Data commit

Task/String-length/00-META.yaml

@@ -0,0 +1,5 @@
+---
+category:
+- String manipulation
+from: http://rosettacode.org/wiki/String_length
+note: Basic language learning

Task/String-length/00-TASK.txt

@@ -0,0 +1,23 @@
+;Task:
+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.
+<br><br>
+
+{{Template:Strings}}
+<br><br>
+

Task/String-length/360-Assembly/string-length.360

@@ -0,0 +1,25 @@
+*        String length             06/07/2016
+LEN      CSECT
+         USING  LEN,15             base register
+         LA     1,L'C              length of C
+         XDECO  1,PG
+         XPRNT  PG,12
+         LA     1,L'H              length of H
+         XDECO  1,PG
+         XPRNT  PG,12
+         LA     1,L'F              length of F
+         XDECO  1,PG
+         XPRNT  PG,12
+         LA     1,L'D              length of D
+         XDECO  1,PG
+         XPRNT  PG,12
+         LA     1,L'PG             length of PG
+         XDECO  1,PG
+         XPRNT  PG,12
+         BR     14                 exit           length
+C        DS     C                  character       1
+H        DS     H                  half word       2
+F        DS     F                  full word       4
+D        DS     D                  double word     8
+PG       DS     CL12               string         12
+         END    LEN

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

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

Task/String-length/6502-Assembly/string-length.6502

@@ -0,0 +1,12 @@
+GetStringLength: ;$00 and $01 make up the pointer to the string's base address.
+                 ;(Of course, any two consecutive zero-page memory locations can fulfill this role.)
+LDY #0           ;Y is both the index into the string and the length counter.
+
+loop_getStringLength:
+LDA ($00),y
+BEQ exit
+INY
+JMP loop_getStringLength
+
+exit:
+RTS               ;string length is now loaded into Y.

Task/String-length/68000-Assembly/string-length.68000

@@ -0,0 +1,15 @@
+GetStringLength:
+; INPUT: A3 = BASE ADDRESS OF STRING
+; RETURNS LENGTH IN D1 (MEASURED IN BYTES)
+MOVE.L #0,D1
+
+loop_getStringLength:
+
+MOVE.B (A3)+,D0
+CMP #0,D0
+BEQ done
+ADDQ.L #1,D1
+BRA loop_getStringLength
+
+done:
+RTS

Task/String-length/8086-Assembly/string-length.8086

@@ -0,0 +1,15 @@
+;INPUT: DS:SI = BASE ADDR. OF STRING
+;TYPICALLY, MS-DOS USES $ TO TERMINATE STRINGS.
+GetStringLength:
+xor cx,cx      ;this takes fewer bytes to encode than "mov cx,0"
+cld            ;makes string functions post-inc rather than post-dec.
+
+loop_GetStringLength:
+lodsb          ;equivalent of "mov al,[ds:si],inc si" except this doesn't alter the flags.
+cmp '$'
+je done        ;if equal, we're finished.
+inc cx         ;add 1 to length counter. A null string will have a length of zero.
+jmp loop_GetStringLength
+
+done:
+ret

Task/String-length/AArch64-Assembly/string-length.aarch64

@@ -0,0 +1,98 @@
+/* ARM assembly AARCH64 Raspberry PI 3B */
+/*  program stringLength64.s   */
+
+/*******************************************/
+/* Constantes file                         */
+/*******************************************/
+/* for this file see task include a file in language AArch64 assembly*/
+.include "../includeConstantesARM64.inc"
+
+/*********************************/
+/* Initialized data              */
+/*********************************/
+.data
+sMessResultByte:        .asciz "===Byte Length=== : @ \n"
+sMessResultChar:        .asciz "===Character Length=== : @ \n"
+szString1:              .asciz "møøse€"
+szCarriageReturn:       .asciz "\n"
+
+/*********************************/
+/* UnInitialized data            */
+/*********************************/
+.bss
+sZoneConv:        .skip 24
+/*********************************/
+/*  code section                 */
+/*********************************/
+.text
+.global main
+main:                                 // entry of program
+    ldr x0,qAdrszString1
+    bl affichageMess                  // display string
+    ldr x0,qAdrszCarriageReturn
+    bl affichageMess
+
+    ldr x0,qAdrszString1
+    mov x1,#0
+1:                                    // loop compute length bytes
+    ldrb w2,[x0,x1]
+    cmp w2,#0
+    cinc x1,x1,ne
+    bne 1b
+
+    mov x0,x1                         // result display
+    ldr x1,qAdrsZoneConv
+    bl conversion10                   // call decimal conversion
+    ldr x0,qAdrsMessResultByte
+    ldr x1,qAdrsZoneConv              // insert conversion in message
+    bl strInsertAtCharInc
+    bl affichageMess
+
+    ldr x0,qAdrszString1
+    mov x1,#0
+    mov x3,#0
+2:                                    // loop compute length characters
+    ldrb w2,[x0,x1]
+    cmp w2,#0
+    beq 6f
+    and x2,x2,#0b11100000             // 3 bytes ?
+    cmp x2,#0b11100000
+    bne 3f
+    add x3,x3,#1
+    add x1,x1,#3
+    b 2b
+3:
+    and x2,x2,#0b11000000              // 2 bytes ?
+    cmp x2,#0b11000000
+    bne 4f
+    add x3,x3,#1
+    add x1,x1,#2
+    b 2b
+4:                                    // else 1 byte
+    add x3,x3,#1
+    add x1,x1,#1
+    b 2b
+
+6:
+    mov x0,x3
+    ldr x1,qAdrsZoneConv
+    bl conversion10                   // call decimal conversion
+    ldr x0,qAdrsMessResultChar
+    ldr x1,qAdrsZoneConv              // insert conversion in message
+    bl strInsertAtCharInc
+    bl affichageMess
+100:                                  // standard end of the program
+    mov x0,0                          // return code
+    mov x8,EXIT                       // request to exit program
+    svc 0                             // perform the system call
+
+qAdrszCarriageReturn:     .quad szCarriageReturn
+qAdrsMessResultByte:      .quad sMessResultByte
+qAdrsMessResultChar:      .quad sMessResultChar
+qAdrszString1:            .quad szString1
+qAdrsZoneConv:            .quad sZoneConv
+/********************************************************/
+/*        File Include fonctions                        */
+/********************************************************/
+/* for this file see task include a file in language AArch64 assembly */
+.include "../includeARM64.inc"

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/ARM-Assembly/string-length.arm

@@ -0,0 +1,102 @@
+/* ARM assembly Raspberry PI  */
+/*  program stringLength.s   */
+
+/* REMARK 1 : this program use routines in a include file
+   see task Include a file language arm assembly
+   for the routine affichageMess conversion10
+   see at end of this program the instruction include */
+/* for constantes see task include a file in arm assembly */
+/************************************/
+/* Constantes                       */
+/************************************/
+.include "../constantes.inc"
+
+/*********************************/
+/* Initialized data              */
+/*********************************/
+.data
+sMessResultByte:        .asciz "===Byte Length=== : @ \n"
+sMessResultChar:        .asciz "===Character Length=== : @ \n"
+szString1:          .asciz "møøse€"
+szCarriageReturn:   .asciz "\n"
+
+
+/*********************************/
+/* UnInitialized data            */
+/*********************************/
+.bss
+sZoneConv:        .skip 24
+/*********************************/
+/*  code section                 */
+/*********************************/
+.text
+.global main
+main:                                 @ entry of program
+    ldr r0,iAdrszString1
+    bl affichageMess                  @ display string
+    ldr r0,iAdrszCarriageReturn
+    bl affichageMess
+
+    ldr r0,iAdrszString1
+    mov r1,#0
+1:                                    @ loop compute length bytes
+    ldrb r2,[r0,r1]
+    cmp r2,#0
+    addne r1,#1
+    bne 1b
+
+    mov r0,r1                         @ result display
+    ldr r1,iAdrsZoneConv
+    bl conversion10                   @ call decimal conversion
+    ldr r0,iAdrsMessResultByte
+    ldr r1,iAdrsZoneConv              @ insert conversion in message
+    bl strInsertAtCharInc
+    bl affichageMess
+
+    ldr r0,iAdrszString1
+    mov r1,#0
+    mov r3,#0
+2:                                    @ loop compute length characters
+    ldrb r2,[r0,r1]
+    cmp r2,#0
+    beq 6f
+    and r2,#0b11100000                @ 3 bytes ?
+    cmp r2,#0b11100000
+    bne 3f
+    add r3,#1
+    add r1,#3
+    b 2b
+3:
+    and r2,#0b11000000                @ 2 bytes ?
+    cmp r2,#0b11000000
+    bne 4f
+    add r3,#1
+    add r1,#2
+    b 2b
+4:                                    @ else 1 byte
+    add r3,#1
+    add r1,#1
+    b 2b
+
+6:
+    mov r0,r3
+    ldr r1,iAdrsZoneConv
+    bl conversion10                   @ call decimal conversion
+    ldr r0,iAdrsMessResultChar
+    ldr r1,iAdrsZoneConv              @ insert conversion in message
+    bl strInsertAtCharInc
+    bl affichageMess
+100:                                  @ standard end of the program
+    mov r0, #0                        @ return code
+    mov r7, #EXIT                     @ request to exit program
+    svc #0                            @ perform the system call
+
+iAdrszCarriageReturn:     .int szCarriageReturn
+iAdrsMessResultByte:      .int sMessResultByte
+iAdrsMessResultChar:      .int sMessResultChar
+iAdrszString1:            .int szString1
+iAdrsZoneConv:            .int sZoneConv
+/***************************************************/
+/*      ROUTINES INCLUDE                           */
+/***************************************************/
+.include "../affichage.inc"

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/Action-/string-length.action

@@ -0,0 +1,8 @@
+PROC Test(CHAR ARRAY s)
+  PrintF("Length of ""%S"" is %B%E",s,s(0))
+RETURN
+
+PROC Main()
+  Test("Hello world!")
+  Test("")
+RETURN

Task/String-length/ActionScript/string-length-1.as

@@ -0,0 +1,34 @@
+package {
+
+    import flash.display.Sprite;
+    import flash.events.Event;
+    import flash.utils.ByteArray;
+
+    public class StringByteLength extends Sprite {
+
+        public function StringByteLength() {
+            if ( stage ) _init();
+            else addEventListener(Event.ADDED_TO_STAGE, _init);
+        }
+
+        private function _init(e:Event = null):void {
+            var s1:String = "The quick brown fox jumps over the lazy dog";
+            var s2:String = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+            var s3:String = "José";
+
+            var b:ByteArray = new ByteArray();
+            b.writeUTFBytes(s1);
+            trace(b.length);  // 43
+
+            b.clear();
+            b.writeUTFBytes(s2);
+            trace(b.length);  // 28
+
+            b.clear();
+            b.writeUTFBytes(s3);
+            trace(b.length);  // 5
+        }
+
+    }
+
+}

Task/String-length/ActionScript/string-length-2.as

@@ -0,0 +1,4 @@
+var s1:String = "The quick brown fox jumps over the lazy dog";
+var s2:String = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+var s3:String = "José";
+trace(s1.length, s2.length, s3.length);  // 43, 14, 4

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/Aime/string-length-1.aime

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

Task/String-length/Aime/string-length-2.aime

@@ -0,0 +1 @@
+~"Hello, World!"

Task/String-length/Apex/string-length.apex

@@ -0,0 +1,2 @@
+String myString = 'abcd';
+System.debug('Size of String', myString.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 +1,32 @@
+set inString to "Hello é̦世界"
+set byteCount to 0
+
+repeat with c in inString
+	set t to id of c
+	if ((count of t) > 0) then
+		repeat with i in t
+			set byteCount to byteCount + doit(i)
+		end repeat
+	else
+		set byteCount to byteCount + doit(t)
+	end if
+end repeat
+
+byteCount
+
+on doit(cid)
+	set n to (cid as integer)
+	if n > 67108863 then -- 0x3FFFFFF
+		return 6
+	else if n > 2097151 then -- 0x1FFFFF
+		return 5
+	else if n > 65535 then -- 0xFFFF
+		return 4
+	else if n > 2047 then -- 0x07FF
+		return 3
+	else if n > 127 then -- 0x7F
+		return 2
+	else
+		return 1
+	end if
+end doit

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/Applesoft-BASIC/string-length.basic

@@ -0,0 +1 @@
+? LEN("HELLO, WORLD!")

Task/String-length/Arturo/string-length.arturo

@@ -0,0 +1,3 @@
+str: "Hello World"
+
+print ["length =" size str]

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/Avail/string-length-1.avail

@@ -0,0 +1 @@
+|"møøse"|

Task/String-length/Avail/string-length-2.avail

@@ -0,0 +1,7 @@
+nonBMPString ::= "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+encoder ::= a UTF8 encoder;
+bytes ::= encoder process nonBMPString;
+|bytes|
+
+// or, as a one-liner
+|a UTF8 encoder process "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"|

Task/String-length/Axe/string-length.axe

@@ -0,0 +1,2 @@
+"HELLO, WORLD"→Str1
+Disp length(Str1)▶Dec,i

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

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

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

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

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

@@ -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/BQN/string-length-1.bqn

@@ -0,0 +1 @@
+BLen ← {(≠𝕩)+´⥊𝕩≥⌜@+128‿2048‿65536}

Task/String-length/BQN/string-length-2.bqn

@@ -0,0 +1 @@
+Len ← ≠

Task/String-length/BQN/string-length-3.bqn

@@ -0,0 +1,5 @@
+•Show >(⊢⋈⊸∾Len⋈BLen)¨⟨
+  "møøse"
+  "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+  "J̲o̲s̲é̲"
+⟩

Task/String-length/BQN/string-length-4.bqn

@@ -0,0 +1,5 @@
+┌─
+╵ "møøse"    5 7
+  "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"  7 28
+  "J̲o̲s̲é̲" 8 13
+                  ┘

Task/String-length/BaCon/string-length.bacon

@@ -0,0 +1,8 @@
+PRINT "Bytelen of 'hello': ", LEN("hello")
+PRINT "Charlen of 'hello': ", ULEN("hello")
+
+PRINT "Bytelen of 'møøse': ", LEN("møøse")
+PRINT "Charlen of 'møøse': ", ULEN("møøse")
+
+PRINT "Bytelen of '𝔘𝔫𝔦𝔠𝔬𝔡𝔢': ", LEN("𝔘𝔫𝔦𝔠𝔬𝔡𝔢")
+PRINT "Charlen of '𝔘𝔫𝔦𝔠𝔬𝔡𝔢': ", ULEN("𝔘𝔫𝔦𝔠𝔬𝔡𝔢")

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/Bracmat/string-length-4.bracmat

@@ -0,0 +1,4 @@
+(CharacterLength=
+  length
+. vap$((=.!arg).!arg):? [?length&!length
+);

Task/String-length/Brainf---/string-length.bf

@@ -0,0 +1,6 @@
+,----- ----- [>,----- -----] ; read a text until a newline
+<[+++++ +++++<] ; restore the original text
+>[[-]<[>+<-]>+>]< ; add one to the accumulator cell for every byte read
+;; from esolang dot org
+>[-]>[-]+>[-]+< [>[-<-<<[->+>+<<]>[-<+>]>>]++++++++++>[-]+>[-]>[-]> [-]<<<<<[->-[>+>>]>[[-<+>]+>+>>]<<<<<]>>-[-<<+>>]<[-]++++++++ [-<++++++>]>>[-<<+>>]<<] <[.[-]<]
+[-]+++++ +++++. ; print newline

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-sharp/string-length-1.cs

@@ -0,0 +1,2 @@
+string s = "Hello, world!";
+int characterLength = s.Length;

Task/String-length/C-sharp/string-length-2.cs

@@ -0,0 +1,4 @@
+using System.Text;
+
+string s = "Hello, world!";
+int byteLength = Encoding.Unicode.GetByteCount(s);

Task/String-length/C-sharp/string-length-3.cs

@@ -0,0 +1 @@
+int utf8ByteLength = Encoding.UTF8.GetByteCount(s);

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/COBOL/string-length-1.cobol

@@ -0,0 +1 @@
+FUNCTION BYTE-LENGTH(str)

Task/String-length/COBOL/string-length-2.cobol

@@ -0,0 +1 @@
+LENGTH OF str

Task/String-length/COBOL/string-length-3.cobol

@@ -0,0 +1 @@
+FUNCTION LENGTH-AN(str)

Task/String-length/COBOL/string-length-4.cobol

@@ -0,0 +1 @@
+FUNCTION LENGTH(str)

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 +1,8 @@
+(def utf-8-octet-length #(-> % (.getBytes "UTF-8") count))
+(map utf-8-octet-length  ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (7 28 14)
+
+(def utf-16-octet-length (comp (partial * 2) count))
+(map utf-16-octet-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (10 28 18)
+
+(def code-unit-length count)
+(map code-unit-length    ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 14 9)

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

@@ -0,0 +1,2 @@
+(def character-length #(.codePointCount % 0 (count %)))
+(map character-length    ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 9)

Task/String-length/Clojure/string-length-3.clj

@@ -0,0 +1,8 @@
+(def grapheme-length
+  #(->> (doto (java.text.BreakIterator/getCharacterInstance)
+          (.setText %))
+        (partial (memfn next))
+        repeatedly
+        (take-while (partial not= java.text.BreakIterator/DONE))
+        count))
+(map grapheme-length     ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 4)

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

@@ -0,0 +1,6 @@
+<cfoutput>
+<cfset str = "Hello World">
+<cfset j = createObject("java","java.lang.String").init(str)>
+<cfset t = j.getBytes()>
+<p>#arrayLen(t)#</p>
+</cfoutput>

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

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

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

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

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.pas

@@ -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.pas

@@ -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/Crystal/string-length-1.crystal

@@ -0,0 +1 @@
+"J̲o̲s̲é̲".bytesize

Task/String-length/Crystal/string-length-2.crystal

@@ -0,0 +1 @@
+"J̲o̲s̲é̲".chars.length

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/DataWeave/string-length.dw

@@ -0,0 +1 @@
+sizeOf("foo")

Task/String-length/Dc/string-length-1.dc

@@ -0,0 +1,3 @@
+[256 / d 0<L 1 + ] sL
+22405534230753963835153736737 d P A P
+lL x f

Task/String-length/Dc/string-length-2.dc

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

Task/String-length/Dyalect/string-length.dyalect

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

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

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

Task/String-length/EMal/string-length-1.emal

@@ -0,0 +1,4 @@
+text moose = "møøse"
+text unicode = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+text jose = "J" + 0U0332 + "o" + 0U0332 + "s" + 0U0332 + "e" + 0U0301 + 0U0332
+text emoji = "𠇰😈🎶🔥é-"

Task/String-length/EMal/string-length-2.emal

@@ -0,0 +1,4 @@
+writeLine((blob!moose).length)
+writeLine((blob!unicode).length)
+writeLine((blob!jose).length)
+writeLine((blob!emoji).length)

Task/String-length/EMal/string-length-3.emal

@@ -0,0 +1,4 @@
+writeLine(moose.codePointsLength)
+writeLine(unicode.codePointsLength)
+writeLine(jose.codePointsLength)
+writeLine(emoji.codePointsLength)

Task/String-length/EMal/string-length-4.emal

@@ -0,0 +1,4 @@
+writeLine(moose.graphemesLength)
+writeLine(unicode.graphemesLength)
+writeLine(jose.graphemesLength)
+writeLine(emoji.graphemesLength)

Task/String-length/EasyLang/string-length.easy

@@ -0,0 +1,8 @@
+# 5
+print len "møøse"
+# 7
+print len "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+# 8
+print len "J̲o̲s̲é̲"
+# 1
+print len "😀"

Task/String-length/Elena/string-length-1.elena

@@ -0,0 +1,11 @@
+import extensions;
+
+public program()
+{
+    var s := "Hello, world!";             // UTF-8 literal
+    var ws := "Привет мир!"w;             // UTF-16 literal
+
+    var s_length := s.Length;             // Number of UTF-8 characters
+    var ws_length := ws.Length;           // Number of UTF-16 characters
+    var u_length := ws.toArray().Length;    //Number of UTF-32 characters
+}

Task/String-length/Elena/string-length-2.elena

@@ -0,0 +1,10 @@
+import extensions;
+
+public program()
+{
+    var s := "Hello, world!";                     // UTF-8 literal
+    var ws := "Привет мир!"w;                     // UTF-16 literal
+
+    var s_byte_length := s.toByteArray().Length;  // Number of bytes
+    var ws_byte_length := ws.toByteArray().Length;  // Number of bytes
+}

Task/String-length/Elixir/string-length-1.elixir

@@ -0,0 +1,3 @@
+name = "J\x{332}o\x{332}s\x{332}e\x{301}\x{332}"
+byte_size(name)
+# => 14

Task/String-length/Elixir/string-length-2.elixir

@@ -0,0 +1,3 @@
+name = "J\x{332}o\x{332}s\x{332}e\x{301}\x{332}"
+Enum.count(String.codepoints(name))
+# => 9

Task/String-length/Elixir/string-length-3.elixir

@@ -0,0 +1,3 @@
+name = "J\x{332}o\x{332}s\x{332}e\x{301}\x{332}"
+String.length(name)
+# => 4

Task/String-length/Emacs-Lisp/string-length-1.l

@@ -0,0 +1,2 @@
+(length "hello")
+;; => 5

Task/String-length/Emacs-Lisp/string-length-2.l

@@ -0,0 +1,2 @@
+(string-bytes "\u1D518\u1D52B\u1D526")
+;; => 12

Task/String-length/Emacs-Lisp/string-length-3.l

@@ -0,0 +1,7 @@
+(let ((str (apply 'string
+                  (mapcar (lambda (c) (decode-char 'ucs c))
+                          '(#x1112 #x1161 #x11ab #x1100 #x1173 #x11af)))))
+  (list (length str)
+        (string-bytes str)
+        (string-width str)))
+;; => (6 18 4)  ;; in emacs 23 up

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

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

Task/String-length/F-Sharp/string-length-1.fs

@@ -0,0 +1,2 @@
+open System.Text
+let byte_length str = Encoding.UTF8.GetByteCount(str)

Task/String-length/F-Sharp/string-length-2.fs

@@ -0,0 +1 @@
+"Hello, World".Length