MediaEmbed: added Bluesky

Closes #238
s9e · Nov 11, 2024 · 922ca9e · rxu · Nov 15, 2024 · JoshyPHP
1 parent 0ad2008
commit 922ca9e
Show file tree

Hide file tree

Showing 11 changed files with 278 additions and 84 deletions.
diff --git a/docs/Plugins/MediaEmbed/Federated_sites.md b/docs/Plugins/MediaEmbed/Federated_sites.md
@@ -1,5 +1,31 @@
 <h2>Federated sites</h2>
 
+
+### Bluesky
+
+The default Bluesky media site can be customized with different hosts. This can be done using the `BlueskyHelper` class. In the example below, we configure the Bluesky media site to support both the main `bsky.app` domain, as well as our own hypothetical instance hosted on `bluesky.local`.
+
+```php
+$configurator = new s9e\TextFormatter\Configurator;
+
+// Use the Bluesky helper to set 'bsky.app' and 'bluesky.local' as supported instances
+$mastodonHelper = $configurator->MediaEmbed->getSiteHelper('bluesky');
+$mastodonHelper->setHosts(['bsky.app', 'bluesky.local']);
+
+// Get an instance of the parser and the renderer
+extract($configurator->finalize());
+
+$text = 'https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v';
+$xml  = $parser->parse($text);
+$html = $renderer->render($xml);
+
+echo $html;
+```
+```html
+<iframe data-s9e-mediaembed="bluesky" allowfullscreen="" loading="lazy" onload="let c=new MessageChannel;c.port1.onmessage=e=&gt;this.style.height=e.data+'px';this.contentWindow.postMessage('s9e:init','*',[c.port2])" scrolling="no" src="https://s9e.github.io/iframe/2/bluesky.min.html#at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v#embed.bsky.app" style="border:0;height:600px;max-width:600px;width:100%"></iframe>
+```
+
+
 ### Mastodon
 
 The default Mastodon media site can be customized with additional hosts. This can be done using the `MastodonHelper` class. In the example below, we add support for toots published by the `infosec.exchange` instance.

diff --git a/docs/Plugins/MediaEmbed/Sites.md b/docs/Plugins/MediaEmbed/Sites.md
@@ -45,6 +45,10 @@
 		<td><code>bitchute</code></td>
 		<td>https://www.bitchute.com/video/y9AejeZ2vD0/</td>
 	</tr>
+	<tr title="Bluesky" id="bluesky">
+		<td><code>bluesky</code></td>
+		<td>https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v<br/>https://bsky.app/profile/bnewbold.net/post/3kxjq2auebs2f</td>
+	</tr>
 	<tr title="Brightcove" id="brightcove">
 		<td><code>brightcove</code></td>
 		<td>https://players.brightcove.net/219646971/default_default/index.html?videoId=4815779906001<br/>https://link.brightcove.com/services/player/bcpid4773906090001?bckey=AQ~~,AAAAAA0Xi_s~,r1xMuE8k5Nyz5IyYc0Hzhl5eZ5cEEvlm&amp;bctid=4815779906001</td>

diff --git a/docs/Plugins/MediaEmbed/Using_default_sites.md b/docs/Plugins/MediaEmbed/Using_default_sites.md
@@ -77,7 +77,7 @@ echo count($configurator->MediaEmbed->defaultSites), " sites remaining.\n";
 ```
 Does YouTube exist? yes
 What about now? no
-133 sites remaining.
+134 sites remaining.
 0 sites remaining.
 ```
 

diff --git a/docs/testdox.txt b/docs/testdox.txt
@@ -6757,6 +6757,11 @@ Xml File Definition Collection (s9e\TextFormatter\Tests\Plugins\MediaEmbed\Confi
  [x] Other default attribute values are left as strings
  [x] Attributes' "required" property is cast to bool
 
+Bluesky Helper (s9e\TextFormatter\Tests\Plugins\MediaEmbed\Configurator\SiteHelpers\BlueskyHelper)
+ [x] addHost() normalizes the host
+ [x] addHost() adds the Bluesky media site if it's not enabled yet
+ [x] addHost() updates the embedded regexp
+
 Mastodon Helper (s9e\TextFormatter\Tests\Plugins\MediaEmbed\Configurator\SiteHelpers\MastodonHelper)
  [x] addHost() normalizes the host
  [x] addHost() adds the Mastodon media site if it's not enabled yet
@@ -6896,6 +6901,8 @@ Parser (s9e\TextFormatter\Tests\Plugins\MediaEmbed\Parser)
  [x] Scraping tests with data set #54
  [x] Scraping tests with data set #55
  [x] Scraping tests with data set #56
+ [x] Scraping tests with data set #57
+ [x] Scraping tests with data set #58
  [x] Scraping+rendering tests with data set #0
  [x] Scraping+rendering tests with data set #1
  [x] Scraping+rendering tests with data set #2

diff --git a/src/Bundles/MediaPack.php b/src/Bundles/MediaPack.php
diff --git a/src/Bundles/MediaPack/Renderer.php b/src/Bundles/MediaPack/Renderer.php
diff --git a/src/Plugins/MediaEmbed/Configurator/Collections/CachedDefinitionCollection.php b/src/Plugins/MediaEmbed/Configurator/Collections/CachedDefinitionCollection.php
@@ -21,6 +21,7 @@ class CachedDefinitionCollection extends SiteDefinitionCollection
 		'bandcamp'=>['attributes'=>[],'example'=>['https://proleter.bandcamp.com/album/curses-from-past-times-ep','https://proleter.bandcamp.com/track/downtown-irony','https://therunons.bandcamp.com/track/still-feel'],'extract'=>[],'homepage'=>'https://bandcamp.com/','host'=>['bandcamp.com'],'iframe'=>['height'=>400,'src'=>'//bandcamp.com/EmbeddedPlayer/size=large/minimal=true/<xsl:choose><xsl:when test="@album_id">album=<xsl:value-of select="@album_id"/><xsl:if test="@track_num">/t=<xsl:value-of select="@track_num"/></xsl:if></xsl:when><xsl:otherwise>track=<xsl:value-of select="@track_id"/></xsl:otherwise></xsl:choose><xsl:if test="$MEDIAEMBED_THEME=\'dark\'">/bgcol=333333/linkcol=0f91ff</xsl:if>','width'=>400],'name'=>'Bandcamp','scrape'=>[['extract'=>['!/album=(?\'album_id\'\\d+)!'],'header'=>'User-agent: PHP (not Mozilla)','match'=>['!bandcamp\\.com/album/.!']],['extract'=>['!(?:"|&quot;)album_id(?:"|&quot;):(?\'album_id\'\\d+)!','!(?:"|&quot;)track_num(?:"|&quot;):(?\'track_num\'\\d+)!','!/track=(?\'track_id\'\\d+)!'],'header'=>'User-agent: PHP (not Mozilla)','match'=>['!bandcamp\\.com/track/.!']]],'tags'=>['music']],
 		'bbcnews'=>['attributes'=>[],'example'=>['https://www.bbc.com/news/video_and_audio/must_see/42847060/calls-to-clean-off-banksy-mural-in-hull','https://www.bbc.co.uk/news/av/world-africa-48141248/fifteen-year-old-nigerian-builds-small-scale-construction-machines','https://www.bbc.co.uk/news/av/embed/p0783sg7/48125671'],'extract'=>['@bbc\\.co(?:m|\\.uk)/news/(?:av|video_and_audio)/(?:\\w+-)+(?\'id\'\\d+)@','@bbc\\.co(?:m|\\.uk)/news/(?:av|video_and_audio)/embed/(?\'id\'\\w+/\\d+)@','@bbc\\.co(?:m|\\.uk)/news/(?:av|video_and_audio)/\\w+/(?\'id\'\\d+)@','@bbc\\.co(?:m|\\.uk)/news/av-embeds/(?\'id\'\\d+)@'],'homepage'=>'https://www.bbc.com/news/video_and_audio/headlines/','host'=>['bbc.co.uk','bbc.com'],'iframe'=>['src'=>'//www.bbc.com/news/av-embeds/<xsl:choose><xsl:when test="starts-with(@playlist,\'/news/\')"><xsl:choose><xsl:when test="contains(@playlist,\'-\')"><xsl:value-of select="substring-after(substring-after(translate(@playlist,\'A\',\'#\'),\'news/\'),\'-\')"/></xsl:when><xsl:otherwise><xsl:value-of select="substring-after(translate(@playlist,\'A\',\'/\'),\'/news/\')"/></xsl:otherwise></xsl:choose></xsl:when><xsl:when test="contains(@id,\'/\')"><xsl:value-of select="substring-after(@id,\'/\')"/></xsl:when><xsl:otherwise><xsl:value-of select="@id"/></xsl:otherwise></xsl:choose>'],'name'=>'BBC News','scrape'=>[],'tags'=>['news']],
 		'bitchute'=>['attributes'=>[],'example'=>'https://www.bitchute.com/video/y9AejeZ2vD0/','extract'=>['@bitchute\\.com/(?:embed|video)/(?\'id\'[-\\w]+)@'],'homepage'=>'https://www.bitchute.com/','host'=>['bitchute.com'],'iframe'=>['src'=>'https://www.bitchute.com/embed/{@id}/'],'name'=>'BitChute','oembed'=>['endpoint'=>'https://www.bitchute.com/oembed/','scheme'=>'https://www.bitchute.com/video/{@id}/'],'scrape'=>[],'tags'=>['videos']],
+		'bluesky'=>['attributes'=>['embedder'=>['filterChain'=>['#regexp(/^(?:[-\\w]*\\.)*bsky\\.app$/)'],'required'=>true],'url'=>['filterChain'=>['urldecode','#regexp(/^at:\\/\\/[.:\\w]+\\/[.\\w]+\\/\\w+$/)'],'required'=>true]],'example'=>['https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v','https://bsky.app/profile/bnewbold.net/post/3kxjq2auebs2f'],'extract'=>['#https://(?\'embedder\'[.\\w]+)/oembed.*?url=(?\'url\'[\\w%.]+)#'],'helper'=>'s9e\\TextFormatter\\Plugins\\MediaEmbed\\Configurator\\SiteHelpers\\BlueskyHelper','homepage'=>'https://bsky.app/','host'=>['bsky.app'],'iframe'=>['data-s9e-livepreview-ignore-attrs'=>'style','height'=>600,'onload'=>'let c=new MessageChannel;c.port1.onmessage=e=>this.style.height=e.data+\'px\';this.contentWindow.postMessage(\'s9e:init\',\'*\',[c.port2])','src'=>'https://s9e.github.io/iframe/2/bluesky.min.html#<xsl:value-of select="@url"/>#<xsl:value-of select="@embedder"/>','width'=>600],'name'=>'Bluesky','scrape'=>[['extract'=>['#https://(?\'embedder\'[.\\w]+)/oembed.*?url=(?\'url\'[\\w%.]+)#'],'match'=>['#/profile/[^/]+/post/.#']]],'source'=>'https://embed.bsky.app/','tags'=>['social']],
 		'brightcove'=>['attributes'=>['bckey'=>['required'=>false]],'example'=>['https://players.brightcove.net/219646971/default_default/index.html?videoId=4815779906001','https://link.brightcove.com/services/player/bcpid4773906090001?bckey=AQ~~,AAAAAA0Xi_s~,r1xMuE8k5Nyz5IyYc0Hzhl5eZ5cEEvlm&bctid=4815779906001'],'extract'=>['@link\\.brightcove\\.com/services/player/bcpid(?\'bcpid\'\\d+).*?bckey=(?\'bckey\'[-,~\\w]+).*?bctid=(?\'bctid\'\\d+)@','@players\\.brightcove\\.net/(?\'bcpid\'\\d+)/.*?videoId=(?\'bctid\'\\d+)@'],'homepage'=>'https://www.brightcove.com/','host'=>['link.brightcove.com','players.brightcove.net'],'iframe'=>['src'=>'https://<xsl:choose><xsl:when test="@bckey">link.brightcove.com/services/player/bcpid<xsl:value-of select="@bcpid"/>?bckey=<xsl:value-of select="@bckey"/>&amp;bctid=<xsl:value-of select="@bctid"/>&amp;secureConnections=true&amp;secureHTMLConnections=true&amp;autoStart=false&amp;height=360&amp;width=640</xsl:when><xsl:otherwise>players.brightcove.net/<xsl:value-of select="@bcpid"/>/default_default/index.html?videoId=<xsl:value-of select="@bctid"/></xsl:otherwise></xsl:choose>'],'name'=>'Brightcove','scrape'=>[],'tags'=>['videos']],
 		'bunny'=>['attributes'=>[],'example'=>'https://video.bunnycdn.com/play/759/eb1c4f77-0cda-46be-b47d-1118ad7c2ffe','extract'=>['@/(?:embed|play)/(?\'video_library_id\'\\d+)/(?\'video_id\'[-\\w]+)@'],'homepage'=>'https://bunny.net/stream/','host'=>['iframe.mediadelivery.net','video.bunnycdn.com'],'iframe'=>['src'=>'https://iframe.mediadelivery.net/embed/{@video_library_id}/{@video_id}?autoplay=false'],'name'=>'Bunny Stream','scrape'=>[],'tags'=>['videos']],
 		'captivate'=>['attributes'=>[],'example'=>['https://player.captivate.fm/episode/03f47eef-4a8f-4616-8922-c77cb3d1edfa','https://decoding-the-gurus.captivate.fm/episode/sam-harris'],'extract'=>['@//player\\.captivate\\.fm/episode/(?\'id\'[-\\w]+)(?:\\?t=(?\'t\'\\d+))?@'],'homepage'=>'https://www.captivate.fm/','host'=>['captivate.fm'],'iframe'=>['height'=>200,'max-width'=>900,'src'=>'https://player.captivate.fm/episode/{@id}?t={@t}','style'=>['border-radius'=>'6px'],'width'=>'100%'],'name'=>'Captivate','scrape'=>[['extract'=>['@//player\\.captivate\\.fm/episode/(?\'id\'[-\\w]+)@'],'match'=>['@//(?!player\\.)[-\\w]+\\.captivate\\.fm/episode/.@']]],'tags'=>['podcasts']],

diff --git a/src/Plugins/MediaEmbed/Configurator/SiteHelpers/BlueskyHelper.php b/src/Plugins/MediaEmbed/Configurator/SiteHelpers/BlueskyHelper.php
@@ -0,0 +1,37 @@
+<?php declare(strict_types=1);
+
+/**
+* @package   s9e\TextFormatter
+* @copyright Copyright (c) The s9e authors
+* @license   http://www.opensource.org/licenses/mit-license.php The MIT License
+*/
+namespace s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers;
+
+use s9e\RegexpBuilder\Builder;
+
+class BlueskyHelper extends AbstractConfigurableHostHelper
+{
+	protected Builder $builder;
+
+	public function addHosts(array $hosts): void
+	{
+		parent::addHosts($hosts);
+
+		if (!isset($this->builder))
+		{
+			$this->builder = new Builder;
+		}
+
+		$siteId = $this->getSiteId();
+		$hosts  = $this->getHosts();
+
+		$this->configurator->tags[$siteId]->attributes['embedder']->filterChain[0]->setRegexp(
+			'/^(?:[-\w]*\.)*' . $this->builder->build($hosts) . '$/'
+		);
+	}
+
+	protected function getSiteId(): string
+	{
+		return 'bluesky';
+	}
+}
diff --git a/src/Plugins/MediaEmbed/Configurator/sites/bluesky.xml b/src/Plugins/MediaEmbed/Configurator/sites/bluesky.xml
@@ -0,0 +1,35 @@
+<site name="Bluesky" homepage="https://bsky.app/" helper="s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers\BlueskyHelper">
+	<source>https://embed.bsky.app/</source>
+	<example>https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v</example>
+	<example>https://bsky.app/profile/bnewbold.net/post/3kxjq2auebs2f</example>
+	<!-- https://web.syu.is/profile/syui.syu.is/post/3krfuqkpfns27 -->
+
+	<tags><tag>social</tag></tags>
+
+	<attributes>
+		<embedder required="true">
+			<filterChain>#regexp(/^(?:[-\w]*\.)*bsky\.app$/)</filterChain>
+		</embedder>
+		<url required="true">
+			<filterChain>urldecode</filterChain>
+			<filterChain>#regexp(/^at:\/\/[.:\w]+\/[.\w]+\/\w+$/)</filterChain>
+		</url>
+	</attributes>
+
+	<!-- https://atproto.com/specs/at-uri-scheme -->
+	<host>bsky.app</host>
+	<extract>#https://(?'embedder'[.\w]+)/oembed.*?url=(?'url'[\w%.]+)#</extract>
+	<scrape>
+		<match>#/profile/[^/]+/post/.#</match>
+		<extract>#https://(?'embedder'[.\w]+)/oembed.*?url=(?'url'[\w%.]+)#</extract>
+	</scrape>
+
+	<iframe width="600" height="600" onload="let c=new MessageChannel;c.port1.onmessage=e=&gt;this.style.height=e.data+'px';this.contentWindow.postMessage('s9e:init','*',[c.port2])" data-s9e-livepreview-ignore-attrs="style">
+		<src><![CDATA[
+			<xsl:text>https://s9e.github.io/iframe/2/bluesky.min.html#</xsl:text>
+			<xsl:value-of select="@url"/>
+			<xsl:text>#</xsl:text>
+			<xsl:value-of select="@embedder"/>
+		]]></src>
+	</iframe>
+</site>
diff --git a/tests/Plugins/MediaEmbed/Configurator/SiteHelpers/BlueskyHelperTest.php b/tests/Plugins/MediaEmbed/Configurator/SiteHelpers/BlueskyHelperTest.php
@@ -0,0 +1,64 @@
+<?php declare(strict_types=1);
+
+namespace s9e\TextFormatter\Tests\Plugins\MediaEmbed\Configurator\SiteHelpers;
+
+use s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers\BlueskyHelper;
+use s9e\TextFormatter\Tests\Test;
+
+/**
+* @covers s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers\AbstractConfigurableHostHelper
+* @covers s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers\AbstractSiteHelper
+* @covers s9e\TextFormatter\Plugins\MediaEmbed\Configurator\SiteHelpers\BlueskyHelper
+*/
+class BlueskyHelperTest extends Test
+{
+	/**
+	* @testdox addHost() normalizes the host
+	*/
+	public function testAddHostNormalize()
+	{
+		$this->configurator->MediaEmbed->add('bluesky');
+
+		$blueskyHelper = new BlueskyHelper($this->configurator);
+		$blueskyHelper->addHost('BLUESKY.LOCAL');
+
+		$parser   = $this->getParser();
+		$actual   = $parser->parse('https://embed.bluesky.local/oembed?format=json&url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v');
+		$expected = '<r><BLUESKY embedder="embed.bluesky.local" url="at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v">https://embed.bluesky.local/oembed?format=json&amp;url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v</BLUESKY></r>';
+
+		$this->assertXmlStringEqualsXmlString($expected, $actual);
+	}
+
+	/**
+	* @testdox addHost() adds the Bluesky media site if it's not enabled yet
+	*/
+	public function testAddHostCreate()
+	{
+		$blueskyHelper = new BlueskyHelper($this->configurator);
+		$blueskyHelper->addHost('BLUESKY.LOCAL');
+
+		$parser   = $this->getParser();
+		$actual   = $parser->parse('https://embed.bluesky.local/oembed?format=json&url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v');
+		$expected = '<r><BLUESKY embedder="embed.bluesky.local" url="at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v">https://embed.bluesky.local/oembed?format=json&amp;url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v</BLUESKY></r>';
+
+		$this->assertXmlStringEqualsXmlString($expected, $actual);
+	}
+
+	/**
+	* @testdox addHost() updates the embedded regexp
+	*/
+	public function testAddHostRegexp()
+	{
+		$blueskyHelper = new BlueskyHelper($this->configurator);
+		$blueskyHelper->addHost('BLUESKY.LOCAL');
+
+		$parser   = $this->getParser();
+		$actual   = $parser->parse('https://embed.bluesky.local/oembed?format=json&url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v');
+		$expected = '<r><BLUESKY embedder="embed.bluesky.local" url="at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v">https://embed.bluesky.local/oembed?format=json&amp;url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v</BLUESKY></r>';
+
+		$actual   = $parser->parse('https://embed.bluesky.local.evil/oembed?format=json&url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v');
+		$expected = '<t>https://embed.bluesky.local.evil/oembed?format=json&amp;url=at%3A%2F%2Fdid%3Aplc%3Az72i7hdynmk6r22z27h6tvur%2Fapp.bsky.feed.post%2F3kkrqzuydho2v</t>';
+
+		$this->assertXmlStringEqualsXmlString($expected, $actual);
+	}
+}
diff --git a/tests/Plugins/MediaEmbed/ParserTest.php b/tests/Plugins/MediaEmbed/ParserTest.php
@@ -567,6 +567,26 @@ function ($configurator)
 					$configurator->MediaEmbed->add('bandcamp');
 				}
 			],
+			[
+				'https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v',
+				'<r><BLUESKY embedder="embed.bsky.app" url="at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v">https://bsky.app/profile/bsky.app/post/3kkrqzuydho2v</BLUESKY></r>',
+				[],
+				function ($configurator)
+				{
+					$configurator->registeredVars['cacheDir'] = __DIR__ . '/../../.cache';
+					$configurator->MediaEmbed->add('bluesky');
+				}
+			],
+			[
+				'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur/post/3kkrqzuydho2v',
+				'<r><BLUESKY embedder="embed.bsky.app" url="at://did:plc:z72i7hdynmk6r22z27h6tvur/app.bsky.feed.post/3kkrqzuydho2v">https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur/post/3kkrqzuydho2v</BLUESKY></r>',
+				[],
+				function ($configurator)
+				{
+					$configurator->registeredVars['cacheDir'] = __DIR__ . '/../../.cache';
+					$configurator->MediaEmbed->add('bluesky');
+				}
+			],
 			[
 				'https://decoding-the-gurus.captivate.fm/episode/sam-harris',
 				'<r><CAPTIVATE id="ec119d4f-acc4-464a-8976-1fafc3e2d23b">https://decoding-the-gurus.captivate.fm/episode/sam-harris</CAPTIVATE></r>',