Automattic\WooCommerce\EmailEditor\Engine\Renderer

Html2Text::convert │ public static │ WC 1.0

Converts HTML into plain text format

Method of the class: Html2Text{}

No Hooks.

Returns

String. The HTML converted to text.

Usage

$result = Html2Text::convert( $html, $options ): string;

$html(string) (required)

The input HTML.

$options

.
Default: array()

Html2Text::convert() Html2Text::convert code ^{WC 10.7.0}

public static function convert( string $html, $options = array() ): string {

	if ( false === $options || true === $options ) {
		// Using old style (< 1.0) of passing in options.
		$options = array( 'ignore_errors' => $options );
	}

	$options = array_merge( static::default_options(), $options );

	// Check all options are valid.
	foreach ( array_keys( $options ) as $key ) {
		if ( ! in_array( $key, array_keys( static::default_options() ), true ) ) {
			// Log invalid option for debugging purposes without exposing in exception.
			// phpcs:ignore WordPress.PHP.DevelopmentFunctions.error_log_error_log -- Security: Logging sensitive data separately from user-facing exception messages.
			error_log( 'Html2Text: Invalid option provided: ' . htmlspecialchars( (string) $key, ENT_QUOTES, 'UTF-8' ) . '. Valid options are: ' . htmlspecialchars( implode( ',', array_keys( static::default_options() ) ), ENT_QUOTES, 'UTF-8' ) );
			// Throw generic error message to avoid exposing user input.
			throw new \InvalidArgumentException( 'Invalid option provided for html2text conversion.' );
		}
	}

	$is_office_document = self::is_office_document( $html );

	if ( $is_office_document ) {
		// Remove office namespace.
		$html = str_replace( array( '<o:p>', '</o:p>' ), '', $html );
	}

	$html = self::fix_newlines( $html );

	// Use mb_convert_encoding for legacy versions of php.
	if ( PHP_MAJOR_VERSION * 10 + PHP_MINOR_VERSION < 81 && mb_detect_encoding( $html, 'UTF-8', true ) ) {
		$converted = mb_convert_encoding( $html, 'HTML-ENTITIES', 'UTF-8' );
		$html      = false !== $converted ? $converted : $html;
	}

	// Ensure $html is always a string before passing to get_document.
	if ( ! is_string( $html ) ) {
		$html = (string) $html;
	}

	$doc = self::get_document( $html, $options );

	$output = self::iterate_over_node( $doc, null, false, $is_office_document, $options );

	// Process output for whitespace/newlines.
	$output = self::process_whitespace_newlines( $output );

	return $output;
}