emacs-28 9bd2f59 1/2: Handle VS-16 correctly for non-emoji codepoints

[Robert Pluim]

branch: emacs-28
commit 9bd2f59db608def1b588b03eff846d3fe8a7fa00
Author: Robert Pluim <rpluim@gmail.com>
Commit: Robert Pluim <rpluim@gmail.com>

    Handle VS-16 correctly for non-emoji codepoints
    
    * admin/unidata/blocks.awk: Remove emoji overrides for codepoints with
    Emoji_Presentation = No, they're no longer necessary.
    * lisp/composite.el: Remove #xFE0F (VS-16) from the range handled by
    `compose-gstring-for-variation-glyph' so it can be handled by
    `font_range'.
    * src/composite.c (syms_of_composite): New variable
    `auto-composition-emoji-eligible-codepoints'.
    * admin/unidata/emoji-zwj.awk: Generate value for
    `auto-composition-emoji-eligible-codepoints'.  Add
    `composition-function-table' entries for 'codepoint + U+FE0F' for
    them.
    * src/font.c (codepoint_is_emoji_eligible): New function to check if
    we should try to use the emoji font for a codepoint.
    (font_range): Use it.
---
 admin/unidata/blocks.awk    | 26 ++------------------------
 admin/unidata/emoji-zwj.awk | 41 +++++++++++++++++++++++++++++++++++++++--
 lisp/composite.el           |  9 ++++++++-
 src/composite.c             | 11 +++++++++++
 src/font.c                  | 20 ++++++++++++++++++--
 5 files changed, 78 insertions(+), 29 deletions(-)

diff --git a/admin/unidata/blocks.awk b/admin/unidata/blocks.awk
index 96b0413..314ac3e 100755
--- a/admin/unidata/blocks.awk
+++ b/admin/unidata/blocks.awk
@@ -221,31 +221,9 @@ FILENAME ~ "emoji-data.txt" && /^[0-9A-F].*; 
Emoji_Presentation / {
 }
 
 END {
-    ## These codepoints have Emoji_Presentation = No, but they are
-    ## used in emoji-sequences.txt and emoji-zwj-sequences.txt (with a
-    ## Variation Selector), so force them into the emoji script so
-    ## they will get composed correctly.  FIXME: delete this when we
-    ## can change the font used for a codepoint based on whether it's
-    ## followed by a VS (usually VS-16)
     idx = 0
-    override_start[idx] = "1F3CB"
-    override_end[idx] = "1F3CC"
-    idx++
-    override_start[idx] = "1F3F3"
-    override_end[idx] = "1F3F4"
-    idx++
-    override_start[idx] = "1F441"
-    override_end[idx] = "1F441"
-    idx++
-    override_start[idx] = "1F574"
-    override_end[idx] = "1F575"
-    idx++
-    override_start[idx] = "1F590"
-    override_end[idx] = "1F590"
-
-    ## These are here so that font_range can choose Emoji presentation
-    ## for the preceding codepoint when it encounters a VS
-    idx++
+    # ## These are here so that font_range can choose Emoji presentation
+    # ## for the preceding codepoint when it encounters a VS
     override_start[idx] = "FE00"
     override_end[idx] = "FE0F"
 
diff --git a/admin/unidata/emoji-zwj.awk b/admin/unidata/emoji-zwj.awk
index 5aca157..d4e2944 100644
--- a/admin/unidata/emoji-zwj.awk
+++ b/admin/unidata/emoji-zwj.awk
@@ -64,6 +64,44 @@ END {
      print ";;; emoji-zwj.el --- emoji zwj character composition table  -*- 
lexical-binding:t -*-"
      print ";;; Automatically generated from 
admin/unidata/emoji-{zwj-,}sequences.txt"
      print "(eval-when-compile (require 'regexp-opt))"
+
+     # The following codepoints are not emoji, but they are part of
+     # emoji sequences.  We have code in font.c:font_range that will
+     # try to display them with the emoji font anyway.
+
+     trigger_codepoints[1] = "261D"
+     trigger_codepoints[2] = "26F9"
+     trigger_codepoints[3] = "270C"
+     trigger_codepoints[4] = "270D"
+     trigger_codepoints[5] = "2764"
+     trigger_codepoints[6] = "1F3CB"
+     trigger_codepoints[7] = "1F3CC"
+     trigger_codepoints[8] = "1F3F3"
+     trigger_codepoints[9] = "1F3F4"
+     trigger_codepoints[10] = "1F441"
+     trigger_codepoints[11] = "1F574"
+     trigger_codepoints[12] = "1F575"
+     trigger_codepoints[13] = "1F590"
+
+     printf "(setq auto-composition-emoji-eligible-codepoints\n"
+     printf "'("
+
+     for (trig in trigger_codepoints)
+     {
+         printf("\n?\\N{U+%s}", trigger_codepoints[trig])
+     }
+     printf "\n))\n\n"
+
+     #  We add entries for 'codepoint U+FE0F' here to ensure that the
+     # code in font_range is triggered.
+
+     for (trig in trigger_codepoints)
+     {
+         codepoint = trigger_codepoints[trig]
+         c = sprintf("\\N{U+%s}", codepoint)
+         vec[codepoint] = vec[codepoint] "\n\"" c "\\N{U+FE0F}\""
+     }
+
      print "(dolist (elt `("
 
      for (elt in ch)
@@ -98,6 +136,5 @@ END {
      print "                                           0"
      print "                                    
'compose-gstring-for-graphic))))"
 
-     print "\n"
-     print "(provide 'emoji-zwj)"
+     printf "\n(provide 'emoji-zwj)"
 }
diff --git a/lisp/composite.el b/lisp/composite.el
index 859253e..99f528a 100644
--- a/lisp/composite.el
+++ b/lisp/composite.el
@@ -834,8 +834,15 @@ and the second is a glyph for a variation selector."
              (lgstring-set-glyph gstring 1 nil)
              (throw 'tag gstring)))))))
 
+;; We explicitly don't handle #xFE0F (VS-16) here, because that's
+;; taken care of by font_range in font.c, which will check for an
+;; emoji font for codepoints used in compositions even if they're not
+;; emoji themselves, and thus choose the Emoji presentation for them
+;; when followed by VS-16.  VS-15 *is* handled here, because if it's
+;; handled in font_range, we end up choosing the Emoji presentation
+;; rather than the Text presentation.
 (let ((elt '([".." 1 compose-gstring-for-variation-glyph])))
-  (set-char-table-range composition-function-table '(#xFE00 . #xFE0F) elt)
+  (set-char-table-range composition-function-table '(#xFE00 . #xFE0E) elt)
   (set-char-table-range composition-function-table '(#xE0100 . #xE01EF) elt))
 
 (defun auto-compose-chars (func from to font-object string direction)
diff --git a/src/composite.c b/src/composite.c
index f456e7a..c170805 100644
--- a/src/composite.c
+++ b/src/composite.c
@@ -2124,6 +2124,17 @@ GSTRING, or modify GSTRING itself and return it.
 See also the documentation of `auto-composition-mode'.  */);
   Vcomposition_function_table = Fmake_char_table (Qnil, Qnil);
 
+  DEFVAR_LISP ("auto-composition-emoji-eligible-codepoints", 
Vauto_composition_emoji_eligible_codepoints,
+              doc: /* List of codepoints for which auto-composition will check 
for an emoji font.
+
+These are codepoints which have Emoji_Presentation = No, and thus by
+default are not displayed as emoji.  In certain circumstances, such as
+when followed by U+FE0F (VS-16) the emoji font should be used for
+them anyway.
+
+This list is auto-generated, you should not need to modify it.  */);
+  Vauto_composition_emoji_eligible_codepoints = Qnil;
+
   defsubr (&Scompose_region_internal);
   defsubr (&Scompose_string_internal);
   defsubr (&Sfind_composition_internal);
diff --git a/src/font.c b/src/font.c
index 83f0f82..6cd4a6b 100644
--- a/src/font.c
+++ b/src/font.c
@@ -3860,6 +3860,23 @@ font_at (int c, ptrdiff_t pos, struct face *face, struct 
window *w,
 
 #ifdef HAVE_WINDOW_SYSTEM
 
+/* Check if CH is a codepoint for which we should attempt to use the
+   emoji font, even if the codepoint itself has Emoji_Presentation =
+   No.  Vauto_composition_emoji_eligible_codepoints is filled in for
+   us by admin/unidata/emoji-zwj.awk.  */
+static bool
+codepoint_is_emoji_eligible (int ch)
+{
+  if (EQ (CHAR_TABLE_REF (Vchar_script_table, ch), Qemoji))
+    return true;
+
+  if (! NILP (Fmemq (make_fixnum (ch),
+                    Vauto_composition_emoji_eligible_codepoints)))
+    return true;
+
+  return false;
+}
+
 /* Check how many characters after character/byte position POS/POS_BYTE
    (at most to *LIMIT) can be displayed by the same font in the window W.
    FACE, if non-NULL, is the face selected for the character at POS.
@@ -3907,8 +3924,7 @@ font_range (ptrdiff_t pos, ptrdiff_t pos_byte, ptrdiff_t 
*limit,
   /* If the composition was triggered by an emoji, use a character
      from 'script-representative-chars', rather than the first
      character in the string, to determine the font to use.  */
-  if (EQ (CHAR_TABLE_REF (Vchar_script_table, ch),
-         Qemoji))
+  if (codepoint_is_emoji_eligible (ch))
     {
       Lisp_Object val = assq_no_quit (Qemoji, Vscript_representative_chars);
       if (CONSP (val))