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

Complexity

Conditions	19
Paths	194

Size

Total Lines	129
Code Lines	46

Duplication

Lines	0
Ratio	0 %

Importance

Changes

0

<?php
    public static function truncateHtml($text, $length = 100, $ending = '...', $exact = false, $considerHtml = true)
    {
        $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);

            $total_length = mb_strlen($ending);

            //$openTags    = [];

            $truncate = '';

            foreach ($lines as $line_matchings) {
                // if there is any html-tag in this line, handle it and add it (uncounted) to the output

                if (!empty($line_matchings[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', $line_matchings[1])) {
                        // do nothing
                        // if tag is a closing tag
                    } elseif (\preg_match('/^<\s*\/(\S+?)\s*>$/s', $line_matchings[1], $tag_matchings)) {
                        // delete tag from $openTags list

                        $pos = \array_search($tag_matchings[1], $openTags);

                        if (false !== $pos) {
                            unset($openTags[$pos]);
                        }
                        // if tag is an opening tag
                    } elseif (\preg_match('/^<\s*([^\s>!]+).*?' . '>$/s', $line_matchings[1], $tag_matchings)) {
                        // add tag to the beginning of $openTags list

                        \array_unshift($openTags, \mb_strtolower($tag_matchings[1]));
                    }

                    // add html-tag to $truncate'd text

                    $truncate .= $line_matchings[1];
                }

                // calculate the length of the plain text part of the line; handle entities as one character

                $content_length = \mb_strlen(\preg_replace('/&[0-9a-z]{2,8};|&#\d{1,7};|[0-9a-f]{1,6};/i', ' ', $line_matchings[2]));

                if ($total_length + $content_length > $length) {
                    // the number of characters which are left

                    $left = $length - $total_length;

                    $entities_length = 0;

                    // search for html entities

                    if (\preg_match_all('/&[0-9a-z]{2,8};|&#\d{1,7};|[0-9a-f]{1,6};/i', $line_matchings[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 - $entities_length) {
                                $left--;

                                $entities_length += \mb_strlen($entity[0]);
                            } else {
                                // no more characters left

                                break;
                            }
                        }
                    }

                    $truncate .= \mb_substr($line_matchings[2], 0, $left + $entities_length);

                    // maximum lenght is reached, so get off the loop

                    break;
                }

                $truncate .= $line_matchings[2];

                $total_length += $content_length;

                // if the maximum length is reached, get off the loop

                if ($total_length >= $length) {
                    break;
                }
            }
        } elseif (\mb_strlen($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;
    }