XoopsModules\Publisher\Common\SysUtility::truncateHtml()

Complexity

Conditions	19
Paths	194

Size

Total Lines	95
Code Lines	47

Duplication

Lines	0
Ratio	0 %

Importance

Changes	3
Bugs	0	Features	0

<?php declare(strict_types=1);
    public static function truncateHtml(
        string $text,
        ?int $length = 100,
        string $ending = '...',
        bool $exact = false,
        bool $considerHtml = true
    ): string {
        $openTags = [];
        if ($considerHtml) {
            // if the plain text is shorter than the maximum length, return the whole text
            if (\mb_strlen(\preg_replace('/<.*?' . '>/', '', $text)) <= $length) {
                return $text;
            }
            // splits all html-tags to scanable lines
            \preg_match_all('/(<.+?' . '>)?([^<>]*)/s', $text, $lines, \PREG_SET_ORDER);
            $totalLength = \mb_strlen($ending);
            //$openTags    = [];
            $truncate = '';
            foreach ($lines as $lineMatchings) {
                // if there is any html-tag in this line, handle it and add it (uncounted) to the output
                if (!empty($lineMatchings[1])) {
                    // if it's an "empty element" with or without xhtml-conform closing slash
                    if (\preg_match('/^<(\s*.+?\/\s*|\s*(img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param)(\s.+?)?)>$/is', $lineMatchings[1])) {
                        // do nothing
                        // if tag is a closing tag
                    } elseif (\preg_match('/^<\s*\/(\S+?)\s*>$/s', $lineMatchings[1], $tagMatchings)) {
                        // delete tag from $openTags list
                        $pos = \array_search($tagMatchings[1], $openTags, true);
                        if (false !== $pos) {
                            unset($openTags[$pos]);
                        }
                        // if tag is an opening tag
                    } elseif (\preg_match('/^<\s*([^\s>!]+).*?' . '>$/s', $lineMatchings[1], $tagMatchings)) {
                        // add tag to the beginning of $openTags list
                        \array_unshift($openTags, \mb_strtolower($tagMatchings[1]));
                    }
                    // add html-tag to $truncate'd text
                    $truncate .= $lineMatchings[1];
                }
                // calculate the length of the plain text part of the line; handle entities as one character
                $contentLength = \mb_strlen(\preg_replace('/&[0-9a-z]{2,8};|&#\d{1,7};|[0-9a-f]{1,6};/i', ' ', $lineMatchings[2]));
                if ($totalLength + $contentLength > $length) {
                    // the number of characters which are left
                    $left            = $length - $totalLength;
                    $entitiesLength = 0;
                    // search for html entities
                    if (\preg_match_all('/&[0-9a-z]{2,8};|&#\d{1,7};|[0-9a-f]{1,6};/i', $lineMatchings[2], $entities, \PREG_OFFSET_CAPTURE)) {
                        // calculate the real length of all entities in the legal range
                        foreach ($entities[0] as $entity) {
                            if ($left >= $entity[1] + 1 - $entitiesLength) {
                                $left--;
                                $entitiesLength += \mb_strlen($entity[0]);
                            } else {
                                // no more characters left
                                break;
                            }
                        }
                    }
                    $truncate .= \mb_substr($lineMatchings[2], 0, $left + $entitiesLength);
                    // maximum length is reached, so get off the loop
                    break;
                }
                $truncate     .= $lineMatchings[2];
                $totalLength += $contentLength;

                // if the maximum length is reached, get off the loop
                if ($totalLength >= $length) {
                    break;
                }
            }
        } else {
            if (\mb_strlen($text) <= $length) {
                return $text;
            }
            $truncate = \mb_substr($text, 0, $length - \mb_strlen($ending));
        }
        // if the words shouldn't be cut in the middle...
        if (!$exact) {
            // ...search the last occurance of a space...
            $spacepos = \mb_strrpos($truncate, ' ');
            if (isset($spacepos)) {
                // ...and cut the text in this position
                $truncate = \mb_substr($truncate, 0, $spacepos);
            }
        }
        // add the defined ending to the text
        $truncate .= $ending;
        if ($considerHtml) {
            // close all unclosed html-tags
            foreach ($openTags as $tag) {
                $truncate .= '</' . $tag . '>';
            }
        }

        return $truncate;
    }