From 8d13db12ff16c59bf5a8ee948b850697da052e9f Mon Sep 17 00:00:00 2001
From: George Baev <geobaev@gmail.com>
Date: Wed, 26 Jan 2022 08:41:06 +0200
Subject: [PATCH 1/2] WS2-1205: Add webspark_cas module.

---
 README.md                                     | 13 +++++
 src/EventSubscriber/WebSparkCasSubscriber.php | 52 +++++++++++++++++++
 webspark_cas.info.yml                         |  8 +++
 webspark_cas.services.yml                     |  6 +++
 4 files changed, 79 insertions(+)
 create mode 100644 README.md
 create mode 100644 src/EventSubscriber/WebSparkCasSubscriber.php
 create mode 100644 webspark_cas.info.yml
 create mode 100644 webspark_cas.services.yml

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..4819bd6
--- /dev/null
+++ b/README.md
@@ -0,0 +1,13 @@
+# WebSpark module
+
+The WebSpark CAS module contains functionality which allows the Elastic Crawler to bypass the CAS redirect and process the web pages successfully.
+
+## Setup
+
+The following setting should be added to the `settings.php` file. If no such setting exists, the default setting will be used.
+
+```php
+$settings['webspark_cas_elastic_crawler_regex'] = '/^Elastic-Crawler .*$/';
+```
+
+This setting describes the RegExp used to determine the `Elastic Crawler` request based on its `User-Agent` HTTP Header value.
diff --git a/src/EventSubscriber/WebSparkCasSubscriber.php b/src/EventSubscriber/WebSparkCasSubscriber.php
new file mode 100644
index 0000000..4279afc
--- /dev/null
+++ b/src/EventSubscriber/WebSparkCasSubscriber.php
@@ -0,0 +1,52 @@
+<?php
+
+namespace Drupal\webspark_cas\EventSubscriber;
+
+use Drupal\cas\Subscriber\CasSubscriber;
+use Symfony\Component\HttpKernel\Event\GetResponseEvent;
+use Drupal\Core\Site\Settings;
+
+/**
+ * WebSpark CAS event subscriber.
+ */
+class WebSparkCasSubscriber extends CasSubscriber {
+
+  /**
+   * {@inheritdoc}
+   */
+  public function handle(GetResponseEvent $event) {
+    if ($this->isElasticCrawlerRequest()) {
+      return;
+    }
+
+    return parent::handle($event);
+  }
+
+  /**
+   * Checks if it is Elastic Crawler request.
+   *
+   * @return bool
+   *   The check result.
+   */
+  protected function isElasticCrawlerRequest(): bool {
+    $current_request = $this->requestStack->getCurrentRequest();
+
+    $defaultPattern = '/^Elastic-Crawler .*$/';
+
+    // Get the regex from $settings if available.
+    $elasticPattern = Settings::get('webspark_cas_elastic_crawler_regex', $defaultPattern);
+
+    $agent = $current_request->server->get('HTTP_USER_AGENT');
+    if (empty($agent)) {
+      return FALSE;
+    }
+
+    if (\preg_match($elasticPattern, $agent)) {
+      // Allow the Elastic crawler.
+      return TRUE;
+    }
+
+    return FALSE;
+  }
+
+}
diff --git a/webspark_cas.info.yml b/webspark_cas.info.yml
new file mode 100644
index 0000000..f07d5b1
--- /dev/null
+++ b/webspark_cas.info.yml
@@ -0,0 +1,8 @@
+name: WebSpark CAS
+type: module
+description: WebSpark CAS
+package: WebSpark
+core: 8.x
+core_version_requirement: ^8 || ^9
+dependencies:
+  - cas:cas
diff --git a/webspark_cas.services.yml b/webspark_cas.services.yml
new file mode 100644
index 0000000..a4795e3
--- /dev/null
+++ b/webspark_cas.services.yml
@@ -0,0 +1,6 @@
+services:
+  cas.subscriber:
+    class: Drupal\webspark_cas\EventSubscriber\WebSparkCasSubscriber
+    arguments: ['@request_stack', '@current_route_match', '@config.factory',  '@current_user', '@plugin.manager.condition', '@cas.helper', '@cas.redirector']
+    tags:
+      - { name: event_subscriber }

From 571d77b94a2ca4b63decf975a0ec8f4b0811dcd2 Mon Sep 17 00:00:00 2001
From: George Baev <georgebaev@users.noreply.github.com>
Date: Wed, 26 Jan 2022 15:52:23 +0200
Subject: [PATCH 2/2] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 4819bd6..9500f0b 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# WebSpark module
+# WebSpark CAS module
 
 The WebSpark CAS module contains functionality which allows the Elastic Crawler to bypass the CAS redirect and process the web pages successfully.