vim-patch:8.2.{1536,1540}: charclass() (#19748)

vim-patch:8.2.1536: cannot get the class of a character; emoji widths are wrong

Problem:    Cannot get the class of a character; emoji widths are wrong in
            some environments.
Solution:   Add charclass(). Update some emoji widths.  Add script to check
            emoji widths.
https://github.com/vim/vim/commit/4e4473c927167fd24e5c8df90e0e8035080cf2da

Use latest charclass() docs from Vim.
Rewrite DoIt() in emoji_list.vim in Lua.
Omit emoji table updates:
- emoji_width update looks wrong as these added ranges are only double-width when followed by 0xFE0F.
- Other updates are too old.

vim-patch:8.2.1540: the user cannot try out emoji character widths

Problem:    The user cannot try out emoji character widths.
Solution:   Move the emoji script to the runtime/tools directory.
https://github.com/vim/vim/commit/98945560c1ae6e2ddee820a7de718a36e3f4b6e5

1 files changed, 16 insertions, 5 deletions

diff --git a/src/nvim/mbyte.c b/src/nvim/mbyte.c
index e4d2d35c1b..378a08131d 100644
--- a/src/nvim/mbyte.c
+++ b/src/nvim/mbyte.c
@@ -1182,6 +1182,11 @@ int utf_class_tab(const int c, const uint64_t *const chartab)
     return 1;               // punctuation
   }
 
+  // emoji
+  if (intable(emoji_all, ARRAY_SIZE(emoji_all), c)) {
+    return 3;
+  }
+
   // binary search in table
   while (top >= bot) {
     mid = (bot + top) / 2;
@@ -1194,11 +1199,6 @@ int utf_class_tab(const int c, const uint64_t *const chartab)
     }
   }
 
-  // emoji
-  if (intable(emoji_all, ARRAY_SIZE(emoji_all), c)) {
-    return 3;
-  }
-
   // most other characters are "word" characters
   return 2;
 }
@@ -2858,3 +2858,14 @@ void f_setcellwidths(typval_T *argvars, typval_T *rettv, FunPtr fptr)
   xfree(cw_table_save);
   redraw_all_later(NOT_VALID);
 }
+
+void f_charclass(typval_T *argvars, typval_T *rettv, FunPtr fptr)
+{
+  if (argvars[0].v_type != VAR_STRING
+      || argvars[0].vval.v_string == NULL
+      || *argvars[0].vval.v_string == NUL) {
+    emsg(_(e_stringreq));
+    return;
+  }
+  rettv->vval.v_number = mb_get_class((const char_u *)argvars[0].vval.v_string);
+}