From: handa <handa@gnu.org>
To: Nima Aryan <nimawebgard@gmail.com>
Cc: b.riefenstahl@turtle-trading.net, 28339@debbugs.gnu.org
Subject: bug#28339: 25.2; Emacs shows ZWNJ character (Zero Width non-Joiner) as Space
Date: Fri, 06 Oct 2017 19:05:41 +0900 [thread overview]
Message-ID: <87infszj4a.fsf@gnu.org> (raw)
In-Reply-To: <CALp2H_2MWgjoEEm6Rp5+5uOdMk-RbFWzaCrweo=pbdzAaq8btA@mail.gmail.com> (message from Nima Aryan on Tue, 19 Sep 2017 13:53:31 +0000)
In article <CALp2H_2MWgjoEEm6Rp5+5uOdMk-RbFWzaCrweo=pbdzAaq8btA@mail.gmail.com>, Nima Aryan <nimawebgard@gmail.com> writes:
> As a user I prefer absorb mode by default but some times thin-space (and
> not simple space) might be a good option to consider.
Attached patch introduces a customizable variable
arabic-shaper-ZWNJ-handling. Shall I install it?
---
K. Handa
handa@gnu.org
------------------------------------------------------------
diff --git a/lisp/composite.el b/lisp/composite.el
index ab39e08..72b0ffc 100644
--- a/lisp/composite.el
+++ b/lisp/composite.el
@@ -442,8 +442,10 @@ lglyph-set-width
(defsubst lglyph-set-adjustment (glyph &optional xoff yoff wadjust)
(aset glyph 9 (vector (or xoff 0) (or yoff 0) (or wadjust 0))))
+;; Return the shallow Copy of GLYPH.
(defsubst lglyph-copy (glyph) (copy-sequence glyph))
+;; Insert GLYPH at the index IDX of GSTRING.
(defun lgstring-insert-glyph (gstring idx glyph)
(let ((nglyphs (lgstring-glyph-len gstring))
(i idx))
@@ -459,6 +461,18 @@ lgstring-insert-glyph
(lgstring-set-glyph gstring i glyph)
gstring))
+;; Remove glyph at IDX from GSTRING.
+(defun lgstring-remove-glyph (gstring idx)
+ (setq gstring (copy-sequence gstring))
+ (lgstring-set-id gstring nil)
+ (let ((len (length gstring)))
+ (setq idx (+ idx 3))
+ (while (< idx len)
+ (aset gstring (1- idx) (aref gstring idx))
+ (setq idx (1+ idx)))
+ (aset gstring (1- len) nil))
+ gstring)
+
(defun compose-glyph-string (gstring from to)
(let ((glyph (lgstring-glyph gstring from))
from-pos to-pos)
diff --git a/lisp/language/misc-lang.el b/lisp/language/misc-lang.el
index 2843c7c..4e10227 100644
--- a/lisp/language/misc-lang.el
+++ b/lisp/language/misc-lang.el
@@ -75,12 +75,72 @@ 'cp1256
(sample-text . "Persian فارسی")
(documentation . "Bidirectional editing is supported.")))
+(defcustom arabic-shaper-ZWNJ-handling nil
+ "How to handle ZWMJ in Arabic text renderling.
+This variable controls the way to handle a glyph for ZWNJ
+returned by the underling shaping engine.
+
+The default value is nil, which means that the ZWNJ glyph is
+displayed as is.
+
+If the value is `absorb', ZWNJ is absorbed into the previous
+grapheme cluster, and not displayed.
+
+If the value is `as-space', the glyph is displayed by a
+thin (i.e. 1-dot width) space.
+
+Customizing the value takes effect when you start Emacs next time."
+ :group 'mule
+ :version "27.1"
+ :type '(choice
+ (const :tag "default" nil)
+ (const :tag "as space" as-space)
+ (const :tag "absorb" absorb)))
+
+(defvar arabic-shape-log nil)
+
+(defun arabic-shape-gstring (gstring)
+ (setq gstring (font-shape-gstring gstring))
+ (push arabic-shaper-ZWNJ-handling arabic-shape-log)
+ (condition-case err
+ (when arabic-shaper-ZWNJ-handling
+ (let ((font (lgstring-font gstring))
+ (i 1)
+ (len (lgstring-glyph-len gstring))
+ (modified nil))
+ (while (< i len)
+ (let ((glyph (lgstring-glyph gstring i)))
+ (when (eq (lglyph-char glyph) #x200c)
+ (cond
+ ((eq arabic-shaper-ZWNJ-handling 'as-space)
+ (if (> (- (lglyph-rbearing glyph) (lglyph-lbearing glyph)) 0)
+ (let ((space-glyph (aref (font-get-glyphs font 0 1 " ") 0)))
+ (when space-glyph
+ (lglyph-set-code glyph (aref space-glyph 3))
+ (lglyph-set-width glyph (aref space-glyph 4)))))
+ (lglyph-set-adjustment glyph 0 0 1)
+ (setq modified t))
+ ((eq arabic-shaper-ZWNJ-handling 'absorb)
+ (let ((prev (lgstring-glyph gstring (1- i))))
+ (lglyph-set-from-to prev (lglyph-from prev) (lglyph-to glyph))
+ (push (cons "remove" (lgstring-glyph gstring i))
+ arabic-shape-log)
+ (setq gstring (lgstring-remove-glyph gstring i))
+ (setq len (1- len)))
+ (setq modified t)))))
+ (setq i (1+ i)))
+ (if modified
+ (lgstring-set-id gstring nil))))
+ (error (push err arabic-shape-log)))
+ gstring)
+
(set-char-table-range
composition-function-table
'(#x600 . #x74F)
- (list (vector "[\u0600-\u074F\u200C\u200D]+" 0 'font-shape-gstring)
- (vector "[\u200C\u200D][\u0600-\u074F\u200C\u200D]+"
- 1 'font-shape-gstring)))
+ (list (vector "[\u0600-\u074F\u200C\u200D]+" 0
+ 'arabic-shape-gstring)
+ (vector "[\u200C\u200D][\u0600-\u074F\u200C\u200D]+" 1
+ 'arabic-shape-gstring)))
(provide 'misc-lang)
next prev parent reply other threads:[~2017-10-06 10:05 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-03 15:57 bug#28339: 25.2; Emacs shows ZWNJ character (Zero Width non-Joiner) as Space Nima Aryan
2017-09-03 17:06 ` Eli Zaretskii
2017-09-03 17:11 ` Eli Zaretskii
2017-09-03 19:31 ` Nima Aryan
2017-09-04 4:26 ` Eli Zaretskii
2017-09-04 5:05 ` sadid sahami
2017-09-04 9:15 ` Eli Zaretskii
2017-09-04 11:43 ` Nima Aryan
2017-09-04 11:49 ` Nima Aryan
2017-09-04 12:11 ` Eli Zaretskii
2017-09-06 23:25 ` handa
2017-09-07 2:40 ` Eli Zaretskii
[not found] ` <CALp2H_0RgoW6NL-N3yLA_io38-y8noymU4gGwEbLGcDV4AX9_g@mail.gmail.com>
2017-09-10 23:08 ` handa
2017-09-11 16:19 ` Eli Zaretskii
2017-09-13 14:06 ` handa
2017-09-13 15:02 ` Eli Zaretskii
2017-09-14 12:24 ` handa
2017-09-14 17:15 ` Eli Zaretskii
2017-09-16 1:32 ` handa
2017-09-16 4:05 ` Nima Aryan
2017-09-16 7:24 ` Eli Zaretskii
2017-09-16 17:30 ` Benjamin Riefenstahl
2017-09-16 17:42 ` Eli Zaretskii
2017-09-16 18:05 ` Benjamin Riefenstahl
2017-09-16 18:23 ` Eli Zaretskii
2017-09-16 18:20 ` Eli Zaretskii
2017-09-18 1:52 ` handa
2017-09-18 15:16 ` Eli Zaretskii
2017-09-19 12:18 ` handa
2017-09-20 7:25 ` Eli Zaretskii
2017-09-18 15:22 ` Benjamin Riefenstahl
2017-09-14 21:13 ` Nima Aryan
[not found] ` <CALp2H_2w50RrBiaWV1dpg760cUpamy1nZdRgrwJKAjESq3no3Q@mail.gmail.com>
2017-09-13 14:02 ` handa
[not found] ` <CALp2H_3tLC71X6-jvH2XD-6qX8O=KE5wHa561QPk-w2OoCX9HA@mail.gmail.com>
2017-09-16 12:36 ` handa
[not found] ` <CALp2H_2MWgjoEEm6Rp5+5uOdMk-RbFWzaCrweo=pbdzAaq8btA@mail.gmail.com>
2017-10-06 10:05 ` handa [this message]
2017-10-06 12:14 ` Eli Zaretskii
2017-10-07 1:11 ` handa
2020-09-04 5:12 ` Lars Ingebrigtsen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=87infszj4a.fsf@gnu.org \
--to=handa@gnu.org \
--cc=28339@debbugs.gnu.org \
--cc=b.riefenstahl@turtle-trading.net \
--cc=nimawebgard@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this external index
https://git.savannah.gnu.org/cgit/emacs.git
https://git.savannah.gnu.org/cgit/emacs/org-mode.git
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.