From d3c3104c11264b6cd810531e865b11469067bd68 Mon Sep 17 00:00:00 2001 From: Roozbeh Pournader Date: Wed, 19 Feb 2025 00:10:42 -0800 Subject: [PATCH 1/3] Add Arabic Tashkil sequences to DoNotEmit.txt [182-A46] Action Item for Roozbeh Pournader, SAH: Add Arabic Tashkil sequences to DoNotEmit.txt as described in L2/25-025, for Unicode Version 17.0. [Ref. 4.1 in L2/25-010] --- unicodetools/data/ucd/dev/DoNotEmit.txt | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/DoNotEmit.txt b/unicodetools/data/ucd/dev/DoNotEmit.txt index 14e3ee01c5..3b49bebcd8 100644 --- a/unicodetools/data/ucd/dev/DoNotEmit.txt +++ b/unicodetools/data/ucd/dev/DoNotEmit.txt @@ -1,6 +1,6 @@ # DoNotEmit-17.0.0.txt -# Date: 2024-07-30, 19:30:00 GMT -# © 2024 Unicode®, Inc. +# Date: 2025-02-19, 08:01:00 GMT +# © 2025 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 # @@ -80,6 +80,8 @@ # Dotless_Form: # Dotless forms of lowercase Latin i and j followed by a # combining dot above. +# Arabic_Tashkil: +# Arabic tashkil combinations that should be avoided. # Hamza_Form: # Sequences containing Arabic hamza above, which should be avoided. # Precomposed_Form: @@ -429,6 +431,8 @@ # Arabic, from text of Section 9.2 and the NamesList 0649 0654; 0626; Hamza_Form # ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE; ARABIC LETTER YEH WITH HAMZA ABOVE +064E 064E; 064B; Arabic_Taskil # ARABIC FATHA, ARABIC FATHA; ARABIC FATHATAN +0650 0650; 063D; Arabic_Taskil # ARABIC KASRA, ARABIC KASRA; ARABIC KASRATAN 0673; 0627 065F; Deprecated # ARABIC LETTER ALEF WITH WAVY HAMZA BELOW; ARABIC LETTER ALEF, ARABIC WAVY HAMZA BELOW 0675; 0674 0627; Preferred_Spelling # ARABIC LETTER HIGH HAMZA ALEF; ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF 0676; 0674 0648; Preferred_Spelling # ARABIC LETTER HIGH HAMZA WAW; ARABIC LETTER HIGH HAMZA, ARABIC LETTER WAW From c5451450c0b5cadcab6236e1ec71193c9f9f3250 Mon Sep 17 00:00:00 2001 From: Roozbeh Pournader Date: Wed, 19 Feb 2025 09:58:23 -0800 Subject: [PATCH 2/3] Fix typo in codepoint --- unicodetools/data/ucd/dev/DoNotEmit.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unicodetools/data/ucd/dev/DoNotEmit.txt b/unicodetools/data/ucd/dev/DoNotEmit.txt index 3b49bebcd8..e9a2cb2499 100644 --- a/unicodetools/data/ucd/dev/DoNotEmit.txt +++ b/unicodetools/data/ucd/dev/DoNotEmit.txt @@ -432,7 +432,7 @@ # Arabic, from text of Section 9.2 and the NamesList 0649 0654; 0626; Hamza_Form # ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE; ARABIC LETTER YEH WITH HAMZA ABOVE 064E 064E; 064B; Arabic_Taskil # ARABIC FATHA, ARABIC FATHA; ARABIC FATHATAN -0650 0650; 063D; Arabic_Taskil # ARABIC KASRA, ARABIC KASRA; ARABIC KASRATAN +0650 0650; 064D; Arabic_Taskil # ARABIC KASRA, ARABIC KASRA; ARABIC KASRATAN 0673; 0627 065F; Deprecated # ARABIC LETTER ALEF WITH WAVY HAMZA BELOW; ARABIC LETTER ALEF, ARABIC WAVY HAMZA BELOW 0675; 0674 0627; Preferred_Spelling # ARABIC LETTER HIGH HAMZA ALEF; ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF 0676; 0674 0648; Preferred_Spelling # ARABIC LETTER HIGH HAMZA WAW; ARABIC LETTER HIGH HAMZA, ARABIC LETTER WAW From bede1a8b6964b339cf840bccda51ac1a9a22486e Mon Sep 17 00:00:00 2001 From: Roozbeh Pournader Date: Wed, 19 Feb 2025 22:46:44 -0800 Subject: [PATCH 3/3] Fix typo in Tashkil Co-authored-by: Markus Scherer --- unicodetools/data/ucd/dev/DoNotEmit.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unicodetools/data/ucd/dev/DoNotEmit.txt b/unicodetools/data/ucd/dev/DoNotEmit.txt index e9a2cb2499..5ca5146baf 100644 --- a/unicodetools/data/ucd/dev/DoNotEmit.txt +++ b/unicodetools/data/ucd/dev/DoNotEmit.txt @@ -431,8 +431,8 @@ # Arabic, from text of Section 9.2 and the NamesList 0649 0654; 0626; Hamza_Form # ARABIC LETTER ALEF MAKSURA, ARABIC HAMZA ABOVE; ARABIC LETTER YEH WITH HAMZA ABOVE -064E 064E; 064B; Arabic_Taskil # ARABIC FATHA, ARABIC FATHA; ARABIC FATHATAN -0650 0650; 064D; Arabic_Taskil # ARABIC KASRA, ARABIC KASRA; ARABIC KASRATAN +064E 064E; 064B; Arabic_Tashkil # ARABIC FATHA, ARABIC FATHA; ARABIC FATHATAN +0650 0650; 064D; Arabic_Tashkil # ARABIC KASRA, ARABIC KASRA; ARABIC KASRATAN 0673; 0627 065F; Deprecated # ARABIC LETTER ALEF WITH WAVY HAMZA BELOW; ARABIC LETTER ALEF, ARABIC WAVY HAMZA BELOW 0675; 0674 0627; Preferred_Spelling # ARABIC LETTER HIGH HAMZA ALEF; ARABIC LETTER HIGH HAMZA, ARABIC LETTER ALEF 0676; 0674 0648; Preferred_Spelling # ARABIC LETTER HIGH HAMZA WAW; ARABIC LETTER HIGH HAMZA, ARABIC LETTER WAW