index 218fe6d25..d50d41304 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-10.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-10.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-10.0.0.txt -# Date: 2022-01-19, 17:49:46 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:26:27 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1177,7 +1177,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-11.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-11.0.0.txt index 1765ff59b..688fcc946 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-11.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-11.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-11.0.0.txt -# Date: 2022-01-19, 19:47:18 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:27:39 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1178,7 +1178,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-12.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-12.0.0.txt index 634d25b9d..ebcd82a7b 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-12.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-12.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-12.0.0.txt -# Date: 2022-01-19, 19:51:52 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:28:49 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1164,7 +1164,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-12.1.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-12.1.0.txt index f4d7035c1..17a9a35fa 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-12.1.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-12.1.0.txt @@ -1,6 +1,6 @@ # Idna2008-12.1.0.txt -# Date: 2022-01-19, 19:56:18 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:30:15 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1164,7 +1164,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-13.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-13.0.0.txt index 1a20c51e2..53911f5ed 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-13.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-13.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-13.0.0.txt -# Date: 2022-01-19, 19:58:19 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:31:13 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1162,7 +1162,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-14.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-14.0.0.txt index 6720edee4..b0347918b 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-14.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-14.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-14.0.0.txt -# Date: 2022-01-19, 20:01:50 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:32:19 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1161,7 +1161,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-15.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-15.0.0.txt index a90b76e71..0162e0c32 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-15.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-15.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-15.0.0.txt -# Date: 2022-05-02, 13:39:45 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:33:22 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1161,7 +1161,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-15.1.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-15.1.0.txt index ac0b8e890..b9521c35c 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-15.1.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-15.1.0.txt @@ -1,5 +1,5 @@ # Idna2008-15.1.0.txt -# Date: 2023-07-28, 14:16:14 GMT [KW] +# Date: 2023-11-13, 11:26:47 GMT [KW] # Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # @@ -1161,7 +1161,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-7.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-7.0.0.txt index 10b2b4248..92b43bd7d 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-7.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-7.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-7.0.0.txt -# Date: 2022-01-19, 13:16:06 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 11:58:37 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1169,7 +1169,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-8.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-8.0.0.txt index 697d4712a..20687e938 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-8.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-8.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-8.0.0.txt -# Date: 2022-01-19, 13:21:12 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:03:34 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1173,7 +1173,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/Idna2008-9.0.0.txt b/unicodetools/data/idna/idna2008derived/Idna2008-9.0.0.txt index 09932b8f4..3b19cf435 100644 --- a/unicodetools/data/idna/idna2008derived/Idna2008-9.0.0.txt +++ b/unicodetools/data/idna/idna2008derived/Idna2008-9.0.0.txt @@ -1,6 +1,6 @@ # Idna2008-9.0.0.txt -# Date: 2022-01-19, 13:25:00 GMT [KW] -# Copyright 2022 Unicode, Inc. +# Date: 2023-11-13, 12:05:09 GMT [KW] +# Copyright 2023 Unicode, Inc. # For terms of use, see https://www.unicode.org/terms_of_use.html # # @@ -1175,7 +1175,8 @@ 19AC..19AF ; UNASSIGNED # .. 19B0..19C9 ; PVALID # NEW TAI LUE VOWEL SIGN VOWEL SHORTENER..NEW TAI LUE TONE MARK-2 19CA..19CF ; UNASSIGNED # .. -19D0..19DA ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE THAM DIGIT ONE +19D0..19D9 ; PVALID # NEW TAI LUE DIGIT ZERO..NEW TAI LUE DIGIT NINE +19DA ; DISALLOWED # NEW TAI LUE THAM DIGIT ONE 19DB..19DD ; UNASSIGNED # .. 19DE..19FF ; DISALLOWED # NEW TAI LUE SIGN LAE..KHMER SYMBOL DAP-PRAM ROC 1A00..1A1B ; PVALID # BUGINESE LETTER KA..BUGINESE VOWEL SIGN AE diff --git a/unicodetools/data/idna/idna2008derived/ReadMe.txt b/unicodetools/data/idna/idna2008derived/ReadMe.txt index 10eead1ba..0d98fe9fb 100644 --- a/unicodetools/data/idna/idna2008derived/ReadMe.txt +++ b/unicodetools/data/idna/idna2008derived/ReadMe.txt @@ -8,6 +8,12 @@ This directory contains data files listing the IDNA2008_Category Property for all versions of the Unicode Standard extending back to Version 6.1.0. +The data files for Version 7.0.0 through Version 15.1.0 were updated +on 2023-11-13 to fix a clerical error that had caused them to be +inconsistent with the source file (IdnaMappingTable.txt) for each of +those versions. The revised derivations now correctly indicate +that U+19DA has IDNA2008_Category=DISALLOWED for those versions. + The listing matches the "IDNA Derived Property" as defined in RFC 5892.