Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
95.89% |
70 / 73 |
|
85.71% |
6 / 7 |
CRAP | |
0.00% |
0 / 1 |
| CommentMentionParserService | |
95.83% |
69 / 72 |
|
85.71% |
6 / 7 |
8 | |
0.00% |
0 / 1 |
| parseToHtml | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
1 | |||
| parseMarkdown | |
100.00% |
40 / 40 |
|
100.00% |
1 / 1 |
1 | |||
| parseContent | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| replaceEmoticons | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| highlightMentions | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
1 | |||
| highlightRecordReferences | |
100.00% |
16 / 16 |
|
100.00% |
1 / 1 |
1 | |||
| extractMentionTokens | |
0.00% |
0 / 3 |
|
0.00% |
0 / 1 |
6 | |||
| 1 | <?php |
| 2 | |
| 3 | declare(strict_types=1); |
| 4 | |
| 5 | /** @license For full copyright and license information, please see the LICENSE.md file. */ |
| 6 | |
| 7 | namespace App\Modules\Comments\Application\Service; |
| 8 | |
| 9 | defined('AMMONLY_APP') || exit('Direct script access is forbidden.'); |
| 10 | |
| 11 | /** |
| 12 | * Service parsing rich text comments: @mentions, #record references, and emoji emoticons. |
| 13 | * |
| 14 | * Provides safe HTML transformation preserving XSS protection. |
| 15 | * |
| 16 | * @package App\Modules\Comments\Application\Service |
| 17 | */ |
| 18 | final readonly class CommentMentionParserService |
| 19 | { |
| 20 | private const array EMOTICON_MAP = [ |
| 21 | ':)' => '😊', |
| 22 | ':-)' => '😊', |
| 23 | ':D' => '😃', |
| 24 | ':-D' => '😃', |
| 25 | ';)' => '😉', |
| 26 | ';-)' => '😉', |
| 27 | ':P' => '😋', |
| 28 | ':-P' => '😋', |
| 29 | ':p' => '😋', |
| 30 | '<3' => '❤️', |
| 31 | '(y)' => '👍', |
| 32 | ':(' => '🙁', |
| 33 | ':-(' => '🙁', |
| 34 | ':o' => '😮', |
| 35 | ':-o' => '😮', |
| 36 | ':O' => '😮', |
| 37 | ':-O' => '😮', |
| 38 | '8)' => '😎', |
| 39 | '8-)' => '😎', |
| 40 | ]; |
| 41 | |
| 42 | /** |
| 43 | * Parses raw input text into safe, enhanced HTML with markdown, mentions, records and emoticons. |
| 44 | * |
| 45 | * @param string $rawText Raw user comment input. |
| 46 | * @return string Safe sanitized HTML snippet. |
| 47 | */ |
| 48 | public function parseToHtml(string $rawText): string |
| 49 | { |
| 50 | $escaped = htmlspecialchars($rawText, ENT_QUOTES | ENT_SUBSTITUTE, 'UTF-8'); |
| 51 | $withMarkdown = $this->parseMarkdown($escaped); |
| 52 | $withEmoticons = $this->replaceEmoticons($withMarkdown); |
| 53 | $withMentions = $this->highlightMentions($withEmoticons); |
| 54 | $withRecords = $this->highlightRecordReferences($withMentions); |
| 55 | |
| 56 | return nl2br($withRecords); |
| 57 | } |
| 58 | |
| 59 | /** |
| 60 | * Parses safe markdown formatting elements into HTML tags. |
| 61 | */ |
| 62 | public function parseMarkdown(string $text): string |
| 63 | { |
| 64 | // 1. Code blocks (```lang ... ```) |
| 65 | $text = (string) preg_replace( |
| 66 | '/```(?:[a-zA-Z0-9_\-]+)?\n?(.*?)\n?```/s', |
| 67 | '<pre class="comment-code-block"><code>$1</code></pre>', |
| 68 | $text |
| 69 | ); |
| 70 | |
| 71 | // 2. Inline code (`code`) |
| 72 | $text = (string) preg_replace( |
| 73 | '/`([^`\n]+)`/', |
| 74 | '<code class="comment-code-inline">$1</code>', |
| 75 | $text |
| 76 | ); |
| 77 | |
| 78 | // 3. Markdown links [text](url) |
| 79 | $text = (string) preg_replace( |
| 80 | '/\[([^\]\n]+)\]\(((?:https?:\/\/|\/)[^\)\s]+)\)/', |
| 81 | '<a href="$2" target="_blank" rel="noopener noreferrer" class="comment-link">$1</a>', |
| 82 | $text |
| 83 | ); |
| 84 | |
| 85 | // 4. Bold (**text**) |
| 86 | $text = (string) preg_replace( |
| 87 | '/\*\*([^\*\n]+)\*\*/', |
| 88 | '<strong>$1</strong>', |
| 89 | $text |
| 90 | ); |
| 91 | |
| 92 | // 5. Italic (*text*) |
| 93 | $text = (string) preg_replace( |
| 94 | '/(?<!\*)\*([^\*\n]+)\*(?!\*)/', |
| 95 | '<em>$1</em>', |
| 96 | $text |
| 97 | ); |
| 98 | |
| 99 | // 6. Underline (__text__) |
| 100 | $text = (string) preg_replace( |
| 101 | '/__([^_\n]+)__/', |
| 102 | '<u>$1</u>', |
| 103 | $text |
| 104 | ); |
| 105 | |
| 106 | // 7. Strikethrough (~text~ or ~~text~~) |
| 107 | $text = (string) preg_replace( |
| 108 | '/~{1,2}([^~\n]+)~{1,2}/', |
| 109 | '<del>$1</del>', |
| 110 | $text |
| 111 | ); |
| 112 | |
| 113 | // 8. Blockquote (> text) |
| 114 | return (string) preg_replace( |
| 115 | '/(?<=^|\n)>\s?(.*)/', |
| 116 | '<blockquote class="comment-blockquote">$1</blockquote>', |
| 117 | $text |
| 118 | ); |
| 119 | } |
| 120 | |
| 121 | /** |
| 122 | * Alias for parseToHtml. |
| 123 | */ |
| 124 | public function parseContent(string $rawText): string |
| 125 | { |
| 126 | return $this->parseToHtml($rawText); |
| 127 | } |
| 128 | |
| 129 | /** |
| 130 | * Replaces classic ASCII text smileys with Unicode emoji characters. |
| 131 | */ |
| 132 | public function replaceEmoticons(string $text): string |
| 133 | { |
| 134 | return str_replace(array_keys(self::EMOTICON_MAP), array_values(self::EMOTICON_MAP), $text); |
| 135 | } |
| 136 | |
| 137 | /** |
| 138 | * Converts @username or @firstname_lastname into highlighted mention chips. |
| 139 | */ |
| 140 | public function highlightMentions(string $text): string |
| 141 | { |
| 142 | return (string) preg_replace( |
| 143 | '/(?<=^|\s)@([a-zA-Z0-9_\.\-\p{L}]+)/u', |
| 144 | '<span class="comment-mention"><i class="bi bi-at" aria-hidden="true"></i>$1</span>', |
| 145 | $text |
| 146 | ); |
| 147 | } |
| 148 | |
| 149 | /** |
| 150 | * Converts #RECORD-123, #Record_Title, or #[Record Title] references into styled record chips. |
| 151 | */ |
| 152 | public function highlightRecordReferences(string $text): string |
| 153 | { |
| 154 | // 1. Bracketed references: #[Title with spaces] |
| 155 | $text = (string) preg_replace( |
| 156 | '/(?<=^|\s)#\[([^\]\r\n]+)\]/u', |
| 157 | '<span class="comment-record-ref" data-ref="$1"><i class="bi bi-hash" aria-hidden="true"></i>$1</span>', |
| 158 | $text |
| 159 | ); |
| 160 | |
| 161 | // 2. Standard token references: #Record_Title or #123 |
| 162 | return (string) preg_replace_callback( |
| 163 | '/(?<=^|\s)#([\p{L}\p{N}_\.\-\/]+)/u', |
| 164 | static function (array $matches): string { |
| 165 | $ref = $matches[1]; |
| 166 | $display = str_replace('_', ' ', $ref); |
| 167 | |
| 168 | return '<span class="comment-record-ref" data-ref="' . $ref . '">' |
| 169 | . '<i class="bi bi-hash" aria-hidden="true"></i>' . $display |
| 170 | . '</span>'; |
| 171 | }, |
| 172 | $text |
| 173 | ); |
| 174 | } |
| 175 | |
| 176 | /** |
| 177 | * Extracts all distinct mention tokens (@token) from raw or formatted text. |
| 178 | * |
| 179 | * @param string $text Input text. |
| 180 | * @return array<int, string> List of lowercased tokens without the '@' prefix. |
| 181 | */ |
| 182 | public function extractMentionTokens(string $text): array |
| 183 | { |
| 184 | if (preg_match_all('/(?<=^|\s)@([a-zA-Z0-9_\.\-\p{L}]+)/u', $text, $matches)) { |
| 185 | return array_values(array_unique(array_map('mb_strtolower', $matches[1]))); |
| 186 | } |
| 187 | |
| 188 | return []; |
| 189 | } |
| 190 | } |