Add estimated reading time for articles

com.woltlab.wcf/templates/articleContentHeaderTitle.tpl

@@ -18,6 +18,15 @@
 			<meta itemprop="datePublished" content="{$article->time|date:'c'}">
 		</li>
 
+		{if $articleContent->getReadingTime()}
+			<li>
+				{icon name='hourglass'}
+				<span>{lang minutes=$articleContent->getReadingTime()}wcf.page.readingTime{/lang}</span>
+				<meta itemprop="timeRequired" content="PT{$articleContent->getReadingTime()}M">
+				<meta itemprop="wordCount" content="{$articleContent->numberOfWords}">
+			</li>
+		{/if}
+
 		{if $article->hasLabels}
 			<li>
 				{icon name='tags'}

wcfsetup/install/files/acp/database/update_com.woltlab.wcf_6.3_step1.php

@@ -42,6 +42,9 @@
                 ->defaultValue(0),
             NotNullVarchar255DatabaseTableColumn::create('slug')
                 ->defaultValue(''),
+            IntDatabaseTableColumn::create('numberOfWords')
+                ->notNull()
+                ->defaultValue(0),
         ]),
     PartialDatabaseTable::create('wcf1_label_group')
         ->columns([

wcfsetup/install/files/lib/data/article/ArticleAction.class.php

@@ -35,6 +35,7 @@
 use wcf\system\user\object\watch\UserObjectWatchHandler;
 use wcf\system\version\VersionTracker;
 use wcf\system\WCF;
+use wcf\util\StringUtil;
 
 /**
  * Executes article related actions.
@@ -110,6 +111,7 @@ public function create()
                     'slug' => $content['slug'] ?? '',
                     'teaser' => $content['teaser'],
                     'content' => $content['content'],
+                    'numberOfWords' => StringUtil::countWords($content['content']),
                     'imageID' => $content['imageID'],
                     'teaserImageID' => $content['teaserImageID'],
                     'metaTitle' => $content['metaTitle'] ?? '',
@@ -210,6 +212,7 @@ public function update()
                             'slug' => $isRevert ? $articleContent->slug : ($content['slug'] ?? ''),
                             'teaser' => $content['teaser'],
                             'content' => $content['content'],
+                            'numberOfWords' => StringUtil::countWords($content['content']),
                             'imageID' => ($isRevert) ? $articleContent->imageID : $content['imageID'],
                             'teaserImageID' => ($isRevert) ? $articleContent->teaserImageID : $content['teaserImageID'],
                             'metaTitle' => $content['metaTitle'] ?? '',
@@ -244,6 +247,7 @@ public function update()
                             'slug' => $isRevert ? '' : ($content['slug'] ?? ''),
                             'teaser' => $content['teaser'],
                             'content' => $content['content'],
+                            'numberOfWords' => StringUtil::countWords($content['content']),
                             'imageID' => ($isRevert) ? null : $content['imageID'],
                             'teaserImageID' => ($isRevert) ? null : $content['teaserImageID'],
                             'metaTitle' => $content['metaTitle'] ?? '',

wcfsetup/install/files/lib/data/article/content/ArticleContent.class.php

@@ -40,6 +40,7 @@
  * @property-read   string  $metaDescription    meta description of the article
  * @property-read   int     $comments           number of comments
  * @property-read   int     $attachments        number of attachments
+ * @property-read   int     $numberOfWords      number of words in the content
  *
  * @extends CollectionDatabaseObject<ArticleContentCollection>
  */
@@ -281,6 +282,16 @@ public static function getArticleContent(int $articleID, ?int $languageID): ?Art
         return null;
     }
 
+    /**
+     * Returns the estimated reading time in minutes.
+     *
+     * @since 6.3
+     */
+    public function getReadingTime(): int
+    {
+        return (int)\ceil($this->numberOfWords / 200);
+    }
+
     /**
      * @since 6.3
      */

wcfsetup/install/files/lib/data/article/content/ArticleContentBuilder.class.php

@@ -9,6 +9,7 @@
 use wcf\system\language\LanguageFactory;
 use wcf\system\message\embedded\object\MessageEmbeddedObjectManager;
 use wcf\system\tagging\TagEngine;
+use wcf\util\StringUtil;
 
 /**
  * Builder for creating and updating article contents.
@@ -69,6 +70,14 @@ public function setTeaser(string $teaser): static
     public function setContent(string $content): static
     {
         $this->properties['content'] = $content;
+        $this->setNumberOfWords(StringUtil::countWords($content));
+
+        return $this;
+    }
+
+    public function setNumberOfWords(int $numberOfWords): static
+    {
+        $this->properties['numberOfWords'] = $numberOfWords;
 
         return $this;
     }

wcfsetup/install/files/lib/system/importer/ArticleImporter.class.php

@@ -9,6 +9,7 @@
 use wcf\system\language\LanguageFactory;
 use wcf\system\tagging\TagEngine;
 use wcf\system\WCF;
+use wcf\util\StringUtil;
 
 /**
  * Imports cms articles.
@@ -110,6 +111,7 @@ public function import(mixed $oldID, array $data, array $additionalData = [])
                 'title' => $contentData['title'],
                 'teaser' => $contentData['teaser'],
                 'content' => $contentData['content'],
+                'numberOfWords' => StringUtil::countWords($contentData['content']),
                 'imageID' => $contentData['imageID'],
                 'teaserImageID' => $contentData['teaserImageID'],
                 'metaTitle' => $contentData['metaTitle'],

wcfsetup/install/files/lib/system/worker/ArticleRebuildDataWorker.class.php

@@ -13,6 +13,7 @@
 use wcf\system\message\embedded\object\MessageEmbeddedObjectManager;
 use wcf\system\search\SearchIndexManager;
 use wcf\system\WCF;
+use wcf\util\StringUtil;
 
 /**
  * Worker implementation for updating articles.
@@ -128,6 +129,9 @@ public function execute()
             $attachmentStatement->execute([$attachmentObjectType->objectTypeID, $articleContent->articleContentID]);
             $builder->setAttachments($attachmentStatement->fetchSingleColumn());
 
+            // count words
+            $builder->setNumberOfWords(StringUtil::countWords($articleContent->content ?? ''));
+
             $builder->update();
         }
 

wcfsetup/install/files/lib/util/StringUtil.class.php

@@ -484,6 +484,21 @@ public static function stripHTML(string $string): string
         );
     }
 
+    /**
+     * Returns the number of words in the given HTML. Tags are treated as word
+     * boundaries and words may contain letters of any script.
+     *
+     * @since 6.3
+     */
+    public static function countWords(string $html): int
+    {
+        $text = \preg_replace('~<!--.*?-->~s', '', $html);
+        $text = \preg_replace('/<\/?[a-zA-Z](?:[^>"\']+|"[^"]*"|\'[^\']*\')*+>/', ' ', $text);
+        $text = \html_entity_decode($text, \ENT_QUOTES | \ENT_HTML5, 'UTF-8');
+
+        return \preg_match_all('~[\p{L}\p{N}\p{M}]+(?:[\'\x{2019}-][\p{L}\p{N}\p{M}]+)*~u', $text);
+    }
+
     /**
      * Returns false if the given word is forbidden by given word filter.
      */

wcfsetup/setup/db/install_com.woltlab.wcf.php

@@ -479,6 +479,9 @@
             SmallintDatabaseTableColumn::create('attachments')
                 ->notNull()
                 ->defaultValue(0),
+            IntDatabaseTableColumn::create('numberOfWords')
+                ->notNull()
+                ->defaultValue(0),
         ])
         ->indices([
             DatabaseTablePrimaryIndex::create()