patch 8.2.1517: cannot easily get the character under the cursorv8.2.1517

Problem:    Cannot easily get the character under the cursor.
Solution:   Add the {chars} argument to strpart().

4 files changed, 36 insertions, 14 deletions

diff --git a/runtime/doc/eval.txt b/runtime/doc/eval.txt
index 370964e56..09ef97963 100644
--- a/runtime/doc/eval.txt
+++ b/runtime/doc/eval.txt
@@ -2836,7 +2836,8 @@ str2list({expr} [, {utf8}])	List	convert each character of {expr} to
 str2nr({expr} [, {base} [, {quoted}]])
 				Number	convert String to Number
 strcharpart({str}, {start} [, {len}])
-				String	{len} characters of {str} at {start}
+				String	{len} characters of {str} at
+					character {start}
 strchars({expr} [, {skipcc}])	Number	character length of the String {expr}
 strdisplaywidth({expr} [, {col}]) Number display length of the String {expr}
 strftime({format} [, {time}])	String	format time with a specified format
@@ -2845,8 +2846,9 @@ stridx({haystack}, {needle} [, {start}])
 				Number	index of {needle} in {haystack}
 string({expr})			String	String representation of {expr} value
 strlen({expr})			Number	length of the String {expr}
-strpart({str}, {start} [, {len}])
-				String	{len} bytes of {str} at byte {start}
+strpart({str}, {start} [, {len} [, {chars}]])
+				String	{len} bytes/chars of {str} at
+					byte {start}
 strptime({format}, {timestring})
 				Number	Convert {timestring} to unix timestamp
 strridx({haystack}, {needle} [, {start}])
@@ -3418,7 +3420,8 @@ byte2line({byte})					*byte2line()*
 
 byteidx({expr}, {nr})					*byteidx()*
 		Return byte index of the {nr}'th character in the string
-		{expr}.  Use zero for the first character, it returns zero.
+		{expr}.  Use zero for the first character, it then returns
+		zero.
 		This function is only useful when there are multibyte
 		characters, otherwise the returned value is equal to {nr}.
 		Composing characters are not counted separately, their byte
@@ -9948,17 +9951,22 @@ strlen({expr})	The result is a Number, which is the length of the String
 		{expr} in bytes.
 		If the argument is a Number it is first converted to a String.
 		For other types an error is given.
-		If you want to count the number of multi-byte characters use
+		If you want to count the number of multibyte characters use
 		|strchars()|.
 		Also see |len()|, |strdisplaywidth()| and |strwidth()|.
 
 		Can also be used as a |method|: >
 			GetString()->strlen()
 
-strpart({src}, {start} [, {len}])			*strpart()*
+strpart({src}, {start} [, {len} [, {chars}]])			*strpart()*
 		The result is a String, which is part of {src}, starting from
 		byte {start}, with the byte length {len}.
-		To count characters instead of bytes use |strcharpart()|.
+		When {chars} is present and TRUE then {len} is the number of
+		characters positions (composing characters are not counted
+		separately, thus "1" means one base character and any
+		following composing characters).
+		To count {start} as characters instead of bytes use
+		|strcharpart()|.
 
 		When bytes are selected which do not exist, this doesn't
 		result in an error, the bytes are simply omitted.
@@ -9970,8 +9978,8 @@ strpart({src}, {start} [, {len}])			*strpart()*
 			strpart("abcdefg", 3)	    == "defg"
 
 <		Note: To get the first character, {start} must be 0.  For
-		example, to get three bytes under and after the cursor: >
-			strpart(getline("."), col(".") - 1, 3)
+		example, to get the character under the cursor: >
+			strpart(getline("."), col(".") - 1, 1, v:true)
 <
 		Can also be used as a |method|: >
 			GetText()->strpart(5)
diff --git a/src/evalfunc.c b/src/evalfunc.c
index c8747e2c1..fcfd4b10d 100644
--- a/src/evalfunc.c
+++ b/src/evalfunc.c
@@ -950,7 +950,7 @@ static funcentry_T global_functions[] =
     {"stridx",		2, 3, FEARG_1,	  ret_number,	f_stridx},
     {"string",		1, 1, FEARG_1,	  ret_string,	f_string},
     {"strlen",		1, 1, FEARG_1,	  ret_number,	f_strlen},
-    {"strpart",		2, 3, FEARG_1,	  ret_string,	f_strpart},
+    {"strpart",		2, 4, FEARG_1,	  ret_string,	f_strpart},
     {"strptime",	2, 2, FEARG_1,	  ret_number,
 #ifdef HAVE_STRPTIME
 	    f_strptime
@@ -8270,10 +8270,8 @@ f_strpart(typval_T *argvars, typval_T *rettv)
     else
 	len = slen - n;	    // default len: all bytes that are available.
 
-    /*
-     * Only return the overlap between the specified part and the actual
-     * string.
-     */
+    // Only return the overlap between the specified part and the actual
+    // string.
     if (n < 0)
     {
 	len += n;
@@ -8286,6 +8284,16 @@ f_strpart(typval_T *argvars, typval_T *rettv)
     else if (n + len > slen)
 	len = slen - n;
 
+    if (argvars[2].v_type != VAR_UNKNOWN && argvars[3].v_type != VAR_UNKNOWN)
+    {
+	int off;
+
+	// length in characters
+	for (off = n; off < slen && len > 0; --len)
+	    off += mb_ptr2len(p + off);
+	len = off - n;
+    }
+
     rettv->v_type = VAR_STRING;
     rettv->vval.v_string = vim_strnsave(p + n, len);
 }
diff --git a/src/testdir/test_functions.vim b/src/testdir/test_functions.vim
index dc06bd72e..e15199b78 100644
--- a/src/testdir/test_functions.vim
+++ b/src/testdir/test_functions.vim
@@ -513,6 +513,10 @@ func Test_strpart()
 
   call assert_equal('lép', strpart('éléphant', 2, 4))
   call assert_equal('léphant', strpart('éléphant', 2))
+
+  call assert_equal('é', strpart('éléphant', 0, 1, 1))
+  call assert_equal('ép', strpart('éléphant', 3, 2, v:true))
+  call assert_equal('ó', strpart('cómposed', 1, 1, 1))
 endfunc
 
 func Test_tolower()
diff --git a/src/version.c b/src/version.c
index 4c2794af0..9eb448b2d 100644
--- a/src/version.c
+++ b/src/version.c
@@ -755,6 +755,8 @@ static char *(features[]) =
 static int included_patches[] =
 {   /* Add new patch number below this line */
 /**/
+    1517,
+/**/
     1516,
 /**/
     1515,