aboutsummaryrefslogtreecommitdiffhomepage
path: root/application/bookmark/LinkUtils.php
blob: 8fa2953a78d3e8f18bbcba3824801d859169c16e (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
<?php

use Shaarli\Bookmark\Bookmark;
use Shaarli\Formatter\BookmarkDefaultFormatter;

/**
 * Extract title from an HTML document.
 *
 * @param string $html HTML content where to look for a title.
 *
 * @return bool|string Extracted title if found, false otherwise.
 */
function html_extract_title($html)
{
    if (preg_match('!<title.*?>(.*?)</title>!is', $html, $matches)) {
        return trim(str_replace("\n", '', $matches[1]));
    }
    return false;
}

/**
 * Extract charset from HTTP header if it's defined.
 *
 * @param string $header HTTP header Content-Type line.
 *
 * @return bool|string Charset string if found (lowercase), false otherwise.
 */
function header_extract_charset($header)
{
    preg_match('/charset=["\']?([^; "\']+)/i', $header, $match);
    if (! empty($match[1])) {
        return strtolower(trim($match[1]));
    }

    return false;
}

/**
 * Extract charset HTML content (tag <meta charset>).
 *
 * @param string $html HTML content where to look for charset.
 *
 * @return bool|string Charset string if found, false otherwise.
 */
function html_extract_charset($html)
{
    // Get encoding specified in HTML header.
    preg_match('#<meta .*charset=["\']?([^";\'>/]+)["\']? */?>#Usi', $html, $enc);
    if (!empty($enc[1])) {
        return strtolower($enc[1]);
    }

    return false;
}

/**
 * Extract meta tag from HTML content in either:
 *   - OpenGraph: <meta property="og:[tag]" ...>
 *   - Meta tag: <meta name="[tag]" ...>
 *
 * @param string $tag  Name of the tag to retrieve.
 * @param string $html HTML content where to look for charset.
 *
 * @return bool|string Charset string if found, false otherwise.
 */
function html_extract_tag($tag, $html)
{
    $propertiesKey = ['property', 'name', 'itemprop'];
    $properties = implode('|', $propertiesKey);
    // We need a OR here to accept either 'property=og:noquote' or 'property="og:unrelated og:my-tag"'
    $orCondition  = '["\']?(?:og:)?' . $tag . '["\']?|["\'][^\'"]*?(?:og:)?' . $tag . '[^\'"]*?[\'"]';
    // Support quotes in double quoted content, and the other way around
    $content = 'content=(["\'])((?:(?!\1).)*)\1';
    // Try to retrieve OpenGraph tag.
    $ogRegex = '#<meta[^>]+(?:' . $properties . ')=(?:' . $orCondition . ')[^>]*' . $content . '.*?>#';
    // If the attributes are not in the order property => content (e.g. Github)
    // New regex to keep this readable... more or less.
    $ogRegexReverse = '#<meta[^>]+' . $content . '[^>]+(?:' . $properties . ')=(?:' . $orCondition . ').*?>#';

    if (
        preg_match($ogRegex, $html, $matches) > 0
        || preg_match($ogRegexReverse, $html, $matches) > 0
    ) {
        return $matches[2];
    }

    return false;
}

/**
 * In a string, converts URLs to clickable bookmarks.
 *
 * @param string $text       input string.
 *
 * @return string returns $text with all bookmarks converted to HTML bookmarks.
 *
 * @see Function inspired from http://www.php.net/manual/en/function.preg-replace.php#85722
 */
function text2clickable($text)
{
    $regex = '!(((?:https?|ftp|file)://|apt:|magnet:)\S+[a-z0-9\(\)]/?)!si';
    $format = function (array $match): string {
        return '<a href="' .
            str_replace(
                BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_OPEN,
                '',
                str_replace(BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_CLOSE, '', $match[1])
            ) .
            '">' . $match[1] . '</a>'
        ;
    };

    return preg_replace_callback($regex, $format, $text);
}

/**
 * Auto-link hashtags.
 *
 * @param string $description Given description.
 * @param string $indexUrl    Root URL.
 *
 * @return string Description with auto-linked hashtags.
 */
function hashtag_autolink($description, $indexUrl = '')
{
    $tokens = '(?:' . BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_OPEN . ')' .
              '(?:' . BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_CLOSE . ')'
    ;
    /*
     * To support unicode: http://stackoverflow.com/a/35498078/1484919
     * \p{Pc} - to match underscore
     * \p{N} - numeric character in any script
     * \p{L} - letter from any language
     * \p{Mn} - any non marking space (accents, umlauts, etc)
     */
    $regex = '/(^|\s)#([\p{Pc}\p{N}\p{L}\p{Mn}' . $tokens . ']+)/mui';
    $format = function (array $match) use ($indexUrl): string {
        $cleanMatch = str_replace(
            BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_OPEN,
            '',
            str_replace(BookmarkDefaultFormatter::SEARCH_HIGHLIGHT_CLOSE, '', $match[2])
        );
        return $match[1] . '<a href="' . $indexUrl . './add-tag/' . $cleanMatch . '"' .
            ' title="Hashtag ' . $cleanMatch . '">' .
                '#' . $match[2] .
        '</a>';
    };

    return preg_replace_callback($regex, $format, $description);
}

/**
 * This function inserts &nbsp; where relevant so that multiple spaces are properly displayed in HTML
 * even in the absence of <pre>  (This is used in description to keep text formatting).
 *
 * @param string $text input text.
 *
 * @return string formatted text.
 */
function space2nbsp($text)
{
    return preg_replace('/(^| ) /m', '$1&nbsp;', $text);
}

/**
 * Format Shaarli's description
 *
 * @param string $description shaare's description.
 * @param string $indexUrl    URL to Shaarli's index.
 * @param bool   $autolink    Turn on/off automatic linkifications of URLs and hashtags
 *
 * @return string formatted description.
 */
function format_description($description, $indexUrl = '', $autolink = true)
{
    if ($autolink) {
        $description = hashtag_autolink(text2clickable($description), $indexUrl);
    }

    return nl2br(space2nbsp($description));
}

/**
 * Generate a small hash for a link.
 *
 * @param DateTime $date Link creation date.
 * @param int      $id   Link ID.
 *
 * @return string the small hash generated from link data.
 */
function link_small_hash($date, $id)
{
    return smallHash($date->format(Bookmark::LINK_DATE_FORMAT) . $id);
}

/**
 * Returns whether or not the link is an internal note.
 * Its URL starts by `?` because it's actually a permalink.
 *
 * @param string $linkUrl
 *
 * @return bool true if internal note, false otherwise.
 */
function is_note($linkUrl)
{
    return isset($linkUrl[0]) && $linkUrl[0] === '?';
}

/**
 * Extract an array of tags from a given tag string, with provided separator.
 *
 * @param string|null $tags      String containing a list of tags separated by $separator.
 * @param string      $separator Shaarli's default: ' ' (whitespace)
 *
 * @return array List of tags
 */
function tags_str2array(?string $tags, string $separator): array
{
    // For whitespaces, we use the special \s regex character
    $separator = $separator === ' ' ? '\s' : $separator;

    return preg_split('/\s*' . $separator . '+\s*/', trim($tags) ?? '', -1, PREG_SPLIT_NO_EMPTY);
}

/**
 * Return a tag string with provided separator from a list of tags.
 * Note that given array is clean up by tags_filter().
 *
 * @param array|null $tags      List of tags
 * @param string     $separator
 *
 * @return string
 */
function tags_array2str(?array $tags, string $separator): string
{
    return implode($separator, tags_filter($tags, $separator));
}

/**
 * Clean an array of tags: trim + remove empty entries
 *
 * @param array|null $tags List of tags
 * @param string     $separator
 *
 * @return array
 */
function tags_filter(?array $tags, string $separator): array
{
    $trimDefault = " \t\n\r\0\x0B";
    return array_values(array_filter(array_map(function (string $entry) use ($separator, $trimDefault): string {
        return trim($entry, $trimDefault . $separator);
    }, $tags ?? [])));
}