Creating implementation for idiom 147 : Remove all non-ASCII characters

Idiom

# 147 Remove all non-ASCII characters

Created by

Lead paragraph

Create string t from string s, keeping only ASCII characters

New implementation

Language

Imports

Code

Documentation URL

Original attribution URL

Online runnable demo

Username

Be concise.

Be useful.

All contributions dictatorially edited by webmasters to match personal tastes.

Please do not paste any copyright violating material.

Please try to avoid dependencies to third-party libraries and frameworks.

Other implementations

function Only_ASCII (S : String) return String is
   subtype ASCII is Character range
      Character'Val (0) .. Character'Val (127);
   T    : String (S'Range);
   Last : Natural := T'First - 1;
begin
   for Char of S loop
      if Char in ASCII then
         Last := Last + 1;
         T (Last) := Char;
      end if;
   end loop;
   return T (T'First .. Last);
end Only_ASCII;

(def t (clojure.string/replace s #"[^\x00-\x7F]" ""))

Demo
Doc

 copy_if(begin(src), end(src), back_inserter(dest),
         [](const auto c) { return static_cast<unsigned char>(c) <= 0x7F; });

Demo

string t = Regex.Replace(s, @"[^\u0000-\u007F]+", string.Empty);

Doc
Origin

import std.array;
import std.algorithm.iteration;
import std.ascii;

auto t = s.filter!(a => a.isASCII).array;

var t = '';
for(var c in s.runes) {
  if(c < 128){
    t = t + String.fromCharCode(c);
  }
}

t = for <<c <- s>>, c in 0..127, into: "", do: <<c>>

t = 
  s 
  |> String.to_charlist()
  |> Enum.filter(&(&1 in 0..127))
  |> List.to_string

n = 0
do i=1,len(s)
   if (iachar(s(i:i)) <= 127) n = n + 1
end do
allocate (character(len=n) :: t)
j = 0
do i=1,len(s)
   if (iachar(s(i:i)) <= 127) then
      j = j + 1
      t(j:j) = s(i:i)
   end if
end do

import (
	"fmt"
	"strings"
	"unicode"
)

t := strings.Map(func(r rune) rune {
	if r > unicode.MaxASCII {
		return -1
	}
	return r
}, s)

Demo

import "regexp"

re := regexp.MustCompile("[[:^ascii:]]")
t := re.ReplaceAllLiteralString(s, "")

Demo
Doc

import Data.Char

f = filter isAscii
t = f s

import Data.Char

t = filter isAscii s

const t = s.replace(/[^\x00-\x7f]/gu, '')

const t = [...s].filter(c => c.charCodeAt(0) <= 0x7f).join('')

import static java.lang.String.valueOf;
import static java.util.stream.Collectors.joining;

String t = s.chars()
    .filter(c -> c < 0x80)
    .mapToObj(x -> valueOf((char) x))
    .collect(joining());

String t = "";
char c;
int i, n = s.length();
for (i = 0; i < n; ++i)
    if ((c = s.charAt(i)) < 0x80)
        t = t + c;

String t = s.replaceAll("[^\\x00-\\x7F]", "");

Origin

(remove-if-not (lambda (i) (<= 0 i 127))
               s
               :key #'char-code)

$t = preg_replace('/[^[:ascii:]]/', '', $s);

var
  i: integer;
begin
  t := '';
  for i := 1 to length(s) do
    if s[i] < #128 then t := t + s[i];
end.

uses RegExpr;

var
  s,t: string;
begin
  t := ReplaceRegExpr('[^\u0000-\u007F]+', s, '', False);
end.

($t = $s) =~ s/[^\x00-\x7f]+//g;

use utf8;
use Encode qw( encode decode );

$t = decode('ascii', encode('ascii', $s, sub { return '' } ) );

Demo
Doc

import re

t = re.sub('[^\u0000-\u007f]', '',  s)

Demo

t = s.encode("ascii", "ignore").decode()

Demo

f = lambda x: ord(x) < 0x80
t = ''.join(filter(f, s))

from re import sub

t = sub(r'[^\x00-\x7f]', '', s)

from re import sub

t = sub(r'[^\0-\176]', '', s)

t = s.gsub(/[[:^ascii:]]/, "")

Demo

t = s.gsub(/[^[:ascii:]]/, "")

Demo

let t = s.chars().filter(|c| c.is_ascii()).collect::<String>();

Demo
Doc

let t = s.replace(|c: char| !c.is_ascii(), "");

Demo
Doc

t := s select: [:character | character isAscii].

Preview