Logo

Programming-Idioms

  • Pascal
  • VB
  • Lua

Idiom #169 String length

Assign to the integer n the number of characters of the string s.
Make sure that multibyte characters are properly handled.
n can be different from the number of bytes of s.

local n = utf8.len(s)

The utf8 module is new in Lua 5.3
local utf8={}
function utf8.bytes(str,index)
 local byte=string.byte(str,index)
 local ret
 if     byte==nil then ret=0
 elseif byte<128  then ret=1
 elseif byte<192  then ret=2
 elseif byte<224  then ret=3
 else                  ret=4
 end
 return ret
end
function utf8.len(str)
 local count=0
 local fini=#str+1
 local index=1
 while index~=fini do
  count=count+1
  index=index+utf8.bytes(str,index)
 end
 return count
end
local n=utf8.len(s)

Use for lua version under 5.3. (which doesn't have utf8 lib)
uses sysutils;
n := s.length;

Works correctly if s is of type UnicodeString and the string is not encoded using combining characters.
uses LazUtf8;
n := length(s);

Single byte encoding or widestring, plain pascal
uses LazUtf8;
n := Utf8Length(s);

UTF8-encoding, as used in Lazarus
Dim n As Integer = s.Length

n : Integer := s'Length;
New implementation...
< > ⌨
programming-idioms.org 
local n = utf8.len(s)
local utf8={}
function utf8.bytes(str,index)
 local byte=string.byte(str,index)
 local ret
 if     byte==nil then ret=0
 elseif byte<128  then ret=1
 elseif byte<192  then ret=2
 elseif byte<224  then ret=3
 else                  ret=4
 end
 return ret
end
function utf8.len(str)
 local count=0
 local fini=#str+1
 local index=1
 while index~=fini do
  count=count+1
  index=index+utf8.bytes(str,index)
 end
 return count
end
local n=utf8.len(s)
n := s.length;
n := length(s);
n := Utf8Length(s);
Dim n As Integer = s.Length

n : Integer := s'Length;
(defn n[s] (.codePointCount s 0 (count s)))
(def n (.codePointCount s 0 (count s)))
IDENTIFICATION DIVISION.
PROGRAM-ID. length.
PROCEDURE DIVISION.
   MOVE FUNCTION LENGTH(s) TO n
STOP RUN.
auto utf8len(std::string_view const& s) -> size_t
{
	std::setlocale(LC_ALL, "en_US.utf8");

	auto n = size_t{};
	auto size = size_t{};
	auto mb = std::mbstate_t{};

	while(size < s.length())
	{
		size += mbrlen(s.data() + size, s.length() - size, &mb);
		n += 1;
	}

	return n;
}
int n = s.Length;
size_t n = s.walkLength;
size_t n = s.byGrapheme.walkLength;
size_t n = s.length;
int n = s.length;
n = String.length s
N = string:length(S)
n = len(s)
n := utf8.RuneCountInString(s)
n = length s
const n = [...s].length;
const n = s.length;
int n = s.length();
val n = s.length
(setf n (length s))
(length s)
NSUInteger n=s.length;
$n = mb_strlen($s, 'UTF-8');
my $n = length( $s );
n = len(s)
n = s.size
n = s.length
let n = s.chars().count();
val n = s.length()
n := s size.