Generate skin tone compositions from emoji-sequences.txt

Read skin tone modifier sequences from emoji-sequences.txt and add
them to the per-character composition rules derived from
emoji-zwj-sequences.txt, rather than adding them as lookback rules for
the skin tone modifiers.  This avoids an issue with the application of
such lookback rules.  See Bug#39799,
specifically
<https://lists.gnu.org/archive/html/bug-gnu-emacs/2021-09/msg01878.html>
for more details.

* admin/unidata/Makefile.in (zwj): Add emoji-sequences.txt as a dependency.
* admin/unidata/emoji-zwj.awk: Match RGI_Emoji_ZWJ_Sequence and
RGI_Emoji_Modifier_Sequence.  Remove manual addition of skin tone
composition rules with lookback.

diff --git a/admin/unidata/Makefile.in b/admin/unidata/Makefile.in
index a2a2e425ffb23851789606d7df30eea83936fc88..a953044a1152fcc15e4318de851ba55d4cb451c2 100644 (file)
--- a/admin/unidata/Makefile.in
+++ b/admin/unidata/Makefile.in
@@ -91,8 +91,8 @@ emoji-zwj.el: ${unidir}/emoji-zwj.el
 
 zwj = ${srcdir}/emoji-zwj.awk
 
-${unidir}/emoji-zwj.el: ${srcdir}/emoji-zwj-sequences.txt ${zwj}
-       $(AM_V_GEN)$(AWK) -f ${zwj} < $< > $@
+${unidir}/emoji-zwj.el: ${srcdir}/emoji-zwj-sequences.txt $(srcdir)/emoji-sequences.txt ${zwj}
+       $(AM_V_GEN)$(AWK) -f ${zwj} $^ > $@
 
 .PHONY: clean bootstrap-clean distclean maintainer-clean gen-clean
 

diff --git a/admin/unidata/emoji-zwj.awk b/admin/unidata/emoji-zwj.awk
index bdc50f5047ae7b295c879fe31339d00b19ea6a79..5aca157cbd4a4fc92323791ec106a612707ebf66 100644 (file)
--- a/admin/unidata/emoji-zwj.awk
+++ b/admin/unidata/emoji-zwj.awk
@@ -39,7 +39,7 @@
 
 ### Code:
 
-/^[0-9A-F]/ {
+/^[0-9A-F].*; RGI_Emoji_(ZWJ|Modifier)_Sequence/ {
     sub(/ *;.*/, "", $0)
     num = split($0, elts)
     if (ch[elts[1]] == "")
@@ -62,7 +62,7 @@
 
 END {
      print ";;; emoji-zwj.el --- emoji zwj character composition table  -*- lexical-binding:t -*-"
-     print ";;; Automatically generated from admin/unidata/emoji-zwj-sequences.txt"
+     print ";;; Automatically generated from admin/unidata/emoji-{zwj-,}sequences.txt"
      print "(eval-when-compile (require 'regexp-opt))"
      print "(dolist (elt `("
 
@@ -78,7 +78,7 @@ END {
      print "                                             0"
      print "                                             'compose-gstring-for-graphic)))))"
 
-     print ";; The following three blocks are derived by hand from emoji-sequences.txt"
+     print ";; The following two blocks are derived by hand from emoji-sequences.txt"
      print ";; FIXME: add support for Emoji_Keycap_Sequence once we learn how to respect FE0F/VS-16"
      print ";; for ASCII characters."
 
@@ -98,14 +98,6 @@ END {
      print "                                           0"
      print "                                    'compose-gstring-for-graphic))))"
 
-     print ";; Skin tones"
-     print "(set-char-table-range composition-function-table"
-     print "                      '(#x1F3FB . #x1F3FF)"
-     print "                      (nconc (char-table-range composition-function-table '(#x1F3FB . #x1F3FF))"
-     print "                             (list (vector \".[\\U0001F3FB-\\U0001F3FF]\""
-     print "                                           1"
-     print "                                    'compose-gstring-for-graphic))))"
-
      print "\n"
      print "(provide 'emoji-zwj)"
 }