PHP code example of wp-php-toolkit / encoding

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

wp-php-toolkit / encoding example snippets

function WordPress\Encoding\wp_is_valid_utf8;

$samples = array(
	'ASCII'          => 'just a test',
	'UTF-8 pencil'   => "\xE2\x9C\x8F",
	'latin-1 byte'   => "B\xFCch",
	'overlong slash' => "\xC1\xBF",
	'surrogate half' => "\xED\xB0\x80",
);

foreach ( $samples as $label => $bytes ) {
	echo sprintf( "%-14s %s\n", $label . ':', wp_is_valid_utf8( $bytes ) ? 'valid' : 'invalid' );
}

function WordPress\Encoding\wp_scrub_utf8;

$broken = "the byte \xC0 should not be here.";
echo wp_scrub_utf8( $broken ) . "\n";

echo wp_scrub_utf8( ".\xE2\x8C\xE2\x8C." ) . "\n";

function WordPress\Encoding\wp_has_noncharacters;

$samples = array(
	'normal text' => 'normal text',
	'U+FFFE'      => "oops \u{FFFE}",
	'U+FDD0'      => "hi \u{FDD0} bye",
);

foreach ( $samples as $label => $text ) {
	echo sprintf( "%-12s %s\n", $label . ':', wp_has_noncharacters( $text ) ? 'reject' : 'ok' );
}

function WordPress\Encoding\wp_is_valid_utf8;
use function WordPress\Encoding\wp_scrub_utf8;
use function WordPress\Encoding\wp_has_noncharacters;

$inputs = array(
	'good'      => 'Café',
	'latin1'    => "caf\xE9",
	'overlong'  => "x\xC1\xBFy",
	'noncharac' => "hi \u{FFFE} there",
);

foreach ( $inputs as $label => $bytes ) {
	$valid    = wp_is_valid_utf8( $bytes );
	$cleaned  = wp_scrub_utf8( $bytes );
	$weird    = wp_has_noncharacters( $cleaned );
	echo sprintf( "%-10s valid=%s noncharacter=%s -> %s\n", $label, $valid ? 'Y' : 'N', $weird ? 'Y' : 'N', $cleaned );
}

function WordPress\Encoding\wp_is_valid_utf8;
use function WordPress\Encoding\wp_scrub_utf8;

$rows = array(
	1 => 'Plain ASCII',
	2 => 'Café',
	3 => "caf\xE9",
	4 => "weird \xC0 byte",
);

foreach ( $rows as $id => $value ) {
	if ( wp_is_valid_utf8( $value ) ) {
		echo "#$id ok: $value\n";
		continue;
	}
	$converted = @iconv( 'ISO-8859-1', 'UTF-8', $value );
	if ( false !== $converted && wp_is_valid_utf8( $converted ) ) {
		echo "#$id recovered as latin1: $converted\n";
	} else {
		echo "#$id unrecoverable, scrubbing: " . wp_scrub_utf8( $value ) . "\n";
	}
}