From bcfc570bac07344cf4409d95972b504bcbc26d24 Mon Sep 17 00:00:00 2001 From: Robert Pluim Date: Sun, 19 Sep 2021 21:07:36 +0200 Subject: [PATCH] Base emoji script membership on Emoji_Presentation The Emoji property describes which codepoints can be displayed as emoji, but Emoji_Presentation governs which are displayed as emoji by default. * admin/notes/unicode: Adjust check-emoji-coverage to look in the Emoji_Presentation sections of emoji-data.txt * admin/unidata/blocks.awk: Assign emoji script using the Emoji_Presentation section. --- admin/notes/unicode | 2 +- admin/unidata/blocks.awk | 7 +------ 2 files changed, 2 insertions(+), 7 deletions(-) diff --git a/admin/notes/unicode b/admin/notes/unicode index 9dc6f3bdca3..0b2ce527948 100644 --- a/admin/notes/unicode +++ b/admin/notes/unicode @@ -100,7 +100,7 @@ FONT-NAME-REGEXP is checked using `string-match'." (save-excursion (goto-char (point-min)) (let (res char name ifont) - (while (re-search-forward "; Emoji [^(]+(\\(.\\)[).\uFE0F]" nil t) + (while (re-search-forward "; Emoji_Presentation [^(]+(\\(.\\)[).]" nil t) (setq char (aref (match-string 1) 0)) (setq ifont (car (internal-char-font nil char))) (when ifont diff --git a/admin/unidata/blocks.awk b/admin/unidata/blocks.awk index 6e52b52f674..29022bf7ddf 100755 --- a/admin/unidata/blocks.awk +++ b/admin/unidata/blocks.awk @@ -202,12 +202,7 @@ FILENAME ~ "Blocks.txt" && /^[0-9A-F]/ { } } -# The space after 'Emoji' is significant in the next two rules. -# This purposely and deliberately excludes codepoints <= 00FF -FILENAME ~ "emoji-data.txt" && /^00[0-9A-F][0-9A-F].*; Emoji / { - next -} -FILENAME ~ "emoji-data.txt" && /^[0-9A-F].*; Emoji / { +FILENAME ~ "emoji-data.txt" && /^[0-9A-F].*; Emoji_Presentation / { sep = index($1, "..") len = length($1) if (sep > 0) {