String matching: Difference between revisions
m →{{header|Julia}}: manners for v0.4 |
mNo edit summary |
||
Line 2,541: | Line 2,541: | ||
string A contains string B 1 time (at position 29) |
string A contains string B 1 time (at position 29) |
||
</pre> |
</pre> |
||
=={{header|Ring}}== |
|||
<lang ring> |
|||
aString = "Welcome to the Ring Programming Language" |
|||
bString = "Ring" |
|||
bStringIndex = substr(aString,bString) |
|||
if bStringIndex > 0 see bStringIndex |
|||
see " : " + bString ok |
|||
</lang> |
|||
=={{header|Ruby}}== |
=={{header|Ruby}}== |
Revision as of 08:27, 9 March 2016
You are encouraged to solve this task according to the task description, using any language you may know.
Basic Data Operation
This is a basic data operation. It represents a fundamental action on a basic data type.
You may see other such operations in the Basic Data Operations category, or:
Integer Operations
Arithmetic |
Comparison
Boolean Operations
Bitwise |
Logical
String Operations
Concatenation |
Interpolation |
Comparison |
Matching
Memory Operations
Pointers & references |
Addresses
Given two strings, demonstrate the following 3 types of matchings:
- Determining if the first string starts with second string
- Determining if the first string contains the second string at any location
- Determining if the first string ends with the second string
Optional requirements:
- Print the location of the match for part 2
- Handle multiple occurrences of a string for part 2.
Ada
<lang Ada> with Ada.Strings.Fixed; use Ada.Strings.Fixed; with Ada.Text_IO; use Ada.Text_IO;
procedure Match_Strings is
S1 : constant String := "abcd"; S2 : constant String := "abab"; S3 : constant String := "ab";
begin
if S1'Length >= S3'Length and then S1 (S1'First..S1'First + S3'Length - 1) = S3 then Put_Line ( & S1 & "' starts with '" & S3 & ); end if; if S2'Length >= S3'Length and then S2 (S2'Last - S3'Length + 1..S2'Last) = S3 then Put_Line ( & S2 & "' ends with '" & S3 & ); end if; Put_Line ( & S3 & "' first appears in '" & S1 & "' at" & Integer'Image (Index (S1, S3))); Put_Line ( & S3 & "' appears in '" & S2 & & Integer'Image (Ada.Strings.Fixed.Count (S2, S3)) & " times" );
end Match_Strings; </lang>
- Output:
'abcd' starts with 'ab' 'abab' ends with 'ab' 'ab' first appears in 'abcd' at 1 'ab' appears in 'abab' 2 times
Aime
<lang aime>text s, t; data b;
s = "Bangkok"; t = "Bang";
b_cast(b, s);
o_form("starts with, embeds, ends with \"~\": ~, ~, ~\n", t, b_seek(b, t) == 0,
b_seek(b, t) != -1, b_seek(b, t) != -1 && b_seek(b, t) + length(t) == length(s));
t = "ok";
o_form("starts with, embeds, ends with \"~\": ~, ~, ~\n", t, b_seek(b, t) == 0,
b_seek(b, t) != -1, b_seek(b, t) != -1 && b_seek(b, t) + length(t) == length(s));
t = "Summer";
o_form("starts with, embeds, ends with \"~\": ~, ~, ~\n", t, b_seek(b, t) == 0,
b_seek(b, t) != -1, b_seek(b, t) != -1 && b_seek(b, t) + length(t) == length(s));</lang>
- Output:
starts with, embeds, ends with "Bang": 1, 1, 0 starts with, embeds, ends with "ok": 0, 1, 1 starts with, embeds, ends with "Summer": 0, 0, 0
ALGOL 68
<lang algol68># define some appropriate OPerators # PRIO STARTSWITH = 5, ENDSWITH = 5; OP STARTSWITH = (STRING str, prefix)BOOL: # assuming LWB = 1 #
IF UPB str < UPB prefix THEN FALSE ELSE str[:UPB prefix]=prefix FI;
OP ENDSWITH = (STRING str, suffix)BOOL: # assuming LWB = 1 #
IF UPB str < UPB suffix THEN FALSE ELSE str[UPB str-UPB suffix+1:]=suffix FI;
INT loc, loc2;
print((
"abcd" STARTSWITH "ab", # returns TRUE # "abcd" ENDSWITH "zn", # returns FALSE # string in string("bb",loc,"abab"), # returns FALSE # string in string("ab",loc,"abab"), # returns TRUE # (string in string("bb",loc,"abab")|loc|-1), # returns -1 # (string in string("ab",loc,"abab")|loc|-1), # returns +1 # (string in string("ab",loc2,"abab"[loc+1:])|loc+loc2|-1) # returns +3 #
))</lang>
- Output:
TFFT -1 +1 +3
AutoHotkey
<lang AutoHotkey> String1 = abcd String2 = abab
If (SubStr(String1,1,StrLen(String2)) = String2)
MsgBox, "%String1%" starts with "%String2%".
IfInString, String1, %String2% {
Position := InStr(String1,String2) StringReplace, String1, String1, %String2%, %String2%, UseErrorLevel MsgBox, "%String1%" contains "%String2%" at position %Position%`, and appears %ErrorLevel% times.
} StringRight, TempVar, String1, StrLen(String2) If TempVar = %String2%
MsgBox, "%String1%" ends with "%String2%".
</lang>
AutoIt
<lang AutoIt>$string1 = "arduinoardblobard" $string2 = "ard"
- == Determining if the first string starts with second string
If StringLeft($string1, StringLen($string2)) = $string2 Then ConsoleWrite("1st string starts with 2nd string." & @CRLF) Else ConsoleWrite("1st string does'nt starts with 2nd string." & @CRLF) EndIf
- == Determining if the first string contains the second string at any location
- == Print the location of the match for part 2
- == Handle multiple occurrences of a string for part 2
$start = 1 $count = 0 $pos = StringInStr($string1, $string2) While $pos $count += 1 ConsoleWrite("1st string contains 2nd string at position: " & $pos & @CRLF) $pos = StringInStr($string1, $string2, 0, 1, $start + $pos + StringLen($string2)) WEnd If $count = 0 Then ConsoleWrite("1st string does'nt contain 2nd string." & @CRLF)
- == Determining if the first string ends with the second string
If StringRight($string1, StringLen($string2)) = $string2 Then ConsoleWrite("1st string ends with 2nd string." & @CRLF) Else ConsoleWrite("1st string does'nt ends with 2nd string." & @CRLF) EndIf
</lang>
AWK
<lang AWK>#!/usr/bin/awk -f {
if ($1 ~ "^"$2) {
print $1" begins with "$2;
} else {
print $1" does not begin with "$2;
}
if ($1 ~ $2) {
print $1" contains "$2;
} else {
print $1" does not contain "$2;
}
if ($1 ~ $2"$") {
print $1" ends with "$2;
} else {
print $1" does not end with "$2;
}
} </lang>
BASIC
<lang qbasic>first$ = "qwertyuiop"
'Determining if the first string starts with second string second$ = "qwerty" IF LEFT$(first$, LEN(second$)) = second$ THEN
PRINT "'"; first$; "' starts with '"; second$; "'"
ELSE
PRINT "'"; first$; "' does not start with '"; second$; "'"
END IF
'Determining if the first string contains the second string at any location 'Print the location of the match for part 2 second$ = "wert" x = INSTR(first$, second$) IF x THEN
PRINT "'"; first$; "' contains '"; second$; "' at position "; x
ELSE
PRINT "'"; first$; "' does not contain '"; second$; "'"
END IF
' Determining if the first string ends with the second string second$ = "random garbage" IF RIGHT$(first$, LEN(second$)) = second$ THEN
PRINT "'"; first$; "' ends with '"; second$; "'"
ELSE
PRINT "'"; first$; "' does not end with '"; second$; "'"
END IF
</lang>
- Output:
'qwertyuiop' starts with 'qwerty' 'qwertyuiop' contains 'wert' at position 2 'qwertyuiop' does not end with 'random garbage'
Applesoft BASIC
<lang ApplesoftBasic>10 A$ = "THIS, THAT, AND THE OTHER THING" 20 S$ = "TH" 30 DEF FN S(P) = MID$(A$, P, LEN(S$)) = S$ 40 PRINT A$ : PRINT
110 S$(1) = "STARTS" 120 S$(0) = "DOES NOT START" 130 PRINT S$(FN S(1))" WITH "S$ : PRINT
210 R$ = "" : FOR I = 1 TO LEN(A$) - LEN(S$) : IF FN S(I) THEN R$ = R$ + STR$(I) + " " 220 NEXT I 230 IF LEN(R$) = 0 THEN PRINT "DOES NOT CONTAIN "S$ 240 IF LEN(R$) THEN PRINT "CONTAINS "S$" LOCATED AT POSITION "R$ 250 PRINT
310 E$(1) = "ENDS" 320 E$(0) = "DOES NOT END" 330 PRINT E$(FN S(LEN(A$) - LEN(S$) + 1))" WITH "S$</lang>
Batch File
<lang dos>::NOTE #1: This implementation might crash, or might not work properly if
- you put some of the CMD special characters (ex. %,!, etc) inside the strings.
- NOTE #2: The comparisons here are case-SENSITIVE.
- NOTE #3: Spaces in strings are considered.
@echo off setlocal enabledelayedexpansion
- The main things...
set "str1=qwertyuiop" set "str2=qwerty" call :str2_lngth call :matchbegin
set "str1=qweiuoiocghiioyiocxiisfguiioiuygvd" set "str2=io" call :str2_lngth call :matchcontain
set "str1=blablabla" set "str2=bbla" call :str2_lngth call :matchend
echo. pause exit /b 0
- /The main things.
- The functions...
- matchbegin
echo. if "!str1:~0,%length%!"=="!str2!" ( echo "%str1%" begins with "%str2%". ) else ( echo "%str1%" does not begin with "%str2%". ) goto :EOF
- matchcontain
echo. set curr=0&set exist=0
- scanchrloop
if "!str1:~%curr%,%length%!"=="" ( if !exist!==0 echo "%str1%" does not contain "%str2%". goto :EOF ) if "!str1:~%curr%,%length%!"=="!str2!" ( echo "%str1%" contains "%str2%". ^(in Position %curr%^) set exist=1 ) set /a curr+=1&goto scanchrloop
- matchend
echo. if "!str1:~-%length%!"=="!str2!" ( echo "%str1%" ends with "%str2%". ) else ( echo "%str1%" does not end with "%str2%". ) goto :EOF
- str2_lngth
set length=0
- loop
if "!str2:~%length%,1!"=="" goto :EOF set /a length+=1 goto loop
- /The functions.</lang>
- Output:
"qwertyuiop" begins with "qwerty". "qweiuoiocghiioyiocxiisfguiioiuygvd" contains "io". (in Position 6) "qweiuoiocghiioyiocxiisfguiioiuygvd" contains "io". (in Position 12) "qweiuoiocghiioyiocxiisfguiioiuygvd" contains "io". (in Position 15) "qweiuoiocghiioyiocxiisfguiioiuygvd" contains "io". (in Position 26) "blablabla" does not end with "bbla". Press any key to continue . . .
BBC BASIC
<lang bbcbasic> first$ = "The fox jumps over the dog"
FOR test% = 1 TO 3 READ second$ starts% = FN_first_starts_with_second(first$, second$) IF starts% PRINT """" first$ """ starts with """ second$ """" ends% = FN_first_ends_with_second(first$, second$) IF ends% PRINT """" first$ """ ends with """ second$ """" where% = FN_first_contains_second_where(first$, second$) IF where% PRINT """" first$ """ contains """ second$ """ at position " ; where% howmany% = FN_first_contains_second_howmany(first$, second$) IF howmany% PRINT """" first$ """ contains """ second$ """ " ; howmany% " time(s)" NEXT DATA "The", "he", "dog" END DEF FN_first_starts_with_second(A$, B$) = B$ = LEFT$(A$, LEN(B$)) DEF FN_first_ends_with_second(A$, B$) = B$ = RIGHT$(A$, LEN(B$)) DEF FN_first_contains_second_where(A$, B$) = INSTR(A$, B$) DEF FN_first_contains_second_howmany(A$, B$) LOCAL I%, N% : I% = 0 REPEAT I% = INSTR(A$, B$, I%+1) IF I% THEN N% += 1 UNTIL I% = 0 = N%
</lang>
- Output:
"The fox jumps over the dog" starts with "The" "The fox jumps over the dog" contains "The" at position 1 "The fox jumps over the dog" contains "The" 1 time(s) "The fox jumps over the dog" contains "he" at position 2 "The fox jumps over the dog" contains "he" 2 time(s) "The fox jumps over the dog" ends with "dog" "The fox jumps over the dog" contains "dog" at position 24 "The fox jumps over the dog" contains "dog" 1 time(s)
Bracmat
Bracmat does pattern matching in expressions subject:pattern
and in strings @(subject:pattern)
. The (sub)pattern ?
is a wild card.
<lang Bracmat>( (sentence="I want a number such that that number will be even.")
& out$(@(!sentence:I ?) & "sentence starts with 'I'" | "sentence does not start with 'I'")
& out$(@(!sentence:? such ?) & "sentence contains 'such'" | "sentence does not contain 'such'")
& out$(@(!sentence:? "even.") & "sentence ends with 'even.'" | "sentence does not end with 'even.'")
& 0:?N
& ( @(!sentence:? be (? & !N+1:?N & ~))
| out$str$("sentence contains " !N " occurrences of 'be'") )
)</lang>
In the last line, Bracmat is forced by the always failing node ~
to backtrack until all occurrences of 'be' are found.
Thereafter the pattern match expression fails.
The interesting part is the side effect: while backtracking,
the accumulator N
keeps track of how many are found.
- Output:
sentence starts with 'I' sentence contains 'such' sentence ends with 'even.' sentence contains 3 occurrences of 'be'
C
Case sensitive matching: <lang C>#include <string.h>
- include <stdio.h>
int startsWith(const char* container, const char* target) {
size_t clen = strlen(container), tlen = strlen(target); if (clen < tlen) return 0; return strncmp(container, target, tlen) == 0;
}
int endsWith(const char* container, const char* target) {
size_t clen = strlen(container), tlen = strlen(target); if (clen < tlen) return 0; return strncmp(container + clen - tlen, target, tlen) == 0;
}
int doesContain(const char* container, const char* target) {
return strstr(container, target) != 0;
}
int main(void) {
printf("Starts with Test ( Hello,Hell ) : %d\n", startsWith("Hello","Hell")); printf("Ends with Test ( Code,ode ) : %d\n", endsWith("Code","ode")); printf("Contains Test ( Google,msn ) : %d\n", doesContain("Google","msn"));
return 0;
}</lang>
- Output:
Starts with Test ( Hello,Hell ) : 1 Ends with Test ( Code,ode ) : 1 Contains Test ( Google,msn ) : 0
Code without using string library to demonstrate how char strings are just pointers: <lang C>#include <stdio.h>
/* returns 0 if no match, 1 if matched, -1 if matched and at end */ int s_cmp(const char *a, const char *b) {
char c1 = 0, c2 = 0; while (c1 == c2) { c1 = *(a++); if ('\0' == (c2 = *(b++))) return c1 == '\0' ? -1 : 1; } return 0;
}
/* returns times matched */ int s_match(const char *a, const char *b) {
int i = 0, count = 0; printf("matching `%s' with `%s':\n", a, b);
while (a[i] != '\0') { switch (s_cmp(a + i, b)) { case -1: printf("matched: pos %d (at end)\n\n", i); return ++count; case 1: printf("matched: pos %d\n", i); ++count; break; } i++; } printf("end match\n\n"); return count;
}
int main() {
s_match("A Short String", "ort S"); s_match("aBaBaBaBa", "aBa"); s_match("something random", "Rand");
return 0;
}</lang>
- Output:
matching `A Short String' with `ort S': matched: pos 4 end match matching `aBaBaBaBa' with `aBa': matched: pos 0 matched: pos 2 matched: pos 4 matched: pos 6 (at end) matching `something random' with `Rand': end match
C++
<lang cpp>#include <string> using namespace std;
string s1="abcd"; string s2="abab"; string s3="ab"; //Beginning s1.compare(0,s3.size(),s3)==0; //End s1.compare(s1.size()-s3.size(),s3.size(),s3)==0; //Anywhere s1.find(s2)//returns string::npos int loc=s2.find(s3)//returns 0 loc=s2.find(s3,loc+1)//returns 2</lang>
C#
<lang csharp> class Program { public static void Main (string[] args) { var value = "abcd".StartsWith("ab"); value = "abcd".EndsWith("zn"); //returns false value = "abab".Contains("bb"); //returns false value = "abab".Contains("ab"); //returns true int loc = "abab".IndexOf("bb"); //returns -1 loc = "abab".IndexOf("ab"); //returns 0 loc = "abab".IndexOf("ab",loc+1); //returns 2 } } </lang>
Clojure
<lang clojure>(def evals '((. "abcd" startsWith "ab") (. "abcd" endsWith "zn") (. "abab" contains "bb") (. "abab" contains "ab") (. "abab" indexOf "bb") (let [loc (. "abab" indexOf "ab")] (. "abab" indexOf "ab" (dec loc)))))
user> (for [i evals] [i (eval i)]) ([(. "abcd" startsWith "ab") true] [(. "abcd" endsWith "zn") false] [(. "abab" contains "bb") false] [(. "abab" contains "ab") true] [(. "abab" indexOf "bb") -1] [(let [loc (. "abab" indexOf "ab")] (. "abab" indexOf "ab" (dec loc))) 0])</lang>
CoffeeScript
This example uses string slices, but a better implementation might use indexOf for slightly better performance.
<lang coffeescript> matchAt = (s, frag, i) ->
s[i...i+frag.length] == frag
startsWith = (s, frag) ->
matchAt s, frag, 0
endsWith = (s, frag) ->
matchAt s, frag, s.length - frag.length
matchLocations = (s, frag) ->
(i for i in [0..s.length - frag.length] when matchAt s, frag, i)
console.log startsWith "tacoloco", "taco" # true console.log startsWith "taco", "tacoloco" # false console.log startsWith "tacoloco", "talk" # false console.log endsWith "tacoloco", "loco" # true console.log endsWith "loco", "tacoloco" # false console.log endsWith "tacoloco", "yoco" # false console.log matchLocations "bababab", "bab" # [0,2,4] console.log matchLocations "xxx", "x" # [0,1,2] </lang>
Common Lisp
<lang lisp> (defun starts-with-p (str1 str2)
"Determine whether `str1` starts with `str2`" (let ((p (search str2 str1))) (and p (= 0 p))))
(print (starts-with-p "foobar" "foo")) ; T (print (starts-with-p "foobar" "bar")) ; NIL
(defun ends-with-p (str1 str2)
"Determine whether `str1` ends with `str2`" (let ((p (mismatch str2 str1 :from-end T))) (or (not p) (= 0 p))))
(print (ends-with-p "foobar" "foo")) ; NIL (print (ends-with-p "foobar" "bar")) ; T
(defun containsp (str1 str2)
"Determine whether `str1` contains `str2`. Instead of just returning T, return a list of starting locations for every occurence of `str2` in `str1`" (unless (string-equal str2 "") (loop for p = (search str2 str1) then (search str2 str1 :start2 (1+ p)) while p collect p)))
(print (containsp "foobar" "oba")) ; (2) (print (containsp "ababaBa" "ba")) ; (1 3) (print (containsp "foobar" "x")) ; NIL </lang>
Component Pascal
BlackBox Component Builder <lang oberon2> MODULE StringMatch; IMPORT StdLog,Strings; CONST strSize = 1024; patSize = 256;
TYPE Matcher* = POINTER TO LIMITED RECORD str: ARRAY strSize OF CHAR; pat: ARRAY patSize OF CHAR; pos: INTEGER END;
PROCEDURE NewMatcher*(IN str: ARRAY OF CHAR): Matcher; VAR m: Matcher; BEGIN NEW(m);m.str := str$;m.pos:= 0; RETURN m END NewMatcher;
PROCEDURE (m: Matcher) Match*(IN pat: ARRAY OF CHAR): INTEGER,NEW; VAR pos: INTEGER; BEGIN m.pat := pat$; pos := m.pos; Strings.Find(m.str,m.pat,pos,m.pos); RETURN m.pos END Match;
PROCEDURE (m: Matcher) Next*(): INTEGER, NEW; VAR pos: INTEGER; BEGIN pos := m.pos + LEN(m.pat$); Strings.Find(m.str,m.pat,pos,m.pos); RETURN m.pos; END Next;
(* Some Helper functions based on Strings module *) PROCEDURE StartsWith(IN str: ARRAY OF CHAR;IN pat: ARRAY OF CHAR): BOOLEAN; VAR pos: INTEGER; BEGIN Strings.Find(str,pat,0,pos); RETURN pos = 0 END StartsWith;
PROCEDURE Contains(IN str: ARRAY OF CHAR;IN pat: ARRAY OF CHAR; OUT pos: INTEGER): BOOLEAN; BEGIN Strings.Find(str,pat,0,pos); RETURN pos >= 0 END Contains;
PROCEDURE EndsWith(IN str: ARRAY OF CHAR;IN pat: ARRAY OF CHAR): BOOLEAN; VAR pos: INTEGER; BEGIN Strings.Find(str,pat,0,pos); RETURN pos + LEN(pat$) = LEN(str$) END EndsWith;
PROCEDURE Do*; CONST aStr = "abcdefghijklmnopqrstuvwxyz"; VAR pat: ARRAY 128 OF CHAR; res: BOOLEAN; at: INTEGER; m: Matcher; BEGIN (* StartsWith *) pat := "abc"; StdLog.String(aStr + " startsWith " + pat + " :>");StdLog.Bool(StartsWith(aStr,pat));StdLog.Ln; pat := "cba"; StdLog.String(aStr + " startsWith " + pat + " :>");StdLog.Bool(StartsWith(aStr,pat));StdLog.Ln; pat := "def"; StdLog.String(aStr + " startsWith " + pat + " :>");StdLog.Bool(StartsWith(aStr,pat));StdLog.Ln; StdLog.Ln; (* Contains *) pat := 'def'; StdLog.String(aStr + " contains " + pat + " :>");StdLog.Bool(Contains(aStr,pat,at)); StdLog.String(" at: ");StdLog.Int(at);StdLog.Ln; pat := 'efd'; StdLog.String(aStr + " contains " + pat + " :>");StdLog.Bool(Contains(aStr,pat,at)); StdLog.String(" at: ");StdLog.Int(at);StdLog.Ln; pat := 'abc'; StdLog.String(aStr + " contains " + pat + " :>");StdLog.Bool(Contains(aStr,pat,at)); StdLog.String(" at: ");StdLog.Int(at);StdLog.Ln; pat := 'xyz'; StdLog.String(aStr + " contains " + pat + " :>");StdLog.Bool(Contains(aStr,pat,at)); StdLog.String(" at: ");StdLog.Int(at);StdLog.Ln; StdLog.Ln; (* EndsWith *) pat := 'xyz'; StdLog.String(aStr + " endsWith " + pat + " :>");StdLog.Bool(EndsWith(aStr,pat));StdLog.Ln; pat := 'zyx'; StdLog.String(aStr + " endsWith " + pat + " :>");StdLog.Bool(EndsWith(aStr,pat));StdLog.Ln; pat := 'abc'; StdLog.String(aStr + " endsWith " + pat + " :>");StdLog.Bool(EndsWith(aStr,pat));StdLog.Ln; pat:= 'def'; StdLog.String(aStr + " endsWith " + pat + " :>");StdLog.Bool(EndsWith(aStr,pat));StdLog.Ln; StdLog.Ln;
m := NewMatcher("abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz");
StdLog.String("Matching 'abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz' against 'abc':> ");
StdLog.Ln;
StdLog.String("Match at: ");StdLog.Int(m.Match("abc"));StdLog.Ln;
StdLog.String("Match at: ");StdLog.Int(m.Next());StdLog.Ln;
StdLog.String("Match at: ");StdLog.Int(m.Next());StdLog.Ln
END Do;
END StringMatch.
</lang>
Execute: ^Q StringMatching.Do
- Output:
abcdefghijklmnopqrstuvwxyz startsWith abc :> $TRUE abcdefghijklmnopqrstuvwxyz startsWith cba :> $FALSE abcdefghijklmnopqrstuvwxyz startsWith def :> $FALSE abcdefghijklmnopqrstuvwxyz contains def :> $TRUE at: 3 abcdefghijklmnopqrstuvwxyz contains efd :> $FALSE at: -1 abcdefghijklmnopqrstuvwxyz contains abc :> $TRUE at: 0 abcdefghijklmnopqrstuvwxyz contains xyz :> $TRUE at: 23 abcdefghijklmnopqrstuvwxyz endsWith xyz :> $TRUE abcdefghijklmnopqrstuvwxyz endsWith zyx :> $FALSE abcdefghijklmnopqrstuvwxyz endsWith abc :> $FALSE abcdefghijklmnopqrstuvwxyz endsWith def :> $FALSE Matching 'abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz' against 'abc':> Match at: 0 Match at: 26 Match at: -1
D
<lang d>void main() {
import std.stdio; import std.algorithm: startsWith, endsWith, find, countUntil;
"abcd".startsWith("ab").writeln; // true "abcd".endsWith("zn").writeln; // false "abab".find("bb").writeln; // empty array (no match) "abcd".find("bc").writeln; // "bcd" (substring start // at match) "abab".countUntil("bb").writeln; // -1 (no match) "abab".countUntil("ba").writeln; // 1 (index of 1st match)
// std.algorithm.startsWith also works on arrays and ranges: [1, 2, 3].countUntil(3).writeln; // 2 [1, 2, 3].countUntil([2, 3]).writeln; // 1
}</lang>
- Output:
true false bcd -1 1 2 1
DCL
<lang DCL>$ first_string = p1 $ length_of_first_string = f$length( first_string ) $ second_string = p2 $ length_of_second_string = f$length( second_string ) $ offset = f$locate( second_string, first_string ) $ if offset .eq. 0 $ then $ write sys$output "first string starts with second string" $ else $ write sys$output "first string does not start with second string" $ endif $ if offset .ne. length_of_first_string $ then $ write sys$output "first string contains the second string at location ", offset $ else $ write sys$output "first string does not contain the second string at any location" $ endif $ temp = f$extract( length_of_first_string - length_of_second_string, length_of_second_string, first_string ) $ if second_string .eqs. temp $ then $ write sys$output "first string ends with the second string" $ else $ write sys$output "first string does not end with the second string" $ endif</lang>
- Output:
$ @string_matching efabcdef ef first string starts with second string first string contains the second string at location 0 first string ends with the second string $ @string_matching efabcdef ab first string does not start with second string first string contains the second string at location 2 first string does not end with the second string $ @string_matching efabcdef def first string does not start with second string first string contains the second string at location 5 first string ends with the second string $ @string_matching efabcdef defx first string does not start with second string first string does not contain the second string at any location first string does not end with the second string
Delphi
<lang Delphi>program CharacterMatching;
{$APPTYPE CONSOLE}
uses StrUtils;
begin
WriteLn(AnsiStartsText('ab', 'abcd')); // True WriteLn(AnsiEndsText('zn', 'abcd')); // False WriteLn(AnsiContainsText('abcd', 'bb')); // False Writeln(AnsiContainsText('abcd', 'ab')); // True WriteLn(Pos('ab', 'abcd')); // 1
end.</lang>
E
<lang e>def f(string1, string2) {
println(string1.startsWith(string2)) var index := 0 while ((index := string1.startOf(string2, index)) != -1) { println(`at $index`) index += 1 }
println(string1.endsWith(string2))
}</lang>
EchoLisp
<lang lisp> (string-suffix? "nette" "Antoinette") → #t (string-prefix? "Simon" "Simon & Garfunkel") → #t
(string-match "Antoinette" "net") → #t ;; contains (string-index "net" "Antoinette") → 5 ;; substring location </lang>
Elena
<lang elena>#import system.
- import extensions.
- symbol program =
[
#var s := "abcd". console writeLine:s:" starts with ab: ":(s startingWith:"ab" literal). console writeLine:s:" starts with cd: ":(s startingWith:"cd" literal). console writeLine:s:" ends with ab: ":(s endingWith:"ab" literal). console writeLine:s:" ends with cd: ":(s endingWith:"cd" literal). console writeLine:s:" contains ab: ":(s containing:"ab" literal). console writeLine:s:" contains bc: ":(s containing:"bc" literal). console writeLine:s:" contains cd: ":(s containing:"cd" literal). console writeLine:s:" contains az: ":(s containing:"az" literal). console writeLine:s:" index of az: ":(s indexOf:"az" &at:0 literal). console writeLine:s:" index of cd: ":(s indexOf:"cd" &at:0 literal). console writeLine:s:" index of bc: ":(s indexOf:"bc" &at:0 literal). console writeLine:s:" index of ab: ":(s indexOf:"ab" &at:0 literal). console readChar.
].</lang>
Elixir
The String module has functions that cover the base requirements. <lang elixir> s1 = "abcd" s2 = "adab" s3 = "ab"
String.starts_with?(s1, s3)
- => true
String.starts_with?(s2, s3)
- => false
String.ends_with?(s1, s3)
- => false
String.ends_with?(s2, s3)
- => true
String.contains?(s1, s3)
- => true
String.contains?(s2, s3)
- => true
</lang>
Emacs Lisp
<lang Emacs Lisp> (defun match (word str)
(progn (setq regex (format "^%s.*$" word) ) (if (string-match regex str)
(insert (format "%s found in beginning of: %s\n" word str) )
(insert (format "%s not found in beginning of: %s\n" word str) ))
(setq pos (string-match word str) )
(if pos
(insert (format "%s found at position %d in: %s\n" word pos str) )
(insert (format "%s not found in: %s\n" word str) )) (setq regex (format "^.*%s$" word) ) (if (string-match regex str)
(insert (format "%s found in end of: %s\n" word str) )
(insert (format "%s not found in end of: %s\n" word str) ))))
(setq string "before center after")
(progn
(match "center" string) (insert "\n") (match "before" string) (insert "\n") (match "after" string) )
</lang> Output:
center not found in beginning of: before center after center found at position 7 in: before center after center not found in end of: before center after before found in beginning of: before center after before found at position 0 in: before center after before not found in end of: before center after after not found in beginning of: before center after after found at position 14 in: before center after after found in end of: before center after
Erlang
<lang erlang> -module(character_matching). -export([starts_with/2,ends_with/2,contains/2]).
%% Both starts_with and ends_with are mappings to 'lists:prefix/2' and %% 'lists:suffix/2', respectively.
starts_with(S1,S2) ->
lists:prefix(S2,S1).
ends_with(S1,S2) ->
lists:suffix(S2,S1).
contains(S1,S2) ->
contains(S1,S2,1,[]).
%% While S1 is at least as long as S2 we check if S2 is its prefix, %% storing the result if it is. When S1 is shorter than S2, we return %% the result. NB: this will work on any arbitrary list in erlang %% since it makes no distinction between strings and lists. contains([_|T]=S1,S2,N,Acc) when length(S2) =< length(S1) ->
case starts_with(S1,S2) of true -> contains(T,S2,N+1,[N|Acc]); false -> contains(T,S2,N+1,Acc) end;
contains(_S1,_S2,_N,Acc) ->
Acc.
</lang>
Euphoria
<lang euphoria>sequence first, second integer x
first = "qwertyuiop"
-- Determining if the first string starts with second string second = "qwerty" if match(second, first) = 1 then
printf(1, "'%s' starts with '%s'\n", {first, second})
else
printf(1, "'%s' does not start with '%s'\n", {first, second})
end if
-- Determining if the first string contains the second string at any location -- Print the location of the match for part 2 second = "wert" x = match(second, first) if x then
printf(1, "'%s' contains '%s' at position %d\n", {first, second, x})
else
printf(1, "'%s' does not contain '%s'\n", {first, second})
end if
-- Determining if the first string ends with the second string second = "uio" if length(second)<=length(first) and match_from(second, first, length(first)-length(second)+1) then
printf(1, "'%s' ends with '%s'\n", {first, second})
else
printf(1, "'%s' does not end with '%s'\n", {first, second})
end if</lang>
- Output:
'qwertyuiop' starts with 'qwerty' 'qwertyuiop' contains 'wert' at position 2 'qwertyuiop' does not end with 'uio'
F#
<lang fsharp>[<EntryPoint>] let main args =
let text = "一二三四五六七八九十" let starts = "一二" let ends = "九十" let contains = "五六" let notContains = "百"
printfn "text = %A" text printfn "starts with %A: %A" starts (text.StartsWith(starts)) printfn "starts with %A: %A" ends (text.StartsWith(ends)) printfn "ends with %A: %A" ends (text.EndsWith(ends)) printfn "ends with %A: %A" starts (text.EndsWith(starts)) printfn "contains %A: %A" contains (text.Contains(contains)) printfn "contains %A: %A" notContains (text.Contains(notContains)) printfn "substring %A begins at position %d (zero-based)" contains (text.IndexOf(contains)) let text2 = text + text printfn "text = %A" text2 Seq.unfold (fun (n : int) -> let idx = text2.IndexOf(contains, n) if idx < 0 then None else Some (idx, idx+1)) 0 |> Seq.iter (printfn "substring %A begins at position %d (zero-based)" contains) 0</lang>
- Output:
text = "一二三四五六七八九十" starts with "一二": true starts with "九十": false ends with "九十": true ends with "一二": false contains "五六": true contains "百": false substring "五六" begins at position 4 (zero-based) text = "一二三四五六七八九十一二三四五六七八九十" substring "五六" begins at position 4 (zero-based) substring "五六" begins at position 14 (zero-based)
Fantom
Fantom provides several self-explanatory string-matching methods:
startsWith
endsWith
contains
index
(takes an optional index, for the start position)indexIgnoreCase
(like above, ignoring case for ASCII characters)indexr
(start search from end of string, with an optional index)indexrIgnoreCase
(like above, ignoring case for ASCII characters)
<lang fantom> class Main {
public static Void main () { string := "Fantom Language" echo ("String is: " + string) echo ("does string start with 'Fantom'? " + string.startsWith("Fantom")) echo ("does string start with 'Language'? " + string.startsWith("Language")) echo ("does string contain 'age'? " + string.contains("age")) echo ("does string contain 'page'? " + string.contains("page")) echo ("does string end with 'Fantom'? " + string.endsWith("Fantom")) echo ("does string end with 'Language'? " + string.endsWith("Language"))
echo ("Location of 'age' is: " + string.index("age")) posn := string.index ("an") echo ("First location of 'an' is: " + posn) posn = string.index ("an", posn+1) echo ("Second location of 'an' is: " + posn) posn = string.index ("an", posn+1) if (posn == null) echo ("No third location of 'an'") }
} </lang>
- Output:
String is: Fantom Language does string start with 'Fantom'? true does string start with 'Language'? false does string contain 'age'? true does string contain 'page'? false does string end with 'Fantom'? false does string end with 'Language'? true Location of 'age' is: 12 First location of 'an' is: 1 Second location of 'an' is: 8 No third location of 'an'
FBSL
<lang qbasic>#APPTYPE CONSOLE
DIM s = "roko, mat jane do"
IF LEFT(s, 4) = "roko" THEN PRINT STRENC(s), " starts with ", STRENC("roko") IF INSTR(s, "mat") THEN PRINT STRENC(s), " contains ", STRENC("mat"), " at ", INSTR IF RIGHT(s, 2) = "do" THEN PRINT STRENC(s), " ends with ", STRENC("do") PRINT STRENC(s), " contains ", STRENC("o"), " at the following locations:", InstrEx(s, "o")
PAUSE
SUB InstrEx(mane, match)
INSTR = 0 WHILE INSTR(mane, match, INSTR + 1): PRINT " ", INSTR;: WEND
END SUB </lang>
- Output:
"roko, mat jane do" starts with "roko" "roko, mat jane do" contains "mat" at 7 "roko, mat jane do" ends with "do" "roko, mat jane do" contains "o" at the following locations: 2 4 17 Press any key to continue...
Forth
<lang forth>: starts-with ( a l a2 l2 -- ? )
tuck 2>r min 2r> compare 0= ;
- ends-with ( a l a2 l2 -- ? )
tuck 2>r negate over + 0 max /string 2r> compare 0= ;
\ use SEARCH ( a l a2 l2 -- a3 l3 ? ) for contains</lang>
Fortran
Fortran does not offer a string type, but since F77 it has been possible to use a CHARACTER variable, of some specified size, whose size may be accessed via the LEN function. When passed as a parameter, a secret additional parameter specifies its size and so string-like usage is possible. Character matching is case sensitive, and, trailing spaces are ignored so that "xx" and "xx " are deemed equal. The function INDEX(text,target) determines the first index in text where target matches, and returns zero if there is no such match. Unfortunately, the function does not allow the specification of a starting position for a search, as to find any second and further matches. One must specify something like INDEX(text(5:),target)
to start with position five, and then deal with the resulting offsets needed to relate the result to positions within the parameter. On the other hand, since there is no "length" conjoined to the text such substring selections can be made without copying the text to a work area, unlike the copy(text,start,stop)
equivalent of Pascal for example. Some Fortran compilers do offer a starting point, and also an option to search backwards from the end, but these facilities are not guaranteed. Similarly, INDEX is only made available for CHARACTER searching, even though it could easily be generalised to other types.
A second problem is presented by the possibility that a logical expression such as L.LT.0 .OR. etc.
will always or might possibly or in certain constructions but not others be fully evaluated, which is to say that the etc will be evaluated even though L < 0 is true so that the result is determined. And in this case, evaluating the etc will cause trouble because the indexing won't work! To be safe, therefore, a rather lame two-stage test is required - though optimising compilers might well shift code around anyway.
In the case of STARTS, these annoyances can be left to the INDEX function rather than comparing the start of A against B. At the cost of it searching the whole of A if B is not at the start. Otherwise, it would be the mirror of ENDS.
<lang Fortran>
SUBROUTINE STARTS(A,B) !Text A starts with text B? CHARACTER*(*) A,B IF (INDEX(A,B).EQ.1) THEN !Searches A to find B. WRITE (6,*) ">",A,"< starts with >",B,"<" ELSE WRITE (6,*) ">",A,"< does not start with >",B,"<" END IF END SUBROUTINE STARTS
SUBROUTINE HAS(A,B) !Text B appears somewhere in text A? CHARACTER*(*) A,B INTEGER L L = INDEX(A,B) !The first position in A where B matches. IF (L.LE.0) THEN WRITE (6,*) ">",A,"< does not contain >",B,"<" ELSE WRITE (6,*) ">",A,"< contains a >",B,"<, offset",L END IF END SUBROUTINE HAS
SUBROUTINE ENDS(A,B) !Text A ends with text B. CHARACTER*(*) A,B INTEGER L L = LEN(A) - LEN(B) !Find the tail end of A that B might match. IF (L.LT.0) THEN !Dare not use an OR, because of full evaluation risks. WRITE (6,*) ">",A,"< is too short to end with >",B,"<" !Might as well have a special message. ELSE IF (A(L + 1:L + LEN(B)).NE.B) THEN !Otherwise, it is safe to look. WRITE (6,*) ">",A,"< does not end with >",B,"<" ELSE WRITE (6,*) ">",A,"< ends with >",B,"<" END IF END SUBROUTINE ENDS
CALL STARTS("This","is") CALL STARTS("Theory","The") CALL HAS("Bananas","an") CALL ENDS("Banana","an") CALL ENDS("Banana","na") CALL ENDS("Brief","Much longer") END
</lang> Output: text strings are bounded by >etc.< in case of leading or trailing spaces.
>This< does not start with >is< >Theory< starts with >The< >Bananas< contains a >an<, offset 2 >Banana< does not end with >an< >Banana< ends with >na< >Brief< is too short to end with >Much longer<
Similar program using modern Fortran style <lang Fortran> !----------------------------------------------------------------------- !Main program string_matching !----------------------------------------------------------------------- program string_matching
implicit none character(len=*), parameter :: fmt= '(I0)' write(*,fmt) starts("this","is") write(*,fmt) starts("theory","the") write(*,fmt) has("bananas","an") write(*,fmt) ends("banana","an") write(*,fmt) ends("banana","na") write(*,fmt) ends("brief","much longer")
contains ! Determining if the first string starts with second string function starts(string1, string2) result(answer) implicit none character(len=*), intent(in) :: string1 character(len=*), intent(in) :: string2 integer :: answer answer = 0 if(len(string2)>len(string1)) return if(string1(1:len(string2))==string2) answer = 1 end function starts ! Determining if the first string contains the second string at any location function has(string1, string2) result(answer) implicit none character(len=*), intent(in) :: string1 character(len=*), intent(in) :: string2 character(len=:),allocatable :: temp integer :: answer, add character(len=*), parameter :: fmt= '(A6,X,I0)' answer = 0 add = 0 if(len(string2)>len(string1)) return answer = index(string1, string2) if(answer==0) return ! Print the location of the match for part 2 write(*,fmt) " at ", answer ! Handle multiple occurrences of a string for part 2. add = answer temp = string1(answer+1:) do while(answer>0) answer = index(temp, string2) add = add + answer if(answer>0) write(*,fmt) " at ", add ! deallocate(temp) temp = string1(add+1:) ! auto reallocation enddo answer = 1 end function has ! Determining if the first string ends with the second string function ends(string1, string2) result(answer) implicit none character(len=*), intent(in) :: string1 character(len=*), intent(in) :: string2 integer :: answer answer = 0 if(len(string2)>len(string1)) return if(string1(len(string1)-len(string2)+1:)==string2) answer = 1 end function ends
end program string_matching </lang> Output: false = 0, true = 1 ( + multiple occurrences if applicable)
0 1 at 2 at 4 1 0 1 0
In recent standards of Fortran strings as intrinsic first-class type and many intrinsic procedures for strings manipulation have been added.
GML
<lang GML>#define charMatch {
first = "qwertyuiop";
// Determining if the first string starts with second string second = "qwerty"; if (string_pos(second, first) > 0) { show_message("'" + first + "' starts with '" + second + "'"); } else { show_message("'" + first + "' does not start with '" + second + "'"); }
second = "wert" // Determining if the first string contains the second string at any location // Print the location of the match for part 2 if (string_pos(second, first) > 0) { show_message("'" + first + "' contains '" + second + "' at position " + string(x)); } else { show_message("'" + first + "' does not contain '" + second + "'"); } // Handle multiple occurrences of a string for part 2. x = string_count(second, first); show_message("'" + first + "' contains " + string(x) + " instances of '" + second + "'");
// Determining if the first string ends with the second string
second = "random garbage" temp = string_copy(first, (string_length(first) - string_length(second)) + 1, string_length(second)); if (temp == second) { show_message("'" + first + "' ends with '" + second + "'"); } else { show_message("'" + first + "' does not end with '" + second + "'"); }
}</lang>
- Output:
(in message boxes, 1 per line)
'qwertyuiop' starts with 'qwerty' 'qwertyuiop' contains 'wert' at position 0 'qwertyuiop' contains 1 instances of 'wert' 'qwertyuiop' does not end with 'random garbage'
Go
<lang go>package main
import (
"fmt" "strings"
)
func match(first, second string) {
fmt.Printf("1. %s starts with %s: %t\n", first, second, strings.HasPrefix(first, second)) i := strings.Index(first, second) fmt.Printf("2. %s contains %s: %t,\n", first, second, i >= 0) if i >= 0 { fmt.Printf("2.1. at location %d,\n", i) for start := i+1;; { if i = strings.Index(first[start:], second); i < 0 { break } fmt.Printf("2.2. at location %d,\n", start+i) start += i+1 } fmt.Println("2.2. and that's all") } fmt.Printf("3. %s ends with %s: %t\n", first, second, strings.HasSuffix(first, second))
}
func main() {
match("abracadabra", "abr")
}</lang>
- Output:
1. abracadabra starts with abr: true 2. abracadabra contains abr: true, 2.1. at location 0, 2.2. at location 7, 2.2. and that's all 3. abracadabra ends with abr: false
Groovy
Examples: <lang groovy>assert "abcd".startsWith("ab") assert ! "abcd".startsWith("zn") assert "abcd".endsWith("cd") assert ! "abcd".endsWith("zn") assert "abab".contains("ba") assert ! "abab".contains("bb")
assert "abab".indexOf("bb") == -1 // not found flag
assert "abab".indexOf("ab") == 0
def indicesOf = { string, substring ->
if (!string) { return [] } def indices = [-1] while (true) { indices << string.indexOf(substring, indices.last()+1) if (indices.last() == -1) break } indices[1..<(indices.size()-1)]
} assert indicesOf("abab", "ab") == [0, 2] assert indicesOf("abab", "ba") == [1] assert indicesOf("abab", "xy") == []</lang>
All assertions pass, so there is no output.
Haskell
<lang haskell>> import Data.List > "abc" `isPrefixOf` "abcdefg" True > "efg" `isSuffixOf` "abcdefg" True > "bcd" `isInfixOf` "abcdefg" True > "abc" `isInfixOf` "abcdefg" -- Prefixes and suffixes are also infixes True > let infixes a b = findIndices (isPrefixOf a) $ tails b > infixes "ab" "abcdefabqqab" [0,6,10]</lang>
Icon and Unicon
<lang Icon>procedure main()
write("Matching s2 :=",image(s2 := "ab")," within s1:= ",image(s1 := "abcdabab")) write("Test #1 beginning ",if match(s2,s1) then "matches " else "failed") writes("Test #2 all matches at positions [") every writes(" ",find(s2,s1)|"]\n") write("Test #3 ending ", if s1[0-:*s2] == s2 then "matches" else "fails")
end</lang>
- Output:
Matching s2 :="ab" within s1:= "abcdabab" Test #1 beginning matches Test #2 all matches at positions [ 1 5 7 ] Test #3 ending matches
J
<lang j>startswith=: ] -: ({.~ #) contains=: +./@:E.~ endswith=: ] -: ({.~ -@#)</lang>
Example use:
<lang j> 'abcd' startswith 'ab' 1
'abcd' startswith 'cd'
0
'abcd' endswith 'ab'
0
'abcd' endswith 'cd'
1
'abcd' contains 'bb'
0
'abcd' contains 'ab'
1
'abcd' contains 'bc'
1
'abab' contains 'ab'
1
'abab' I.@E.~ 'ab' NB. find starting indicies
0 2</lang>
Note that these verbs contain no constraints restricting them to sequences of characters and so also apply to arrays of type other than character: <lang j> 0 1 2 3 startswith 0 1 NB. integer 1
4.2 5.1 1.3 9 3 contains 1.3 4.2 NB. floating point
0
4.2 5.1 1.3 4.2 9 3 contains 1.3 4.2
1</lang>
Java
<lang java>"abcd".startsWith("ab") //returns true "abcd".endsWith("zn") //returns false "abab".contains("bb") //returns false "abab".contains("ab") //returns true int loc = "abab".indexOf("bb") //returns -1 loc = "abab".indexOf("ab") //returns 0 loc = "abab".indexOf("ab",loc+1) //returns 2</lang>
JavaScript
<lang javascript>var stringA = "tacoloco"
, stringB = "co" , q1, q2, q2multi, m , q2matches = []
// stringA starts with stringB q1 = stringA.substring(0, stringB.length) == stringB
// stringA contains stringB q2 = stringA.indexOf(stringB)
// multiple matches q2multi = new RegExp(stringB,'g')
while(m = q2multi.exec(stringA)){ q2matches.push(m.index) }
// stringA ends with stringB q3 = stringA.substr(-stringB.length) == stringB
console.log("1: Does '"+stringA+"' start with '"+stringB+"'? " + ( q1 ? "Yes." : "No.")) console.log("2: Is '"+stringB+"' contained in '"+stringA+"'? " + (~q2 ? "Yes, at index "+q2+"." : "No.")) if (~q2 && q2matches.length > 1){ console.log(" In fact, it happens "+q2matches.length+" times within '"+stringA+"', at index"+(q2matches.length > 1 ? "es" : "")+" "+q2matches.join(', ')+".") } console.log("3: Does '"+stringA+"' end with '"+stringB+"'? " + ( q3 ? "Yes." : "No."))</lang>
- Output:
1: Does 'tacoloco' start with 'co'? No. 2: Is 'co' contained in 'tacoloco'? Yes, at index 2. In fact, it happens 2 times within 'tacoloco', at indexes 2, 6. 3: Does 'tacoloco' end with 'co'? Yes.
Lasso
<lang Lasso>local(
a = 'a quick brown peanut jumped over a quick brown fox', b = 'a quick brown'
)
//Determining if the first string starts with second string
- a->beginswith(#b) // true
//Determining if the first string contains the second string at any location
- a >> #b // true
- a->contains(#b) // true
//Determining if the first string ends with the second string
- a->endswith(#b) // false</lang>
jq
Using the builtins of jq 1.4 and later: <lang jq># startswith/1 is boolean: "abc" | startswith("ab")
- => true</lang>
<lang jq># index/1 returns the index or null,
- so the jq test "if index(_) then ...." can be used
- without any type conversion.
"abcd" | index( "bc")
- => 1</lang>
<lang jq># endswith/1 is also boolean: "abc" | endswith("bc")
- => true</lang>
Using the regex functions available in jq 1.5: <lang jq>"abc" | test( "^ab")
"abcd" | test("bc")
"abcd" | test("cd$")</lang>
Multiple Occurrences
To determine all the indices of one string in another: <lang sh># In jq 1.4 or later: jq -n '"abcdabcd" | indices("bc")' [
1, 5
]</lang>
In jq 1.5, the regex function match/1 can also be used: <lang sh>$ jq -n '"abcdabcd" | match("bc"; "g") | .offset' 1 5</lang>
Julia
<lang julia>startswith("abcd","ab") #returns true search("abcd","ab") #returns 1:2, indices range where string was found endswith("abcd","zn") #returns false ismatch(r"ab","abcd") #returns true where 1st arg is regex string julia>for r in each_match(r"ab","abab") println(r.offset) end 1 3</lang>
K
<lang k>startswith: {:[0<#p:_ss[x;y];~*p;0]} endswith: {0=(-#y)+(#x)-*_ss[x;y]} contains: {0<#_ss[x;y]}</lang>
Example:
<lang k> startswith["abcd";"ab"] 1
startswith["abcd";"bc"]
0
endswith["abcd";"cd"]
1
endswith["abcd";"bc"]
0
contains["abcdef";"cde"]
1
contains["abcdef";"bdef"]
0
_ss["abcdabceabc";"abc"] / location of matches
0 4 8</lang>
LabVIEW
These images solve the task's requirements in order.
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.
Lang5
<lang lang5>: 2array 2 compress ; : bi* '_ set dip _ execute ; : bi@ dup bi* ;
- comb "" split ; : concat "" join ; : dip swap '_ set execute _ ;
- first 0 extract swap drop ; : flip comb reverse concat ;
- contains
swap 'comb bi@ length do # create a matrix. 1 - "dup 1 1 compress rotate" dip dup 0 == if break then loop drop length compress swap drop "length 1 -" bi@ rot 0 0 "'2array dip" '2array bi* swap 2array slice reverse : concat.(*) concat ; 'concat "'concat. apply" bi* eq 1 1 compress index collapse length if expand drop else drop 0 then ; # r: position.
- end-with 'flip bi@ start-with ;
- start-with 'comb bi@ length rot swap iota subscript 'concat bi@ eq ;
"rosettacode" "rosetta" start-with . # 1 "rosettacode" "taco" contains . # 5 "rosettacode" "ocat" contains . # 0 "rosettacode" "edoc" end-with . # 0 "rosettacode" "code" contains . # 7</lang>
Liberty BASIC
<lang lb>'1---Determining if the first string starts with second string st1$="first string" st2$="first" if left$(st1$,len(st2$))=st2$ then
print "First string starts with second string."
end if
'2---Determining if the first string contains the second string at any location '2.1---Print the location of the match for part 2 st1$="Mississippi" st2$="i" if instr(st1$,st2$) then
print "First string contains second string." print "Second string is at location ";instr(st1$,st2$)
end if
'2.2---Handle multiple occurrences of a string for part 2. pos=instr(st1$,st2$) while pos
count=count+1 pos=instr(st1$,st2$,pos+len(st2$))
wend print "Number of times second string appears in first string is ";count
'3---Determining if the first string ends with the second string st1$="first string" st2$="string" if right$(st1$,len(st2$))=st2$ then
print "First string ends with second string."
end if
</lang>
Logo
<lang logo>to starts.with? :sub :thing
if empty? :sub [output "true] if empty? :thing [output "false] if not equal? first :sub first :thing [output "false] output starts.with? butfirst :sub butfirst :thing
end
to ends.with? :sub :thing
if empty? :sub [output "true] if empty? :thing [output "false] if not equal? last :sub last :thing [output "false] output ends.with? butlast :sub butlast :thing
end
show starts.with? "dog "doghouse ; true show ends.with? "house "doghouse ; true show substring? "gho "doghouse ; true (built-in)</lang>
Lua
<lang lua>s1 = "string" s2 = "str" s3 = "ing" s4 = "xyz"
print( "s1 starts with s2: ", string.find( s1, s2 ) == 1 ) print( "s1 starts with s3: ", string.find( s1, s3 ) == 1, "\n" )
print( "s1 contains s3: ", string.find( s1, s3 ) ~= nil ) print( "s1 contains s3: ", string.find( s1, s4 ) ~= nil, "\n" )
print( "s1 ends with s2: ", select( 2, string.find( s1, s2 ) ) == string.len( s1 ) ) print( "s1 ends with s3: ", select( 2, string.find( s1, s3 ) ) == string.len( s1 ) )</lang>
Maple
These facilities are all to be found in the StringTools package in Maple. <lang Maple> > with( StringTools ): # bind package exports at the top-level > s := "dzrIemaWWIMidXYZwGiqkOOn": > s[1..4]; # pick a prefix
"dzrI"
> IsPrefix( s[ 1 .. 4 ], s ); # check it
true
> s[ -4 .. -1 ]; # pick a suffix
"kOOn"
> IsSuffix( s[ -4 .. -1 ], s ); # check it
true
> p := Search( "XYZ", s ); # find a substring
p := 14
> s[ p .. p + 2 ]; # check
"XYZ"
> SearchAll( [ "WWI", "XYZ" ], s ); # search for multiple patterns
[8, 1], [14, 2]
> to 3 do s := cat( s, s ) end: length( s ); # build a longer string by repeated doubling
192
> p := SearchAll( "XYZ", s ); # find all occurrences
p := 14, 38, 62, 86, 110, 134, 158, 182
> {seq}( s[ i .. i + 2 ], i = p ); # check them
{"XYZ"}
</lang> The StringTools package also contains facilities for regular expression matching, but for fixed string patterns, the Search and SearchAll tools are much faster.
Mathematica
<lang Mathematica>StartWith[x_, y_] := MemberQ[Flatten[StringPosition[x, y]], 1] EndWith[x_, y_] := MemberQ[Flatten[StringPosition[x, y]], StringLength[x]] StartWith["XYZaaabXYZaaaaXYZXYZ", "XYZ"] EndWith["XYZaaabXYZaaaaXYZXYZ", "XYZ"] StringPosition["XYZaaabXYZaaaaXYZXYZ", "XYZ"]</lang>
- Output:
True True {{1,3},{8,10},{15,17},{18,20}}
MATLAB / Octave
<lang Matlab>
% 1. Determining if the first string starts with second string
strcmp(str1,str2,length(str2))
% 2. Determining if the first string contains the second string at any location
~isempty(strfind(s1,s2))
% 3. Determining if the first string ends with the second string
( (length(str1)>=length(str2)) && strcmp(str1(end+[1-length(str2):0]),str2) )
% 1. Print the location of the match for part 2
disp(strfind(s1,s2))
% 2. Handle multiple occurrences of a string for part 2.
ix = strfind(s1,s2); % ix is a vector containing the starting positions of s2 within s1 </lang>
NetRexx
<lang NetRexx>/* NetRexx */ options replace format comments java crossref savelog symbols
lipsum = x_ = 0 x_ = x_ + 1; lipsum[0] = x_; lipsum[x_] = 'Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.' x_ = x_ + 1; lipsum[0] = x_; lipsum[x_] = lipsum[1].reverse
srch = srch[1] = 'Lorem ipsum dolor sit amet' srch[2] = 'consectetur adipisicing elit' srch[3] = 'dolore magna aliqua.'
loop j_ = 1 to lipsum[0]
x1 = lipsum[j_].pos(srch[1]) x2 = lipsum[j_].pos(srch[2]) x3 = lipsum[j_].lastpos(srch[3])
report(x1 = 1, lipsum[j_], srch[1], 'Test string starts with search string:', 'Test string does not start with search string:') report(x2 > 0, lipsum[j_], srch[2], 'Search string located in test string at position:' x2, 'Search string not found within test string:') report(x3 \= srch[3].length, lipsum[j_], srch[3], 'Test string ends with search string:', 'Test string does not start with search string:') end j_
many = x_ = 0 x_ = x_ + 1; many[0] = x_; many[x_] = 'How many times does "many times" occur in this string?' x_ = x_ + 1; many[0] = x_; many[x_] = 'How often does "many times" occur in this string?' x_ = x_ + 1; many[0] = x_; many[x_] = 'How often does it occur in this string?' srch[4] = 'many times'
loop j_ = 1 to many[0]
o_ = 0 k_ = 0 loop label dups until o_ = 0 o_ = many[j_].pos(srch[4], o_ + 1) if o_ \= 0 then k_ = k_ + 1 end dups report(k_ > 0, many[j_], srch[4], 'Number of times search string occurs:' k_, 'Search string not found') end j_
method report(state = boolean, ts, ss, testSuccess, testFailure) public static
if state then say testSuccess else say testFailure say ' Test string:' ts say ' Search string:' ss say
return
</lang>
NewLISP
<lang NewLISP>(setq str "abcdefbcghi")
- test if str starts with "ab"
(starts-with str "ab")
- find "bc" inside str
(find "bc" str)
- test if str ends with "ghi"
(ends-with str "ghi")
- find all positions of pattern inside str
(define (find-all-pos pattern str)
(let ((idx -1) (pos '())) (while (setq idx (find pattern str 0 (+ idx 1))) (push idx pos -1))))
(find-all-pos "bc" str)</lang>
Nim
<lang nim>import strutils
var s: string = "The quick brown fox" if startsWith(s, "The quick"):
echo("Starts with: The quick")
if endsWith(s, "brown Fox"):
echo("Ends with: brown fox")
var pos = find(s, " brown ") # -1 if not found if contains(s, " brown "): # showing the contains() proc, but could use if pos!=-1:
echo('"' & " brown " & '"' & " is located at position: " & $pos)</lang>
- Output:
Starts with: The quick Ends with: brown fox " brown " is located at position: 9
Objective-C
<lang objc>[@"abcd" hasPrefix:@"ab"] //returns true [@"abcd" hasSuffix:@"zn"] //returns false int loc = [@"abab" rangeOfString:@"bb"].location //returns -1 loc = [@"abab" rangeOfString:@"ab"].location //returns 0 loc = [@"abab" rangeOfString:@"ab" options:0 range:NSMakeRange(loc+1, [@"abab" length]-(loc+1))].location //returns 2</lang>
Objeck
<lang objeck> bundle Default {
class Matching { function : Main(args : System.String[]) ~ Nil { "abcd"->StartsWith("ab")->PrintLine(); # returns true "abcd"->EndsWith("zn")->PrintLine(); # returns false ("abab"->Find("bb") <> -1)->PrintLine(); # returns false ("abab"->Find("ab") <> -1)->PrintLine(); # returns true loc := "abab"->Find("bb"); # returns -1 loc := "abab"->Find("ab"); # returns 0 loc := "abab"->Find("ab", loc + 1); # returns 2 } }
} </lang>
OCaml
<lang ocaml>let match1 s1 s2 =
let len1 = String.length s1 and len2 = String.length s2 in if len1 < len2 then false else let sub = String.sub s1 0 len2 in (sub = s2)</lang>
testing in the top-level:
# match1 "Hello" "Hello World!" ;; - : bool = false # match1 "Hello World!" "Hello" ;; - : bool = true
<lang ocaml>let match2 s1 s2 =
let len1 = String.length s1 and len2 = String.length s2 in if len1 < len2 then false else let rec aux i = if i < 0 then false else let sub = String.sub s1 i len2 in if (sub = s2) then true else aux (pred i) in aux (len1 - len2)</lang>
# match2 "It's raining, Hello World!" "umbrella" ;; - : bool = false # match2 "It's raining, Hello World!" "Hello" ;; - : bool = true
<lang ocaml>let match3 s1 s2 =
let len1 = String.length s1 and len2 = String.length s2 in if len1 < len2 then false else let sub = String.sub s1 (len1 - len2) len2 in (sub = s2)</lang>
# match3 "Hello World" "Hello" ;; - : bool = false # match3 "Hello World" "World" ;; - : bool = true
<lang ocaml>let match2_loc s1 s2 =
let len1 = String.length s1 and len2 = String.length s2 in if len1 < len2 then (false, -1) else let rec aux i = if i < 0 then (false, -1) else let sub = String.sub s1 i len2 in if (sub = s2) then (true, i) else aux (pred i) in aux (len1 - len2)</lang>
# match2_loc "The sun's shining, Hello World!" "raining" ;; - : bool * int = (false, -1) # match2_loc "The sun's shining, Hello World!" "shining" ;; - : bool * int = (true, 10)
<lang ocaml>let match2_num s1 s2 =
let len1 = String.length s1 and len2 = String.length s2 in if len1 < len2 then (false, 0) else let rec aux i n = if i < 0 then (n <> 0, n) else let sub = String.sub s1 i len2 in if (sub = s2) then aux (pred i) (succ n) else aux (pred i) (n) in aux (len1 - len2) 0</lang>
# match2_num "This cloud looks like a camel, \ that other cloud looks like a llama" "stone" ;; - : bool * int = (false, 0) # match2_num "This cloud looks like a camel, \ that other cloud looks like a llama" "cloud" ;; - : bool * int = (true, 2)
Oforth
<lang Oforth>func: stringMatching(s1, s2) { | i |
s2 isAllAt(s1, 1) ifTrue: [ System.Out s1 << " begins with " << s2 << cr ] s2 isAllAt(s1, s1 size s2 size - 1 + ) ifTrue: [ System.Out s1 << " ends with " << s2 << cr ]
s1 indexOfAll(s2) ->i i ifNotNull: [ System.Out s1 << " includes " << s2 << " at position : " << i << cr ]
"\nAll positions : " println 1 ->i while (s1 indexOfAllFrom(s2, i) dup ->i notNull) [ System.Out s1 << " includes " << s2 << " at position : " << i << cr i s2 size + ->i ]
}</lang>
- Output:
>stringMatching("arduinoardblobard", "ard") arduinoardblobard begins with ard arduinoardblobard ends with ard arduinoardblobard includes ard at position : 1 All positions : arduinoardblobard includes ard at position : 1 arduinoardblobard includes ard at position : 8 arduinoardblobard includes ard at position : 15
OxygenBasic
<lang oxygenbasic> string s="sdfkjhgsdfkdfgkbopefioqwurti487sdfkrglkjfs9wrtgjglsdfkdkjcnmmb.,msfjflkjsdfk"
string f="sdfk"
string cr=chr(13)+chr(10),tab=chr(9)
string pr="FIND STRING LOCATIONS" cr cr
sys a=0, b=1, count=0, ls=len(s), lf=len(f)
do
a=instr b,s,f if a=0 then exit do count++ if a=1 then pr+="Begins with keyword" cr pr+=count tab a cr if a=ls-lf+1 then pr+="Ends with keyword at " a cr b=a+1
end do
pr+=cr "Total matches: " count cr
print pr
'FIND STRING LOCATIONS ' 'Begins with keyword '1 1 '2 8 '3 32 '4 51 '5 73 'Ends with keyword at 73 ' 'Total matches: 5 </lang>
PARI/GP
This meets the first but not the second of the optional requirements. Note that GP treats any nonzero value as true so the location found by contains() can be ignore if not needed. <lang parigp>startsWith(string, prefix)={
string=Vec(string); prefix=Vec(prefix); if(#prefix > #string, return(0)); for(i=1,#prefix,if(prefix[i]!=string[i], return(0))); 1
}; contains(string, inner)={
my(good); string=Vec(string); inner=Vec(inner); for(i=0,#string-#inner, good=1; for(j=1,#inner, if(inner[j]!=string[i+j], good=0; break) ); if(good, return(i+1)) ); 0
}; endsWith(string, suffix)={
string=Vec(string); suffix=Vec(suffix); if(#suffix > #string, return(0)); for(i=1,#suffix,if(prefix[i]!=string[i+#string-#suffix], return(0))); 1
};</lang>
Perl
Using regexes:
<lang perl>$str1 =~ /^\Q$str2\E/ # true if $str1 starts with $str2 $str1 =~ /\Q$str2\E/ # true if $str1 contains $str2 $str1 =~ /\Q$str2\E$/ # true if $str1 ends with $str2</lang>
Using index
:
<lang perl>index($str1, $str2) == 0 # true if $str1 starts with $str2 index($str1, $str2) != -1 # true if $str1 contains $str2 rindex($str1, $str2) == length($str1) - length($str2) # true if $str1 ends with $str2</lang>
Using substr
:
<lang perl>substr($str1, 0, length($str2)) eq $str2 # true if $str1 starts with $str2 substr($str1, - length($str2)) eq $str2 # true if $str1 ends with $str2</lang>
Bonus task (printing all positions where $str2
appears in $str1
):
<lang perl>print $-[0], "\n" while $str1 =~ /\Q$str2\E/g; # using a regex</lang> <lang perl>my $i = -1; print $i, "\n" while ($i = index $str1, $str2, $i + 1) != -1; # using index</lang>
Perl 6
<lang perl6>my @subs = (
# Regex-based: sub R_contains ( Str $_, Str $s2 ) { ? m/ $s2 / }, sub R_starts_with ( Str $_, Str $s2 ) { ? m/ ^ $s2 / }, sub R_ends_with ( Str $_, Str $s2 ) { ? m/ $s2 $ / },
# Index-based: sub I_contains ( Str $_, Str $s2 ) { .index( $s2) .defined }, sub I_starts_with ( Str $_, Str $s2 ) { my $m = .index( $s2); $m.defined and $m == 0 }, sub I_ends_with ( Str $_, Str $s2 ) { my $m = .rindex($s2); $m.defined and $m == .chars - $s2.chars },
# Substr-based: sub S_starts_with ( Str $_, Str $s2 ) { .substr(0, $s2.chars) eq $s2 }, sub S_ends_with ( Str $_, Str $s2 ) { .substr( *-$s2.chars) eq $s2 },
# Optional tasks: sub R_find ( Str $_, Str $s2 ) { $/.from if /$s2/ }, sub R_find_all ( Str $_, Str $s2 ) { my @p = .match: /$s2/, :g; @p».from if @p; },
);
my $str1 = 'abcbcbcd'; my @str2s = < ab bc cd zz >;
say "'$str1' vs:".fmt('%15s '), @str2s.fmt('%-15s'); for [1, 4, 6], [2, 5, 7], [0, 3], [8, 9] {
say(); for @subs[.list] -> $sub { say "{$sub.name}:".fmt('%15s '), @str2s.map({ ~$sub.($str1, $_) }).fmt('%-15s'); }
}</lang>
- Output:
'abcbcbcd' vs: ab bc cd zz R_starts_with: Bool::True Bool::False Bool::False Bool::False I_starts_with: Bool::True Bool::False Bool::False Bool::False S_starts_with: Bool::True Bool::False Bool::False Bool::False R_ends_with: Bool::False Bool::False Bool::True Bool::False I_ends_with: Bool::False Bool::False Bool::True Bool::False S_ends_with: Bool::False Bool::False Bool::True Bool::False R_contains: Bool::True Bool::True Bool::True Bool::False I_contains: Bool::True Bool::True Bool::True Bool::False R_find: 0 1 6 Nil() R_find_all: 0 1 3 5 6 Nil()
Phix
<lang Phix>constant word = "the", -- (also try this with "th"/"he")
sentence = "the last thing the man said was the"
-- sentence = "thelastthingthemansaidwasthe" -- (practically the same results)
-- A common, but potentially inefficient idiom for checking for a substring at the start is: if match(word,sentence)=1 then
?"yes(1)"
end if -- A more efficient method is to test the appropriate slice if length(sentence)>=length(word) and sentence[1..length(word)]=word then
?"yes(2)"
end if -- Which is almost identical to checking for a word at the end if length(sentence)>=length(word) and sentence[-length(word)..-1]=word then
?"yes(3)"
end if -- Or sometimes you will see this, a tiny bit more efficient: if length(sentence)>=length(word) and match(word,sentence,length(sentence)-length(word)+1) then
?"yes(4)"
end if -- Finding all occurences is a snap: integer r = match(word,sentence) while r!=0 do
?r r = match(word,sentence,r+1)
end while</lang>
- Output:
"yes(1)" "yes(2)" "yes(3)" "yes(4)" 1 16 33
PHP
<lang php><?php /**********************************************************************************
- This program gets needle and haystack from the caller (chm.html) (see below)
- and checks for occurrences of the needle in the haystack
- 02.05.2013 Walter Pachl
- Comments or Suggestions welcome
- /
$haystack = $_POST['haystack']; if ($haystack==) {$haystack='no haystack given';} $needle = $_POST['needle']; if ($needle==) {$needle='no needle given';}
function rexxpos($h,$n) {
$pos = strpos($h,$n); if ($pos === false) { $pos=-1; } else { $pos=$pos+1; } return ($pos); }
$pos=rexxpos($haystack,$needle); $tx1 = ""; if ($pos==-1){ $n=0; } // not found else { $n=1; } // found once (so far) // Special cases if ($pos==1){ $tx1="needle found to be the start of the haystack"; } if ($pos==strlen($haystack)-strlen($needle)+1)
{ $tx1="needle found at end of haystack"; }
if ($n>0) { // look for other occurrences
$pl=$pos; // list of positions $p=$pos; // $x="*************************************"; $h=$haystack; while ($p>0) { $h=substr($x,0,$p).substr($h,$p); $p=rexxpos($h,$needle); if ( $p>0 ) { $n=$n+1; $pl=$pl.", ".$p; } } if ($n==1) { $txt="needle found once in haystack, position: $pl."; } else if ($n==2) { $txt="needle found twice in haystack, position(s): $pl."; } else { $txt="needle found $n times in haystack, position(s): $pl."; }
} else { $txt="needle not found in haystack."; } ?> <html>
<head> <title>Character Matching</title> <meta name="author" content="Walter Pachl"> <meta name="date" content="02.05.2013"> <style> p { font: 120% courier; } </style> </head> <body>
Haystack: '<?php echo "$haystack" ?>'
Needle: '<?php echo "$needle" ?>'
<?php echo "$txt" ?>
<?php echo "$tx1" ?>
</body>
</html></lang> <lang php><?php <!DOCTYPE html> <html>
<head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> <title>Character matching</title> </head> <body> <form id="test" name="test" method="post" action="chmx.php">
Character matching
Given two strings, demonstrate the following 3 types of matchings:
- Determining if the first string starts with second string
- Determining if the first string contains the second string at any location
- Determining if the first string ends with the second string
Optional requirements:
- Print the location of the match(es) for part 2
- Handle multiple occurrences of a string for part 2.
Haystack: <input type="text" name="haystack" size="80">
Needle: <input type="text" name="needle" size="80">
Press <input name="Submit" type="submit" class="erfolg" value="CHECK"/> to invoke chmx.php.
</form> </body>
</html></lang>
PicoLisp
<lang PicoLisp>: (pre? "ab" "abcd") -> "abcd"
- (pre? "xy" "abcd")
-> NIL
- (sub? "bc" "abcd")
-> "abcd"
- (sub? "xy" "abcd")
-> NIL
- (tail (chop "cd") (chop "abcd"))
-> ("c" "d")
- (tail (chop "xy") (chop "abcd"))
-> NIL
(de positions (Pat Str)
(setq Pat (chop Pat)) (make (for ((I . L) (chop Str) L (cdr L)) (and (head Pat L) (link I)) ) ) )
- (positions "bc" "abcdabcd")
-> (2 6)</lang>
PL/I
<lang PL/I> /* Let s be one string, t be the other that might exist within s. */
/* 8-1-2011 */
k = index(s, t); if k = 0 then put skip edit (t, ' is nowhere in sight') (a); else if k = 1 then
put skip edit (t, ' starts at the beginning of ', s) (a);
else if k+length(t)-1 = length(s) then
put skip edit (t, ' is at the end of ', s) (a);
else put skip edit (t, ' is within ', s) (a);
if k > 0 then put skip edit (t, ' starts at position ', k) (a); </lang>
Optional extra:
<lang PL/I> /* Handle multiple occurrences. */
n = 1; do forever; k = index(s, t, n); if k = 0 then do; if n = 1 then put skip list (t, ' is nowhere in sight'); stop; end; else if k = 1 then put skip edit ('<', t, '> starts at the beginning of ', s) (a); else if k+length(t)-1 = length(s) then put skip edit ('<', t, '> is at the end of ', s) (a); else put skip edit ('<', t, '> is within ', s) (a); n = k + length(t);
if k > 0 then put skip edit ('<', t, '> starts at position ', trim(k)) (a); else stop; end;
</lang>
PureBasic
<lang PureBasic>Procedure StartsWith(String1$, String2$)
Protected Result If FindString(String1$, String2$, 1) =1 ; E.g Found in possition 1 Result =CountString(String1$, String2$) EndIf ProcedureReturn Result
EndProcedure
Procedure EndsWith(String1$, String2$)
Protected Result, dl=Len(String1$)-Len(String2$) If dl>=0 And Right(String1$, Len(String2$))=String2$ Result =CountString(String1$, String2$) EndIf ProcedureReturn Result
EndProcedure</lang> And a verification <lang PureBasic>If OpenConsole()
PrintN(Str(StartsWith("Rosettacode", "Rosetta"))) ; = 1 PrintN(Str(StartsWith("Rosettacode", "code"))) ; = 0 PrintN(Str(StartsWith("eleutherodactylus cruralis", "e"))) ; = 3 PrintN(Str(EndsWith ("Rosettacode", "Rosetta"))) ; = 0 PrintN(Str(EndsWith ("Rosettacode", "code"))) ; = 1 PrintN(Str(EndsWith ("Rosettacode", "e"))) ; = 2 Print(#CRLF$ + #CRLF$ + "Press ENTER to exit"): Input() CloseConsole()
EndIf</lang>
An alternate and more complete solution: <lang PureBasic>Procedure startsWith(string1$, string2$)
;returns one if string1$ starts with string2$, otherwise returns zero If FindString(string1$, string2$, 1) = 1 ProcedureReturn 1 EndIf ProcedureReturn 0
EndProcedure
Procedure contains(string1$, string2$, location = 0)
;returns the location of the next occurrence of string2$ in string1$ starting from location, ;or zero if no remaining occurrences of string2$ are found in string1$ ProcedureReturn FindString(string1$, string2$, location + 1)
EndProcedure
Procedure endsWith(string1$, string2$)
;returns one if string1$ ends with string2$, otherwise returns zero Protected ls = Len(string2$) If Len(string1$) - ls >= 0 And Right(string1$, ls) = string2$ ProcedureReturn 1 EndIf ProcedureReturn 0
EndProcedure
If OpenConsole()
PrintN(Str(startsWith("RosettaCode", "Rosetta"))) ; = 1, true PrintN(Str(startsWith("RosettaCode", "Code"))) ; = 0, false PrintN("") PrintN(Str(contains("RosettaCode", "luck"))) ; = 0, no occurrences Define location Repeat location = contains("eleutherodactylus cruralis", "e", location) PrintN(Str(location)) ;display each occurrence: 1, 3, 7, & 0 (no more occurrences) Until location = 0 PrintN("") PrintN(Str(endsWith ("RosettaCode", "Rosetta"))) ; = 0, false PrintN(Str(endsWith ("RosettaCode", "Code"))) ; = 1, true Print(#CRLF$ + #CRLF$ + "Press ENTER to exit"): Input() CloseConsole()
EndIf</lang>
- Output:
1 0 0 1 3 7 0 0 1
PowerShell
<lang Powershell> "spicywiener".StartsWith("spicy") "spicywiener".Contains("icy") "spicywiener".EndsWith("wiener") "spicywiener".IndexOf("icy") [regex]::Matches("spicywiener", "i").count </lang>
- Output:
True True True 2 2
Python
<lang python>"abcd".startswith("ab") #returns True "abcd".endswith("zn") #returns False "bb" in "abab" #returns False "ab" in "abab" #returns True loc = "abab".find("bb") #returns -1 loc = "abab".find("ab") #returns 0 loc = "abab".find("ab",loc+1) #returns 2</lang>
Racket
<lang racket>
- lang racket
(require srfi/13) (string-prefix? "ab" "abcd") (string-suffix? "cd" "abcd") (string-contains "abab" "bb") (string-contains "abab" "ba") </lang>
- Output:
#t #t #f 1
Retro
<lang Retro>: startsWith? ( $1 $2 - f )
withLength &swap dip 0 swap ^strings'getSubset compare ;
"abcdefghijkl" "abcde" startsWith? "abcdefghijkl" "bcd" startsWith?
"abcdefghijkl" "bcd" ^strings'search "abcdefghijkl" "zmq" ^strings'search
- endsWith? ( $1 $2 - f )
swap withLength + over getLength - compare ;
"abcdefghijkl" "ijkl" endsWith? "abcdefghijkl" "abc" endsWith?</lang>
REXX
Extra coding was added to take care of using plurals in the output messages. <lang rexx>/*REXX program demonstrates some basic character string testing. */ parse arg a b /*obtain A and B from the C.L. */ say 'string A = ' a /*display string A to terminal.*/ say 'string B = ' b /* " " B " " */ say if left(A,length(b))==b then say 'string A starts with string B'
else say "string A doesn't start with string B"
say
/*another method, however a wee bit obtuse. */
/*¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬ if compare(a,b)==length(b) then say 'string A starts with string B'
else say "string A doesn't start with string B"
¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬¬*/
/* [↑] above is a big comment. */
p=pos(b,a) if p==0 then say "string A doesn't contain string B"
else say 'string A contains string B (starting in position' p")"
say if right(A,length(b))==b then say 'string A ends with string B'
else say "string A doesn't end with string B"
say Ps=; p=0; do until p==0
p=pos(b, a, p+1) if p\==0 then Ps = Ps',' p end /*until ···*/
Ps=space(strip(Ps, 'L', ",")) times=words(Ps) if times==0 then say "string A doesn't contain string B"
else say 'string A contains string B ', times 'time'left('s',times>1), "(at position"left('s', times>1) Ps')'
/*stick a fork in it, we're done.*/</lang>
- Output:
when the following is specified (five Marx brothers)
string A = Chico_Harpo_Groucho_Zeppo_Gummo string B = p string A doesn't start with string B string A contains string B (starting in position 10) string A doesn't end with string B string A contains string B 3 times (at positions 10, 23, 24)
- Output:
when the following is specified
string A = Chico_Harpo_Groucho_Zeppo_Gummo string B = Z string A doesn't start with string B string A contains string B (starting in position 21) string A doesn't end with string B string A contains string B 1 time (at position 21)
- Output:
when the following is specified
string A = Chico_Harpo_Groucho_Zeppo_Gummo string B = Chi string A starts with string B string A contains string B (starting in position 1) string A doesn't end with string B string A contains string B 1 time (at position 1)
- Output:
when the following is specified
string A = Chico_Harpo_Groucho_Zeppo_Gummo string B = mmo string A doesn't start with string B string A contains string B (starting in position 29) string A ends with string B string A contains string B 1 time (at position 29)
Ring
<lang ring> aString = "Welcome to the Ring Programming Language" bString = "Ring" bStringIndex = substr(aString,bString) if bStringIndex > 0 see bStringIndex
see " : " + bString ok
</lang>
Ruby
<lang ruby>p 'abcd'.start_with?('ab') #returns true p 'abcd'.end_with?('ab') #returns false p 'abab'.include?('bb') #returns false p 'abab'.include?('ab') #returns true p 'abab'['bb'] #returns nil p 'abab'['ab'] #returns "ab" p 'abab'.index('bb') #returns nil p 'abab'.index('ab') #returns 0 p 'abab'.index('ab', 1) #returns 2 p 'abab'.rindex('ab') #returns 2</lang>
Run BASIC
<lang runbasic>s1$ = "abc def ghi klmnop" s2$ = "abc" ' begins with s3$ = "ef" ' is in the string s4$ = "nop" ' ends with
sn2$ = "abcx" ' not begins with sn3$ = "efx" ' not in the string sn4$ = "nopx" ' not ends with
if left$(s1$,len(s2$)) <> s2$ then a$ = "Not " print "String:";s1$;" does ";a$;"begin with:";s2$
if instr(s1$,s3$) = 0 then a$ = "Not " print "String:";s1$;" does ";a$;"contain:";s3$
if mid$(s1$,len(s1$) + 1 - len(s4$),len(s4$)) <> s4$ then a$ = "Not " print "String:";s1$;" does ";a$;"end with:";s4$
' ----------- not ----------------------------- print if left$(s1$,len(sn2$)) <> sn2$ then a$ = "Not " print "String:";s1$;" does ";a$;"begin with:";sn2$
if instr(s1$,sn3$) = 0 then a$ = "Not " print "String:";s1$;" does ";a$;"contain:";sn3$
if mid$(s1$,len(s1$) + 1 - len(sn4$),len(sn4$)) <> sn4$ then a$ = "Not " print "String:";s1$;" does ";a$;"end with:";sn4$</lang>
- Output:
String:abc def ghi klmnop does begin with:abc String:abc def ghi klmnop does contain:ef String:abc def ghi klmnop does end with:nop String:abc def ghi klmnop does Not begin with:abcx String:abc def ghi klmnop does Not contain:efx String:abc def ghi klmnop does Not end with:nopx
Rust
<lang rust>fn print_match(possible_match: Option<usize>) {
match possible_match { Some(match_pos) => println!("Found match at pos {}", match_pos), None => println!("Did not find any matches") }
}
fn main() {
let s1 = "abcd"; let s2 = "abab"; let s3 = "ab"; // Determining if the first string starts with second string assert!(s1.starts_with(s3)); // Determining if the first string contains the second string at any location assert!(s1.contains(s3)); // Print the location of the match print_match(s1.find(s3)); // Found match at pos 0 print_match(s1.find(s2)); // Did not find any matches // Determining if the first string ends with the second string assert!(s2.ends_with(s3));
}</lang>
Scala
<lang scala>"abcd".startsWith("ab") //returns true "abcd".endsWith("zn") //returns false "abab".contains("bb") //returns false "abab".contains("ab") //returns true
var loc="abab".indexOf("bb") //returns -1 loc = "abab".indexOf("ab") //returns 0 loc = "abab".indexOf("ab", loc+1) //returns 2</lang>
Seed7
<lang seed7>$ include "seed7_05.s7i";
const proc: main is func
local var integer: position is 0; begin writeln(startsWith("abcd", "ab")); # write TRUE writeln(endsWith("abcd", "zn")); # write FALSE writeln(pos("abab", "bb") <> 0); # write FALSE writeln(pos("abab", "ab") <> 0); # write TRUE writeln(pos("abab", "bb")); # write 0 position := pos("abab", "ab"); writeln(position); # position is 1 position := pos("abab", "ab", succ(position)); writeln(position); # position is 3 end func;</lang>
- Output:
TRUE FALSE FALSE TRUE 0 1 3
Sidef
<lang ruby>var first = "abc-abcdef-abcd"; var second = "abc";
say first.begins_with(second); #=> true say first.contains(second); #=> true say first.ends_with(second); #=> false
- Get and print the location of the match
say first.index(second); #=> 0
- Find multiple occurrences of a string
var pos = -1; while (pos = first.index(second, pos+1) != -1) {
say "Match at pos: #{pos}";
}</lang>
Smalltalk
<lang smalltalk>a startsWith: b a includesSubCollection: b a endsWith: b a indexOfSubCollection: b a indexOfSubCollection: b startingAt: pos</lang>
SNOBOL4
<lang SNOBOL4> s1 = 'abcdabefgab'
s2 = 'ab' s3 = 'xy' OUTPUT = ?(s1 ? POS(0) s2) "1. " s2 " begins " s1 OUTPUT = ?(s1 ? POS(0) s3) "1. " s3 " begins " s1 ;# fails
n = 0
again s1 POS(n) ARB s2 @a :F(p3)
OUTPUT = "2. " s2 " found at position "
+ a - SIZE(s2) " in " s1
n = a :(again)
p3 OUTPUT = ?(s1 ? s2 RPOS(0)) "3. " s2 " ends " s1 END</lang>
- Output:
1. ab begins abcdabefgab 2. ab found at position 0 in abcdabefgab 2. ab found at position 4 in abcdabefgab 2. ab found at position 9 in abcdabefgab 3. ab ends abcdabefgab
Standard ML
<lang sml>String.isPrefix "ab" "abcd"; (* returns true *) String.isSuffix "zn" "abcd"; (* returns false *) String.isSubstring "bb" "abab"; (* returns false *) String.isSubstring "ab" "abab"; (* returns true *)
- 2 (Substring.base (#2 (Substring.position "bb" (Substring.full "abab")))); (* returns 4 *)
val loc = #2 (Substring.base (#2 (Substring.position "ab" (Substring.full "abab")))); (* returns 0 *) val loc' = #2 (Substring.base (#2 (Substring.position "ab" (Substring.extract ("abab", loc+1, NONE))))); (* returns 2 *)</lang>
Swift
<lang swift>var str = "Hello, playground" str.hasPrefix("Hell") //True str.hasPrefix("hell") //False
str.containsString("llo") //True str.containsString("xxoo") //False
str.hasSuffix("playground") //True str.hasSuffix("world") //False</lang>
Tcl
In this code, we are looking in various ways for the string in the variable needle in the string in the variable haystack. <lang tcl>set isPrefix [string equal -length [string length $needle] $haystack $needle] set isContained [expr {[string first $needle $haystack] >= 0}] set isSuffix [string equal $needle [string range $haystack end-[expr {[string length $needle]-1}] end]]</lang>
Of course, in the cases where the needle is a glob-safe string (i.e., doesn't have any of the characters “*?[\” in), this can be written far more conveniently: <lang tcl>set isPrefix [string match $needle* $haystack] set isContained [string match *$needle* $haystack] set isSuffix [string match *$needle $haystack]</lang>
Another powerful technique is to use the regular expression engine in literal string mode:
<lang tcl>set isContained [regexp ***=$needle $haystack]</lang>
This can be extended by getting the regexp
to return the locations of the matches, enabling the other forms of match to be done:
<lang tcl>set matchLocations [regexp -indices -all -inline ***=$needle $haystack]
- Each match location is a pair, being the index into the string where the needle started
- to match and the index where the needle finished matching
set isContained [expr {[llength $matchLocations] > 0}] set isPrefix [expr {[lindex $matchLocations 0 0] == 0}] set isSuffix [expr {[lindex $matchLocations end 1] == [string length $haystack]-1}] set firstMatchStart [lindex $matchLocations 0 0] puts "Found \"$needle\" in \"$haystack\" at $firstMatchStart" foreach location $matchLocations {
puts "needle matched at index [lindex $location 0]"
}</lang>
TUSCRIPT
<lang tuscript> $$ MODE TUSCRIPT ASK "string1", string1="" ASK "string2", string2=""
IF (string1.sw.string2) THEN PRINT string1," starts with ",string2 ELSE PRINT string1," not starts with ",string2 ENDIF SET beg=STRING (string1,string2,0,0,0,end) IF (beg!=0) THEN PRINT string1," contains ",string2 PRINT " starting in position ",beg PRINT " ending in position ",end ELSE PRINT string1," not contains ",string2 ENDIF
IF (string1.ew.string2) THEN PRINT string1," ends with ",string2 ELSE PRINT string1," not ends with ",string2 ENDIF </lang>
- Output:
string1 >Rosetta Code string2 >Code Rosetta Code not starts with Code Rosetta Code contains Code starting in position 9 ending in position 13 Rosetta Code ends with Code
TXR
TXR Lisp
<lang txrlisp>(tree-case *args*
((big small) (cond ((< (length big) (length small)) (put-line `@big is shorter than @small`)) ((str= big small) (put-line `@big and @small are equal`)) ((match-str big small) (put-line `@small is a prefix of @big`)) ((match-str big small -1) (put-line `@small is a suffix of @big`)) (t (let ((pos (search-str big small))) (if pos (put-line `@small occurs in @big at position @pos`) (put-line `@small does not occur in @big`)))))) (otherwise (put-line `usage: @(ldiff *full-args* *args*) <bigstring> <smallstring>`)))</lang>
- Output:
$ txr cmatch2.tl x usage: txr cmatch2.tl <bigstring> <smallstring> $ txr cmatch2.tl x y z usage: txr cmatch2.tl <bigstring> <smallstring> $ txr cmatch2.tl catalog cat cat is a prefix of catalog $ txr cmatch2.tl catalog log log is a suffix of catalog $ txr cmatch2.tl catalog at at occurs in catalog at position 1 $ txr cmatch2.tl catalog catalogue catalog is shorter than catalogue $ txr cmatch2.tl catalog catalog catalog and catalog are equal $ txr cmatch2.tl catalog dog dog does not occur in catalog
Pattern Language
<lang txr>@line @(cases) @ line @ (output) second line is the same as first line @ (end) @(or) @ (skip)@line @ (output) first line is a suffix of the second line @ (end) @(or) @ line@(skip) @ (output) first line is a suffix of the second line @ (end) @(or) @ prefix@line@(skip) @ (output) first line is embedded in the second line at position @(length prefix) @ (end) @(or) @ (output) first line is not found in the second line @ (end) @(end)</lang>
- Output:
$ txr cmatch.txr - 123 01234 first line is embedded in the second line at position 1 $ txr cmatch.txr - 123 0123 first line is a suffix of the second line
VBScript
<lang vb>Function StartsWith(s1,s2) StartsWith = False If Left(s1,Len(s2)) = s2 Then StartsWith = True End If End Function
Function Contains(s1,s2) Contains = False If InStr(1,s1,s2) Then Contains = True & " at positions " j = 1 Do Until InStr(j,s1,s2) = False Contains = Contains & InStr(j,s1,s2) & ", " If j = 1 Then If Len(s2) = 1 Then j = j + InStr(j,s1,s2) Else j = j + (InStr(j,s1,s2) + (Len(s2) - 1)) End If Else If Len(s2) = 1 Then j = j + ((InStr(j,s1,s2) - j) + 1) Else j = j + ((InStr(j,s1,s2) - j) + (Len(s2) - 1)) End If End If Loop End If End Function
Function EndsWith(s1,s2) EndsWith = False If Right(s1,Len(s2)) = s2 Then EndsWith = True End If End Function
WScript.StdOut.Write "Starts with test, 'foo' in 'foobar': " & StartsWith("foobar","foo") WScript.StdOut.WriteLine WScript.StdOut.Write "Contains test, 'o' in 'fooooobar': " & Contains("fooooobar","o") WScript.StdOut.WriteLine WScript.StdOut.Write "Ends with test, 'bar' in 'foobar': " & EndsWith("foobar","bar")</lang>
- Output:
Starts with test, 'foo' in 'foobar': True Contains test, 'o' in 'fooooobar': True at positions 2, 3, 4, 5, 6, Ends with test, 'bar' in 'foobar': True
XPL0
<lang XPL0>include c:\cxpl\codes; \intrinsic 'code' declarations string 0; \use zero-terminated strings
func StrLen(A); \Return number of characters in a string char A; int I; for I:= 0 to -1>>1-1 do
if A(I) = 0 then return I;
func StrFind(A, B); \Search for string B in string A \Returns index of first occurrence of string B in A, or -1 if B is not found char A, B; \strings to be compared int LA, LB, I, J; [LA:= StrLen(A);
LB:= StrLen(B); for I:= 0 to LA-LB do [for J:= 0 to LB-1 do if B(J) # A(J+I) then J:= LB+1; if J = LB then return I; \found ];
return -1; ];
char Str; int I, J; [Str:= "pack my box with"; \ 0123456789012345 Text(0, if StrFind(Str, "pack") = 0 then "yes" else "no"); CrLf(0); \1. Text(0, if StrFind(Str, "ack") = 0 then "yes" else "no"); CrLf(0); I:= StrFind(Str, "x w"); Text(0, if I >= 0 then "yes" else "no"); \2. Text(0, ", at offset "); IntOut(0, I); CrLf(0); I:= 0; J:= 0; \offsets of space characters loop [I:= StrFind(Str+J, " ");
if I < 0 then quit; IntOut(0, I+J); ChOut(0, ^ ); J:= J+I+1; ];
CrLf(0); Text(0, if StrFind(Str, "X w") >= 0 then "yes" else "no"); CrLf(0); Text(0, if StrFind(Str, "with") = StrLen(Str)-StrLen("with") then "yes" else "no"); CrLf(0); \3. Text(0, if StrFind(Str, "x w" ) = StrLen(Str)-StrLen("x w" ) then "yes" else "no"); CrLf(0); ]</lang>
- Output:
yes no yes, at offset 10 4 7 11 no yes no
zkl
<lang zkl>fcn f(text,p){ if(text.find(p)==0)println("Yep") else println("Nope") } f("foobar","foo") //--> Yep f("foobar","bar") //--> Nope</lang> <lang zkl>fcn f(text,p){ if(Void!=(n:=text.find(p)))println("Contained @",n) else println("Nope") } f("foobar","ob") //--> Contained @2 f("foobar","food") //--> Nope</lang> <lang zkl>fcn f(text,p){
if( Void!=(n:=text.rfind(p)) and n+p.len()==text.len() ) println("tail gunner") else println("Nope")
} f("foobar","r"); f("foobar","ar"); //--> tail gunners f("foobar","ob"); //--> Nope f("foobarfoobar","bar"); //--> tail gunner</lang>
- Programming Tasks
- String manipulation
- Basic Data Operations
- Simple
- Ada
- Aime
- ALGOL 68
- AutoHotkey
- AutoIt
- AWK
- BASIC
- Applesoft BASIC
- Batch File
- BBC BASIC
- Bracmat
- C
- C++
- C sharp
- Clojure
- CoffeeScript
- Common Lisp
- Component Pascal
- D
- DCL
- Delphi
- E
- EchoLisp
- Elena
- Elixir
- Emacs Lisp
- Erlang
- Euphoria
- F Sharp
- Fantom
- FBSL
- Forth
- Fortran
- GML
- Go
- Groovy
- Haskell
- Icon
- Unicon
- J
- Java
- JavaScript
- Lasso
- Jq
- Julia
- K
- LabVIEW
- Lang5
- Liberty BASIC
- Logo
- Lua
- Maple
- Mathematica
- MATLAB
- Octave
- NetRexx
- NewLISP
- Nim
- Objective-C
- Objeck
- OCaml
- Oforth
- OxygenBasic
- PARI/GP
- Perl
- Perl 6
- Phix
- PHP
- PicoLisp
- PL/I
- PureBasic
- PowerShell
- Python
- Racket
- Retro
- REXX
- Ring
- Ruby
- Run BASIC
- Rust
- Scala
- Seed7
- Sidef
- Smalltalk
- SNOBOL4
- Standard ML
- Swift
- Tcl
- TUSCRIPT
- TXR
- VBScript
- XPL0
- Zkl
- Bc/Omit
- Dc/Omit