Split different scanners in separate classes (#165)

* Split different scanners in separate classes

* fix unit tests

* fix phpstan errors

* Improve BaseUrlScanner

* Use addCommands to fix compatibility with symfony 8

* Update README

Author: Gared

README.md

@@ -7,14 +7,15 @@ What is this tool doing?
 * Check the API version (pad.example.com/api)
 * Check the etherpad version
 * Check if the pads are publicly accessible
+* Check if websocket is working
 * Check if the server is healthy (pad.example.com/health)
 * Check if the admin area is accessible with default credentials (pad.example.com/admin)
 * Check if any (frontend) plugins are installed
 * Check if the server is running since a long time (pad.example.com/stats)
 
 ## Try it out
 
-You can try this tool out on the https://scanner.etherpad.org which is using this library.
+You can try this tool out on https://scanner.etherpad.org/instances which is using this library.
 
 ## Requirements
 

bin/console.php

@@ -12,9 +12,11 @@
 require __DIR__ . '/../vendor/autoload.php';
 
 $application = new Application();
-$application->add(new ScanCommand());
-$application->add(new GenerateRevisionLookupCommand());
-$application->add(new GenerateFileHashesCommand());
-$application->add(new CheckFileHashesCommand());
-$application->add(new GenerateFileHashesAllVersionsCommand());
+$application->addCommands([
+    new ScanCommand(),
+    new GenerateRevisionLookupCommand(),
+    new GenerateFileHashesCommand(),
+    new CheckFileHashesCommand(),
+    new GenerateFileHashesAllVersionsCommand(),
+]);
 $application->run();

composer.json

@@ -16,7 +16,7 @@
     "php": ">=8.3",
     "ext-json": "*",
     "guzzlehttp/guzzle": "^7.8",
-    "symfony/console": "^6.4|^7.0",
+    "symfony/console": "^6.4|^7.0|^8.0",
     "elephantio/elephant.io": "5.1.*"
   },
   "require-dev": {

composer.lock

@@ -2,3 +2,4 @@ parameters:
     level: 8
     paths:
         - src
+        - bin

phpstan.neon

@@ -5,8 +5,8 @@
 
 use Gared\EtherScan\Model\VersionRange;
 use Gared\EtherScan\Service\FileHashLookupService;
+use Gared\EtherScan\Service\StaticFileClient;
 use GuzzleHttp\Client;
-use GuzzleHttp\Exception\GuzzleException;
 use Symfony\Component\Console\Attribute\AsCommand;
 use Symfony\Component\Console\Command\Command;
 use Symfony\Component\Console\Input\InputArgument;
@@ -19,7 +19,7 @@
 )]
 class CheckFileHashesCommand extends Command
 {
-    protected function configure()
+    protected function configure(): void
     {
         $this
             ->addArgument('url', InputArgument::REQUIRED, 'Url to etherpad instance')
@@ -32,12 +32,13 @@ protected function execute(InputInterface $input, OutputInterface $output): int
         $version = $input->getArgument('version');
 
         $fileHashLookup = new FileHashLookupService();
+        $staticFileClient = new StaticFileClient(new Client());
 
         $files = FileHashLookupService::getFileNames();
 
         $versionRanges = [];
         foreach  ($files as $file) {
-            $fileHash = $this->getFileHash($url, $file);
+            $fileHash = $staticFileClient->getFileHash($url, $file);
             $versionRange = $fileHashLookup->getEtherpadVersionRange($file, $fileHash);
             if ($versionRange !== null) {
                 $versionRanges[] = $versionRange;
@@ -84,24 +85,4 @@ private function calculateVersion(array $versionRanges): VersionRange
 
         return new VersionRange($minVersion, $maxVersion);
     }
-
-    private function getFileHash(string $url, string $path): ?string
-    {
-        try {
-            $client = new Client([
-                'base_uri' => $url,
-                'timeout' => 5.0,
-                'verify' => false,
-            ]);
-            $response = $client->get($path, [
-                'headers' => ['Accept-Encoding' => 'gzip'],
-            ]);
-
-            $body = (string)$response->getBody();
-            return hash('md5', $body);
-        } catch (GuzzleException) {
-        }
-
-        return null;
-    }
 }

src/Console/CheckFileHashesCommand.php

@@ -4,8 +4,8 @@
 namespace Gared\EtherScan\Console;
 
 use Gared\EtherScan\Service\FileHashLookupService;
+use Gared\EtherScan\Service\StaticFileClient;
 use GuzzleHttp\Client;
-use GuzzleHttp\Exception\GuzzleException;
 use Symfony\Component\Console\Attribute\AsCommand;
 use Symfony\Component\Console\Command\Command;
 use Symfony\Component\Console\Input\InputArgument;
@@ -19,7 +19,7 @@
 )]
 class GenerateFileHashesCommand extends Command
 {
-    protected function configure()
+    protected function configure(): void
     {
         $this->addArgument('url', InputArgument::REQUIRED, 'Url to etherpad instance');
     }
@@ -29,13 +29,14 @@ protected function execute(InputInterface $input, OutputInterface $output): int
         $url = $input->getArgument('url');
 
         $fileHashLookup = new FileHashLookupService();
+        $staticFileClient = new StaticFileClient(new Client());
 
         $files = FileHashLookupService::getFileNames();
 
         $tableRows = [];
 
         foreach  ($files as $file) {
-            $fileHash = $this->getFileHash($url, $file);
+            $fileHash = $staticFileClient->getFileHash($url, $file);
             $versionRange = $fileHashLookup->getEtherpadVersionRange($file, $fileHash);
             $tableRows[] = [$file, $fileHash, $versionRange];
         }
@@ -45,25 +46,4 @@ protected function execute(InputInterface $input, OutputInterface $output): int
 
         return self::SUCCESS;
     }
-
-    private function getFileHash(string $url, string $path): ?string
-    {
-        try {
-            $client = new Client([
-                'base_uri' => $url,
-                'timeout' => 5.0,
-                'verify' => false,
-            ]);
-            $response = $client->get($path, [
-                'headers' => ['Accept-Encoding' => 'gzip'],
-            ]);
-
-            $body = (string)$response->getBody();
-            return hash('md5', $body);
-        } catch (GuzzleException $e) {
-            var_dump($e->getMessage());
-        }
-
-        return null;
-    }
 }

src/Console/GenerateFileHashesCommand.php

@@ -26,9 +26,12 @@ protected function execute(InputInterface $input, OutputInterface $output): int
     {
         $outputHelper = new ScanCommandOutputHelper(new SymfonyStyle($input, $output), $output);
 
-        $scanner = new ScannerService($input->getArgument('url'));
-        $scanner->scan($outputHelper);
+        $scanner = new ScannerService();
+        $scanner->scan(
+            url: $input->getArgument('url'),
+            callback: $outputHelper,
+        );
 
         return self::SUCCESS;
     }
-}
+}

src/Console/ScanCommand.php

@@ -5,7 +5,6 @@
 
 use DateTimeImmutable;
 use DateTimeInterface;
-use Exception;
 use Gared\EtherScan\Service\Scanner\Health\HealthResponseException;
 use Gared\EtherScan\Service\ScannerServiceCallbackInterface;
 use GuzzleHttp\Exception\GuzzleException;

src/Console/ScanCommandOutputHelper.php

@@ -0,0 +1,28 @@
+<?php
+
+namespace Gared\EtherScan\Model;
+
+class Config
+{
+    public readonly string $padId;
+    public ?string $pathPrefix = null;
+
+    public function __construct(
+        public string $baseUrl,
+        public readonly float $timeout = 5.0,
+    ) {
+        $domain = parse_url($this->baseUrl, PHP_URL_HOST);
+        if (is_string($domain) === false) {
+            $domain = $this->baseUrl;
+        }
+        $hash = $this->generateShortHash($domain);
+        $this->padId = 'test' . $hash;
+    }
+
+    private function generateShortHash(string $domain): string
+    {
+        $base64 = base64_encode(hash('sha256', $domain, true));
+        $hashStripped = str_replace(['+', '/'], '', $base64);
+        return substr($hashStripped, 0, 5);
+    }
+}