preg_replace_callback - PHP code example

The php Function Preg_Replace_Callback

The php function preg_replace_callback is a powerful tool that goes beyond standard regular expression find/replace functionality. It allows developers to use custom callback functions for each matched string, making it possible to easily implement more complex templating logic. This article provides a clear explanation of this functionality together with carefully crafted examples that illustrate some of its most common uses.

Preg_replace_callback is the newest member of the PHP family of regular expression functions and offers a great deal of versatility for developers that need to modify strings based on matching patterns. Its flexibility makes it an indispensable tool when developing templating code.

Like its sister function, preg_replace, it accepts an array of data keys as the subject and an argument that specifies the pattern to search for and the replacement string. If the pattern contains delimiters such as spaces or backslashes that need to be escaped, the preg_replace_callback() function also escapes them for you. However, the time it takes to process a large array will increase linearly as the number of data keys increases. This is a result of the fact that all methods for replacing placeholders in a template (including the str_replace method) work on an O(n) algorithm and need to check each data key for matching patterns.

preg_replace_callback example

$value = substr($value, -$attr['ellipsis']);
            }

            $value = $this->style('default', $prefix).$this->style($style, $value);

            goto href;
        }

        $map = static::$controlCharsMap;
        $startCchr = $this->colors ? "\033[m\033[{$this->styles['default']}m" : '';
        $endCchr = $this->colors ? "\033[m\033[{$this->styles[$style]}m" : '';
        $value = preg_replace_callback(static::$controlCharsRx, function D$c) use ($map, $startCchr, $endCchr) {
            $s = $startCchr;
            $c = $c[$i = 0];
            do {
                $s .= $map[$c[$i]] ?? sprintf('\x%02X', \ord($c[$i]));
            } while (isset($c[++$i]));

            return $s.$endCchr;
        }, $value, -1, $cchrCount);

        if (!($attr['binary'] ?? false)) {
            $value = preg_replace_callback(static::$unicodeCharsRx, function D$c) use (&$cchrCount, $startCchr, $endCchr) {

function filter_block_content( $text, $allowed_html = 'post', $allowed_protocols = array() ) {
 $result = '';

 if ( str_contains( $text, '' ) ) {
 $text = preg_replace_callback( '%%', '_filter_block_content_callback', $text );
 }

 $blocks = parse_blocks( $text );
 foreach ( $blocks as $block ) {
 $block = filter_block_kses( $block, $allowed_html, $allowed_protocols );
 $result .= serialize_block( $block );
 }

 return $result;
}

private function fileExcerpt(string $file, int $line, int $srcContext = 3): string
 {
 if (is_file($file) && is_readable($file)) {
 // highlight_file could throw warnings // see https://bugs.php.net/25725 $code = @highlight_file($file, true);
 if (\PHP_VERSION_ID >= 80300) {
 // remove main pre/code tags $code = preg_replace('#^<pre.*?>\s*<code.*?>(.*)</code>\s*</pre>#s', '\\1', $code);
 // split multiline code tags $code = preg_replace_callback('#<code ([^>]++)>((?:[^<]*+\\n)++[^<]*+)</code>#', fn ($m) => "<code $m[1]>".str_replace("\n", "</code>\n<code $m[1]>", $m[2]).'</code>', $code);
 // Convert spaces to html entities to preserve indentation when rendered $code = str_replace(' ', ' ', $code);
 $content = explode("\n", $code);
 } else {
 // remove main code/span tags $code = preg_replace('#^<code.*?>\s*<span.*?>(.*)\s*</code>#s', '\\1', $code);
 // split multiline spans $code = preg_replace_callback('#]++)>((?:[^<]*+ )++[^<]*+)#', fn ($m) => "".str_replace(' ', " ", $m[2]).'', $code);
 $content = explode(' ', $code);
 }

// Ensure this context is only added once if shortcodes are nested. $has_filter = has_filter( 'wp_get_attachment_image_context', '_filter_do_shortcode_context' );
 $filter_added = false;

 if ( ! $has_filter ) {
 $filter_added = add_filter( 'wp_get_attachment_image_context', '_filter_do_shortcode_context' );
 }

 $content = do_shortcodes_in_html_tags( $content, $ignore_html, $tagnames );

 $pattern = get_shortcode_regex( $tagnames );
 $content = preg_replace_callback( "/$pattern/", 'do_shortcode_tag', $content );

 // Always restore square braces so we don't break things like <!--[if IE ]>. $content = unescape_invalid_shortcodes( $content );

 // Only remove the filter if it was added in this scope. if ( $filter_added ) {
 remove_filter( 'wp_get_attachment_image_context', '_filter_do_shortcode_context' );
 }

 return $content;
}

$overwrite = true;
 }

 // Are we offsetting the binds? // If so, take care of them here in one // fell swoop. if (isset($options['offset']) && is_string($to)) {
 // Get a constant string to work with. $to = preg_replace('/(\$\d+)/', '$X', $to);

 for ($i = (int) $options['offset'] + 1; $i < (int) $options['offset'] + 7; $i++) {
 $to = preg_replace_callback(
 '/\$X/',
 static fn ($m) => '$' . $i,
 $to,
 1
 );
 }
 }

 $routeKey = $from;

 // Replace our regex pattern placeholders with the actual thing

$host = \defined('INTL_IDNA_VARIANT_UTS46') ? idn_to_ascii($host, \IDNA_DEFAULT | \IDNA_USE_STD3_RULES | \IDNA_CHECK_BIDI | \IDNA_CHECK_CONTEXTJ | \IDNA_NONTRANSITIONAL_TO_ASCII, \INTL_IDNA_VARIANT_UTS46) ?: strtolower($host) : strtolower($host);
            $host .= $port ? ':'.$port : '';
        }

        foreach (['user', 'pass', 'path', 'query', 'fragment'] as $part) {
            if (!isset($parts[$part])) {
                continue;
            }

            if (str_contains($parts[$part], '%')) {
                // https://tools.ietf.org/html/rfc3986#section-2.3                 $parts[$part] = preg_replace_callback('/%(?:2[DE]|3[0-9]|[46][1-9A-F]|5F|[57][0-9A]|7E)++/i', fn ($m) => rawurldecode($m[0]), $parts[$part]);
            }

            // https://tools.ietf.org/html/rfc3986#section-3.3             $parts[$part] = preg_replace_callback("#[^-A-Za-z0-9._~!$&/'()[\]*+,;=:@{}%]++#", fn ($m) => rawurlencode($m[0]), $parts[$part]);
        }

        return [
            'scheme' => $scheme,
            'authority' => null !== $host ? '//'.(isset($parts['user']) ? $parts['user'].(isset($parts['pass']) ? ':'.$parts['pass'] : '').'@' : '').$host : null,
            'path' => isset($parts['path'][0]) ? $parts['path'] : null,
            'query' => isset($parts['query']) ? '?'.$parts['query'] : null,

$rx = '{^(?';
 $code .= "\n {$state->mark} => ".self::export($rx);
 $startingMark = $state->mark;
 $state->mark += \strlen($rx);
 $state->regex = $rx;

 foreach ($perHost as [$hostRegex, $routes]) {
 if ($matchHost) {
 if ($hostRegex) {
 preg_match('#^.\^(.*)\$.[a-zA-Z]*$#', $hostRegex, $rx);
 $state->vars = [];
 $hostRegex = '(?i:'.preg_replace_callback('#\?P<([^>]++)>#', $state->getVars, $rx[1]).')\.';
 $state->hostVars = $state->vars;
 } else {
 $hostRegex = '(?:(?:[^./]*+\.)++)';
 $state->hostVars = [];
 }
 $state->mark += \strlen($rx = ($prev ? ')' : '')."|{$hostRegex}(?");
 $code .= "\n .".self::export($rx);
 $state->regex .= $rx;
 $prev = true;
 }

$key = $match[1];

            if (isset($resolving[$key])) {
                throw new ParameterCircularReferenceException(array_keys($resolving));
            }

            $resolving[$key] = true;

            return $this->resolved ? $this->get($key) : $this->resolveValue($this->get($key), $resolving);
        }

        return preg_replace_callback('/%%|%([^%\s]+)%/', function D$match) use ($resolving, $value) {
            // skip %%             if (!isset($match[1])) {
                return '%%';
            }

            $key = $match[1];
            if (isset($resolving[$key])) {
                throw new ParameterCircularReferenceException(array_keys($resolving));
            }

            $resolved = $this->get($key);

    public function escapeHtmlAttr(string $string)
    {
        $string = $this->toUtf8($string);
        if ($string === '' || ctype_digit($string)) {
            return $string;
        }

        $result = preg_replace_callback('/[^a-z0-9,\.\-_]/iSu', $this->htmlAttrMatcher, $string);
        return $this->fromUtf8($result);
    }

    /** * Escape a string for the Javascript context. This does not use json_encode(). An extended * set of characters are escaped beyond ECMAScript's rules for Javascript literal string * escaping in order to prevent misinterpretation of Javascript as HTML leading to the * injection of special characters and entities. The escaping used should be tolerant * of cases where HTML escaping was not applied on top of Javascript escaping correctly. * Backslash escaping is not used as it still leaves the escaped character as-is and so * is not useful in a HTML context. * * @return string */

$text = $this->messages[$matches[1]];
 } else {
 return $matches[0];
 }

 if (isset($matches[2])) {
 $text = sprintf('%'.$matches[2], $text);
 }

 return $text;
 };
 $line = preg_replace_callback($regex, $callback, $this->format);

 // gets string length for each sub line with multiline format $linesLength = array_map(fn ($subLine) => Helper::width(Helper::removeDecoration($this->output->getFormatter(), rtrim($subLine, "\r"))), explode("\n", $line));

 $linesWidth = max($linesLength);

 $terminalWidth = $this->terminal->getWidth();
 if ($linesWidth <= $terminalWidth) {
 return $line;
 }

    public function format(RequestInterface $request, ResponseInterface $response = null, \Throwable $error = null): string
    {
        $cache = [];

        /** @var string */
        return \preg_replace_callback(
            '/{\s*([A-Za-z_\-\.0-9]+)\s*}/',
            function Darray $matches) use ($request, $response, $error, &$cache) {
                if (isset($cache[$matches[1]])) {
                    return $cache[$matches[1]];
                }

                $result = '';
                switch ($matches[1]) {
                    case 'request':
                        $result = Psr7\Message::toString($request);
                        break;

/** * Filter html source * * @param string $source * * @return string|null */
 public function DfilterSource($source)
 {
 // To allow the return of a reference, we need to add an interim variable $source = preg_replace_callback('#<(a|form|iframe|link|img)[^<>]*(href|src|action)="([^"]*)".*>#Umsi', [$this, 'rewriteSrc'], $source);

 return $source;
 }

 /** * Rewrite source link * * @see \Shopware_Controllers_Backend_Newsletter::outputFilter * * @param array $src * * @throws Exception * @throws SmartyException * * @return string */

return $this->correctPluginName($vars);
 }

 /** * Changes the name to a camelcased combination of vendor and name * * @param array<string, string> $vars * @return array<string, string> */
 private function correctPluginName(array $vars): array
 {
 $camelCasedName = preg_replace_callback('/(-[a-z])/', function D$matches) {
 return strtoupper($matches[0][1]);
 }, $vars['name']);

 if (null === $camelCasedName) {
 throw new \RuntimeException('Failed to run preg_replace_callback: '.preg_last_error());
 }

 $vars['name'] = ucfirst($vars['vendor']) . ucfirst($camelCasedName);

 return $vars;
 }

$fieldValue = [];

        $Q = 'Q' === $scheme;

        foreach ($chars as $c) {
            if ('utf-8' !== $out && false === $c = self::iconv('utf-8', $out, $c)) {
                return false;
            }

            $o = $Q
                ? $c = preg_replace_callback(
                    '/[=_\?\x00-\x1F\x80-\xFF]/',
                    [__CLASS__, 'qpByteCallback'],
                    $c
                )
                : base64_encode($lineData.$c);

            if (isset($o[$lineBreak - $lineLength])) {
                if (!$Q) {
                    $lineData = base64_encode($lineData);
                }
                $fieldValue[] = $lineStart.$lineData.'?=';