TYPO3\CMS\Core\Utility\GeneralUtility::xml2arrayProcess()

Complexity

Conditions	20
Paths	1283

Size

Total Lines	100
Code Lines	67

Duplication

Lines	19
Ratio	19 %

Importance

Changes

0

<?php
    protected static function xml2arrayProcess($string, $NSprefix = '', $reportDocTag = false)
    {
        // Disables the functionality to allow external entities to be loaded when parsing the XML, must be kept
        $previousValueOfEntityLoader = libxml_disable_entity_loader(true);
        // Create parser:
        $parser = xml_parser_create();
        $vals = [];
        $index = [];
        xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
        xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 0);
        // Default output charset is UTF-8, only ASCII, ISO-8859-1 and UTF-8 are supported!!!
        $match = [];
        preg_match('/^[[:space:]]*<\\?xml[^>]*encoding[[:space:]]*=[[:space:]]*"([^"]*)"/', substr($string, 0, 200), $match);

It seems like substr($string, 0, 200) can also be of type false; however, parameter $subject of preg_match() does only seem to accept string, maybe add an additional type check?

        $theCharset = $match[1] ?: 'utf-8';
        // us-ascii / utf-8 / iso-8859-1
        xml_parser_set_option($parser, XML_OPTION_TARGET_ENCODING, $theCharset);
        // Parse content:
        xml_parse_into_struct($parser, $string, $vals, $index);
        libxml_disable_entity_loader($previousValueOfEntityLoader);
        // If error, return error message:
        if (xml_get_error_code($parser)) {
            return 'Line ' . xml_get_current_line_number($parser) . ': ' . xml_error_string(xml_get_error_code($parser));
        }
        xml_parser_free($parser);
        // Init vars:
        $stack = [[]];
        $stacktop = 0;
        $current = [];
        $tagName = '';
        $documentTag = '';
        // Traverse the parsed XML structure:
        foreach ($vals as $key => $val) {
            // First, process the tag-name (which is used in both cases, whether "complete" or "close")
            $tagName = $val['tag'];
            if (!$documentTag) {
                $documentTag = $tagName;
            }
            // Test for name space:
            $tagName = $NSprefix && substr($tagName, 0, strlen($NSprefix)) == $NSprefix ? substr($tagName, strlen($NSprefix)) : $tagName;
            // Test for numeric tag, encoded on the form "nXXX":
            $testNtag = substr($tagName, 1);

It seems like $tagName can also be of type false; however, parameter $string of substr() does only seem to accept string, maybe add an additional type check?

            // Closing tag.
            $tagName = $tagName[0] === 'n' && MathUtility::canBeInterpretedAsInteger($testNtag) ? (int)$testNtag : $tagName;
            // Test for alternative index value:
            if ((string)($val['attributes']['index'] ?? '') !== '') {
                $tagName = $val['attributes']['index'];
            }
            // Setting tag-values, manage stack:
            switch ($val['type']) {
                case 'open':
                    // If open tag it means there is an array stored in sub-elements. Therefore increase the stackpointer and reset the accumulation array:
                    // Setting blank place holder
                    $current[$tagName] = [];
                    $stack[$stacktop++] = $current;
                    $current = [];
                    break;
                case 'close':
                    // If the tag is "close" then it is an array which is closing and we decrease the stack pointer.
                    $oldCurrent = $current;
                    $current = $stack[--$stacktop];
                    // Going to the end of array to get placeholder key, key($current), and fill in array next:
                    end($current);
                    $current[key($current)] = $oldCurrent;
                    unset($oldCurrent);
                    break;
                case 'complete':
                    // If "complete", then it's a value. If the attribute "base64" is set, then decode the value, otherwise just set it.
                    if (!empty($val['attributes']['base64'])) {
                        $current[$tagName] = base64_decode($val['value']);
                    } else {
                        // Had to cast it as a string - otherwise it would be evaluate FALSE if tested with isset()!!
                        $current[$tagName] = (string)($val['value'] ?? '');
                        // Cast type:
                        switch ((string)($val['attributes']['type'] ?? '')) {
                            case 'integer':
                                $current[$tagName] = (int)$current[$tagName];
                                break;
                            case 'double':
                                $current[$tagName] = (double) $current[$tagName];
                                break;
                            case 'boolean':
                                $current[$tagName] = (bool)$current[$tagName];
                                break;
                            case 'NULL':
                                $current[$tagName] = null;
                                break;
                            case 'array':
                                // MUST be an empty array since it is processed as a value; Empty arrays would end up here because they would have no tags inside...
                                $current[$tagName] = [];
                                break;
                        }
                    }
                    break;
            }
        }
        if ($reportDocTag) {
            $current[$tagName]['_DOCUMENT_TAG'] = $documentTag;
        }
        // Finally return the content of the document tag.
        return $current[$tagName];
    }