Character codes: Difference between revisions

Content added Content deleted

Inline

Latest revision as of 17:21, 18 April 2024

Task

Given a character value in your language, print its code (could be ASCII code, Unicode code, or whatever your language uses).

Example

The character 'a' (lowercase letter A) has a code of 97 in ASCII (as well as Unicode, as ASCII forms the beginning of Unicode).

Conversely, given a code, print out the corresponding character.

11l

print(‘a’.code)       // prints "97"
print(Char(code' 97)) // prints "a"

S/360 architecture and EBCDIC was born together. In EBCDIC, the character 'a' (lowercase letter A) has a code of 129 in decimal and '81'x in hexadecimal. To perform conversion, we use IC (insert character) and STC (store character) opcodes.

*        Character codes EBCDIC    15/02/2017
CHARCODE CSECT
         USING  CHARCODE,R13       base register
         B      72(R15)            skip savearea
         DC     17F'0'             savearea
         STM    R14,R12,12(R13)    prolog
         ST     R13,4(R15)         " <-
         ST     R15,8(R13)         " ->
         LR     R13,R15            " addressability
* Character to Decimal
         SR     R1,R1              r1=0
         IC     R1,=C'a'           insert character 'a'
         XDECO  R1,PG
         XPRNT  PG,L'PG            print -> 129
* Hexadecimal to character
         SR     R1,R1              r1=0
         IC     R1,=X'81'          insert character X'81'
         STC    R1,CHAR            store character r1
         XPRNT  CHAR,L'CHAR        print -> 'a'
* Decimal to character
         LH     R1,=H'129'         r1=129
         STC    R1,CHAR            store character r1
         XPRNT  CHAR,L'CHAR        print -> 'a'
*
         XDUMP  CHAR,L'CHAR        dump -> X'81'
*
RETURN   L      R13,4(0,R13)       epilog 
         LM     R14,R12,12(R13)    " restore
         XR     R15,R15            " rc=0
         BR     R14                exit
PG       DS     CL12
CHAR     DS     CL1 
         YREGS
         END    CHARCODE

Output:

         129
a
a

68000 Assembly

The printing routine only understands ASCII characters as codes anyway, so the "given a code produce its character" part is trivial. The PrintChar routine is omitted for brevity. It converts the two cursor variables to a FIX layer address and outputs the character using the NEOGEO's FIX layer (the layer where text is displayed). Characters are stored in ROM and arranged in ASCII order.

        JSR ResetCoords					;RESET TYPING CURSOR

	MOVE.B #'A',D1
	MOVE.W #25,D2
	MOVE.B #0,(softCarriageReturn) ;new line takes the cursor to left edge of screen.
	jsr PrintAllTheCodes
	
	jsr ResetCoords
	MOVE.B #8,(Cursor_X)
	MOVE.B #'a',D1
	MOVE.W #25,D2
	MOVE.B #8,(softCarriageReturn) 
	;set the writing cursor to column 3 of the screen
	;so we don't erase the old output.
	
	
	jsr PrintAllTheCodes
	

forever:
	bra forever
	

	
PrintAllTheCodes:
	MOVE.B D1,D0
	jsr PrintChar			;print the character as-is
	
	MOVE.B #" ",D0
	jsr PrintChar
	MOVE.B #"=",D0
	jsr PrintChar
	MOVE.B #" ",D0
	jsr PrintChar
	
	MOVE.B D1,D0			;get ready to print the code
	
	JSR UnpackNibbles8
	SWAP D0
	ADD.B #$30,D0
	JSR PrintChar

	SWAP D0
	CMP.B #10,D0
	BCS noCorrectHex
	ADD.B #$07,D0
noCorrectHex:
	ADD.B #$30,D0
	JSR PrintChar
	
	MOVE.B (softCarriageReturn),D0
	JSR doNewLine2				;new line, with D0 as the carraige return point.
	
	ADDQ.B #1,D1
	DBRA D2,PrintAllTheCodes
	rts


UnpackNibbles8:
; INPUT: D0 = THE VALUE YOU WISH TO UNPACK.
; HIGH NIBBLE IN HIGH WORD OF D0, LOW NIBBLE IN LOW WORD. SWAP D0 TO GET THE OTHER HALF.
	pushWord D1
		CLR.W D1		
		MOVE.B D0,D1
		CLR.L D0
		MOVE.B D1,D0	 ;now D0 = D1 = $000000II, where I = input
		
		AND.B #$F0,D0	 ;chop off bottom nibble
		LSR.B #4,D0		 ;downshift top nibble into bottom nibble of the word
		SWAP D0			 ;store in high word
		AND.B #$0F,D1	 ;chop off bottom nibble
		MOVE.B D1,D0	 ;store in low word
	popWord D1
	rts

Output can be seen here.

AArch64 Assembly

Works with: as version Raspberry Pi 3B version Buster 64 bits

/* ARM assembly AARCH64 Raspberry PI 3B */
/*  program character64.s   */

/*******************************************/
/* Constantes file                         */
/*******************************************/
/* for this file see task include a file in language AArch64 assembly*/
.include "../includeConstantesARM64.inc"
 
/*******************************************/
/* Initialized data                        */
/*******************************************/
.data
szMessCodeChar:    .asciz "The code of character is : @ \n"
/*******************************************/
/* UnInitialized data                      */
/*******************************************/
.bss 
sZoneconv:           .skip 32
/*******************************************/
/*  code section                           */
/*******************************************/
.text
.global main 
main:                          // entry of program
 
    mov x0,'A'
    ldr x1,qAdrsZoneconv
    bl conversion10S
    ldr x0,qAdrszMessCodeChar
    ldr x1,qAdrsZoneconv
    bl strInsertAtCharInc      // insert result at @ character
    bl affichageMess
    mov x0,'a'
    ldr x1,qAdrsZoneconv
    bl conversion10S
    ldr x0,qAdrszMessCodeChar
    ldr x1,qAdrsZoneconv
    bl strInsertAtCharInc     // insert result at @ character
    bl affichageMess
    mov x0,'1'
    ldr x1,qAdrsZoneconv
    bl conversion10S
    ldr x0,qAdrszMessCodeChar
    ldr x1,qAdrsZoneconv
    bl strInsertAtCharInc     // insert result at @ character
    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
qAdrsZoneconv:             .quad  sZoneconv
qAdrszMessCodeChar:        .quad szMessCodeChar
/********************************************************/
/*        File Include fonctions                        */
/********************************************************/
/* for this file see task include a file in language AArch64 assembly */
.include "../includeARM64.inc"

ABAP

In ABAP you must first cast the character to a byte field and back to a number in order to get its ASCII value.

report zcharcode
data: c value 'A', n type i.
field-symbols <n> type x.

assign c to <n> casting.
move <n> to n.
write: c, '=', n left-justified.

Output:

A = 65

ACL2

Similar to Common Lisp:

(cw "~x0" (char-code #\a))
(cw "~x0" (code-char 97))

Action!

PROC Main()
  CHAR c=['a]
  BYTE b=[97]

  Put(c) Put('=) PrintBE(c)
  PrintB(b) Put('=) Put(b)
RETURN

Output:

Screenshot from Atari 8-bit computer

a=97
97=a

ActionScript

In ActionScript, you cannot take the character code of a character directly. Instead you must create a string and call charCodeAt with the character's position in the string as a parameter.

trace(String.fromCharCode(97)); //prints 'a' 
trace("a".charCodeAt(0));//prints '97'

Ada

with Ada.Text_IO;  use Ada.Text_IO;

procedure Char_Code is
begin
   Put_Line (Character'Val (97) & " =" & Integer'Image (Character'Pos ('a')));
end Char_Code;

The predefined language attributes S'Pos and S'Val for every discrete subtype, and Character is such a type, yield the position of a value and value by its position correspondingly.

Output:

a = 97

Aime

# prints "97"
o_integer('a');
o_byte('\n');
# prints "a"
o_byte(97);
o_byte('\n');

ALGOL 68

In ALGOL 68 the format $g$ is type aware, hence the type conversion operators abs & repr are used to set the type.

main:(
  printf(($gl$, ABS "a")); # for ASCII this prints "+97" EBCDIC prints "+129" #
  printf(($gl$, REPR 97))  # for ASCII this prints "a"; EBCDIC prints "/" #
)

Character conversions may be available in the standard prelude so that when a foreign tape is mounted, the characters will be converted transparently as the tape's records are read.

FILE tape;
INT errno = open(tape, "/dev/tape1", stand out channel)
make conv(tape, ebcdic conv);
FOR record DO getf(tape, ( ~ )) OD; ~ # etc ... #

Every channel has an associated standard character conversion that can be determined using the stand conv query routine and then the conversion applied to a particular file/tape. eg.

 make conv(tape, stand conv(stand out channel))

ALGOL W

begin
    % display the character code of "a" (97 in ASCII)                        %
    write( decode( "a" ) );
    % display the character corresponding to 97 ("a" in ASCII)               %
    write( code( 97 ) );
end.

APL

Works with: Dyalog APL

Works with: GNU APL

In GNU APL and Dyalog, ⎕UCS with an integer returns the corresponding Unicode character:

      ⎕UCS 97
a

and ⎕UCS with a character returns the corresponding code:

      ⎕UCS 'a'
97

Like most things in APL, ⎕UCS can also be used with an array or with a string (which is an array of characters):

      ⎕UCS 65 80 76
APL
      ⎕UCS 'Hello, world!'
72 101 108 108 111 44 32 119 111 114 108 100 33

AppleScript

log(id of "a")
log(id of "aA")

Output:

(*97*)
(*97, 65*)

The converse instruction is character id — or either of its synonyms string id and Unicode text id. Because of a bug admitted to in Apple's AppleScript Language Guide, the expression text id, which one might expect to work, can't be used.

character id 97
--> "a"

character id {72, 101, 108, 108, 111, 33}
--> "Hello!"

string id {72, 101, 108, 108, 111, 33}
--> "Hello!"

Unicode text id {72, 101, 108, 108, 111, 33}
--> "Hello!"

ARM Assembly

Works with: as version Raspberry Pi

/* ARM assembly Raspberry PI  */
/*  program character.s   */

/* Constantes    */
.equ STDOUT, 1     @ Linux output console
.equ EXIT,   1     @ Linux syscall
.equ WRITE,  4     @ Linux syscall
/* Initialized data */
.data
szMessCodeChar: .ascii "The code of character is :"
sZoneconv:		 .fill 12,1,' '
szCarriageReturn:  .asciz "\n"

/* UnInitialized data */
.bss 

/*  code section */
.text
.global main 
main:                /* entry of program  */
    push {fp,lr}    /* saves 2 registers */
	
    mov r0,#'A'
    ldr r1,iAdrsZoneconv
    bl conversion10S
    ldr r0,iAdrszMessCodeChar
    bl affichageMess
    mov r0,#'a'
    ldr r1,iAdrsZoneconv
    bl conversion10S
    ldr r0,iAdrszMessCodeChar
    bl affichageMess
    mov r0,#'1'
    ldr r1,iAdrsZoneconv
    bl conversion10S
    ldr r0,iAdrszMessCodeChar
    bl affichageMess
 
100:   /* standard end of the program */
    mov r0, #0                  @ return code
    pop {fp,lr}                 @restaur 2 registers
    mov r7, #EXIT              @ request to exit program
    swi 0                       @ perform the system call
iAdrsZoneconv:		.int  sZoneconv
iAdrszMessCodeChar:		.int szMessCodeChar
/******************************************************************/
/*     display text with size calculation                         */ 
/******************************************************************/
/* r0 contains the address of the message */
affichageMess:
    push {fp,lr}    			/* save  registres */ 
    push {r0,r1,r2,r7}    		/* save others registers */
    mov r2,#0   				/* counter length */
1:      	/* loop length calculation */
    ldrb r1,[r0,r2]  			/* read octet start position + index */
    cmp r1,#0       			/* if 0 its over */
    addne r2,r2,#1   			/* else add 1 in the length */
    bne 1b          			/* and loop */
                                /* so here r2 contains the length of the message */
    mov r1,r0        			/* address message in r1 */
    mov r0,#STDOUT      		/* code to write to the standard output Linux */
    mov r7, #WRITE             /* code call system "write" */
    swi #0                      /* call systeme */
    pop {r0,r1,r2,r7}     		/* restaur others registers */
    pop {fp,lr}    				/* restaur des  2 registres */ 
    bx lr	        			/* return  */
	
/***************************************************/
/*   conversion register signed décimal     */
/***************************************************/
/* r0 contient le registre   */
/* r1 contient l adresse de la zone de conversion */
conversion10S:
    push {r0-r5,lr}    /* save des registres */
    mov r2,r1       /* debut zone stockage */
    mov r5,#'+'     /* par defaut le signe est + */
    cmp r0,#0       /* nombre négatif ? */
    movlt r5,#'-'     /* oui le signe est - */
    mvnlt r0,r0       /* et inversion en valeur positive */
    addlt r0,#1
    mov r4,#10   /* longueur de la zone */
1: /* debut de boucle de conversion */
    bl divisionpar10 /* division  */
    add r1,#48        /* ajout de 48 au reste pour conversion ascii */	
    strb r1,[r2,r4]  /* stockage du byte en début de zone r5 + la position r4 */
    sub r4,r4,#1      /* position précedente */
    cmp r0,#0     
    bne 1b	       /* boucle si quotient different de zéro */
    strb r5,[r2,r4]  /* stockage du signe à la position courante */
    subs r4,r4,#1   /* position précedente */
    blt  100f         /* si r4 < 0  fin  */
    /* sinon il faut completer le debut de la zone avec des blancs */
    mov r3,#' '   /* caractere espace */	
2:
    strb r3,[r2,r4]  /* stockage du byte  */
    subs r4,r4,#1   /* position précedente */
    bge 2b        /* boucle si r4 plus grand ou egal a zero */
100:  /* fin standard de la fonction  */
    pop {r0-r5,lr}   /*restaur desregistres */
    bx lr   

/***************************************************/
/*   division par 10   signé                       */
/* Thanks to http://thinkingeek.com/arm-assembler-raspberry-pi/*  
/* and   http://www.hackersdelight.org/            */
/***************************************************/
/* r0 contient le dividende   */
/* r0 retourne le quotient */	
/* r1 retourne le reste  */
divisionpar10:	
  /* r0 contains the argument to be divided by 10 */
   push {r2-r4}   /* save registers  */
   mov r4,r0 
   ldr r3, .Ls_magic_number_10 /* r1 <- magic_number */
   smull r1, r2, r3, r0   /* r1 <- Lower32Bits(r1*r0). r2 <- Upper32Bits(r1*r0) */
   mov r2, r2, ASR #2     /* r2 <- r2 >> 2 */
   mov r1, r0, LSR #31    /* r1 <- r0 >> 31 */
   add r0, r2, r1         /* r0 <- r2 + r1 */
   add r2,r0,r0, lsl #2   /* r2 <- r0 * 5 */
   sub r1,r4,r2, lsl #1   /* r1 <- r4 - (r2 * 2)  = r4 - (r0 * 10) */
   pop {r2-r4}
   bx lr                  /* leave function */
   bx lr                  /* leave function */
.Ls_magic_number_10: .word 0x66666667

Arturo

print to :integer first "a"
print to :integer `a`
print to :char 97

Output:

97
97
a

AutoHotkey

MsgBox % Chr(97)
MsgBox % Asc("a")

AWK

AWK has no built-in way to convert a character into ASCII (or whatever) code; but a function that does so can be easily built using an associative array (where the keys are the characters). The opposite can be done using printf (or sprintf) with %c

function ord(c)
{
  return chmap[c]
}
BEGIN {
  for(i=0; i < 256; i++) {
    chmap[sprintf("%c", i)] = i
  }
  print ord("a"), ord("b")
  printf "%c %c\n", 97, 98
  s = sprintf("%c%c", 97, 98)
  print s
}

Axe

Disp 'a'▶Dec,i
Disp 97▶Char,i

Babel

'abcdefg' str2ar
{%d nl <<} eachar

Output:

97 98 99 100 101 102 103

(98 97 98 101 108) ls2lf ar2str nl <<

Output:

babel

BASIC

Works with: QBasic version 1.1

Works with: QuickBasic version 4.5

charCode = 97
char = "a"
PRINT CHR$(charCode) 'prints a
PRINT ASC(char) 'prints 97

On the ZX Spectrum string variable names must be a single letter but numeric variables can be multiple characters:

Works with: ZX Spectrum Basic

10 LET c = 97: REM c is a character code
20 LET d$ = "b": REM d$ holds the character
30 PRINT CHR$(c): REM this prints a
40 PRINT CODE(d$): REM this prints 98

Applesoft BASIC

CHR$(97) is used in place of "a" because on the older model Apple II, lower case is difficult to input.

?CHR$(97)"="ASC(CHR$(97))

Output:

a=97

Output as it appears on the text display on the Apple II and Apple II plus, with the original text character ROM:

!=97

BaCon

' ASCII
c$ = "$"
PRINT c$, ": ", ASC(c$)

' UTF-8
uc$ = "€"
PRINT uc$, ": ", UCS(uc$), ", ", UCS(c$)

Output:

$: 36
€: 8364, 36

Chipmunk Basic

10 print "a - > ";asc("a")
20 print "98 -> ";chr$(98)

Commodore BASIC

Commodore BASIC uses PETSCII code for its character set.

10 CH = 65:        REM IN PETSCII CODE FOR 'A' IS 65
20 D$ = "B":       REM D$ HOLDS THE CHARACTER 'B'
30 PRINT CHR$(CH): REM THIS PRINTS 'A'
40 PRINT ASC(D$):  REM THIS PRINTS 66

Output:

A
 66

GW-BASIC

Works with: PC-BASIC version any

Works with: BASICA

10 PRINT "a - > "; ASC("a")
20 PRINT "98 -> "; CHR$(98)

IS-BASIC

100 PRINT ORD("A")
110 PRINT CHR$(65)

MSX Basic

Works with: MSX BASIC version any

10 PRINT "a - > "; ASC("a")
20 PRINT "98 -> "; CHR$(98)

QBasic

Works with: BASICA

Works with: Chipmunk Basic

Works with: FreeBASIC

Works with: GW-BASIC

Works with: MSX BASIC

Works with: PC-BASIC

Works with: Run BASIC

Works with: Yabasic

PRINT "a - > "; ASC("a")
PRINT "98 -> "; CHR$(98)

Sinclair ZX81 BASIC

10 REM THE ZX81 USES ITS OWN NON-ASCII CHARACTER SET
20 REM WHICH DOES NOT INCLUDE LOWER-CASE LETTERS
30 PRINT CODE "A"
40 PRINT CHR$ 38

Output:

38
A

SmallBASIC

Print "a  -> "; Asc("a")
Print "98 -> "; Chr(98)

True BASIC

PRINT "a - > "; ord("a")
PRINT "98 -> "; chr$(98)
END

XBasic

Works with: Windows XBasic

Works with: Linux XBasic

PROGRAM	"Character codes"
VERSION	"0.0000"

DECLARE FUNCTION  Entry ()

FUNCTION  Entry ()
    PRINT "a - >"; ASC("a")
    PRINT "98 -> "; CHR$(98)
END FUNCTION
END PROGRAM

Yabasic

print "a - > ", asc("a")
print "98 -> ", chr$(98)

BASIC256

# ASCII char
charCode = 97
char$ = "a"
print chr(97)	#prints a
print asc("a")  #prints 97

# Unicode char
charCode = 960
char$ = "π"
print chr(960)  #prints π
print asc("π")  #prints 960

Output:

Batch File

@echo off

:: Supports all ASCII characters and codes from 34-126 with the exceptions of:
:: 38  &
:: 60  <
:: 62  >
:: 94  ^
:: 124 |

:_main
call:_toCode a
call:_toChar 97
pause>nul
exit /b

:_toCode
setlocal enabledelayedexpansion
set codecount=32

for /l %%i in (33,1,126) do (
  set /a codecount+=1
  cmd /c exit %%i 
  if %1==!=exitcodeAscii! (
    echo !codecount!
    exit /b
  )
)

:_toChar
setlocal
cmd /c exit %1
echo %=exitcodeAscii%
exit /b

Input:

toCode a
toChar 97

Output:

97
a

BBC BASIC

      charCode = 97
      char$ = "a"
      PRINT CHR$(charCode) : REM prints a
      PRINT ASC(char$) : REM prints 97

Befunge

The instruction . will output as an integer. , will output as ASCII character.

"a". 99*44*+, @

BQN

BQN's character arithmetic makes it easy to convert between numbers and characters. Since arithmetic generalizes to arrays, the same function works for both integers and arrays. Here, only the conversion from number to character is defined, since it can be automatically inverted with Undo (⁼): the inverse simply subtracts @.

   FromCharCode ← @⊸+
@⊸+
   FromCharCode 97
'a'
   FromCharCode 97‿67‿126
"aC~"
   FromCharCode⁼ 'a'
97

Bracmat

( put
$ ( str
  $ ( "\nLatin a
        ISO-9959-1: "
      asc$a
      " = "
      chr$97
      "
             UTF-8: "
      utf$a
      " = "
      chu$97
      \n
      "Cyrillic а (UTF-8): "
      utf$а
      " = "
      chu$1072
      \n
    )
  )
)

Output:

Latin a
       ISO-9959-1: 97 = a
            UTF-8: 97 = a

Cyrillic а (UTF-8): 1072 = а

C

char is already an integer type in C, and it gets automatically promoted to int. So you can use a character where you would otherwise use an integer. Conversely, you can use an integer where you would normally use a character, except you may need to cast it, as char is smaller.

#include <stdio.h>

int main() {
  printf("%d\n", 'a'); /* prints "97" */
  printf("%c\n", 97); /* prints "a"; we don't have to cast because printf is type agnostic */
  return 0;
}

C#

C# represents strings and characters internally as Unicode, so casting a char to an int returns its Unicode character encoding.

using System;

namespace RosettaCode.CharacterCode
{
    class Program
    {
        static void Main(string[] args)
        {
            Console.WriteLine((int) 'a');   //Prints "97"
            Console.WriteLine((char) 97);   //Prints "a"
        }
    }
}

C++

char is already an integer type in C++, and it gets automatically promoted to int. So you can use a character where you would otherwise use an integer. Conversely, you can use an integer where you would normally use a character, except you may need to cast it, as char is smaller.

In this case, the output operator << is overloaded to handle integer (outputs the decimal representation) and character (outputs just the character) types differently, so we need to cast it in both cases.

#include <iostream>

int main() {
  std::cout << (int)'a' << std::endl; // prints "97"
  std::cout << (char)97 << std::endl; // prints "a"
  return 0;
}

Clojure

(print (int \a)) ; prints "97"
(print (char 97)) ; prints \a

; Unicode is also available, as Clojure uses the underlying java Strings & chars
(print (int \π))  ; prints 960
(print (char 960)) ; prints \π

; use String because char in Java can't represent characters outside Basic Multilingual Plane
(print (.codePointAt "𝅘𝅥𝅮" 0)) ; prints 119136
(print (String. (int-array 1 119136) 0 1)) ; prints 𝅘𝅥𝅮

CLU

start_up = proc ()
    po: stream := stream$primary_output()
    
    % To turn a character code into an integer, use char$c2i
    % (but then to print it, it needs to be turned into a string first
    % with int$unparse)
    stream$putl(po, int$unparse( char$c2i( 'a' ) ) ) % prints '97' 
    
    % To turn an integer into a character code, use char$i2c
    stream$putc(po, char$i2c( 97 ) );  % prints 'a'
end start_up

Output:

97
a

COBOL

Tested with GnuCOBOL on an ASCII based GNU/Linux system. Running this code on EBCDIC native hardware would display a control code and 000000093.

       identification division.
       program-id. character-codes.
       remarks. COBOL is an ordinal language, first is 1.
       remarks. 42nd ASCII code is ")" not, "*".
       procedure division.
       display function char(42)
       display function ord('*')
       goback.
       end program character-codes.

Output:

prompt$ cobc -xj character-codes.cob
)
000000043

CoffeeScript

CoffeeScript transcompiles to JavaScript, so it uses the JS standard library.

console.log 'a'.charCodeAt 0 # 97
console.log String.fromCharCode 97 # a

Common Lisp

(princ (char-code #\a)) ; prints "97"
(princ (code-char 97)) ; prints "a"

Component Pascal

BlackBox Component Builder

PROCEDURE CharCodes*;
VAR
	c : CHAR;
BEGIN
	c := 'A';
	StdLog.Char(c);StdLog.String(":> ");StdLog.Int(ORD(c));StdLog.Ln;
	c := CHR(3A9H);
	StdLog.Char(c);StdLog.String(":> ");StdLog.Int(ORD(c));StdLog.Ln
END CharCodes;

Output:

A:>  65
Ω:>  937

D

void main() {
    import std.stdio, std.utf;

    string test = "a";
    size_t index = 0;

    // Get four-byte utf32 value for index 0.
    writefln("%d", test.decode(index));

    // 'index' has moved to next character input position.
    assert(index == 1);
}

Output:

Dc

A dc program cannot look into strings. But it can convert numeric values into single char strings or print numeric codes directly:

97P

Output:

Delphi

Example from Studio 2006.

program Project1;

{$APPTYPE CONSOLE}

uses
  SysUtils;
var
  aChar:Char;
  aCode:Byte;
  uChar:WideChar;
  uCode:Word;
begin
  aChar := Chr(97);       Writeln(aChar);
  aCode := Ord(aChar);    Writeln(aCode);
  uChar := WideChar(97);  Writeln(uChar);
  uCode := Ord(uChar);    Writeln(uCode);

  Readln;
end.

Draco

proc nonrec main() void:
    writeln(pretend(97, char));   /* prints "a" */
    writeln(pretend('a', byte));  /* prints 97 */
corp

DWScript

PrintLn(Ord('a'));
PrintLn(Chr(97));

Dyalect

print('a'.Order())
print(Char(97))

E

? 'a'.asInteger()
# value: 97

? <import:java.lang.makeCharacter>.asChar(97)
# value: 'a'

EasyLang

print strcode "a"
print strchar 97

Ecstasy

module CharacterCodes {
    @Inject Console console;
    void run() {
        for (Char char : ['\0', '\d', 'A', '$', '¢', '~', '˜']) {
            // character to its integer value
            UInt32 codepoint = char.codepoint;

            // integer value back to its character value
            Char fromCodePoint = codepoint.toChar();   // or: "new Char(codepoint)"

            console.print($|Character {char.quoted()}:\
                           | Unicode codepoint={char.codepoint},\
                           | ASCII={char.ascii},\
                           | UTF8 bytes={char.utf8()},\
                           | char from codepoint={fromCodePoint.quoted()}
                         );
        }
    }
}

Output:

Character '\0': Unicode codepoint=0, ASCII=True, UTF8 bytes=0x00, char from codepoint='\0'
Character '\d': Unicode codepoint=127, ASCII=True, UTF8 bytes=0x7F, char from codepoint='\d'
Character 'A': Unicode codepoint=65, ASCII=True, UTF8 bytes=0x41, char from codepoint='A'
Character '$': Unicode codepoint=36, ASCII=True, UTF8 bytes=0x24, char from codepoint='$'
Character '¢': Unicode codepoint=162, ASCII=False, UTF8 bytes=0xC2A2, char from codepoint='¢'
Character '~': Unicode codepoint=126, ASCII=True, UTF8 bytes=0x7E, char from codepoint='~'
Character '˜': Unicode codepoint=732, ASCII=False, UTF8 bytes=0xCB9C, char from codepoint='˜'

Eiffel

All characters are of the type CHARACTER_8 (ASCII encoding) or CHARACTER_32 (Unicode encoding). CHARACTER is a synonym for either of these two (depending on the compiler option). Characters can be assigned using character literals (a single character enclosed in single quotes) or code value notation (of the form '%/value/' where value is an integer literal of any of the recognized forms).

class
	APPLICATION
inherit
	ARGUMENTS
create
	make

feature {NONE} -- Initialization

	make
			-- Run application.
		local
			c8: CHARACTER_8
			c32: CHARACTER_32
		do
			c8 := '%/97/'			-- using code value notation
			c8 := '%/0x61/'			-- same as above, but using hexadecimal literal
			print(c8.natural_32_code)	-- prints "97"
			print(c8)			-- prints the character "a"
			
			c32 := 'a'			-- using character literal
			print(c32.natural_32_code)	-- prints "97"
			print(c32)			-- prints "U+00000061"

			--c8 := 'π'			-- compile-time error (c8 does not have enough range)
			c32 := 'π'			-- assigns Unicode value 960
		end
end

Limitations: There is no "put_character_32" feature for standard io (FILE class), so there appears to be no way to print Unicode characters.

Elena

ELENA 6.x :

import extensions;

public program()
{
    var ch := $97;

    console.printLine(ch);
    console.printLine(ch.toInt())
}

Output:

a
97

Elixir

A String in Elixir is a UTF-8 encoded binary.

iex(1)> code = ?a
97
iex(2)> to_string([code])
"a"

Emacs Lisp

(string-to-char "a") ;=> 97
(format "%c" 97) ;=> "a"

EMal

^|ord and chr work with Unicode code points|^
writeLine(ord("a")) # prints "97"
writeLine(chr(97))  # prints "a"
writeLine(ord("π")) # prints "960"
writeLine(chr(960)) # prints "π"
writeLine()
var cps = int[]
for each var c in text["a", "π", "字", "🐘"]
  var cp = ord(c)
  cps.append(cp)
  writeLine(c + " = " + cp)
end
writeLine()
for each int i in cps
  var c = chr(i)
  writeLine(i + " = " + c)
end

Output:

97
a
960
π

a = 97
π = 960
字 = 23383
🐘 = 128024

97 = a
960 = π
23383 = 字
128024 = 🐘

Erlang

In Erlang, lists and strings are the same, only the representation changes. Thus:

1> F = fun([X]) -> X end. 
#Fun<erl_eval.6.13229925>
2> F("a").
97

If entered manually, one can also get ASCII codes by prefixing characters with $:

3> $a.
97

Unicode is fully supported since release R13A only.

Euphoria

printf(1,"%d\n", 'a') -- prints "97"
printf(1,"%s\n", 97) -- prints "a"

F#

let c = 'A'
let n = 65
printfn "%d" (int c)
printfn "%c" (char n)

Output:

65
A

Factor

CHAR: katakana-letter-a .
"ア" first .

12450 1string print

FALSE

'A."
"65,

Fantom

A character is represented in single quotes: the 'toInt' method returns the code for the character. The 'toChar' method converts an integer into its respective character.

fansh> 97.toChar
a
fansh> 'a'.toInt
97

Fennel

(string.byte :A) ; 65
(string.char 65) ; "A"

Forth

As with C, characters are just integers on the stack which are treated as ASCII.

char a
dup .    \ 97
emit     \ a

Fortran

Functions ACHAR and IACHAR specifically work with the ASCII character set, while the results of CHAR and ICHAR will depend on the default character set being used.

WRITE(*,*) ACHAR(97), IACHAR("a")   
WRITE(*,*) CHAR(97), ICHAR("a")

Free Pascal

See Pascal

FreeBASIC

' FreeBASIC v1.05.0 win64
Print "a - > "; Asc("a")
Print "98 -> "; Chr(98)
Print
Print "Press any key to exit the program"
Sleep
End

Output:

a - > 97
98 -> b

Frink

The function char[x] in Frink returns the numerical Unicode codepoints for a string or character, or returns the Unicode string for an integer value or array of integer values. The chars[x] returns an array even if the string is a single character. These functions also correctly handle upper-plane Unicode characters as a single codepoint.

println[char["a"]]              // prints 97
println[chars["a"]]             // prints [97] (an array)
println[char[97]]               // prints a
println[char["Frink rules!"]]   // prints [70, 114, 105, 110, 107, 32, 114, 117, 108, 101, 115, 33]
println[[70, 114, 105, 110, 107, 32, 114, 117, 108, 101, 115, 33]]  // prints "Frink rules!"

FutureBasic

print "a -> ";  ASC("a")
print "98 -> "; CHR$(98)

handleevents

Output:

a -> 97
98 -> b

Gambas

Public Sub Form_Open()
Dim sChar As String 

sChar = InputBox("Enter a character")
Print "Character " & sChar & " = ASCII " & Str(Asc(sChar))

sChar = InputBox("Enter a ASCII code")
Print "ASCII code " & sChar & " represents " & Chr(Val(sChar))

End

Output:

Character W = ASCII 87
ASCII code 35 represents #

GAP==

# Code must be in 0 .. 255.
CharInt(65);
# 'A'
IntChar('Z');
# 90

Go

In Go, a character literal is simply an integer constant of the character code:

fmt.Println('a') // prints "97"
fmt.Println('π') // prints "960"

package main

import (
	"fmt"
)

func main() {
	// Given a character value in your language, print its code
	fmt.Printf("%d\n", 'A') // prt 65
	// Given a code, print out the corresponding character.
	fmt.Printf("%c\n", 65) // prt A
}

Literal constants in Go are not typed (named constants can be). The variable and constant types most commonly used for character data are byte, rune, and string. This example program shows character codes (as literals) stored in typed variables, and printed out with default formatting. Note that since byte and rune are integer types, the default formatting is a printable base 10 number. String is not numeric, and a little extra work must be done to print the character codes.

package main

import "fmt"

func main() {
	// yes, there is more concise syntax, but this makes
	// the data types very clear.
	var b byte = 'a'
	var r rune = 'π'
	var s string = "aπ"

	fmt.Println(b, r, s)
	fmt.Println("string cast to []rune:", []rune(s))
	// A range loop over a string gives runes, not bytes
	fmt.Print("    string range loop: ")
	for _, c := range s {
		fmt.Print(c, " ") // c is type rune
	}
	// We can also print the bytes of a string without an explicit loop
	fmt.Printf("\n         string bytes: % #x\n", s)
}

Output:

97 960 aπ
string cast to []rune: [97 960]
    string range loop: 97 960 
         string bytes: 0x61 0xcf 0x80

For the second part of the task, printing the character of a given code, the %c verb of fmt.Printf will do this directly from integer values, emitting the UTF-8 encoding of the code, (which will typically print the character depending on your hardware and operating system configuration).

b := byte(97)
r := rune(960)
fmt.Printf("%c %c\n%c %c\n", 97, 960, b, r)

Output:

a π
a π

You can think of the default formatting of strings as being the printable characters of the string. In fact however, it is even simpler. Since we expect our output device to interpret UTF-8, and we expect our string to contain UTF-8, the default formatting simply dumps the bytes of the string to the output.

Examples showing strings constructed from integer constants and then printed:

fmt.Println(string(97)) // prints "a"
fmt.Println(string(960)) // prints "π"
fmt.Println(string([]rune{97, 960})) // prints "aπ"

Golfscript

To convert a number to a string, we use the array to string coercion.

97[]+''+p

To convert a string to a number, we have a many options, of which the simplest and shortest are:

'a')\;p
'a'(\;p
'a'0=p
'a'{}/p

Groovy

Groovy does not have a character literal at all, so one-character strings have to be coerced to char. Groovy printf (like Java, but unlike C) is not type-agnostic, so the cast or coercion from char to int is also required. The reverse direction is considerably simpler.

printf ("%d\n", ('a' as char) as int)
printf ("%c\n", 97)

Output:

97
a

Haskell

import Data.Char

main = do
  print (ord 'a') -- prints "97"
  print (chr 97) -- prints "'a'"
  print (ord 'π') -- prints "960"
  print (chr 960) -- prints "'\960'"

HicEst

WRITE(Messagebox) ICHAR('a'), CHAR(97)

HolyC

Print("%d\n", 'a'); /* prints "97" */
Print("%c\n", 97);  /* prints "a" */

Hoon

|%
++  enc
  |=  char=@t  `@ud`char
++  dec
  |=  code=@ud  `@t`code
--

i

software {
	print(number('a'))
	print(text([97]))
}

Icon and Unicon

procedure main(arglist)
if *arglist > 0 then L := arglist else L := [97, "a"]

every x := !L do 
   write(x, " ==> ", char(integer(x)) | ord(x) )  # char produces a character, ord produces a number
end

Icon and Unicon do not currently support double byte character sets.

Output:

97 ==> a
a ==> 97

Io

Here character is a sequence (string) of length one.

"a" at(0) println       // --> 97
97 asCharacter println  // --> a

"π" at(0) println       // --> 960
960 asCharacter println // --> π

J

   4 u: 97 98 99 9786
abc☺

   3 u: 7 u: 'abc☺'
97 98 99 9786

7 u: converts to utf-16 (8 u: would convert to utf-8, and 9 u: would convert to utf-32), and 3 u: converts what the uncode consortium calls "code points" to numeric form. Since J character literals are utf-8 (primarily because that's how OS interfaces work), by itself 3 u: would give us:

   3 u: 'abc☺'
97 98 99 226 152 186

Also, if we limit ourselves to ascii, we have other ways of accomplishing the same thing. a. is a list of the 8 bit character codes and we can index from it, or search it (though that's mostly a notational convenience, since the underlying type already gives us all we need to know).

   97 98 99{a.
abc
   a.i.'abc'
97 98 99

Java

In Java, a char is a 2-byte unsigned value, so it will fit within an 4-byte int.

To convert a character to it's ASCII code, cast the char to an int.
The following will yield 97.

(int) 'a'

You could also specify a unicode hexadecimal value, using the \u escape sequence.

(int) '\u0061'

To convert an ASCII code to it's ASCII representation, cast the int value to a char.

(char) 97

Java also offers the Character class, comprised of several utilities for Unicode based operations.
Here are a few examples.

Get the integer value represented by the ASCII character.
The second parameter here, is the radix. This will return an int with the value of 1.

Character.digit('1', 10)

Inversely, get the ASCII representation of the integer.
Again, the second parameter is the radix. This will return a char with the value of '1'.

Character.forDigit(1, 10)

JavaScript

Here character is just a string of length 1

console.log('a'.charCodeAt(0)); // prints "97"
console.log(String.fromCharCode(97)); // prints "a"

ES6 brings String.codePointAt() and String.fromCodePoint(), which provide access to 4-byte unicode characters, in addition to the usual 2-byte unicode characters.

['字'.codePointAt(0), '🐘'.codePointAt(0)]

Output:

[23383, 128024]

and

[23383, 128024].map(function (x) {
	return String.fromCodePoint(x);
})

Output:

["字", "🐘"]

Joy

'a ord.
97 chr.

jq

jq data strings are JSON strings, which can be "explode"d into an array of integers, each representing a Unicode codepoint. The inverse of the explode filter is implode. explode can of course be used for single-character strings, and so for example:

"a" | explode  # => [ 97 ]
[97] | implode # => "a"

Here is a filter which can be used to convert an integer to the corresponding

character:

def chr: [.] | implode;

Example: 1024 | chr # => "Ѐ"

Julia

Julia character constants (of type Char) are treated as an integer type representing the Unicode codepoint of the character, and can easily be converted to and from other integer types.

println(Int('a'))
println(Char(97))

Output:

97
a

K

  _ic "abcABC"
97 98 99 65 66 67

  _ci 97 98 99 65 66 67
"abcABC"

Kotlin

fun main() {
    var c = 'a'
    var i = c.code
    println("$c  <-> $i")
    i += 2
    c = i.toChar()
    println("$i <-> $c")
}

Output:

a  <-> 97
99 <-> c

LabVIEW

This image is a VI Snippet, an executable image of LabVIEW code. The LabVIEW version is shown on the top-right hand corner. You can download it, then drag-and-drop it onto the LabVIEW block diagram from a file browser, and it will appear as runnable, editable code.

Lang

Translation of: Python

fn.println(fn.toValue(a)) # Prints "97"
fn.println(fn.toChar(97)) # Prints "a"

# Unicode
fn.println(fn.toValue(π)) # Prints "960"
fn.println(fn.toChar(960)) # Prints "π"

Lang5

: CHAR  "!\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[" comb
        '\\ comb -1 remove append "]^_`abcdefghijklmnopqrstuvwxyz{|}~" comb append ;
: CODE  95 iota 33 + ;                : comb  "" split ;
: extract'  rot 1 compress index subscript expand drop ;
: chr  CHAR CODE extract' ;
: ord  CODE CHAR extract' ;

'a ord .    # 97
97 chr .    # a

langur

Langur has code point literals (enclosed in straight single quotes), which may use escape codes. They are integers.

The s2cp(), cp2s(), and s2gc() functions convert between code point integers, grapheme clusters and strings. Also, string indexing is by code point.

val .a1 = 'a'
val .a2 = 97
val .a3 = "a"[1]
val .a4 = s2cp "a", 1
val .a5 = [.a1, .a2, .a3, .a4]

writeln .a1 == .a2
writeln .a2 == .a3
writeln .a3 == .a4
writeln "numbers: ", join ", ", [.a1, .a2, .a3, .a4, .a5]
writeln "letters: ", join ", ", map cp2s, [.a1, .a2, .a3, .a4, .a5]

Output:

true
true
true
numbers: 97, 97, 97, 97, [97, 97, 97, 97]
letters: a, a, a, a, aaaa

Lasso

'a'->integer
'A'->integer
97->bytes
65->bytes

Output:

97

65 a

A

LFE

In LFE/Erlang, lists and strings are the same, only the representation changes. For example:

> (list 68 111 110 39 116 32 80 97 110 105 99 46)
"Don't Panic."

As for this exercise, here's how you could print out the ASCII code for a letter, and a letter from the ASCII code:

> (: io format '"~w~n" '"a")
97
ok
> (: io format '"~p~n" (list '(97)))
"a"
ok

Liberty BASIC

charCode = 97
char$ = "a"
print chr$(charCode) 'prints a
print asc(char$) 'prints 97

LIL

LIL does not handle NUL bytes in character strings, char 0 returns an empty string.

print [char 97]
print [codeat "a" 0]

Output:

a
97

Lingo

-- returns Unicode code point (=ASCII code for ASCII characters) for character
put chartonum("a")
-- 97

-- returns character for Unicode code point (=ASCII code for ASCII characters)
put numtochar(934)
-- Φ

Little

puts("Unicode value of ñ is ${scan("ñ", "%c")}");
printf("The code 241 in Unicode is the letter: %c.\n", 241);

LiveCode

Since 7.0.x works with unicode
put charToNum("") && numToChar(240)

Logo

Logo characters are words of length 1.

print ascii "a    ; 97
print char 97     ; a

Logtalk

|?- char_code(Char, 97), write(Char).
a
Char = a
yes

|?- char_code(a, Code), write(Code).
97
Code = 97
yes

Lua

print(string.byte("a")) -- prints "97"
print(string.char(97)) -- prints "a"

M2000 Interpreter

\\ ANSI
Print Asc("a")
Print Chr$(Asc("a"))
\\ Utf16-Le
Print ChrCode("a")
Print ChrCode$(ChrCode("a"))

\\ (,) is an empty array.

Function Codes(a$) {
      If Len(A$)=0 then =(,) : Exit          
      Buffer Mem as byte*Len(a$)
      \\ Str$(string) return one byte character
      Return Mem, 0:=Str$(a$)
           Inventory Codes
      For i=0 to len(Mem)-1
      Append Codes, i:=Eval(Mem, i)
      Next i
      =Codes
}
Print Codes("abcd")
\\ 97 98 99 100

Maple

There are two ways to do this in Maple. First, there are procedures in StringTools for this purpose.

> use StringTools in Ord( "A" ); Char( 65 ) end;
                                   65

                                  "A"

Second, the procedure convert handles conversions to and from byte values.

> convert( "A", bytes );
                                  [65]

> convert( [65], bytes );
                                  "A"

Mathematica / Wolfram Language

Use the FromCharacterCode and ToCharacterCode functions:

ToCharacterCode["abcd"]
FromCharacterCode[{97}]

Output:

{97, 98, 99, 100}
"a"

MATLAB / Octave

There are two built-in function that perform these tasks. To convert from a number to a character use:

character = char(asciiNumber)

To convert from a character to its corresponding ascii character use:

asciiNumber = double(character)

or if you need this number as an integer not a double use:

asciiNumber = uint16(character)
asciiNumber = uint32(character)
asciiNumber = uint64(character)

Sample Usage:

>> char(87)

ans =

W

>> double('W')

ans =

    87

>> uint16('W')

ans =

     87

Maxima

ascii(65);
"A"

cint("A");
65

Metafont

Metafont handles only ASCII (even though codes beyond 127 can be given and used as real ASCII codes)

message "enter a letter: ";
string a;
a := readstring;
message decimal (ASCII a); % writes the decimal number of the first character
                           % of the string a
message "enter a number: ";
num := scantokens readstring;
message char num;   % num can be anything between 0 and 255; what will be seen
                    % on output depends on the encoding used by the "terminal"; e.g.
                    % any code beyond 127 when UTF-8 encoding is in use will give
                    % a bad encoding; e.g. to see correctly an "è", we should write
message char10;  % (this add a newline...)
message char hex"c3" & char hex"a8";  % since C3 A8 is the UTF-8 encoding for "è"
end

Microsoft Small Basic

TextWindow.WriteLine("The ascii code for 'A' is: " + Text.GetCharacterCode("A") + ".") 
TextWindow.WriteLine("The character for '65' is: " + Text.GetCharacter(65) + ".")

Output:

The ascii code for 'A' is: 65.
The character for '65' is: A.
Press any key to continue...

MiniScript

Translation of: Wren

MiniScript does not have a character type as such but one can use single character strings instead. Strings can contain any Unicode code point.

cps = []
for c in ["a", "π", "字", "🐘"]
  cp = c.code
  cps.push cp
  print c + " = " + cp
end for
print
for i in cps
  print i + " = " + char(i)
end for

Output:

a = 97
π = 960
字 = 23383
🐘 = 128024

97 = a
960 = π
23383 = 字
128024 = 🐘

Modula-2

MODULE asc;

IMPORT  InOut;

VAR     letter          : CHAR;
        ascii           : CARDINAL;

BEGIN
  letter := 'a';
  InOut.Write (letter);
  ascii := ORD (letter);
  InOut.Write (11C);            (*  ASCII TAB   *)
  InOut.WriteCard (ascii, 8);
  ascii := ascii - ORD ('0');
  InOut.Write (11C);            (*  ASCII TAB   *)
  InOut.Write (CHR (ascii));
  InOut.WriteLn
END asc.

Output:

jan@Beryllium:~/modula/rosetta$ ./asc
a             97        1

Modula-3

The built in functions ORD and VAL work on characters, among other things.

ORD('a') (* Returns 97 *)
VAL(97, CHAR); (* Returns 'a' *)

MUMPS

WRITE $ASCII("M")
WRITE $CHAR(77)

Nanoquery

println ord("a")
println chr(97)

println ord("π")
println chr(960)

Output:

Neko

Neko treats strings as an array of bytes

// An 'a' and a 'b'
var s = "a";
var c = 98;
var h = " ";

$print("Character code for 'a': ", $sget(s, 0), "\n");

$sset(h, 0, c);
$print("Character code ", c,  ": ", h, "\n");

Output:

Character code for 'a': 97
Character code 98: b

Neko also has standard primitives for handling the byte array as UTF-8

// While Neko also includes some UTF-8 operations,
//  native strings are just arrays of bytes
var us = "¥·£·€·$·¢·₡·₢·₣·₤·₥·₦·₧·₨·₩·₪·₫·₭·₮·₯·₹";

// load some Std lib primitives
utfGet = $loader.loadprim("std@utf8_get", 2);
utfSub = $loader.loadprim("std@utf8_sub", 3);
utfAlloc = $loader.loadprim("std@utf8_buf_alloc", 1);
utfAdd = $loader.loadprim("std@utf8_buf_add", 2);
utfContent = $loader.loadprim("std@utf8_buf_content", 1);

// Pull out the Euro currency symbol from the UTF-8 currency sampler
var uc = utfGet(us, 4);
$print("UFT-8 code for '", utfSub(us, 4, 1), "': ", uc, "\n");

// Build a UTF-8 buffer
var buf = utfAlloc(4);

// Add a Pound Sterling symbol
uc = 8356;
utfAdd(buf, uc);
$print("UTF-8 code ", uc, ": ", utfContent(buf), "\n");

Output:

UFT-8 code for '€': 8364
UTF-8 code 8356: ₤

NESL

In NESL, character literals are prefixed with a backtick. The functions char_code and code_char convert between characters and integer character codes.

char_code(`a);

it = 97 : int

code_char(97);

it = `a : char

NetRexx

NetRexx provides built-in functions to convert between character and decimal/hexadecimal.

/* NetRexx */
options replace format comments java crossref symbols nobinary

runSample(arg)
return

-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
method runSample(arg) private static
  -- create some sample data: character, hex and unicode
  samp = ' ' || 'a'.sequence('e') || '$' || '\xa2'.sequence('\xa5') || '\u20a0'.sequence('\u20b5')
  -- use the C2D C2X D2C and X2C built-in functions
  say "'"samp"'"
  say '   | Chr    C2D  C2X D2C X2C'
  say '---+ --- ------ ---- --- ---'
  loop ci = 1 to samp.length
    cc = samp.substr(ci, 1)
    cd = cc.c2d -- char to decimal
    cx = cc.c2x -- char to hexadecimal
    dc = cd.d2c -- decimal to char
    xc = cx.x2c -- hexadecimal to char
    say ci.right(3)"| '"cc"'" cd.right(6) cx.right(4, 0) "'"dc"' '"xc"'"
    end ci
  return

Output:

' abcde$¢£¤¥₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵'
   | Chr    C2D  C2X D2C X2C
---+ --- ------ ---- --- ---
  1| ' '     32 0020 ' ' ' '
  2| 'a'     97 0061 'a' 'a'
  3| 'b'     98 0062 'b' 'b'
  4| 'c'     99 0063 'c' 'c'
  5| 'd'    100 0064 'd' 'd'
  6| 'e'    101 0065 'e' 'e'
  7| '$'     36 0024 '$' '$'
  8| '¢'    162 00A2 '¢' '¢'
  9| '£'    163 00A3 '£' '£'
 10| '¤'    164 00A4 '¤' '¤'
 11| '¥'    165 00A5 '¥' '¥'
 12| '₠'   8352 20A0 '₠' '₠'
 13| '₡'   8353 20A1 '₡' '₡'
 14| '₢'   8354 20A2 '₢' '₢'
 15| '₣'   8355 20A3 '₣' '₣'
 16| '₤'   8356 20A4 '₤' '₤'
 17| '₥'   8357 20A5 '₥' '₥'
 18| '₦'   8358 20A6 '₦' '₦'
 19| '₧'   8359 20A7 '₧' '₧'
 20| '₨'   8360 20A8 '₨' '₨'
 21| '₩'   8361 20A9 '₩' '₩'
 22| '₪'   8362 20AA '₪' '₪'
 23| '₫'   8363 20AB '₫' '₫'
 24| '€'   8364 20AC '€' '€'
 25| '₭'   8365 20AD '₭' '₭'
 26| '₮'   8366 20AE '₮' '₮'
 27| '₯'   8367 20AF '₯' '₯'
 28| '₰'   8368 20B0 '₰' '₰'
 29| '₱'   8369 20B1 '₱' '₱'
 30| '₲'   8370 20B2 '₲' '₲'
 31| '₳'   8371 20B3 '₳' '₳'
 32| '₴'   8372 20B4 '₴' '₴'
 33| '₵'   8373 20B5 '₵' '₵'

Nim

echo ord('a') # echoes 97
echo chr(97) # echoes a

import unicode

echo int("π".runeAt(0)) # echoes 960
echo Rune(960) # echoes π

NS-HUBASIC

NS-HUBASIC uses a non-ASCII character set that doesn't include letters in lowercase.

10 PRINT CODE "A"
20 PRINT CHR$(38)

Output:

 0A
&

Oberon-2

MODULE Ascii;
IMPORT Out;
VAR
	c: CHAR;
	d: INTEGER;
BEGIN
	c := CHR(97);
	d := ORD("a");
	Out.Int(d,3);Out.Ln;
	Out.Char(c);Out.Ln
END Ascii.

Output:

97

a

Objeck

'a'->As(Int)->PrintLine();
97->As(Char)->PrintLine();

Object Pascal

See Pascal

OCaml

Printf.printf "%d\n" (int_of_char 'a'); (* prints "97" *)
Printf.printf "%c\n" (char_of_int 97); (* prints "a" *)

The following are aliases for the above functions:

# Char.code ;;
- : char -> int = <fun>
# Char.chr;;
- : int -> char = <fun>

Oforth

Oforth has not type or class for characters. A character is an integer which value is its unicode code.

'a' println

Output:

OpenEdge/Progress

MESSAGE
   CHR(97) SKIP
   ASC("a") 
VIEW-AS ALERT-BOX.

Oz

Characters in Oz are the same as integers in the range 0-255 (ISO 8859-1 encoding). To print a number as a character, we need to use it as a string (i.e. a list of integers from 0 to 255):

{System.show &a}  %% prints "97"
{System.showInfo [97]}  %% prints "a"

PARI/GP

print(Vecsmall("a")[1]);
print(Strchr([72, 101, 108, 108, 111, 44, 32, 119, 111, 114, 108, 100, 33]))

Pascal

writeln(ord('a'));
writeln(chr(97));

Plain English

\ Obs: The little-a byte is a byte equal to 97.
Write the little-a byte's whereabouts on the console.
Put 97 into a number. 
Write the number's target on the console.

Perl

Narrow

The code is straightforward when characters are all narrow (single byte).

use strict;
use warnings;
use utf8;
binmode(STDOUT, ':utf8');
use Encode;
use Unicode::UCD 'charinfo';
use List::AllUtils qw(zip natatime);

for my $c (split //, 'AΑА薵') {
    my $o = ord $c;
    my $utf8 = join '', map { sprintf "%x ", ord } split //, Encode::encode("utf8", $c);
    my $iterator = natatime 2, zip
        @{['Character', 'Character name',       'Ordinal(s)', 'Hex ordinal(s)',   'UTF-8', 'Round trip']},
        @{[ $c,          charinfo($o)->{'name'}, $o,           sprintf("0x%x",$o), $utf8,   chr $o,    ]};
    while ( my ($label, $value) = $iterator->() ) {
        printf "%14s: %s\n", $label, $value
    }
    print "\n";
}

Output:

     Character: A
Character name: LATIN CAPITAL LETTER A
    Ordinal(s): 65
Hex ordinal(s): 0x41
         UTF-8: 41
    Round trip: A

     Character: Α
Character name: GREEK CAPITAL LETTER ALPHA
    Ordinal(s): 913
Hex ordinal(s): 0x391
         UTF-8: ce 91
    Round trip: Α

     Character: А
Character name: CYRILLIC CAPITAL LETTER A
    Ordinal(s): 1040
Hex ordinal(s): 0x410
         UTF-8: d0 90
    Round trip: А

     Character: 薵
Character name: CJK UNIFIED IDEOGRAPH-2A6A5
    Ordinal(s): 173733
Hex ordinal(s): 0x2a6a5
         UTF-8: f0 aa 9a a5
    Round trip: 薵

Wide

Have to work a little harder to handle wide (multi-byte) characters.

use strict;
use warnings;
use feature 'say';
use utf8;
binmode(STDOUT, ':utf8');
use Unicode::Normalize 'NFC';
use Unicode::UCD qw(charinfo charprop);

while ('Δ̂🇺🇸👨‍👩‍👧‍👦' =~ /(\X)/g) {   
    my @ordinals = map { ord } split //, my $c = $1;
    printf "%14s: %s\n"x7 . "\n",
    'Character',        NFC $c,
    'Character name',   join(', ', map { charinfo($_)->{'name'} } @ordinals),
    'Unicode property', join(', ', map { charprop($_, "Gc")     } @ordinals),
    'Ordinal(s)',       join(' ', @ordinals),
    'Hex ordinal(s)',   join(' ',  map { sprintf("0x%x", $_)    } @ordinals),
    'UTF-8',            join('',   map { sprintf "%x ", ord     } (utf8::encode($c), split //, $c)),
    'Round trip',       join('',   map { chr                    } @ordinals);
}

Output:

       Character: Δ̂
  Character name: GREEK CAPITAL LETTER DELTA, COMBINING CIRCUMFLEX ACCENT
Unicode property: Uppercase_Letter, Nonspacing_Mark
      Ordinal(s): 916 770
  Hex ordinal(s): 0x394 0x302
           UTF-8: ce 94 cc 82
      Round trip: Δ̂

       Character: 🇺🇸
  Character name: REGIONAL INDICATOR SYMBOL LETTER U, REGIONAL INDICATOR SYMBOL LETTER S
Unicode property: Other_Symbol, Other_Symbol
      Ordinal(s): 127482 127480
  Hex ordinal(s): 0x1f1fa 0x1f1f8
           UTF-8: f0 9f 87 ba f0 9f 87 b8
      Round trip: 🇺🇸

       Character: 👨‍👩‍👧‍👦
  Character name: MAN, ZERO WIDTH JOINER, WOMAN, ZERO WIDTH JOINER, GIRL, ZERO WIDTH JOINER, BOY
Unicode property: Other_Symbol, Format, Other_Symbol, Format, Other_Symbol, Format, Other_Symbol
      Ordinal(s): 128104 8205 128105 8205 128103 8205 128102
  Hex ordinal(s): 0x1f468 0x200d 0x1f469 0x200d 0x1f467 0x200d 0x1f466
           UTF-8: f0 9f 91 a8 e2 80 8d f0 9f 91 a9 e2 80 8d f0 9f 91 a7 e2 80 8d f0 9f 91 a6
      Round trip: 👨‍👩‍👧‍👦

Phix

Library: Phix/basics

Characters and their ascii codes are one and the same. (See also printf, %d / %s / %c.)

?'A'
puts(1,65)

Output:

65
A

Phixmonti

'a' print nl
97 tochar print

PHP

Here character is just a string of length 1

echo ord('a'), "\n"; // prints "97"
echo chr(97), "\n"; // prints "a"

Picat

main => 
  println(chr(97)),
  println(ord('a')),
  println(ord(a)).

Output:

a
97
97

PicoLisp

: (char "a")
-> 97
: (char "字")
-> 23383
: (char 23383)
-> "字"
: (chop "文字")
-> ("文" "字")
: (mapcar char @)
-> (25991 23383)

PL/I

declare 1 u union,
          2 c character (1),
          2 i fixed binary (8) unsigned;
c = 'a'; put skip list (i); /* prints 97  */
i = 97;  put skip list (c); /* prints 'a' */

PowerShell

Powershell does allow for character literals with [convert]

$char = [convert]::toChar(0x2f) #=> /

PowerShell does not allow for character literals directly, so to get a character one first needs to convert a single-character string to a char:

$char = [char] 'a'

Then a simple cast to int yields the character code:

$charcode = [int] $char   # => 97

This also works with Unicode:

[int] [char] '☺'          # => 9786

For converting an integral character code into the actual character, a cast to char suffices:

[char] 97    # a
[char] 9786  # ☺

Prolog

SWI-Prolog has predefined predicate char_code/2.

?- char_code(a, X).
X = 97.

?- char_code(X, 97).
X = a.

PureBasic

PureBasic allows compiling code so that it will use either Ascii or a Unicode (UCS-2) encoding for representing its string content. It also allows for the source code that is being compiled to be in either Ascii or UTF-8 encoding. A one-character string is used here to hold the character and a numerical character type is used to hold the character code. The character type is either one or two bytes in size, depending on whether compiling for Ascii or Unicode respectively.

If OpenConsole()
  ;Results are the same when compiled for Ascii or Unicode
  charCode.c = 97
  Char.s = "a"
  PrintN(Chr(charCode))   ;prints a
  PrintN(Str(Asc(Char)))  ;prints 97

  Print(#CRLF$ + #CRLF$ + "Press ENTER to exit")
  Input()
  CloseConsole()
EndIf

This version should be compiled with Unicode setting and the source code to be encoded using UTF-8.

If OpenConsole()
  ;UTF-8 encoding compiled for Unicode (UCS-2)
  charCode.c = 960 
  Char.s = "π"            
  PrintN(Chr(charCode))   ;prints π
  PrintN(Str(Asc(Char)))  ;prints 960

  Print(#CRLF$ + #CRLF$ + "Press ENTER to exit")
  Input()
  CloseConsole()
EndIf

Python

Works with: Python version 2.x

Here character is just a string of length 1

8-bit characters:

print ord('a') # prints "97"
print chr(97)  # prints "a"

Unicode characters:

print ord(u'π')   # prints "960"
print unichr(960) # prints "π"

Works with: Python version 3.x

Here character is just a string of length 1

print(ord('a')) # prints "97" (will also work in 2.x)
print(ord('π')) # prints "960"
print(chr(97))  # prints "a" (will also work in 2.x)
print(chr(960)) # prints "π"

Quackery

As a dialogue in the Quackery shell.

Welcome to Quackery.

Enter "leave" to leave the shell.

/O> char a
...

Stack: 97

/O> emit
...
a
Stack empty.

R

ascii <- as.integer(charToRaw("hello world")); ascii
text <- rawToChar(as.raw(ascii)); text

Racket

#lang racket

(define (code ch)
  (printf "The unicode number for ~s is ~a\n" ch (char->integer ch)))
(code #\a)
(code #\λ)

(define (char n)
  (printf "The unicode number ~a is the character ~s\n" n (integer->char n)))
(char 97)
(char 955)

Raku

(formerly Perl 6) Both Perl 5 and Raku have good Unicode support, though Raku attempts to make working with Unicode effortless. Note that even multi-byte emoji and characters outside the BMP are considered single characters. Also note: all of these routines are built into the base compiler. No need to load external libraries. See Wikipedia: Unicode character properties for explanation of Unicode property.

for 'AΑА𪚥🇺🇸👨‍👩‍👧‍👦'.comb {
    .put for
    [ 'Character',
      'Character name',
      'Unicode property',
      'Unicode script',
      'Unicode block',
      'Added in Unicode version',
      'Ordinal(s)',
      'Hex ordinal(s)',
      'UTF-8',
      'UTF-16LE',
      'UTF-16BE',
      'Round trip by name',
      'Round trip by ordinal'
    ]».fmt('%25s:')
    Z
    [ $_,
      .uninames.join(', '),
      .uniprops.join(', '),
      .uniprops('Script').join(', '),
      .uniprops('Block').join(', '),
      .uniprops('Age').join(', '),
      .ords,
      .ords.fmt('0x%X'),
      .encode('utf8'   )».fmt('%02X'),
      .encode('utf16le')».fmt('%02X').join.comb(4),
      .encode('utf16be')».fmt('%02X').join.comb(4),
      .uninames».uniparse.join,
      .ords.chrs
    ];
    say '';
}

Output:

                Character: A
           Character name: LATIN CAPITAL LETTER A
         Unicode property: Lu
           Unicode script: Latin
            Unicode block: Basic Latin
 Added in Unicode version: 1.1
               Ordinal(s): 65
           Hex ordinal(s): 0x41
                    UTF-8: 41
                 UTF-16LE: 4100
                 UTF-16BE: 0041
       Round trip by name: A
    Round trip by ordinal: A

                Character: Α
           Character name: GREEK CAPITAL LETTER ALPHA
         Unicode property: Lu
           Unicode script: Greek
            Unicode block: Greek and Coptic
 Added in Unicode version: 1.1
               Ordinal(s): 913
           Hex ordinal(s): 0x391
                    UTF-8: CE 91
                 UTF-16LE: 9103
                 UTF-16BE: 0391
       Round trip by name: Α
    Round trip by ordinal: Α

                Character: А
           Character name: CYRILLIC CAPITAL LETTER A
         Unicode property: Lu
           Unicode script: Cyrillic
            Unicode block: Cyrillic
 Added in Unicode version: 1.1
               Ordinal(s): 1040
           Hex ordinal(s): 0x410
                    UTF-8: D0 90
                 UTF-16LE: 1004
                 UTF-16BE: 0410
       Round trip by name: А
    Round trip by ordinal: А

                Character: 𪚥
           Character name: CJK UNIFIED IDEOGRAPH-2A6A5
         Unicode property: Lo
           Unicode script: Han
            Unicode block: CJK Unified Ideographs Extension B
 Added in Unicode version: 3.1
               Ordinal(s): 173733
           Hex ordinal(s): 0x2A6A5
                    UTF-8: F0 AA 9A A5
                 UTF-16LE: 69D8 A5DE
                 UTF-16BE: D869 DEA5
       Round trip by name: 𪚥
    Round trip by ordinal: 𪚥

                Character: 🇺🇸
           Character name: REGIONAL INDICATOR SYMBOL LETTER U, REGIONAL INDICATOR SYMBOL LETTER S
         Unicode property: So, So
           Unicode script: Common, Common
            Unicode block: Enclosed Alphanumeric Supplement, Enclosed Alphanumeric Supplement
 Added in Unicode version: 6.0, 6.0
               Ordinal(s): 127482 127480
           Hex ordinal(s): 0x1F1FA 0x1F1F8
                    UTF-8: F0 9F 87 BA F0 9F 87 B8
                 UTF-16LE: 3CD8 FADD 3CD8 F8DD
                 UTF-16BE: D83C DDFA D83C DDF8
       Round trip by name: 🇺🇸
    Round trip by ordinal: 🇺🇸

                Character: 👨‍👩‍👧‍👦
           Character name: MAN, ZERO WIDTH JOINER, WOMAN, ZERO WIDTH JOINER, GIRL, ZERO WIDTH JOINER, BOY
         Unicode property: So, Cf, So, Cf, So, Cf, So
           Unicode script: Common, Inherited, Common, Inherited, Common, Inherited, Common
            Unicode block: Miscellaneous Symbols and Pictographs, General Punctuation, Miscellaneous Symbols and Pictographs, General Punctuation, Miscellaneous Symbols and Pictographs, General Punctuation, Miscellaneous Symbols and Pictographs
 Added in Unicode version: 6.0, 1.1, 6.0, 1.1, 6.0, 1.1, 6.0
               Ordinal(s): 128104 8205 128105 8205 128103 8205 128102
           Hex ordinal(s): 0x1F468 0x200D 0x1F469 0x200D 0x1F467 0x200D 0x1F466
                    UTF-8: F0 9F 91 A8 E2 80 8D F0 9F 91 A9 E2 80 8D F0 9F 91 A7 E2 80 8D F0 9F 91 A6
                 UTF-16LE: 3DD8 68DC 0D20 3DD8 69DC 0D20 3DD8 67DC 0D20 3DD8 66DC
                 UTF-16BE: D83D DC68 200D D83D DC69 200D D83D DC67 200D D83D DC66
       Round trip by name: 👨‍👩‍👧‍👦
    Round trip by ordinal: 👨‍👩‍👧‍👦

RapidQ

Print Chr$(97)
Print Asc("a")

Red

Red []
print to-integer first "a" ;; -> 97
print to-integer #"a"      ;; -> 97
print to-binary "a"        ;; -> #{61} 
print to-char 97           ;; -> a

Retro

'c putc

REXX

REXX supports handling of characters with built-in functions (BIFs), whether it be hexadecimal, binary (bits), or decimal code(s).

ASCII

/*REXX program displays a char's ASCII code/value (or EBCDIC if run on an EBCDIC system)*/
yyy= 'c'                               /*assign a lowercase       c        to   YYY.    */
yyy= "c"                               /* (same as above)                               */
say  'from char, yyy code=' yyy

yyy= '63'x                             /*assign hexadecimal      63        to   YYY.    */
yyy= '63'X                             /* (same as above)                               */
say  'from  hex, yyy code=' yyy

yyy= x2c(63)                           /*assign hexadecimal      63        to   YYY.    */
say  'from  hex, yyy code=' yyy

yyy= '01100011'b                       /*assign a binary      0011 0100    to   YYY.    */
yyy= '0110 0011'b                      /* (same as above)                               */
yyy= '0110 0011'B                      /*   "   "    "                                  */
say  'from  bin, yyy code=' yyy

yyy= d2c(99)                           /*assign decimal code     99        to   YYY.    */
say  'from  dec, yyy code=' yyy

say                                    /*     [↓]    displays the value of  YYY  in ··· */
say  'char code: '   yyy               /* character code  (as an 8-bit ASCII character).*/
say  ' hex code: '   c2x(yyy)          /*    hexadecimal                                */
say  ' dec code: '   c2d(yyy)          /*        decimal                                */
say  ' bin code: '   x2b( c2x(yyy) )   /*         binary  (as a bit string)             */
                                       /*stick a fork in it, we're all done with display*/

output

from char, yyy code= c
from  hex, yyy code= c
from  hex, yyy code= c
from  bin, yyy code= c
from  dec, yyy code= c

char code:  c
 hex code:  63
 dec code:  99
 bin code:  01100011

EBCDIC

/* REXX */
yyy='c'               /*assign a lowercase   c to  YYY */
yyy='83'x             /*assign hexadecimal  83 to  YYY */
                      /*the  X  can be upper/lowercase.*/
yyy=x2c(83)           /* (same as above)               */
yyy='10000011'b       /* (same as above)               */
yyy='1000 0011'b      /* (same as above)               */
                      /*the  B  can be upper/lowercase.*/
yyy=d2c(129)          /*assign decimal code 129 to YYY */

say yyy               /*displays the value of  YYY                   */
say c2x(yyy)          /*displays the value of  YYY in hexadecimal.   */
say c2d(yyy)          /*displays the value of  YYY in decimal.       */
say x2b(c2x(yyy))/*displays the value of YYY in binary (bit string). */

Output:

Ring

see ascii("a") + nl
see char(97) + nl

RPL

Input:

"a" NUM
97 CHR

Output:

2: 97
1: "a"

Ruby

In Ruby 1.9 characters are represented as length-1 strings; same as in Python. The previous "character literal" syntax ?a is now the same as "a". Subscripting a string also gives a length-1 string. There is now an "ord" method of strings to convert a character into its integer code.

> "a".ord
=> 97
> 97.chr
=> "a"

Run BASIC

print chr$(97) 'prints a
print asc("a") 'prints 97

Rust

use std::char::from_u32;

fn main() {
    //ascii char
    println!("{}", 'a' as u8);
    println!("{}", 97 as char);

    //unicode char
    println!("{}", 'π' as u32);
    println!("{}", from_u32(960).unwrap());
}

Output:

Sather

class MAIN is
  main is
    #OUT + 'a'.int + "\n"; -- or
    #OUT + 'a'.ascii_int + "\n";
    #OUT + CHAR::from_ascii_int(97) + "\n";
  end;
end;

Scala

Library: Scala

Scala supports unicode characters, but each character is UTF-16, so there is not a 1-to-1 relationship for supplementary character sets.

In a REPL session

scala> 'a' toInt
res2: Int = 97

scala> 97 toChar
res3: Char = a

scala> '\u0061'
res4: Char = a

scala> "\uD869\uDEA5"
res5: String = 𪚥

Full swing workout

Taken the supplemental character sets in account.

import java.lang.Character._; import scala.annotation.tailrec

object CharacterCode extends App {
  def intToChars(n: Int): Array[Char] = java.lang.Character.toChars(n)

  def UnicodeToList(UTFstring: String) = {
    @tailrec
    def inner(str: List[Char], acc: List[String], surrogateHalf: Option[Char]): List[String] = {
      (str, surrogateHalf) match {
        case (Nil, _) => acc
        case (ch :: rest, None) => if (ch.isSurrogate) inner(rest, acc, Some(ch))
        else inner(rest, acc :+ ch.toString, None)
        case (ch :: rest, Some(f)) => inner(rest, (acc :+ (f.toString + ch)), None)
      }
    }
    inner(UTFstring.toList, Nil, None)
  }

  def UnicodeToInt(utf: String) = {
    def charToInt(high: Char, low: Char) =
      { if (isSurrogatePair(high, low)) toCodePoint(high, low) else high.toInt }
    charToInt(utf(0), if (utf.size > 1) utf(1) else 0)
  }

  def UTFtoHexString(utf: String) = { utf.map(ch => f"${ch.toInt}%04X").mkString("\"\\u", "\\u", "\"") }

  def flags(ch: String) = { // Testing Unicode character properties
    (if (ch matches "\\p{M}") "Y" else "N") + (if (ch matches "\\p{Mn}") "Y" else "N")
  }

  val str = '\uFEFF' /*big-endian BOM*/ + "\u0301a" +
    "$áabcde¢£¤¥©ÇßĲĳŁłʒλπक्तु•₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵℃←→⇒∙⌘☃☹☺☻ア字文𠀀" + intToChars(173733).mkString

  println(s"Example string: $str")
  println("""    | Chr C/C++/Java source  Code Point Hex      Dec Mn Name
		  	!----+ --- ------------------------- ------- -------- -- """.stripMargin('!') + "-" * 27)

  (UnicodeToList(str)).zipWithIndex.map {
    case (coll, nr) =>
      f"$nr%4d: $coll\t${UTFtoHexString(coll)}%27s U+${UnicodeToInt(coll)}%05X" +
        f"${"(" + UnicodeToInt(coll).toString}%8s) ${flags(coll)}  ${getName(coll(0).toInt)} "
  }.foreach(println)
}

Output:

Example string: ́a$áabcde¢£¤¥©ÇßĲĳŁłʒλπक्तु•₠₡₢₣₤₥₦₧₨₩₪₫€₭₮₯₰₱₲₳₴₵℃←→⇒∙⌘☃☹☺☻ア字文𠀀𪚥
    | Chr C/C++/Java source  Code Point Hex      Dec Mn Name
----+ --- ------------------------- ------- -------- -- ---------------------------
   0: 	                   "\uFEFF" U+0FEFF  (65279) NN  ZERO WIDTH NO-BREAK SPACE 
   1: ́	                   "\u0301" U+00301    (769) YY  COMBINING ACUTE ACCENT 
   2: a	                   "\u0061" U+00061     (97) NN  LATIN SMALL LETTER A 
   3: $	                   "\u0024" U+00024     (36) NN  DOLLAR SIGN 
   4: á	                   "\u00E1" U+000E1    (225) NN  LATIN SMALL LETTER A WITH ACUTE 
   5: a	                   "\u0061" U+00061     (97) NN  LATIN SMALL LETTER A 
   6: b	                   "\u0062" U+00062     (98) NN  LATIN SMALL LETTER B 
   7: c	                   "\u0063" U+00063     (99) NN  LATIN SMALL LETTER C 
   8: d	                   "\u0064" U+00064    (100) NN  LATIN SMALL LETTER D 
   9: e	                   "\u0065" U+00065    (101) NN  LATIN SMALL LETTER E 
  10: ¢	                   "\u00A2" U+000A2    (162) NN  CENT SIGN 
  11: £	                   "\u00A3" U+000A3    (163) NN  POUND SIGN 
  12: ¤	                   "\u00A4" U+000A4    (164) NN  CURRENCY SIGN 
  13: ¥	                   "\u00A5" U+000A5    (165) NN  YEN SIGN 
  14: ©	                   "\u00A9" U+000A9    (169) NN  COPYRIGHT SIGN 
  15: Ç	                   "\u00C7" U+000C7    (199) NN  LATIN CAPITAL LETTER C WITH CEDILLA 
  16: ß	                   "\u00DF" U+000DF    (223) NN  LATIN SMALL LETTER SHARP S 
  17: Ĳ	                   "\u0132" U+00132    (306) NN  LATIN CAPITAL LIGATURE IJ 
  18: ĳ	                   "\u0133" U+00133    (307) NN  LATIN SMALL LIGATURE IJ 
  19: Ł	                   "\u0141" U+00141    (321) NN  LATIN CAPITAL LETTER L WITH STROKE 
  20: ł	                   "\u0142" U+00142    (322) NN  LATIN SMALL LETTER L WITH STROKE 
  21: ʒ	                   "\u0292" U+00292    (658) NN  LATIN SMALL LETTER EZH 
  22: λ	                   "\u03BB" U+003BB    (955) NN  GREEK SMALL LETTER LAMDA 
  23: π	                   "\u03C0" U+003C0    (960) NN  GREEK SMALL LETTER PI 
  24: क	                   "\u0915" U+00915   (2325) NN  DEVANAGARI LETTER KA 
  25: ्	                   "\u094D" U+0094D   (2381) YY  DEVANAGARI SIGN VIRAMA 
  26: त	                   "\u0924" U+00924   (2340) NN  DEVANAGARI LETTER TA 
  27: ु	                   "\u0941" U+00941   (2369) YY  DEVANAGARI VOWEL SIGN U 
  28: •	                   "\u2022" U+02022   (8226) NN  BULLET 
  29: ₠	                   "\u20A0" U+020A0   (8352) NN  EURO-CURRENCY SIGN 
  30: ₡	                   "\u20A1" U+020A1   (8353) NN  COLON SIGN 
  31: ₢	                   "\u20A2" U+020A2   (8354) NN  CRUZEIRO SIGN 
  32: ₣	                   "\u20A3" U+020A3   (8355) NN  FRENCH FRANC SIGN 
  33: ₤	                   "\u20A4" U+020A4   (8356) NN  LIRA SIGN 
  34: ₥	                   "\u20A5" U+020A5   (8357) NN  MILL SIGN 
  35: ₦	                   "\u20A6" U+020A6   (8358) NN  NAIRA SIGN 
  36: ₧	                   "\u20A7" U+020A7   (8359) NN  PESETA SIGN 
  37: ₨	                   "\u20A8" U+020A8   (8360) NN  RUPEE SIGN 
  38: ₩	                   "\u20A9" U+020A9   (8361) NN  WON SIGN 
  39: ₪	                   "\u20AA" U+020AA   (8362) NN  NEW SHEQEL SIGN 
  40: ₫	                   "\u20AB" U+020AB   (8363) NN  DONG SIGN 
  41: €	                   "\u20AC" U+020AC   (8364) NN  EURO SIGN 
  42: ₭	                   "\u20AD" U+020AD   (8365) NN  KIP SIGN 
  43: ₮	                   "\u20AE" U+020AE   (8366) NN  TUGRIK SIGN 
  44: ₯	                   "\u20AF" U+020AF   (8367) NN  DRACHMA SIGN 
  45: ₰	                   "\u20B0" U+020B0   (8368) NN  GERMAN PENNY SIGN 
  46: ₱	                   "\u20B1" U+020B1   (8369) NN  PESO SIGN 
  47: ₲	                   "\u20B2" U+020B2   (8370) NN  GUARANI SIGN 
  48: ₳	                   "\u20B3" U+020B3   (8371) NN  AUSTRAL SIGN 
  49: ₴	                   "\u20B4" U+020B4   (8372) NN  HRYVNIA SIGN 
  50: ₵	                   "\u20B5" U+020B5   (8373) NN  CEDI SIGN 
  51: ℃	                   "\u2103" U+02103   (8451) NN  DEGREE CELSIUS 
  52: ←	                   "\u2190" U+02190   (8592) NN  LEFTWARDS ARROW 
  53: →	                   "\u2192" U+02192   (8594) NN  RIGHTWARDS ARROW 
  54: ⇒	                   "\u21D2" U+021D2   (8658) NN  RIGHTWARDS DOUBLE ARROW 
  55: ∙	                   "\u2219" U+02219   (8729) NN  BULLET OPERATOR 
  56: ⌘	                   "\u2318" U+02318   (8984) NN  PLACE OF INTEREST SIGN 
  57: ☃	                   "\u2603" U+02603   (9731) NN  SNOWMAN 
  58: ☹	                   "\u2639" U+02639   (9785) NN  WHITE FROWNING FACE 
  59: ☺	                   "\u263A" U+0263A   (9786) NN  WHITE SMILING FACE 
  60: ☻	                   "\u263B" U+0263B   (9787) NN  BLACK SMILING FACE 
  61: ア	                   "\u30A2" U+030A2  (12450) NN  KATAKANA LETTER A 
  62: 字	                   "\u5B57" U+05B57  (23383) NN  CJK UNIFIED IDEOGRAPHS 5B57 
  63: 文	                   "\u6587" U+06587  (25991) NN  CJK UNIFIED IDEOGRAPHS 6587 
  64: 	                   "\uF8FF" U+0F8FF  (63743) NN  PRIVATE USE AREA F8FF 
  65: 𠀀	             "\uD840\uDC00" U+20000 (131072) NN  HIGH SURROGATES D840 
  66: 𪚥	             "\uD869\uDEA5" U+2A6A5 (173733) NN  HIGH SURROGATES D869

More background info: "Java: a rough guide to character encoding"

Scheme

(display (char->integer #\a)) (newline) ; prints "97"
(display (integer->char 97)) (newline) ; prints "a"

Seed7

writeln(ord('a'));
writeln(chr(97));

SenseTalk

put CharToNum("a")
put NumToChar(97)

SequenceL

SequenceL natively supports ASCII characters.
SequenceL Interpreter Session:

cmd:>asciiToInt('a')
97
cmd:>intToAscii(97)
'a'

Sidef

say 'a'.ord;    # => 97
say 97.chr;     # => 'a'

Slate

$a code.
97 as: String Character.

Smalltalk

($a asInteger) displayNl. "output 97"
(Character value: 97) displayNl. "output a"

Works with: Smalltalk/X

Ansi Smalltalk defines codePoint

Transcript showCR:$a codePoint.
Transcript showCR:(Character codePoint:97).
Transcript showCR:(98 asCharacter).

'abcmøøse𝔘𝔫𝔦𝔠𝔬𝔡𝔢' do:[:ch | 
    Transcript showCR:ch codePoint
]

Output:

SmileBASIC

PRINT CHR$(97) 'a
PRINT ASC("a") '97

SNOBOL4

Snobol implementations may or may not have built-in char( ) and ord ( ) or asc( ). These are based on examples in the Snobol4+ tutorial and work with the native (1-byte) charset.

        define('chr(n)') :(chr_end)
chr     &alphabet tab(n) len(1) . chr :s(return)f(freturn)
chr_end

        define('asc(str)c') :(asc_end)
asc     str len(1) . c
        &alphabet break(c) @asc :s(return)f(freturn)
asc_end

*       # Test and display
        output = char(65) ;* Built-in
        output = chr(65)
        output = asc('A')
end

Output:

A
A
65

SparForte

As a structured script.

#!/usr/local/bin/spar
pragma annotate( summary, "charcode" )
       @( description, "Given a character value in your language, print its code (could be" )
       @( description, "ASCII code, Unicode code, or whatever your language uses). For example," )
       @( description, "the character 'a' (lowercase letter A) has a code of 97 in ASCII (as" )
       @( description, "well as Unicode, as ASCII forms the beginning of Unicode). Conversely," )
       @( description, "given a code, print out the corresponding character. " )
       @( category, "tutorials" )
       @( see_also, "http://rosettacode.org/wiki/Character_codes" )
       @( author, "Ken O. Burtch");
pragma license( unrestricted );

pragma restriction( no_external_commands );

procedure charcode is
  code : constant natural := 97;
  ch   : constant character := 'a';
begin
  put_line( "character code" & strings.image( code ) & " = character " & strings.val( code ) );
  put_line( "character " & ch & " = character code" & strings.image( numerics.pos( ch ) ) );
end charcode;

SPL

In SPL all characters are used in UTF-16LE encoding.

x = #.array("a")
#.output("a -> ",x[1]," ",x[2])
x = [98,0]
#.output("98 0 -> ",#.str(x))

Output:

a -> 97 0
98 0 -> b

Standard ML

print (Int.toString (ord #"a") ^ "\n"); (* prints "97" *)
print (Char.toString (chr 97) ^ "\n"); (* prints "a" *)

Stata

The Mata ascii function transforms a string into a numeric vector of UTF-8 bytes. For instance:

: ascii("α")
         1     2
    +-------------+
  1 |  206   177  |
    +-------------+

Where 206, 177 is the UTF-8 encoding of Unicode character 945 (GREEK SMALL LETTER ALPHA).

ASCII characters are mapped to single bytes:

: ascii("We the People")
         1     2     3     4     5     6     7     8     9    10    11    12    13
    +-------------------------------------------------------------------------------+
  1 |   87   101    32   116   104   101    32    80   101   111   112   108   101  |
    +-------------------------------------------------------------------------------+

Conversely, the char function transforms a byte vector into a string:

: char((73,32,115,116,97,110,100,32,104,101,114,101))
  I stand here

Swift

The type that represent a Unicode code point is UnicodeScalar. You can initialize it with a string literal:

let c1: UnicodeScalar = "a"
println(c1.value) // prints "97"
let c2: UnicodeScalar = "π"
println(c2.value) // prints "960"

Or, you can get it by iterating a string's unicode scalars view:

let s1 = "a"
for c in s1.unicodeScalars {
  println(c.value) // prints "97"
}
let s2 = "π"
for c in s2.unicodeScalars {
  println(c.value) // prints "960"
}

You can also initialize it from a UInt32 integer:

let i1: UInt32 = 97
println(UnicodeScalar(i1)) // prints "a"
let i2: UInt32 = 960
println(UnicodeScalar(i2)) // prints "π"

Tailspin

Tailspin works with Unicode codepoints

'abc' -> $::asCodePoints -> !OUT::write
'$#10;' -> !OUT::write
'$#97;' -> !OUT::write

Output:

[97, 98, 99]
a

Tcl

# ASCII
puts [scan "a" %c]   ;# ==> 97
puts [format %c 97]  ;# ==> a
# Unicode is the same
puts [scan "π" %c]   ;# ==> 960
puts [format %c 960] ;# ==> π

TI-83 BASIC

TI-83 BASIC provides no built in way to do this, so in all String<-->List routines and anything else which requires character codes, a workaround using inString( and sub( is used. In this example, the code of 'A' is displayed, and then the character matching a user-defined code is displayed.

"ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789→Str1
Disp inString(Str1,"A
Input "CODE? ",A
Disp sub(Str1,A,1

TI-89 BASIC

The TI-89 uses an 8-bit charset/encoding which is similar to ISO-8859-1, but with more mathematical symbols and Greek letters. At least codes 14-31, 128-160, 180 differ. The ASCII region is unmodified. (TODO: Give a complete list.)

The TI Connect X desktop software converts between this unique character set and Unicode characters, though sometimes in a consistent but inappropriate fashion.

The below program will display the character and code for any key pressed. Some keys do not correspond to characters and have codes greater than 255. The portion of the program actually implementing the task is marked with a line of “©”s.

Prgm
  Local k, s
  ClrIO
  Loop
    Disp "Press a key, or ON to exit."
    getKey() © clear buffer
    0 → k : While k = 0 : getKey() → k : EndWhile
    ClrIO
    If k ≥ 256 Then
      Disp "Not a character."
      Disp "Code: " & string(k)
    Else

      char(k) → s                           ©
      © char() and ord() are inverses.      ©
      Disp "Character: " & s                ©
      Disp "Code: " & string(ord(s))        ©

    EndIf
  EndLoop
EndPrgm

Trith

Characters are Unicode code points, so the solution is the same for Unicode characters as it is for ASCII characters:

"a" ord print
97 chr print

"π" ord print
960 chr print

TUSCRIPT

$$ MODE TUSCRIPT
SET character ="a", code=DECODE (character,byte)
PRINT character,"=",code

Output:

a=97

uBasic/4tH

uBasic/4tH is an integer BASIC, just like Tiny BASIC. However, the function ORD() is supported, just as CHR(). The latter is only allowed within a PRINT statement.

z = ORD("a") : PRINT CHR(z)    ' Prints "a"

UNIX Shell

Aamrun$ printf "%d\n" \'a
97
Aamrun$ printf "\x$(printf %x 97)\n"
a
Aamrun$

Ursa

# outputs the character value for 'a'
out (ord "a") endl console
# outputs the character 'a' given its value
out (chr 97) endl console

Ursala

Character code functions are not built in but easily defined as reifications of the character table.

#import std
#import nat

chr = -: num characters
asc = -:@rlXS num characters

#cast %cnX

test = (chr97,asc`a)

Output:

(`a,97)

Uxntal

( uxnasm char-codes.tal char-codes.rom && uxncli char-codes.rom )

|00 @System &vector $2 &expansion $2 &wst $1 &rst $1 &metadata $2 &r $2 &g $2 &b $2 &debug $1 &state $1
|10 @Console &vector $2 &read $1 &pad $4 &type $1 &write $1 &error $1

|0100
    [ LIT "a ] print-hex
    newline
    #61 .Console/write DEO
    newline

    ( exit )
    #80 .System/state DEO
BRK

@print-hex
    DUP #04 SFT print-digit #0f AND print-digit
JMP2r

@print-digit
    DUP #09 GTH #27 MUL ADD #30 ADD .Console/write DEO
JMP2r

@newline
    #0a .Console/write DEO
JMP2r

Output:

61
a

VBA

Debug.Print Chr(97) 'Prints a
Debug.Print [Code("a")] ' Prints 97

VBScript

'prints a
WScript.StdOut.WriteLine Chr(97)

'prints 97
WScript.StdOut.WriteLine Asc("a")

Vim Script

The behavior of the two functions depends on the value of the option encoding.

"encoding is set to utf-8
echo char2nr("a")
"Prints 97

echo nr2char(97)
"Prints a

Visual Basic .NET

Console.WriteLine(Chr(97)) 'Prints a
Console.WriteLine(Asc("a")) 'Prints 97

V (Vlang)

fn main() {
    println('a'[0]) // prints "97"
	println('π'[0]) // prints "207"

	s := 'aπ'
	println('string cast to bytes: ${s.bytes()}')
	for c in s {
		print('0x${c:x} ')
	}
}

Output:

97
207
string cast to bytes: [a, 0xcf, 0x80]
97->0x61 207->0xcf 128->0x80

Wren

Wren does not have a character type as such but one can use single character strings instead. Strings can contain any Unicode code point.

var cps = []
for (c in ["a", "π", "字", "🐘"]) {
    var cp = c.codePoints[0]
    cps.add(cp)
    System.print("%(c) = %(cp)")
}
System.print()
for (i in cps) {
    var c = String.fromCodePoint(i)
    System.print("%(i) = %(c)")
}

Output:

a = 97
π = 960
字 = 23383
🐘 = 128024

97 = a
960 = π
23383 = 字
128024 = 🐘

XLISP

In a REPL:

[1] (INTEGER->CHAR 97)

#\a
[2] (CHAR->INTEGER #\a)

97

XPL0

A character is represented by an integer value equal to its ASCII code. The up-arrow character is used to convert the immediately following character to an integer equal to its ASCII code.

IntOut(0, ^a);  \(Integer Out)  displays "97" on the console (device 0)
ChOut(0, 97);   \(Character Out) displays "a" on the console (device 0)

Z80 Assembly

The Z80 doesn't understand what ASCII codes are by itself. Most computers/systems that use it will have firmware that maps each code to its corresponding glyph. Printing a character given its code is trivial. On the Amstrad CPC:

LD A,'a'
call &BB5a

Printing a character code given a character takes slightly more work. You'll need to separate each hexadecimal digit of the ASCII code, convert each digit to ASCII, and print it. Once again, thanks to Keith of [Chibiakumas] for this code:

ShowHex:	
	push af
		and %11110000
			rrca
			rrca
			rrca
			rrca
		call PrintHexChar
	pop af
	and %00001111
	;call PrintHexChar  (execution flows into it naturally)
PrintHexChar:
	or a	   ;Clear Carry Flag
	daa
	add a,&F0
	adc a,&40     ;this sequence of instructions converts a single hex digit to ASCII. 

	jp PrintChar  ;this is whatever routine prints to the screen on your system. 
                      ;  It must end in a "ret" and it must take the accumulator as its argument.

Zig

const std = @import("std");
const unicode = std.unicode;

pub fn main() !void {
    const stdout = std.io.getStdOut().writer();

    try characterAsciiCodes(stdout);
    try characterUnicodeCodes(stdout);
}

fn characterAsciiCodes(writer: anytype) !void {
    try writer.writeAll("Sample ASCII characters and codes:\n");

    // Zig's string is just an array of bytes (u8).
    const message: []const u8 = "ABCabc";

    for (message) |val| {
        try writer.print("  '{c}' code: {d} [hexa: 0x{x}]\n", .{ val, val, val });
    }
    try writer.writeByte('\n');
}

fn characterUnicodeCodes(writer: anytype) !void {
    try writer.writeAll("Sample Unicode characters and codes:\n");

    const message: []const u8 = "あいうえお";

    const utf8_view = unicode.Utf8View.initUnchecked(message);
    var iter = utf8_view.iterator();

    while (iter.nextCodepoint()) |val| {
        var array: [4]u8 = undefined;
        const slice = array[0..try unicode.utf8Encode(val, &array)];

        try writer.print("  '{s}' code: {d} [hexa: U+{x}]\n", .{ slice, val, val });
    }
    try writer.writeByte('\n');
}

Output:

Sample ASCII characters and codes:
  'A' code: 65 [hexa: 0x41]
  'B' code: 66 [hexa: 0x42]
  'C' code: 67 [hexa: 0x43]
  'a' code: 97 [hexa: 0x61]
  'b' code: 98 [hexa: 0x62]
  'c' code: 99 [hexa: 0x63]

Sample Unicode characters and codes:
  'あ' code: 12354 [hexa: U+3042]
  'い' code: 12356 [hexa: U+3044]
  'う' code: 12358 [hexa: U+3046]
  'え' code: 12360 [hexa: U+3048]
  'お' code: 12362 [hexa: U+304a]

zkl

The character set is 8 bit ASCII (but doesn't care if you use UTF-8 or unicode characters).

 "a".toAsc()  //-->97
(97).toChar() //-->"a"

Zoea

program: character_codes
  input: a
  output: 97

Zoea Visual

Character Codes

ZX Spectrum Basic

10 PRINT CHR$ 97: REM prints a
20 PRINT CODE "a": REM prints 97