Unicode and byte notation in various places and programming languages

unicode-and-byte-notation.md

Unicode and byte notation

Letter: A
Code points: U+0041
UTF-8 bytes: 41
UTF-16BE bytes: 00 41

Pound sign: £
Code points: U+00A3
UTF-8 bytes: C2 A3
UTF-16BE bytes: 00 A3

Ball emoji: ⚽
Code points: U+26BD
UTF-8 bytes: E2 9A BD
UTF-16BE bytes: 26 BD

Brazil flag emoji: 🇧🇷
Code points: U+1F1E7 U+1F1F7
UTF-8 bytes: F0 9F 87 A7 F0 9F 87 B7
UTF-16BE bytes: D8 3C DD E7 D8 3C DD F7

HTML

<!-- Directly -->
<p>Letter: A</p>
<p>Pound: £</p>
<p>Ball: ⚽</p>
<p>Brazil: 🇧🇷</p>

<!-- Code point to code point (base 10) -->
<p>Letter: &#65;</p>
<p>Pound: &#163;</p>
<p>Ball: &#9917;</p>
<p>Brazil: &#127463;&#127479;</p>

<!-- Code point to code point (base 16) -->
<p>Letter: &#x41;</p>
<p>Pound: &#xA3;</p>
<p>Ball: &#x26BD;</p>
<p>Brazil: &#x1F1E7;&#x1F1F7;</p>

<!-- Alias (only a few code points) -->
<p>Pound: &pound;</p>

CSS

/* Directly */
#letter::after {
    content: 'A';
}

#pound::after {
    content: '£';
}

#ball::after {
    content: '⚽';
}

#brazil::after {
    content: '🇧🇷';
}

/* Code point to code point */
#letter::after {
    content: '\41';
}

#pound::after {
    content: '\A3';
}

#ball::after {
    content: '\26BD';
}

#brazil::after {
    content: '\1F1E7\1F1F7';
}

URL

# Byte to byte (UTF-8)
https://example.com/?letter=A
https://example.com/?letter=%41 # <-- No need to escape the "A" to "%41"
https://example.com/?pound=%C2%A3
https://example.com/?ball=%E2%9A%BD
https://example.com/?brazil=%F0%9F%87%A7%F0%9F%87%B7

PHP

<?php
// Directly
$letter = 'A';
$pound = '£';
$ball = '⚽';
$brazil = '🇧🇷';

// Byte to byte (UTF-8)
$letter = "\x41"; // Or: chr(0x41);
$pound = "\xC2\xA3"; // Or: chr(0xC2) . chr(0xA3);
$ball = "\xE2\x9A\xBD"; // Or: chr(0xE2) . chr(0x9A) . chr(0xBD);
$brazil = "\xF0\x9F\x87\xA7\xF0\x9F\x87\xB7"; // Or: chr(0xF0) . chr(0x9F) ...

// Code point to code point
$letter = "\u{0041}"; // Or: mb_chr(0x41);
$pound = "\u{00A3}"; // Or: mb_chr(0xA3);
$ball = "\u{26BD}"; // Or: mb_chr(0x26BD);
$brazil = "\u{1F1E7}\u{1F1F7}"; // Or: mb_chr(0x1F1E7) . mb_chr(0x1F1F7);

Javascript

// Directly
let letter = 'A';
let pound = '£';
let ball = '⚽';
let brazil = '🇧🇷';

// Byte to byte (UTF-16BE)
let letter = '\u0041';
let pound = '\u00A3';
let ball = '\u26BD';
let brazil = '\uD83C\uDDE7\uD83C\uDDF7';

Python

# Directly
letter = 'A'
pound = '£'
ball = '⚽'
brazil = '🇧🇷'

# Byte to byte (UTF-8)
letter = b"\x41".decode('utf-8')
pound = b"\xC2\xA3".decode('utf-8')
ball = b"\xE2\x9A\xBD".decode('utf-8')
brazil = b"\xF0\x9F\x87\xA7\xF0\x9F\x87\xB7".decode('utf-8')

# Code point to code point
letter = "\u0041"
pound = "\u00A3"
ball = "\u26BD"
brazil = "\U0001F1E7\U0001F1F7"

Bash

# Directly
letter='A'
pound='£'
ball='⚽'
brazil='🇧🇷'

# Byte to byte (UTF-8)
letter=$'\x41'
pound=$'\xC2\xA3'
ball=$'\xE2\x9A\xBD'
brazil=$'\xF0\x9F\x87\xA7\xF0\x9F\x87\xB7'

# Code point to code point
letter=$'\u0041'
pound=$'\u00A3'
ball=$'\u26BD'
brazil=$'\U0001F1E7\U0001F1F7'