Add the utf16idx() and strutf16len() functions and add UTF-16 flag to the byteidx(), byteidxcomp() and charidx() functions

Author: yegappan

runtime/doc/builtin.txt

@@ -81,8 +81,10 @@ bufnr([{buf} [, {create}]])	Number	Number of the buffer {buf}
 bufwinid({buf})			Number	window ID of buffer {buf}
 bufwinnr({buf})			Number	window number of buffer {buf}
 byte2line({byte})		Number	line number at byte count {byte}
-byteidx({expr}, {nr})		Number	byte index of {nr}'th char in {expr}
-byteidxcomp({expr}, {nr})	Number	byte index of {nr}'th char in {expr}
+byteidx({expr}, {nr} [, {utf16}])
+				Number	byte index of {nr}'th char in {expr}
+byteidxcomp({expr}, {nr} [, {utf16}])
+				Number	byte index of {nr}'th char in {expr}
 call({func}, {arglist} [, {dict}])
 				any	call {func} with arguments {arglist}
 ceil({expr})			Float	round {expr} up
@@ -117,7 +119,7 @@ changenr()			Number	current change number
 char2nr({expr} [, {utf8}])	Number	ASCII/UTF-8 value of first char in {expr}
 charclass({string})		Number	character class of {string}
 charcol({expr} [, {winid}])	Number	column number of cursor or mark
-charidx({string}, {idx} [, {countcc}])
+charidx({string}, {idx} [, {countcc} [, {utf16}]])
 				Number	char index of byte {idx} in {string}
 chdir({dir})			String	change current working directory
 cindent({lnum})			Number	C indent for line {lnum}
@@ -604,6 +606,8 @@ strptime({format}, {timestring})
 strridx({haystack}, {needle} [, {start}])
 				Number	last index of {needle} in {haystack}
 strtrans({expr})		String	translate string to make it printable
+strutf16len({string} [, {countcc}])
+				Number	number of UTF-16 code units in {string}
 strwidth({expr})		Number	display cell length of the String {expr}
 submatch({nr} [, {list}])	String or List
 					specific match in ":s" or substitute()
@@ -704,6 +708,8 @@ undofile({name})		String	undo file name for {name}
 undotree()			List	undo file tree
 uniq({list} [, {func} [, {dict}]])
 				List	remove adjacent duplicates from a list
+utf16idx({string}, {idx} [, {countcc} [, {charidx}]])
+				Number	UTF-16 index of byte {idx} in {string}
 values({dict})			List	values in {dict}
 virtcol({expr} [, {list}])	Number or List
 					screen column of cursor or mark
@@ -1363,7 +1369,7 @@ byte2line({byte})					*byte2line()*
 <		{not available when compiled without the |+byte_offset|
 		feature}
 
-byteidx({expr}, {nr})					*byteidx()*
+byteidx({expr}, {nr} [, {utf16}])			*byteidx()*
 		Return byte index of the {nr}'th character in the String
 		{expr}.  Use zero for the first character, it then returns
 		zero.
@@ -1373,6 +1379,13 @@ byteidx({expr}, {nr})					*byteidx()*
 		length is added to the preceding base character.  See
 		|byteidxcomp()| below for counting composing characters
 		separately.
+		When {utf16} is TRUE, {nr} is used as the UTF-16 index in the
+		String {expr} instead of as the character index.  The UTF-16
+		index is the index in the string when it is encoded with
+		16-bit words.  If the specified UTF-16 index is in the middle
+		of a character (e.g. in a 4-byte character), then the byte
+		index of the first byte in the character is returned.
+		Refer to |string-offset-encoding| for more information.
 		Example : >
 			echo matchstr(str, ".", byteidx(str, 3))
 <		will display the fourth character.  Another way to do the
@@ -1384,11 +1397,17 @@ byteidx({expr}, {nr})					*byteidx()*
 		If there are less than {nr} characters -1 is returned.
 		If there are exactly {nr} characters the length of the string
 		in bytes is returned.
-
+		See |charidx()| and |utf16idx()| for getting the character and
+		UTF-16 index respectively from the byte index.
+		Examples: >
+			echo byteidx('a😊😊', 2)	returns 5
+			echo byteidx('a😊😊', 2, 1)	returns 1
+			echo byteidx('a😊😊', 3, 1)	returns 5
+<
 		Can also be used as a |method|: >
 			GetName()->byteidx(idx)
 
-byteidxcomp({expr}, {nr})					*byteidxcomp()*
+byteidxcomp({expr}, {nr} [, {utf16}])			*byteidxcomp()*
 		Like byteidx(), except that a composing character is counted
 		as a separate character.  Example: >
 			let s = 'e' .. nr2char(0x301)
@@ -1493,7 +1512,7 @@ charcol({expr} [, {winid}])				*charcol()*
 			GetPos()->col()
 <
 							*charidx()*
-charidx({string}, {idx} [, {countcc}])
+charidx({string}, {idx} [, {countcc} [, {utf16}]])
 		Return the character index of the byte at {idx} in {string}.
 		The index of the first character is zero.
 		If there are no multibyte characters the returned value is
@@ -1503,17 +1522,22 @@ charidx({string}, {idx} [, {countcc}])
 		added to the preceding base character.
 		When {countcc} is |TRUE|, then composing characters are
 		counted as separate characters.
+		When {utf16} is TRUE, {idx} is used as the UTF-16 index in the
+		String {expr} instead of as the byte index.
 		Returns -1 if the arguments are invalid or if {idx} is greater
 		than the index of the last byte in {string}.  An error is
 		given if the first argument is not a string, the second
 		argument is not a number or when the third argument is present
 		and is not zero or one.
 		See |byteidx()| and |byteidxcomp()| for getting the byte index
-		from the character index.
+		from the character index and |utf16idx()| for getting the
+		UTF-16 index from the character index.
+		Refer to |string-offset-encoding| for more information.
 		Examples: >
 			echo charidx('áb́ć', 3)		returns 1
 			echo charidx('áb́ć', 6, 1)	returns 4
 			echo charidx('áb́ć', 16)		returns -1
+			echo charidx('a😊😊', 4, 0, 1)	returns 2
 <
 		Can also be used as a |method|: >
 			GetName()->charidx(idx)
@@ -9243,6 +9267,27 @@ strtrans({string})					*strtrans()*
 		Can also be used as a |method|: >
 			GetString()->strtrans()
 
+strutf16len({string} [, {countcc}])			*strutf16len()*
+		The result is a Number, which is the number of UTF-16 code
+		units in String {string}.
+		When {countcc} is TRUE, composing characters are counted
+		separately.
+		When {countcc} is omitted or FALSE, composing characters are
+		ignored.
+
+		Returns zero on error.
+
+		Also see |strlen()| and |strcharlen()|.
+		Examples: >
+		    echo strutf16len('a')		returns 1
+		    echo strutf16len('©')		returns 1
+		    echo strutf16len('😊')		returns 2
+		    echo strutf16len('ą́')		returns 1
+		    echo strutf16len('ą́', v:true)	returns 3
+
+		Can also be used as a |method|: >
+			GetText()->strutf16len()
+<
 strwidth({string})					*strwidth()*
 		The result is a Number, which is the number of display cells
 		String {string} occupies.  A Tab character is counted as one
@@ -10058,6 +10103,31 @@ uniq({list} [, {func} [, {dict}]])			*uniq()* *E882*
 
 		Can also be used as a |method|: >
 			mylist->uniq()
+<
+							*utf16idx()*
+utf16idx({string}, {idx} [, {countcc} [, {charidx}]])
+		Same as |charidx()| but returns the UTF-16 index of the byte
+		at {idx} in {string}.
+		When {charidx} is TRUE, {idx} is used as the character index
+		in the String {string} instead of as the byte index.
+		An {idx} in the middle of a UTF-8 sequence is rounded upwards
+		to the end of that sequence.
+		See |byteidx()| and |byteidxcomp()| for getting the byte index
+		from the UTF-16 index and |charidx()| for getting the
+		character index from the UTF-16 index.
+		Refer to |string-offset-encoding| for more information.
+		Examples: >
+			echo utf16idx('a😊😊', 3)	returns 2
+			echo utf16idx('a😊😊', 7)	returns 4
+			echo utf16idx('a😊😊', 1, 0, 1)	returns 2
+			echo utf16idx('a😊😊', 2, 0, 1)	returns 4
+			echo utf16idx('aą́c', 6)		returns 2
+			echo utf16idx('aą́c', 6, 1)	returns 4
+			echo utf16idx('a😊😊', 9)	returns -1
+<
+		Can also be used as a |method|: >
+			GetName()->utf16idx(idx)
+
 
 values({dict})						*values()*
 		Return a |List| with all the values of {dict}.  The |List| is

runtime/doc/eval.txt

@@ -1580,6 +1580,26 @@ Examples: >
 	echo $"The square root of {{9}} is {sqrt(9)}"
 <	The square root of {9} is 3.0 ~
 
+						*string-offset-encoding*
+A string can consist of one byte or two byte or four byte characters.  A
+string offset can use UTF-8 encoding (byte) or UTF-16 encoding (16-bit words)
+or UTF-32 encoding (character).  In legacy vim scripts UTF-8 encoding (byte)
+is used for string offsets and in vim9 scripts UTF-32 encoding (character) is
+used for string offsets.
+
+The different offsets for the string "a©😊" are below:
+
+  UTF-8 offsets:
+      [0]: 61, [1]: C2, [2]: A9, [3]: F0, [4]: 9F, [5]: 98, [6]: 8A
+  UTF-16 offsets:
+      [0]: 61, [1]: C2 A9, [2]: F0 9F, [3]: 98 8A
+  UTF-32 offsets:
+      [0]: 61, [1]: C2 A9, [2]: F0 9F 98 8A
+
+The functions |byteidx()|, |utf16idx()| and |charidx()| can be used to convert
+between these indices.  The functions |strlen()|, |strutf16len()| and
+|strcharlen()| return the number of bytes, UTF-16 code units and characters in
+a string respectively.
 
 option						*expr-option* *E112* *E113*
 ------

runtime/doc/usr_41.txt

@@ -754,6 +754,7 @@ String manipulation:					*string-functions*
 	strlen()		length of a string in bytes
 	strcharlen()		length of a string in characters
 	strchars()		number of characters in a string
+	strutf16len()		number of UTF-16 code units in a string
 	strwidth()		size of string when displayed
 	strdisplaywidth()	size of string when displayed, deals with tabs
 	setcellwidths()		set character cell width overrides
@@ -771,6 +772,7 @@ String manipulation:					*string-functions*
 	byteidx()		byte index of a character in a string
 	byteidxcomp()		like byteidx() but count composing characters
 	charidx()		character index of a byte in a string
+	utf16idx()		UTF-16 index of a byte in a string
 	repeat()		repeat a string multiple times
 	eval()			evaluate a string expression
 	execute()		execute an Ex command and get the output

src/evalfunc.c

@@ -1751,9 +1751,9 @@ static funcentry_T global_functions[] =
 			ret_number,	    f_bufwinnr},
     {"byte2line",	1, 1, FEARG_1,	    arg1_number,
 			ret_number,	    f_byte2line},
-    {"byteidx",		2, 2, FEARG_1,	    arg2_string_number,
+    {"byteidx",		2, 3, FEARG_1,	    arg3_string_number_bool,
 			ret_number,	    f_byteidx},
-    {"byteidxcomp",	2, 2, FEARG_1,	    arg2_string_number,
+    {"byteidxcomp",	2, 3, FEARG_1,	    arg3_string_number_bool,
 			ret_number,	    f_byteidxcomp},
     {"call",		2, 3, FEARG_1,	    arg3_any_list_dict,
 			ret_any,	    f_call},
@@ -1803,7 +1803,7 @@ static funcentry_T global_functions[] =
 			ret_number,	    f_charclass},
     {"charcol",		1, 2, FEARG_1,	    arg2_string_or_list_number,
 			ret_number,	    f_charcol},
-    {"charidx",		2, 3, FEARG_1,	    arg3_string_number_bool,
+    {"charidx",		2, 4, FEARG_1,	    arg3_string_number_bool,
 			ret_number,	    f_charidx},
     {"chdir",		1, 1, FEARG_1,	    arg1_string,
 			ret_string,	    f_chdir},
@@ -2601,6 +2601,8 @@ static funcentry_T global_functions[] =
 			ret_number,	    f_strridx},
     {"strtrans",	1, 1, FEARG_1,	    arg1_string,
 			ret_string,	    f_strtrans},
+    {"strutf16len",	1, 2, FEARG_1,	    arg2_string_bool,
+			ret_number,	    f_strutf16len},
     {"strwidth",	1, 1, FEARG_1,	    arg1_string,
 			ret_number,	    f_strwidth},
     {"submatch",	1, 2, FEARG_1,	    arg2_number_bool,
@@ -2785,6 +2787,8 @@ static funcentry_T global_functions[] =
 			ret_dict_any,	    f_undotree},
     {"uniq",		1, 3, FEARG_1,	    arg13_sortuniq,
 			ret_first_arg,	    f_uniq},
+    {"utf16idx",	2, 4, FEARG_1,	    arg3_string_number_bool,
+			ret_number,	    f_utf16idx},
     {"values",		1, 1, FEARG_1,	    arg1_dict_any,
 			ret_list_member,    f_values},
     {"virtcol",		1, 2, FEARG_1,	    arg2_string_or_list_bool,

src/proto/strings.pro

@@ -36,12 +36,14 @@ void f_string(typval_T *argvars, typval_T *rettv);
 void f_strlen(typval_T *argvars, typval_T *rettv);
 void f_strcharlen(typval_T *argvars, typval_T *rettv);
 void f_strchars(typval_T *argvars, typval_T *rettv);
+void f_strutf16len(typval_T *argvars, typval_T *rettv);
 void f_strdisplaywidth(typval_T *argvars, typval_T *rettv);
 void f_strwidth(typval_T *argvars, typval_T *rettv);
 void f_strcharpart(typval_T *argvars, typval_T *rettv);
 void f_strpart(typval_T *argvars, typval_T *rettv);
 void f_strridx(typval_T *argvars, typval_T *rettv);
 void f_strtrans(typval_T *argvars, typval_T *rettv);
+void f_utf16idx(typval_T *argvars, typval_T *rettv);
 void f_tolower(typval_T *argvars, typval_T *rettv);
 void f_toupper(typval_T *argvars, typval_T *rettv);
 void f_tr(typval_T *argvars, typval_T *rettv);