I'm working on modernizing Rosetta Code's infrastructure. Starting with communications. Please accept this time-limited open invite to RC's Slack.. --Michael Mol (talk) 20:59, 30 May 2020 (UTC)

Unique characters in each string

From Rosetta Code
Unique characters in each string is a draft programming task. It is not yet considered ready to be promoted as a complete task, for reasons that should be found in its talk page.
Task

Given a list of strings, find the characters appearing exactly once in each string.

The result should be in alphabetical order.

Use the following list for this task:

        ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]

For this list, the result would be: 1 2 3 a b c

Other tasks related to string operations:
Metrics
Counting
Remove/replace
Anagrams/Derangements/shuffling
Find/Search/Determine
Formatting
Song lyrics/poems/Mad Libs/phrases
Tokenize
Sequences



Ada[edit]

with Ada.Text_Io;
 
procedure Unique_Characters is
 
type Occurence_Count is array (Character) of Natural;
type Occurence_List is array (Positive range <>) of Occurence_Count;
 
function Occurences (Item : String) return Occurence_Count is
Count : Occurence_Count := (others => 0);
begin
for C of Item loop
Count (C) := Count (C) + 1;
end loop;
return Count;
end Occurences;
 
procedure Put_Unique (List : Occurence_List) is
use Ada.Text_Io;
begin
for C in List (List'First)'Range loop
if (for all I in List'Range => List (I) (C) = 1) then
Put (C);
Put (' ');
end if;
end loop;
end Put_Unique;
 
begin
Put_Unique ((1 => Occurences ("1a3c52debeffd"),
2 => Occurences ("2b6178c97a938stf"),
3 => Occurences ("3ycxdb1fgxa2yz")));
end Unique_Characters;
Output:
1 2 3 a b c

ALGOL 68[edit]

BEGIN # find the characters that occur once only in each element of a list  #
# of stings #
OP UNIQUEINEACH = ( []STRING s )STRING:
IF INT required count = ( UPB s + 1 ) - LWB s;
required count < 1
THEN "" # the list is empty #
ELSE # non-empty list #
[ 0 : max abs char ]INT counts; # counts of used characters #
[ 0 : max abs char ]INT all;
FOR i FROM LWB all TO UPB all DO all[ i ] := 0 OD;
# count the occurances of the characters in the elements of s #
FOR i FROM LWB s TO UPB s DO
FOR i FROM LWB counts TO UPB counts DO counts[ i ] := 0 OD;
FOR j FROM LWB s[ i ] TO UPB s[ i ] DO
counts[ ABS s[ i ][ j ] ] +:= 1
OD;
FOR j FROM LWB counts TO UPB counts DO
# the character is unique in this string #
IF counts[ j ] = 1 THEN all[ j ] +:= 1 FI
OD
OD;
# construct a string of the characters that occur only once #
# in each string #
STRING result := "";
FOR i FROM LWB all TO UPB all DO
IF all[ i ] = required count THEN result +:= REPR i FI
OD;
result
FI; # UNIQUEINEACH #
# task test case #
STRING unique = UNIQUEINEACH []STRING( "1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz" );
FOR c FROM LWB unique TO UPB unique DO print( ( " ", unique[ c ] ) ) OD
END
Output:
 1 2 3 a b c

AppleScript[edit]

AppleScriptObjC[edit]

The filtering here is case sensitive, the sorting dependent on locale.

use AppleScript version "2.4" -- OS X 10.10 (Yosemite) or later
use framework "Foundation"
 
on uniqueCharactersInEachString(listOfstrings)
set astid to AppleScript's text item delimiters
set AppleScript's text item delimiters to ""
set countedSet to current application's class "NSCountedSet"'s setWithArray:(characters of (listOfstrings as text))
set AppleScript's text item delimiters to astid
set mutableSet to current application's class "NSMutableSet"'s setWithSet:(countedSet)
repeat with thisString in listOfstrings
tell mutableSet to intersectSet:(current application's class "NSSet"'s setWithArray:(thisString's characters))
tell countedSet to minusSet:(mutableSet)
end repeat
tell mutableSet to minusSet:(countedSet)
set sortDescriptor to current application's class "NSSortDescriptor"'s sortDescriptorWithKey:("self") ¬
ascending:(true) selector:("localizedStandardCompare:")
 
return (mutableSet's sortedArrayUsingDescriptors:({sortDescriptor})) as list
end uniqueCharactersInEachString
 
uniqueCharactersInEachString({"1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"})
Output:
{"1", "2", "3", "a", "b", "c"}

Core language only[edit]

This can be case-insensitive if required. (Just leave out the 'considering case' statement round the call to the handler). The requirement for AppleScript 2.3.1 is only for the 'use' command which loads the "Heap Sort" script. If "Heap Sort"'s instead loaded with the older 'load script' command or copied into the code, this will work on systems as far back as Mac OS X 10.5 (Leopard) and possibly earlier. Same output as above.

use AppleScript version "2.3.1" -- OS X 10.9 (Mavericks) or later
use sorter : script "Heap Sort" -- <https://www.rosettacode.org/wiki/Sorting_algorithms/Heapsort#AppleScript>
 
on uniqueCharactersInEachString(listOfStrings)
script o
property allCharacters : {}
property uniques : {}
 
on isInAllStrings(thisCharacter)
repeat with thisString in listOfStrings
if (thisCharacter is not in thisString) then return false
end repeat
 
return true
end isInAllStrings
end script
 
set astid to AppleScript's text item delimiters
set AppleScript's text item delimiters to ""
set o's allCharacters to text items of (listOfStrings as text)
set AppleScript's text item delimiters to astid
 
set characterCount to (count o's allCharacters)
tell sorter to sort(o's allCharacters, 1, characterCount)
 
set i to 1
set stringCount to (count listOfStrings)
set currentCharacter to beginning of o's allCharacters
repeat with j from 2 to characterCount
set thisCharacter to item j of o's allCharacters
if (thisCharacter is not currentCharacter) then
if ((j - i = stringCount) and (o's isInAllStrings(currentCharacter))) then ¬
set end of o's uniques to currentCharacter
set i to j
set currentCharacter to thisCharacter
end if
end repeat
if ((j + 1 - i = stringCount) and (o's isInAllStrings(currentCharacter))) then ¬
set end of o's uniques to currentCharacter
 
return o's uniques
end uniqueCharactersInEachString
 
considering case
uniqueCharactersInEachString({"1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"})
end considering

Arturo[edit]

arr: ["1a3c52debeffd" "2b6178c97a938stf" "3ycxdb1fgxa2yz"]
uniques: split first arr
 
loop arr 'str [
uniques: intersection uniques
select split str 'x ->
1 = size match str x
]
 
print sort uniques
Output:
1 2 3 a b c

AWK[edit]

 
# syntax: GAWK -f UNIQUE_CHARACTERS_IN_EACH_STRING.AWK
#
# sorting:
# PROCINFO["sorted_in"] is used by GAWK
# SORTTYPE is used by Thompson Automation's TAWK
#
BEGIN {
PROCINFO["sorted_in"] = "@ind_str_asc" ; SORTTYPE = 1
n = split("1a3c52debeffd,2b6178c97a938stf,3ycxdb1fgxa2yz",arr1,",")
for (i=1; i<=n; i++) {
str = arr1[i]
printf("%s\n",str)
total_c += leng = length(str)
for (j=1; j<=leng; j++) {
arr2[substr(str,j,1)][i]++
}
}
for (c in arr2) {
flag = 0
for (i=1; i<=n; i++) {
if (arr2[c][i] != 1) {
flag = 1
}
}
if (flag == 0) {
rec = sprintf("%s%s",rec,c)
}
}
printf("%d strings, %d characters, %d different, %d unique: %s\n",n,total_c,length(arr2),length(rec),rec)
exit(0)
}
 
Output:
1a3c52debeffd
2b6178c97a938stf
3ycxdb1fgxa2yz
3 strings, 43 characters, 20 different, 6 unique: 123abc

F#[edit]

 
// Unique characters in each string: Nigel Galloway. May 12th., 2021
let fN g=g|>Seq.countBy id|>Seq.filter(fun(_,n)->n=1)
let fUc g=g|>List.map fN|>Seq.concat|>Seq.countBy id|>Seq.filter(fun(_,n)->n=List.length g)|>Seq.map(fun((n,_),_)->n)|>Seq.sort
printfn "%s" (fUc ["1a3c52debeffd";"2b6178c97a938stf";"3ycxdb1fgxa2yz"]|>Array.ofSeq|>System.String)
 
Output:
123abc

Factor[edit]

Works with: Factor version 0.99 2021-02-05
USING: io kernel sequences.interleaved sets sorting ;
 
{ "1a3c52debeffd" "2b6178c97a938sf" "3ycxdb1fgxa2yz" }
[ intersect-all ] [ [ duplicates ] gather without ] bi
natural-sort CHAR: space <interleaved> print
 
! How it works:
! intersect-all obtain elements present in every string -> "1a3c2bf"
! [ duplicates ] gather obtain elements that repeat within a single string -> "efd798xy"
! without from the first string, remove elements that are in the second -> "1a3c2b"
Output:
1 2 3 a b c

Go[edit]

package main
 
import (
"fmt"
"sort"
)
 
func main() {
strings := []string{"1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"}
u := make(map[rune]int)
for _, s := range strings {
m := make(map[rune]int)
for _, c := range s {
m[c]++
}
for k, v := range m {
if v == 1 {
u[k]++
}
}
}
var chars []rune
for k, v := range u {
if v == 3 {
chars = append(chars, k)
}
}
sort.Slice(chars, func(i, j int) bool { return chars[i] < chars[j] })
fmt.Println(string(chars))
}
Output:
123abc

Haskell[edit]

import qualified Data.Map.Strict as M
import Data.Maybe (fromJust)
import qualified Data.Set as S
 
onceInEach :: [String] -> String
onceInEach [] = []
onceInEach ws@(x : xs) =
S.elems $
S.filter
((wordCount ==) . fromJust . flip M.lookup freq)
( foldr
(S.intersection . S.fromList)
(S.fromList x)
xs
)
where
wordCount = length ws
freq =
foldr
(flip (M.insertWith (+)) 1)
M.empty
(concat ws)
 
--------------------------- TEST -------------------------
main :: IO ()
main =
(putStrLn . onceInEach)
[ "1a3c52debeffd",
"2b6178c97a938stf",
"3ycxdb1fgxa2yz"
]
Output:
123abc

JavaScript[edit]

(() => {
"use strict";
 
// --- CHARACTERS SEEN EXACTLY ONCE IN EACH STRING ---
 
// onceInEach :: [String] -> String
const onceInEach = ws =>
// Characters which occur exactly once
// in each word in a given list.
0 < ws.length ? (() => {
const
charFreqs = charCounts(ws.join("")),
charSet = s => new Set([...s]),
wordCount = ws.length;
 
return sort([
...foldr(
compose(intersect, charSet)
)(
charSet(ws[0])
)(
ws.slice(1)
)
]
.filter(c => wordCount === charFreqs[c])
).join("");
})() : "";
 
 
// ---------------------- TEST -----------------------
const main = () =>
onceInEach([
"1a3c52debeffd",
"2b6178c97a938stf",
"3ycxdb1fgxa2yz"
]);
 
// --------------------- GENERIC ---------------------
 
// charCounts :: String -> Dict Char Int
const charCounts = cs =>
// Dictionary of chars, with the
// frequency of each in cs.
[...cs].reduce(
(a, c) => Object.assign(
a, {
[c]: 1 + (a[c] || 0)
}
), {}
);
 
 
// compose (<<<) :: (b -> c) -> (a -> b) -> a -> c
const compose = (...fs) =>
// A function defined by the right-to-left
// composition of all the functions in fs.
fs.reduce(
(f, g) => x => f(g(x)),
x => x
);
 
 
// foldr :: (a -> b -> b) -> b -> [a] -> b
const foldr = f =>
// Note that that the signature of foldr differs
// from that of foldl - the positions of
// current value and accumulator in f are reversed
acc => xs => [...xs].reduceRight(
(a, x) => f(x)(a),
acc
);
 
 
// intersect :: Set -> Set -> Set
const intersect = a =>
// The intersection of two sets.
b => new Set([...a].filter(i => b.has(i)));
 
 
// sort :: Ord a => [a] -> [a]
const sort = xs =>
// An A-Z sorted copy of xs.
[...xs].slice().sort(
(a, b) => a < b ? -1 : (a > b ? 1 : 0)
);
 
 
// MAIN ---
return main();
})();
Output:
123abc

jq[edit]

Works with: jq

Works with gojq, the Go implementation of jq

Helper functions

# bag of words
def bow(stream):
reduce stream as $word ({}; .[($word|tostring)] += 1);
 
# input: an array of arrays that represent sets
# output: a stream of the items in all the input arrays
def intersections:
 
# intersection of (two) sets
# If a and b are sorted lists, and if all the elements respectively of a and b are distinct,
# then [a,b] | ios will emit the stream of elements in the set-intersection of a and b.
def ios:
.[0] as $a | .[1] as $b
| if 0 == ($a|length) or 0 == ($b|length) then empty
elif $a[0] == $b[0] then $a[0], ([$a[1:], $b[1:]] | ios)
elif $a[0] < $b[0] then [$a[1:], $b] | ios
else [$a, $b[1:]] | ios
end;
 
if length == 0 then empty
elif length == 1 then .[0][]
elif length == 2 then ios
elif (.[0]|length) == 0 then empty
else [.[0], [ .[1:] | intersections]] | ios
end;

The task

def once_in_each_string:
# convert each string to an array of the constituent characters
map((explode | map([.]|implode)))
# identify the singleton characters in each string; `keys` sorts the keys
| map( bow(.[]) | with_entries(select(.value==1)) | keys)
| intersections ;
 
["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
| [once_in_each_string]
 
Output:
["1","2","3","a","b","c"]

Julia[edit]

list = ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
 
onceineachstring(list) = filter(c -> all(w -> count(x -> x == c, w) == 1, list), (sort ∘ unique ∘ prod)(list))
 
println(onceineachstring(list))
 
Output:

['1', '2', '3', 'a', 'b', 'c']

Nim[edit]

import strutils,  tables
 
var result = AllChars
for str in ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]:
let charCount = str.toCountTable # Mapping char -> count.
var uniqueChars: set[char] # Set of unique chars.
for ch, count in charCount.pairs:
if count == 1: uniqueChars.incl ch
result = result * uniqueChars # Intersection.
 
echo result
Output:
{'1', '2', '3', 'a', 'b', 'c'}

Perl[edit]

#!/usr/bin/perl
 
use strict; # https://rosettacode.org/wiki/Unique_characters_in_each_string
use warnings;
 
my @strings = ("1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz");
my $chars = join "\n", @strings;
print "@{[ sort grep
$chars !~ /$_.*$_/ && # the 'only once in each string' test
@strings == $chars =~ s/$_//g, # the 'in every string' test
$chars =~ /./g ]}\n"
;
Output:
1 2 3 a b c

Phix[edit]

include builtins\sets.e

function once(integer ch, i, string s)
    integer l = length(s)
    return (i=1 or ch!=s[i-1])
       and (i=l or ch!=s[i+1])
end function

sequence set = {"1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"},
         res = intersection(apply(true,filter,{apply(set,sort),once}))
printf(1,"found %d unique common characters: %s\n",{length(res),res})
Output:
found 6 unique common characters: 123abc

PicoLisp[edit]

(de acc (V K N)
(if (assoc K (val V))
(inc (nth (cadr @) N))
(push V (list K (list 1 0 0))) ) )
(de un (Lst)
(let (Len (length Lst) D)
(for (I . Lst) (mapcar chop Lst)
(for L Lst
(acc 'D L I) ) )
(mapcar
car
(by
car
sort
(filter '((L) (fully =1 (cadr L))) D) ) ) ) )
(println
(un
(quote
"1a3c52debeffd"
"2b6178c97a938stf"
"3ycxdb1fgxa2yz" ) ) )
Output:
("1" "2" "3" "a" "b" "c")

Python[edit]

LIST = ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
 
print(sorted([ch for ch in set([c for c in ''.join(LIST)]) if all(w.count(ch) == 1 for w in LIST)]))
 
Output:
['1', '2', '3', 'a', 'b', 'c']

Raku[edit]

my $strings = <1a3c52debeffd 2b6178c97a938stf 3ycxdb1fgxa2yz>;
 
put sort keys [] $strings.map: *.comb.Bag.grep: *.value == 1
Output:
1 2 3 a b c

REXX[edit]

This REXX program doesn't assume ASCII (or any other) order.   This example was run on an ASCII machine.

If this REXX program is run on an  ASCII  machine,   it will use the   ASCII   order of characters,   in this case,
decimal digits,   uppercase Latin letters,   and then lowercase Latin letters,   with other characters interspersed.

On an  EBCDIC  machine,   the order would be lowercase Latin letters,   uppercase Latin letters,   and then the
decimal digits,   with other characters interspersed.

On an  EBCDIC  machine,   the lowercase letters and the uppercase letters   aren't   contiguous.

/*REXX pgm finds and shows characters that are  unique in each string  and  once only.  */
parse arg $ /*obtain optional arguments from the CL*/
if $='' | $="," then $= '1a3c52debeffd' "2b6178c97a938stf" '3ycxdb1fgxa2yz'
if $='' then do; say "***error*** no lists were specified."; exit 13; end
#= words($); $$= /*#: # words in $; $$: $ with no blanks*/
do i=1 for #;  !.i= word($, i) /*for speed, build a list of words in $*/
$$= $$ ||  !.i /*build a list of all the strings. */
end /*i*/
@= /*will be a list of all unique chars. */
do j=0 for 256; x= d2c(j) /*process all the possible characters. */
if pos(x, $$)==0 then iterate /*Char not found in any string in $ ? */
do k=1 for #; _= pos(x, !.k) /*examine each string in the $ list. */
if _==0 then iterate j /*Character not found? Then skip it. */
if pos(x, !.k, _+1)>0 then iterate j /* " is a dup? " " " */
end /*k*/
@= @ x /*append a character, append it to list*/
end /*j*/ /*stick a fork in it, we're all done. */
 
@@= space(@, 0); L= length(@@) /*elided superfluous blanks; get length*/
if @@=='' then @= " (none)" /*if none were found, pretty up message*/
if L==0 then L= "no" /*do the same thing for the # of chars.*/
say 'unique characters are: ' @ /*display the unique characters found. */
say
say 'Found ' L " unique characters." /*display the # of unique chars found. */
output   when using the default input:
unique characters are:   1 2 3 a b c

Found  6  unique characters.

Ring[edit]

 
see "working..." + nl
see "Unique characters in each string are:" + nl
row = 0
str = ""
cList = []
uniqueChars = ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
lenChars = len(uniqueChars)
 
for n = 1 to lenChars
str = str + uniqueChars[n]
next
 
for n = 1 to len(str)
flag = 1
for m = 1 to lenChars
cnt = count(uniqueChars[m],str[n])
if cnt != 1
flag = 0
exit
ok
next
if flag = 1
ind = find(cList,str[n])
if ind = 0
add(cList,str[n])
ok
ok
next
cList = sort(cList)
for n = 1 to len(cList)
row = row + 1
see "" + cList[n] + " "
next
see nl
 
see "Found " + row + " unique characters in each string" + nl
see "done..." + nl
 
func count(cString,dString)
sum = 0
while substr(cString,dString) > 0
sum++
cString = substr(cString,substr(cString,dString)+len(string(sum)))
end
return sum
 
Output:
working...
Unique characters in each string are:
1 2 3 a b c 
Found 6 unique characters in each string
done...

Ruby[edit]

arr = ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
 
uniqs_in_str = arr.map{|str| str.chars.tally.filter_map{|char, count| char if count == 1} }
puts uniqs_in_str.inject(&:intersection).sort.join(" ")
 
Output:
1 2 3 a b c

Wren[edit]

Library: Wren-seq
Library: Wren-sort
import "/seq" for Lst
import "/sort" for Sort
 
var strings = ["1a3c52debeffd", "2b6178c97a938stf", "3ycxdb1fgxa2yz"]
var uniqueChars = []
for (s in strings) {
var u = Lst.individuals(s.toList).where { |l| l[1] == 1 }.map { |l| l[0] }
uniqueChars.addAll(u)
}
var n = strings.count
uniqueChars = Lst.individuals(uniqueChars).where { |l| l[1] == n }.map { |l| l[0] }.toList
Sort.insertion(uniqueChars)
System.print("Found %(uniqueChars.count) unique character(s) common to each string, namely:")
System.print(uniqueChars.join(" "))
Output:
Found 6 unique character(s) common to each string, namely:
1 2 3 a b c