all tasks

Task/String-length/0DESCRIPTION

@@ -0,0 +1,5 @@
+In this task, the goal is to find the <em>character</em> and <em>byte</em> length of a string. This means encodings like [[UTF-8]] need to be handled properly, as there is not necessarily a one-to-one relationship between bytes and characters. By ''character'', we mean an individual Unicode ''code point'', not a user-visible ''grapheme'' containing combining characters. For example, the character length of "møøse" is 5 but the byte length is 7 in UTF-8 and 10 in UTF-16.
+
+Non-BMP code points (those between 0x10000 and 0x10FFFF) must also be handled correctly: answers should produce actual character counts in code points, not in code unit counts. Therefore a string like "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" (consisting of the 7 Unicode characters U+1D518  U+1D52B U+1D526 U+1D520 U+1D52C U+1D521 U+1D522) is 7 characters long, '''not''' 14 UTF-16 code units; and it is 28 bytes long whether encoded in UTF-8 or in  UTF-16.
+
+Please mark your examples with <nowiki>===Character Length=== or ===Byte Length===</nowiki>. If your language is capable of providing the string length in graphemes, mark those examples with <nowiki>===Grapheme Length===</nowiki>.  For example, the string "J̲o̲s̲é̲" ("J\x{332}o\x{332}s\x{332}e\x{301}\x{332}") has 4 user-visible graphemes, 9 characters (code points), and 14 bytes when encoded in UTF-8.

Task/String-length/1META.yaml

@@ -0,0 +1,2 @@
+---
+note: Basic language learning

Task/String-length/4D/string-length.4d

@@ -0,0 +1 @@
+$length:=Length("Hello, world!")

Task/String-length/ALGOL-68/string-length-1.alg

@@ -0,0 +1,7 @@
+BITS bits := bits pack((TRUE, TRUE, FALSE, FALSE)); # packed array of BOOL #
+BYTES bytes := bytes pack("Hello, world"); # packed array of CHAR #
+print((
+  "BITS and BYTES are fixed width:", new line,
+  "bits width:", bits width, ", max bits: ", max bits, ", bits:", bits, new line,
+  "bytes width: ",bytes width, ", UPB:",UPB STRING(bytes), ", string:", STRING(bytes),"!", new line
+))

Task/String-length/ALGOL-68/string-length-2.alg

@@ -0,0 +1,7 @@
+STRING str := "hello, world";
+INT length := UPB str;
+printf(($"Length of """g""" is "g(3)l$,str,length));
+
+printf(($l"STRINGS can start at -1, in which case LWB must be used:"l$));
+STRING s := "abcd"[@-1];
+print(("s:",s, ", LWB:", LWB s, ", UPB:",UPB s, ", LEN:",UPB s - LWB s + 1))

Task/String-length/AWK/string-length-1.awk

@@ -0,0 +1,4 @@
+w=length("Hello, world!")      # static string example
+x=length("Hello," s " world!") # dynamic string example
+y=length($1)                   # input field example
+z=length(s)                    # variable name example

Task/String-length/AWK/string-length-2.awk

@@ -0,0 +1,2 @@
+#!/usr/bin/awk -f
+{print"The length of this line is "length($0)}

Task/String-length/ActionScript/string-length.as

@@ -0,0 +1 @@
+myStrVar.length()

Task/String-length/Ada/string-length-1.ada

@@ -0,0 +1,2 @@
+Str    : String := "Hello World";
+Length : constant Natural := Str'Size / 8;

Task/String-length/Ada/string-length-2.ada

@@ -0,0 +1,6 @@
+Latin_1_Str    : String           := "Hello World";
+UCS_16_Str     : Wide_String      := "Hello World";
+Unicode_Str    : Wide_Wide_String := "Hello World";
+Latin_1_Length : constant Natural := Latin_1_Str'Length;
+UCS_16_Length  : constant Natural := UCS_16_Str'Length;
+Unicode_Length : constant Natural := Unicode_Str'Length;

Task/String-length/AppleScript/string-length-1.applescript

@@ -0,0 +1 @@
+count of "Hello World"

Task/String-length/AppleScript/string-length-2.applescript

@@ -0,0 +1,12 @@
+set inString to "Hello World" as Unicode text
+set byteCount to 0
+set idList to id of inString
+
+repeat with incr in idList
+  set byteCount to byteCount + 2
+  if incr as integer > 65535 then
+    set byteCount to byteCount + 2
+  end if
+end repeat
+
+byteCount

Task/String-length/AppleScript/string-length-3.applescript

@@ -0,0 +1 @@
+count of "Hello World"

Task/String-length/AppleScript/string-length-4.applescript

@@ -0,0 +1 @@
+count "Hello World"

Task/String-length/AutoHotkey/string-length-1.ahk

@@ -0,0 +1 @@
+Msgbox % StrLen("Hello World")

Task/String-length/AutoHotkey/string-length-2.ahk

@@ -0,0 +1,3 @@
+String := "Hello World"
+StringLen, Length, String
+Msgbox % Length

Task/String-length/BASIC/string-length-1.basic

@@ -0,0 +1,2 @@
+ INPUT a$
+ PRINT LEN(a$)

Task/String-length/BASIC/string-length-2.basic

@@ -0,0 +1,2 @@
+10 INPUT a$
+20 PRINT LEN(a$)

Task/String-length/BBC-BASIC/string-length-1.bbc

@@ -0,0 +1,2 @@
+      INPUT text$
+      PRINT LEN(text$)

Task/String-length/BBC-BASIC/string-length-2.bbc

@@ -0,0 +1,12 @@
+      CP_ACP = 0
+      CP_UTF8 = &FDE9
+
+      textA$ = "møøse"
+      textW$ = "                 "
+      textU$ = "                 "
+
+      SYS "MultiByteToWideChar", CP_ACP, 0, textA$, -1, !^textW$, LEN(textW$)/2 TO nW%
+      SYS "WideCharToMultiByte", CP_UTF8, 0, textW$, -1, !^textU$, LEN(textU$), 0, 0
+      PRINT "Length in bytes (ANSI encoding) = " ; LEN(textA$)
+      PRINT "Length in bytes (UTF-16 encoding) = " ; 2*(nW%-1)
+      PRINT "Length in bytes (UTF-8 encoding) = " ; LEN($$!^textU$)

Task/String-length/Batch-File/string-length.bat

@@ -0,0 +1,17 @@
+@echo off
+setlocal enabledelayedexpansion
+call :length %1 res
+echo length of %1 is %res%
+goto :eof
+
+:length
+set str=%~1
+set cnt=0
+:loop
+if "%str%" equ "" (
+	set %2=%cnt%
+	goto :eof
+	)
+set str=!str:~1!
+set /a cnt = cnt + 1
+goto loop

Task/String-length/Bracmat/string-length-1.bracmat

@@ -0,0 +1,7 @@
+(ByteLength=
+  length
+.   @(!arg:? [?length)
+  & !length
+);
+
+out$ByteLength$𝔘𝔫𝔦𝔠𝔬𝔡𝔢

Task/String-length/Bracmat/string-length-2.bracmat

@@ -0,0 +1,16 @@
+(CharacterLength=
+  length c
+.     0:?length
+    & @( !arg
+       :   ?
+           ( %?c
+           & utf$!c:?k
+           & 1+!length:?length
+           & ~
+           )
+           ?
+       )
+  | !length
+);
+
+out$CharacterLength$𝔘𝔫𝔦𝔠𝔬𝔡𝔢

Task/String-length/Bracmat/string-length-3.bracmat

@@ -0,0 +1,14 @@
+(CharacterLength=
+  length c p
+.     0:?length:?p
+    & @( !arg
+       :   ?
+           ( [!p %?c
+           & utf$!c:?k
+           & 1+!length:?length
+           )
+           ([?p&~)
+           ?
+       )
+  | !length
+);

Task/String-length/C++/string-length-1.cpp

@@ -0,0 +1,11 @@
+#include <string> // (not <string.h>!)
+using std::string;
+
+int main()
+{
+  string s = "Hello, world!";
+  string::size_type length = s.length(); // option 1: In Characters/Bytes
+  string::size_type size = s.size();     // option 2: In Characters/Bytes
+  // In bytes same as above since sizeof(char) == 1
+  string::size_type bytes = s.length() * sizeof(string::value_type);
+}

Task/String-length/C++/string-length-2.cpp

@@ -0,0 +1,8 @@
+#include <string>
+using std::wstring;
+
+int main()
+{
+  wstring s = L"\u304A\u306F\u3088\u3046";
+  wstring::size_type length = s.length() * sizeof(wstring::value_type); // in bytes
+}

Task/String-length/C++/string-length-3.cpp

@@ -0,0 +1,8 @@
+#include <string>
+using std::wstring;
+
+int main()
+{
+  wstring s = L"\u304A\u306F\u3088\u3046";
+  wstring::size_type length = s.length();
+}

Task/String-length/C++/string-length-4.cpp

@@ -0,0 +1,9 @@
+#include <iostream>
+#include <codecvt>
+int main()
+{
+    std::string utf8 = "\x7a\xc3\x9f\xe6\xb0\xb4\xf0\x9d\x84\x8b"; // U+007a, U+00df, U+6c34, U+1d10b
+    std::cout << "Byte length: " << utf8.size() << '\n';
+    std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> conv;
+    std::cout << "Character length: " << conv.from_bytes(utf8).size() << '\n';
+}

Task/String-length/C++/string-length-5.cpp

@@ -0,0 +1,37 @@
+#include <cwchar>  // for mbstate_t
+#include <locale>
+
+// give the character length for a given named locale
+std::size_t char_length(std::string const& text, char const* locale_name)
+{
+  // locales work on pointers; get length and data from string and
+  // then don't touch the original string any more, to avoid
+  // invalidating the data pointer
+  std::size_t len = text.length();
+  char const* input = text.data();
+
+  // get the named locale
+  std::locale loc(locale_name);
+
+  // get the conversion facet of the locale
+  typedef std::codecvt<wchar_t, char, std::mbstate_t> cvt_type;
+  cvt_type const& cvt = std::use_facet<cvt_type>(loc);
+
+  // allocate buffer for conversion destination
+  std::size_t bufsize = cvt.max_length()*len;
+  wchar_t* destbuf = new wchar_t[bufsize];
+  wchar_t* dest_end;
+
+  // do the conversion
+  mbstate_t state = mbstate_t();
+  cvt.in(state, input, input+len, input, destbuf, destbuf+bufsize, dest_end);
+
+  // determine the length of the converted sequence
+  std::size_t length = dest_end - destbuf;
+
+  // get rid of the buffer
+  delete[] destbuf;
+
+  // return the result
+  return length;
+}

Task/String-length/C++/string-length-6.cpp

@@ -0,0 +1,10 @@
+#include <iostream>
+
+int main()
+{
+  // Tür (German for door) in UTF8
+  std::cout << char_length("\x54\xc3\xbc\x72", "de_DE.utf8") << "\n"; // outputs 3
+
+  // Tür in ISO-8859-1
+  std::cout << char_length("\x54\xfc\x72", "de_DE") << "\n"; // outputs 3
+}

Task/String-length/C/string-length-1.c

@@ -0,0 +1,9 @@
+#include <string.h>
+
+int main(void)
+{
+  const char *string = "Hello, world!";
+  size_t length = strlen(string);
+
+  return 0;
+}

Task/String-length/C/string-length-2.c

@@ -0,0 +1,10 @@
+int main(void)
+{
+  const char *string = "Hello, world!";
+  size_t length = 0;
+
+  const char *p = string;
+  while (*p++ != '\0') length++;
+
+  return 0;
+}

Task/String-length/C/string-length-3.c

@@ -0,0 +1,9 @@
+#include <stdlib.h>
+
+int main(void)
+{
+  char s[] = "Hello, world!";
+  size_t length = sizeof s - 1;
+
+  return 0;
+}

Task/String-length/C/string-length-4.c

@@ -0,0 +1,14 @@
+#include <stdio.h>
+#include <wchar.h>
+
+int main(void)
+{
+   wchar_t *s = L"\x304A\x306F\x3088\x3046"; /* Japanese hiragana ohayou */
+   size_t length;
+
+   length = wcslen(s);
+   printf("Length in characters = %d\n", length);
+   printf("Length in bytes      = %d\n", sizeof(s) * sizeof(wchar_t));
+
+   return 0;
+}

Task/String-length/C/string-length-5.c

@@ -0,0 +1,13 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <locale.h>
+
+int main()
+{
+	setlocale(LC_CTYPE, "");
+	char moose[] = "møøse";
+	printf("bytes: %d\n", sizeof(moose) - 1);
+	printf("chars: %d\n", (int)mbstowcs(0, moose, 0));
+
+	return 0;
+}

Task/String-length/Clean/string-length.clean

@@ -0,0 +1,6 @@
+import StdEnv
+
+strlen :: String -> Int
+strlen string = size string
+
+Start = strlen "Hello, world!"

Task/String-length/Clojure/string-length-1.clj

@@ -0,0 +1,2 @@
+(count (.getBytes "Hello, world!")) ; 13 bytes
+(count (.getBytes "π")) ; two bytes

Task/String-length/Clojure/string-length-2.clj

@@ -0,0 +1 @@
+(count "Hello, world!")

Task/String-length/ColdFusion/string-length-1.cfm

@@ -0,0 +1 @@
+#len("Hello World")#

Task/String-length/ColdFusion/string-length-2.cfm

@@ -0,0 +1 @@
+#len("Hello World")#

Task/String-length/Common-Lisp/string-length-1.lisp

@@ -0,0 +1 @@
+(length (sb-ext:string-to-octets "Hello Wørld"))

Task/String-length/Common-Lisp/string-length-2.lisp

@@ -0,0 +1 @@
+(length "Hello World")

Task/String-length/Component-Pascal/string-length-1.component

@@ -0,0 +1,14 @@
+MODULE TestLen;
+
+	IMPORT Out;
+
+	PROCEDURE DoCharLength*;
+		VAR s: ARRAY 16 OF CHAR; len: INTEGER;
+	BEGIN
+		s := "møøse";
+		len := LEN(s$);
+		Out.String("s: "); Out.String(s); Out.Ln;
+		Out.String("Length of characters: "); Out.Int(len, 0); Out.Ln
+	END DoCharLength;
+
+END TestLen.

Task/String-length/Component-Pascal/string-length-2.component

@@ -0,0 +1,15 @@
+MODULE TestLen;
+
+	IMPORT Out;
+
+	PROCEDURE DoByteLength*;
+		VAR s: ARRAY 16 OF CHAR; len, v: INTEGER;
+	BEGIN
+		s := "møøse";
+		len := LEN(s$);
+		v := SIZE(CHAR) * len;
+		Out.String("s: "); Out.String(s); Out.Ln;
+		Out.String("Length of characters in bytes: "); Out.Int(v, 0); Out.Ln
+	END DoByteLength;
+
+END TestLen.

Task/String-length/D/string-length-1.d

@@ -0,0 +1,31 @@
+import std.stdio;
+
+void showByteLen(T)(T[] str) {
+    writefln("Byte length: %2d - %(%02x%)",
+             str.length * T.sizeof, cast(ubyte[])str);
+}
+
+void main() {
+    string s1a = "møøse"; // UTF-8
+    showByteLen(s1a);
+    wstring s1b = "møøse"; // UTF-16
+    showByteLen(s1b);
+    dstring s1c = "møøse"; // UTF-32
+    showByteLen(s1c);
+    writeln();
+
+    string s2a = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showByteLen(s2a);
+    wstring s2b = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showByteLen(s2b);
+    dstring s2c = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showByteLen(s2c);
+    writeln();
+
+    string s3a = "J̲o̲s̲é̲";
+    showByteLen(s3a);
+    wstring s3b = "J̲o̲s̲é̲";
+    showByteLen(s3b);
+    dstring s3c = "J̲o̲s̲é̲";
+    showByteLen(s3c);
+}

Task/String-length/D/string-length-2.d

@@ -0,0 +1,31 @@
+import std.stdio, std.range, std.conv;
+
+void showCodePointsLen(T)(T[] str) {
+    writefln("Character length: %2d - %(%x %)",
+             str.walkLength(), cast(uint[])to!(dchar[])(str));
+}
+
+void main() {
+    string s1a = "møøse"; // UTF-8
+    showCodePointsLen(s1a);
+    wstring s1b = "møøse"; // UTF-16
+    showCodePointsLen(s1b);
+    dstring s1c = "møøse"; // UTF-32
+    showCodePointsLen(s1c);
+    writeln();
+
+    string s2a = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showCodePointsLen(s2a);
+    wstring s2b = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showCodePointsLen(s2b);
+    dstring s2c = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+    showCodePointsLen(s2c);
+    writeln();
+
+    string s3a = "J̲o̲s̲é̲";
+    showCodePointsLen(s3a);
+    wstring s3b = "J̲o̲s̲é̲";
+    showCodePointsLen(s3b);
+    dstring s3c = "J̲o̲s̲é̲";
+    showCodePointsLen(s3c);
+}

Task/String-length/Dc/string-length.dc

@@ -0,0 +1 @@
+[abcde]Zp

Task/String-length/E/string-length.e

@@ -0,0 +1 @@
+"Hello World".size()

Task/String-length/Euphoria/string-length.euphoria

@@ -0,0 +1 @@
+print(1,length("Hello World"))

Task/String-length/Factor/string-length-1.factor

@@ -0,0 +1,2 @@
+: string-byte-length ( string -- n ) [ code-point-length ] map-sum ;
+: string-byte-length-2 ( string -- n ) utf8 encode length ;

Task/String-length/Factor/string-length-2.factor

@@ -0,0 +1 @@
+length

Task/String-length/Fantom/string-length-1.fantom

@@ -0,0 +1,14 @@
+fansh> c := "møøse"
+møøse
+fansh> c.toBuf.size   // find the byte length of the string in default (UTF8) encoding
+7
+fansh> c.toBuf.toHex  // display UTF8 representation
+6dc3b8c3b87365
+fansh> c.toBuf(Charset.utf16LE).size    // byte length in UTF16 little-endian
+10
+fansh> c.toBuf(Charset.utf16LE).toHex   // display as UTF16 little-endian
+6d00f800f80073006500
+fansh> c.toBuf(Charset.utf16BE).size    // byte length in UTF16 big-endian
+10
+fansh> c.toBuf(Charset.utf16BE).toHex   // display as UTF16 big-endian
+006d00f800f800730065

Task/String-length/Fantom/string-length-2.fantom

@@ -0,0 +1,4 @@
+fansh> c := "møøse"
+møøse
+fansh> c.size
+5

Task/String-length/Forth/string-length-1.fth

@@ -0,0 +1,3 @@
+CREATE s ," Hello world" \ create string "s"
+s C@ ( -- length=11 )
+s COUNT  ( addr len )   \ convert to a stack string, described below

Task/String-length/Forth/string-length-2.fth

@@ -0,0 +1,2 @@
+S" string" ( addr len)
+DUP .   \ 6

Task/String-length/Forth/string-length-3.fth

@@ -0,0 +1,9 @@
+2 base !
+: utf8+ ( str -- str )
+  begin
+    char+
+    dup c@
+    11000000 and
+    10000000 <>
+  until ;
+decimal

Task/String-length/Forth/string-length-4.fth

@@ -0,0 +1,8 @@
+: count-utf8 ( zstr -- n )
+  0
+  begin
+    swap dup c@
+  while
+    utf8+
+    swap 1+
+  repeat drop ;

Task/String-length/GAP/string-length.gap

@@ -0,0 +1,3 @@
+Length("abc");
+# or same result with
+Size("abc");

Task/String-length/GW-BASIC/string-length.gw-basic

@@ -0,0 +1,2 @@
+10 INPUT A$
+20 PRINT LEN(A$)

Task/String-length/Go/string-length-1.go

@@ -0,0 +1,12 @@
+package main
+
+import "fmt"
+
+func main() {
+    m := "møøse"
+    u := "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+    j := "J̲o̲s̲é̲"
+    fmt.Printf("%d %s % x\n", len(m), m, m)
+    fmt.Printf("%d %s %x\n", len(u), u, u)
+    fmt.Printf("%d %s % x\n", len(j), j, j)
+}

Task/String-length/Go/string-length-2.go

@@ -0,0 +1,15 @@
+package main
+
+import (
+    "fmt"
+    "unicode/utf8"
+)
+
+func main() {
+    m := "møøse"
+    u := "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+    j := "J̲o̲s̲é̲"
+    fmt.Printf("%d %s %x\n", utf8.RuneCountInString(m), m, []rune(m))
+    fmt.Printf("%d %s %x\n", utf8.RuneCountInString(u), u, []rune(u))
+    fmt.Printf("%d %s %x\n", utf8.RuneCountInString(j), j, []rune(j))
+}

Task/String-length/Go/string-length-3.go

@@ -0,0 +1,30 @@
+package main
+
+import (
+    "fmt"
+    "unicode"
+    "unicode/utf8"
+)
+
+func main() {
+    m := "møøse"
+    u := "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+    j := "J̲o̲s̲é̲"
+    fmt.Printf("%d %s %x\n", grLen(m), m, []rune(m))
+    fmt.Printf("%d %s %x\n", grLen(u), u, []rune(u))
+    fmt.Printf("%d %s %x\n", grLen(j), j, []rune(j))
+}
+
+func grLen(s string) int {
+    if len(s) == 0 {
+        return 0
+    }
+    gr := 1
+    _, s1 := utf8.DecodeRuneInString(s)
+    for _, r := range s[s1:] {
+        if !unicode.Is(unicode.Mn, r) {
+            gr++
+        }
+    }
+    return gr
+}

Task/String-length/Groovy/string-length.groovy

@@ -0,0 +1 @@
+println "Hello World!".size()

Task/String-length/Haskell/string-length-1.hs

@@ -0,0 +1,11 @@
+import Data.Encoding
+import Data.ByteString as B
+
+strUTF8  :: ByteString
+strUTF8  = encode UTF8  "Hello World!"
+
+strUTF32 :: ByteString
+strUTF32 = encode UTF32 "Hello World!"
+
+strlenUTF8  = B.length strUTF8
+strlenUTF32 = B.length strUTF32

Task/String-length/Haskell/string-length-2.hs

@@ -0,0 +1 @@
+strlen = length "Hello, world!"

Task/String-length/HicEst/string-length.hicest

@@ -0,0 +1 @@
+LEN("1 character == 1 byte") ! 21

Task/String-length/IDL/string-length-1.idl

@@ -0,0 +1 @@
+length = strlen("Hello, world!")

Task/String-length/IDL/string-length-2.idl

@@ -0,0 +1 @@
+length = strlen("Hello, world!")

Task/String-length/Icon/string-length.icon

@@ -0,0 +1 @@
+   length := *s

Task/String-length/Io/string-length-1.io

@@ -0,0 +1 @@
+"møøse" sizeInBytes

Task/String-length/Io/string-length-2.io

@@ -0,0 +1 @@
+"møøse" size

Task/String-length/J/string-length-1.j

@@ -0,0 +1,2 @@
+   #     'møøse'
+7

Task/String-length/J/string-length-2.j

@@ -0,0 +1,2 @@
+   #7 u: 'møøse'
+5

Task/String-length/Java/string-length-1.java

@@ -0,0 +1,2 @@
+String s = "Hello, world!";
+int byteCount = s.length() * 2;

Task/String-length/Java/string-length-2.java

@@ -0,0 +1,3 @@
+String s = "Hello, world!";
+int byteCountUTF16 = s.getBytes("UTF-16").length;
+int byteCountUTF8  = s.getBytes("UTF-8").length;

Task/String-length/Java/string-length-3.java

@@ -0,0 +1,2 @@
+String s = "Hello, world!";
+int not_really_the_length = s.length(); // XXX: does not (always) count Unicode characters (code points)!

Task/String-length/Java/string-length-4.java

@@ -0,0 +1,3 @@
+String str = "\uD834\uDD2A"; //U+1D12A
+int not_really__the_length = str.length(); // value is 2, which is not the length in characters
+int actual_length = str.codePointCount(0, str.length()); // value is 1, which is the length in characters

Task/String-length/Java/string-length-5.java

@@ -0,0 +1,19 @@
+import java.text.BreakIterator;
+
+public class Grapheme {
+  public static void main(String[] args) {
+    printLength("møøse");
+    printLength("𝔘𝔫𝔦𝔠𝔬𝔡𝔢");
+    printLength("J̲o̲s̲é̲");
+  }
+
+  public static void printLength(String s) {
+    BreakIterator it = BreakIterator.getCharacterInstance();
+    it.setText(s);
+    int count = 0;
+    while (it.next() != BreakIterator.DONE) {
+      count++;
+    }
+    System.out.println("Grapheme length: " + count+ " " + s);
+  }
+}

Task/String-length/JavaScript/string-length-1.js

@@ -0,0 +1,2 @@
+var s = "Hello, world!";
+var byteCount = s.length * 2; //26

Task/String-length/JavaScript/string-length-2.js

@@ -0,0 +1,5 @@
+var str1 = "Hello, world!";
+var len1 = str1.length; //13
+
+var str2 = "\uD834\uDD2A"; //U+1D12A represented by a UTF-16 surrogate pair
+var len2 = str2.length; //2

Task/String-length/JudoScript/string-length-1.judoscript

@@ -0,0 +1,2 @@
+//Store length of hello world in length and print it
+. length = "Hello World".length();

Task/String-length/JudoScript/string-length-2.judoscript

@@ -0,0 +1,2 @@
+//Store length of hello world in length and print it
+. length = "Hello World".length()

Task/String-length/LSE64/string-length-1.lse64

@@ -0,0 +1 @@
+" Hello world" @ 1 + 8 * ,   # 96 = (11+1)*(size of a cell) = 12*8

Task/String-length/LSE64/string-length-2.lse64

@@ -0,0 +1 @@
+" Hello world" @ ,   # 11

Task/String-length/Logo/string-length.logo

@@ -0,0 +1,3 @@
+print count "|Hello World|  ; 11
+print count "møøse            ; 5
+print char 248   ; ø - implies ISO-Latin character set

Task/String-length/Lua/string-length-1.lua

@@ -0,0 +1,2 @@
+str = "Hello world"
+length = #str

Task/String-length/Lua/string-length-2.lua

@@ -0,0 +1,2 @@
+str = "Hello world"
+length = string.len(str)

Task/String-length/Lua/string-length-3.lua

@@ -0,0 +1,2 @@
+str = "Hello world"
+length = #str

Task/String-length/Lua/string-length-4.lua

@@ -0,0 +1,2 @@
+str = "Hello world"
+length = string.len(str)

Task/String-length/MATLAB/string-length-1.m

@@ -0,0 +1,5 @@
+>> length('møøse')
+
+ans =
+
+     5

Task/String-length/MATLAB/string-length-2.m

@@ -0,0 +1,5 @@
+>> numel(dec2hex('møøse'))
+
+ans =
+
+    10

Task/String-length/MAXScript/string-length.maxscript

@@ -0,0 +1 @@
+"Hello world".count

Task/String-length/Mathematica/string-length-1.math

@@ -0,0 +1 @@
+StringLength["Hello world"]

Task/String-length/Mathematica/string-length-2.math

@@ -0,0 +1 @@
+StringByteCount["Hello world"]

Task/String-length/Maxima/string-length.maxima

@@ -0,0 +1,3 @@
+s: "the quick brown fox jumps over the lazy dog";
+slength(s);
+/* 43 */

Task/String-length/Metafont/string-length.metafont

@@ -0,0 +1,6 @@
+string s;
+s := "Hello Moose";
+show length(s);          % 11 (ok)
+s := "Hello Møøse";
+show length(s);          % 13 (number of bytes when the string is UTF-8 encoded,
+                         % since ø takes two bytes)

Task/String-length/Modula-3/string-length-1.mod3

@@ -0,0 +1,9 @@
+MODULE ByteLength EXPORTS Main;
+
+IMPORT IO, Fmt, Text;
+
+VAR s: TEXT := "Foo bar baz";
+
+BEGIN
+  IO.Put("Byte length of s: " & Fmt.Int((Text.Length(s) * BYTESIZE(s))) & "\n");
+END ByteLength.

Task/String-length/Modula-3/string-length-2.mod3

@@ -0,0 +1,9 @@
+MODULE StringLength EXPORTS Main;
+
+IMPORT IO, Fmt, Text;
+
+VAR s: TEXT := "Foo bar baz";
+
+BEGIN
+  IO.Put("String length of s: " & Fmt.Int(Text.Length(s)) & "\n");
+END StringLength.

Task/String-length/Nemerle/string-length-1.nemerle

@@ -0,0 +1,2 @@
+def message = "How long am I anyways?";
+def charlength = message.Length;

Task/String-length/Nemerle/string-length-2.nemerle

@@ -0,0 +1,4 @@
+using System.Text;
+
+def message = "How long am I anyways?";
+def bytelength = Encoding.Unicode.GetByteCount(message);