vim-patch:8.2.2606: strchars() defaults to counting composing characters

Problem:    strchars() defaults to counting composing characters.
Solution:   Add strcharlen() which ignores composing characters.

70ce8a1561

Use docs from latest Vim instead.

Co-authored-by: Bram Moolenaar <Bram@vim.org>

runtime/doc/builtin.txt

@@ -466,10 +466,11 @@ str2list({expr} [, {utf8}])	List	convert each character of {expr} to
 					ASCII/UTF-8 value
 str2nr({expr} [, {base} [, {quoted}]])
 				Number	convert String to Number
+strcharlen({expr})		Number	character length of the String {expr}
 strcharpart({str}, {start} [, {len}])
 				String	{len} characters of {str} at
 					character {start}
-strchars({expr} [, {skipcc}])	Number	character length of the String {expr}
+strchars({expr} [, {skipcc}])	Number	character count of the String {expr}
 strdisplaywidth({expr} [, {col}]) Number display length of the String {expr}
 strftime({format} [, {time}])	String	format time with a specified format
 strgetchar({str}, {index})	Number	get char {index} from {str}
@@ -7836,6 +7837,21 @@ str2nr({string} [, {base}])			*str2nr()*
 		Can also be used as a |method|: >
 			GetText()->str2nr()
 
+
+strcharlen({string})					*strcharlen()*
+		The result is a Number, which is the number of characters
+		in String {string}.  Composing characters are ignored.
+		|strchars()| can count the number of characters, counting
+		composing characters separately.
+
+		Returns 0 if {string} is empty or on error.
+
+		Also see |strlen()|, |strdisplaywidth()| and |strwidth()|.
+
+		Can also be used as a |method|: >
+			GetText()->strcharlen()
+
+
 strcharpart({src}, {start} [, {len}])			*strcharpart()*
 		Like |strpart()| but using character index and length instead
 		of byte index and length.  Composing characters are counted
@@ -7850,12 +7866,14 @@ strcharpart({src}, {start} [, {len}])			*strcharpart()*
 		Can also be used as a |method|: >
 			GetText()->strcharpart(5)
 
+
 strchars({string} [, {skipcc}])					*strchars()*
 		The result is a Number, which is the number of characters
 		in String {string}.
 		When {skipcc} is omitted or zero, composing characters are
 		counted separately.
 		When {skipcc} set to 1, Composing characters are ignored.
+		|strcharlen()| always does this.
 
 		Returns zero on error.
 

runtime/doc/usr_41.txt

@@ -619,7 +619,8 @@ String manipulation:					*string-functions*
 	stridx()		first index of a short string in a long string
 	strridx()		last index of a short string in a long string
 	strlen()		length of a string in bytes
-	strchars()		length of a string in characters
+	strcharlen()		length of a string in characters
+	strchars()		number of characters in a string
 	strwidth()		size of string when displayed
 	strdisplaywidth()	size of string when displayed, deals with tabs
 	setcellwidths()		set character cell width overrides

src/nvim/eval.lua

@@ -376,6 +376,7 @@ return {
     str2float={args=1, base=1},
     str2list={args={1, 2}, base=1},
     str2nr={args={1, 3}, base=1},
+    strcharlen={args=1, base=1},
     strcharpart={args={2, 3}, base=1},
     strchars={args={1, 2}, base=1},
     strdisplaywidth={args={1, 2}, base=1},

src/nvim/eval/funcs.c

@@ -8447,13 +8447,30 @@ static void f_strlen(typval_T *argvars, typval_T *rettv, EvalFuncData fptr)
   rettv->vval.v_number = (varnumber_T)strlen(tv_get_string(&argvars[0]));
 }
 
+static void strchar_common(typval_T *argvars, typval_T *rettv, bool skipcc)
+{
+  const char *s = tv_get_string(&argvars[0]);
+  varnumber_T len = 0;
+  int (*func_mb_ptr2char_adv)(const char_u **pp);
+
+  func_mb_ptr2char_adv = skipcc ? mb_ptr2char_adv : mb_cptr2char_adv;
+  while (*s != NUL) {
+    func_mb_ptr2char_adv((const char_u **)&s);
+    len++;
+  }
+  rettv->vval.v_number = len;
+}
+
+/// "strcharlen()" function
+static void f_strcharlen(typval_T *argvars, typval_T *rettv, EvalFuncData fptr)
+{
+  strchar_common(argvars, rettv, true);
+}
+
 /// "strchars()" function
 static void f_strchars(typval_T *argvars, typval_T *rettv, EvalFuncData fptr)
 {
-  const char *s = tv_get_string(&argvars[0]);
   int skipcc = false;
-  varnumber_T len = 0;
-  int (*func_mb_ptr2char_adv)(const char_u **pp);
 
   if (argvars[1].v_type != VAR_UNKNOWN) {
     skipcc = (int)tv_get_bool(&argvars[1]);
@@ -8461,12 +8478,7 @@ static void f_strchars(typval_T *argvars, typval_T *rettv, EvalFuncData fptr)
   if (skipcc < 0 || skipcc > 1) {
     semsg(_(e_using_number_as_bool_nr), skipcc);
   } else {
-    func_mb_ptr2char_adv = skipcc ? mb_ptr2char_adv : mb_cptr2char_adv;
-    while (*s != NUL) {
-      func_mb_ptr2char_adv((const char_u **)&s);
-      len++;
-    }
-    rettv->vval.v_number = len;
+    strchar_common(argvars, rettv, skipcc);
   }
 }
 

src/nvim/testdir/test_utf8.vim

@@ -12,7 +12,7 @@ func Test_visual_block_insert()
   bwipeout!
 endfunc
 
-" Test for built-in function strchars()
+" Test for built-in functions strchars() and strcharlen()
 func Test_strchars()
   let inp = ["a", "あいa", "A\u20dd", "A\u20dd\u20dd", "\u20dd"]
   let exp = [[1, 1, 1], [3, 3, 3], [2, 2, 1], [3, 3, 1], [1, 1, 1]]
@@ -21,6 +21,13 @@ func Test_strchars()
     call assert_equal(exp[i][1], inp[i]->strchars(0))
     call assert_equal(exp[i][2], strchars(inp[i], 1))
   endfor
+
+  let exp = [1, 3, 1, 1, 1]
+  for i in range(len(inp))
+    call assert_equal(exp[i], inp[i]->strcharlen())
+    call assert_equal(exp[i], strcharlen(inp[i]))
+  endfor
+
   call assert_fails("let v=strchars('abc', [])", 'E745:')
   call assert_fails("let v=strchars('abc', 2)", 'E1023:')
 endfunc