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
|
<?php
use Shaarli\Bookmark\LinkDB;
/**
* Get cURL callback function for CURLOPT_WRITEFUNCTION
*
* @param string $charset to extract from the downloaded page (reference)
* @param string $title to extract from the downloaded page (reference)
* @param string $curlGetInfo Optionally overrides curl_getinfo function
*
* @return Closure
*/
function get_curl_download_callback(&$charset, &$title, $curlGetInfo = 'curl_getinfo')
{
$isRedirected = false;
/**
* cURL callback function for CURLOPT_WRITEFUNCTION (called during the download).
*
* While downloading the remote page, we check that the HTTP code is 200 and content type is 'html/text'
* Then we extract the title and the charset and stop the download when it's done.
*
* @param resource $ch cURL resource
* @param string $data chunk of data being downloaded
*
* @return int|bool length of $data or false if we need to stop the download
*/
return function (&$ch, $data) use ($curlGetInfo, &$charset, &$title, &$isRedirected) {
$responseCode = $curlGetInfo($ch, CURLINFO_RESPONSE_CODE);
if (!empty($responseCode) && in_array($responseCode, [301, 302])) {
$isRedirected = true;
return strlen($data);
}
if (!empty($responseCode) && $responseCode !== 200) {
return false;
}
// After a redirection, the content type will keep the previous request value
// until it finds the next content-type header.
if (! $isRedirected || strpos(strtolower($data), 'content-type') !== false) {
$contentType = $curlGetInfo($ch, CURLINFO_CONTENT_TYPE);
}
if (!empty($contentType) && strpos($contentType, 'text/html') === false) {
return false;
}
if (!empty($contentType) && empty($charset)) {
$charset = header_extract_charset($contentType);
}
if (empty($charset)) {
$charset = html_extract_charset($data);
}
if (empty($title)) {
$title = html_extract_title($data);
}
// We got everything we want, stop the download.
if (!empty($responseCode) && !empty($contentType) && !empty($charset) && !empty($title)) {
return false;
}
return strlen($data);
};
}
/**
* 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;
}
/**
* Count private links in given linklist.
*
* @param array|Countable $links Linklist.
*
* @return int Number of private links.
*/
function count_private($links)
{
$cpt = 0;
foreach ($links as $link) {
if ($link['private']) {
$cpt += 1;
}
}
return $cpt;
}
/**
* In a string, converts URLs to clickable links.
*
* @param string $text input string.
*
* @return string returns $text with all links converted to HTML links.
*
* @see Function inspired from http://www.php.net/manual/en/function.preg-replace.php#85722
*/
function text2clickable($text)
{
$regex = '!(((?:https?|ftp|file)://|apt:|magnet:)\S+[a-z0-9\(\)]/?)!si';
return preg_replace($regex, '<a href="$1">$1</a>', $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 = '')
{
/*
* 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}]+)/mui';
$replacement = '$1<a href="'. $indexUrl .'?addtag=$2" title="Hashtag $2">#$2</a>';
return preg_replace($regex, $replacement, $description);
}
/**
* This function inserts 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 ', $text);
}
/**
* Format Shaarli's description
*
* @param string $description shaare's description.
* @param string $indexUrl URL to Shaarli's index.
* @return string formatted description.
*/
function format_description($description, $indexUrl = '')
{
return nl2br(space2nbsp(hashtag_autolink(text2clickable($description), $indexUrl)));
}
/**
* 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(LinkDB::LINK_DATE_FORMAT) . $id);
}
|
