X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FContent%2FText%2FHTML.php;h=89a680501f1674761d0c394cf1bc17799a50a6b5;hb=a8402109b183e81dad4e5443883dd292df094b86;hp=2e55c71d2021759c2c875b8c5c702471c258d3b9;hpb=d3bbed176ff67d69b6424a892c2a358ecda5d824;p=friendica.git
diff --git a/src/Content/Text/HTML.php b/src/Content/Text/HTML.php
index 2e55c71d20..89a680501f 100644
--- a/src/Content/Text/HTML.php
+++ b/src/Content/Text/HTML.php
@@ -1,6 +1,6 @@
](.*?)https?://www.youtube.com/embed/([A-Za-z0-9\-_=]+)(.*?)#ism',
'[youtube]$2[/youtube]',
$s
);
-
+
$s = preg_replace(
'##ism',
'[vimeo]$2[/vimeo]',
$s
);
-
+
return $s;
}
-
+
/**
* transform link href and img src from relative to absolute
*
@@ -764,30 +739,30 @@ class HTML
if (empty($base)) {
return $text;
}
-
+
$base = rtrim($base, '/');
-
+
$base2 = $base . "/";
-
+
// Replace links
$pattern = "/]*) href=\"(?!http|https|\/)([^\"]*)\"/";
$replace = "]*) href=\"(?!http|https)([^\"]*)\"/";
$replace = "]*) src=\"(?!http|https|\/)([^\"]*)\"/";
$replace = "
]*) src=\"(?!http|https)([^\"]*)\"/";
$replace = "
$1', $s);
- $s = preg_replace("/\<(.*?)(src|href)=(.*?)\&\;(.*?)\>/ism", '<$1$2=$3&$4>', $s);
- return $s;
- }
-
/**
* Given a HTML text and a set of filtering reasons, adds a content hiding header with the provided reasons
*
@@ -1020,4 +982,77 @@ class HTML
return $text;
}
+
+ /**
+ * XPath arbitrary string quoting
+ *
+ * @see https://stackoverflow.com/a/45228168
+ * @param string $value
+ * @return string
+ */
+ public static function xpathQuote(string $value): string
+ {
+ if (false === strpos($value, '"')) {
+ return '"' . $value . '"';
+ }
+
+ if (false === strpos($value, "'")) {
+ return "'" . $value . "'";
+ }
+
+ // if the value contains both single and double quotes, construct an
+ // expression that concatenates all non-double-quote substrings with
+ // the quotes, e.g.:
+ //
+ // concat("'foo'", '"', "bar")
+ return 'concat(' . implode(', \'"\', ', array_map([self::class, 'xpathQuote'], explode('"', $value))) . ')';
+ }
+
+ /**
+ * Checks if the provided URL is present in the DOM document in an element with the rel="me" attribute
+ *
+ * XHTML Friends Network http://gmpg.org/xfn/
+ *
+ * @param DOMDocument $doc
+ * @param UriInterface $meUrl
+ * @return bool
+ */
+ public static function checkRelMeLink(DOMDocument $doc, UriInterface $meUrl): bool
+ {
+ $xpath = new \DOMXpath($doc);
+
+ // This expression checks that "me" is among the space-delimited values of the "rel" attribute.
+ // And that the href attribute contains exactly the provided URL
+ $expression = "//*[contains(concat(' ', normalize-space(@rel), ' '), ' me ')][@href = " . self::xpathQuote($meUrl) . "]";
+
+ $result = $xpath->query($expression);
+
+ return $result !== false && $result->length > 0;
+ }
+
+ /**
+ * @param DOMDocument $doc
+ * @return string|null Lowercase charset
+ */
+ public static function extractCharset(DOMDocument $doc): ?string
+ {
+ $xpath = new DOMXPath($doc);
+
+ $expression = "string(//meta[@charset]/@charset)";
+ if ($charset = $xpath->evaluate($expression)) {
+ return strtolower($charset);
+ }
+
+ try {
+ // This expression looks for a meta tag with the http-equiv attribute set to "content-type" ignoring case
+ // whose content attribute contains a "charset" string and returns its value
+ $expression = "string(//meta[@http-equiv][translate(@http-equiv, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz') = 'content-type'][contains(translate(@content, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'charset')]/@content)";
+ $mediaType = MediaType::fromContentType($xpath->evaluate($expression));
+ if (isset($mediaType->parameters['charset'])) {
+ return strtolower($mediaType->parameters['charset']);
+ }
+ } catch(\InvalidArgumentException $e) {}
+
+ return null;
+ }
}