X-Git-Url: https://git.mxchange.org/?a=blobdiff_plain;f=src%2FContent%2FText%2FHTML.php;h=f9f340135cf51cf22cab2bf62c941166305b2f4c;hb=7e618856ab09ac74a3760e238c73ecb9515f6701;hp=9121087296a977d539e89018546af79c822615d0;hpb=8b7cb5d9efeab580c2592e0fbe301f7142b73a3d;p=friendica.git

diff --git a/src/Content/Text/HTML.php b/src/Content/Text/HTML.php
index 9121087296..f9f340135c 100644
--- a/src/Content/Text/HTML.php
+++ b/src/Content/Text/HTML.php
@@ -1,6 +1,6 @@
 <?php
 /**
- * @copyright Copyright (C) 2010-2022, the Friendica project
+ * @copyright Copyright (C) 2010-2023, the Friendica project
  *
  * @license GNU AGPL version 3 or any later version
  *
@@ -23,6 +23,7 @@ namespace Friendica\Content\Text;
 
 use DOMDocument;
 use DOMXPath;
+use Friendica\Protocol\HTTP\MediaType;
 use Friendica\Content\Widget\ContactBlock;
 use Friendica\Core\Hook;
 use Friendica\Core\Renderer;
@@ -33,6 +34,7 @@ use Friendica\Util\Network;
 use Friendica\Util\Strings;
 use Friendica\Util\XML;
 use League\HTMLToMarkdown\HtmlConverter;
+use Psr\Http\Message\UriInterface;
 
 class HTML
 {
@@ -114,7 +116,7 @@ class HTML
 					/** @var \DOMNode $child */
 					foreach ($node->childNodes as $key => $child) {
 						/* Remove empty text nodes at the start or at the end of the children list */
-						if ($key > 0 && $key < $node->childNodes->length - 1 || $child->nodeName != '#text' || trim($child->nodeValue)) {
+						if ($key > 0 && $key < $node->childNodes->length - 1 || $child->nodeName != '#text' || trim($child->nodeValue) !== '') {
 							$newNode = $child->cloneNode(true);
 							$node->parentNode->insertBefore($newNode, $node);
 						}
@@ -144,10 +146,10 @@ class HTML
 	public static function toBBCode(string $message, string $basepath = ''): string
 	{
 		/*
-		 * Check if message is empty to prevent a lot code below being executed
+		 * Check if message is empty to prevent a lot of code below from being executed
 		 * for just an empty message.
 		 */
-		if (empty($message)) {
+		if ($message === '') {
 			return '';
 		}
 
@@ -736,22 +738,22 @@ class HTML
 			'[youtube]$2[/youtube]',
 			$s
 		);
-	
+
 		$s = preg_replace(
 			'#<iframe[^>](.*?)https?://www.youtube.com/embed/([A-Za-z0-9\-_=]+)(.*?)</iframe>#ism',
 			'[youtube]$2[/youtube]',
 			$s
 		);
-	
+
 		$s = preg_replace(
 			'#<iframe[^>](.*?)https?://player.vimeo.com/video/([0-9]+)(.*?)</iframe>#ism',
 			'[vimeo]$2[/vimeo]',
 			$s
 		);
-	
+
 		return $s;
 	}
-	
+
 	/**
 	 * transform link href and img src from relative to absolute
 	 *
@@ -764,30 +766,30 @@ class HTML
 		if (empty($base)) {
 			return $text;
 		}
-	
+
 		$base = rtrim($base, '/');
-	
+
 		$base2 = $base . "/";
-	
+
 		// Replace links
 		$pattern = "/<a([^>]*) href=\"(?!http|https|\/)([^\"]*)\"/";
 		$replace = "<a\${1} href=\"" . $base2 . "\${2}\"";
 		$text = preg_replace($pattern, $replace, $text);
-	
+
 		$pattern = "/<a([^>]*) href=\"(?!http|https)([^\"]*)\"/";
 		$replace = "<a\${1} href=\"" . $base . "\${2}\"";
 		$text = preg_replace($pattern, $replace, $text);
-	
+
 		// Replace images
 		$pattern = "/<img([^>]*) src=\"(?!http|https|\/)([^\"]*)\"/";
 		$replace = "<img\${1} src=\"" . $base2 . "\${2}\"";
 		$text = preg_replace($pattern, $replace, $text);
-	
+
 		$pattern = "/<img([^>]*) src=\"(?!http|https)([^\"]*)\"/";
 		$replace = "<img\${1} src=\"" . $base . "\${2}\"";
 		$text = preg_replace($pattern, $replace, $text);
-	
-	
+
+
 		// Done
 		return $text;
 	}
@@ -840,7 +842,7 @@ class HTML
 
 		if ($redirect) {
 			$url = Contact::magicLinkByContact($contact);
-			if (strpos($url, 'redir/') === 0) {
+			if (strpos($url, 'contact/redir/') === 0) {
 				$sparkle = ' sparkle';
 			}
 		}
@@ -907,19 +909,6 @@ class HTML
 		return Renderer::replaceMacros(Renderer::getMarkupTemplate('searchbox.tpl'), $values);
 	}
 
-	/**
-	 * Replace naked text hyperlink with HTML formatted hyperlink
-	 *
-	 * @param string $s
-	 * @return string
-	 */
-	public static function toLink(string $s): string
-	{
-		$s = preg_replace("/(https?\:\/\/[a-zA-Z0-9\:\/\-\?\&\;\.\=\_\~\#\'\%\$\!\+]*)/", ' <a href="$1" target="_blank" rel="noopener noreferrer">$1</a>', $s);
-		$s = preg_replace("/\<(.*?)(src|href)=(.*?)\&amp\;(.*?)\>/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 +1009,77 @@ 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;
+	}
 }