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.
4e4473c927

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.
98945560c1

runtime/doc/builtin.txt

@@ -77,6 +77,7 @@ changenr()			Number	current change number
 chanclose({id} [, {stream}])	Number	Closes a channel or one of its streams
 chansend({id}, {data})		Number	Writes {data} to channel
 char2nr({expr} [, {utf8}])	Number	ASCII/UTF-8 value of first char in {expr}
+charclass({string})		Number	character class of {string}
 charcol({expr})			Number	column number of cursor or mark
 charidx({string}, {idx} [, {countcc}])
 				Number	char index of byte {idx} in {string}
@@ -1064,7 +1065,19 @@ char2nr({string} [, {utf8}])					*char2nr()*
 
 		Can also be used as a |method|: >
 			GetChar()->char2nr()
-<
+
+charclass({string})					*charclass()*
+		Return the character class of the first character in {string}.
+		The character class is one of:
+			0	blank
+			1	punctuation
+			2	word character
+			3	emoji
+			other	specific Unicode class
+		The class is used in patterns and word motions.
+		Returns 0 if {string} is not a |String|.
+
+
 							*charcol()*
 charcol({expr})	Same as |col()| but returns the character index of the column
 		position given with {expr} instead of the byte position.

runtime/doc/usr_41.txt

@@ -606,6 +606,7 @@ String manipulation:					*string-functions*
 	strtrans()		translate a string to make it printable
 	tolower()		turn a string to lowercase
 	toupper()		turn a string to uppercase
+	charclass()		class of a character
 	match()			position where a pattern matches in a string
 	matchend()		position where a pattern match ends in a string
 	matchfuzzy()		fuzzy matches a string in a list of strings

runtime/tools/emoji_list.vim

@@ -0,0 +1,21 @@
+" Script to fill the window with emoji characters, one per line.
+" Source this script: :source %
+
+if &modified
+  new
+else
+  enew
+endif
+
+lua << EOF
+  local lnum = 1
+  for c = 0x100, 0x1ffff do
+    local cs = vim.fn.nr2char(c)
+    if vim.fn.charclass(cs) == 3 then
+      vim.fn.setline(lnum, '|' .. cs .. '| ' .. vim.fn.strwidth(cs))
+      lnum = lnum + 1
+    end
+  end
+EOF
+
+set nomodified

src/nvim/eval.lua

@@ -72,6 +72,7 @@ return {
     chanclose={args={1, 2}},
     chansend={args=2},
     char2nr={args={1, 2}, base=1},
+    charclass={args=1, base=1},
     charcol={args=1, base=1},
     charidx={args={2, 3}, base=1},
     chdir={args=1, base=1},

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);
+}

src/nvim/testdir/test_functions.vim

@@ -1769,6 +1769,13 @@ func Test_char2nr()
   call assert_equal(12354, char2nr('あ', 1))
 endfunc
 
+func Test_charclass()
+  call assert_equal(0, charclass(' '))
+  call assert_equal(1, charclass('.'))
+  call assert_equal(2, charclass('x'))
+  call assert_equal(3, charclass("\u203c"))
+endfunc
+
 func Test_eventhandler()
   call assert_equal(0, eventhandler())
 endfunc