diff options
Diffstat (limited to 'application/bookmark/LinkUtils.php')
-rw-r--r-- | application/bookmark/LinkUtils.php | 72 |
1 files changed, 63 insertions, 9 deletions
diff --git a/application/bookmark/LinkUtils.php b/application/bookmark/LinkUtils.php index e7af4d55..d65e97ed 100644 --- a/application/bookmark/LinkUtils.php +++ b/application/bookmark/LinkUtils.php | |||
@@ -66,16 +66,19 @@ function html_extract_tag($tag, $html) | |||
66 | { | 66 | { |
67 | $propertiesKey = ['property', 'name', 'itemprop']; | 67 | $propertiesKey = ['property', 'name', 'itemprop']; |
68 | $properties = implode('|', $propertiesKey); | 68 | $properties = implode('|', $propertiesKey); |
69 | // Try to retrieve OpenGraph image. | 69 | // We need a OR here to accept either 'property=og:noquote' or 'property="og:unrelated og:my-tag"' |
70 | $ogRegex = '#<meta[^>]+(?:'. $properties .')=["\']?(?:og:)?'. $tag .'["\'\s][^>]*content=["\']?(.*?)["\'/>]#'; | 70 | $orCondition = '["\']?(?:og:)?' . $tag . '["\']?|["\'][^\'"]*?(?:og:)?' . $tag . '[^\'"]*?[\'"]'; |
71 | // Try to retrieve OpenGraph tag. | ||
72 | $ogRegex = '#<meta[^>]+(?:' . $properties . ')=(?:' . $orCondition . ')[^>]*content=(["\'])([^\1]*?)\1.*?>#'; | ||
71 | // If the attributes are not in the order property => content (e.g. Github) | 73 | // If the attributes are not in the order property => content (e.g. Github) |
72 | // New regex to keep this readable... more or less. | 74 | // New regex to keep this readable... more or less. |
73 | $ogRegexReverse = '#<meta[^>]+content=["\']([^"\']+)[^>]+(?:'. $properties .')=["\']?(?:og)?:'. $tag .'["\'\s/>]#'; | 75 | $ogRegexReverse = '#<meta[^>]+content=(["\'])([^\1]*?)\1[^>]+(?:' . $properties . ')=(?:' . $orCondition . ').*?>#'; |
74 | 76 | ||
75 | if (preg_match($ogRegex, $html, $matches) > 0 | 77 | if ( |
78 | preg_match($ogRegex, $html, $matches) > 0 | ||
76 | || preg_match($ogRegexReverse, $html, $matches) > 0 | 79 | || preg_match($ogRegexReverse, $html, $matches) > 0 |
77 | ) { | 80 | ) { |
78 | return $matches[1]; | 81 | return $matches[2]; |
79 | } | 82 | } |
80 | 83 | ||
81 | return false; | 84 | return false; |
@@ -114,7 +117,7 @@ function hashtag_autolink($description, $indexUrl = '') | |||
114 | * \p{Mn} - any non marking space (accents, umlauts, etc) | 117 | * \p{Mn} - any non marking space (accents, umlauts, etc) |
115 | */ | 118 | */ |
116 | $regex = '/(^|\s)#([\p{Pc}\p{N}\p{L}\p{Mn}]+)/mui'; | 119 | $regex = '/(^|\s)#([\p{Pc}\p{N}\p{L}\p{Mn}]+)/mui'; |
117 | $replacement = '$1<a href="'. $indexUrl .'./add-tag/$2" title="Hashtag $2">#$2</a>'; | 120 | $replacement = '$1<a href="' . $indexUrl . './add-tag/$2" title="Hashtag $2">#$2</a>'; |
118 | return preg_replace($regex, $replacement, $description); | 121 | return preg_replace($regex, $replacement, $description); |
119 | } | 122 | } |
120 | 123 | ||
@@ -136,12 +139,17 @@ function space2nbsp($text) | |||
136 | * | 139 | * |
137 | * @param string $description shaare's description. | 140 | * @param string $description shaare's description. |
138 | * @param string $indexUrl URL to Shaarli's index. | 141 | * @param string $indexUrl URL to Shaarli's index. |
139 | 142 | * @param bool $autolink Turn on/off automatic linkifications of URLs and hashtags | |
143 | * | ||
140 | * @return string formatted description. | 144 | * @return string formatted description. |
141 | */ | 145 | */ |
142 | function format_description($description, $indexUrl = '') | 146 | function format_description($description, $indexUrl = '', $autolink = true) |
143 | { | 147 | { |
144 | return nl2br(space2nbsp(hashtag_autolink(text2clickable($description), $indexUrl))); | 148 | if ($autolink) { |
149 | $description = hashtag_autolink(text2clickable($description), $indexUrl); | ||
150 | } | ||
151 | |||
152 | return nl2br(space2nbsp($description)); | ||
145 | } | 153 | } |
146 | 154 | ||
147 | /** | 155 | /** |
@@ -169,3 +177,49 @@ function is_note($linkUrl) | |||
169 | { | 177 | { |
170 | return isset($linkUrl[0]) && $linkUrl[0] === '?'; | 178 | return isset($linkUrl[0]) && $linkUrl[0] === '?'; |
171 | } | 179 | } |
180 | |||
181 | /** | ||
182 | * Extract an array of tags from a given tag string, with provided separator. | ||
183 | * | ||
184 | * @param string|null $tags String containing a list of tags separated by $separator. | ||
185 | * @param string $separator Shaarli's default: ' ' (whitespace) | ||
186 | * | ||
187 | * @return array List of tags | ||
188 | */ | ||
189 | function tags_str2array(?string $tags, string $separator): array | ||
190 | { | ||
191 | // For whitespaces, we use the special \s regex character | ||
192 | $separator = $separator === ' ' ? '\s' : $separator; | ||
193 | |||
194 | return preg_split('/\s*' . $separator . '+\s*/', trim($tags) ?? '', -1, PREG_SPLIT_NO_EMPTY); | ||
195 | } | ||
196 | |||
197 | /** | ||
198 | * Return a tag string with provided separator from a list of tags. | ||
199 | * Note that given array is clean up by tags_filter(). | ||
200 | * | ||
201 | * @param array|null $tags List of tags | ||
202 | * @param string $separator | ||
203 | * | ||
204 | * @return string | ||
205 | */ | ||
206 | function tags_array2str(?array $tags, string $separator): string | ||
207 | { | ||
208 | return implode($separator, tags_filter($tags, $separator)); | ||
209 | } | ||
210 | |||
211 | /** | ||
212 | * Clean an array of tags: trim + remove empty entries | ||
213 | * | ||
214 | * @param array|null $tags List of tags | ||
215 | * @param string $separator | ||
216 | * | ||
217 | * @return array | ||
218 | */ | ||
219 | function tags_filter(?array $tags, string $separator): array | ||
220 | { | ||
221 | $trimDefault = " \t\n\r\0\x0B"; | ||
222 | return array_values(array_filter(array_map(function (string $entry) use ($separator, $trimDefault): string { | ||
223 | return trim($entry, $trimDefault . $separator); | ||
224 | }, $tags ?? []))); | ||
225 | } | ||