From 8f17e4de2d7d5ab21e752b27a355d28b1e17d971 Mon Sep 17 00:00:00 2001
From: Eli Zaretskii <eliz@gnu.org>
Date: Wed, 4 May 2022 11:14:45 +0300
Subject: [PATCH] Fix 'bidi-class' property of unassigned codepoints
* admin/unidata/unidata-gen.el (unidata-file-alist): Update the
default values of 'bidi-class' according to the latest Unicode
Standard.
* admin/notes/unicode: Mention possible changes in
DerivedBidiClass.txt that need to be reflected in unidata-gen.el.
* lisp/international/characters.el (#xfb50, #xfdf0): Fix the
Arabic block characters. (Bug#55256)
---
admin/notes/unicode | 6 ++++++
admin/unidata/unidata-gen.el | 12 +++++++++---
lisp/international/characters.el | 3 ++-
3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/admin/notes/unicode b/admin/notes/unicode
index 41661995000..f699f4fb1c0 100644
--- a/admin/notes/unicode
+++ b/admin/notes/unicode
@@ -36,6 +36,12 @@ copyright.html in admin/unidata (some of them might need trailing
whitespace removed before they can be committed to the Emacs
repository).
+Next, review the assignment of default values of the Bidi Class
+property to blocks in the file extracted/DerivedBidiClass.txt from the
+UCD (search for "unassigned" in that file). Any changes should be
+reflected in the unidata-gen.el file, where it sets up the default
+values around line 210.
+
Then Emacs should be rebuilt for them to take effect. Rebuilding
Emacs updates several derived files elsewhere in the Emacs source
tree, mainly in lisp/international/.
diff --git a/admin/unidata/unidata-gen.el b/admin/unidata/unidata-gen.el
index ad72eed9955..149f7535588 100644
--- a/admin/unidata/unidata-gen.el
+++ b/admin/unidata/unidata-gen.el
@@ -209,9 +209,15 @@ Property value is one of the following symbols:
;; The assignment of default values to blocks of code points
;; follows the file DerivedBidiClass.txt from the Unicode
;; Character Database (UCD).
- (L (#x0600 #x06FF AL) (#xFB50 #xFDFF AL) (#xFE70 #xFEFF AL)
- (#x0590 #x05FF R) (#x07C0 #x08FF R)
- (#xFB1D #xFB4F R) (#x10800 #x10FFF R) (#x1E800 #x1EFFF R))
+ (L (#x0600 #x07BF AL) (#x0860 #x08FF AL) (#xFB50 #xFDCF AL)
+ (#xFDF0 #xFDFF AL) (#xFE70 #xFEFF AL) (#x10D00 #x10D3F AL)
+ (#x10F30 #x10F6F AL) (#x1EC70 #x1ECBF AL) (#x1ED00 #x1ED4F AL)
+ (#x1EE00 #x1EEFF AL)
+ (#x0590 #x05FF R) (#x07C0 #x085F R) (#xFB1D #xFB4F R)
+ (#x10800 #x10CFF R) (#x10D40 #x10F2F R) (#x10F70 #x10FFF R)
+ (#x1E800 #x1EC6F R) (#x1ECC0 #x1ECFF R) (#x1ED50 #x1EDFF R)
+ (#x1EF00 #x1EFFF R)
+ (#x20A0 #x20CF ET))
;; The order of elements must be in sync with bidi_type_t in
;; src/dispextern.h.
(L R EN AN BN B AL LRE LRO RLE RLO PDF LRI RLI FSI PDI
diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index 63ac455ea6a..03fb1810866 100644
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -303,7 +303,8 @@ with L, LRE, or LRO Unicode bidi character type.")
(setq charsets (cdr charsets))))
(modify-category-entry '(#x600 . #x6ff) ?b)
(modify-category-entry '(#x870 . #x8ff) ?b)
-(modify-category-entry '(#xfb50 . #xfdff) ?b)
+(modify-category-entry '(#xfb50 . #xfdc0) ?b)
+(modify-category-entry '(#xfdf0 . #xfdff) ?b)
(modify-category-entry '(#xfe70 . #xfefe) ?b)
;; Cyrillic character set (ISO-8859-5)
--
2.39.5