Tokenize a string: Difference between revisions
No edit summary |
m (→{{header|Wren}}: Changed to Wren S/H) |
||
(297 intermediate revisions by more than 100 users not shown) | |||
Line 1: | Line 1: | ||
{{task|String manipulation}} |
{{task|String manipulation}} |
||
[[Category:Simple]] |
|||
Separate the string "Hello,How,Are,You,Today" by commas into an array (or list) so that each element of it stores a different word. Display the words to the 'user', in the simplest manner possible, separated by a period. To simplify, you may display a trailing period. |
|||
Separate the string "Hello,How,Are,You,Today" by commas into an array (or list) so that each element of it stores a different word. |
|||
Display the words to the 'user', in the simplest manner possible, separated by a period. |
|||
To simplify, you may display a trailing period. |
|||
{{Template:Strings}} |
|||
<br><br> |
|||
=={{header|11l}}== |
|||
{{trans|Python}} |
|||
<syntaxhighlight lang="11l">V text = ‘Hello,How,Are,You,Today’ |
|||
V tokens = text.split(‘,’) |
|||
print(tokens.join(‘.’))</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|360 Assembly}}== |
|||
<syntaxhighlight lang="360asm">* Tokenize a string - 08/06/2018 |
|||
TOKSTR CSECT |
|||
USING TOKSTR,R13 base register |
|||
B 72(R15) skip savearea |
|||
DC 17F'0' savearea |
|||
SAVE (14,12) save previous context |
|||
ST R13,4(R15) link backward |
|||
ST R15,8(R13) link forward |
|||
LR R13,R15 set addressability |
|||
MVC N,=A(1) n=1 |
|||
LA R7,1 i1=1 |
|||
LA R6,1 i=1 |
|||
DO WHILE=(C,R6,LE,LENS) do i=1 to length(s); |
|||
LA R4,S-1 @s-1 |
|||
AR R4,R6 +i |
|||
MVC C,0(R4) c=substr(s,i,1) |
|||
IF CLI,C,EQ,C',' THEN if c=',' then do |
|||
BAL R14,TOK call tok |
|||
LR R2,R8 i2 |
|||
SR R2,R7 i2-i1 |
|||
LA R2,1(R2) i2-i1+1 |
|||
L R1,N n |
|||
SLA R1,1 *2 |
|||
STH R2,TALEN-2(R1) talen(n)=i2-i1+1 |
|||
L R2,N n |
|||
LA R2,1(R2) n+1 |
|||
ST R2,N n=n+1 |
|||
LA R7,1(R6) i1=i+1 |
|||
ENDIF , endif |
|||
LA R6,1(R6) i++ |
|||
ENDDO , enddo i |
|||
BAL R14,TOK call tok |
|||
LR R2,R8 i2 |
|||
SR R2,R7 i2-i1 |
|||
LA R2,1(R2) i2-i1+1 |
|||
L R1,N n |
|||
SLA R1,1 *2 |
|||
STH R2,TALEN-2(R1) talen(n)=i2-i1+1 |
|||
LA R11,PG pgi=@pg |
|||
LA R6,1 i=1 |
|||
DO WHILE=(C,R6,LE,N) do i=1 to n |
|||
LR R1,R6 i |
|||
SLA R1,1 *2 |
|||
LH R10,TALEN-2(R1) l=talen(i) |
|||
LR R1,R6 i |
|||
SLA R1,3 *8 |
|||
LA R4,TABLE-8(R1) @table(i) |
|||
LR R2,R10 l |
|||
BCTR R2,0 ~ |
|||
EX R2,MVCX output table(i) length(l) |
|||
AR R11,R10 pgi=pgi+l |
|||
IF C,R6,NE,N THEN if i^=n then |
|||
MVC 0(1,R11),=C'.' output '.' |
|||
LA R11,1(R11) pgi=pgi+1 |
|||
ENDIF , endif |
|||
LA R6,1(R6) i++ |
|||
ENDDO , enddo i |
|||
XPRNT PG,L'PG print |
|||
L R13,4(0,R13) restore previous savearea pointer |
|||
RETURN (14,12),RC=0 restore registers from calling sav |
|||
TOK LR R5,R6 i <-- |
|||
BCTR R5,0 i-1 | |
|||
LR R8,R5 i2=i-1 |
|||
SR R5,R7 i2-i1 |
|||
LA R5,1(R5) l=i2-i1+1 source length |
|||
L R1,N n |
|||
SLA R1,3 *8 |
|||
LA R2,TABLE-8(R1) @table(n) |
|||
LA R4,S-1 @s-1 |
|||
AR R4,R7 @s+i1-1 |
|||
LA R3,8 target length |
|||
MVCL R2,R4 table(n)=substr(s,i1,i2-i1+1) | |
|||
BR R14 End TOK subroutine <-- |
|||
MVCX MVC 0(0,R11),0(R4) output table(i) |
|||
S DC CL80'Hello,How,Are,You,Today' <== input string == |
|||
LENS DC F'23' length(s) <== |
|||
TABLE DC 8CL8' ' table(8) |
|||
TALEN DC 8H'0' talen(8) |
|||
C DS CL1 char |
|||
N DS F number of tokens |
|||
PG DC CL80' ' buffer |
|||
YREGS |
|||
END TOKSTR</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|8080 Assembly}}== |
|||
<syntaxhighlight lang="8080asm">puts: equ 9 |
|||
org 100h |
|||
jmp demo |
|||
;;; Split the string at DE by the character in C. |
|||
;;; Store pointers to the beginning of the elements starting at HL |
|||
;;; The amount of elements is returned in B. |
|||
split: mvi b,0 ; Amount of elements |
|||
sloop: mov m,e ; Store pointer at [HL] |
|||
inx h |
|||
mov m,d |
|||
inx h |
|||
inr b ; Increment counter |
|||
sscan: ldax d ; Get current character |
|||
inx d |
|||
cpi '$' ; Done? |
|||
rz ; Then stop |
|||
cmp c ; Place to split? |
|||
jnz sscan ; If not, keep going |
|||
dcx d |
|||
mvi a,'$' ; End the string here |
|||
stax d |
|||
inx d |
|||
jmp sloop ; Next part |
|||
;;; Test on the string given in the task |
|||
demo: lxi h,parts ; Parts array |
|||
lxi d,hello ; String |
|||
mvi c,',' |
|||
call split ; Split the string |
|||
lxi h,parts ; Print each part |
|||
loop: mov e,m ; Load pointer into DE |
|||
inx h |
|||
mov d,m |
|||
inx h |
|||
push h ; Keep the array pointer |
|||
push b ; And the counter |
|||
mvi c,puts ; Print the string |
|||
call 5 |
|||
lxi d,period ; And a period |
|||
mvi c,puts |
|||
call 5 |
|||
pop b ; Restore the counter |
|||
pop h ; Restore the array pointer |
|||
dcr b ; One fewer string left |
|||
jnz loop |
|||
ret |
|||
period: db '. $' |
|||
hello: db 'Hello,How,Are,You,Today$' |
|||
parts: equ $</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello. How. Are. You. Today.</pre> |
|||
=={{header|8086 Assembly}}== |
|||
<syntaxhighlight lang="asm"> cpu 8086 |
|||
org 100h |
|||
section .text |
|||
jmp demo |
|||
;;; Split the string at DS:SI on the character in DL. |
|||
;;; Store pointers to strings starting at ES:DI. |
|||
;;; The amount of strings is returned in CX. |
|||
split: xor cx,cx ; Zero out counter |
|||
.loop: mov ax,si ; Store pointer to current location |
|||
stosw |
|||
inc cx ; Increment counter |
|||
.scan: lodsb ; Get byte |
|||
cmp al,'$' ; End of string? |
|||
je .done |
|||
cmp al,dl ; Character to split on? |
|||
jne .scan |
|||
mov [si-1],byte '$' ; Terminate string |
|||
jmp .loop |
|||
.done: ret |
|||
;;; Test on the string given in the task |
|||
demo: mov si,hello ; String to split |
|||
mov di,parts ; Place to store pointers |
|||
mov dl,',' ; Character to split string on |
|||
call split |
|||
;;; Print the resulting strings, and periods |
|||
mov si,parts ; Array of string pointers |
|||
print: lodsw ; Load next pointer |
|||
mov dx,ax ; Print string using DOS |
|||
mov ah,9 |
|||
int 21h |
|||
mov dx,period ; Then print a period |
|||
int 21h |
|||
loop print ; Loop while there are strings |
|||
ret |
|||
section .data |
|||
period: db '. $' |
|||
hello: db 'Hello,How,Are,You,Today$' |
|||
section .bss |
|||
parts: resw 10</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello. How. Are. You. Today. </pre> |
|||
=={{header|AArch64 Assembly}}== |
|||
{{works with|as|Raspberry Pi 3B version Buster 64 bits}} |
|||
<syntaxhighlight lang="aarch64 assembly"> |
|||
/* ARM assembly AARCH64 Raspberry PI 3B */ |
|||
/* program strTokenize64.s */ |
|||
/*******************************************/ |
|||
/* Constantes file */ |
|||
/*******************************************/ |
|||
/* for this file see task include a file in language AArch64 assembly*/ |
|||
.include "../includeConstantesARM64.inc" |
|||
.equ NBPOSTESECLAT, 20 |
|||
/*******************************************/ |
|||
/* Initialized data */ |
|||
/*******************************************/ |
|||
.data |
|||
szMessFinal: .asciz "Words are : \n" |
|||
szString: .asciz "Hello,How,Are,You,Today" |
|||
szMessError: .asciz "Error tokenize !!\n" |
|||
szCarriageReturn: .asciz "\n" |
|||
/*******************************************/ |
|||
/* UnInitialized data */ |
|||
/*******************************************/ |
|||
.bss |
|||
/*******************************************/ |
|||
/* code section */ |
|||
/*******************************************/ |
|||
.text |
|||
.global main |
|||
main: |
|||
ldr x0,qAdrszString // string address |
|||
mov x1,',' // separator |
|||
bl stTokenize |
|||
cmp x0,-1 // error ? |
|||
beq 99f |
|||
mov x2,x0 // table address |
|||
ldr x0,qAdrszMessFinal // display message |
|||
bl affichageMess |
|||
ldr x4,[x2] // number of areas |
|||
add x2,x2,8 // first area |
|||
mov x3,0 // loop counter |
|||
mov x0,x2 |
|||
1: // display loop |
|||
ldr x0,[x2,x3, lsl 3] // address area |
|||
bl affichageMess |
|||
ldr x0,qAdrszCarriageReturn // display carriage return |
|||
bl affichageMess |
|||
add x3,x3,1 // counter + 1 |
|||
cmp x3,x4 // end ? |
|||
blt 1b // no -> loop |
|||
b 100f |
|||
99: // display error message |
|||
ldr x0,qAdrszMessError |
|||
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 |
|||
qAdrszString: .quad szString |
|||
//qAdrszFinalString: .quad szFinalString |
|||
qAdrszMessFinal: .quad szMessFinal |
|||
qAdrszMessError: .quad szMessError |
|||
qAdrszCarriageReturn: .quad szCarriageReturn |
|||
/*******************************************************************/ |
|||
/* Separate string by separator into an array */ |
|||
/* areas are store on the heap Linux */ |
|||
/*******************************************************************/ |
|||
/* x0 contains string address */ |
|||
/* x1 contains separator character (, or . or : ) */ |
|||
/* x0 returns table address with first item = number areas */ |
|||
/* and other items contains pointer of each string */ |
|||
stTokenize: |
|||
stp x1,lr,[sp,-16]! // save registers |
|||
mov x16,x0 |
|||
mov x9,x1 // save separator |
|||
mov x14,0 |
|||
1: // compute length string for place reservation on the heap |
|||
ldrb w12,[x0,x14] |
|||
cbz x12, 2f |
|||
add x14,x14,1 |
|||
b 1b |
|||
2: |
|||
ldr x12,qTailleTable |
|||
add x15,x12,x14 |
|||
and x15,x15,0xFFFFFFFFFFFFFFF0 |
|||
add x15,x15,16 // align word on the heap |
|||
// place reservation on the heap |
|||
mov x0,0 // heap address |
|||
mov x8,BRK // call system linux 'brk' |
|||
svc 0 // call system |
|||
cmp x0,-1 // error call system |
|||
beq 100f |
|||
mov x14,x0 // save address heap begin = begin array |
|||
add x0,x0,x15 // reserve x15 byte on the heap |
|||
mov x8,BRK // call system linux 'brk' |
|||
svc 0 |
|||
cmp x0,-1 |
|||
beq 100f |
|||
// string copy on the heap |
|||
add x13,x14,x12 // behind the array |
|||
mov x0,x16 |
|||
mov x1,x13 |
|||
3: // loop copy string |
|||
ldrb w12,[x0],1 // read one byte and increment pointer one byte |
|||
strb w12,[x1],1 // store one byte and increment pointer one byte |
|||
cbnz x12,3b // end of string ? no -> loop |
|||
mov x0,#0 |
|||
str x0,[x14] |
|||
str x13,[x14,8] |
|||
mov x12,#1 // areas counter |
|||
4: // loop load string character |
|||
ldrb w0,[x13] |
|||
cbz x0,5f // end string |
|||
cmp x0,x9 // separator ? |
|||
cinc x13,x13,ne // no -> next location |
|||
bne 4b // and loop |
|||
strb wzr,[x13] // store zero final of string |
|||
add x13,x13,1 // next character |
|||
add x12,x12,1 // areas counter + 1 |
|||
str x13,[x14,x12, lsl #3] // store address area in the table at index x2 |
|||
b 4b // and loop |
|||
5: |
|||
str x12,[x14] // store number areas |
|||
mov x0,x14 // returns array address |
|||
100: |
|||
ldp x1,lr,[sp],16 // restaur 2 registers |
|||
ret // return to address lr x30 |
|||
qTailleTable: .quad 8 * NBPOSTESECLAT |
|||
/********************************************************/ |
|||
/* File Include fonctions */ |
|||
/********************************************************/ |
|||
/* for this file see task include a file in language AArch64 assembly */ |
|||
.include "../includeARM64.inc" |
|||
</syntaxhighlight> |
|||
{{Output}} |
|||
<pre> |
|||
Words are : |
|||
Hello |
|||
How |
|||
Are |
|||
You |
|||
Today |
|||
</pre> |
|||
=={{header|ACL2}}== |
|||
<syntaxhighlight lang="lisp">(defun split-at (xs delim) |
|||
(if (or (endp xs) (eql (first xs) delim)) |
|||
(mv nil (rest xs)) |
|||
(mv-let (before after) |
|||
(split-at (rest xs) delim) |
|||
(mv (cons (first xs) before) after)))) |
|||
(defun split (xs delim) |
|||
(if (endp xs) |
|||
nil |
|||
(mv-let (before after) |
|||
(split-at xs delim) |
|||
(cons before (split after delim))))) |
|||
(defun css->strs (css) |
|||
(if (endp css) |
|||
nil |
|||
(cons (coerce (first css) 'string) |
|||
(css->strs (rest css))))) |
|||
(defun split-str (str delim) |
|||
(css->strs (split (coerce str 'list) delim))) |
|||
(defun print-with (strs delim) |
|||
(if (endp strs) |
|||
(cw "~%") |
|||
(progn$ (cw (first strs)) |
|||
(cw (coerce (list delim) 'string)) |
|||
(print-with (rest strs) delim))))</syntaxhighlight> |
|||
{{out}} |
|||
<pre>> (print-with (split-str "Hello,How,Are,You,Today" #\,) #\.) |
|||
Hello.How.Are.You.Today.</pre> |
|||
=={{header|Action!}}== |
|||
The user must type in the monitor the following command after compilation and before running the program!<pre>SET EndProg=*</pre> |
|||
{{libheader|Action! Tool Kit}} |
|||
<syntaxhighlight lang="action!">CARD EndProg ;required for ALLOCATE.ACT |
|||
INCLUDE "D2:ALLOCATE.ACT" ;from the Action! Tool Kit. You must type 'SET EndProg=*' from the monitor after compiling, but before running this program! |
|||
DEFINE PTR="CARD" |
|||
BYTE FUNC Split(CHAR ARRAY s CHAR c PTR ARRAY items) |
|||
BYTE i,count,start,len |
|||
CHAR ARRAY item |
|||
IF s(0)=0 THEN RETURN (0) FI |
|||
i=1 count=0 |
|||
WHILE i<s(0) |
|||
DO |
|||
start=i |
|||
WHILE i<=s(0) AND s(i)#c |
|||
DO |
|||
i==+1 |
|||
OD |
|||
len=i-start |
|||
item=Alloc(len+1) |
|||
SCopyS(item,s,start,i-1) |
|||
items(count)=item |
|||
count==+1 |
|||
i==+1 |
|||
OD |
|||
RETURN (count) |
|||
PROC Join(PTR ARRAY items BYTE count CHAR c CHAR ARRAY s) |
|||
BYTE i,pos |
|||
CHAR POINTER srcPtr,dstPtr |
|||
CHAR ARRAY item |
|||
s(0)=0 |
|||
IF count=0 THEN RETURN FI |
|||
pos=1 |
|||
FOR i=0 TO count-1 |
|||
DO |
|||
item=items(i) |
|||
srcPtr=item+1 |
|||
dstPtr=s+pos |
|||
MoveBlock(dstPtr,srcPtr,item(0)) |
|||
pos==+item(0) |
|||
IF i<count-1 THEN |
|||
s(pos)='. |
|||
pos==+1 |
|||
FI |
|||
OD |
|||
s(0)=pos-1 |
|||
RETURN |
|||
PROC Clear(PTR ARRAY items BYTE POINTER count) |
|||
BYTE i |
|||
CHAR ARRAY item |
|||
IF count^=0 THEN RETURN FI |
|||
FOR i=0 TO count^-1 |
|||
DO |
|||
item=items(i) |
|||
Free(item,item(0)+1) |
|||
OD |
|||
count^=0 |
|||
RETURN |
|||
PROC Main() |
|||
CHAR ARRAY s="Hello,How,Are,You,Today" |
|||
CHAR ARRAY r(256) |
|||
PTR ARRAY items(100) |
|||
BYTE i,count |
|||
Put(125) PutE() ;clear screen |
|||
AllocInit(0) |
|||
count=Split(s,',,items) |
|||
Join(items,count,'.,r) |
|||
PrintF("Input:%E""%S""%E%E",s) |
|||
PrintE("Split:") |
|||
FOR i=0 TO count-1 |
|||
DO |
|||
PrintF("""%S""",items(i)) |
|||
IF i<count-1 THEN |
|||
Print(", ") |
|||
ELSE |
|||
PutE() PutE() |
|||
FI |
|||
OD |
|||
PrintF("Join:%E""%S""%E",r) |
|||
Clear(items,@count) |
|||
RETURN</syntaxhighlight> |
|||
{{out}} |
|||
[https://gitlab.com/amarok8bit/action-rosetta-code/-/raw/master/images/Tokenize_a_string.png Screenshot from Atari 8-bit computer] |
|||
<pre> |
|||
Input: |
|||
"Hello,How,Are,You,Today" |
|||
Split: |
|||
"Hello", "How", "Are", "You", "Today" |
|||
Join: |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
=={{header|ActionScript}}== |
=={{header|ActionScript}}== |
||
< |
<syntaxhighlight lang="actionscript">var hello:String = "Hello,How,Are,You,Today"; |
||
var tokens:Array = hello.split(","); |
var tokens:Array = hello.split(","); |
||
trace(tokens.join(".")); |
trace(tokens.join(".")); |
||
// Or as a one-liner |
// Or as a one-liner |
||
trace("Hello,How,Are,You,Today".split(",").join("."));</ |
trace("Hello,How,Are,You,Today".split(",").join("."));</syntaxhighlight> |
||
=={{header|Ada}}== |
=={{header|Ada}}== |
||
< |
<syntaxhighlight lang="ada">with Ada.Text_IO, Ada.Containers.Indefinite_Vectors, Ada.Strings.Fixed, Ada.Strings.Maps; |
||
use Ada.Text_IO, Ada.Containers, Ada.Strings, Ada.Strings.Fixed, Ada.Strings.Maps; |
|||
with Ada.Text_Io; use Ada.Text_Io; |
|||
procedure |
procedure Tokenize is |
||
package String_Vectors is new Indefinite_Vectors (Positive, String); |
|||
Source_String : String := "Hello,How,Are,You,Today"; |
|||
use String_Vectors; |
|||
Index_List : array(1..256) of Natural; |
|||
Input : String := "Hello,How,Are,You,Today"; |
|||
Start : Positive := Input'First; |
|||
Finish : Natural := 0; |
|||
Output : Vector := Empty_Vector; |
|||
begin |
begin |
||
while Start <= Input'Last loop |
|||
Index_List(Next_Index) := 1; |
|||
Find_Token (Input, To_Set (','), Start, Outside, Start, Finish); |
|||
while Index_List(Next_Index) < Source_String'Last loop |
|||
exit when Start > Finish; |
|||
Output.Append (Input (Start .. Finish)); |
|||
Index_List(Next_Index) := 1 + Index(Source_String(Index_List(Next_Index - 1)..Source_String'Last), ","); |
|||
Start := Finish + 1; |
|||
Index_List(Next_Index) := Source_String'Last + 2; |
|||
end if; |
|||
Put(Source_String(Index_List(Next_Index - 1)..Index_List(Next_Index)-2) & "."); |
|||
end loop; |
end loop; |
||
for S of Output loop |
|||
end Parse_Commas;</lang> |
|||
Put (S & "."); |
|||
end loop; |
|||
end Tokenize;</syntaxhighlight> |
|||
=={{header|ALGOL 68}}== |
=={{header|ALGOL 68}}== |
||
< |
<syntaxhighlight lang="algol68">main:( |
||
OP +:= = (REF FLEX[]STRING in out, STRING item)VOID:( |
OP +:= = (REF FLEX[]STRING in out, STRING item)VOID:( |
||
Line 52: | Line 559: | ||
out |
out |
||
); |
); |
||
PROC char split = (REF STRING beetles, STRING chars)[]STRING: ( |
PROC char split = (REF STRING beetles, STRING chars)[]STRING: ( |
||
""" Split beetles where character is found in chars """; |
""" Split beetles where character is found in chars """; |
||
Line 78: | Line 585: | ||
printf(($g"."$, string split(beetles, ", "),$l$)); |
printf(($g"."$, string split(beetles, ", "),$l$)); |
||
printf(($g"."$, char split(beetles, ", "),$l$)) |
printf(($g"."$, char split(beetles, ", "),$l$)) |
||
)</ |
)</syntaxhighlight> |
||
{{out}} |
|||
Output:<pre> |
|||
<pre> |
|||
John Lennon.Paul McCartney.George Harrison.Ringo Starr. |
|||
John |
John Lennon.Paul McCartney.George Harrison.Ringo Starr. |
||
John.Lennon..Paul.McCartney..George.Harrison..Ringo.Starr. |
|||
</pre> |
</pre> |
||
=={{header|Amazing Hopper}}== |
|||
Hopper provides instructions for separating and modifying tokens from a string. |
|||
Let "s" be a string; "n" token number: |
|||
1) {n}, $(s) ==> gets token "n" from string "s". |
|||
2) {"word", n} $$(s) ==> replace token "n" of "s", with "word". |
|||
Note: the "splitnumber" macro cannot separate a number converted to a string by the "XTOSTR" function, because this function "rounds" the number to the decimal position by default. |
|||
<syntaxhighlight lang="hopper"> |
|||
#include <hopper.h> |
|||
#proto splitdate(_DATETIME_) |
|||
#proto splitnumber(_N_) |
|||
#proto split(_S_,_T_) |
|||
main: |
|||
s="this string will be separated into parts with space token separator" |
|||
aS=0,let( aS :=_split(s," ")) |
|||
{","}toksep // set a new token separator |
|||
{"String: ",s} |
|||
{"\nArray:\n",aS}, |
|||
{"\nSize="}size(aS),println // "size" return an array: {dims,#rows,#cols,#pages} |
|||
{"\nOriginal number: ",-125.489922},println |
|||
w=0,let(w:=_split number(-125.489922) ) |
|||
{"Integer part: "}[1]get(w) // get first element from array "w" |
|||
{"\nDecimal part: "}[2]get(w),println // get second element from array "w" |
|||
{"\nDate by DATENOW(TODAY) macro: "},print |
|||
dt=0, let( dt :=_splitdate(datenow(TODAY);!puts)) // "!" keep first element from stack |
|||
{"\nDate: "}[1]get(dt) |
|||
{"\nTime: "}[2]get(dt),println |
|||
exit(0) |
|||
.locals |
|||
splitdate(_DATETIME_) |
|||
_SEP_=0,gettoksep,mov(_SEP_) // "gettoksep" return actual token separator |
|||
{","}toksep, // set a new token separator |
|||
_NEWARRAY_={} |
|||
{1},$( _DATETIME_ ), |
|||
{2},$( _DATETIME_ ),pushall(_NEWARRAY_) |
|||
{_SEP_}toksep // restore ols token separator |
|||
{_NEWARRAY_} |
|||
back |
|||
splitnumber(_X_) |
|||
part_int=0,part_dec=0, |
|||
{_X_},!trunc,mov(part_int), |
|||
minus(part_int), !sign,mul |
|||
xtostr,mov(part_dec), part_dec+=2, // "part_dec+=2", delete "0." from "part_dec" |
|||
{part_dec}xtonum,mov(part_dec) |
|||
_NEWARRAY_={},{part_int,part_dec},pushall(_NEWARRAY_) |
|||
{_NEWARRAY_} |
|||
back |
|||
split(_S_,_T_) |
|||
_NEWARRAY_={},_VAR1_=0,_SEP_=0,gettoksep,mov(_SEP_) |
|||
{_T_}toksep,totaltoken(_S_), |
|||
mov(_VAR1_), // for total tokens |
|||
_VAR2_=1, // for real position of tokens into the string |
|||
___SPLIT_ITER: |
|||
{_VAR2_}$( _S_ ),push(_NEWARRAY_) |
|||
++_VAR2_,--_VAR1_ |
|||
{ _VAR1_ },jnz(___SPLIT_ITER) // jump to "___SPLIT_ITER" if "_VAR1_" is not zero. |
|||
clear(_VAR2_),clear(_VAR1_) |
|||
{_SEP_}toksep |
|||
{_NEWARRAY_} |
|||
back |
|||
</syntaxhighlight> |
|||
{{Out}} |
|||
<pre>Output: |
|||
String: this string will be separated into parts with space token separator |
|||
Array: |
|||
this,string,will,be,separated,into,parts,with,space,token,separator |
|||
Size=1,11 |
|||
Original number: -125.49 |
|||
Integer part: -125 |
|||
Decimal part: 489922 |
|||
Date by DATENOW(TODAY) macro: 22/11/2021,18:41:20:13 |
|||
Date: 22/11/2021 |
|||
Time: 18:41:20:13 |
|||
</pre> |
|||
=={{header|APL}}== |
|||
<syntaxhighlight lang="apl"> '.',⍨¨ ','(≠⊆⊢)'abc,123,X' ⍝ [1] Do the split: ','(≠⊆⊢)'abc,123,X'; [2] append the periods: '.',⍨¨ |
|||
abc. 123. X. ⍝ 3 strings (char vectors), each with a period at the end. |
|||
</syntaxhighlight> |
|||
=={{header|AppleScript}}== |
|||
<syntaxhighlight lang="applescript">on run |
|||
intercalate(".", splitOn(",", "Hello,How,Are,You,Today")) |
|||
end run |
|||
-- splitOn :: String -> String -> [String] |
|||
on splitOn(strDelim, strMain) |
|||
set {dlm, my text item delimiters} to {my text item delimiters, strDelim} |
|||
set lstParts to text items of strMain |
|||
set my text item delimiters to dlm |
|||
return lstParts |
|||
end splitOn |
|||
-- intercalate :: String -> [String] -> String |
|||
on intercalate(strText, lstText) |
|||
set {dlm, my text item delimiters} to {my text item delimiters, strText} |
|||
set strJoined to lstText as text |
|||
set my text item delimiters to dlm |
|||
return strJoined |
|||
end intercalate</syntaxhighlight> |
|||
{{Out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
Or, |
|||
<syntaxhighlight lang="applescript">set my text item delimiters to "," |
|||
set tokens to the text items of "Hello,How,Are,You,Today" |
|||
set my text item delimiters to "." |
|||
log tokens as text</syntaxhighlight> |
|||
{{Out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|ARM Assembly}}== |
|||
{{works with|as|Raspberry Pi}} |
|||
<syntaxhighlight lang="arm assembly"> |
|||
/* ARM assembly Raspberry PI */ |
|||
/* program strTokenize.s */ |
|||
/* Constantes */ |
|||
.equ STDOUT, 1 @ Linux output console |
|||
.equ EXIT, 1 @ Linux syscall |
|||
.equ WRITE, 4 @ Linux syscall |
|||
.equ NBPOSTESECLAT, 20 |
|||
/* Initialized data */ |
|||
.data |
|||
szMessFinal: .asciz "Words are : \n" |
|||
szString: .asciz "Hello,How,Are,You,Today" |
|||
szMessError: .asciz "Error tokenize !!\n" |
|||
szCarriageReturn: .asciz "\n" |
|||
/* UnInitialized data */ |
|||
.bss |
|||
/* code section */ |
|||
.text |
|||
.global main |
|||
main: |
|||
ldr r0,iAdrszString @ string address |
|||
mov r1,#',' @ separator |
|||
bl stTokenize |
|||
cmp r0,#-1 @ error ? |
|||
beq 99f |
|||
mov r2,r0 @ table address |
|||
ldr r0,iAdrszMessFinal @ display message |
|||
bl affichageMess |
|||
ldr r4,[r2] @ number of areas |
|||
add r2,#4 @ first area |
|||
mov r3,#0 @ loop counter |
|||
1: @ display loop |
|||
ldr r0,[r2,r3, lsl #2] @ address area |
|||
bl affichageMess |
|||
ldr r0,iAdrszCarriageReturn @ display carriage return |
|||
bl affichageMess |
|||
add r3,#1 @ counter + 1 |
|||
cmp r3,r4 @ end ? |
|||
blt 1b @ no -> loop |
|||
b 100f |
|||
99: @ display error message |
|||
ldr r0,iAdrszMessError |
|||
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 |
|||
iAdrszString: .int szString |
|||
iAdrszFinalString: .int szFinalString |
|||
iAdrszMessFinal: .int szMessFinal |
|||
iAdrszMessError: .int szMessError |
|||
iAdrszCarriageReturn: .int szCarriageReturn |
|||
/******************************************************************/ |
|||
/* display text with size calculation */ |
|||
/******************************************************************/ |
|||
/* r0 contains the address of the message */ |
|||
affichageMess: |
|||
push {r0,r1,r2,r7,lr} @ save 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" |
|||
svc #0 @ call systeme |
|||
pop {r0,r1,r2,r7,lr} @ restaur des 2 registres |
|||
bx lr @ return |
|||
/*******************************************************************/ |
|||
/* Separate string by separator into an array */ |
|||
/* areas are store on the heap Linux */ |
|||
/*******************************************************************/ |
|||
/* r0 contains string address */ |
|||
/* r1 contains separator character (, or . or : ) */ |
|||
/* r0 returns table address with first item = number areas */ |
|||
/* and other items contains pointer of each string */ |
|||
stTokenize: |
|||
push {r1-r8,lr} @ save des registres |
|||
mov r6,r0 |
|||
mov r8,r1 @ save separator |
|||
bl strLength @ length string for place reservation on the heap |
|||
mov r4,r0 |
|||
ldr r5,iTailleTable |
|||
add r5,r0 |
|||
and r5,#0xFFFFFFFC |
|||
add r5,#4 @ align word on the heap |
|||
@ place reservation on the heap |
|||
mov r0,#0 @ heap address |
|||
mov r7, #0x2D @ call system linux 'brk' |
|||
svc #0 @ call system |
|||
cmp r0,#-1 @ error call system |
|||
beq 100f |
|||
mov r3,r0 @ save address heap begin |
|||
add r0,r5 @ reserve r5 byte on the heap |
|||
mov r7, #0x2D @ call system linux 'brk' |
|||
svc #0 |
|||
cmp r0,#-1 |
|||
beq 100f |
|||
@ string copy on the heap |
|||
mov r0,r6 |
|||
mov r1,r3 |
|||
1: @ loop copy string |
|||
ldrb r2,[r0],#1 @ read one byte and increment pointer one byte |
|||
strb r2,[r1],#1 @ store one byte and increment pointer one byte |
|||
cmp r2,#0 @ end of string ? |
|||
bne 1b @ no -> loop |
|||
add r4,r3 @ r4 contains address table begin |
|||
mov r0,#0 |
|||
str r0,[r4] |
|||
str r3,[r4,#4] |
|||
mov r2,#1 @ areas counter |
|||
2: @ loop load string character |
|||
ldrb r0,[r3] |
|||
cmp r0,#0 |
|||
beq 3f @ end string |
|||
cmp r0,r8 @ separator ? |
|||
addne r3,#1 @ no -> next location |
|||
bne 2b @ and loop |
|||
mov r0,#0 @ store zero final of string |
|||
strb r0,[r3] |
|||
add r3,#1 @ next character |
|||
add r2,#1 @ areas counter + 1 |
|||
str r3,[r4,r2, lsl #2] @ store address area in the table at index r2 |
|||
b 2b @ and loop |
|||
3: |
|||
str r2,[r4] @ returns number areas |
|||
mov r0,r4 |
|||
100: |
|||
pop {r1-r8,lr} |
|||
bx lr |
|||
iTailleTable: .int 4 * NBPOSTESECLAT |
|||
/***************************************************/ |
|||
/* calcul size string */ |
|||
/***************************************************/ |
|||
/* r0 string address */ |
|||
/* r0 returns size string */ |
|||
strLength: |
|||
push {r1,r2,lr} |
|||
mov r1,#0 @ init counter |
|||
1: |
|||
ldrb r2,[r0,r1] @ load byte of string index r1 |
|||
cmp r2,#0 @ end string ? |
|||
addne r1,#1 @ no -> +1 counter |
|||
bne 1b @ and loop |
|||
100: |
|||
mov r0,r1 |
|||
pop {r1,r2,lr} |
|||
bx lr |
|||
</syntaxhighlight> |
|||
=={{header|Arturo}}== |
|||
<syntaxhighlight lang="rebol">str: "Hello,How,Are,You,Today" |
|||
print join.with:"." split.by:"," str</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Astro}}== |
|||
<syntaxhighlight lang="python">let text = 'Hello,How,Are,You,Today' |
|||
let tokens = text.split(||,||) |
|||
print tokens.join(with: '.')</syntaxhighlight> |
|||
=={{header|AutoHotkey}}== |
=={{header|AutoHotkey}}== |
||
< |
<syntaxhighlight lang="autohotkey">string := "Hello,How,Are,You,Today" |
||
stringsplit, string, string, `, |
stringsplit, string, string, `, |
||
loop, % string0 |
loop, % string0 |
||
{ |
{ |
||
msgbox % string%A_Index% |
msgbox % string%A_Index% |
||
}</ |
}</syntaxhighlight> |
||
=={{header|AWK}}== |
=={{header|AWK}}== |
||
< |
<syntaxhighlight lang="awk">BEGIN { |
||
s = "Hello,How,Are,You,Today" |
s = "Hello,How,Are,You,Today" |
||
split(s, arr, ",") |
split(s, arr, ",") |
||
Line 99: | Line 928: | ||
} |
} |
||
print |
print |
||
}</ |
}</syntaxhighlight> |
||
A more ''idiomatic'' way for AWK is |
A more ''idiomatic'' way for AWK is |
||
< |
<syntaxhighlight lang="awk">BEGIN { FS = "," } |
||
{ |
{ |
||
for(i=1; i <= NF; i++) printf $i "."; |
for(i=1; i <= NF; i++) printf $i "."; |
||
print "" |
print "" |
||
}</ |
}</syntaxhighlight> |
||
which "tokenize" each line of input and this is achieved by using "," as field separator |
which "tokenize" each line of input and this is achieved by using "," as field separator |
||
=={{header| |
=={{header|BASIC}}== |
||
==={{header|Applesoft BASIC}}=== |
|||
<lang dos>@echo off |
|||
<syntaxhighlight lang="applesoftbasic">100 T$ = "HELLO,HOW,ARE,YOU,TODAY" |
|||
setlocal enabledelayedexpansion |
|||
110 GOSUB 200"TOKENIZE |
|||
call :tokenize %1 res |
|||
120 FOR I = 1 TO N |
|||
echo %res% |
|||
130 PRINT A$(I) "." ; |
|||
goto :eof |
|||
140 NEXT |
|||
150 PRINT |
|||
160 END |
|||
200 IF N = 0 THEN DIM A$(256) |
|||
:tokenize |
|||
210 N = 1 |
|||
220 A$(N) = " |
|||
:loop |
|||
230 FOR TI = 1 TO LEN(T$) |
|||
for %%i in (%str%) do set %2=!%2!.%%i |
|||
240 C$ = MID$(T$, TI, 1) |
|||
set %2=!%2:~1! |
|||
250 T = C$ = "," |
|||
goto :eof</lang> |
|||
260 IF T THEN C$ = " |
|||
270 N = N + T |
|||
280 IF T THEN A$(N) = C$ |
|||
290 A$(N) = A$(N) + C$ |
|||
300 NEXT TI |
|||
310 RETURN</syntaxhighlight> |
|||
==={{header|BaCon}}=== |
|||
''Demo'' |
|||
BaCon includes extensive support for ''delimited strings''. |
|||
<lang dos>>tokenize.cmd "Hello,How,Are,You,Today" |
|||
<syntaxhighlight lang="bacon">OPTION BASE 1 |
|||
Hello.How.Are.You.Today</lang> |
|||
string$ = "Hello,How,Are,You,Today" |
|||
=={{header|BASIC}}== |
|||
{{works with|QBasic}} |
|||
' Tokenize a string into an array |
|||
SPLIT string$ BY "," TO array$ |
|||
' Print array elements with new delimiter |
|||
PRINT COIL$(i, UBOUND(array$), array$[i], ".") |
|||
' Or simply replace the delimiter |
|||
PRINT DELIM$(string$, ",", ".")</syntaxhighlight> |
|||
{{out}} |
|||
<pre>prompt$ ./tokenize |
|||
Hello.How.Are.You.Today |
|||
Hello.How.Are.You.Today</pre> |
|||
==={{header|BASIC256}}=== |
|||
<syntaxhighlight lang="basic256">instring$ = "Hello,How,Are,You,Today" |
|||
tokens$ = explode(instring$,",") |
|||
for i = 0 to tokens$[?]-1 |
|||
print tokens$[i]; "."; |
|||
next i |
|||
end</syntaxhighlight> |
|||
==={{header|BBC BASIC}}=== |
|||
{{works with|BBC BASIC for Windows}} |
|||
<syntaxhighlight lang="bbcbasic"> INSTALL @lib$+"STRINGLIB" |
|||
text$ = "Hello,How,Are,You,Today" |
|||
n% = FN_split(text$, ",", array$()) |
|||
FOR i% = 0 TO n%-1 |
|||
PRINT array$(i%) "." ; |
|||
NEXT |
|||
PRINT</syntaxhighlight> |
|||
==={{header|Chipmunk Basic}}=== |
|||
Solutions [[#Applesoft BASIC|Applesoft BASIC]] and [[#Commodore BASIC|Commodore BASIC]] work without changes. |
|||
==={{header|Commodore BASIC}}=== |
|||
Based on the AppleSoft BASIC version. |
|||
<syntaxhighlight lang="commodorebasic">10 REM TOKENIZE A STRING ... ROSETTACODE.ORG |
|||
20 T$ = "HELLO,HOW,ARE,YOU,TODAY" |
|||
30 GOSUB 200, TOKENIZE |
|||
40 FOR I = 1 TO N |
|||
50 PRINT A$(I) "." ; |
|||
60 NEXT |
|||
70 PRINT |
|||
80 END |
|||
200 IF N = 0 THEN DIM A$(256) |
|||
210 N = 1 |
|||
220 A$(N) = "" |
|||
230 FOR L = 1 TO LEN(T$) |
|||
240 C$ = MID$(T$, L, 1) |
|||
250 IF C$<>"," THEN A$(N) = A$(N) + C$: GOTO 270 |
|||
260 N = N + 1 |
|||
270 NEXT L |
|||
280 RETURN</syntaxhighlight> |
|||
==={{header|FreeBASIC}}=== |
|||
<syntaxhighlight lang="freebasic">sub tokenize( instring as string, tokens() as string, sep as string ) |
|||
redim tokens(0 to 0) as string |
|||
dim as string*1 ch |
|||
dim as uinteger t=0 |
|||
for i as uinteger = 1 to len(instring) |
|||
ch = mid(instring,i,1) |
|||
if ch = sep then |
|||
t = t + 1 |
|||
redim preserve tokens(0 to t) |
|||
else |
|||
tokens(t) = tokens(t) + ch |
|||
end if |
|||
next i |
|||
return |
|||
end sub |
|||
dim as string instring = "Hello,How,Are,You,Today" |
|||
redim as string tokens(-1) |
|||
tokenize( instring, tokens(), "," ) |
|||
for i as uinteger = 0 to ubound(tokens) |
|||
print tokens(i);"."; |
|||
next i</syntaxhighlight> |
|||
==={{header|Liberty BASIC}}=== |
|||
<syntaxhighlight lang="lb">'Note that Liberty Basic's array usage can reach element #10 before having to DIM the array |
|||
For i = 0 To 4 |
|||
array$(i) = Word$("Hello,How,Are,You,Today", (i + 1), ",") |
|||
array$ = array$ + array$(i) + "." |
|||
Next i |
|||
Print Left$(array$, (Len(array$) - 1))</syntaxhighlight> |
|||
==={{header|MSX Basic}}=== |
|||
The [[#Commodore BASIC|Commodore BASIC]] solution works without any changes. |
|||
==={{header|PowerBASIC}}=== |
|||
PowerBASIC has a few keywords that make parsing strings trivial: <code>PARSE</code>, <code>PARSE$</code>, and <code>PARSECOUNT</code>. (<code>PARSE$</code>, not shown here, is for extracting tokens one at a time, while <code>PARSE</code> extracts all tokens at once into an array. <code>PARSECOUNT</code> returns the number of tokens found.) |
|||
<syntaxhighlight lang="powerbasic">FUNCTION PBMAIN () AS LONG |
|||
DIM parseMe AS STRING |
|||
parseMe = "Hello,How,Are,You,Today" |
|||
REDIM parsed(PARSECOUNT(parseMe) - 1) AS STRING |
|||
PARSE parseMe, parsed() 'comma is default delimiter |
|||
DIM L0 AS LONG, outP AS STRING |
|||
outP = parsed(0) |
|||
FOR L0 = 1 TO UBOUND(parsed) 'could reuse parsecount instead of ubound |
|||
outP = outP & "." & parsed(L0) |
|||
NEXT |
|||
MSGBOX outP |
|||
END FUNCTION</syntaxhighlight> |
|||
==={{header|PureBasic}}=== |
|||
'''As described |
|||
<syntaxhighlight lang="purebasic">NewList MyStrings.s() |
|||
For i=1 To 5 |
|||
AddElement(MyStrings()) |
|||
MyStrings()=StringField("Hello,How,Are,You,Today",i,",") |
|||
Next i |
|||
ForEach MyStrings() |
|||
Print(MyStrings()+".") |
|||
Next</syntaxhighlight> |
|||
'''Still, easier would be |
|||
<syntaxhighlight lang="purebasic">Print(ReplaceString("Hello,How,Are,You,Today",",","."))</syntaxhighlight> |
|||
==={{header|QBasic}}=== |
|||
<lang qbasic>DIM parseMe AS STRING |
|||
<syntaxhighlight lang="qbasic">DIM parseMe AS STRING |
|||
parseMe = "Hello,How,Are,You,Today" |
parseMe = "Hello,How,Are,You,Today" |
||
Line 176: | Line 1,144: | ||
PRINT "."; parsed(L0); |
PRINT "."; parsed(L0); |
||
NEXT |
NEXT |
||
END IF</ |
END IF</syntaxhighlight> |
||
=={{header| |
==={{header|Run BASIC}}=== |
||
<syntaxhighlight lang="runbasic">text$ = "Hello,How,Are,You,Today" |
|||
{{works with|BBC BASIC for Windows}} |
|||
FOR i = 1 to 5 |
|||
<lang bbcbasic> INSTALL @lib$+"STRINGLIB" |
|||
textArray$(i) = word$(text$,i,",") |
|||
print textArray$(i);" "; |
|||
text$ = "Hello,How,Are,You,Today" |
|||
NEXT</syntaxhighlight> |
|||
n% = FN_split(text$, ",", array$()) |
|||
FOR i% = 0 TO n%-1 |
|||
==={{header|VBScript}}=== |
|||
PRINT array$(i%) "." ; |
|||
====One liner==== |
|||
NEXT |
|||
<syntaxhighlight lang="vb">WScript.Echo Join(Split("Hello,How,Are,You,Today", ","), ".")</syntaxhighlight> |
|||
PRINT</lang> |
|||
In fact, the Visual Basic solution (below) could have done the same, as Join() is available. |
|||
==={{header|Visual Basic}}=== |
|||
{{trans|PowerBASIC}} |
|||
Unlike PowerBASIC, there is no need to know beforehand how many tokens are in the string -- <code>Split</code> automagically builds the array for you. |
|||
<syntaxhighlight lang="vb">Sub Main() |
|||
Dim parseMe As String, parsed As Variant |
|||
parseMe = "Hello,How,Are,You,Today" |
|||
parsed = Split(parseMe, ",") |
|||
Dim L0 As Long, outP As String |
|||
outP = parsed(0) |
|||
For L0 = 1 To UBound(parsed) |
|||
outP = outP & "." & parsed(L0) |
|||
Next |
|||
MsgBox outP |
|||
End Sub</syntaxhighlight> |
|||
=={{header|Batch File}}== |
|||
<syntaxhighlight lang="dos">@echo off |
|||
setlocal enabledelayedexpansion |
|||
call :tokenize %1 res |
|||
echo %res% |
|||
goto :eof |
|||
:tokenize |
|||
set str=%~1 |
|||
:loop |
|||
for %%i in (%str%) do set %2=!%2!.%%i |
|||
set %2=!%2:~1! |
|||
goto :eof</syntaxhighlight> |
|||
''Demo'' |
|||
>tokenize.cmd "Hello,How,Are,You,Today" |
|||
Hello.How.Are.You.Today |
|||
=={{header|BQN}}== |
|||
Uses a splitting idiom from bqncrate. |
|||
<syntaxhighlight lang="bqn">Split ← (+`׬)⊸-∘= ⊔ ⊢ |
|||
∾⟜'.'⊸∾´ ',' Split "Hello,How,Are,You,Today"</syntaxhighlight> |
|||
{{out}} |
|||
<pre>"Hello.How.Are.You.Today"</pre> |
|||
=={{header|Bracmat}}== |
=={{header|Bracmat}}== |
||
Solution that employs string pattern matching to spot the commas |
Solution that employs string pattern matching to spot the commas |
||
< |
<syntaxhighlight lang="bracmat">( "Hello,How,Are,You,Today":?String |
||
& :?ReverseList |
& :?ReverseList |
||
& whl |
& whl |
||
Line 203: | Line 1,219: | ||
) |
) |
||
& out$!List |
& out$!List |
||
)</syntaxhighlight> |
|||
) |
|||
</lang> |
|||
Solution that starts by evaluating the input and employs the circumstance that the comma is a list constructing binary operator and that the string does not contain any other characters that are interpreted as operators on evaluation. |
Solution that starts by evaluating the input and employs the circumstance that the comma is a list constructing binary operator and that the string does not contain any other characters that are interpreted as operators on evaluation. |
||
< |
<syntaxhighlight lang="bracmat">( get$("Hello,How,Are,You,Today",MEM):?CommaseparatedList |
||
& :?ReverseList |
& :?ReverseList |
||
& whl |
& whl |
||
Line 218: | Line 1,233: | ||
) |
) |
||
& out$!List |
& out$!List |
||
)</syntaxhighlight> |
|||
) |
|||
</lang> |
|||
=={{header|C}}== |
=={{header|C}}== |
||
{{works with|ANSI C}} |
{{works with|ANSI C}} |
||
Line 227: | Line 1,242: | ||
This example uses the ''strtok()'' function to separate the tokens. This function is destructive (replacing token separators with '\0'), so we have to make a copy of the string (using ''strdup()'') before tokenizing. ''strdup()'' is not part of [[ANSI C]], but is available on most platforms. It can easily be implemented with a combination of ''strlen()'', ''malloc()'', and ''strcpy()''. |
This example uses the ''strtok()'' function to separate the tokens. This function is destructive (replacing token separators with '\0'), so we have to make a copy of the string (using ''strdup()'') before tokenizing. ''strdup()'' is not part of [[ANSI C]], but is available on most platforms. It can easily be implemented with a combination of ''strlen()'', ''malloc()'', and ''strcpy()''. |
||
< |
<syntaxhighlight lang="c">#include<string.h> |
||
#include<stdio.h> |
#include<stdio.h> |
||
#include<stdlib.h> |
#include<stdlib.h> |
||
Line 248: | Line 1,263: | ||
return 0; |
return 0; |
||
}</ |
}</syntaxhighlight> |
||
Another way to accomplish the task without the built-in string functions is to temporarily modify the separator character. This method does not need any additional memory, but requires the input string to be writeable. |
Another way to accomplish the task without the built-in string functions is to temporarily modify the separator character. This method does not need any additional memory, but requires the input string to be writeable. |
||
< |
<syntaxhighlight lang="c">#include<stdio.h> |
||
typedef |
typedef void (*callbackfunc)(const char *); |
||
void doprint(const char *s) { |
void doprint(const char *s) { |
||
Line 259: | Line 1,274: | ||
} |
} |
||
void tokenize(char *s, char delim, callbackfunc |
void tokenize(char *s, char delim, callbackfunc cb) { |
||
char *olds = s; |
char *olds = s; |
||
char olddelim = delim; |
char olddelim = delim; |
||
Line 276: | Line 1,291: | ||
tokenize(array, ',', doprint); |
tokenize(array, ',', doprint); |
||
return 0; |
return 0; |
||
}</ |
}</syntaxhighlight> |
||
=={{header|C sharp|C#}}== |
=={{header|C sharp|C#}}== |
||
< |
<syntaxhighlight lang="csharp">string str = "Hello,How,Are,You,Today"; |
||
// or Regex.Split ( "Hello,How,Are,You,Today", "," ); |
// or Regex.Split ( "Hello,How,Are,You,Today", "," ); |
||
// (Regex is in System.Text.RegularExpressions namespace |
// (Regex is in System.Text.RegularExpressions namespace) |
||
string[] strings = str.Split(','); |
string[] strings = str.Split(','); |
||
Console.WriteLine(String.Join(".", strings)); |
|||
</syntaxhighlight> |
|||
{ |
|||
Console.WriteLine (s + "."); |
|||
}</lang> |
|||
=={{header|C++}}== |
=={{header|C++}}== |
||
{{works with|ANSI C++}} |
|||
{{ |
{{works with|C++98}} |
||
std::getline() is typically used to tokenize strings on a single-character delimiter |
|||
<syntaxhighlight lang="cpp">#include <string> |
|||
This is not the most efficient method as it involves redundant copies in the background, but it is very easy to use. In most cases it will be a good choice as long as it is not used as an inner loop in a performance critical system. |
|||
#include <sstream> |
|||
#include <vector> |
|||
#include <iterator> |
|||
#include <iostream> |
|||
#include <algorithm> |
|||
int main() |
|||
{ |
|||
std::string s = "Hello,How,Are,You,Today"; |
|||
std::vector<std::string> v; |
|||
std::istringstream buf(s); |
|||
for(std::string token; getline(buf, token, ','); ) |
|||
v.push_back(token); |
|||
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, ".")); |
|||
std::cout << '\n'; |
|||
}</syntaxhighlight> |
|||
{{works with|C++98}} |
|||
Note doxygen tags in comments before function, describing details of interface. |
|||
C++ allows the user to redefine what is considered whitespace. If the delimiter is whitespace, tokenization becomes effortless. |
|||
< |
<syntaxhighlight lang="cpp">#include <string> |
||
#include <locale> |
|||
#include <sstream> |
|||
#include <vector> |
#include <vector> |
||
#include <iterator> |
|||
/// \brief convert input string into vector of string tokens |
|||
#include <iostream> |
|||
/// |
|||
#include <algorithm> |
|||
/// \note consecutive delimiters will be treated as single delimiter |
|||
struct comma_ws : std::ctype<char> { |
|||
/// \note delimiters are _not_ included in return data |
|||
static const mask* make_table() { |
|||
/// |
|||
static std::vector<mask> v(classic_table(), classic_table() + table_size); |
|||
/// \param input string to be parsed |
|||
v[','] |= space; // comma will be classified as whitespace |
|||
/// \param delims list of delimiters. |
|||
return &v[0]; |
|||
} |
|||
comma_ws(std::size_t refs = 0) : ctype<char>(make_table(), false, refs) {} |
|||
}; |
|||
int main() |
|||
{ |
|||
std::string s = "Hello,How,Are,You,Today"; |
|||
std::istringstream buf(s); |
|||
buf.imbue(std::locale(buf.getloc(), new comma_ws)); |
|||
std::istream_iterator<std::string> beg(buf), end; |
|||
std::vector<std::string> v(beg, end); |
|||
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, ".")); |
|||
std::cout << '\n'; |
|||
}</syntaxhighlight> |
|||
{{works with|C++98}} |
|||
std::vector<std::string> tokenize_str(const std::string & str, |
|||
{{libheader|boost}} |
|||
const std::string & delims=", \t") |
|||
The boost library has multiple options for easy tokenization. |
|||
<syntaxhighlight lang="cpp">#include <string> |
|||
#include <vector> |
|||
#include <iterator> |
|||
#include <algorithm> |
|||
#include <iostream> |
|||
#include <boost/tokenizer.hpp> |
|||
int main() |
|||
{ |
{ |
||
std::string s = "Hello,How,Are,You,Today"; |
|||
using namespace std; |
|||
boost::tokenizer<> tok(s); |
|||
// Skip delims at beginning, find start of first token |
|||
std::vector<std::string> v(tok.begin(), tok.end()); |
|||
string::size_type lastPos = str.find_first_not_of(delims, 0); |
|||
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, ".")) |
|||
// Find next delimiter @ end of token |
|||
std::cout << '\n'; |
|||
string::size_type pos = str.find_first_of(delims, lastPos); |
|||
}</syntaxhighlight> |
|||
{{works with|C++23}} |
|||
// output vector |
|||
C++20 and C++23 drastically improve the ergonomics of simple manipulation of ranges. |
|||
vector<string> tokens; |
|||
<syntaxhighlight lang="cpp">#include <string> |
|||
while (string::npos != pos || string::npos != lastPos) |
|||
#include <ranges> |
|||
{ |
|||
#include <iostream> |
|||
// Found a token, add it to the vector. |
|||
int main() { |
|||
tokens.push_back(str.substr(lastPos, pos - lastPos)); |
|||
std::string s = "Hello,How,Are,You,Today"; |
|||
// Skip delims. Note the "not_of". this is beginning of token |
|||
s = s // Assign the final string back to the string variable |
|||
lastPos = str.find_first_not_of(delims, pos); |
|||
| std::views::split(',') // Produce a range of the comma separated words |
|||
// Find next delimiter at end of token. |
|||
| std::views::join_with('.') // Concatenate the words into a single range of characters |
|||
pos = str.find_first_of(delims, lastPos); |
|||
| std::ranges::to<std::string>(); // Convert the range of characters into a regular string |
|||
} |
|||
std::cout << s; |
|||
}</syntaxhighlight> |
|||
=={{header|Ceylon}}== |
|||
return tokens; |
|||
{{works with|Ceylon 1.2}} |
|||
}</lang> |
|||
<syntaxhighlight lang="ceylon">shared void tokenizeAString() { |
|||
value input = "Hello,How,Are,You,Today"; |
|||
value tokens = input.split(','.equals); |
|||
print(".".join(tokens)); |
|||
}</syntaxhighlight> |
|||
=={{header|CFEngine}}== |
|||
<syntaxhighlight lang="cfengine">bundle agent main |
|||
{ |
|||
reports: |
|||
"${with}" with => join(".", splitstring("Hello,How,Are,You,Today", ",", 99)); |
|||
} |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre>cf-agent -KIf ./tokenize-a-string.cf |
|||
R: Hello.How.Are.You.Today</pre> |
|||
See https://docs.cfengine.com/docs/master/reference-functions.html for a complete list of available functions. |
|||
here is sample usage code: |
|||
=={{header|Clojure}}== |
|||
<lang cpp>#include <iostream> |
|||
Using native Clojure functions and Java Interop: |
|||
int main() { |
|||
<syntaxhighlight lang="clojure">(apply str (interpose "." (.split #"," "Hello,How,Are,You,Today")))</syntaxhighlight> |
|||
using namespace std; |
|||
string s("Hello,How,Are,You,Today"); |
|||
Using the clojure.string library: |
|||
vector<string> v(tokenize_str(s)); |
|||
<syntaxhighlight lang="clojure">(clojure.string/join "." (clojure.string/split "Hello,How,Are,You,Today" #","))</syntaxhighlight> |
|||
=={{header|CLU}}== |
|||
for (unsigned i = 0; i < v.size(); i++) |
|||
<syntaxhighlight lang="clu">% This iterator splits the string on a given character, |
|||
cout << v[i] << "."; |
|||
% and returns each substring in order. |
|||
tokenize = iter (s: string, c: char) yields (string) |
|||
cout << endl; |
|||
while ~string$empty(s) do |
|||
return 0; |
|||
next: int := string$indexc(c, s) |
|||
}</lang> |
|||
if next = 0 then |
|||
yield(s) |
|||
break |
|||
else |
|||
yield(string$substr(s, 1, next-1)) |
|||
s := string$rest(s, next+1) |
|||
end |
|||
end |
|||
end tokenize |
|||
start_up = proc () |
|||
po: stream := stream$primary_output() |
|||
str: string := "Hello,How,Are,You,Today" |
|||
for part: string in tokenize(str, ',') do |
|||
stream$putl(po, part || ".") |
|||
end |
|||
end start_up</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello. |
|||
How. |
|||
Are. |
|||
You. |
|||
Today.</pre> |
|||
=={{header|COBOL}}== |
|||
This can be made to handle more complex cases; UNSTRING allows multiple delimiters, capture of which delimiter was used for each field, a POINTER for starting position (set on ending), along with match TALLYING. |
|||
<syntaxhighlight lang="cobol"> |
|||
identification division. |
|||
program-id. tokenize. |
|||
environment division. |
|||
configuration section. |
|||
repository. |
|||
function all intrinsic. |
|||
data division. |
|||
working-storage section. |
|||
01 period constant as ".". |
|||
01 cmma constant as ",". |
|||
01 start-with. |
|||
05 value "Hello,How,Are,You,Today". |
|||
01 items. |
|||
05 item pic x(6) occurs 5 times. |
|||
procedure division. |
|||
tokenize-main. |
|||
unstring start-with delimited by cmma |
|||
into item(1) item(2) item(3) item(4) item(5) |
|||
display trim(item(1)) period trim(item(2)) period |
|||
trim(item(3)) period trim(item(4)) period |
|||
trim(item(5)) |
|||
goback. |
|||
end program tokenize. |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
prompt$ cobc -xj tokenize.cob |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|CoffeeScript}}== |
=={{header|CoffeeScript}}== |
||
< |
<syntaxhighlight lang="coffeescript"> |
||
arr = "Hello,How,Are,You,Today".split "," |
arr = "Hello,How,Are,You,Today".split "," |
||
console.log arr.join "." |
console.log arr.join "." |
||
</syntaxhighlight> |
|||
</lang> |
|||
=={{header|ColdFusion}}== |
|||
=== Classic tag based CFML === |
|||
<syntaxhighlight lang="cfm"> |
|||
<cfoutput> |
|||
<cfset wordListTag = "Hello,How,Are,You,Today"> |
|||
#Replace( wordListTag, ",", ".", "all" )# |
|||
</cfoutput> |
|||
</syntaxhighlight> |
|||
{{Output}} |
|||
<pre> |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
=== Script Based CFML === |
|||
<syntaxhighlight lang="cfm"><cfscript> |
|||
wordList = "Hello,How,Are,You,Today"; |
|||
splitList = replace( wordList, ",", ".", "all" ); |
|||
writeOutput( splitList ); |
|||
</cfscript></syntaxhighlight> |
|||
{{Output}} |
|||
<pre> |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
=={{header|Common Lisp}}== |
=={{header|Common Lisp}}== |
||
Line 360: | Line 1,522: | ||
There are libraries out there that handle splitting (e.g., [http://www.cliki.net/SPLIT-SEQUENCE SPLIT-SEQUENCE], and the more-general [http://weitz.de/cl-ppcre/ CL-PPCRE]), but this is a simple one-off, too. When the words are written with write-with-periods, there is no final period after the last word. |
There are libraries out there that handle splitting (e.g., [http://www.cliki.net/SPLIT-SEQUENCE SPLIT-SEQUENCE], and the more-general [http://weitz.de/cl-ppcre/ CL-PPCRE]), but this is a simple one-off, too. When the words are written with write-with-periods, there is no final period after the last word. |
||
< |
<syntaxhighlight lang="lisp">(defun comma-split (string) |
||
(loop |
(loop for start = 0 then (1+ finish) |
||
for finish = (position #\, string :start start) |
|||
collecting (subseq string start finish) |
|||
until (null finish))) |
|||
(defun write-with-periods (strings) |
(defun write-with-periods (strings) |
||
(format t "~{~A~^.~}" strings))</ |
(format t "~{~A~^.~}" strings))</syntaxhighlight> |
||
=={{header| |
=={{header|Cowgol}}== |
||
<syntaxhighlight lang="cowgol">include "cowgol.coh"; |
|||
<lang lisp>(apply str (interpose "." (seq (.split #"," "Hello,How,Are,You,Today"))))</lang> |
|||
include "strings.coh"; |
|||
# Tokenize a string. Note: the string is modified in place. |
|||
=={{header|D}}== |
|||
sub tokenize(sep: uint8, str: [uint8], out: [[uint8]]): (length: intptr) is |
|||
length := 0; |
|||
loop |
|||
[out] := str; |
|||
out := @next out; |
|||
length := length + 1; |
|||
while [str] != 0 and [str] != sep loop |
|||
str := @next str; |
|||
end loop; |
|||
if [str] == sep then |
|||
[str] := 0; |
|||
str := @next str; |
|||
else |
|||
break; |
|||
end if; |
|||
end loop; |
|||
end sub; |
|||
# The string |
|||
var string: [uint8] := "Hello,How,Are,You,Today"; |
|||
# Make a mutable copy |
|||
void main() { |
|||
var buf: uint8[64]; |
|||
writeln("Hello,How,Are,You,Today".split(",").join(".")); |
|||
CopyString(string, &buf[0]); |
|||
}</lang> |
|||
Output: |
|||
# Tokenize the copy |
|||
var parts: [uint8][64]; |
|||
var length := tokenize(',', &buf[0], &parts[0]) as @indexof parts; |
|||
# Print each string |
|||
var i: @indexof parts := 0; |
|||
while i < length loop |
|||
print(parts[i]); |
|||
print(".\n"); |
|||
i := i + 1; |
|||
end loop;</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello. |
|||
How. |
|||
Are. |
|||
You. |
|||
Today.</pre> |
|||
=={{header|Crystal}}== |
|||
<syntaxhighlight lang="crystal">puts "Hello,How,Are,You,Today".split(',').join('.')</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|D}}== |
|||
<syntaxhighlight lang="d">void main() { |
|||
import std.stdio, std.string; |
|||
"Hello,How,Are,You,Today".split(',').join('.').writeln; |
|||
}</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
<pre>Hello.How.Are.You.Today</pre> |
||
=={{header|Delphi}}== |
=={{header|Delphi}}== |
||
=== Using String.split === |
|||
{{libheader| System.SysUtils}} |
|||
<syntaxhighlight lang="delphi"> |
|||
program Tokenize_a_string; |
|||
{$APPTYPE CONSOLE} |
|||
uses |
|||
System.SysUtils; |
|||
var |
|||
Words: TArray<string>; |
|||
begin |
|||
Words := 'Hello,How,Are,You,Today'.Split([',']); |
|||
Writeln(string.Join(#10, Words)); |
|||
Readln; |
|||
end. |
|||
</syntaxhighlight> |
|||
=== Using TStringList === |
|||
<lang Delphi> |
|||
<syntaxhighlight lang="delphi"> |
|||
program TokenizeString; |
program TokenizeString; |
||
Line 417: | Line 1,650: | ||
end. |
end. |
||
</syntaxhighlight> |
|||
</lang> |
|||
The result is: |
The result is: |
||
<syntaxhighlight lang="delphi"> |
|||
<lang Delphi> |
|||
Hello |
Hello |
||
How |
How |
||
Line 427: | Line 1,660: | ||
You |
You |
||
Today |
Today |
||
</syntaxhighlight> |
|||
</lang> |
|||
=={{header|dt}}== |
|||
<syntaxhighlight lang="dt">"Hello,How,Are,You,Today" "," split "." join pl</syntaxhighlight> |
|||
=={{header|Dyalect}}== |
|||
<syntaxhighlight lang="dyalect">var str = "Hello,How,Are,You,Today" |
|||
var strings = str.Split(',') |
|||
print(values: strings, separator: ".")</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Déjà Vu}}== |
|||
<syntaxhighlight lang="dejavu">!print join "." split "Hello,How,Are,You,Today" ","</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|E}}== |
=={{header|E}}== |
||
< |
<syntaxhighlight lang="e">".".rjoin("Hello,How,Are,You,Today".split(","))</syntaxhighlight> |
||
=={{header|EasyLang}}== |
|||
<syntaxhighlight lang="easylang"> |
|||
s$ = "Hello,How,Are,You,Today" |
|||
a$[] = strsplit s$ "," |
|||
for s$ in a$[] |
|||
write s$ & "." |
|||
. |
|||
</syntaxhighlight> |
|||
=={{header|Elena}}== |
|||
ELENA 6.x: |
|||
<syntaxhighlight lang="elena">import system'routines; |
|||
import extensions; |
|||
public program() |
|||
{ |
|||
auto string := "Hello,How,Are,You,Today"; |
|||
string.splitBy(",").forEach::(s) |
|||
{ |
|||
console.print(s,".") |
|||
} |
|||
}</syntaxhighlight> |
|||
=={{header|Elixir}}== |
|||
<syntaxhighlight lang="elixir"> |
|||
tokens = String.split("Hello,How,Are,You,Today", ",") |
|||
IO.puts Enum.join(tokens, ".") |
|||
</syntaxhighlight> |
|||
=={{header|EMal}}== |
|||
<syntaxhighlight lang="emal"> |
|||
text value = "Hello,How,Are,You,Today" |
|||
List tokens = value.split(",") |
|||
writeLine(tokens.join(".")) |
|||
# single line version |
|||
writeLine("Hello,How,Are,You,Today".split(",").join(".")) |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|Erlang}}== |
=={{header|Erlang}}== |
||
< |
<syntaxhighlight lang="erlang">-module(tok). |
||
-export([start/0]). |
-export([start/0]). |
||
Line 439: | Line 1,731: | ||
Lst = string:tokens("Hello,How,Are,You,Today",","), |
Lst = string:tokens("Hello,How,Are,You,Today",","), |
||
io:fwrite("~s~n", [string:join(Lst,".")]), |
io:fwrite("~s~n", [string:join(Lst,".")]), |
||
ok.</ |
ok.</syntaxhighlight> |
||
=={{header|Euphoria}}== |
=={{header|Euphoria}}== |
||
< |
<syntaxhighlight lang="euphoria">function split(sequence s, integer c) |
||
sequence out |
sequence out |
||
integer first, delim |
integer first, delim |
||
Line 463: | Line 1,755: | ||
for i = 1 to length(s) do |
for i = 1 to length(s) do |
||
puts(1, s[i] & ',') |
puts(1, s[i] & ',') |
||
end for</ |
end for</syntaxhighlight> |
||
=={{header|F_Sharp|F#}}== |
|||
<syntaxhighlight lang="fsharp">System.String.Join(".", "Hello,How,Are,You,Today".Split(','))</syntaxhighlight> |
|||
=={{header|Factor}}== |
=={{header|Factor}}== |
||
< |
<syntaxhighlight lang="factor">"Hello,How,Are,You,Today" "," split "." join print</syntaxhighlight> |
||
=={{header|Falcon}}== |
|||
'''VBA/Python programmer's approach to this solution, not sure if it's the most falconic way''' |
|||
<syntaxhighlight lang="falcon"> |
|||
/* created by Aykayayciti Earl Lamont Montgomery |
|||
April 9th, 2018 */ |
|||
a = [] |
|||
a = strSplit("Hello,How,Are,You,Today", ",") |
|||
index = 0 |
|||
start = 0 |
|||
b = "" |
|||
for index in [ start : len(a)-1 : 1 ] |
|||
b = b + a[index] + "." |
|||
end |
|||
> b |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You. |
|||
[Finished in 0.2s] |
|||
</pre> |
|||
=={{header|Fantom}}== |
=={{header|Fantom}}== |
||
Line 472: | Line 1,790: | ||
A string can be split on a given character, returning a list of the intervening strings. |
A string can be split on a given character, returning a list of the intervening strings. |
||
< |
<syntaxhighlight lang="fantom"> |
||
class Main |
class Main |
||
{ |
{ |
||
Line 485: | Line 1,803: | ||
} |
} |
||
} |
} |
||
</syntaxhighlight> |
|||
</lang> |
|||
=={{header|Fennel}}== |
|||
{{trans|Lua}} |
|||
<syntaxhighlight lang="fennel">(fn string.split [self sep] |
|||
(let [pattern (string.format "([^%s]+)" sep) |
|||
fields {}] |
|||
(self:gsub pattern (fn [c] (tset fields (+ 1 (length fields)) c))) |
|||
fields)) |
|||
(let [str "Hello,How,Are,You,Today"] |
|||
(print (table.concat (str:split ",") ".")))</syntaxhighlight> |
|||
=={{header|Forth}}== |
=={{header|Forth}}== |
||
There is no standard string split routine, but it is easily written. The results are saved temporarily to the dictionary. |
There is no standard string split routine, but it is easily written. The results are saved temporarily to the dictionary. |
||
< |
<syntaxhighlight lang="forth">: split ( str len separator len -- tokens count ) |
||
here >r 2swap |
here >r 2swap |
||
begin |
begin |
||
Line 507: | Line 1,836: | ||
1 ?do dup 2@ type ." ." cell+ cell+ loop 2@ type ; |
1 ?do dup 2@ type ." ." cell+ cell+ loop 2@ type ; |
||
s" Hello,How,Are,You,Today" s" ," split .tokens \ Hello.How.Are.You.Today</ |
s" Hello,How,Are,You,Today" s" ," split .tokens \ Hello.How.Are.You.Today</syntaxhighlight> |
||
=={{header|Fortran}}== |
=={{header|Fortran}}== |
||
{{works with|Fortran|90 and later}} |
{{works with|Fortran|90 and later}} |
||
< |
<syntaxhighlight lang="fortran">PROGRAM Example |
||
CHARACTER(23) :: str = "Hello,How,Are,You,Today" |
CHARACTER(23) :: str = "Hello,How,Are,You,Today" |
||
Line 533: | Line 1,862: | ||
END DO |
END DO |
||
END PROGRAM Example</ |
END PROGRAM Example</syntaxhighlight> |
||
=={{header| |
=={{header|Frink}}== |
||
<syntaxhighlight lang="frink"> |
|||
<lang pascal> |
|||
println[join[".", split[",", "Hello,How,Are,You,Today"]]] |
|||
program TokenizeString; |
|||
</syntaxhighlight> |
|||
=={{header|FutureBasic}}== |
|||
{$mode objfpc}{$H+} |
|||
<syntaxhighlight lang="futurebasic"> |
|||
window 1, @"Tokenize a string" |
|||
void local fn DoIt |
|||
const |
|||
CFStringRef string = @"Hello,How,Are,You,Today" |
|||
CFArrayRef tokens = fn StringComponentsSeparatedByString( string, @"," ) |
|||
var |
|||
print fn ArrayComponentsJoinedByString( tokens, @"." ) |
|||
I: Integer; |
|||
end fn |
|||
VResult: string = ''; |
|||
begin |
|||
fn DoIt |
|||
for I := 1 to Length(CHelloStr) do |
|||
begin |
|||
HandleEvents |
|||
if CHelloStr[I] = ',' then |
|||
</syntaxhighlight> |
|||
VResult += LineEnding |
|||
{{out}} |
|||
else |
|||
<pre> |
|||
VResult += CHelloStr[I]; |
|||
Hello.How.Are.You.Today |
|||
end; |
|||
</pre> |
|||
WriteLn(VResult); |
|||
end; |
|||
=={{header|Gambas}}== |
|||
</lang> |
|||
'''[https://gambas-playground.proko.eu/?gist=218e240236cdf1419a405abfed906ed3 Click this link to run this code]''' |
|||
<syntaxhighlight lang="gambas">Public Sub Main() |
|||
Dim sString As String[] = Split("Hello,How,Are,You,Today") |
|||
Print sString.Join(".") |
|||
End</syntaxhighlight> |
|||
Output: |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
The result is: |
|||
<lang pascal> |
|||
Hello |
|||
How |
|||
Are |
|||
You |
|||
Today |
|||
</lang> |
|||
'''Credits''': [http://code.google.com/p/lazsolutions/ silvioprog], 15:10, 8 January 2012 (UTC) |
|||
=={{header|GAP}}== |
=={{header|GAP}}== |
||
< |
<syntaxhighlight lang="gap">SplitString("Hello,How,Are,You,Today", ","); |
||
# [ "Hello", "How", "Are", "You", "Today" ] |
# [ "Hello", "How", "Are", "You", "Today" ] |
||
JoinStringsWithSeparator(last, "."); |
JoinStringsWithSeparator(last, "."); |
||
# "Hello.How.Are.You.Today"</ |
# "Hello.How.Are.You.Today"</syntaxhighlight> |
||
=={{header|Genie}}== |
|||
<syntaxhighlight lang="genie">[indent=4] |
|||
init |
|||
str:string = "Hello,How,Are,You,Today" |
|||
words:array of string[] = str.split(",") |
|||
joined:string = string.joinv(".", words) |
|||
print joined</syntaxhighlight> |
|||
{{out}} |
|||
<pre>prompt$ valac tokenize.gs |
|||
prompt$ ./tokenize |
|||
Hello.How.Are.You.Today</pre> |
|||
=={{header|Go}}== |
=={{header|Go}}== |
||
< |
<syntaxhighlight lang="go">package main |
||
import ( |
import ( |
||
Line 585: | Line 1,933: | ||
s := "Hello,How,Are,You,Today" |
s := "Hello,How,Are,You,Today" |
||
fmt.Println(strings.Join(strings.Split(s, ","), ".")) |
fmt.Println(strings.Join(strings.Split(s, ","), ".")) |
||
}</ |
}</syntaxhighlight> |
||
=={{header|Groovy}}== |
|||
<syntaxhighlight lang="groovy">println 'Hello,How,Are,You,Today'.split(',').join('.')</syntaxhighlight> |
|||
=={{header|Haskell}}== |
=={{header|Haskell}}== |
||
'''Using Data.Text''' |
|||
<syntaxhighlight lang="haskell">{-# OPTIONS_GHC -XOverloadedStrings #-} |
|||
import Data.Text (splitOn,intercalate) |
|||
import qualified Data.Text.IO as T (putStrLn) |
|||
main = T.putStrLn . intercalate "." $ splitOn "," "Hello,How,Are,You,Today"</syntaxhighlight> |
|||
Output: Hello.How.Are.You.Today |
|||
'''Alternate Solution''' |
|||
The necessary operations are unfortunately not in the standard library (yet), but simple to write: |
The necessary operations are unfortunately not in the standard library (yet), but simple to write: |
||
< |
<syntaxhighlight lang="haskell">splitBy :: (a -> Bool) -> [a] -> [[a]] |
||
splitBy _ [] = [] |
splitBy _ [] = [] |
||
splitBy f list = first : splitBy f (dropWhile f rest) where |
splitBy f list = first : splitBy f (dropWhile f rest) where |
||
Line 606: | Line 1,968: | ||
-- using regular expression to split: |
-- using regular expression to split: |
||
import Text.Regex |
import Text.Regex |
||
putStrLn $ joinWith "." $ splitRegex (mkRegex ",") $ "Hello,How,Are,You,Today"</ |
putStrLn $ joinWith "." $ splitRegex (mkRegex ",") $ "Hello,How,Are,You,Today"</syntaxhighlight> |
||
Tokenizing can also be realized by using unfoldr and break: |
Tokenizing can also be realized by using unfoldr and break: |
||
< |
<syntaxhighlight lang="haskell">*Main> mapM_ putStrLn $ takeWhile (not.null) $ unfoldr (Just . second(drop 1). break (==',')) "Hello,How,Are,You,Today" |
||
Hello |
Hello |
||
How |
How |
||
Are |
Are |
||
You |
You |
||
Today</ |
Today</syntaxhighlight> |
||
* You need to import the modules Data.List and Control.Arrow |
* You need to import the modules Data.List and Control.Arrow |
||
As special cases, splitting / joining by white space and by newlines are provided by the Prelude functions < |
As special cases, splitting / joining by white space and by newlines are provided by the Prelude functions <code>words</code> / <code>unwords</code> and <code>lines</code> / <code>unlines</code>, respectively. |
||
=={{header|Groovy}}== |
|||
<lang groovy>println 'Hello,How,Are,You,Today'.split(',').join('.')</lang> |
|||
=={{header|HicEst}}== |
=={{header|HicEst}}== |
||
< |
<syntaxhighlight lang="hicest">CHARACTER string="Hello,How,Are,You,Today", list |
||
nWords = INDEX(string, ',', 256) + 1 |
nWords = INDEX(string, ',', 256) + 1 |
||
Line 635: | Line 1,994: | ||
DO i = 1, nWords |
DO i = 1, nWords |
||
WRITE(APPend) TRIM(CHAR(i, maxWordLength, list)), '.' |
WRITE(APPend) TRIM(CHAR(i, maxWordLength, list)), '.' |
||
ENDDO</ |
ENDDO</syntaxhighlight> |
||
=={{header|Icon}} and {{header|Unicon}}== |
=={{header|Icon}} and {{header|Unicon}}== |
||
< |
<syntaxhighlight lang="icon">procedure main() |
||
A := [] |
A := [] |
||
"Hello,How,Are,You,Today" ? |
"Hello,How,Are,You,Today" ? { |
||
while put(A, 1(tab(upto(',')),=",")) |
|||
put(A,tab(0)) |
|||
} |
|||
every writes(!A,".") |
every writes(!A,".") |
||
write() |
write() |
||
end</ |
end</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
<pre> |
||
->ss |
|||
Hello.How.Are.You. |
|||
Hello.How.Are.You.Today. |
|||
-> |
|||
-> |
|||
</pre> |
</pre> |
||
A Unicon-specific solution is: |
|||
<syntaxhighlight lang="unicon">import util |
|||
procedure main() |
|||
A := stringToList("Hello,How,Are,You,Today", ',') |
|||
every writes(!A,".") |
|||
write() |
|||
end</syntaxhighlight> |
|||
One wonders what the expected output should be with the input string ",,,,". |
|||
=={{header|Io}}== |
=={{header|Io}}== |
||
< |
<syntaxhighlight lang="io">"Hello,How,Are,You,Today" split(",") join(".") println</syntaxhighlight> |
||
=={{header|J}}== |
=={{header|J}}== |
||
< |
<syntaxhighlight lang="j"> s=: 'Hello,How,Are,You,Today' |
||
] t=: <;._1 ',',s |
] t=: <;._1 ',',s |
||
+-----+---+---+---+-----+ |
+-----+---+---+---+-----+ |
||
Line 664: | Line 2,038: | ||
'.' (I.','=s)}s NB. two steps combined |
'.' (I.','=s)}s NB. two steps combined |
||
Hello.How.Are.You.Today</ |
Hello.How.Are.You.Today</syntaxhighlight> |
||
Alternatively using the system library/script <tt>strings</tt> |
Alternatively using the system library/script <tt>strings</tt> |
||
< |
<syntaxhighlight lang="j"> require 'strings' |
||
',' splitstring s |
',' splitstring s |
||
+-----+---+---+---+-----+ |
+-----+---+---+---+-----+ |
||
Line 674: | Line 2,048: | ||
'.' joinstring ',' splitstring s |
'.' joinstring ',' splitstring s |
||
Hello.How.Are.You.Today</ |
Hello.How.Are.You.Today</syntaxhighlight> |
||
<tt>splitstring</tt> and <tt>joinstring</tt> also work with longer "delimiters": |
<tt>splitstring</tt> and <tt>joinstring</tt> also work with longer "delimiters": |
||
< |
<syntaxhighlight lang="j"> '"'([ ,~ ,) '","' joinstring ',' splitstring s |
||
"Hello","How","Are","You","Today"</ |
"Hello","How","Are","You","Today"</syntaxhighlight> |
||
But, of course, this could be solved with simple string replacement: |
|||
<syntaxhighlight lang="j"> rplc&',.' s |
|||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
The task asks us to ''Separate the string "Hello,How,Are,You,Today" by commas into an array (or list) so that each element of it stores a different word.'' but for many purposes the original string is an adequate data structure. Note also that given a string, a list of "word start" indices and "word length" integers can be logically equivalent to having an "array of words" -- and, depending on implementation details may be a superior or inferior choice to some other representation. But, in current definition of this task, the concept of "word length" plays no useful role. |
|||
Note also that J provides several built-in concepts of parsing: split on leading delimiter, split on trailing delimiter, split J language words. Also, it's sometimes more efficient to append to a string than to prepend to it. So a common practice for parsing on an embedded delimiter is to append a copy of the delimiter to the string and then use the appended result: |
|||
<syntaxhighlight lang="j"> fn;._2 string,','</syntaxhighlight> |
|||
Here '''fn''' is applied to each ',' delimited substring and the results are assembled into an array. |
|||
Or, factoring out the names: |
|||
<syntaxhighlight lang="j"> fn ((;._2)(@(,&','))) string</syntaxhighlight> |
|||
=={{header|Java}}== |
=={{header|Java}}== |
||
Line 686: | Line 2,076: | ||
The first is by splitting the String into an array of Strings. The separator is actually a regular expression so you could do very powerful things with this, but make sure to escape any characters with special meaning in regex. |
The first is by splitting the String into an array of Strings. The separator is actually a regular expression so you could do very powerful things with this, but make sure to escape any characters with special meaning in regex. |
||
{{works with|Java|1.8+}} |
|||
<syntaxhighlight lang="java5">String toTokenize = "Hello,How,Are,You,Today"; |
|||
System.out.println(String.join(".", toTokenize.split(",")));</syntaxhighlight> |
|||
{{works with|Java|1.4+}} |
{{works with|Java|1.4+}} |
||
< |
<syntaxhighlight lang="java5">String toTokenize = "Hello,How,Are,You,Today"; |
||
String words[] = toTokenize.split(",");//splits on one comma, multiple commas yield multiple splits |
String words[] = toTokenize.split(",");//splits on one comma, multiple commas yield multiple splits |
||
Line 694: | Line 2,089: | ||
for(int i=0; i<words.length; i++) { |
for(int i=0; i<words.length; i++) { |
||
System.out.print(words[i] + "."); |
System.out.print(words[i] + "."); |
||
}</ |
}</syntaxhighlight> |
||
The other way is to use StringTokenizer. It will skip any empty tokens. So if two commas are given in line, there will be an empty string in the array given by the split function, but no empty string with the StringTokenizer object. This method takes more code to use, but allows you to get tokens incrementally instead of all at once. |
The other way is to use StringTokenizer. It will skip any empty tokens. So if two commas are given in line, there will be an empty string in the array given by the split function, but no empty string with the StringTokenizer object. This method takes more code to use, but allows you to get tokens incrementally instead of all at once. |
||
{{works with|Java|1.0+}} |
{{works with|Java|1.0+}} |
||
< |
<syntaxhighlight lang="java5">String toTokenize = "Hello,How,Are,You,Today"; |
||
StringTokenizer tokenizer = new StringTokenizer(toTokenize, ","); |
StringTokenizer tokenizer = new StringTokenizer(toTokenize, ","); |
||
while(tokenizer.hasMoreTokens()) { |
while(tokenizer.hasMoreTokens()) { |
||
System.out.print(tokenizer.nextToken() + "."); |
System.out.print(tokenizer.nextToken() + "."); |
||
}</ |
}</syntaxhighlight> |
||
=={{header|JavaScript}}== |
=={{header|JavaScript}}== |
||
<syntaxhighlight lang="javascript">console.log( |
|||
{{works with|Firefox|2.0}} |
|||
"Hello,How,Are,You,Today" |
|||
.split(",") |
|||
.join(".") |
|||
);</syntaxhighlight>A more advanced program to tokenise strings:<syntaxhighlight lang="javascript" line="1"> |
|||
const Tokeniser = (function () { |
|||
const numberRegex = /-?(\d+\.d+|\d+\.|\.\d+|\d+)((e|E)(\+|-)?\d+)?/g; |
|||
return { |
|||
settings: { |
|||
operators: ["<", ">", "=", "+", "-", "*", "/", "?", "!"], |
|||
separators: [",", ".", ";", ":", " ", "\t", "\n"], |
|||
groupers: ["(", ")", "[", "]", "{", "}", '"', '"', "'", "'"], |
|||
keepWhiteSpacesAsTokens: false, |
|||
trimTokens: true |
|||
}, |
|||
isNumber: function (value) { |
|||
if (typeof value === "number") { |
|||
return true; |
|||
} else if (typeof value === "string") { |
|||
return numberRegex.test(value); |
|||
} |
|||
return false; |
|||
}, |
|||
closeGrouper: function (grouper) { |
|||
if (this.settings.groupers.includes(grouper)) { |
|||
return this.settings.groupers[this.settings.groupers.indexOf(grouper) + 1]; |
|||
} |
|||
return null; |
|||
}, |
|||
tokenType: function (char) { |
|||
if (this.settings.operators.includes(char)) { |
|||
return "operator"; |
|||
} else if (this.settings.separators.includes(char)) { |
|||
return "separator"; |
|||
} else if (this.settings.groupers.includes(char)) { |
|||
return "grouper"; |
|||
} |
|||
return "other"; |
|||
}, |
|||
parseString: function (str) { |
|||
if (typeof str !== "string") { |
|||
if (str === null) { |
|||
return "null"; |
|||
} if (typeof str === "object") { |
|||
str = JSON.stringify(str); |
|||
} else { |
|||
str = str.toString(); |
|||
} |
|||
} |
|||
let tokens = [], _tempToken = ""; |
|||
for (let i = 0; i < str.length; i++) { |
|||
if (this.tokenType(_tempToken) !== this.tokenType(str[i]) || this.tokenType(str[i]) === "separator") { |
|||
if (_tempToken.trim() !== "") { |
|||
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken); |
|||
} else if (this.settings.keepWhiteSpacesAsTokens) { |
|||
tokens.push(_tempToken); |
|||
} |
|||
_tempToken = str[i]; |
|||
if (this.tokenType(_tempToken) === "separator") { |
|||
if (_tempToken.trim() !== "") { |
|||
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken); |
|||
} else if (this.settings.keepWhiteSpacesAsTokens) { |
|||
tokens.push(_tempToken); |
|||
} |
|||
_tempToken = ""; |
|||
} |
|||
} else { |
|||
_tempToken += str[i]; |
|||
} |
|||
} |
|||
if (_tempToken.trim() !== "") { |
|||
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken); |
|||
} else if (this.settings.keepWhiteSpacesAsTokens) { |
|||
tokens.push(_tempToken); |
|||
} |
|||
return tokens.filter((token) => token !== ""); |
|||
} |
|||
}; |
|||
})(); |
|||
</syntaxhighlight>Output:<syntaxhighlight lang="javascript"> |
|||
Tokeniser.parseString("Hello,How,Are,You,Today"); |
|||
// -> ['Hello', ',', 'How', ',', 'Are', ',', 'You', ',', 'Today'] |
|||
</syntaxhighlight> |
|||
=={{header| |
=={{header|jq}}== |
||
<syntaxhighlight lang="jq">split(",") | join(".")</syntaxhighlight>Example:<syntaxhighlight lang="sh">$ jq -r 'split(",") | join(".")' |
|||
<lang lb>'Note that Liberty Basic's array usage can reach element #10 before having to DIM the array |
|||
"Hello,How,Are,You,Today" |
|||
For i = 0 To 4 |
|||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
array$ = array$ + array$(i) + "." |
|||
=={{header|Jsish}}== |
|||
Next i |
|||
Being in the ECMAScript family, Jsi is blessed with many easy to use character, string and array manipulation routines. |
|||
<syntaxhighlight lang="javascript">puts('Hello,How,Are,You,Today'.split(',').join('.'))</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Julia}}== |
|||
<syntaxhighlight lang="julia"> |
|||
s = "Hello,How,Are,You,Today" |
|||
a = split(s, ",") |
|||
t = join(a, ".") |
|||
println("The string \"", s, "\"") |
|||
println("Splits into ", a) |
|||
println("Reconstitutes to \"", t, "\"") |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
The string "Hello,How,Are,You,Today" |
|||
Splits into SubString{ASCIIString}["Hello","How","Are","You","Today"] |
|||
Reconstitutes to "Hello.How.Are.You.Today" |
|||
</pre> |
|||
=={{header|K}}== |
|||
<syntaxhighlight lang="k">words: "," \: "Hello,How,Are,You,Today" |
|||
"." /: words</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
{{works with|ngn/k}}<syntaxhighlight lang=K>","\"Hello,How,Are,You,Today" |
|||
("Hello" |
|||
"How" |
|||
"Are" |
|||
"You" |
|||
"Today")</syntaxhighlight> |
|||
=={{header|Klingphix}}== |
|||
<syntaxhighlight lang="klingphix">( "Hello,How,Are,You,Today" "," ) split len [ get print "." print ] for |
|||
nl "End " input</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today. |
|||
End</pre> |
|||
=={{header|Kotlin}}== |
|||
{{works with|Kotlin|1.0b4}} |
|||
<syntaxhighlight lang="scala">fun main(args: Array<String>) { |
|||
val input = "Hello,How,Are,You,Today" |
|||
println(input.split(',').joinToString(".")) |
|||
}</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Ksh}}== |
|||
<syntaxhighlight lang="ksh"> |
|||
#!/bin/ksh |
|||
# Tokenize a string |
|||
# # Variables: |
|||
# |
|||
string="Hello,How,Are,You,Today" |
|||
inputdelim=\, # a comma |
|||
outputdelim=\. # a period |
|||
# # Functions: |
|||
# |
|||
# # Function _tokenize(str, indelim, outdelim) |
|||
# |
|||
function _tokenize { |
|||
typeset _str ; _str="$1" |
|||
typeset _ind ; _ind="$2" |
|||
typeset _outd ; _outd="$3" |
|||
while [[ ${_str} != ${_str/${_ind}/${_outd}} ]]; do |
|||
_str=${_str/${_ind}/${_outd}} |
|||
done |
|||
echo "${_str}" |
|||
} |
|||
###### |
|||
# main # |
|||
###### |
|||
_tokenize "${string}" "${inputdelim}" "${outputdelim}"</syntaxhighlight> |
|||
{{out}}<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|LabVIEW}}== |
|||
To tokenize the string, we use the Search/Split String function to split the string by its first comma. Add the beginning (up to, but not including the comma) to the end of the array, remove the first comma from the rest of the string, and pass it back through the shift register to the loop's next iteration. This is repeated until the string is empty. Printing is a simple matter of concatenation.<br/> |
|||
{{VI solution|LabVIEW_Tokenize_a_string.png}} |
|||
=={{header|Lambdatalk}}== |
|||
<syntaxhighlight lang="scheme"> |
|||
{S.replace , by . in Hello,How,Are,You,Today}. |
|||
-> Hello.How.Are.You.Today. |
|||
</syntaxhighlight> |
|||
=={{header|Lang}}== |
|||
<syntaxhighlight lang="lang"> |
|||
$str = Hello,How,Are,You,Today |
|||
fn.println(fn.join(\., fn.split($str, \,))) |
|||
</syntaxhighlight> |
|||
=={{header|Lang5}}== |
|||
<syntaxhighlight lang="lang5">'Hello,How,Are,You,Today ', split '. join .</syntaxhighlight> |
|||
=={{header|LDPL}}== |
|||
<syntaxhighlight lang="ldpl"> |
|||
DATA: |
|||
explode/words is text vector |
|||
explode/index is number |
|||
explode/string is text |
|||
explode/length is number |
|||
explode/stringlength is number |
|||
explode/current-token is text |
|||
explode/char is text |
|||
explode/separator is text |
|||
i is number |
|||
PROCEDURE: |
|||
# Ask for a sentence |
|||
display "Enter a sentence: " |
|||
accept explode/string |
|||
# Declare explode Subprocedure |
|||
# Splits a text into a text vector by a certain delimiter |
|||
# Input parameters: |
|||
# - explode/string: the string to explode (destroyed) |
|||
# - explode/separator: the character used to separate the string (preserved) |
|||
# Output parameters: |
|||
# - explode/words: vector of splitted words |
|||
# - explode/length: length of explode/words |
|||
sub-procedure explode |
|||
join explode/string and explode/separator in explode/string |
|||
store length of explode/string in explode/stringlength |
|||
store 0 in explode/index |
|||
store 0 in explode/length |
|||
store "" in explode/current-token |
|||
while explode/index is less than explode/stringlength do |
|||
get character at explode/index from explode/string in explode/char |
|||
if explode/char is equal to explode/separator then |
|||
store explode/current-token in explode/words:explode/length |
|||
add explode/length and 1 in explode/length |
|||
store "" in explode/current-token |
|||
else |
|||
join explode/current-token and explode/char in explode/current-token |
|||
end if |
|||
add explode/index and 1 in explode/index |
|||
repeat |
|||
subtract 1 from explode/length in explode/length |
|||
end sub-procedure |
|||
# Separate the entered string |
|||
store " " in explode/separator |
|||
call sub-procedure explode |
|||
while i is less than or equal to explode/length do |
|||
display explode/words:i crlf |
|||
add 1 and i in i |
|||
repeat |
|||
</syntaxhighlight> |
|||
=={{header|LFE}}== |
|||
<syntaxhighlight lang="lisp"> |
|||
> (set split (string:tokens "Hello,How,Are,You,Today" ",")) |
|||
("Hello" "How" "Are" "You" "Today") |
|||
> (string:join split ".") |
|||
"Hello.How.Are.You.Today" |
|||
</syntaxhighlight> |
|||
=={{header|Lingo}}== |
|||
Print Left$(array$, (Len(array$) - 1))</lang> |
|||
<syntaxhighlight lang="lingo">input = "Hello,How,Are,You,Today" |
|||
_player.itemDelimiter = "," |
|||
output = "" |
|||
repeat with i = 1 to input.item.count |
|||
put input.item[i]&"." after output |
|||
end repeat |
|||
delete the last char of output |
|||
put output |
|||
-- "Hello.How.Are.You.Today"</syntaxhighlight> |
|||
=={{header|Logo}}== |
=={{header|Logo}}== |
||
{{works with|UCB Logo}} |
{{works with|UCB Logo}} |
||
< |
<syntaxhighlight lang="logo">to split :str :sep |
||
output parse map [ifelse ? = :sep ["| |] [?]] :str |
output parse map [ifelse ? = :sep ["| |] [?]] :str |
||
end</ |
end</syntaxhighlight> |
||
This form is more robust, doing the right thing if there are embedded spaces. |
This form is more robust, doing the right thing if there are embedded spaces. |
||
< |
<syntaxhighlight lang="logo">to split :str :by [:acc []] [:w "||] |
||
if empty? :str [output lput :w :acc] |
if empty? :str [output lput :w :acc] |
||
ifelse equal? first :str :by ~ |
ifelse equal? first :str :by ~ |
||
[output (split butfirst :str :by lput :w :acc)] ~ |
[output (split butfirst :str :by lput :w :acc)] ~ |
||
[output (split butfirst :str :by :acc lput first :str :w)] |
[output (split butfirst :str :by :acc lput first :str :w)] |
||
end</ |
end</syntaxhighlight> |
||
< |
<syntaxhighlight lang="logo">? show split "Hello,How,Are,You,Today ", |
||
[Hello How Are You Today]</ |
[Hello How Are You Today]</syntaxhighlight> |
||
=={{header|Lua}}== |
|||
<lang lua>require"re" |
|||
=={{header|Logtalk}}== |
|||
record = re.compile[[ |
|||
Using Logtalk built-in support for Definite Clause Grammars (DCGs) and representing the strings as atoms for readbility: |
|||
record <- ( <field> (',' <field>)* ) -> {} (%nl / !.) |
|||
<syntaxhighlight lang="logtalk"> |
|||
field <- <escaped> / <nonescaped> |
|||
:- object(spliting). |
|||
nonescaped <- { [^,"%nl]* } |
|||
escaped <- '"' {~ ([^"] / '""' -> '"')* ~} '"' |
|||
]] |
|||
:- public(convert/2). |
|||
print(unpack(record:match"hello,how,are,you,today"))</lang> |
|||
:- mode(convert(+atom, -atom), one). |
|||
A different solution using the string-library of Lua: |
|||
<lang lua>str = "Hello,How,Are,You,Today" |
|||
convert(StringIn, StringOut) :- |
|||
tokens = {} |
|||
atom_chars(StringIn, CharactersIn), |
|||
for w in string.gmatch( str, "(%a+)" ) do |
|||
phrase(split(',', Tokens), CharactersIn), |
|||
tokens[#tokens+1] = w |
|||
phrase(split('.', Tokens), CharactersOut), |
|||
end |
|||
atom_chars(StringOut, CharactersOut). |
|||
split(Separator, [t([Character| Characters])| Tokens]) --> |
|||
for i = 1, #tokens do |
|||
[Character], {Character \== Separator}, split(Separator, [t(Characters)| Tokens]). |
|||
print( tokens[i] ) |
|||
split(Separator, [t([])| Tokens]) --> |
|||
end</lang> |
|||
[Separator], split(Separator, Tokens). |
|||
split(_, [t([])]) --> |
|||
[]. |
|||
% the look-ahead in the next rule prevents adding a spurious separator at the end |
|||
split(_, []), [Character] --> |
|||
[Character]. |
|||
:- end_object. |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
| ?- spliting::convert('Hello,How,Are,You,Today', Converted). |
|||
Converted = 'Hello.How.Are.You.Today' |
|||
yes |
|||
</pre> |
|||
=={{header| |
=={{header|Lua}}== |
||
Split function callously stolen from the lua-users wiki |
|||
<lang Mathematica>Row[Riffle[StringSplit["Hello,How,Are,You,Today", ","], "."]]</lang> |
|||
<syntaxhighlight lang="lua">function string:split (sep) |
|||
local sep, fields = sep or ":", {} |
|||
local pattern = string.format("([^%s]+)", sep) |
|||
self:gsub(pattern, function(c) fields[#fields+1] = c end) |
|||
return fields |
|||
end |
|||
local str = "Hello,How,Are,You,Today" |
|||
print(table.concat(str:split(","), "."))</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|M2000 Interpreter}}== |
|||
<syntaxhighlight lang="m2000 interpreter"> |
|||
Module CheckIt { |
|||
Function Tokenize$(s){ |
|||
\\ letter$ pop a string from stack of values |
|||
\\ shift 2 swap top two values on stack of values |
|||
fold1=lambda m=1 ->{ |
|||
shift 2 :if m=1 then m=0:drop: push letter$ else push letter$+"."+letter$ |
|||
} |
|||
=s#fold$(fold1) |
|||
} |
|||
Print Tokenize$(piece$("Hello,How,Are,You,Today",",")) ="Hello.How.Are.You.Today" ' true |
|||
} |
|||
Checkit |
|||
</syntaxhighlight> |
|||
=={{header|M4}}== |
=={{header|M4}}== |
||
< |
<syntaxhighlight lang="m4">define(`s',`Hello,How,Are,You,Today') |
||
define(`set',`define(`$1[$2]',`$3')') |
define(`set',`define(`$1[$2]',`$3')') |
||
define(`get',`defn($1[$2])') |
define(`get',`defn($1[$2])') |
||
Line 774: | Line 2,470: | ||
define(`show', |
define(`show', |
||
`ifelse(eval(j<n),1,`get(a,j).`'define(`j',incr(j))`'show')') |
`ifelse(eval(j<n),1,`get(a,j).`'define(`j',incr(j))`'show')') |
||
show</ |
show</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
<pre> |
||
Hello.How.Are.You.Today. |
Hello.How.Are.You.Today. |
||
</pre> |
</pre> |
||
=={{header| |
=={{header|Maple}}== |
||
<syntaxhighlight lang="maple">StringTools:-Join(StringTools:-Split("Hello,How,Are,You,Today", ","),".");</syntaxhighlight> |
|||
<lang MATLAB>function tokenizeString(string,delimeter) |
|||
{{Out|Output}} |
|||
<pre>"Hello.How.Are.You.Today"</pre> |
|||
=={{header|Mathematica}}/{{header|Wolfram Language}}== |
|||
tokens = {}; |
|||
<syntaxhighlight lang="mathematica">StringJoin@StringSplit["Hello,How,Are,You,Today", "," -> "."]</syntaxhighlight> |
|||
while not(isempty(string)) |
|||
[tokens{end+1},string] = strtok(string,delimeter); |
|||
end |
|||
for i = (1:numel(tokens)-1) |
|||
fprintf([tokens{i} '.']) |
|||
end |
|||
fprintf([tokens{end} '\n']) |
|||
end</lang> |
|||
=={{header|MATLAB}} / {{header|Octave}}== |
|||
Output: |
|||
<syntaxhighlight lang="matlab"> |
|||
<lang MATLAB>>> tokenizeString('Hello,How,Are,You,Today',',') |
|||
Hello |
s=strsplit('Hello,How,Are,You,Today',',') |
||
fprintf(1,'%s.',s{:}) |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today. |
|||
</pre> |
|||
=={{header|Maxima}}== |
|||
<syntaxhighlight lang="maxima">l: split("Hello,How,Are,You,Today", ",")$ |
|||
printf(true, "~{~a~^.~}~%", l)$</syntaxhighlight> |
|||
A slightly different way |
|||
<syntaxhighlight lang="maxima"> |
|||
split("Hello,How,Are,You,Today",",")$ |
|||
simplode(%,"."); |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
=={{header|MAXScript}}== |
=={{header|MAXScript}}== |
||
< |
<syntaxhighlight lang="maxscript">output = "" |
||
for word in (filterString "Hello,How,Are,You,Today" ",") do |
for word in (filterString "Hello,How,Are,You,Today" ",") do |
||
( |
( |
||
output += (word + ".") |
output += (word + ".") |
||
) |
) |
||
format "%\n" output</ |
format "%\n" output</syntaxhighlight> |
||
=={{header|Mercury}}== |
|||
<syntaxhighlight lang="text"> |
|||
:- module string_tokenize. |
|||
:- interface. |
|||
:- import_module io. |
|||
:- pred main(io::di, io::uo) is det. |
|||
:- implementation. |
|||
:- import_module list, string. |
|||
main(!IO) :- |
|||
Tokens = string.split_at_char((','), "Hello,How,Are,You,Today"), |
|||
io.write_list(Tokens, ".", io.write_string, !IO), |
|||
io.nl(!IO).</syntaxhighlight> |
|||
=={{header|min}}== |
|||
{{works with|min|0.19.3}} |
|||
<syntaxhighlight lang="min">"Hello,How,Are,You,Today" "," split "." join print</syntaxhighlight> |
|||
=={{header|MiniScript}}== |
|||
<syntaxhighlight lang="miniscript">tokens = "Hello,How,Are,You,Today".split(",") |
|||
print tokens.join(".")</syntaxhighlight> |
|||
=={{header|MMIX}}== |
=={{header|MMIX}}== |
||
< |
<syntaxhighlight lang="mmix">sep IS ',' |
||
EOS IS 0 |
EOS IS 0 |
||
NL IS 10 |
NL IS 10 |
||
Line 863: | Line 2,596: | ||
LDBU t,tp |
LDBU t,tp |
||
PBNZ t,2B % UNTIL EOB(uffer) |
PBNZ t,2B % UNTIL EOB(uffer) |
||
TRAP 0,Halt,0</ |
TRAP 0,Halt,0</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
|||
<pre>~/MIX/MMIX/Progs> mmix tokenizing |
|||
~/MIX/MMIX/Progs> mmix tokenizing |
|||
Hello |
|||
Hello |
|||
How |
|||
How |
|||
Are |
|||
Are |
|||
You |
|||
You |
|||
Today</pre> |
|||
Today |
|||
</pre> |
|||
=={{header|Modula-3}}== |
=={{header|Modula-3}}== |
||
< |
<syntaxhighlight lang="modula3">MODULE Tokenize EXPORTS Main; |
||
IMPORT IO, TextConv; |
IMPORT IO, TextConv; |
||
Line 890: | Line 2,625: | ||
END; |
END; |
||
IO.Put("\n"); |
IO.Put("\n"); |
||
END Tokenize.</ |
END Tokenize.</syntaxhighlight> |
||
=={{header|MUMPS}}== |
=={{header|MUMPS}}== |
||
< |
<syntaxhighlight lang="mumps">TOKENS |
||
NEW I,J,INP |
NEW I,J,INP |
||
SET INP="Hello,how,are,you,today" |
SET INP="Hello,how,are,you,today" |
||
Line 898: | Line 2,634: | ||
NEW J FOR J=1:1:I WRITE INP(J) WRITE:J'=I "." |
NEW J FOR J=1:1:I WRITE INP(J) WRITE:J'=I "." |
||
KILL I,J,INP // Kill is optional. "New" variables automatically are killed on "Quit" |
KILL I,J,INP // Kill is optional. "New" variables automatically are killed on "Quit" |
||
QUIT</ |
QUIT</syntaxhighlight> |
||
In use: |
In use: |
||
USER>D TOKENS^ROSETTA |
|||
Hello.how.are.you.today</pre> |
|||
Hello.how.are.you.today |
|||
=={{header|Nanoquery}}== |
|||
<syntaxhighlight lang="nanoquery">for word in "Hello,How,Are,You,Today".split(",") |
|||
print word + "." |
|||
end</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today.</pre> |
|||
=={{header|Nemerle}}== |
=={{header|Nemerle}}== |
||
< |
<syntaxhighlight lang="nemerle">using System; |
||
using System.Console; |
using System.Console; |
||
using Nemerle.Utility.NString; |
using Nemerle.Utility.NString; |
||
Line 917: | Line 2,661: | ||
// a quick in place list comprehension takes care of that |
// a quick in place list comprehension takes care of that |
||
} |
} |
||
}</ |
}</syntaxhighlight> |
||
=={{header|NetRexx}}== |
|||
<syntaxhighlight lang="netrexx">/*NetRexx program ***************************************************** |
|||
* 20.08.2012 Walter Pachl derived from REXX Version 3 |
|||
**********************************************************************/ |
|||
sss='Hello,How,Are,You,Today' |
|||
Say 'input string='sss |
|||
Say '' |
|||
Say 'Words in the string:' |
|||
ss =sss.translate(' ',',') |
|||
Loop i=1 To ss.words() |
|||
Say ss.word(i)'.' |
|||
End |
|||
Say 'End-of-list.'</syntaxhighlight> |
|||
Output as in REXX version |
|||
=={{header|NewLISP}}== |
|||
<syntaxhighlight lang="newlisp">(print (join (parse "Hello,How,Are,You,Today" ",") "."))</syntaxhighlight> |
|||
=={{header|Nial}}== |
|||
Example for <b>Q'Nial7</b>, using <code>set "nodecor</code> and <code>set "diagram</code> switches for better display of the array structure: |
|||
Define Array with input string: |
|||
<syntaxhighlight lang="nial"> s := 'Hello,How,Are,You,Today' |
|||
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |
|||
|H|e|l|l|o|,|H|o|w|,|A|r|e|,|Y|o|u|,|T|o|d|a|y| |
|||
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+</syntaxhighlight> |
|||
Split string at the commas: |
|||
<syntaxhighlight lang="nial"> t := s eachall = `, cut s |
|||
+-----------+-------+-------+-------+-----------+ |
|||
|+-+-+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+-+-+| |
|||
||H|e|l|l|o|||H|o|w|||A|r|e|||Y|o|u|||T|o|d|a|y|| |
|||
|+-+-+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+-+-+| |
|||
+-----------+-------+-------+-------+-----------+</syntaxhighlight> |
|||
Join string with <code>.</code> and remove last <code>.</code> |
|||
<syntaxhighlight lang="nial"> u := front content (cart t `.) |
|||
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |
|||
|H|e|l|l|o|.|H|o|w|.|A|r|e|.|Y|o|u|.|T|o|d|a|y| |
|||
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+</syntaxhighlight> |
|||
Less cluttered display, using <code>set "sketch;set "nodecor</code> display switches. |
|||
<syntaxhighlight lang="nial"> s:='Hello,How,Are,You,Today' |
|||
Hello,How,Are,You,Today |
|||
t:= s eachall = `, cut s |
|||
+-----+---+---+---+-----+ |
|||
|Hello|How|Are|You|Today| |
|||
+-----+---+---+---+-----+ |
|||
u:=front content (cart t `.) |
|||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
Or as a one-liner: |
|||
<syntaxhighlight lang="nial"> |
|||
front content (cart (s eachall = `, cut s) `.) |
|||
</syntaxhighlight> |
|||
=={{header|Nim}}== |
|||
<syntaxhighlight lang="nim">import strutils |
|||
let text = "Hello,How,Are,You,Today" |
|||
let tokens = text.split(',') |
|||
echo tokens.join(".")</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Objeck}}== |
|||
<syntaxhighlight lang="objeck"> |
|||
class Parse { |
|||
function : Main(args : String[]) ~ Nil { |
|||
tokens := "Hello,How,Are,You,Today"->Split(","); |
|||
each(i : tokens) { |
|||
tokens[i]->PrintLine(); |
|||
}; |
|||
} |
|||
}</syntaxhighlight> |
|||
=={{header|Objective-C}}== |
=={{header|Objective-C}}== |
||
Line 924: | Line 2,752: | ||
{{works with|Cocoa}} |
{{works with|Cocoa}} |
||
< |
<syntaxhighlight lang="objc">NSString *text = @"Hello,How,Are,You,Today"; |
||
NSArray *tokens = [text componentsSeparatedByString:@","]; |
NSArray *tokens = [text componentsSeparatedByString:@","]; |
||
NSString *result = [tokens componentsJoinedByString:@"."]; |
NSString *result = [tokens componentsJoinedByString:@"."]; |
||
NSLog(result);</ |
NSLog(result);</syntaxhighlight> |
||
=={{header|Objeck}}== |
|||
<lang objeck> |
|||
bundle Default { |
|||
class Parse { |
|||
function : Main(args : String[]) ~ Nil { |
|||
tokens := "Hello,How,Are,You,Today"->Split(","); |
|||
each(i : tokens) { |
|||
tokens[i]->PrintLine(); |
|||
}; |
|||
} |
|||
} |
|||
} |
|||
</lang> |
|||
=={{header|OCaml}}== |
=={{header|OCaml}}== |
||
To split on a single-character separator: |
To split on a single-character separator: |
||
<syntaxhighlight lang="ocaml">let words = String.split_on_char ',' "Hello,How,Are,You,Today" in |
|||
<lang ocaml>let rec split_char sep str = |
|||
String.concat "." words |
|||
try |
|||
</syntaxhighlight> |
|||
let i = String.index str sep in |
|||
String.sub str 0 i :: |
|||
split_char sep (String.sub str (i+1) (String.length str - i - 1)) |
|||
with Not_found -> |
|||
[str]</lang> |
|||
The function split_on_char has been introduced in OCaml 4.04. In previous versions, it could be implemented by: |
|||
Or the [[:Category:Recursion|tail-recursive]] equivalent: |
|||
<syntaxhighlight lang="ocaml">let split_on_char sep s = |
|||
<lang ocaml>(* [try .. with] structures break tail-recursion, |
|||
let r = ref [] in |
|||
so we externalise it in a sub-function *) |
|||
let j = ref (String.length s) in |
|||
let string_index str c = |
|||
for i = String.length s - 1 downto 0 do |
|||
if s.[i] = sep then begin |
|||
with Not_found -> None |
|||
r := String.sub s (i + 1) (!j - i - 1) :: !r; |
|||
j := i |
|||
end |
|||
done; |
|||
String.sub s 0 !j :: !r</syntaxhighlight> |
|||
=={{header|Oforth}}== |
|||
let split_char sep str = |
|||
let rec aux acc str = |
|||
match string_index str sep with |
|||
| Some i -> |
|||
let this = String.sub str 0 i |
|||
and next = String.sub str (i+1) (String.length str - i - 1) in |
|||
aux (this::acc) next |
|||
| None -> |
|||
List.rev(str::acc) |
|||
in |
|||
aux [] str |
|||
;;</lang> |
|||
<syntaxhighlight lang="oforth">"Hello,How,Are,You,Today" wordsWith(',') println</syntaxhighlight> |
|||
But both of these will process extraneous String.sub (so one string alloc) to generate the "rest of the string" each time to pass to the next call. For N tokens there will be (N - 2) unneeded allocs. To resolve this here is a version which keeps track of the index in the string we will look next: |
|||
{{out}} |
|||
<lang ocaml>let split_char sep str = |
|||
<pre> |
|||
let string_index_from i = |
|||
[Hello, How, Are, You, Today] |
|||
try Some (String.index_from str i sep) |
|||
</pre> |
|||
with Not_found -> None |
|||
in |
|||
let rec aux i acc = match string_index_from i with |
|||
| Some i' -> |
|||
let w = String.sub str i (i' - i) in |
|||
aux (succ i') (w::acc) |
|||
| None -> |
|||
let w = String.sub str i (String.length str - i) in |
|||
List.rev (w::acc) |
|||
in |
|||
aux 0 []</lang> |
|||
Splitting on a string separator using the regular expressions library: |
|||
<lang ocaml>#load "str.cma";; |
|||
let split_str sep str = |
|||
Str.split (Str.regexp_string sep) str</lang> |
|||
=={{header|ooRexx}}== |
|||
There is already a library function for joining: |
|||
<syntaxhighlight lang="oorexx">text='Hello,How,Are,You,Today' |
|||
<lang ocaml>String.concat sep strings</lang> |
|||
do while text \= '' |
|||
parse var text word1 ',' text |
|||
call charout 'STDOUT:',word1'.' |
|||
end</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today.</pre> |
|||
=={{header|OpenEdge/Progress}}== |
=={{header|OpenEdge/Progress}}== |
||
< |
<syntaxhighlight lang="progress">FUNCTION tokenizeString RETURNS CHAR ( |
||
i_c AS CHAR |
i_c AS CHAR |
||
): |
): |
||
Line 1,023: | Line 2,818: | ||
MESSAGE |
MESSAGE |
||
tokenizeString( "Hello,How,Are,You,Today" ) |
tokenizeString( "Hello,How,Are,You,Today" ) |
||
VIEW-AS ALERT-BOX.</ |
VIEW-AS ALERT-BOX.</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
<pre> |
||
--------------------------- |
--------------------------- |
||
Message |
Message |
||
--------------------------- |
--------------------------- |
||
Hello.How.Are.You.Today |
Hello.How.Are.You.Today |
||
--------------------------- |
--------------------------- |
||
OK |
OK |
||
--------------------------- |
--------------------------- |
||
</pre> |
</pre> |
||
=={{header|Oz}}== |
=={{header|Oz}}== |
||
< |
<syntaxhighlight lang="oz">for T in {String.tokens "Hello,How,Are,You,Today" &,} do |
||
{System.printInfo T#"."} |
{System.printInfo T#"."} |
||
end</ |
end</syntaxhighlight> |
||
=={{header|PARI/GP}}== |
|||
===Version #1.=== |
|||
Simple version, like the most custom ones here (for this task). This version has 1 character delimiter, |
|||
which is not allowed in the beginning and at the end of string, in addition, double, triple, etc., delimiters |
|||
are not allowed too. |
|||
{{Works with|PARI/GP|2.7.4 and above}} |
|||
<syntaxhighlight lang="parigp"> |
|||
\\ Tokenize a string str according to 1 character delimiter d. Return a list of tokens. |
|||
\\ Using ssubstr() from http://rosettacode.org/wiki/Substring#PARI.2FGP |
|||
\\ tokenize() 3/5/16 aev |
|||
tokenize(str,d)={ |
|||
my(str=Str(str,d),vt=Vecsmall(str),d1=sasc(d),Lr=List(),sn=#str,v1,p1=1); |
|||
for(i=p1,sn, v1=vt[i]; if(v1==d1, listput(Lr,ssubstr(str,p1,i-p1)); p1=i+1)); |
|||
return(Lr); |
|||
} |
|||
{ |
|||
\\ TEST |
|||
print(" *** Testing tokenize from Version #1:"); |
|||
print("1.", tokenize("Hello,How,Are,You,Today",",")); |
|||
\\ BOTH 2 & 3 are NOT OK!! |
|||
print("2.",tokenize("Hello,How,Are,You,Today,",",")); |
|||
print("3.",tokenize(",Hello,,How,Are,You,Today",",")); |
|||
} |
|||
</syntaxhighlight> |
|||
{{Output}} |
|||
<pre> |
|||
*** Testing tokenize from Version #1: |
|||
1.List(["Hello", "How", "Are", "You", "Today"]) |
|||
2.List(["Hello", "How", "Are", "You", "Today", ","]) |
|||
3.List([",Hello,,How,Are,You,Today,", "Hello", ",How,Are,You,Today,", "How", "Ar |
|||
e", "You", "Today"]) |
|||
</pre> |
|||
===Version #2.=== |
|||
Advanced version. Delimiter is allowed in any place. In addition, multiple delimiters are allowed too. |
|||
This is really useful for considering omitted data. |
|||
This version can be used for positional parameters processing, or for processing data from tables with string rows. |
|||
{{Works with|PARI/GP|2.7.4 and above}} |
|||
<syntaxhighlight lang="parigp"> |
|||
\\ Tokenize a string str according to 1 character delimiter d. Return a list of tokens. |
|||
\\ Using ssubstr() from http://rosettacode.org/wiki/Substring#PARI.2FGP |
|||
\\ stok() 3/5/16 aev |
|||
stok(str,d)={ |
|||
my(d1c=ssubstr(d,1,1),str=Str(str,d1c),vt=Vecsmall(str),d1=sasc(d1c), |
|||
Lr=List(),sn=#str,v1,p1=1,vo=32); |
|||
if(sn==1, return(List(""))); if(vt[sn-1]==d1,sn--); |
|||
for(i=1,sn, v1=vt[i]; |
|||
if(v1!=d1, vo=v1; next); |
|||
if(vo==d1||i==1, listput(Lr,""); p1=i+1; vo=v1; next); |
|||
if(i-p1>0, listput(Lr,ssubstr(str,p1,i-p1)); p1=i+1); |
|||
vo=v1; |
|||
); |
|||
return(Lr); |
|||
} |
|||
{ |
|||
\\ TEST |
|||
print(" *** Testing stok from Version #2:"); |
|||
\\ pp - positional parameter(s) |
|||
print("1. 5 pp: ", stok("Hello,How,Are,You,Today",",")); |
|||
print("2. 5 pp: ", stok("Hello,How,Are,You,Today,",",")); |
|||
print("3. 9 pp: ", stok(",,Hello,,,How,Are,You,Today",",")); |
|||
print("4. 6 pp: ", stok(",,,,,,",",")); |
|||
print("5. 1 pp: ", stok(",",",")); |
|||
print("6. 1 pp: ", stok("Hello-o-o??",",")); |
|||
print("7. 0 pp: ", stok("",",")); |
|||
} |
|||
</syntaxhighlight> |
|||
{{Output}} |
|||
<pre> |
|||
*** Testing stok from Version #2: |
|||
1. 5 pp: List(["Hello", "How", "Are", "You", "Today"]) |
|||
2. 5 pp: List(["Hello", "How", "Are", "You", "Today"]) |
|||
3. 9 pp: List(["", "", "Hello", "", "", "How", "Are", "You", "Today"]) |
|||
4. 6 pp: List(["", "", "", "", "", ""]) |
|||
5. 1 pp: List([""]) |
|||
6. 1 pp: List(["Hello-o-o??"]) |
|||
7. 0 pp: List([""]) |
|||
</pre> |
|||
=={{header|Pascal}}== |
=={{header|Pascal}}== |
||
{{works with|Free_Pascal}} |
|||
See [[Tokenize_a_string#Delphi | Delphi]] |
|||
<syntaxhighlight lang="pascal">program TokenizeString; |
|||
{$mode objfpc}{$H+} |
|||
uses |
|||
SysUtils, Classes; |
|||
const |
|||
TestString = 'Hello,How,Are,You,Today'; |
|||
var |
|||
Tokens: TStringList; |
|||
I: Integer; |
|||
begin |
|||
// Uses FCL facilities, "harder" algorithm not implemented |
|||
Tokens := TStringList.Create; |
|||
try |
|||
Tokens.Delimiter := ','; |
|||
Tokens.DelimitedText := TestString; |
|||
Tokens.Delimiter := '.'; // For example |
|||
// To standard Output |
|||
WriteLn(Format('Tokenize from: "%s"', [TestString])); |
|||
WriteLn(Format('to: "%s"',[Tokens.DelimitedText])); |
|||
finally |
|||
Tokens.Free; |
|||
end; |
|||
end.</syntaxhighlight> |
|||
The result is: |
|||
Tokenize from: "Hello,How,Are,You,Today" |
|||
to: "Hello.How.Are.You.Today" |
|||
=={{header|Perl}}== |
=={{header|Perl}}== |
||
< |
<syntaxhighlight lang="perl">print join('.', split /,/, 'Hello,How,Are,You,Today'), "\n";</syntaxhighlight> |
||
CLI one-liner form: |
|||
<syntaxhighlight lang="perl">echo "Hello,How,Are,You,Today" | perl -aplF/,/ -e '$" = "."; $_ = "@F";'</syntaxhighlight> |
|||
which is a compact way of telling Perl to do |
|||
<syntaxhighlight lang="perl">BEGIN { $/ = "\n"; $\ = "\n"; } |
|||
LINE: while (defined($_ = <ARGV>)) { |
|||
chomp $_; |
|||
our(@F) = split(/,/, $_, 0); |
|||
$" = '.'; |
|||
$_ = "@F"; |
|||
} |
|||
continue { |
|||
die "-p destination: $!\n" unless print $_; |
|||
}</syntaxhighlight> |
|||
=={{header| |
=={{header|Phix}}== |
||
<!--<syntaxhighlight lang="phix">(phixonline)--> |
|||
{{works with|Rakudo|#22 "Thousand Oaks"}} |
|||
<span style="color: #0000FF;">?</span><span style="color: #7060A8;">join</span><span style="color: #0000FF;">(</span><span style="color: #7060A8;">split</span><span style="color: #0000FF;">(</span><span style="color: #008000;">"Hello,How,Are,You,Today"</span><span style="color: #0000FF;">,</span><span style="color: #008000;">","</span><span style="color: #0000FF;">),</span><span style="color: #008000;">"."</span><span style="color: #0000FF;">)</span> |
|||
<lang perl6>'Hello,How,Are,You,Today'.split(',').join('.').say;</lang> |
|||
<!--</syntaxhighlight>--> |
|||
{{Out}} |
|||
<pre> |
|||
"Hello.How.Are.You.Today" |
|||
</pre> |
|||
=={{header| |
=={{header|Phixmonti}}== |
||
<syntaxhighlight lang="phixmonti">/# "Hello,How,Are,You,Today" "," "." subst print #/ |
|||
<lang PicoLisp>(mapcar pack |
|||
"Hello,How,Are,You,Today" "," " " subst split len for get print "." print endfor</syntaxhighlight> |
|||
=={{header|Pike}}== |
|||
<lang pike>("Hello,How,Are,You,Today" / ",") * ".";</lang> |
|||
=={{header|PHP}}== |
=={{header|PHP}}== |
||
{{works with|PHP|5.x}} |
{{works with|PHP|5.x}} |
||
< |
<syntaxhighlight lang="php"><?php |
||
$str = 'Hello,How,Are,You,Today'; |
$str = 'Hello,How,Are,You,Today'; |
||
echo implode('.', explode(',', $str)); |
echo implode('.', explode(',', $str)); |
||
?></ |
?></syntaxhighlight> |
||
=={{header|Picat}}== |
|||
Using the built-in functions <code>split/2</code> and <code>join/2</code>. |
|||
<syntaxhighlight lang="picat">import util. |
|||
go => |
|||
S = "Hello,How,Are,You,Today", |
|||
T = S.split(","), |
|||
println(T), |
|||
T.join(".").println(), |
|||
% As a one liner: |
|||
S.split(",").join(".").println().</syntaxhighlight> |
|||
{{out}} |
|||
<pre>[Hello,How,Are,You,Today] |
|||
Hello.How.Are.You.Today |
|||
Hello.How.Are.You.Today</pre> |
|||
=={{header|PicoLisp}}== |
|||
<syntaxhighlight lang="picolisp">(mapcar pack |
|||
(split (chop "Hello,How,Are,You,Today") ",") )</syntaxhighlight> |
|||
=={{header|Pike}}== |
|||
<syntaxhighlight lang="pike">("Hello,How,Are,You,Today" / ",") * ".";</syntaxhighlight> |
|||
=={{header|PL/I}}== |
=={{header|PL/I}}== |
||
<syntaxhighlight lang="pli">tok: Proc Options(main); |
|||
<lang PL/I> |
|||
declare s character (100) initial ('Hello,How,Are,You,Today'); |
declare s character (100) initial ('Hello,How,Are,You,Today'); |
||
declare n fixed binary (31); |
declare n fixed binary (31); |
||
Line 1,087: | Line 3,039: | ||
put skip list (string(table)); |
put skip list (string(table)); |
||
end; |
end; |
||
end;</syntaxhighlight> |
|||
</lang> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|PL/M}}== |
|||
<syntaxhighlight lang="plm">100H: |
|||
/* CP/M CALLS */ |
|||
BDOS: PROCEDURE (FN, ARG); DECLARE FN BYTE, ARG ADDRESS; GO TO 5; END BDOS; |
|||
EXIT: PROCEDURE; CALL BDOS(0,0); END EXIT; |
|||
PRINT: PROCEDURE (S); DECLARE S ADDRESS; CALL BDOS(9,S); END PRINT; |
|||
/* SPLIT A STRING ON CHARACTER 'SEP'. |
|||
THE 'PARTS' ARRAY WILL CONTAIN POINTERS TO THE START OF EACH ELEMENT. |
|||
THE AMOUNT OF PARTS IS RETURNED. |
|||
*/ |
|||
TOKENIZE: PROCEDURE (SEP, STR, PARTS) ADDRESS; |
|||
DECLARE SEP BYTE, (STR, PARTS) ADDRESS; |
|||
DECLARE (N, P BASED PARTS) ADDRESS; |
|||
DECLARE CH BASED STR BYTE; |
|||
N = 0; |
|||
LOOP: |
|||
P(N) = STR; |
|||
N = N + 1; |
|||
DO WHILE CH <> '$' AND CH <> SEP; |
|||
STR = STR + 1; |
|||
END; |
|||
IF CH = '$' THEN RETURN N; |
|||
CH = '$'; |
|||
STR = STR + 1; |
|||
GO TO LOOP; |
|||
END TOKENIZE; |
|||
/* TEST ON THE GIVEN INPUT */ |
|||
DECLARE HELLO (24) BYTE INITIAL ('HELLO,HOW,ARE,YOU,TODAY$'); |
|||
DECLARE PARTS (10) ADDRESS; |
|||
DECLARE (I, LEN) ADDRESS; |
|||
LEN = TOKENIZE(',', .HELLO, .PARTS); |
|||
DO I = 0 TO LEN-1; |
|||
CALL PRINT(PARTS(I)); |
|||
CALL PRINT(.'. $'); |
|||
END; |
|||
CALL EXIT; |
|||
EOF;</syntaxhighlight> |
|||
{{out}} |
|||
<pre>HELLO. HOW. ARE. YOU. TODAY. </pre> |
|||
=={{header|Plain English}}== |
|||
<syntaxhighlight lang="plainenglish">To run: |
|||
Start up. |
|||
Split "Hello,How,Are,You,Today" into some string things given the comma byte. |
|||
Join the string things with the period byte giving a string. |
|||
Destroy the string things. |
|||
Write the string on the console. |
|||
Wait for the escape key. |
|||
Shut down. |
|||
To join some string things with a byte giving a string: |
|||
Get a string thing from the string things. |
|||
Loop. |
|||
If the string thing is nil, exit. |
|||
Append the string thing's string to the string. |
|||
If the string thing's next is not nil, append the byte to the string. |
|||
Put the string thing's next into the string thing. |
|||
Repeat.</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|Pop11}}== |
=={{header|Pop11}}== |
||
Line 1,096: | Line 3,117: | ||
First show the use of sysparse_string to break up a string and make a list of strings. |
First show the use of sysparse_string to break up a string and make a list of strings. |
||
< |
<syntaxhighlight lang="pop11">;;; Make a list of strings from a string using space as separator |
||
lvars list; |
lvars list; |
||
sysparse_string('the cat sat on the mat') -> list; |
sysparse_string('the cat sat on the mat') -> list; |
||
;;; print the list of strings |
;;; print the list of strings |
||
list => |
list => |
||
** [the cat sat on the mat]</ |
** [the cat sat on the mat]</syntaxhighlight> |
||
By giving it an extra parameter 'true' we can make it recognize numbers and produce a list of strings and numbers |
By giving it an extra parameter 'true' we can make it recognize numbers and produce a list of strings and numbers |
||
< |
<syntaxhighlight lang="pop11">lvars list; |
||
sysparse_string('one 1 two 2 three 3 four 4', true) -> list; |
sysparse_string('one 1 two 2 three 3 four 4', true) -> list; |
||
;;; print the list of strings and numbers |
;;; print the list of strings and numbers |
||
Line 1,114: | Line 3,135: | ||
** <true> |
** <true> |
||
isinteger(list(2))=> |
isinteger(list(2))=> |
||
** <true></ |
** <true></syntaxhighlight> |
||
Now show some uses of the built in procedure sys_parse_string, which allows more options: |
Now show some uses of the built in procedure sys_parse_string, which allows more options: |
||
< |
<syntaxhighlight lang="pop11">;;; Make pop-11 print strings with quotes |
||
true -> pop_pr_quotes; |
true -> pop_pr_quotes; |
||
;;; |
;;; |
||
Line 1,132: | Line 3,153: | ||
;;; print the list of strings |
;;; print the list of strings |
||
strings => |
strings => |
||
** ['Hello' 'How' 'Are' 'You' 'Today']</ |
** ['Hello' 'How' 'Are' 'You' 'Today']</syntaxhighlight> |
||
If {% ... %} were used instead of [% ... %] the result would be |
If {% ... %} were used instead of [% ... %] the result would be |
||
a vector (i.e. array) of strings rather than a list of strings. |
a vector (i.e. array) of strings rather than a list of strings. |
||
< |
<syntaxhighlight lang="pop11">{% sys_parse_string(str, `,`) %} -> strings; |
||
;;; print the vector |
;;; print the vector |
||
strings => |
strings => |
||
** {'Hello' 'How' 'Are' 'You' 'Today'}</ |
** {'Hello' 'How' 'Are' 'You' 'Today'}</syntaxhighlight> |
||
It is also possible to give sys_parse_string a 'conversion' procedure, which is applied to each of the tokens. |
It is also possible to give sys_parse_string a 'conversion' procedure, which is applied to each of the tokens. |
||
E.g. it could be used to produce a vector of numbers, using the conversion procedure 'strnumber', which converts a string to a number: |
E.g. it could be used to produce a vector of numbers, using the conversion procedure 'strnumber', which converts a string to a number: |
||
< |
<syntaxhighlight lang="pop11">lvars numbers; |
||
{% sys_parse_string('100 101 102 103 99.9 99.999', strnumber) %} -> numbers; |
{% sys_parse_string('100 101 102 103 99.9 99.999', strnumber) %} -> numbers; |
||
;;; the result is a vector containing integers and floats, |
;;; the result is a vector containing integers and floats, |
||
;;; which can be printed thus: |
;;; which can be printed thus: |
||
numbers => |
numbers => |
||
** {100 101 102 103 99.9 99.999}</ |
** {100 101 102 103 99.9 99.999}</syntaxhighlight> |
||
Using lower level pop-11 facilities to tokenise the string: |
Using lower level pop-11 facilities to tokenise the string: |
||
< |
<syntaxhighlight lang="pop11">;;; Declare and initialize variables |
||
lvars str='Hello,How,Are,You,Today'; |
lvars str='Hello,How,Are,You,Today'; |
||
;;; Iterate over string |
;;; Iterate over string |
||
Line 1,171: | Line 3,192: | ||
endif; |
endif; |
||
;;; Reverse the list |
;;; Reverse the list |
||
rev(ls) -> ls;</ |
rev(ls) -> ls;</syntaxhighlight> |
||
Since the task requires to use array we convert list to array |
Since the task requires to use array we convert list to array |
||
< |
<syntaxhighlight lang="pop11">;;; Put list elements and lenght on the stack |
||
destlist(ls); |
destlist(ls); |
||
;;; Build a vector from them |
;;; Build a vector from them |
||
Line 1,183: | Line 3,204: | ||
printf(ar(i), '%s.'); |
printf(ar(i), '%s.'); |
||
endfor; |
endfor; |
||
printf('\n');</ |
printf('\n');</syntaxhighlight> |
||
We could use list directly for printing: |
We could use list directly for printing: |
||
< |
<syntaxhighlight lang="pop11">for i in ls do |
||
printf(i, '%s.'); |
printf(i, '%s.'); |
||
endfor;</ |
endfor;</syntaxhighlight> |
||
so the conversion to vector is purely to satisfy task formulation. |
so the conversion to vector is purely to satisfy task formulation. |
||
=={{header|PowerBASIC}}== |
|||
PowerBASIC has a few keywords that make parsing strings trivial: <code>PARSE</code>, <code>PARSE$</code>, and <code>PARSECOUNT</code>. (<code>PARSE$</code>, not shown here, is for extracting tokens one at a time, while <code>PARSE</code> extracts all tokens at once into an array. <code>PARSECOUNT</code> returns the number of tokens found.) |
|||
<lang powerbasic>FUNCTION PBMAIN () AS LONG |
|||
DIM parseMe AS STRING |
|||
parseMe = "Hello,How,Are,You,Today" |
|||
REDIM parsed(PARSECOUNT(parseMe) - 1) AS STRING |
|||
PARSE parseMe, parsed() 'comma is default delimiter |
|||
DIM L0 AS LONG, outP AS STRING |
|||
outP = parsed(0) |
|||
FOR L0 = 1 TO UBOUND(parsed) 'could reuse parsecount instead of ubound |
|||
outP = outP & "." & parsed(L0) |
|||
NEXT |
|||
MSGBOX outP |
|||
END FUNCTION</lang> |
|||
=={{header|PowerShell}}== |
=={{header|PowerShell}}== |
||
{{works with|PowerShell|1}} |
{{works with|PowerShell|1}} |
||
< |
<syntaxhighlight lang="powershell">$words = "Hello,How,Are,You,Today".Split(',') |
||
[string]::Join('.', $words)</ |
[string]::Join('.', $words)</syntaxhighlight> |
||
{{works with|PowerShell|2}} |
{{works with|PowerShell|2}} |
||
< |
<syntaxhighlight lang="powershell">$words = "Hello,How,Are,You,Today" -split ',' |
||
$words -join '.'</ |
$words -join '.'</syntaxhighlight> |
||
{{works with|PowerShell|2}} |
|||
The StringSplitOptions enumeration weeds out the return of empty elements. |
|||
<syntaxhighlight lang="powershell"> |
|||
"Hello,How,Are,You,Today", ",,Hello,,Goodbye,," | ForEach-Object {($_.Split(',',[StringSplitOptions]::RemoveEmptyEntries)) -join "."} |
|||
</syntaxhighlight> |
|||
{{Out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
Hello.Goodbye |
|||
</pre> |
|||
=={{header|Prolog}}== |
=={{header|Prolog}}== |
||
{{works with|SWI Prolog}} |
{{works with|SWI Prolog}} |
||
< |
<syntaxhighlight lang="prolog">splitup(Sep,[token(B)|BL]) --> splitup(Sep,B,BL). |
||
splitup(Sep,[A|AL],B) --> [A], {\+ [A] = Sep }, splitup(Sep,AL,B). |
splitup(Sep,[A|AL],B) --> [A], {\+ [A] = Sep }, splitup(Sep,AL,B). |
||
splitup(Sep,[],[B|BL]) --> Sep, splitup(Sep,B,BL). |
splitup(Sep,[],[B|BL]) --> Sep, splitup(Sep,B,BL). |
||
Line 1,233: | Line 3,244: | ||
phrase(splitup(".",Tokens),Backtogether), |
phrase(splitup(".",Tokens),Backtogether), |
||
string_to_list(ABack,Backtogether), |
string_to_list(ABack,Backtogether), |
||
writeln(ABack).</ |
writeln(ABack).</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
<pre> |
||
?- start. |
|||
Hello.How.Are.You.Today</pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
{{works with|SWI Prolog 7}} |
|||
=={{header|PureBasic}}== |
|||
Using the SWI Prolog string data type and accompanying predicates, |
|||
'''As described |
|||
this can be accomplished in a few lines in the top level: |
|||
<lang PureBasic>NewList MyStrings.s() |
|||
<syntaxhighlight lang="prolog"> |
|||
For i=1 To 5 |
|||
?- split_string("Hello,How,Are,You,Today", ",", "", Split), |
|||
AddElement(MyStrings()) |
|||
| atomics_to_string(Split, ".", PeriodSeparated), |
|||
MyStrings()=StringField("Hello,How,Are,You,Today",i,",") |
|||
| writeln(PeriodSeparated). |
|||
Next i |
|||
Hello.How.Are.You.Today |
|||
</syntaxhighlight> |
|||
ForEach MyStrings() |
|||
Print(MyStrings()+".") |
|||
Next</lang> |
|||
'''Still, easier would be |
|||
<lang PureBasic>Print(ReplaceString("Hello,How,Are,You,Today",",","."))</lang> |
|||
=={{header|Python}}== |
=={{header|Python}}== |
||
{{works with|Python|2.5}}{{works with|Python|3.0}} |
{{works with|Python|2.5}}{{works with|Python|3.0}} |
||
< |
<syntaxhighlight lang="python">text = "Hello,How,Are,You,Today" |
||
tokens = text.split(',') |
tokens = text.split(',') |
||
print ('.'.join(tokens))</ |
print ('.'.join(tokens))</syntaxhighlight> |
||
Or if interpretation of the task description means you don't need to keep an intermediate array: |
Or if interpretation of the task description means you don't need to keep an intermediate array: |
||
< |
<syntaxhighlight lang="python">print ('.'.join('Hello,How,Are,You,Today'.split(',')))</syntaxhighlight> |
||
=={{header|Q}}== |
|||
<syntaxhighlight lang="q">words: "," vs "Hello,How,Are,You,Today" |
|||
"." sv words</syntaxhighlight> |
|||
{{out}} |
|||
<pre>"Hello.How.Are.You.Today"</pre> |
|||
=={{header|QB64}}== |
|||
''CBTJD'': 2020/03/12 |
|||
<syntaxhighlight lang="vb">a$ = "Hello,How,Are,You,Today" ' | Initialize original string. |
|||
FOR na = 1 TO LEN(a$) ' | Start loop to count number of commas. |
|||
IF MID$(a$, na, 1) = "," THEN nc = nc + 1 ' | For each comma, increment nc. |
|||
NEXT ' | End of loop. |
|||
DIM t$(nc) ' | Dim t$ array with total number of commas (nc). Array base is 0. |
|||
FOR nb = 1 TO LEN(a$) ' | Start loop to find each word. |
|||
c$ = MID$(a$, nb, 1) ' | Look at each character in the string. |
|||
IF c$ = "," THEN ' | If the character is a comma, increase the t$ array for the next word. |
|||
t = t + 1 ' | t = token word count. Starts at 0 because array base is 0. |
|||
ELSE ' | Or... |
|||
t$(t) = t$(t) + c$ ' | Add each character to the current token (t$) word. |
|||
END IF ' | End of decision tree. |
|||
NEXT ' | End of loop. |
|||
FOR nd = 0 TO t ' | Start loop to create final desired output. |
|||
tf$ = tf$ + t$(nd) + "." ' | Add each token word from t$ followed by a period to the final tf$. |
|||
NEXT ' | End of loop. |
|||
PRINT LEFT$(tf$, LEN(tf$) - 1) ' | Print all but the last period of tf$. |
|||
END ' | Program end. |
|||
</syntaxhighlight> |
|||
'''Alternative method using word$ function:''' |
|||
---- |
|||
''CBTJD'': 2020/03/12 |
|||
<syntaxhighlight lang="vb">a$ = "Hello,How,Are,You,Today" ' | Initialize original string. |
|||
DIM t$(LEN(a$) / 2) ' | Create an overestimated sized array. |
|||
FOR nd = 1 TO LEN(a$) ' | Start loop to find each comma. |
|||
IF MID$(a$, nd, 1) = "," THEN ' | If a comma is found... |
|||
tc = tc + 1 ' | Increment tc for each found comma. |
|||
t$(tc) = word$(a$, tc, ",") ' | Assign tc word to t$(tc) array. |
|||
END IF ' | End decision tree. |
|||
NEXT ' | End loop. |
|||
t$(tc + 1) = word$(a$, tc + 1, ",") ' | Assign last word to next array position. |
|||
ft$ = t$(1) ' | Start final return string ft$ with first array value. |
|||
FOR ne = 2 TO tc + 1 ' | Start loop to add periods and array values. |
|||
ft$ = ft$ + "." + t$(ne) ' | Concatenate a period with subsequent array values. |
|||
NEXT ' | End loop. |
|||
PRINT ft$ ' | Print final return string ft$. |
|||
FUNCTION word$ (inSTG$, inDEC, inPRM$) ' | word$ function accepts original string, word number, and separator. |
|||
inSTG$ = inSTG$ + inPRM$ ' | Add a separator to the end of the original string. |
|||
FOR na = 1 TO LEN(inSTG$) ' | Start loop to count total number of separators. |
|||
IF MID$(inSTG$, na, 1) = inPRM$ THEN nc = nc + 1 ' | If separator found, increment nc. |
|||
NEXT ' | End loop. |
|||
IF inDEC > nc THEN word$ = "": GOTO DONE ' | If requested word number (inDEC) is greater than total words (nc), bail. |
|||
FOR nd = 1 TO inDEC ' | Start loop to find requested numbered word. |
|||
last = st ' | Remember the position of the last separator. |
|||
st = INSTR(last + 1, inSTG$, inPRM$) ' | Find the next separator. |
|||
NEXT ' | End loop. |
|||
word$ = MID$(inSTG$, last + 1, st - last - 1) ' | Return requested word. |
|||
DONE: ' | Label for bail destination of word count error check. |
|||
END FUNCTION ' | End of function. |
|||
</syntaxhighlight> |
|||
=={{header|Quackery}}== |
|||
<syntaxhighlight lang="quackery"> [ [] [] rot |
|||
witheach |
|||
[ dup char , = iff |
|||
[ drop nested join [] ] |
|||
else join ] |
|||
nested join ] is tokenise ( $ --> [ ) |
|||
[ witheach [ echo$ say "." ] ] is display ( [ --> ) |
|||
$ "Hello,How,Are,You,Today" tokenise display</syntaxhighlight> |
|||
{{Out}} |
|||
<pre>Hello.How.Are.You.Today.</pre> |
|||
=={{header|R}}== |
=={{header|R}}== |
||
< |
<syntaxhighlight lang="r">text <- "Hello,How,Are,You,Today" |
||
junk <- strsplit(text, split=",") |
junk <- strsplit(text, split=",") |
||
print(paste(unlist(junk), collapse="."))</ |
print(paste(unlist(junk), collapse="."))</syntaxhighlight> |
||
or the one liner |
or the one liner |
||
< |
<syntaxhighlight lang="r">paste(unlist(strsplit(text, split=",")), collapse=".")</syntaxhighlight> |
||
=={{header|Racket}}== |
|||
<syntaxhighlight lang="racket"> |
|||
#lang racket |
|||
(string-join (string-split "Hello,How,Are,You,Today" ",") ".") |
|||
;; -> "Hello.How.Are.You.Today" |
|||
</syntaxhighlight> |
|||
=={{header|Raku}}== |
|||
(formerly Perl 6) |
|||
{{works with|Rakudo|#22 "Thousand Oaks"}} |
|||
<syntaxhighlight lang="raku" line>'Hello,How,Are,You,Today'.split(',').join('.').say;</syntaxhighlight> |
|||
Or with function calls: |
|||
<syntaxhighlight lang="raku" line>say join '.', split ',', 'Hello,How,Are,You,Today';</syntaxhighlight> |
|||
=={{header|Raven}}== |
=={{header|Raven}}== |
||
< |
<syntaxhighlight lang="raven">'Hello,How,Are,You,Today' ',' split '.' join print</syntaxhighlight> |
||
=={{header|REBOL}}== |
=={{header|REBOL}}== |
||
< |
<syntaxhighlight lang="rebol">print ["Original:" original: "Hello,How,Are,You,Today"] |
||
tokens: parse original "," |
tokens: parse original "," |
||
dotted: "" repeat i tokens [append dotted rejoin [i "."]] |
dotted: "" repeat i tokens [append dotted rejoin [i "."]] |
||
print ["Dotted: " dotted]</ |
print ["Dotted: " dotted]</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
|||
Original: Hello,How,Are,You,Today |
|||
Dotted: Hello.How.Are.You.Today. |
|||
</pre> |
|||
=={{header|Red}}== |
|||
<pre>Original: Hello,How,Are,You,Today |
|||
<syntaxhighlight lang="red">str: "Hello,How,Are,You,Today" |
|||
>> tokens: split str "," |
|||
>> probe tokens |
|||
["Hello" "How" "Are" "You" "Today"] |
|||
>> periods: replace/all form tokens " " "." ;The word FORM converts the list series to a string removing quotes. |
|||
>> print periods ;then REPLACE/ALL spaces with period |
|||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
=={{header|Retro}}== |
=={{header|Retro}}== |
||
<syntaxhighlight lang="retro">{{ |
|||
<lang Retro>{{ |
|||
: char ( -$ ) " " ; |
: char ( -$ ) " " ; |
||
: tokenize ( $-$$ ) |
: tokenize ( $-$$ ) |
||
Line 1,303: | Line 3,416: | ||
[ tokenize action dup 1 <> ] while drop |
[ tokenize action dup 1 <> ] while drop |
||
^buffer'get drop ; |
^buffer'get drop ; |
||
}}</ |
}}</syntaxhighlight> |
||
This will suffice to split a string into an array of substrings. It is used like this: |
This will suffice to split a string into an array of substrings. It is used like this: |
||
< |
<syntaxhighlight lang="retro">create strings 100 allot |
||
"Hello,How,Are,You,Today" ', strings split</ |
"Hello,How,Are,You,Today" ', strings split</syntaxhighlight> |
||
Since the buffer' vocabulary creates a zero-terminated buffer, we can display it using the each@ combinator and a simple quote: |
Since the buffer' vocabulary creates a zero-terminated buffer, we can display it using the each@ combinator and a simple quote: |
||
< |
<syntaxhighlight lang="retro">strings [ @ "%s." puts ] ^types'STRING each@</syntaxhighlight> |
||
=={{header|REXX}}== |
=={{header|REXX}}== |
||
===version 1=== |
===version 1=== |
||
This REXX version doesn't append a period to the last word in the list. |
|||
<lang rexx>sss='Hello,How,Are,You,Today' /*words seperated by commas. */ |
|||
<syntaxhighlight lang="rexx">/*REXX program separates a string of comma─delimited words, and echoes them ──► terminal*/ |
|||
say 'input string='sss /*echo the string to console. */ |
|||
original = 'Hello,How,Are,You,Today' /*some words separated by commas (,). */ |
|||
say |
|||
say 'The input string:' original /*display original string ──► terminal.*/ |
|||
new= original /*make a copy of the string. */ |
|||
do |
do #=1 until new=='' /*keep processing until NEW is empty.*/ |
||
parse var new |
parse var new @.# ',' new /*parse words delineated by a comma (,)*/ |
||
end /*#*/ /* [↑] the new array is named @. */ |
|||
end |
|||
say /* NEW is destructively parsed. [↑] */ |
|||
say 'Words in the string |
say center(' Words in the string ', 40, "═") /*display a nice header for the list. */ |
||
do j=1 for # /*display all the words (one per line),*/ |
|||
say @.j || left(., j\==#) /*maybe append a period (.) to a word. */ |
|||
end /*j*/ /* [↑] don't append a period if last. */ |
|||
say center(' End─of─list ', 40, "═") /*display a (EOL) trailer for the list.*/</syntaxhighlight> |
|||
end |
|||
{{out|output|text= when using the internal default input:}} |
|||
say 'End-of-list.' /*Display a trailer for the list*/</lang> |
|||
Output: |
|||
<pre> |
<pre> |
||
input string |
The input string: Hello,How,Are,You,Today |
||
Words in the string |
═════════ Words in the string ══════════ |
||
Hello. |
Hello. |
||
How. |
How. |
||
Are. |
Are. |
||
You. |
You. |
||
Today |
Today |
||
═════════════ End─of─list ══════════════ |
|||
End-of-list. |
|||
</pre> |
</pre> |
||
===version 2=== |
===version 2=== |
||
This REXX version won't work if any of the words have an embedded blank (or possible a tab character) in them, as in: |
|||
<lang rexx>sss='Hello,How,Are,You,Today' /*words seperated by commas. */ |
|||
say 'input string='sss /*echo the string to console. */ |
|||
say |
|||
say 'Words in the string:' /*Display a header for the list. */ |
|||
Hello,Betty Sue,How,Are,You,Today |
|||
do until sss=='' /*keep going until SSS is empty. */ |
|||
<syntaxhighlight lang="rexx">/*REXX program to separate a string of comma-delimited words and echo */ |
|||
parse var sss x ',' sss /*parse words delinated by comma.*/ |
|||
sss='Hello,How,Are,You,Today' |
|||
say x'.' /*show a word appended with a '.'*/ |
|||
say 'input string='sss |
|||
end |
|||
say '' |
|||
say 'Words in the string:' |
|||
ss =translate(sss,' ',',') |
|||
dot='.' |
|||
Do i=1 To words(ss) |
|||
If i=words(ss) Then dot='' |
|||
say word(ss,i)dot |
|||
End |
|||
say 'End-of-list.'</syntaxhighlight> |
|||
'''output''' is similar to REXX version 1. |
|||
=={{header|Ring}}== |
|||
say 'End-of-list.' /*Display a trailer for the list.*/</lang> |
|||
<syntaxhighlight lang="ring"> |
|||
Output is identical to Version 1. |
|||
see substr("Hello,How,Are,You,Today", ",", ".") |
|||
</syntaxhighlight> |
|||
=={{header|RPL}}== |
|||
The program below fully complies with the task requirements, e.g. the input string is converted to a list of words, then the list is converted to a string. |
|||
{{works with|Halcyon Calc|4.2.8}} |
|||
{| class="wikitable" |
|||
! RPL code |
|||
! Comment |
|||
|- |
|||
| |
|||
≪ |
|||
"}" + "{" SWAP + STR→ |
|||
1 OVER SIZE '''FOR''' j |
|||
DUP j GET →STR 2 OVER SIZE 1 - SUB j SWAP PUT |
|||
'''NEXT''' |
|||
"" 1 3 PICK SIZE '''FOR''' j |
|||
OVER j GET + |
|||
'''IF''' OVER SIZE j ≠ '''THEN''' "." + '''END''' |
|||
'''NEXT''' SWAP DROP |
|||
≫ '<span style="color:blue">'''TOKNZ'''</span>' STO |
|||
| |
|||
<span style="color:blue">'''TOKNZ'''</span> ''<span style="color:grey">( "word,word" → "word.word" )</span> '' |
|||
convert string into list (words being between quotes) |
|||
loop for each list item |
|||
convert it to a string, remove quotes at beginning and end |
|||
loop for each list item |
|||
add item to output string |
|||
if not last item, append "." |
|||
clean stack |
|||
return output string |
|||
|} |
|||
"Hello,How,Are,You,Today" <span style="color:blue">'''TOKNZ'''</span> |
|||
</pre> |
|||
'''Output:''' |
|||
<span style="color:grey"> 1:</span> "Hello.How.Are.You.Today" |
|||
If direct string-to-string conversion is allowed, then this one-liner for HP-48+ will do the job: |
|||
≪ 1 OVER SIZE '''FOR''' j '''IF''' DUP j DUP SUB "," == '''THEN''' j "." REPL '''END NEXT''' ≫ '<span style="color:blue">'''TOKNZ'''</span>' STO |
|||
=={{header|Ruby}}== |
=={{header|Ruby}}== |
||
< |
<syntaxhighlight lang="ruby">puts "Hello,How,Are,You,Today".split(',').join('.')</syntaxhighlight> |
||
=={{header|Rust}}== |
|||
<syntaxhighlight lang="rust">fn main() { |
|||
let s = "Hello,How,Are,You,Today"; |
|||
let tokens: Vec<&str> = s.split(",").collect(); |
|||
println!("{}", tokens.join(".")); |
|||
}</syntaxhighlight> |
|||
=={{header|S-lang}}== |
|||
<syntaxhighlight lang="s-lang">variable a = strchop("Hello,How,Are,You,Today", ',', 0); |
|||
print(strjoin(a, "."));</syntaxhighlight> |
|||
{{out}} |
|||
<pre>"Hello.How.Are.You.Today"</pre> |
|||
=={{header|Scala}}== |
=={{header|Scala}}== |
||
< |
<syntaxhighlight lang="scala">println("Hello,How,Are,You,Today" split "," mkString ".")</syntaxhighlight> |
||
=={{header|Scheme}}== |
=={{header|Scheme}}== |
||
{{works with|Guile}} |
{{works with|Guile}} |
||
< |
<syntaxhighlight lang="scheme">(use-modules (ice-9 regex)) |
||
(define s "Hello,How,Are,You,Today") |
(define s "Hello,How,Are,You,Today") |
||
(define words (map match:substring (list-matches "[^,]+" s))) |
(define words (map match:substring (list-matches "[^,]+" s))) |
||
Line 1,374: | Line 3,546: | ||
(display (list-ref words n)) |
(display (list-ref words n)) |
||
(if (< n (- (length words) 1)) |
(if (< n (- (length words) 1)) |
||
(display ".")))</ |
(display ".")))</syntaxhighlight> |
||
(with SRFI 13) |
(with SRFI 13) |
||
< |
<syntaxhighlight lang="scheme">(define s "Hello,How,Are,You,Today") |
||
(define words (string-tokenize s (char-set-complement (char-set #\,)))) |
(define words (string-tokenize s (char-set-complement (char-set #\,)))) |
||
(define t (string-join words "."))</ |
(define t (string-join words "."))</syntaxhighlight> |
||
{{works with|Gauche Scheme}} |
|||
<syntaxhighlight lang="scheme">(print |
|||
(string-join |
|||
(string-split "Hello,How,Are,You,Today" #\,) |
|||
".")) </syntaxhighlight> |
|||
{{output}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|Seed7}}== |
=={{header|Seed7}}== |
||
< |
<syntaxhighlight lang="seed7">var array string: tokens is 0 times ""; |
||
tokens := split("Hello,How,Are,You,Today", ",");</syntaxhighlight> |
|||
=={{header|Self}}== |
|||
<syntaxhighlight lang="self">| s = 'Hello,How,Are,You,Today' | |
|||
((s splitOn: ',') joinUsing: '.') printLine. |
|||
</syntaxhighlight> |
|||
=={{header|Sidef}}== |
|||
<syntaxhighlight lang="ruby">'Hello,How,Are,You,Today'.split(',').join('.').say;</syntaxhighlight> |
|||
=={{header|Simula}}== |
|||
<syntaxhighlight lang="simula">BEGIN |
|||
CLASS TEXTARRAY(N); INTEGER N; |
|||
BEGIN |
|||
TEXT ARRAY ARR(1:N); |
|||
END TEXTARRAY; |
|||
REF(TEXTARRAY) PROCEDURE SPLIT(T,DELIM); TEXT T; CHARACTER DELIM; |
|||
BEGIN |
|||
INTEGER N, I, LPOS; |
|||
REF(TEXTARRAY) A; |
|||
N := 1; |
|||
T.SETPOS(1); |
|||
WHILE T.MORE DO |
|||
IF T.GETCHAR = DELIM THEN |
|||
N := N+1; |
|||
A :- NEW TEXTARRAY(N); |
|||
I := 0; |
|||
LPOS := 1; |
|||
T.SETPOS(LPOS); |
|||
WHILE T.MORE DO |
|||
IF T.GETCHAR = DELIM THEN |
|||
BEGIN |
|||
I := I+1; |
|||
A.ARR(I) :- T.SUB(LPOS,T.POS-LPOS-1); |
|||
LPOS := T.POS; |
|||
END; |
|||
I := I+1; |
|||
A.ARR(I) :- T.SUB(LPOS,T.LENGTH-LPOS+1); |
|||
SPLIT :- A; |
|||
END SPLIT; |
|||
BEGIN |
|||
TEXT S; |
|||
REF(TEXTARRAY) TA; |
|||
INTEGER I; |
|||
S :- "HELLO,HOW,ARE,YOU,TODAY"; |
|||
TA :- SPLIT(S,','); |
|||
FOR I := 1 STEP 1 UNTIL TA.N DO |
|||
BEGIN |
|||
OUTTEXT(TA.ARR(I)); |
|||
OUTCHAR('.'); |
|||
END; |
|||
OUTIMAGE; |
|||
END; |
|||
END. |
|||
tokens := split("Hello,How,Are,You,Today", ",");</lang> |
|||
</syntaxhighlight> |
|||
{{out}} |
|||
<pre>HELLO.HOW.ARE.YOU.TODAY.</pre> |
|||
=={{header|Slate}}== |
=={{header|Slate}}== |
||
< |
<syntaxhighlight lang="slate">('Hello,How,Are,You,Today' splitWith: $,) join &separator: '.'.</syntaxhighlight> |
||
=={{header|Slope}}== |
|||
<syntaxhighlight lang="slope">(display |
|||
(list->string |
|||
(string->list |
|||
"Hello,How,Are,You,Today" |
|||
",") |
|||
"."))</syntaxhighlight> |
|||
{{out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
=={{header|Smalltalk}}== |
=={{header|Smalltalk}}== |
||
< |
<syntaxhighlight lang="smalltalk">|array | |
||
array := 'Hello,How,Are,You,Today' subStrings: $,. |
array := 'Hello,How,Are,You,Today' subStrings: $,. |
||
array fold: [:concatenation :string | concatenation, '.', string ]</ |
array fold: [:concatenation :string | concatenation, '.', string ]</syntaxhighlight> |
||
Some implementations also have a ''join:'' convenience method that allows the following shorter solution: |
Some implementations also have a ''join:'' convenience method that allows the following shorter solution: |
||
< |
<syntaxhighlight lang="smalltalk">('Hello,How,Are,You,Today' subStrings: $,) join: '.'</syntaxhighlight> |
||
The solution displaying a trailing period would be: |
The solution displaying a trailing period would be: |
||
< |
<syntaxhighlight lang="smalltalk">|array | |
||
array := 'Hello,How,Are,You,Today' subStrings: $,. |
array := 'Hello,How,Are,You,Today' subStrings: $,. |
||
array inject: '' into: [:concatenation :string | concatenation, string, '.' ]</ |
array inject: '' into: [:concatenation :string | concatenation, string, '.' ]</syntaxhighlight> |
||
=={{header|SNOBOL4}}== |
=={{header|SNOBOL4}}== |
||
Line 1,408: | Line 3,662: | ||
For this task, it's convenient to define Perl-style split( ) and join( ) functions. |
For this task, it's convenient to define Perl-style split( ) and join( ) functions. |
||
< |
<syntaxhighlight lang="snobol4"> define('split(chs,str)i,j,t,w2') :(split_end) |
||
split t = table() |
split t = table() |
||
sp1 str pos(0) (break(chs) | rem) $ t<i = i + 1> |
sp1 str pos(0) (break(chs) | rem) $ t<i = i + 1> |
||
Line 1,424: | Line 3,678: | ||
* # Test and display |
* # Test and display |
||
output = join('.',split(',','Hello,How,Are,You,Today')) |
output = join('.',split(',','Hello,How,Are,You,Today')) |
||
end</ |
end</syntaxhighlight> |
||
{{out}} |
|||
Output: |
|||
<pre> |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|Standard ML}}== |
=={{header|Standard ML}}== |
||
< |
<syntaxhighlight lang="sml">val splitter = String.tokens (fn c => c = #","); |
||
val main = (String.concatWith ".") o splitter;</ |
val main = (String.concatWith ".") o splitter;</syntaxhighlight> |
||
Test: |
Test: |
||
< |
<syntaxhighlight lang="sml">- main "Hello,How,Are,You,Today" |
||
val it = "Hello.How.Are.You.Today" : string</ |
val it = "Hello.How.Are.You.Today" : string</syntaxhighlight> |
||
=={{header|Swift}}== |
|||
{{works with|Swift|3.x}} |
|||
<syntaxhighlight lang="swift">let text = "Hello,How,Are,You,Today" |
|||
let tokens = text.components(separatedBy: ",") // for single or multi-character separator |
|||
print(tokens) |
|||
let result = tokens.joined(separator: ".") |
|||
print(result)</syntaxhighlight> |
|||
{{works with|Swift|2.x}} |
|||
<syntaxhighlight lang="swift">let text = "Hello,How,Are,You,Today" |
|||
let tokens = text.characters.split(",").map{String($0)} // for single-character separator |
|||
print(tokens) |
|||
let result = tokens.joinWithSeparator(".") |
|||
print(result)</syntaxhighlight> |
|||
{{works with|Swift|1.x}} |
|||
<syntaxhighlight lang="swift">let text = "Hello,How,Are,You,Today" |
|||
let tokens = split(text, { $0 == "," }) // for single-character separator |
|||
println(tokens) |
|||
let result = ".".join(tokens) |
|||
println(result)</syntaxhighlight> |
|||
For multi-character separators:<syntaxhighlight lang="swift">import Foundation |
|||
let text = "Hello,How,Are,You,Today" |
|||
let tokens = text.componentsSeparatedByString(",") |
|||
print(tokens)</syntaxhighlight> |
|||
=={{header|Tcl}}== |
=={{header|Tcl}}== |
||
Generating a list form a string by splitting on a comma: |
Generating a list form a string by splitting on a comma: |
||
< |
<syntaxhighlight lang="tcl">split $string ","</syntaxhighlight> |
||
Joining the elements of a list by a period: |
Joining the elements of a list by a period: |
||
< |
<syntaxhighlight lang="tcl">join $list "."</syntaxhighlight> |
||
Thus the whole thing would look like this: |
Thus the whole thing would look like this: |
||
< |
<syntaxhighlight lang="tcl">puts [join [split "Hello,How,Are,You,Today" ","] "."]</syntaxhighlight> |
||
If you'd like to retain the list in a variable with the name "words", it would only be marginally more complex: |
If you'd like to retain the list in a variable with the name "words", it would only be marginally more complex: |
||
< |
<syntaxhighlight lang="tcl">puts [join [set words [split "Hello,How,Are,You,Today" ","]] "."]</syntaxhighlight> |
||
(In general, the <tt>regexp</tt> command is also used in Tcl for tokenization of strings, but this example does not need that level of complexity.) |
(In general, the <tt>regexp</tt> command is also used in Tcl for tokenization of strings, but this example does not need that level of complexity.) |
||
Line 1,456: | Line 3,741: | ||
<code>tr</code> knows nothing about arrays, so this solution only changes each comma to a period. |
<code>tr</code> knows nothing about arrays, so this solution only changes each comma to a period. |
||
< |
<syntaxhighlight lang="bash">echo 'Hello,How,Are,You,Today' | tr ',' '.'</syntaxhighlight> |
||
=={{header|Transd}}== |
|||
<syntaxhighlight lang="Scheme">#lang transd |
|||
MainModule: { |
|||
_start: (lambda locals: s "Hello,How,Are,You,Today" |
|||
(textout (join (split s ",") ".")) |
|||
) |
|||
}</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today |
|||
</pre> |
|||
=={{header|TUSCRIPT}}== |
|||
<syntaxhighlight lang="tuscript"> |
|||
$$ MODE TUSCRIPT |
|||
SET string="Hello,How,Are,You,Today" |
|||
SET string=SPLIT (string,":,:") |
|||
SET string=JOIN (string,".") |
|||
</syntaxhighlight> |
|||
=={{header|TXR}}== |
=={{header|TXR}}== |
||
Line 1,463: | Line 3,769: | ||
sequences of non-commas. |
sequences of non-commas. |
||
< |
<syntaxhighlight lang="txr">@(next :list "Hello,How,Are,You,Today") |
||
@(coll)@{token /[^,]+/}@(end) |
@(coll)@{token /[^,]+/}@(end) |
||
@(output) |
@(output) |
||
@(rep)@token.@(last)@token@(end) |
@(rep)@token.@(last)@token@(end) |
||
@(end)</ |
@(end)</syntaxhighlight> |
||
Different approach. Collect tokens, each of |
Different approach. Collect tokens, each of |
||
Line 1,473: | Line 3,779: | ||
before a comma, or else extends to the end of the line. |
before a comma, or else extends to the end of the line. |
||
< |
<syntaxhighlight lang="txr">@(next :list "Hello,How,Are,You,Today") |
||
@(coll)@(maybe)@token,@(or)@token@(end)@(end) |
@(coll)@(maybe)@token,@(or)@token@(end)@(end) |
||
@(output) |
@(output) |
||
@(rep)@token.@(last)@token@(end) |
@(rep)@token.@(last)@token@(end) |
||
@(end)</ |
@(end)</syntaxhighlight> |
||
Using TXR Lisp: |
Using TXR Lisp: |
||
<lang |
<syntaxhighlight lang="bash">txr -p '(cat-str (split-str "Hello,How,Are,You,Today" ",") ".")' |
||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
<pre>$ txr tok.txr |
|||
result="Hello.How.Are.You.Today"</pre> |
|||
=={{header|TUSCRIPT}}== |
|||
<lang tuscript> |
|||
$$ MODE TUSCRIPT |
|||
SET string="Hello,How,Are,You,Today" |
|||
SET string=SPLIT (string,":,:") |
|||
SET string=JOIN (string,".") |
|||
</lang> |
|||
=={{header|UnixPipes}}== |
|||
{{works with|Bourne Shell}} |
|||
<lang bash>token() { |
|||
(IFS=, read -r A B; echo "$A".; test -n "$B" && (echo "$B" | token)) |
|||
} |
|||
echo "Hello,How,Are,You" | token</lang> |
|||
=={{header|UNIX Shell}}== |
=={{header|UNIX Shell}}== |
||
{{works with|Bourne Shell}} |
{{works with|Bourne Shell}} |
||
< |
<syntaxhighlight lang="bash">string='Hello,How,Are,You,Today' |
||
(IFS=, |
(IFS=, |
||
printf '%s.' $string |
printf '%s.' $string |
||
echo)</ |
echo)</syntaxhighlight> |
||
---- |
---- |
||
{{works with|Bourne Again SHell}} |
{{works with|Bourne Again SHell}} |
||
{{works with|Public Domain Korn SHell|5.2.14}} |
{{works with|Public Domain Korn SHell|5.2.14}} |
||
< |
<syntaxhighlight lang="bash">#! /bin/bash |
||
stripchar-l () |
stripchar-l () |
||
#removes the specified character from the left side of the string |
#removes the specified character from the left side of the string |
||
Line 1,570: | Line 3,858: | ||
join "$( split "$list" "$input_delimiter" )" \ |
join "$( split "$list" "$input_delimiter" )" \ |
||
"$contains_a_space" "$output_delimiter"; |
"$contains_a_space" "$output_delimiter"; |
||
}</ |
}</syntaxhighlight> |
||
''Example'' |
''Example'' |
||
< |
<syntaxhighlight lang="bash"> strtokenize "Hello,How,Are,You,Today" "," "." |
||
Hello.How.Are.You.Today </ |
Hello.How.Are.You.Today </syntaxhighlight> |
||
---- |
|||
{{works with|Almquist Shell}} |
|||
{{works with|bash}} |
|||
{{works with|pdksh}} |
|||
{{works with|ksh93}} |
|||
{{works with|zsh}} |
|||
<syntaxhighlight lang="sh"> |
|||
string1="Hello,How,Are,You,Today" |
|||
elements_quantity=$(echo $string1|tr "," "\n"|wc -l) |
|||
present_element=1 |
|||
while [ $present_element -le $elements_quantity ];do |
|||
echo $string1|cut -d "," -f $present_element|tr -d "\n" |
|||
if [ $present_element -lt $elements_quantity ];then echo -n ".";fi |
|||
present_element=$(expr $present_element + 1) |
|||
done |
|||
echo |
|||
# or to cheat |
|||
echo "Hello,How,Are,You,Today"|tr "," "."</syntaxhighlight> |
|||
=={{header|UnixPipes}}== |
|||
{{works with|Bourne Shell}} |
|||
<syntaxhighlight lang="bash">token() { |
|||
(IFS=, read -r A B; echo "$A".; test -n "$B" && (echo "$B" | token)) |
|||
} |
|||
echo "Hello,How,Are,You" | token</syntaxhighlight> |
|||
=={{header|Ursa}}== |
|||
<syntaxhighlight lang="ursa">decl string text |
|||
set text "Hello,How,Are,You,Today" |
|||
decl string<> tokens |
|||
set tokens (split text ",") |
|||
for (decl int i) (< i (size tokens)) (inc i) |
|||
out tokens<i> "." console |
|||
end for |
|||
out endl console</syntaxhighlight> |
|||
=={{header|Ursala}}== |
=={{header|Ursala}}== |
||
Line 1,583: | Line 3,910: | ||
second order function parameterized by the delimiter. Character |
second order function parameterized by the delimiter. Character |
||
literals are preceded by a backquote. |
literals are preceded by a backquote. |
||
< |
<syntaxhighlight lang="ursala">#import std |
||
token_list = sep`, 'Hello,How,Are,You,Today' |
token_list = sep`, 'Hello,How,Are,You,Today' |
||
Line 1,589: | Line 3,916: | ||
#cast %s |
#cast %s |
||
main = mat`. token_list</ |
main = mat`. token_list</syntaxhighlight> |
||
{{out}} |
|||
output: |
|||
<pre> |
|||
<pre>'Hello.How.Are.You.Today'</pre> |
|||
'Hello.How.Are.You.Today' |
|||
</pre> |
|||
=={{header|Vala}}== |
=={{header|Vala}}== |
||
<syntaxhighlight lang="vala">void main() { |
|||
<lang vala> |
|||
string s = "Hello,How,Are,You,Today"; |
|||
// declare test string |
|||
print(@"$(string.joinv(".", s.split(",")))"); |
|||
string s = "Hello,How,Are,You,Today"; |
|||
}</syntaxhighlight> |
|||
// create array of strings, could use var words instead if desired |
|||
{{out}} |
|||
string[] words = s.split(","); |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
// create string by joining array of strings with . |
|||
string joined = string.joinv(".", words); |
|||
</lang> |
|||
=={{header| |
=={{header|VBA}}== |
||
<syntaxhighlight lang="vb">Sub Main() |
|||
====One liner==== |
|||
Dim temp() As String |
|||
<lang vb>wscript.echo Join( Split( "Hello,How,Are,You,Today", "," ), "." )</lang> |
|||
temp = Tokenize("Hello,How,Are,You,Today", ",") |
|||
Display temp, Space(5) |
|||
End Sub |
|||
Private Function Tokenize(strS As String, sep As String) As String() |
|||
In fact, the following Visual Basic could have done the same, as Join() is available. |
|||
Tokenize = Split(strS, sep) |
|||
End Function |
|||
Private Sub Display(arr() As String, sep As String) |
|||
=={{header|Visual Basic}}== |
|||
Debug.Print Join(arr, sep) |
|||
{{trans|PowerBASIC}} |
|||
End Sub</syntaxhighlight> |
|||
{{Out}} |
|||
<pre>Hello How Are You Today</pre> |
|||
=={{header|VBScript}}== |
|||
Unlike PowerBASIC, there is no need to know beforehand how many tokens are in the string -- <code>Split</code> automagically builds the array for you. |
|||
<syntaxhighlight lang="vb"> |
|||
s = "Hello,How,Are,You,Today" |
|||
<lang vb>Sub Main() |
|||
WScript.StdOut.Write Join(Split(s,","),".") |
|||
Dim parseMe As String, parsed As Variant |
|||
</syntaxhighlight> |
|||
parseMe = "Hello,How,Are,You,Today" |
|||
{{Out}} |
|||
<pre>Hello.How.Are.You.Today</pre> |
|||
parsed = Split(parseMe, ",") |
|||
Dim L0 As Long, outP As String |
|||
outP = parsed(0) |
|||
For L0 = 1 To UBound(parsed) |
|||
outP = outP & "." & parsed(L0) |
|||
Next |
|||
MsgBox outP |
|||
End Sub</lang> |
|||
=={{header|Vedit macro language}}== |
=={{header|Vedit macro language}}== |
||
Line 1,635: | Line 3,961: | ||
The contents of each text register is then displayed to user, separated by a period. |
The contents of each text register is then displayed to user, separated by a period. |
||
< |
<syntaxhighlight lang="vedit">Buf_Switch(Buf_Free) |
||
Ins_Text("Hello,How,Are,You,Today") |
Ins_Text("Hello,How,Are,You,Today") |
||
Line 1,654: | Line 3,980: | ||
} |
} |
||
Buf_Quit(OK)</ |
Buf_Quit(OK)</syntaxhighlight> |
||
=={{header|V (Vlang)}}== |
|||
<syntaxhighlight lang="go">// Tokenize a string, in V (Vlang) |
|||
// Tectonics: v run tokenize-a-string.v |
|||
module main |
|||
// starts here |
|||
pub fn main() { |
|||
println("Hello,How,Are,You,Today".split(',').join('.')) |
|||
}</syntaxhighlight> |
|||
{{out}} |
|||
<pre>prompt$ v run rosetta/tokenize-a-string.v |
|||
Hello.How.Are.You.Today</pre> |
|||
=={{header|WinBatch}}== |
|||
<syntaxhighlight lang="winbatch">text = 'Hello,How,Are,You,Today' |
|||
result = '' |
|||
BoxOpen('WinBatch Tokenizing Example', '') |
|||
for ix = 1 to itemcount(text,',') |
|||
result = result : itemextract(ix, text, ',') : '.' |
|||
BoxText(result) |
|||
next |
|||
display(10, 'End of Program', 'Dialog and program will close momentarily.') |
|||
BoxShut()</syntaxhighlight> |
|||
{{out}} |
|||
Hello.How.Are.You.Today. |
|||
=={{header|Wortel}}== |
|||
<syntaxhighlight lang="wortel">@join "." @split "," "Hello,How,Are,You,Today"</syntaxhighlight> |
|||
Returns |
|||
<pre>"Hello.How.Are.You.Today"</pre> |
|||
=={{header|Wren}}== |
|||
<syntaxhighlight lang="wren">var s = "Hello,How,Are,You,Today" |
|||
var t = s.split(",").join(".") + "." |
|||
System.print(t)</syntaxhighlight> |
|||
{{out}} |
|||
<pre> |
|||
Hello.How.Are.You.Today. |
|||
</pre> |
|||
=={{header|XPath 2.0}}== |
|||
<syntaxhighlight lang="xpath">string-join(tokenize("Hello,How,Are,You,Today", ","), ".")</syntaxhighlight> |
|||
{{out}} |
|||
Hello.How.Are.You.Today |
|||
=={{header|XPL0}}== |
|||
<syntaxhighlight lang="xpl0">string 0; |
|||
include c:\cxpl\codes; |
|||
int I, J, K, Char; |
|||
char String, Array(5,6); \5 words and 5 maximum chars + terminating 0 |
|||
[String:= "Hello,How,Are,You,Today"; |
|||
I:= 0; K:= 0; |
|||
repeat J:= 0; |
|||
loop [Char:= String(I); |
|||
I:= I+1; |
|||
if Char=^, or Char=0 then quit; |
|||
Array(K,J):= Char; |
|||
J:= J+1; |
|||
]; |
|||
Array(K,J):= 0; \terminate word |
|||
K:= K+1; \next word in array |
|||
until K>=5; |
|||
for K:= 4 downto 0 do [Text(0, addr Array(K,0)); ChOut(0, ^.)]; |
|||
CrLf(0); |
|||
]</syntaxhighlight> |
|||
The 'addr' operator is used to fetch the 32-bit address of Array rather |
|||
than a byte from the character array. |
|||
Output (done in reverse order to emphasize the tokens are indeed separate): |
|||
<pre> |
|||
Today.You.Are.How.Hello. |
|||
</pre> |
|||
=={{header|Yabasic}}== |
|||
<syntaxhighlight lang="yabasic">dim s$(1) |
|||
n = token("Hello. How are you today?", s$(), ".? ") |
|||
for i = 1 to n |
|||
print s$(i); |
|||
if i < n print "."; |
|||
next |
|||
print</syntaxhighlight> |
|||
=={{header|Zig}}== |
|||
<syntaxhighlight lang="zig">const std = @import("std"); |
|||
pub fn main() void { |
|||
const string = "Hello,How,Are,You,Today"; |
|||
var tokens = std.mem.split(u8, string, ","); |
|||
std.debug.print("{s}", .{tokens.next().?}); |
|||
while (tokens.next()) |token| { |
|||
std.debug.print(".{s}", .{token}); |
|||
} |
|||
}</syntaxhighlight> |
|||
=={{header|zkl}}== |
|||
<syntaxhighlight lang="zkl">"Hello,How,Are,You,Today".split(",").concat(".").println(); |
|||
Hello.How.Are.You.Today</syntaxhighlight> |
|||
=={{header|Zoea}}== |
|||
<syntaxhighlight lang="zoea"> |
|||
program: tokenize_a_string |
|||
input: "Hello,How,Are,You,Today" |
|||
output: "Hello.How.Are.You.Today" |
|||
</syntaxhighlight> |
|||
=={{header|Zoea Visual}}== |
|||
[http://zoea.co.uk/examples/zv-rc/Tokenize_string.png Tokenize a string] |
|||
=={{header|Zsh}}== |
=={{header|Zsh}}== |
||
< |
<syntaxhighlight lang="zsh">str='Hello,How,Are,You,Today' |
||
tokens=(${(s:,:)str}) |
tokens=(${(s:,:)str}) |
||
print ${(j:.:)tokens}</ |
print ${(j:.:)tokens}</syntaxhighlight> |
||
Or, using SH_SPLIT_WORD: |
Or, using SH_SPLIT_WORD: |
||
< |
<syntaxhighlight lang="zsh">str='Hello,How,Are,You,Today' |
||
IFS=, echo ${(j:.:)${=str}}</ |
IFS=, echo ${(j:.:)${=str}}</syntaxhighlight> |
||
{{omit from|PARI/GP|No real capacity for string manipulation}} |
{{omit from|PARI/GP|No real capacity for string manipulation}} |
Latest revision as of 14:45, 14 February 2024
You are encouraged to solve this task according to the task description, using any language you may know.
Separate the string "Hello,How,Are,You,Today" by commas into an array (or list) so that each element of it stores a different word.
Display the words to the 'user', in the simplest manner possible, separated by a period.
To simplify, you may display a trailing period.
- Metrics
- Counting
- Word frequency
- Letter frequency
- Jewels and stones
- I before E except after C
- Bioinformatics/base count
- Count occurrences of a substring
- Count how many vowels and consonants occur in a string
- Remove/replace
- XXXX redacted
- Conjugate a Latin verb
- Remove vowels from a string
- String interpolation (included)
- Strip block comments
- Strip comments from a string
- Strip a set of characters from a string
- Strip whitespace from a string -- top and tail
- Strip control codes and extended characters from a string
- Anagrams/Derangements/shuffling
- Word wheel
- ABC problem
- Sattolo cycle
- Knuth shuffle
- Ordered words
- Superpermutation minimisation
- Textonyms (using a phone text pad)
- Anagrams
- Anagrams/Deranged anagrams
- Permutations/Derangements
- Find/Search/Determine
- ABC words
- Odd words
- Word ladder
- Semordnilap
- Word search
- Wordiff (game)
- String matching
- Tea cup rim text
- Alternade words
- Changeable words
- State name puzzle
- String comparison
- Unique characters
- Unique characters in each string
- Extract file extension
- Levenshtein distance
- Palindrome detection
- Common list elements
- Longest common suffix
- Longest common prefix
- Compare a list of strings
- Longest common substring
- Find common directory path
- Words from neighbour ones
- Change e letters to i in words
- Non-continuous subsequences
- Longest common subsequence
- Longest palindromic substrings
- Longest increasing subsequence
- Words containing "the" substring
- Sum of the digits of n is substring of n
- Determine if a string is numeric
- Determine if a string is collapsible
- Determine if a string is squeezable
- Determine if a string has all unique characters
- Determine if a string has all the same characters
- Longest substrings without repeating characters
- Find words which contains all the vowels
- Find words which contains most consonants
- Find words which contains more than 3 vowels
- Find words which first and last three letters are equals
- Find words which odd letters are consonants and even letters are vowels or vice_versa
- Formatting
- Substring
- Rep-string
- Word wrap
- String case
- Align columns
- Literals/String
- Repeat a string
- Brace expansion
- Brace expansion using ranges
- Reverse a string
- Phrase reversals
- Comma quibbling
- Special characters
- String concatenation
- Substring/Top and tail
- Commatizing numbers
- Reverse words in a string
- Suffixation of decimal numbers
- Long literals, with continuations
- Numerical and alphabetical suffixes
- Abbreviations, easy
- Abbreviations, simple
- Abbreviations, automatic
- Song lyrics/poems/Mad Libs/phrases
- Mad Libs
- Magic 8-ball
- 99 Bottles of Beer
- The Name Game (a song)
- The Old lady swallowed a fly
- The Twelve Days of Christmas
- Tokenize
- Text between
- Tokenize a string
- Word break problem
- Tokenize a string with escaping
- Split a character string based on change of character
- Sequences
11l
V text = ‘Hello,How,Are,You,Today’
V tokens = text.split(‘,’)
print(tokens.join(‘.’))
- Output:
Hello.How.Are.You.Today
360 Assembly
* Tokenize a string - 08/06/2018
TOKSTR CSECT
USING TOKSTR,R13 base register
B 72(R15) skip savearea
DC 17F'0' savearea
SAVE (14,12) save previous context
ST R13,4(R15) link backward
ST R15,8(R13) link forward
LR R13,R15 set addressability
MVC N,=A(1) n=1
LA R7,1 i1=1
LA R6,1 i=1
DO WHILE=(C,R6,LE,LENS) do i=1 to length(s);
LA R4,S-1 @s-1
AR R4,R6 +i
MVC C,0(R4) c=substr(s,i,1)
IF CLI,C,EQ,C',' THEN if c=',' then do
BAL R14,TOK call tok
LR R2,R8 i2
SR R2,R7 i2-i1
LA R2,1(R2) i2-i1+1
L R1,N n
SLA R1,1 *2
STH R2,TALEN-2(R1) talen(n)=i2-i1+1
L R2,N n
LA R2,1(R2) n+1
ST R2,N n=n+1
LA R7,1(R6) i1=i+1
ENDIF , endif
LA R6,1(R6) i++
ENDDO , enddo i
BAL R14,TOK call tok
LR R2,R8 i2
SR R2,R7 i2-i1
LA R2,1(R2) i2-i1+1
L R1,N n
SLA R1,1 *2
STH R2,TALEN-2(R1) talen(n)=i2-i1+1
LA R11,PG pgi=@pg
LA R6,1 i=1
DO WHILE=(C,R6,LE,N) do i=1 to n
LR R1,R6 i
SLA R1,1 *2
LH R10,TALEN-2(R1) l=talen(i)
LR R1,R6 i
SLA R1,3 *8
LA R4,TABLE-8(R1) @table(i)
LR R2,R10 l
BCTR R2,0 ~
EX R2,MVCX output table(i) length(l)
AR R11,R10 pgi=pgi+l
IF C,R6,NE,N THEN if i^=n then
MVC 0(1,R11),=C'.' output '.'
LA R11,1(R11) pgi=pgi+1
ENDIF , endif
LA R6,1(R6) i++
ENDDO , enddo i
XPRNT PG,L'PG print
L R13,4(0,R13) restore previous savearea pointer
RETURN (14,12),RC=0 restore registers from calling sav
TOK LR R5,R6 i <--
BCTR R5,0 i-1 |
LR R8,R5 i2=i-1
SR R5,R7 i2-i1
LA R5,1(R5) l=i2-i1+1 source length
L R1,N n
SLA R1,3 *8
LA R2,TABLE-8(R1) @table(n)
LA R4,S-1 @s-1
AR R4,R7 @s+i1-1
LA R3,8 target length
MVCL R2,R4 table(n)=substr(s,i1,i2-i1+1) |
BR R14 End TOK subroutine <--
MVCX MVC 0(0,R11),0(R4) output table(i)
S DC CL80'Hello,How,Are,You,Today' <== input string ==
LENS DC F'23' length(s) <==
TABLE DC 8CL8' ' table(8)
TALEN DC 8H'0' talen(8)
C DS CL1 char
N DS F number of tokens
PG DC CL80' ' buffer
YREGS
END TOKSTR
- Output:
Hello.How.Are.You.Today
8080 Assembly
puts: equ 9
org 100h
jmp demo
;;; Split the string at DE by the character in C.
;;; Store pointers to the beginning of the elements starting at HL
;;; The amount of elements is returned in B.
split: mvi b,0 ; Amount of elements
sloop: mov m,e ; Store pointer at [HL]
inx h
mov m,d
inx h
inr b ; Increment counter
sscan: ldax d ; Get current character
inx d
cpi '$' ; Done?
rz ; Then stop
cmp c ; Place to split?
jnz sscan ; If not, keep going
dcx d
mvi a,'$' ; End the string here
stax d
inx d
jmp sloop ; Next part
;;; Test on the string given in the task
demo: lxi h,parts ; Parts array
lxi d,hello ; String
mvi c,','
call split ; Split the string
lxi h,parts ; Print each part
loop: mov e,m ; Load pointer into DE
inx h
mov d,m
inx h
push h ; Keep the array pointer
push b ; And the counter
mvi c,puts ; Print the string
call 5
lxi d,period ; And a period
mvi c,puts
call 5
pop b ; Restore the counter
pop h ; Restore the array pointer
dcr b ; One fewer string left
jnz loop
ret
period: db '. $'
hello: db 'Hello,How,Are,You,Today$'
parts: equ $
- Output:
Hello. How. Are. You. Today.
8086 Assembly
cpu 8086
org 100h
section .text
jmp demo
;;; Split the string at DS:SI on the character in DL.
;;; Store pointers to strings starting at ES:DI.
;;; The amount of strings is returned in CX.
split: xor cx,cx ; Zero out counter
.loop: mov ax,si ; Store pointer to current location
stosw
inc cx ; Increment counter
.scan: lodsb ; Get byte
cmp al,'$' ; End of string?
je .done
cmp al,dl ; Character to split on?
jne .scan
mov [si-1],byte '$' ; Terminate string
jmp .loop
.done: ret
;;; Test on the string given in the task
demo: mov si,hello ; String to split
mov di,parts ; Place to store pointers
mov dl,',' ; Character to split string on
call split
;;; Print the resulting strings, and periods
mov si,parts ; Array of string pointers
print: lodsw ; Load next pointer
mov dx,ax ; Print string using DOS
mov ah,9
int 21h
mov dx,period ; Then print a period
int 21h
loop print ; Loop while there are strings
ret
section .data
period: db '. $'
hello: db 'Hello,How,Are,You,Today$'
section .bss
parts: resw 10
- Output:
Hello. How. Are. You. Today.
AArch64 Assembly
/* ARM assembly AARCH64 Raspberry PI 3B */
/* program strTokenize64.s */
/*******************************************/
/* Constantes file */
/*******************************************/
/* for this file see task include a file in language AArch64 assembly*/
.include "../includeConstantesARM64.inc"
.equ NBPOSTESECLAT, 20
/*******************************************/
/* Initialized data */
/*******************************************/
.data
szMessFinal: .asciz "Words are : \n"
szString: .asciz "Hello,How,Are,You,Today"
szMessError: .asciz "Error tokenize !!\n"
szCarriageReturn: .asciz "\n"
/*******************************************/
/* UnInitialized data */
/*******************************************/
.bss
/*******************************************/
/* code section */
/*******************************************/
.text
.global main
main:
ldr x0,qAdrszString // string address
mov x1,',' // separator
bl stTokenize
cmp x0,-1 // error ?
beq 99f
mov x2,x0 // table address
ldr x0,qAdrszMessFinal // display message
bl affichageMess
ldr x4,[x2] // number of areas
add x2,x2,8 // first area
mov x3,0 // loop counter
mov x0,x2
1: // display loop
ldr x0,[x2,x3, lsl 3] // address area
bl affichageMess
ldr x0,qAdrszCarriageReturn // display carriage return
bl affichageMess
add x3,x3,1 // counter + 1
cmp x3,x4 // end ?
blt 1b // no -> loop
b 100f
99: // display error message
ldr x0,qAdrszMessError
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
qAdrszString: .quad szString
//qAdrszFinalString: .quad szFinalString
qAdrszMessFinal: .quad szMessFinal
qAdrszMessError: .quad szMessError
qAdrszCarriageReturn: .quad szCarriageReturn
/*******************************************************************/
/* Separate string by separator into an array */
/* areas are store on the heap Linux */
/*******************************************************************/
/* x0 contains string address */
/* x1 contains separator character (, or . or : ) */
/* x0 returns table address with first item = number areas */
/* and other items contains pointer of each string */
stTokenize:
stp x1,lr,[sp,-16]! // save registers
mov x16,x0
mov x9,x1 // save separator
mov x14,0
1: // compute length string for place reservation on the heap
ldrb w12,[x0,x14]
cbz x12, 2f
add x14,x14,1
b 1b
2:
ldr x12,qTailleTable
add x15,x12,x14
and x15,x15,0xFFFFFFFFFFFFFFF0
add x15,x15,16 // align word on the heap
// place reservation on the heap
mov x0,0 // heap address
mov x8,BRK // call system linux 'brk'
svc 0 // call system
cmp x0,-1 // error call system
beq 100f
mov x14,x0 // save address heap begin = begin array
add x0,x0,x15 // reserve x15 byte on the heap
mov x8,BRK // call system linux 'brk'
svc 0
cmp x0,-1
beq 100f
// string copy on the heap
add x13,x14,x12 // behind the array
mov x0,x16
mov x1,x13
3: // loop copy string
ldrb w12,[x0],1 // read one byte and increment pointer one byte
strb w12,[x1],1 // store one byte and increment pointer one byte
cbnz x12,3b // end of string ? no -> loop
mov x0,#0
str x0,[x14]
str x13,[x14,8]
mov x12,#1 // areas counter
4: // loop load string character
ldrb w0,[x13]
cbz x0,5f // end string
cmp x0,x9 // separator ?
cinc x13,x13,ne // no -> next location
bne 4b // and loop
strb wzr,[x13] // store zero final of string
add x13,x13,1 // next character
add x12,x12,1 // areas counter + 1
str x13,[x14,x12, lsl #3] // store address area in the table at index x2
b 4b // and loop
5:
str x12,[x14] // store number areas
mov x0,x14 // returns array address
100:
ldp x1,lr,[sp],16 // restaur 2 registers
ret // return to address lr x30
qTailleTable: .quad 8 * NBPOSTESECLAT
/********************************************************/
/* File Include fonctions */
/********************************************************/
/* for this file see task include a file in language AArch64 assembly */
.include "../includeARM64.inc"
- Output:
Words are : Hello How Are You Today
ACL2
(defun split-at (xs delim)
(if (or (endp xs) (eql (first xs) delim))
(mv nil (rest xs))
(mv-let (before after)
(split-at (rest xs) delim)
(mv (cons (first xs) before) after))))
(defun split (xs delim)
(if (endp xs)
nil
(mv-let (before after)
(split-at xs delim)
(cons before (split after delim)))))
(defun css->strs (css)
(if (endp css)
nil
(cons (coerce (first css) 'string)
(css->strs (rest css)))))
(defun split-str (str delim)
(css->strs (split (coerce str 'list) delim)))
(defun print-with (strs delim)
(if (endp strs)
(cw "~%")
(progn$ (cw (first strs))
(cw (coerce (list delim) 'string))
(print-with (rest strs) delim))))
- Output:
> (print-with (split-str "Hello,How,Are,You,Today" #\,) #\.) Hello.How.Are.You.Today.
Action!
The user must type in the monitor the following command after compilation and before running the program!
SET EndProg=*
CARD EndProg ;required for ALLOCATE.ACT
INCLUDE "D2:ALLOCATE.ACT" ;from the Action! Tool Kit. You must type 'SET EndProg=*' from the monitor after compiling, but before running this program!
DEFINE PTR="CARD"
BYTE FUNC Split(CHAR ARRAY s CHAR c PTR ARRAY items)
BYTE i,count,start,len
CHAR ARRAY item
IF s(0)=0 THEN RETURN (0) FI
i=1 count=0
WHILE i<s(0)
DO
start=i
WHILE i<=s(0) AND s(i)#c
DO
i==+1
OD
len=i-start
item=Alloc(len+1)
SCopyS(item,s,start,i-1)
items(count)=item
count==+1
i==+1
OD
RETURN (count)
PROC Join(PTR ARRAY items BYTE count CHAR c CHAR ARRAY s)
BYTE i,pos
CHAR POINTER srcPtr,dstPtr
CHAR ARRAY item
s(0)=0
IF count=0 THEN RETURN FI
pos=1
FOR i=0 TO count-1
DO
item=items(i)
srcPtr=item+1
dstPtr=s+pos
MoveBlock(dstPtr,srcPtr,item(0))
pos==+item(0)
IF i<count-1 THEN
s(pos)='.
pos==+1
FI
OD
s(0)=pos-1
RETURN
PROC Clear(PTR ARRAY items BYTE POINTER count)
BYTE i
CHAR ARRAY item
IF count^=0 THEN RETURN FI
FOR i=0 TO count^-1
DO
item=items(i)
Free(item,item(0)+1)
OD
count^=0
RETURN
PROC Main()
CHAR ARRAY s="Hello,How,Are,You,Today"
CHAR ARRAY r(256)
PTR ARRAY items(100)
BYTE i,count
Put(125) PutE() ;clear screen
AllocInit(0)
count=Split(s,',,items)
Join(items,count,'.,r)
PrintF("Input:%E""%S""%E%E",s)
PrintE("Split:")
FOR i=0 TO count-1
DO
PrintF("""%S""",items(i))
IF i<count-1 THEN
Print(", ")
ELSE
PutE() PutE()
FI
OD
PrintF("Join:%E""%S""%E",r)
Clear(items,@count)
RETURN
- Output:
Screenshot from Atari 8-bit computer
Input: "Hello,How,Are,You,Today" Split: "Hello", "How", "Are", "You", "Today" Join: "Hello.How.Are.You.Today"
ActionScript
var hello:String = "Hello,How,Are,You,Today";
var tokens:Array = hello.split(",");
trace(tokens.join("."));
// Or as a one-liner
trace("Hello,How,Are,You,Today".split(",").join("."));
Ada
with Ada.Text_IO, Ada.Containers.Indefinite_Vectors, Ada.Strings.Fixed, Ada.Strings.Maps;
use Ada.Text_IO, Ada.Containers, Ada.Strings, Ada.Strings.Fixed, Ada.Strings.Maps;
procedure Tokenize is
package String_Vectors is new Indefinite_Vectors (Positive, String);
use String_Vectors;
Input : String := "Hello,How,Are,You,Today";
Start : Positive := Input'First;
Finish : Natural := 0;
Output : Vector := Empty_Vector;
begin
while Start <= Input'Last loop
Find_Token (Input, To_Set (','), Start, Outside, Start, Finish);
exit when Start > Finish;
Output.Append (Input (Start .. Finish));
Start := Finish + 1;
end loop;
for S of Output loop
Put (S & ".");
end loop;
end Tokenize;
ALGOL 68
main:(
OP +:= = (REF FLEX[]STRING in out, STRING item)VOID:(
[LWB in out: UPB in out+1]STRING new;
new[LWB in out: UPB in out]:=in out;
new[UPB new]:=item;
in out := new
);
PROC string split = (REF STRING beetles, STRING substr)[]STRING:(
""" Split beetles where substr is found """;
FLEX[1:0]STRING out;
INT start := 1, pos;
WHILE string in string(substr, pos, beetles[start:]) DO
out +:= STRING(beetles[start:start+pos-2]);
start +:= pos + UPB substr - 1
OD;
IF start > LWB beetles THEN
out +:= STRING(beetles[start:])
FI;
out
);
PROC char split = (REF STRING beetles, STRING chars)[]STRING: (
""" Split beetles where character is found in chars """;
FLEX[1:0]STRING out;
FILE beetlef;
associate(beetlef, beetles); # associate a FILE handle with a STRING #
make term(beetlef, chars); # make term: assign CSV string terminator #
PROC raise logical file end = (REF FILE f)BOOL: except logical file end;
on logical file end(beetlef, raise logical file end);
STRING solo;
DO
getf(beetlef, ($g$, solo));
out+:=solo;
getf(beetlef, ($x$)) # skip CHAR separator #
OD;
except logical file end:
SKIP;
out
);
STRING beetles := "John Lennon, Paul McCartney, George Harrison, Ringo Starr";
printf(($g"."$, string split(beetles, ", "),$l$));
printf(($g"."$, char split(beetles, ", "),$l$))
)
- Output:
John Lennon.Paul McCartney.George Harrison.Ringo Starr. John.Lennon..Paul.McCartney..George.Harrison..Ringo.Starr.
Amazing Hopper
Hopper provides instructions for separating and modifying tokens from a string. Let "s" be a string; "n" token number:
1) {n}, $(s) ==> gets token "n" from string "s".
2) {"word", n} $$(s) ==> replace token "n" of "s", with "word".
Note: the "splitnumber" macro cannot separate a number converted to a string by the "XTOSTR" function, because this function "rounds" the number to the decimal position by default.
#include <hopper.h>
#proto splitdate(_DATETIME_)
#proto splitnumber(_N_)
#proto split(_S_,_T_)
main:
s="this string will be separated into parts with space token separator"
aS=0,let( aS :=_split(s," "))
{","}toksep // set a new token separator
{"String: ",s}
{"\nArray:\n",aS},
{"\nSize="}size(aS),println // "size" return an array: {dims,#rows,#cols,#pages}
{"\nOriginal number: ",-125.489922},println
w=0,let(w:=_split number(-125.489922) )
{"Integer part: "}[1]get(w) // get first element from array "w"
{"\nDecimal part: "}[2]get(w),println // get second element from array "w"
{"\nDate by DATENOW(TODAY) macro: "},print
dt=0, let( dt :=_splitdate(datenow(TODAY);!puts)) // "!" keep first element from stack
{"\nDate: "}[1]get(dt)
{"\nTime: "}[2]get(dt),println
exit(0)
.locals
splitdate(_DATETIME_)
_SEP_=0,gettoksep,mov(_SEP_) // "gettoksep" return actual token separator
{","}toksep, // set a new token separator
_NEWARRAY_={}
{1},$( _DATETIME_ ),
{2},$( _DATETIME_ ),pushall(_NEWARRAY_)
{_SEP_}toksep // restore ols token separator
{_NEWARRAY_}
back
splitnumber(_X_)
part_int=0,part_dec=0,
{_X_},!trunc,mov(part_int),
minus(part_int), !sign,mul
xtostr,mov(part_dec), part_dec+=2, // "part_dec+=2", delete "0." from "part_dec"
{part_dec}xtonum,mov(part_dec)
_NEWARRAY_={},{part_int,part_dec},pushall(_NEWARRAY_)
{_NEWARRAY_}
back
split(_S_,_T_)
_NEWARRAY_={},_VAR1_=0,_SEP_=0,gettoksep,mov(_SEP_)
{_T_}toksep,totaltoken(_S_),
mov(_VAR1_), // for total tokens
_VAR2_=1, // for real position of tokens into the string
___SPLIT_ITER:
{_VAR2_}$( _S_ ),push(_NEWARRAY_)
++_VAR2_,--_VAR1_
{ _VAR1_ },jnz(___SPLIT_ITER) // jump to "___SPLIT_ITER" if "_VAR1_" is not zero.
clear(_VAR2_),clear(_VAR1_)
{_SEP_}toksep
{_NEWARRAY_}
back
- Output:
Output: String: this string will be separated into parts with space token separator Array: this,string,will,be,separated,into,parts,with,space,token,separator Size=1,11 Original number: -125.49 Integer part: -125 Decimal part: 489922 Date by DATENOW(TODAY) macro: 22/11/2021,18:41:20:13 Date: 22/11/2021 Time: 18:41:20:13
APL
'.',⍨¨ ','(≠⊆⊢)'abc,123,X' ⍝ [1] Do the split: ','(≠⊆⊢)'abc,123,X'; [2] append the periods: '.',⍨¨
abc. 123. X. ⍝ 3 strings (char vectors), each with a period at the end.
AppleScript
on run
intercalate(".", splitOn(",", "Hello,How,Are,You,Today"))
end run
-- splitOn :: String -> String -> [String]
on splitOn(strDelim, strMain)
set {dlm, my text item delimiters} to {my text item delimiters, strDelim}
set lstParts to text items of strMain
set my text item delimiters to dlm
return lstParts
end splitOn
-- intercalate :: String -> [String] -> String
on intercalate(strText, lstText)
set {dlm, my text item delimiters} to {my text item delimiters, strText}
set strJoined to lstText as text
set my text item delimiters to dlm
return strJoined
end intercalate
- Output:
Hello.How.Are.You.Today
Or,
set my text item delimiters to ","
set tokens to the text items of "Hello,How,Are,You,Today"
set my text item delimiters to "."
log tokens as text
- Output:
Hello.How.Are.You.Today
ARM Assembly
/* ARM assembly Raspberry PI */
/* program strTokenize.s */
/* Constantes */
.equ STDOUT, 1 @ Linux output console
.equ EXIT, 1 @ Linux syscall
.equ WRITE, 4 @ Linux syscall
.equ NBPOSTESECLAT, 20
/* Initialized data */
.data
szMessFinal: .asciz "Words are : \n"
szString: .asciz "Hello,How,Are,You,Today"
szMessError: .asciz "Error tokenize !!\n"
szCarriageReturn: .asciz "\n"
/* UnInitialized data */
.bss
/* code section */
.text
.global main
main:
ldr r0,iAdrszString @ string address
mov r1,#',' @ separator
bl stTokenize
cmp r0,#-1 @ error ?
beq 99f
mov r2,r0 @ table address
ldr r0,iAdrszMessFinal @ display message
bl affichageMess
ldr r4,[r2] @ number of areas
add r2,#4 @ first area
mov r3,#0 @ loop counter
1: @ display loop
ldr r0,[r2,r3, lsl #2] @ address area
bl affichageMess
ldr r0,iAdrszCarriageReturn @ display carriage return
bl affichageMess
add r3,#1 @ counter + 1
cmp r3,r4 @ end ?
blt 1b @ no -> loop
b 100f
99: @ display error message
ldr r0,iAdrszMessError
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
iAdrszString: .int szString
iAdrszFinalString: .int szFinalString
iAdrszMessFinal: .int szMessFinal
iAdrszMessError: .int szMessError
iAdrszCarriageReturn: .int szCarriageReturn
/******************************************************************/
/* display text with size calculation */
/******************************************************************/
/* r0 contains the address of the message */
affichageMess:
push {r0,r1,r2,r7,lr} @ save 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"
svc #0 @ call systeme
pop {r0,r1,r2,r7,lr} @ restaur des 2 registres
bx lr @ return
/*******************************************************************/
/* Separate string by separator into an array */
/* areas are store on the heap Linux */
/*******************************************************************/
/* r0 contains string address */
/* r1 contains separator character (, or . or : ) */
/* r0 returns table address with first item = number areas */
/* and other items contains pointer of each string */
stTokenize:
push {r1-r8,lr} @ save des registres
mov r6,r0
mov r8,r1 @ save separator
bl strLength @ length string for place reservation on the heap
mov r4,r0
ldr r5,iTailleTable
add r5,r0
and r5,#0xFFFFFFFC
add r5,#4 @ align word on the heap
@ place reservation on the heap
mov r0,#0 @ heap address
mov r7, #0x2D @ call system linux 'brk'
svc #0 @ call system
cmp r0,#-1 @ error call system
beq 100f
mov r3,r0 @ save address heap begin
add r0,r5 @ reserve r5 byte on the heap
mov r7, #0x2D @ call system linux 'brk'
svc #0
cmp r0,#-1
beq 100f
@ string copy on the heap
mov r0,r6
mov r1,r3
1: @ loop copy string
ldrb r2,[r0],#1 @ read one byte and increment pointer one byte
strb r2,[r1],#1 @ store one byte and increment pointer one byte
cmp r2,#0 @ end of string ?
bne 1b @ no -> loop
add r4,r3 @ r4 contains address table begin
mov r0,#0
str r0,[r4]
str r3,[r4,#4]
mov r2,#1 @ areas counter
2: @ loop load string character
ldrb r0,[r3]
cmp r0,#0
beq 3f @ end string
cmp r0,r8 @ separator ?
addne r3,#1 @ no -> next location
bne 2b @ and loop
mov r0,#0 @ store zero final of string
strb r0,[r3]
add r3,#1 @ next character
add r2,#1 @ areas counter + 1
str r3,[r4,r2, lsl #2] @ store address area in the table at index r2
b 2b @ and loop
3:
str r2,[r4] @ returns number areas
mov r0,r4
100:
pop {r1-r8,lr}
bx lr
iTailleTable: .int 4 * NBPOSTESECLAT
/***************************************************/
/* calcul size string */
/***************************************************/
/* r0 string address */
/* r0 returns size string */
strLength:
push {r1,r2,lr}
mov r1,#0 @ init counter
1:
ldrb r2,[r0,r1] @ load byte of string index r1
cmp r2,#0 @ end string ?
addne r1,#1 @ no -> +1 counter
bne 1b @ and loop
100:
mov r0,r1
pop {r1,r2,lr}
bx lr
Arturo
str: "Hello,How,Are,You,Today"
print join.with:"." split.by:"," str
- Output:
Hello.How.Are.You.Today
Astro
let text = 'Hello,How,Are,You,Today'
let tokens = text.split(||,||)
print tokens.join(with: '.')
AutoHotkey
string := "Hello,How,Are,You,Today"
stringsplit, string, string, `,
loop, % string0
{
msgbox % string%A_Index%
}
AWK
BEGIN {
s = "Hello,How,Are,You,Today"
split(s, arr, ",")
for(i=1; i < length(arr); i++) {
printf arr[i] "."
}
print
}
A more idiomatic way for AWK is
BEGIN { FS = "," }
{
for(i=1; i <= NF; i++) printf $i ".";
print ""
}
which "tokenize" each line of input and this is achieved by using "," as field separator
BASIC
Applesoft BASIC
100 T$ = "HELLO,HOW,ARE,YOU,TODAY"
110 GOSUB 200"TOKENIZE
120 FOR I = 1 TO N
130 PRINT A$(I) "." ;
140 NEXT
150 PRINT
160 END
200 IF N = 0 THEN DIM A$(256)
210 N = 1
220 A$(N) = "
230 FOR TI = 1 TO LEN(T$)
240 C$ = MID$(T$, TI, 1)
250 T = C$ = ","
260 IF T THEN C$ = "
270 N = N + T
280 IF T THEN A$(N) = C$
290 A$(N) = A$(N) + C$
300 NEXT TI
310 RETURN
BaCon
BaCon includes extensive support for delimited strings.
OPTION BASE 1
string$ = "Hello,How,Are,You,Today"
' Tokenize a string into an array
SPLIT string$ BY "," TO array$
' Print array elements with new delimiter
PRINT COIL$(i, UBOUND(array$), array$[i], ".")
' Or simply replace the delimiter
PRINT DELIM$(string$, ",", ".")
- Output:
prompt$ ./tokenize Hello.How.Are.You.Today Hello.How.Are.You.Today
BASIC256
instring$ = "Hello,How,Are,You,Today"
tokens$ = explode(instring$,",")
for i = 0 to tokens$[?]-1
print tokens$[i]; ".";
next i
end
BBC BASIC
INSTALL @lib$+"STRINGLIB"
text$ = "Hello,How,Are,You,Today"
n% = FN_split(text$, ",", array$())
FOR i% = 0 TO n%-1
PRINT array$(i%) "." ;
NEXT
PRINT
Chipmunk Basic
Solutions Applesoft BASIC and Commodore BASIC work without changes.
Commodore BASIC
Based on the AppleSoft BASIC version.
10 REM TOKENIZE A STRING ... ROSETTACODE.ORG
20 T$ = "HELLO,HOW,ARE,YOU,TODAY"
30 GOSUB 200, TOKENIZE
40 FOR I = 1 TO N
50 PRINT A$(I) "." ;
60 NEXT
70 PRINT
80 END
200 IF N = 0 THEN DIM A$(256)
210 N = 1
220 A$(N) = ""
230 FOR L = 1 TO LEN(T$)
240 C$ = MID$(T$, L, 1)
250 IF C$<>"," THEN A$(N) = A$(N) + C$: GOTO 270
260 N = N + 1
270 NEXT L
280 RETURN
FreeBASIC
sub tokenize( instring as string, tokens() as string, sep as string )
redim tokens(0 to 0) as string
dim as string*1 ch
dim as uinteger t=0
for i as uinteger = 1 to len(instring)
ch = mid(instring,i,1)
if ch = sep then
t = t + 1
redim preserve tokens(0 to t)
else
tokens(t) = tokens(t) + ch
end if
next i
return
end sub
dim as string instring = "Hello,How,Are,You,Today"
redim as string tokens(-1)
tokenize( instring, tokens(), "," )
for i as uinteger = 0 to ubound(tokens)
print tokens(i);".";
next i
Liberty BASIC
'Note that Liberty Basic's array usage can reach element #10 before having to DIM the array
For i = 0 To 4
array$(i) = Word$("Hello,How,Are,You,Today", (i + 1), ",")
array$ = array$ + array$(i) + "."
Next i
Print Left$(array$, (Len(array$) - 1))
MSX Basic
The Commodore BASIC solution works without any changes.
PowerBASIC
PowerBASIC has a few keywords that make parsing strings trivial: PARSE
, PARSE$
, and PARSECOUNT
. (PARSE$
, not shown here, is for extracting tokens one at a time, while PARSE
extracts all tokens at once into an array. PARSECOUNT
returns the number of tokens found.)
FUNCTION PBMAIN () AS LONG
DIM parseMe AS STRING
parseMe = "Hello,How,Are,You,Today"
REDIM parsed(PARSECOUNT(parseMe) - 1) AS STRING
PARSE parseMe, parsed() 'comma is default delimiter
DIM L0 AS LONG, outP AS STRING
outP = parsed(0)
FOR L0 = 1 TO UBOUND(parsed) 'could reuse parsecount instead of ubound
outP = outP & "." & parsed(L0)
NEXT
MSGBOX outP
END FUNCTION
PureBasic
As described
NewList MyStrings.s()
For i=1 To 5
AddElement(MyStrings())
MyStrings()=StringField("Hello,How,Are,You,Today",i,",")
Next i
ForEach MyStrings()
Print(MyStrings()+".")
Next
Still, easier would be
Print(ReplaceString("Hello,How,Are,You,Today",",","."))
QBasic
DIM parseMe AS STRING
parseMe = "Hello,How,Are,You,Today"
DIM tmpLng1 AS INTEGER, tmpLng2 AS INTEGER, parsedCount AS INTEGER
tmpLng2 = 1
parsedCount = -1
'count number of tokens
DO
tmpLng1 = INSTR(tmpLng2, parseMe, ",")
IF tmpLng1 THEN
parsedCount = parsedCount + 1
tmpLng2 = tmpLng1 + 1
ELSE
IF tmpLng2 < (LEN(parseMe) + 1) THEN parsedCount = parsedCount + 1
EXIT DO
END IF
LOOP
IF parsedCount > -1 THEN
REDIM parsed(parsedCount) AS STRING
tmpLng2 = 1
parsedCount = -1
'parse
DO
tmpLng1 = INSTR(tmpLng2, parseMe, ",")
IF tmpLng1 THEN
parsedCount = parsedCount + 1
parsed(parsedCount) = MID$(parseMe, tmpLng2, tmpLng1 - tmpLng2)
tmpLng2 = tmpLng1 + 1
ELSE
IF tmpLng2 < (LEN(parseMe) + 1) THEN
parsedCount = parsedCount + 1
parsed(parsedCount) = MID$(parseMe, tmpLng2)
END IF
EXIT DO
END IF
LOOP
PRINT parsed(0);
FOR L0 = 1 TO parsedCount
PRINT "."; parsed(L0);
NEXT
END IF
Run BASIC
text$ = "Hello,How,Are,You,Today"
FOR i = 1 to 5
textArray$(i) = word$(text$,i,",")
print textArray$(i);" ";
NEXT
VBScript
One liner
WScript.Echo Join(Split("Hello,How,Are,You,Today", ","), ".")
In fact, the Visual Basic solution (below) could have done the same, as Join() is available.
Visual Basic
Unlike PowerBASIC, there is no need to know beforehand how many tokens are in the string -- Split
automagically builds the array for you.
Sub Main()
Dim parseMe As String, parsed As Variant
parseMe = "Hello,How,Are,You,Today"
parsed = Split(parseMe, ",")
Dim L0 As Long, outP As String
outP = parsed(0)
For L0 = 1 To UBound(parsed)
outP = outP & "." & parsed(L0)
Next
MsgBox outP
End Sub
Batch File
@echo off
setlocal enabledelayedexpansion
call :tokenize %1 res
echo %res%
goto :eof
:tokenize
set str=%~1
:loop
for %%i in (%str%) do set %2=!%2!.%%i
set %2=!%2:~1!
goto :eof
Demo
>tokenize.cmd "Hello,How,Are,You,Today" Hello.How.Are.You.Today
BQN
Uses a splitting idiom from bqncrate.
Split ← (+`׬)⊸-∘= ⊔ ⊢
∾⟜'.'⊸∾´ ',' Split "Hello,How,Are,You,Today"
- Output:
"Hello.How.Are.You.Today"
Bracmat
Solution that employs string pattern matching to spot the commas
( "Hello,How,Are,You,Today":?String
& :?ReverseList
& whl
' ( @(!String:?element "," ?String)
& !element !ReverseList:?ReverseList
)
& !String:?List
& whl
' ( !ReverseList:%?element ?ReverseList
& (!element.!List):?List
)
& out$!List
)
Solution that starts by evaluating the input and employs the circumstance that the comma is a list constructing binary operator and that the string does not contain any other characters that are interpreted as operators on evaluation.
( get$("Hello,How,Are,You,Today",MEM):?CommaseparatedList
& :?ReverseList
& whl
' ( !CommaseparatedList:(?element,?CommaseparatedList)
& !element !ReverseList:?ReverseList
)
& !CommaseparatedList:?List
& whl
' ( !ReverseList:%?element ?ReverseList
& (!element.!List):?List
)
& out$!List
)
C
This example uses the strtok() function to separate the tokens. This function is destructive (replacing token separators with '\0'), so we have to make a copy of the string (using strdup()) before tokenizing. strdup() is not part of ANSI C, but is available on most platforms. It can easily be implemented with a combination of strlen(), malloc(), and strcpy().
#include<string.h>
#include<stdio.h>
#include<stdlib.h>
int main(void)
{
char *a[5];
const char *s="Hello,How,Are,You,Today";
int n=0, nn;
char *ds=strdup(s);
a[n]=strtok(ds, ",");
while(a[n] && n<4) a[++n]=strtok(NULL, ",");
for(nn=0; nn<=n; ++nn) printf("%s.", a[nn]);
putchar('\n');
free(ds);
return 0;
}
Another way to accomplish the task without the built-in string functions is to temporarily modify the separator character. This method does not need any additional memory, but requires the input string to be writeable.
#include<stdio.h>
typedef void (*callbackfunc)(const char *);
void doprint(const char *s) {
printf("%s.", s);
}
void tokenize(char *s, char delim, callbackfunc cb) {
char *olds = s;
char olddelim = delim;
while(olddelim && *s) {
while(*s && (delim != *s)) s++;
*s ^= olddelim = *s; // olddelim = *s; *s = 0;
cb(olds);
*s++ ^= olddelim; // *s = olddelim; s++;
olds = s;
}
}
int main(void)
{
char array[] = "Hello,How,Are,You,Today";
tokenize(array, ',', doprint);
return 0;
}
C#
string str = "Hello,How,Are,You,Today";
// or Regex.Split ( "Hello,How,Are,You,Today", "," );
// (Regex is in System.Text.RegularExpressions namespace)
string[] strings = str.Split(',');
Console.WriteLine(String.Join(".", strings));
C++
std::getline() is typically used to tokenize strings on a single-character delimiter
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
#include <iostream>
#include <algorithm>
int main()
{
std::string s = "Hello,How,Are,You,Today";
std::vector<std::string> v;
std::istringstream buf(s);
for(std::string token; getline(buf, token, ','); )
v.push_back(token);
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, "."));
std::cout << '\n';
}
C++ allows the user to redefine what is considered whitespace. If the delimiter is whitespace, tokenization becomes effortless.
#include <string>
#include <locale>
#include <sstream>
#include <vector>
#include <iterator>
#include <iostream>
#include <algorithm>
struct comma_ws : std::ctype<char> {
static const mask* make_table() {
static std::vector<mask> v(classic_table(), classic_table() + table_size);
v[','] |= space; // comma will be classified as whitespace
return &v[0];
}
comma_ws(std::size_t refs = 0) : ctype<char>(make_table(), false, refs) {}
};
int main()
{
std::string s = "Hello,How,Are,You,Today";
std::istringstream buf(s);
buf.imbue(std::locale(buf.getloc(), new comma_ws));
std::istream_iterator<std::string> beg(buf), end;
std::vector<std::string> v(beg, end);
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, "."));
std::cout << '\n';
}
The boost library has multiple options for easy tokenization.
#include <string>
#include <vector>
#include <iterator>
#include <algorithm>
#include <iostream>
#include <boost/tokenizer.hpp>
int main()
{
std::string s = "Hello,How,Are,You,Today";
boost::tokenizer<> tok(s);
std::vector<std::string> v(tok.begin(), tok.end());
copy(v.begin(), v.end(), std::ostream_iterator<std::string>(std::cout, "."))
std::cout << '\n';
}
C++20 and C++23 drastically improve the ergonomics of simple manipulation of ranges.
#include <string>
#include <ranges>
#include <iostream>
int main() {
std::string s = "Hello,How,Are,You,Today";
s = s // Assign the final string back to the string variable
| std::views::split(',') // Produce a range of the comma separated words
| std::views::join_with('.') // Concatenate the words into a single range of characters
| std::ranges::to<std::string>(); // Convert the range of characters into a regular string
std::cout << s;
}
Ceylon
shared void tokenizeAString() {
value input = "Hello,How,Are,You,Today";
value tokens = input.split(','.equals);
print(".".join(tokens));
}
CFEngine
bundle agent main
{
reports:
"${with}" with => join(".", splitstring("Hello,How,Are,You,Today", ",", 99));
}
- Output:
cf-agent -KIf ./tokenize-a-string.cf R: Hello.How.Are.You.Today
See https://docs.cfengine.com/docs/master/reference-functions.html for a complete list of available functions.
Clojure
Using native Clojure functions and Java Interop:
(apply str (interpose "." (.split #"," "Hello,How,Are,You,Today")))
Using the clojure.string library:
(clojure.string/join "." (clojure.string/split "Hello,How,Are,You,Today" #","))
CLU
% This iterator splits the string on a given character,
% and returns each substring in order.
tokenize = iter (s: string, c: char) yields (string)
while ~string$empty(s) do
next: int := string$indexc(c, s)
if next = 0 then
yield(s)
break
else
yield(string$substr(s, 1, next-1))
s := string$rest(s, next+1)
end
end
end tokenize
start_up = proc ()
po: stream := stream$primary_output()
str: string := "Hello,How,Are,You,Today"
for part: string in tokenize(str, ',') do
stream$putl(po, part || ".")
end
end start_up
- Output:
Hello. How. Are. You. Today.
COBOL
This can be made to handle more complex cases; UNSTRING allows multiple delimiters, capture of which delimiter was used for each field, a POINTER for starting position (set on ending), along with match TALLYING.
identification division.
program-id. tokenize.
environment division.
configuration section.
repository.
function all intrinsic.
data division.
working-storage section.
01 period constant as ".".
01 cmma constant as ",".
01 start-with.
05 value "Hello,How,Are,You,Today".
01 items.
05 item pic x(6) occurs 5 times.
procedure division.
tokenize-main.
unstring start-with delimited by cmma
into item(1) item(2) item(3) item(4) item(5)
display trim(item(1)) period trim(item(2)) period
trim(item(3)) period trim(item(4)) period
trim(item(5))
goback.
end program tokenize.
- Output:
prompt$ cobc -xj tokenize.cob Hello.How.Are.You.Today
CoffeeScript
arr = "Hello,How,Are,You,Today".split ","
console.log arr.join "."
ColdFusion
Classic tag based CFML
<cfoutput>
<cfset wordListTag = "Hello,How,Are,You,Today">
#Replace( wordListTag, ",", ".", "all" )#
</cfoutput>
- Output:
"Hello.How.Are.You.Today"
Script Based CFML
<cfscript>
wordList = "Hello,How,Are,You,Today";
splitList = replace( wordList, ",", ".", "all" );
writeOutput( splitList );
</cfscript>
- Output:
"Hello.How.Are.You.Today"
Common Lisp
There are libraries out there that handle splitting (e.g., SPLIT-SEQUENCE, and the more-general CL-PPCRE), but this is a simple one-off, too. When the words are written with write-with-periods, there is no final period after the last word.
(defun comma-split (string)
(loop for start = 0 then (1+ finish)
for finish = (position #\, string :start start)
collecting (subseq string start finish)
until (null finish)))
(defun write-with-periods (strings)
(format t "~{~A~^.~}" strings))
Cowgol
include "cowgol.coh";
include "strings.coh";
# Tokenize a string. Note: the string is modified in place.
sub tokenize(sep: uint8, str: [uint8], out: [[uint8]]): (length: intptr) is
length := 0;
loop
[out] := str;
out := @next out;
length := length + 1;
while [str] != 0 and [str] != sep loop
str := @next str;
end loop;
if [str] == sep then
[str] := 0;
str := @next str;
else
break;
end if;
end loop;
end sub;
# The string
var string: [uint8] := "Hello,How,Are,You,Today";
# Make a mutable copy
var buf: uint8[64];
CopyString(string, &buf[0]);
# Tokenize the copy
var parts: [uint8][64];
var length := tokenize(',', &buf[0], &parts[0]) as @indexof parts;
# Print each string
var i: @indexof parts := 0;
while i < length loop
print(parts[i]);
print(".\n");
i := i + 1;
end loop;
- Output:
Hello. How. Are. You. Today.
Crystal
puts "Hello,How,Are,You,Today".split(',').join('.')
- Output:
Hello.How.Are.You.Today
D
void main() {
import std.stdio, std.string;
"Hello,How,Are,You,Today".split(',').join('.').writeln;
}
- Output:
Hello.How.Are.You.Today
Delphi
Using String.split
program Tokenize_a_string;
{$APPTYPE CONSOLE}
uses
System.SysUtils;
var
Words: TArray<string>;
begin
Words := 'Hello,How,Are,You,Today'.Split([',']);
Writeln(string.Join(#10, Words));
Readln;
end.
Using TStringList
program TokenizeString;
{$APPTYPE CONSOLE}
uses
Classes;
var
tmp: TStringList;
i: Integer;
begin
// Instantiate TStringList class
tmp := TStringList.Create;
try
{ Use the TStringList's CommaText property to get/set
all the strings in a single comma-delimited string }
tmp.CommaText := 'Hello,How,Are,You,Today';
{ Now loop through the TStringList and display each
token on the console }
for i := 0 to Pred(tmp.Count) do
Writeln(tmp[i]);
finally
tmp.Free;
end;
Readln;
end.
The result is:
Hello
How
Are
You
Today
dt
"Hello,How,Are,You,Today" "," split "." join pl
Dyalect
var str = "Hello,How,Are,You,Today"
var strings = str.Split(',')
print(values: strings, separator: ".")
- Output:
Hello.How.Are.You.Today
Déjà Vu
!print join "." split "Hello,How,Are,You,Today" ","
- Output:
Hello.How.Are.You.Today
E
".".rjoin("Hello,How,Are,You,Today".split(","))
EasyLang
s$ = "Hello,How,Are,You,Today"
a$[] = strsplit s$ ","
for s$ in a$[]
write s$ & "."
.
Elena
ELENA 6.x:
import system'routines;
import extensions;
public program()
{
auto string := "Hello,How,Are,You,Today";
string.splitBy(",").forEach::(s)
{
console.print(s,".")
}
}
Elixir
tokens = String.split("Hello,How,Are,You,Today", ",")
IO.puts Enum.join(tokens, ".")
EMal
text value = "Hello,How,Are,You,Today"
List tokens = value.split(",")
writeLine(tokens.join("."))
# single line version
writeLine("Hello,How,Are,You,Today".split(",").join("."))
- Output:
Hello.How.Are.You.Today Hello.How.Are.You.Today
Erlang
-module(tok).
-export([start/0]).
start() ->
Lst = string:tokens("Hello,How,Are,You,Today",","),
io:fwrite("~s~n", [string:join(Lst,".")]),
ok.
Euphoria
function split(sequence s, integer c)
sequence out
integer first, delim
out = {}
first = 1
while first<=length(s) do
delim = find_from(c,s,first)
if delim = 0 then
delim = length(s)+1
end if
out = append(out,s[first..delim-1])
first = delim + 1
end while
return out
end function
sequence s
s = split("Hello,How,Are,You,Today", ',')
for i = 1 to length(s) do
puts(1, s[i] & ',')
end for
F#
System.String.Join(".", "Hello,How,Are,You,Today".Split(','))
Factor
"Hello,How,Are,You,Today" "," split "." join print
Falcon
VBA/Python programmer's approach to this solution, not sure if it's the most falconic way
/* created by Aykayayciti Earl Lamont Montgomery
April 9th, 2018 */
a = []
a = strSplit("Hello,How,Are,You,Today", ",")
index = 0
start = 0
b = ""
for index in [ start : len(a)-1 : 1 ]
b = b + a[index] + "."
end
> b
- Output:
Hello.How.Are.You. [Finished in 0.2s]
Fantom
A string can be split on a given character, returning a list of the intervening strings.
class Main
{
public static Void main ()
{
str := "Hello,How,Are,You,Today"
words := str.split(',')
words.each |Str word|
{
echo ("${word}. ")
}
}
}
Fennel
(fn string.split [self sep]
(let [pattern (string.format "([^%s]+)" sep)
fields {}]
(self:gsub pattern (fn [c] (tset fields (+ 1 (length fields)) c)))
fields))
(let [str "Hello,How,Are,You,Today"]
(print (table.concat (str:split ",") ".")))
Forth
There is no standard string split routine, but it is easily written. The results are saved temporarily to the dictionary.
: split ( str len separator len -- tokens count )
here >r 2swap
begin
2dup 2, \ save this token ( addr len )
2over search \ find next separator
while
dup negate here 2 cells - +! \ adjust last token length
2over nip /string \ start next search past separator
repeat
2drop 2drop
r> here over - ( tokens length )
dup negate allot \ reclaim dictionary
2 cells / ; \ turn byte length into token count
: .tokens ( tokens count -- )
1 ?do dup 2@ type ." ." cell+ cell+ loop 2@ type ;
s" Hello,How,Are,You,Today" s" ," split .tokens \ Hello.How.Are.You.Today
Fortran
PROGRAM Example
CHARACTER(23) :: str = "Hello,How,Are,You,Today"
CHARACTER(5) :: word(5)
INTEGER :: pos1 = 1, pos2, n = 0, i
DO
pos2 = INDEX(str(pos1:), ",")
IF (pos2 == 0) THEN
n = n + 1
word(n) = str(pos1:)
EXIT
END IF
n = n + 1
word(n) = str(pos1:pos1+pos2-2)
pos1 = pos2+pos1
END DO
DO i = 1, n
WRITE(*,"(2A)", ADVANCE="NO") TRIM(word(i)), "."
END DO
END PROGRAM Example
Frink
println[join[".", split[",", "Hello,How,Are,You,Today"]]]
FutureBasic
window 1, @"Tokenize a string"
void local fn DoIt
CFStringRef string = @"Hello,How,Are,You,Today"
CFArrayRef tokens = fn StringComponentsSeparatedByString( string, @"," )
print fn ArrayComponentsJoinedByString( tokens, @"." )
end fn
fn DoIt
HandleEvents
- Output:
Hello.How.Are.You.Today
Gambas
Click this link to run this code
Public Sub Main()
Dim sString As String[] = Split("Hello,How,Are,You,Today")
Print sString.Join(".")
End
Output:
Hello.How.Are.You.Today
GAP
SplitString("Hello,How,Are,You,Today", ",");
# [ "Hello", "How", "Are", "You", "Today" ]
JoinStringsWithSeparator(last, ".");
# "Hello.How.Are.You.Today"
Genie
[indent=4]
init
str:string = "Hello,How,Are,You,Today"
words:array of string[] = str.split(",")
joined:string = string.joinv(".", words)
print joined
- Output:
prompt$ valac tokenize.gs prompt$ ./tokenize Hello.How.Are.You.Today
Go
package main
import (
"fmt"
"strings"
)
func main() {
s := "Hello,How,Are,You,Today"
fmt.Println(strings.Join(strings.Split(s, ","), "."))
}
Groovy
println 'Hello,How,Are,You,Today'.split(',').join('.')
Haskell
Using Data.Text
{-# OPTIONS_GHC -XOverloadedStrings #-}
import Data.Text (splitOn,intercalate)
import qualified Data.Text.IO as T (putStrLn)
main = T.putStrLn . intercalate "." $ splitOn "," "Hello,How,Are,You,Today"
Output: Hello.How.Are.You.Today
Alternate Solution
The necessary operations are unfortunately not in the standard library (yet), but simple to write:
splitBy :: (a -> Bool) -> [a] -> [[a]]
splitBy _ [] = []
splitBy f list = first : splitBy f (dropWhile f rest) where
(first, rest) = break f list
splitRegex :: Regex -> String -> [String]
joinWith :: [a] -> [[a]] -> [a]
joinWith d xs = concat $ List.intersperse d xs
-- "concat $ intersperse" can be replaced with "intercalate" from the Data.List in GHC 6.8 and later
putStrLn $ joinWith "." $ splitBy (== ',') $ "Hello,How,Are,You,Today"
-- using regular expression to split:
import Text.Regex
putStrLn $ joinWith "." $ splitRegex (mkRegex ",") $ "Hello,How,Are,You,Today"
Tokenizing can also be realized by using unfoldr and break:
*Main> mapM_ putStrLn $ takeWhile (not.null) $ unfoldr (Just . second(drop 1). break (==',')) "Hello,How,Are,You,Today"
Hello
How
Are
You
Today
- You need to import the modules Data.List and Control.Arrow
As special cases, splitting / joining by white space and by newlines are provided by the Prelude functions words
/ unwords
and lines
/ unlines
, respectively.
HicEst
CHARACTER string="Hello,How,Are,You,Today", list
nWords = INDEX(string, ',', 256) + 1
maxWordLength = LEN(string) - 2*nWords
ALLOCATE(list, nWords*maxWordLength)
DO i = 1, nWords
EDIT(Text=string, SePaRators=',', item=i, WordEnd, CoPyto=CHAR(i, maxWordLength, list))
ENDDO
DO i = 1, nWords
WRITE(APPend) TRIM(CHAR(i, maxWordLength, list)), '.'
ENDDO
Icon and Unicon
- Output:
->ss Hello.How.Are.You.Today. ->
A Unicon-specific solution is:
import util
procedure main()
A := stringToList("Hello,How,Are,You,Today", ',')
every writes(!A,".")
write()
end
One wonders what the expected output should be with the input string ",,,,".
Io
"Hello,How,Are,You,Today" split(",") join(".") println
J
s=: 'Hello,How,Are,You,Today'
] t=: <;._1 ',',s
+-----+---+---+---+-----+
|Hello|How|Are|You|Today|
+-----+---+---+---+-----+
; t,&.>'.'
Hello.How.Are.You.Today.
'.' (I.','=s)}s NB. two steps combined
Hello.How.Are.You.Today
Alternatively using the system library/script strings
require 'strings'
',' splitstring s
+-----+---+---+---+-----+
|Hello|How|Are|You|Today|
+-----+---+---+---+-----+
'.' joinstring ',' splitstring s
Hello.How.Are.You.Today
splitstring and joinstring also work with longer "delimiters":
'"'([ ,~ ,) '","' joinstring ',' splitstring s
"Hello","How","Are","You","Today"
But, of course, this could be solved with simple string replacement:
rplc&',.' s
Hello.How.Are.You.Today
The task asks us to Separate the string "Hello,How,Are,You,Today" by commas into an array (or list) so that each element of it stores a different word. but for many purposes the original string is an adequate data structure. Note also that given a string, a list of "word start" indices and "word length" integers can be logically equivalent to having an "array of words" -- and, depending on implementation details may be a superior or inferior choice to some other representation. But, in current definition of this task, the concept of "word length" plays no useful role.
Note also that J provides several built-in concepts of parsing: split on leading delimiter, split on trailing delimiter, split J language words. Also, it's sometimes more efficient to append to a string than to prepend to it. So a common practice for parsing on an embedded delimiter is to append a copy of the delimiter to the string and then use the appended result:
fn;._2 string,','
Here fn is applied to each ',' delimited substring and the results are assembled into an array.
Or, factoring out the names:
fn ((;._2)(@(,&','))) string
Java
There are multiple ways to tokenize a String in Java.
The first is by splitting the String into an array of Strings. The separator is actually a regular expression so you could do very powerful things with this, but make sure to escape any characters with special meaning in regex.
String toTokenize = "Hello,How,Are,You,Today";
System.out.println(String.join(".", toTokenize.split(",")));
String toTokenize = "Hello,How,Are,You,Today";
String words[] = toTokenize.split(",");//splits on one comma, multiple commas yield multiple splits
//toTokenize.split(",+") if you want to ignore empty fields
for(int i=0; i<words.length; i++) {
System.out.print(words[i] + ".");
}
The other way is to use StringTokenizer. It will skip any empty tokens. So if two commas are given in line, there will be an empty string in the array given by the split function, but no empty string with the StringTokenizer object. This method takes more code to use, but allows you to get tokens incrementally instead of all at once.
String toTokenize = "Hello,How,Are,You,Today";
StringTokenizer tokenizer = new StringTokenizer(toTokenize, ",");
while(tokenizer.hasMoreTokens()) {
System.out.print(tokenizer.nextToken() + ".");
}
JavaScript
console.log(
"Hello,How,Are,You,Today"
.split(",")
.join(".")
);
A more advanced program to tokenise strings:
const Tokeniser = (function () {
const numberRegex = /-?(\d+\.d+|\d+\.|\.\d+|\d+)((e|E)(\+|-)?\d+)?/g;
return {
settings: {
operators: ["<", ">", "=", "+", "-", "*", "/", "?", "!"],
separators: [",", ".", ";", ":", " ", "\t", "\n"],
groupers: ["(", ")", "[", "]", "{", "}", '"', '"', "'", "'"],
keepWhiteSpacesAsTokens: false,
trimTokens: true
},
isNumber: function (value) {
if (typeof value === "number") {
return true;
} else if (typeof value === "string") {
return numberRegex.test(value);
}
return false;
},
closeGrouper: function (grouper) {
if (this.settings.groupers.includes(grouper)) {
return this.settings.groupers[this.settings.groupers.indexOf(grouper) + 1];
}
return null;
},
tokenType: function (char) {
if (this.settings.operators.includes(char)) {
return "operator";
} else if (this.settings.separators.includes(char)) {
return "separator";
} else if (this.settings.groupers.includes(char)) {
return "grouper";
}
return "other";
},
parseString: function (str) {
if (typeof str !== "string") {
if (str === null) {
return "null";
} if (typeof str === "object") {
str = JSON.stringify(str);
} else {
str = str.toString();
}
}
let tokens = [], _tempToken = "";
for (let i = 0; i < str.length; i++) {
if (this.tokenType(_tempToken) !== this.tokenType(str[i]) || this.tokenType(str[i]) === "separator") {
if (_tempToken.trim() !== "") {
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken);
} else if (this.settings.keepWhiteSpacesAsTokens) {
tokens.push(_tempToken);
}
_tempToken = str[i];
if (this.tokenType(_tempToken) === "separator") {
if (_tempToken.trim() !== "") {
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken);
} else if (this.settings.keepWhiteSpacesAsTokens) {
tokens.push(_tempToken);
}
_tempToken = "";
}
} else {
_tempToken += str[i];
}
}
if (_tempToken.trim() !== "") {
tokens.push(this.settings.trimTokens ? _tempToken.trim() : _tempToken);
} else if (this.settings.keepWhiteSpacesAsTokens) {
tokens.push(_tempToken);
}
return tokens.filter((token) => token !== "");
}
};
})();
Output:
Tokeniser.parseString("Hello,How,Are,You,Today");
// -> ['Hello', ',', 'How', ',', 'Are', ',', 'You', ',', 'Today']
jq
split(",") | join(".")
Example:
$ jq -r 'split(",") | join(".")'
"Hello,How,Are,You,Today"
Hello.How.Are.You.Today
Jsish
Being in the ECMAScript family, Jsi is blessed with many easy to use character, string and array manipulation routines.
puts('Hello,How,Are,You,Today'.split(',').join('.'))
- Output:
Hello.How.Are.You.Today
Julia
s = "Hello,How,Are,You,Today"
a = split(s, ",")
t = join(a, ".")
println("The string \"", s, "\"")
println("Splits into ", a)
println("Reconstitutes to \"", t, "\"")
- Output:
The string "Hello,How,Are,You,Today" Splits into SubString{ASCIIString}["Hello","How","Are","You","Today"] Reconstitutes to "Hello.How.Are.You.Today"
K
words: "," \: "Hello,How,Are,You,Today"
"." /: words
- Output:
"Hello.How.Are.You.Today"
","\"Hello,How,Are,You,Today"
("Hello"
"How"
"Are"
"You"
"Today")
Klingphix
( "Hello,How,Are,You,Today" "," ) split len [ get print "." print ] for
nl "End " input
- Output:
Hello.How.Are.You.Today. End
Kotlin
fun main(args: Array<String>) {
val input = "Hello,How,Are,You,Today"
println(input.split(',').joinToString("."))
}
- Output:
Hello.How.Are.You.Today
Ksh
#!/bin/ksh
# Tokenize a string
# # Variables:
#
string="Hello,How,Are,You,Today"
inputdelim=\, # a comma
outputdelim=\. # a period
# # Functions:
#
# # Function _tokenize(str, indelim, outdelim)
#
function _tokenize {
typeset _str ; _str="$1"
typeset _ind ; _ind="$2"
typeset _outd ; _outd="$3"
while [[ ${_str} != ${_str/${_ind}/${_outd}} ]]; do
_str=${_str/${_ind}/${_outd}}
done
echo "${_str}"
}
######
# main #
######
_tokenize "${string}" "${inputdelim}" "${outputdelim}"
- Output:
Hello.How.Are.You.Today
LabVIEW
To tokenize the string, we use the Search/Split String function to split the string by its first comma. Add the beginning (up to, but not including the comma) to the end of the array, remove the first comma from the rest of the string, and pass it back through the shift register to the loop's next iteration. This is repeated until the string is empty. Printing is a simple matter of concatenation.
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.
Lambdatalk
{S.replace , by . in Hello,How,Are,You,Today}.
-> Hello.How.Are.You.Today.
Lang
$str = Hello,How,Are,You,Today
fn.println(fn.join(\., fn.split($str, \,)))
Lang5
'Hello,How,Are,You,Today ', split '. join .
LDPL
DATA:
explode/words is text vector
explode/index is number
explode/string is text
explode/length is number
explode/stringlength is number
explode/current-token is text
explode/char is text
explode/separator is text
i is number
PROCEDURE:
# Ask for a sentence
display "Enter a sentence: "
accept explode/string
# Declare explode Subprocedure
# Splits a text into a text vector by a certain delimiter
# Input parameters:
# - explode/string: the string to explode (destroyed)
# - explode/separator: the character used to separate the string (preserved)
# Output parameters:
# - explode/words: vector of splitted words
# - explode/length: length of explode/words
sub-procedure explode
join explode/string and explode/separator in explode/string
store length of explode/string in explode/stringlength
store 0 in explode/index
store 0 in explode/length
store "" in explode/current-token
while explode/index is less than explode/stringlength do
get character at explode/index from explode/string in explode/char
if explode/char is equal to explode/separator then
store explode/current-token in explode/words:explode/length
add explode/length and 1 in explode/length
store "" in explode/current-token
else
join explode/current-token and explode/char in explode/current-token
end if
add explode/index and 1 in explode/index
repeat
subtract 1 from explode/length in explode/length
end sub-procedure
# Separate the entered string
store " " in explode/separator
call sub-procedure explode
while i is less than or equal to explode/length do
display explode/words:i crlf
add 1 and i in i
repeat
LFE
> (set split (string:tokens "Hello,How,Are,You,Today" ","))
("Hello" "How" "Are" "You" "Today")
> (string:join split ".")
"Hello.How.Are.You.Today"
Lingo
input = "Hello,How,Are,You,Today"
_player.itemDelimiter = ","
output = ""
repeat with i = 1 to input.item.count
put input.item[i]&"." after output
end repeat
delete the last char of output
put output
-- "Hello.How.Are.You.Today"
Logo
to split :str :sep
output parse map [ifelse ? = :sep ["| |] [?]] :str
end
This form is more robust, doing the right thing if there are embedded spaces.
to split :str :by [:acc []] [:w "||]
if empty? :str [output lput :w :acc]
ifelse equal? first :str :by ~
[output (split butfirst :str :by lput :w :acc)] ~
[output (split butfirst :str :by :acc lput first :str :w)]
end
? show split "Hello,How,Are,You,Today ",
[Hello How Are You Today]
Logtalk
Using Logtalk built-in support for Definite Clause Grammars (DCGs) and representing the strings as atoms for readbility:
:- object(spliting).
:- public(convert/2).
:- mode(convert(+atom, -atom), one).
convert(StringIn, StringOut) :-
atom_chars(StringIn, CharactersIn),
phrase(split(',', Tokens), CharactersIn),
phrase(split('.', Tokens), CharactersOut),
atom_chars(StringOut, CharactersOut).
split(Separator, [t([Character| Characters])| Tokens]) -->
[Character], {Character \== Separator}, split(Separator, [t(Characters)| Tokens]).
split(Separator, [t([])| Tokens]) -->
[Separator], split(Separator, Tokens).
split(_, [t([])]) -->
[].
% the look-ahead in the next rule prevents adding a spurious separator at the end
split(_, []), [Character] -->
[Character].
:- end_object.
- Output:
| ?- spliting::convert('Hello,How,Are,You,Today', Converted). Converted = 'Hello.How.Are.You.Today' yes
Lua
Split function callously stolen from the lua-users wiki
function string:split (sep)
local sep, fields = sep or ":", {}
local pattern = string.format("([^%s]+)", sep)
self:gsub(pattern, function(c) fields[#fields+1] = c end)
return fields
end
local str = "Hello,How,Are,You,Today"
print(table.concat(str:split(","), "."))
- Output:
Hello.How.Are.You.Today
M2000 Interpreter
Module CheckIt {
Function Tokenize$(s){
\\ letter$ pop a string from stack of values
\\ shift 2 swap top two values on stack of values
fold1=lambda m=1 ->{
shift 2 :if m=1 then m=0:drop: push letter$ else push letter$+"."+letter$
}
=s#fold$(fold1)
}
Print Tokenize$(piece$("Hello,How,Are,You,Today",",")) ="Hello.How.Are.You.Today" ' true
}
Checkit
M4
define(`s',`Hello,How,Are,You,Today')
define(`set',`define(`$1[$2]',`$3')')
define(`get',`defn($1[$2])')
define(`n',0)
define(`fill',
`set(a,n,$1)`'define(`n',incr(n))`'ifelse(eval($#>1),1,`fill(shift($@))')')
fill(s)
define(`j',0)
define(`show',
`ifelse(eval(j<n),1,`get(a,j).`'define(`j',incr(j))`'show')')
show
- Output:
Hello.How.Are.You.Today.
Maple
StringTools:-Join(StringTools:-Split("Hello,How,Are,You,Today", ","),".");
- Output:
"Hello.How.Are.You.Today"
Mathematica/Wolfram Language
StringJoin@StringSplit["Hello,How,Are,You,Today", "," -> "."]
MATLAB / Octave
s=strsplit('Hello,How,Are,You,Today',',')
fprintf(1,'%s.',s{:})
- Output:
Hello.How.Are.You.Today.
Maxima
l: split("Hello,How,Are,You,Today", ",")$
printf(true, "~{~a~^.~}~%", l)$
A slightly different way
split("Hello,How,Are,You,Today",",")$
simplode(%,".");
- Output:
"Hello.How.Are.You.Today"
MAXScript
output = ""
for word in (filterString "Hello,How,Are,You,Today" ",") do
(
output += (word + ".")
)
format "%\n" output
Mercury
:- module string_tokenize.
:- interface.
:- import_module io.
:- pred main(io::di, io::uo) is det.
:- implementation.
:- import_module list, string.
main(!IO) :-
Tokens = string.split_at_char((','), "Hello,How,Are,You,Today"),
io.write_list(Tokens, ".", io.write_string, !IO),
io.nl(!IO).
min
"Hello,How,Are,You,Today" "," split "." join print
MiniScript
tokens = "Hello,How,Are,You,Today".split(",")
print tokens.join(".")
MMIX
sep IS ','
EOS IS 0
NL IS 10
// main registers
p IS $255
tp GREG
c GREG
t GREG
LOC Data_Segment
GREG @
Text BYTE "Hello,How,Are,You,Today",EOS
token BYTE 0
eot IS @+255
LOC #100 % main () {
Main LDA p,Text %
LDA tp,token % initialize pointers
2H LDBU c,p % DO get char
BZ c,5F % break if char == EOS
CMP t,c,sep % if char != sep then
PBNZ t,3F % store char
SET t,NL % terminate token with NL,EOS
STBU t,tp
SET t,EOS
INCL tp,1
STBU t,tp
JMP 4F % continue
3H STBU c,tp % store char
4H INCL tp,1 % update pointers
INCL p,1
JMP 2B % LOOP
5H SET t,NL % terminate last token and buffer
STBU t,tp
SET t,EOS
INCL tp,1
STBU t,tp
% next part is not really necessary
% program runs only once
% INCL tp,1 % terminate buffer
% STBU t,tp
LDA tp,token % reset token pointer
% REPEAT
2H ADD p,tp,0 % start of token
TRAP 0,Fputs,StdOut % output token
ADD tp,tp,p
INCL tp,1 % step to next token
LDBU t,tp
PBNZ t,2B % UNTIL EOB(uffer)
TRAP 0,Halt,0
- Output:
~/MIX/MMIX/Progs> mmix tokenizing Hello How Are You Today
Modula-3
MODULE Tokenize EXPORTS Main;
IMPORT IO, TextConv;
TYPE Texts = REF ARRAY OF TEXT;
VAR tokens: Texts;
string := "Hello,How,Are,You,Today";
sep := SET OF CHAR {','};
BEGIN
tokens := NEW(Texts, TextConv.ExplodedSize(string, sep));
TextConv.Explode(string, tokens^, sep);
FOR i := FIRST(tokens^) TO LAST(tokens^) DO
IO.Put(tokens[i] & ".");
END;
IO.Put("\n");
END Tokenize.
MUMPS
TOKENS
NEW I,J,INP
SET INP="Hello,how,are,you,today"
NEW I FOR I=1:1:$LENGTH(INP,",") SET INP(I)=$PIECE(INP,",",I)
NEW J FOR J=1:1:I WRITE INP(J) WRITE:J'=I "."
KILL I,J,INP // Kill is optional. "New" variables automatically are killed on "Quit"
QUIT
In use:
USER>D TOKENS^ROSETTA Hello.how.are.you.today
Nanoquery
for word in "Hello,How,Are,You,Today".split(",")
print word + "."
end
- Output:
Hello.How.Are.You.Today.
Nemerle
using System;
using System.Console;
using Nemerle.Utility.NString;
module Tokenize
{
Main() : void
{
def cswords = "Hello,How,Are,You,Today";
WriteLine(Concat(".", $[s | s in cswords.Split(',')]));
// Split() produces an array while Concat() consumes a list
// a quick in place list comprehension takes care of that
}
}
NetRexx
/*NetRexx program *****************************************************
* 20.08.2012 Walter Pachl derived from REXX Version 3
**********************************************************************/
sss='Hello,How,Are,You,Today'
Say 'input string='sss
Say ''
Say 'Words in the string:'
ss =sss.translate(' ',',')
Loop i=1 To ss.words()
Say ss.word(i)'.'
End
Say 'End-of-list.'
Output as in REXX version
NewLISP
(print (join (parse "Hello,How,Are,You,Today" ",") "."))
Nial
Example for Q'Nial7, using set "nodecor
and set "diagram
switches for better display of the array structure:
Define Array with input string:
s := 'Hello,How,Are,You,Today'
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|H|e|l|l|o|,|H|o|w|,|A|r|e|,|Y|o|u|,|T|o|d|a|y|
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Split string at the commas:
t := s eachall = `, cut s
+-----------+-------+-------+-------+-----------+
|+-+-+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+-+-+|
||H|e|l|l|o|||H|o|w|||A|r|e|||Y|o|u|||T|o|d|a|y||
|+-+-+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+|+-+-+-+-+-+|
+-----------+-------+-------+-------+-----------+
Join string with .
and remove last .
u := front content (cart t `.)
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
|H|e|l|l|o|.|H|o|w|.|A|r|e|.|Y|o|u|.|T|o|d|a|y|
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Less cluttered display, using set "sketch;set "nodecor
display switches.
s:='Hello,How,Are,You,Today'
Hello,How,Are,You,Today
t:= s eachall = `, cut s
+-----+---+---+---+-----+
|Hello|How|Are|You|Today|
+-----+---+---+---+-----+
u:=front content (cart t `.)
Hello.How.Are.You.Today
Or as a one-liner:
front content (cart (s eachall = `, cut s) `.)
Nim
import strutils
let text = "Hello,How,Are,You,Today"
let tokens = text.split(',')
echo tokens.join(".")
- Output:
Hello.How.Are.You.Today
Objeck
class Parse {
function : Main(args : String[]) ~ Nil {
tokens := "Hello,How,Are,You,Today"->Split(",");
each(i : tokens) {
tokens[i]->PrintLine();
};
}
}
Objective-C
NSString *text = @"Hello,How,Are,You,Today";
NSArray *tokens = [text componentsSeparatedByString:@","];
NSString *result = [tokens componentsJoinedByString:@"."];
NSLog(result);
OCaml
To split on a single-character separator:
let words = String.split_on_char ',' "Hello,How,Are,You,Today" in
String.concat "." words
The function split_on_char has been introduced in OCaml 4.04. In previous versions, it could be implemented by:
let split_on_char sep s =
let r = ref [] in
let j = ref (String.length s) in
for i = String.length s - 1 downto 0 do
if s.[i] = sep then begin
r := String.sub s (i + 1) (!j - i - 1) :: !r;
j := i
end
done;
String.sub s 0 !j :: !r
Oforth
"Hello,How,Are,You,Today" wordsWith(',') println
- Output:
[Hello, How, Are, You, Today]
ooRexx
text='Hello,How,Are,You,Today'
do while text \= ''
parse var text word1 ',' text
call charout 'STDOUT:',word1'.'
end
- Output:
Hello.How.Are.You.Today.
OpenEdge/Progress
FUNCTION tokenizeString RETURNS CHAR (
i_c AS CHAR
):
DEF VAR ii AS INT.
DEF VAR carray AS CHAR EXTENT.
DEF VAR cresult AS CHAR.
EXTENT( carray ) = NUM-ENTRIES( i_c ).
DO ii = 1 TO NUM-ENTRIES( i_c ):
carray[ ii ] = ENTRY( ii, i_c ).
END.
DO ii = 1 TO EXTENT( carray ).
cresult = cresult + "." + carray[ ii ].
END.
RETURN SUBSTRING( cresult, 2 ).
END FUNCTION. /* tokenizeString */
MESSAGE
tokenizeString( "Hello,How,Are,You,Today" )
VIEW-AS ALERT-BOX.
- Output:
--------------------------- Message --------------------------- Hello.How.Are.You.Today --------------------------- OK ---------------------------
Oz
for T in {String.tokens "Hello,How,Are,You,Today" &,} do
{System.printInfo T#"."}
end
PARI/GP
Version #1.
Simple version, like the most custom ones here (for this task). This version has 1 character delimiter, which is not allowed in the beginning and at the end of string, in addition, double, triple, etc., delimiters are not allowed too.
\\ Tokenize a string str according to 1 character delimiter d. Return a list of tokens.
\\ Using ssubstr() from http://rosettacode.org/wiki/Substring#PARI.2FGP
\\ tokenize() 3/5/16 aev
tokenize(str,d)={
my(str=Str(str,d),vt=Vecsmall(str),d1=sasc(d),Lr=List(),sn=#str,v1,p1=1);
for(i=p1,sn, v1=vt[i]; if(v1==d1, listput(Lr,ssubstr(str,p1,i-p1)); p1=i+1));
return(Lr);
}
{
\\ TEST
print(" *** Testing tokenize from Version #1:");
print("1.", tokenize("Hello,How,Are,You,Today",","));
\\ BOTH 2 & 3 are NOT OK!!
print("2.",tokenize("Hello,How,Are,You,Today,",","));
print("3.",tokenize(",Hello,,How,Are,You,Today",","));
}
- Output:
*** Testing tokenize from Version #1: 1.List(["Hello", "How", "Are", "You", "Today"]) 2.List(["Hello", "How", "Are", "You", "Today", ","]) 3.List([",Hello,,How,Are,You,Today,", "Hello", ",How,Are,You,Today,", "How", "Ar e", "You", "Today"])
Version #2.
Advanced version. Delimiter is allowed in any place. In addition, multiple delimiters are allowed too. This is really useful for considering omitted data. This version can be used for positional parameters processing, or for processing data from tables with string rows.
\\ Tokenize a string str according to 1 character delimiter d. Return a list of tokens.
\\ Using ssubstr() from http://rosettacode.org/wiki/Substring#PARI.2FGP
\\ stok() 3/5/16 aev
stok(str,d)={
my(d1c=ssubstr(d,1,1),str=Str(str,d1c),vt=Vecsmall(str),d1=sasc(d1c),
Lr=List(),sn=#str,v1,p1=1,vo=32);
if(sn==1, return(List(""))); if(vt[sn-1]==d1,sn--);
for(i=1,sn, v1=vt[i];
if(v1!=d1, vo=v1; next);
if(vo==d1||i==1, listput(Lr,""); p1=i+1; vo=v1; next);
if(i-p1>0, listput(Lr,ssubstr(str,p1,i-p1)); p1=i+1);
vo=v1;
);
return(Lr);
}
{
\\ TEST
print(" *** Testing stok from Version #2:");
\\ pp - positional parameter(s)
print("1. 5 pp: ", stok("Hello,How,Are,You,Today",","));
print("2. 5 pp: ", stok("Hello,How,Are,You,Today,",","));
print("3. 9 pp: ", stok(",,Hello,,,How,Are,You,Today",","));
print("4. 6 pp: ", stok(",,,,,,",","));
print("5. 1 pp: ", stok(",",","));
print("6. 1 pp: ", stok("Hello-o-o??",","));
print("7. 0 pp: ", stok("",","));
}
- Output:
*** Testing stok from Version #2: 1. 5 pp: List(["Hello", "How", "Are", "You", "Today"]) 2. 5 pp: List(["Hello", "How", "Are", "You", "Today"]) 3. 9 pp: List(["", "", "Hello", "", "", "How", "Are", "You", "Today"]) 4. 6 pp: List(["", "", "", "", "", ""]) 5. 1 pp: List([""]) 6. 1 pp: List(["Hello-o-o??"]) 7. 0 pp: List([""])
Pascal
program TokenizeString;
{$mode objfpc}{$H+}
uses
SysUtils, Classes;
const
TestString = 'Hello,How,Are,You,Today';
var
Tokens: TStringList;
I: Integer;
begin
// Uses FCL facilities, "harder" algorithm not implemented
Tokens := TStringList.Create;
try
Tokens.Delimiter := ',';
Tokens.DelimitedText := TestString;
Tokens.Delimiter := '.'; // For example
// To standard Output
WriteLn(Format('Tokenize from: "%s"', [TestString]));
WriteLn(Format('to: "%s"',[Tokens.DelimitedText]));
finally
Tokens.Free;
end;
end.
The result is:
Tokenize from: "Hello,How,Are,You,Today" to: "Hello.How.Are.You.Today"
Perl
print join('.', split /,/, 'Hello,How,Are,You,Today'), "\n";
CLI one-liner form:
echo "Hello,How,Are,You,Today" | perl -aplF/,/ -e '$" = "."; $_ = "@F";'
which is a compact way of telling Perl to do
BEGIN { $/ = "\n"; $\ = "\n"; }
LINE: while (defined($_ = <ARGV>)) {
chomp $_;
our(@F) = split(/,/, $_, 0);
$" = '.';
$_ = "@F";
}
continue {
die "-p destination: $!\n" unless print $_;
}
Phix
?join(split("Hello,How,Are,You,Today",","),".")
- Output:
"Hello.How.Are.You.Today"
Phixmonti
/# "Hello,How,Are,You,Today" "," "." subst print #/
"Hello,How,Are,You,Today" "," " " subst split len for get print "." print endfor
PHP
<?php
$str = 'Hello,How,Are,You,Today';
echo implode('.', explode(',', $str));
?>
Picat
Using the built-in functions split/2
and join/2
.
import util.
go =>
S = "Hello,How,Are,You,Today",
T = S.split(","),
println(T),
T.join(".").println(),
% As a one liner:
S.split(",").join(".").println().
- Output:
[Hello,How,Are,You,Today] Hello.How.Are.You.Today Hello.How.Are.You.Today
PicoLisp
(mapcar pack
(split (chop "Hello,How,Are,You,Today") ",") )
Pike
("Hello,How,Are,You,Today" / ",") * ".";
PL/I
tok: Proc Options(main);
declare s character (100) initial ('Hello,How,Are,You,Today');
declare n fixed binary (31);
n = tally(s, ',')+1;
begin;
declare table(n) character (50) varying;
declare c character (1);
declare (i, k) fixed binary (31);
table = ''; k = 1;
do i = 1 to length(s);
c = substr(s, i, 1);
if c = ',' then k = k + 1;
else table(k) = table(k) || c;
end;
/* display the table */
table = table || '.';
put skip list (string(table));
end;
end;
- Output:
Hello.How.Are.You.Today
PL/M
100H:
/* CP/M CALLS */
BDOS: PROCEDURE (FN, ARG); DECLARE FN BYTE, ARG ADDRESS; GO TO 5; END BDOS;
EXIT: PROCEDURE; CALL BDOS(0,0); END EXIT;
PRINT: PROCEDURE (S); DECLARE S ADDRESS; CALL BDOS(9,S); END PRINT;
/* SPLIT A STRING ON CHARACTER 'SEP'.
THE 'PARTS' ARRAY WILL CONTAIN POINTERS TO THE START OF EACH ELEMENT.
THE AMOUNT OF PARTS IS RETURNED.
*/
TOKENIZE: PROCEDURE (SEP, STR, PARTS) ADDRESS;
DECLARE SEP BYTE, (STR, PARTS) ADDRESS;
DECLARE (N, P BASED PARTS) ADDRESS;
DECLARE CH BASED STR BYTE;
N = 0;
LOOP:
P(N) = STR;
N = N + 1;
DO WHILE CH <> '$' AND CH <> SEP;
STR = STR + 1;
END;
IF CH = '$' THEN RETURN N;
CH = '$';
STR = STR + 1;
GO TO LOOP;
END TOKENIZE;
/* TEST ON THE GIVEN INPUT */
DECLARE HELLO (24) BYTE INITIAL ('HELLO,HOW,ARE,YOU,TODAY$');
DECLARE PARTS (10) ADDRESS;
DECLARE (I, LEN) ADDRESS;
LEN = TOKENIZE(',', .HELLO, .PARTS);
DO I = 0 TO LEN-1;
CALL PRINT(PARTS(I));
CALL PRINT(.'. $');
END;
CALL EXIT;
EOF;
- Output:
HELLO. HOW. ARE. YOU. TODAY.
Plain English
To run:
Start up.
Split "Hello,How,Are,You,Today" into some string things given the comma byte.
Join the string things with the period byte giving a string.
Destroy the string things.
Write the string on the console.
Wait for the escape key.
Shut down.
To join some string things with a byte giving a string:
Get a string thing from the string things.
Loop.
If the string thing is nil, exit.
Append the string thing's string to the string.
If the string thing's next is not nil, append the byte to the string.
Put the string thing's next into the string thing.
Repeat.
- Output:
Hello.How.Are.You.Today
Pop11
The natural solution in Pop11 uses lists.
There are built in libraries for tokenising strings, illustrated below, along with code that the user could create for the task.
First show the use of sysparse_string to break up a string and make a list of strings.
;;; Make a list of strings from a string using space as separator
lvars list;
sysparse_string('the cat sat on the mat') -> list;
;;; print the list of strings
list =>
** [the cat sat on the mat]
By giving it an extra parameter 'true' we can make it recognize numbers and produce a list of strings and numbers
lvars list;
sysparse_string('one 1 two 2 three 3 four 4', true) -> list;
;;; print the list of strings and numbers
list =>
** [one 1 two 2 three 3 four 4]
;;; check that first item is a string and second an integer
isstring(list(1))=>
** <true>
isinteger(list(2))=>
** <true>
Now show some uses of the built in procedure sys_parse_string, which allows more options:
;;; Make pop-11 print strings with quotes
true -> pop_pr_quotes;
;;;
;;; Create a string of tokens using comma as token separator
lvars str='Hello,How,Are,You,Today';
;;;
;;; Make a list of strings by applying sys_parse_string
;;; to str, using the character `,` as separator (the default
;;; separator, if none is provided, is the space character).
lvars strings;
[% sys_parse_string(str, `,`) %] -> strings;
;;;
;;; print the list of strings
strings =>
** ['Hello' 'How' 'Are' 'You' 'Today']
If {% ... %} were used instead of [% ... %] the result would be a vector (i.e. array) of strings rather than a list of strings.
{% sys_parse_string(str, `,`) %} -> strings;
;;; print the vector
strings =>
** {'Hello' 'How' 'Are' 'You' 'Today'}
It is also possible to give sys_parse_string a 'conversion' procedure, which is applied to each of the tokens. E.g. it could be used to produce a vector of numbers, using the conversion procedure 'strnumber', which converts a string to a number:
lvars numbers;
{% sys_parse_string('100 101 102 103 99.9 99.999', strnumber) %} -> numbers;
;;; the result is a vector containing integers and floats,
;;; which can be printed thus:
numbers =>
** {100 101 102 103 99.9 99.999}
Using lower level pop-11 facilities to tokenise the string:
;;; Declare and initialize variables
lvars str='Hello,How,Are,You,Today';
;;; Iterate over string
lvars ls = [], i, j = 1;
for i from 1 to length(str) do
;;; If comma
if str(i) = `,` then
;;; Prepend word (substring) to list
cons(substring(j, i - j, str), ls) -> ls;
i + 1 -> j;
endif;
endfor;
;;; Prepend final word (if needed)
if j <= length(str) then
cons(substring(j, length(str) - j + 1, str), ls) -> ls;
endif;
;;; Reverse the list
rev(ls) -> ls;
Since the task requires to use array we convert list to array
;;; Put list elements and lenght on the stack
destlist(ls);
;;; Build a vector from them
lvars ar = consvector();
;;; Display in a loop, putting trailing period
for i from 1 to length(ar) do
printf(ar(i), '%s.');
endfor;
printf('\n');
We could use list directly for printing:
for i in ls do
printf(i, '%s.');
endfor;
so the conversion to vector is purely to satisfy task formulation.
PowerShell
$words = "Hello,How,Are,You,Today".Split(',')
[string]::Join('.', $words)
$words = "Hello,How,Are,You,Today" -split ','
$words -join '.'
The StringSplitOptions enumeration weeds out the return of empty elements.
"Hello,How,Are,You,Today", ",,Hello,,Goodbye,," | ForEach-Object {($_.Split(',',[StringSplitOptions]::RemoveEmptyEntries)) -join "."}
- Output:
Hello.How.Are.You.Today Hello.Goodbye
Prolog
splitup(Sep,[token(B)|BL]) --> splitup(Sep,B,BL).
splitup(Sep,[A|AL],B) --> [A], {\+ [A] = Sep }, splitup(Sep,AL,B).
splitup(Sep,[],[B|BL]) --> Sep, splitup(Sep,B,BL).
splitup(_Sep,[],[]) --> [].
start :-
phrase(splitup(",",Tokens),"Hello,How,Are,You,Today"),
phrase(splitup(".",Tokens),Backtogether),
string_to_list(ABack,Backtogether),
writeln(ABack).
- Output:
?- start. Hello.How.Are.You.Today
Using the SWI Prolog string data type and accompanying predicates, this can be accomplished in a few lines in the top level:
?- split_string("Hello,How,Are,You,Today", ",", "", Split),
| atomics_to_string(Split, ".", PeriodSeparated),
| writeln(PeriodSeparated).
Hello.How.Are.You.Today
Python
text = "Hello,How,Are,You,Today"
tokens = text.split(',')
print ('.'.join(tokens))
Or if interpretation of the task description means you don't need to keep an intermediate array:
print ('.'.join('Hello,How,Are,You,Today'.split(',')))
Q
words: "," vs "Hello,How,Are,You,Today"
"." sv words
- Output:
"Hello.How.Are.You.Today"
QB64
CBTJD: 2020/03/12
a$ = "Hello,How,Are,You,Today" ' | Initialize original string.
FOR na = 1 TO LEN(a$) ' | Start loop to count number of commas.
IF MID$(a$, na, 1) = "," THEN nc = nc + 1 ' | For each comma, increment nc.
NEXT ' | End of loop.
DIM t$(nc) ' | Dim t$ array with total number of commas (nc). Array base is 0.
FOR nb = 1 TO LEN(a$) ' | Start loop to find each word.
c$ = MID$(a$, nb, 1) ' | Look at each character in the string.
IF c$ = "," THEN ' | If the character is a comma, increase the t$ array for the next word.
t = t + 1 ' | t = token word count. Starts at 0 because array base is 0.
ELSE ' | Or...
t$(t) = t$(t) + c$ ' | Add each character to the current token (t$) word.
END IF ' | End of decision tree.
NEXT ' | End of loop.
FOR nd = 0 TO t ' | Start loop to create final desired output.
tf$ = tf$ + t$(nd) + "." ' | Add each token word from t$ followed by a period to the final tf$.
NEXT ' | End of loop.
PRINT LEFT$(tf$, LEN(tf$) - 1) ' | Print all but the last period of tf$.
END ' | Program end.
Alternative method using word$ function:
CBTJD: 2020/03/12
a$ = "Hello,How,Are,You,Today" ' | Initialize original string.
DIM t$(LEN(a$) / 2) ' | Create an overestimated sized array.
FOR nd = 1 TO LEN(a$) ' | Start loop to find each comma.
IF MID$(a$, nd, 1) = "," THEN ' | If a comma is found...
tc = tc + 1 ' | Increment tc for each found comma.
t$(tc) = word$(a$, tc, ",") ' | Assign tc word to t$(tc) array.
END IF ' | End decision tree.
NEXT ' | End loop.
t$(tc + 1) = word$(a$, tc + 1, ",") ' | Assign last word to next array position.
ft$ = t$(1) ' | Start final return string ft$ with first array value.
FOR ne = 2 TO tc + 1 ' | Start loop to add periods and array values.
ft$ = ft$ + "." + t$(ne) ' | Concatenate a period with subsequent array values.
NEXT ' | End loop.
PRINT ft$ ' | Print final return string ft$.
FUNCTION word$ (inSTG$, inDEC, inPRM$) ' | word$ function accepts original string, word number, and separator.
inSTG$ = inSTG$ + inPRM$ ' | Add a separator to the end of the original string.
FOR na = 1 TO LEN(inSTG$) ' | Start loop to count total number of separators.
IF MID$(inSTG$, na, 1) = inPRM$ THEN nc = nc + 1 ' | If separator found, increment nc.
NEXT ' | End loop.
IF inDEC > nc THEN word$ = "": GOTO DONE ' | If requested word number (inDEC) is greater than total words (nc), bail.
FOR nd = 1 TO inDEC ' | Start loop to find requested numbered word.
last = st ' | Remember the position of the last separator.
st = INSTR(last + 1, inSTG$, inPRM$) ' | Find the next separator.
NEXT ' | End loop.
word$ = MID$(inSTG$, last + 1, st - last - 1) ' | Return requested word.
DONE: ' | Label for bail destination of word count error check.
END FUNCTION ' | End of function.
Quackery
[ [] [] rot
witheach
[ dup char , = iff
[ drop nested join [] ]
else join ]
nested join ] is tokenise ( $ --> [ )
[ witheach [ echo$ say "." ] ] is display ( [ --> )
$ "Hello,How,Are,You,Today" tokenise display
- Output:
Hello.How.Are.You.Today.
R
text <- "Hello,How,Are,You,Today"
junk <- strsplit(text, split=",")
print(paste(unlist(junk), collapse="."))
or the one liner
paste(unlist(strsplit(text, split=",")), collapse=".")
Racket
#lang racket
(string-join (string-split "Hello,How,Are,You,Today" ",") ".")
;; -> "Hello.How.Are.You.Today"
Raku
(formerly Perl 6)
'Hello,How,Are,You,Today'.split(',').join('.').say;
Or with function calls:
say join '.', split ',', 'Hello,How,Are,You,Today';
Raven
'Hello,How,Are,You,Today' ',' split '.' join print
REBOL
print ["Original:" original: "Hello,How,Are,You,Today"]
tokens: parse original ","
dotted: "" repeat i tokens [append dotted rejoin [i "."]]
print ["Dotted: " dotted]
- Output:
Original: Hello,How,Are,You,Today Dotted: Hello.How.Are.You.Today.
Red
str: "Hello,How,Are,You,Today"
>> tokens: split str ","
>> probe tokens
["Hello" "How" "Are" "You" "Today"]
>> periods: replace/all form tokens " " "." ;The word FORM converts the list series to a string removing quotes.
>> print periods ;then REPLACE/ALL spaces with period
Hello.How.Are.You.Today
Retro
{{
: char ( -$ ) " " ;
: tokenize ( $-$$ )
@char ^strings'splitAtChar withLength 1- over + 0 swap ! tempString ;
: action ( $- )
keepString ^buffer'add ;
---reveal---
: split ( $cb- )
^buffer'set !char
char ^strings'append
[ tokenize action dup 1 <> ] while drop
^buffer'get drop ;
}}
This will suffice to split a string into an array of substrings. It is used like this:
create strings 100 allot
"Hello,How,Are,You,Today" ', strings split
Since the buffer' vocabulary creates a zero-terminated buffer, we can display it using the each@ combinator and a simple quote:
strings [ @ "%s." puts ] ^types'STRING each@
REXX
version 1
This REXX version doesn't append a period to the last word in the list.
/*REXX program separates a string of comma─delimited words, and echoes them ──► terminal*/
original = 'Hello,How,Are,You,Today' /*some words separated by commas (,). */
say 'The input string:' original /*display original string ──► terminal.*/
new= original /*make a copy of the string. */
do #=1 until new=='' /*keep processing until NEW is empty.*/
parse var new @.# ',' new /*parse words delineated by a comma (,)*/
end /*#*/ /* [↑] the new array is named @. */
say /* NEW is destructively parsed. [↑] */
say center(' Words in the string ', 40, "═") /*display a nice header for the list. */
do j=1 for # /*display all the words (one per line),*/
say @.j || left(., j\==#) /*maybe append a period (.) to a word. */
end /*j*/ /* [↑] don't append a period if last. */
say center(' End─of─list ', 40, "═") /*display a (EOL) trailer for the list.*/
- output when using the internal default input:
The input string: Hello,How,Are,You,Today ═════════ Words in the string ══════════ Hello. How. Are. You. Today ═════════════ End─of─list ══════════════
version 2
This REXX version won't work if any of the words have an embedded blank (or possible a tab character) in them, as in:
Hello,Betty Sue,How,Are,You,Today
/*REXX program to separate a string of comma-delimited words and echo */
sss='Hello,How,Are,You,Today'
say 'input string='sss
say ''
say 'Words in the string:'
ss =translate(sss,' ',',')
dot='.'
Do i=1 To words(ss)
If i=words(ss) Then dot=''
say word(ss,i)dot
End
say 'End-of-list.'
output is similar to REXX version 1.
Ring
see substr("Hello,How,Are,You,Today", ",", ".")
RPL
The program below fully complies with the task requirements, e.g. the input string is converted to a list of words, then the list is converted to a string.
RPL code | Comment |
---|---|
≪
"}" + "{" SWAP + STR→
1 OVER SIZE FOR j
DUP j GET →STR 2 OVER SIZE 1 - SUB j SWAP PUT
NEXT
"" 1 3 PICK SIZE FOR j
OVER j GET +
IF OVER SIZE j ≠ THEN "." + END
NEXT SWAP DROP
≫ 'TOKNZ' STO
|
TOKNZ ( "word,word" → "word.word" ) convert string into list (words being between quotes) loop for each list item convert it to a string, remove quotes at beginning and end loop for each list item add item to output string if not last item, append "." clean stack return output string |
"Hello,How,Are,You,Today" TOKNZ
Output:
1: "Hello.How.Are.You.Today"
If direct string-to-string conversion is allowed, then this one-liner for HP-48+ will do the job:
≪ 1 OVER SIZE FOR j IF DUP j DUP SUB "," == THEN j "." REPL END NEXT ≫ 'TOKNZ' STO
Ruby
puts "Hello,How,Are,You,Today".split(',').join('.')
Rust
fn main() {
let s = "Hello,How,Are,You,Today";
let tokens: Vec<&str> = s.split(",").collect();
println!("{}", tokens.join("."));
}
S-lang
variable a = strchop("Hello,How,Are,You,Today", ',', 0);
print(strjoin(a, "."));
- Output:
"Hello.How.Are.You.Today"
Scala
println("Hello,How,Are,You,Today" split "," mkString ".")
Scheme
(use-modules (ice-9 regex))
(define s "Hello,How,Are,You,Today")
(define words (map match:substring (list-matches "[^,]+" s)))
(do ((n 0 (+ n 1))) ((= n (length words)))
(display (list-ref words n))
(if (< n (- (length words) 1))
(display ".")))
(with SRFI 13)
(define s "Hello,How,Are,You,Today")
(define words (string-tokenize s (char-set-complement (char-set #\,))))
(define t (string-join words "."))
(print
(string-join
(string-split "Hello,How,Are,You,Today" #\,)
"."))
- Output:
Hello.How.Are.You.Today
Seed7
var array string: tokens is 0 times "";
tokens := split("Hello,How,Are,You,Today", ",");
Self
| s = 'Hello,How,Are,You,Today' |
((s splitOn: ',') joinUsing: '.') printLine.
Sidef
'Hello,How,Are,You,Today'.split(',').join('.').say;
Simula
BEGIN
CLASS TEXTARRAY(N); INTEGER N;
BEGIN
TEXT ARRAY ARR(1:N);
END TEXTARRAY;
REF(TEXTARRAY) PROCEDURE SPLIT(T,DELIM); TEXT T; CHARACTER DELIM;
BEGIN
INTEGER N, I, LPOS;
REF(TEXTARRAY) A;
N := 1;
T.SETPOS(1);
WHILE T.MORE DO
IF T.GETCHAR = DELIM THEN
N := N+1;
A :- NEW TEXTARRAY(N);
I := 0;
LPOS := 1;
T.SETPOS(LPOS);
WHILE T.MORE DO
IF T.GETCHAR = DELIM THEN
BEGIN
I := I+1;
A.ARR(I) :- T.SUB(LPOS,T.POS-LPOS-1);
LPOS := T.POS;
END;
I := I+1;
A.ARR(I) :- T.SUB(LPOS,T.LENGTH-LPOS+1);
SPLIT :- A;
END SPLIT;
BEGIN
TEXT S;
REF(TEXTARRAY) TA;
INTEGER I;
S :- "HELLO,HOW,ARE,YOU,TODAY";
TA :- SPLIT(S,',');
FOR I := 1 STEP 1 UNTIL TA.N DO
BEGIN
OUTTEXT(TA.ARR(I));
OUTCHAR('.');
END;
OUTIMAGE;
END;
END.
- Output:
HELLO.HOW.ARE.YOU.TODAY.
Slate
('Hello,How,Are,You,Today' splitWith: $,) join &separator: '.'.
Slope
(display
(list->string
(string->list
"Hello,How,Are,You,Today"
",")
"."))
- Output:
Hello.How.Are.You.Today
Smalltalk
|array |
array := 'Hello,How,Are,You,Today' subStrings: $,.
array fold: [:concatenation :string | concatenation, '.', string ]
Some implementations also have a join: convenience method that allows the following shorter solution:
('Hello,How,Are,You,Today' subStrings: $,) join: '.'
The solution displaying a trailing period would be:
|array |
array := 'Hello,How,Are,You,Today' subStrings: $,.
array inject: '' into: [:concatenation :string | concatenation, string, '.' ]
SNOBOL4
For this task, it's convenient to define Perl-style split( ) and join( ) functions.
define('split(chs,str)i,j,t,w2') :(split_end)
split t = table()
sp1 str pos(0) (break(chs) | rem) $ t<i = i + 1>
+ span(chs) (break(chs) | '') . w2 = w2 :s(sp1)
* t<i> = differ(str,'') str ;* Uncomment for CSnobol
split = array(i)
sp2 split<j = j + 1> = t<j> :s(sp2)f(return)
split_end
define('join(ch,a)i,') :(join_end)
join join = join a<i = i + 1>
join = join ?a<i + 1> ch :s(join)f(return)
join_end
* # Test and display
output = join('.',split(',','Hello,How,Are,You,Today'))
end
- Output:
Hello.How.Are.You.Today
Standard ML
val splitter = String.tokens (fn c => c = #",");
val main = (String.concatWith ".") o splitter;
Test:
- main "Hello,How,Are,You,Today"
val it = "Hello.How.Are.You.Today" : string
Swift
let text = "Hello,How,Are,You,Today"
let tokens = text.components(separatedBy: ",") // for single or multi-character separator
print(tokens)
let result = tokens.joined(separator: ".")
print(result)
let text = "Hello,How,Are,You,Today"
let tokens = text.characters.split(",").map{String($0)} // for single-character separator
print(tokens)
let result = tokens.joinWithSeparator(".")
print(result)
let text = "Hello,How,Are,You,Today"
let tokens = split(text, { $0 == "," }) // for single-character separator
println(tokens)
let result = ".".join(tokens)
println(result)
For multi-character separators:
import Foundation
let text = "Hello,How,Are,You,Today"
let tokens = text.componentsSeparatedByString(",")
print(tokens)
Tcl
Generating a list form a string by splitting on a comma:
split $string ","
Joining the elements of a list by a period:
join $list "."
Thus the whole thing would look like this:
puts [join [split "Hello,How,Are,You,Today" ","] "."]
If you'd like to retain the list in a variable with the name "words", it would only be marginally more complex:
puts [join [set words [split "Hello,How,Are,You,Today" ","]] "."]
(In general, the regexp command is also used in Tcl for tokenization of strings, but this example does not need that level of complexity.)
tr
tr
knows nothing about arrays, so this solution only changes each comma to a period.
echo 'Hello,How,Are,You,Today' | tr ',' '.'
Transd
#lang transd
MainModule: {
_start: (lambda locals: s "Hello,How,Are,You,Today"
(textout (join (split s ",") "."))
)
}
- Output:
Hello.How.Are.You.Today
TUSCRIPT
$$ MODE TUSCRIPT
SET string="Hello,How,Are,You,Today"
SET string=SPLIT (string,":,:")
SET string=JOIN (string,".")
TXR
Collecting tokens which consist of non-empty sequences of non-commas.
@(next :list "Hello,How,Are,You,Today")
@(coll)@{token /[^,]+/}@(end)
@(output)
@(rep)@token.@(last)@token@(end)
@(end)
Different approach. Collect tokens, each of which is a piece of text which either terminates before a comma, or else extends to the end of the line.
@(next :list "Hello,How,Are,You,Today")
@(coll)@(maybe)@token,@(or)@token@(end)@(end)
@(output)
@(rep)@token.@(last)@token@(end)
@(end)
Using TXR Lisp:
txr -p '(cat-str (split-str "Hello,How,Are,You,Today" ",") ".")'
Hello.How.Are.You.Today
UNIX Shell
string='Hello,How,Are,You,Today'
(IFS=,
printf '%s.' $string
echo)
#! /bin/bash
stripchar-l ()
#removes the specified character from the left side of the string
#USAGE: stripchar "stuff" "s" --> tuff
{
string="$1";
string=${string#"$2"};
echo "$string"
}
join ()
#join a string of characters on a specified delimiter
#USAGE: join "1;2;3;4" ";" "," --> 1,2,3,4
{
local result="";
local list="$1";
OLDIFS="$IFS";
local IFS=${2-" "};
local output_field_seperator=${3-" "};
for element in $list;
do
result="$result$output_field_seperator$element";
done;
result="`stripchar-l "$result" "$output_field_seperator"`";
echo "$result";
IFS="$OLDIFS"
}
split ()
{
#split a string of characters on a specified delimiter
#USAGE: split "1;2;3;4" ";" --> 1 2 3 4
local list="$1";
local input_field_seperator=${2-" "};
local output_field_seperator=" ";
#defined in terms of join
join "$list" "$input_field_seperator" "$output_field_seperator"
}
strtokenize ()
{
#splits up a string of characters into tokens,
#based on a user supplied delimiter
#USAGE:strtokenize "1;2;3;4" ";" ":" --> 1:2:3:4
local list="$1";
local input_delimiter=${2-" "};
local output_delimiter=${3-" "};
local contains_a_space=" "; #added to highlight the use
#of " " as an argument to join
#splits it input then joins it with a user supplied delimiter
join "$( split "$list" "$input_delimiter" )" \
"$contains_a_space" "$output_delimiter";
}
Example
strtokenize "Hello,How,Are,You,Today" "," "."
Hello.How.Are.You.Today
string1="Hello,How,Are,You,Today"
elements_quantity=$(echo $string1|tr "," "\n"|wc -l)
present_element=1
while [ $present_element -le $elements_quantity ];do
echo $string1|cut -d "," -f $present_element|tr -d "\n"
if [ $present_element -lt $elements_quantity ];then echo -n ".";fi
present_element=$(expr $present_element + 1)
done
echo
# or to cheat
echo "Hello,How,Are,You,Today"|tr "," "."
UnixPipes
token() {
(IFS=, read -r A B; echo "$A".; test -n "$B" && (echo "$B" | token))
}
echo "Hello,How,Are,You" | token
Ursa
decl string text
set text "Hello,How,Are,You,Today"
decl string<> tokens
set tokens (split text ",")
for (decl int i) (< i (size tokens)) (inc i)
out tokens<i> "." console
end for
out endl console
Ursala
A list of strings is made by separating at the commas using the library function, sep. A single string is then made by joining the list of strings with periods using the library function, mat. Each of these is a second order function parameterized by the delimiter. Character literals are preceded by a backquote.
#import std
token_list = sep`, 'Hello,How,Are,You,Today'
#cast %s
main = mat`. token_list
- Output:
'Hello.How.Are.You.Today'
Vala
void main() {
string s = "Hello,How,Are,You,Today";
print(@"$(string.joinv(".", s.split(",")))");
}
- Output:
Hello.How.Are.You.Today
VBA
Sub Main()
Dim temp() As String
temp = Tokenize("Hello,How,Are,You,Today", ",")
Display temp, Space(5)
End Sub
Private Function Tokenize(strS As String, sep As String) As String()
Tokenize = Split(strS, sep)
End Function
Private Sub Display(arr() As String, sep As String)
Debug.Print Join(arr, sep)
End Sub
- Output:
Hello How Are You Today
VBScript
s = "Hello,How,Are,You,Today"
WScript.StdOut.Write Join(Split(s,","),".")
- Output:
Hello.How.Are.You.Today
Vedit macro language
Vedit does not use the concepts of array or list. Normally, the text is processed as text in an edit buffer.
However, this example shows how to split the text into multiple text registers (10, 11, 12 etc.). The contents of each text register is then displayed to user, separated by a period.
Buf_Switch(Buf_Free)
Ins_Text("Hello,How,Are,You,Today")
// Split the text into text registers 10, 11, ...
BOF
#1 = 9
Repeat(ALL) {
#1++
#2 = Cur_Pos
Search(",", ADVANCE+ERRBREAK)
Reg_Copy_Block(#1, #2, Cur_Pos-1)
}
Reg_Copy_Block(#1, #2, EOB_Pos)
// Display the list
for (#3 = 10; #3 <= #1; #3++) {
Reg_Type(#3) Message(".")
}
Buf_Quit(OK)
V (Vlang)
// Tokenize a string, in V (Vlang)
// Tectonics: v run tokenize-a-string.v
module main
// starts here
pub fn main() {
println("Hello,How,Are,You,Today".split(',').join('.'))
}
- Output:
prompt$ v run rosetta/tokenize-a-string.v Hello.How.Are.You.Today
WinBatch
text = 'Hello,How,Are,You,Today'
result = ''
BoxOpen('WinBatch Tokenizing Example', '')
for ix = 1 to itemcount(text,',')
result = result : itemextract(ix, text, ',') : '.'
BoxText(result)
next
display(10, 'End of Program', 'Dialog and program will close momentarily.')
BoxShut()
- Output:
Hello.How.Are.You.Today.
Wortel
@join "." @split "," "Hello,How,Are,You,Today"
Returns
"Hello.How.Are.You.Today"
Wren
var s = "Hello,How,Are,You,Today"
var t = s.split(",").join(".") + "."
System.print(t)
- Output:
Hello.How.Are.You.Today.
XPath 2.0
string-join(tokenize("Hello,How,Are,You,Today", ","), ".")
- Output:
Hello.How.Are.You.Today
XPL0
string 0;
include c:\cxpl\codes;
int I, J, K, Char;
char String, Array(5,6); \5 words and 5 maximum chars + terminating 0
[String:= "Hello,How,Are,You,Today";
I:= 0; K:= 0;
repeat J:= 0;
loop [Char:= String(I);
I:= I+1;
if Char=^, or Char=0 then quit;
Array(K,J):= Char;
J:= J+1;
];
Array(K,J):= 0; \terminate word
K:= K+1; \next word in array
until K>=5;
for K:= 4 downto 0 do [Text(0, addr Array(K,0)); ChOut(0, ^.)];
CrLf(0);
]
The 'addr' operator is used to fetch the 32-bit address of Array rather than a byte from the character array.
Output (done in reverse order to emphasize the tokens are indeed separate):
Today.You.Are.How.Hello.
Yabasic
dim s$(1)
n = token("Hello. How are you today?", s$(), ".? ")
for i = 1 to n
print s$(i);
if i < n print ".";
next
print
Zig
const std = @import("std");
pub fn main() void {
const string = "Hello,How,Are,You,Today";
var tokens = std.mem.split(u8, string, ",");
std.debug.print("{s}", .{tokens.next().?});
while (tokens.next()) |token| {
std.debug.print(".{s}", .{token});
}
}
zkl
"Hello,How,Are,You,Today".split(",").concat(".").println();
Hello.How.Are.You.Today
Zoea
program: tokenize_a_string
input: "Hello,How,Are,You,Today"
output: "Hello.How.Are.You.Today"
Zoea Visual
Zsh
str='Hello,How,Are,You,Today'
tokens=(${(s:,:)str})
print ${(j:.:)tokens}
Or, using SH_SPLIT_WORD:
str='Hello,How,Are,You,Today'
IFS=, echo ${(j:.:)${=str}}
- Programming Tasks
- String manipulation
- Simple
- 11l
- 360 Assembly
- 8080 Assembly
- 8086 Assembly
- AArch64 Assembly
- ACL2
- Action!
- Action! Tool Kit
- ActionScript
- Ada
- ALGOL 68
- Amazing Hopper
- APL
- AppleScript
- ARM Assembly
- Arturo
- Astro
- AutoHotkey
- AWK
- BASIC
- Applesoft BASIC
- BaCon
- BASIC256
- BBC BASIC
- Chipmunk Basic
- Commodore BASIC
- FreeBASIC
- Liberty BASIC
- MSX Basic
- PowerBASIC
- PureBasic
- QBasic
- Run BASIC
- VBScript
- Visual Basic
- Batch File
- BQN
- Bracmat
- C
- POSIX
- C sharp
- C++
- Boost
- Ceylon
- CFEngine
- Clojure
- CLU
- COBOL
- CoffeeScript
- ColdFusion
- Common Lisp
- Cowgol
- Crystal
- D
- Delphi
- System.SysUtils
- Dt
- Dyalect
- Déjà Vu
- E
- EasyLang
- Elena
- Elixir
- EMal
- Erlang
- Euphoria
- F Sharp
- Factor
- Falcon
- Fantom
- Fennel
- Forth
- Fortran
- Frink
- FutureBasic
- Gambas
- GAP
- Genie
- Go
- Groovy
- Haskell
- HicEst
- Icon
- Unicon
- Io
- J
- Java
- JavaScript
- Jq
- Jsish
- Julia
- K
- Klingphix
- Kotlin
- Ksh
- LabVIEW
- Lambdatalk
- Lang
- Lang5
- LDPL
- LFE
- Lingo
- Logo
- Logtalk
- Lua
- M2000 Interpreter
- M4
- Maple
- Mathematica
- Wolfram Language
- MATLAB
- Octave
- Maxima
- MAXScript
- Mercury
- Min
- MiniScript
- MMIX
- Modula-3
- MUMPS
- Nanoquery
- Nemerle
- NetRexx
- NewLISP
- Nial
- Nim
- Objeck
- Objective-C
- OCaml
- Oforth
- OoRexx
- OpenEdge/Progress
- Oz
- PARI/GP
- Pascal
- Perl
- Phix
- Phixmonti
- PHP
- Picat
- PicoLisp
- Pike
- PL/I
- PL/M
- Plain English
- Pop11
- PowerShell
- Prolog
- Python
- Q
- QB64
- Quackery
- R
- Racket
- Raku
- Raven
- REBOL
- Red
- Retro
- REXX
- Ring
- RPL
- Ruby
- Rust
- S-lang
- Scala
- Scheme
- Seed7
- Self
- Sidef
- Simula
- Slate
- Slope
- Smalltalk
- SNOBOL4
- Standard ML
- Swift
- Tcl
- Tr
- Transd
- TUSCRIPT
- TXR
- UNIX Shell
- UnixPipes
- Ursa
- Ursala
- Vala
- VBA
- Vedit macro language
- V (Vlang)
- WinBatch
- Wortel
- Wren
- XPath 2.0
- XPL0
- Yabasic
- Zig
- Zkl
- Zoea
- Zoea Visual
- Zsh
- PARI/GP/Omit
- Pages with too many expensive parser function calls