From 8811d3dd5eda9d92b6d398a6eb0f8ddd8a08a7b8 Mon Sep 17 00:00:00 2001
From: ThysTips <contact@antoinethys.com>
Date: Sat, 1 Feb 2025 15:25:32 +0100
Subject: [PATCH 1/4] build: Add php deployer

Signed-off-by: ThysTips <contact@antoinethys.com>
---
 deploy.php | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)
 create mode 100644 deploy.php

diff --git a/deploy.php b/deploy.php
new file mode 100644
index 0000000..827948f
--- /dev/null
+++ b/deploy.php
@@ -0,0 +1,39 @@
+<?php
+namespace Deployer;
+
+require 'recipe/symfony.php';
+// require 'contrib/webpack_encore.php';
+require 'contrib/npm.php';
+
+// Config
+set('nodejs_version', 'node_22.x');
+set('keep_releases', '3');
+set('repository', 'gitea@git.test.nestor-server.fr:Colgora/Mangarr.git');
+set('webpack_encore/env', 'production');
+set('composer_options', '--verbose --prefer-dist --no-progress --no-interaction --optimize-autoloader');
+
+set('shared_files', ['.env.local','var/log/prod.log']);
+set('shared_dirs', ['config/secrets','public/cbz','public/tmp','public/images']);
+// add('writable_dirs', []);
+
+desc('Runs webpack encore build');
+task('webpack_encore:build', function () {
+    run("cd {{release_path}} && npm run encore {{webpack_encore/env}}");
+});
+
+desc('Run messenger consume');
+task('messenger:consume', function () {
+    run("sudo supervisorctl restart messenger-consume:*");
+});
+
+host('mangarr.test.nestor-server.fr')
+    ->set('remote_user', 'colgora')
+    ->set('deploy_path', '/var/www/mangarr')
+    ->set('branch', 'main');
+
+// Hooks
+after('deploy:vendors', 'npm:install');
+after('npm:install', 'webpack_encore:build');
+after('deploy:vendors', 'database:migrate');
+after('deploy:symlink', 'messenger:consume');
+after('deploy:failed', 'deploy:unlock');

From d4142012ec9b25ad47862c74b1c115989bc69237 Mon Sep 17 00:00:00 2001
From: ThysTips <contact@antoinethys.com>
Date: Sat, 1 Feb 2025 17:02:55 +0100
Subject: [PATCH 2/4] fix: npm deployment script

Signed-off-by: ThysTips <contact@antoinethys.com>
---
 deploy.php | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/deploy.php b/deploy.php
index 827948f..f6ceaa8 100644
--- a/deploy.php
+++ b/deploy.php
@@ -18,7 +18,7 @@ set('shared_dirs', ['config/secrets','public/cbz','public/tmp','public/images'])
 
 desc('Runs webpack encore build');
 task('webpack_encore:build', function () {
-    run("cd {{release_path}} && npm run encore {{webpack_encore/env}}");
+    run("cd {{release_path}} && npm run build");
 });
 
 desc('Run messenger consume');

From 0e3d72cc5e0dd06ff9ee2d1db6bab593408d070d Mon Sep 17 00:00:00 2001
From: "ext.jeremy.guillot@maxicoffee.domains" <j.guillot_ext@maxicoffee.com>
Date: Fri, 31 Jan 2025 19:23:02 +0100
Subject: [PATCH 3/4] feat: debut rerefonte DDD CQRS

---
 compose.yaml                                  |  2 +-
 .../Application/Command/ScrapeChapter.php     | 11 +++
 .../CommandHandler/ScrapeChapterHandler.php   | 31 +++++++
 .../ScrapingJobRepositoryInterface.php        | 12 +++
 .../Contract/Service/ScraperInterface.php     | 12 +++
 .../Domain/Event/ChapterScrapingCompleted.php | 21 +++++
 .../Domain/Event/ChapterScrapingStarted.php   | 15 ++++
 .../Domain/Event/PageScrapingProgressed.php   | 23 +++++
 .../Scraping/Domain/Model/ScrapingJob.php     | 84 +++++++++++++++++++
 .../Domain/Model/ScrapingProgress.php         | 19 +++++
 .../Scraping/Domain/Model/ScrapingStatus.php  | 11 +++
 .../Domain/Model/ValueObject/ImageUrl.php     | 24 ++++++
 .../Domain/Model/ValueObject/PageNumber.php   | 24 ++++++
 .../DoctrineScrapingJobRepository.php         | 51 +++++++++++
 .../Persistence/Entity/ScrapingJobEntity.php  | 83 ++++++++++++++++++
 .../Service/Scraper/HtmlScraper.php           | 61 ++++++++++++++
 16 files changed, 483 insertions(+), 1 deletion(-)
 create mode 100644 src/Domain/Scraping/Application/Command/ScrapeChapter.php
 create mode 100644 src/Domain/Scraping/Application/CommandHandler/ScrapeChapterHandler.php
 create mode 100644 src/Domain/Scraping/Domain/Contract/Repository/ScrapingJobRepositoryInterface.php
 create mode 100644 src/Domain/Scraping/Domain/Contract/Service/ScraperInterface.php
 create mode 100644 src/Domain/Scraping/Domain/Event/ChapterScrapingCompleted.php
 create mode 100644 src/Domain/Scraping/Domain/Event/ChapterScrapingStarted.php
 create mode 100644 src/Domain/Scraping/Domain/Event/PageScrapingProgressed.php
 create mode 100644 src/Domain/Scraping/Domain/Model/ScrapingJob.php
 create mode 100644 src/Domain/Scraping/Domain/Model/ScrapingProgress.php
 create mode 100644 src/Domain/Scraping/Domain/Model/ScrapingStatus.php
 create mode 100644 src/Domain/Scraping/Domain/Model/ValueObject/ImageUrl.php
 create mode 100644 src/Domain/Scraping/Domain/Model/ValueObject/PageNumber.php
 create mode 100644 src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
 create mode 100644 src/Domain/Scraping/Infrastructure/Persistence/Entity/ScrapingJobEntity.php
 create mode 100644 src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php

diff --git a/compose.yaml b/compose.yaml
index f5e815a..d109c66 100644
--- a/compose.yaml
+++ b/compose.yaml
@@ -25,7 +25,7 @@ services:
     ports:
       # HTTP
       - target: 80
-        published: ${HTTP_PORT:-80}
+        published: ${HTTP_PORT:-8081}
         protocol: tcp
       # HTTPS
       - target: 443
diff --git a/src/Domain/Scraping/Application/Command/ScrapeChapter.php b/src/Domain/Scraping/Application/Command/ScrapeChapter.php
new file mode 100644
index 0000000..6c44853
--- /dev/null
+++ b/src/Domain/Scraping/Application/Command/ScrapeChapter.php
@@ -0,0 +1,11 @@
+<?php
+
+namespace App\Domain\Scraping\Application\Command\ScrapeChapter;
+
+class ScrapeChapterCommand
+{
+    public function __construct(
+        public readonly string $chapterId,
+        public readonly string $sourceId
+    ) {}
+}
diff --git a/src/Domain/Scraping/Application/CommandHandler/ScrapeChapterHandler.php b/src/Domain/Scraping/Application/CommandHandler/ScrapeChapterHandler.php
new file mode 100644
index 0000000..38adbd3
--- /dev/null
+++ b/src/Domain/Scraping/Application/CommandHandler/ScrapeChapterHandler.php
@@ -0,0 +1,31 @@
+<?php
+
+namespace App\Domain\Scraping\Application\Command\ScrapeChapter;
+
+use App\Domain\Scraping\Domain\Contract\ScraperInterface;
+use App\Domain\Scraping\Domain\Repository\ScrapingJobRepositoryInterface;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingStarted;
+use Symfony\Component\Messenger\MessageBusInterface;
+
+class ScrapeChapterHandler
+{
+    public function __construct(
+        private readonly ScraperInterface $scraper,
+        private readonly ScrapingJobRepositoryInterface $scrapingJobRepository,
+        private readonly MessageBusInterface $eventBus
+    ) {}
+
+    public function handle(ScrapeChapterCommand $command): void
+    {
+        $job = $this->scraper->createScrapingJob(
+            $command->chapterId,
+            $command->sourceId
+        );
+        
+        $this->scrapingJobRepository->save($job);
+        
+        $this->eventBus->dispatch(new ChapterScrapingStarted($job->getId()));
+        
+        $this->scraper->scrape($job);
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Contract/Repository/ScrapingJobRepositoryInterface.php b/src/Domain/Scraping/Domain/Contract/Repository/ScrapingJobRepositoryInterface.php
new file mode 100644
index 0000000..194e847
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Contract/Repository/ScrapingJobRepositoryInterface.php
@@ -0,0 +1,12 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Repository;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+
+interface ScrapingJobRepositoryInterface
+{
+    public function save(ScrapingJob $job): void;
+    public function findById(string $id): ?ScrapingJob;
+    public function findByChapterId(string $chapterId): ?ScrapingJob;
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Contract/Service/ScraperInterface.php b/src/Domain/Scraping/Domain/Contract/Service/ScraperInterface.php
new file mode 100644
index 0000000..be898a7
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Contract/Service/ScraperInterface.php
@@ -0,0 +1,12 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Contract;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+
+interface ScraperInterface
+{
+    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob;
+    public function scrape(ScrapingJob $job): void;
+    public function supports(string $sourceType): bool;
+}
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Event/ChapterScrapingCompleted.php b/src/Domain/Scraping/Domain/Event/ChapterScrapingCompleted.php
new file mode 100644
index 0000000..199a248
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Event/ChapterScrapingCompleted.php
@@ -0,0 +1,21 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Event;
+
+class ChapterScrapingCompleted
+{
+    public function __construct(
+        private readonly string $jobId,
+        private readonly array $scrapedPages
+    ) {}
+
+    public function getJobId(): string
+    {
+        return $this->jobId;
+    }
+
+    public function getScrapedPages(): array
+    {
+        return $this->scrapedPages;
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Event/ChapterScrapingStarted.php b/src/Domain/Scraping/Domain/Event/ChapterScrapingStarted.php
new file mode 100644
index 0000000..2549442
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Event/ChapterScrapingStarted.php
@@ -0,0 +1,15 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Event;
+
+class ChapterScrapingStarted
+{
+    public function __construct(
+        private readonly string $jobId
+    ) {}
+
+    public function getJobId(): string
+    {
+        return $this->jobId;
+    }
+}
diff --git a/src/Domain/Scraping/Domain/Event/PageScrapingProgressed.php b/src/Domain/Scraping/Domain/Event/PageScrapingProgressed.php
new file mode 100644
index 0000000..0f4e6c0
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Event/PageScrapingProgressed.php
@@ -0,0 +1,23 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Event;
+
+use App\Domain\Scraping\Domain\Model\ScrapingProgress;
+
+class PageScrapingProgressed
+{
+    public function __construct(
+        private readonly string $jobId,
+        private readonly ScrapingProgress $progress
+    ) {}
+
+    public function getJobId(): string
+    {
+        return $this->jobId;
+    }
+
+    public function getProgress(): ScrapingProgress
+    {
+        return $this->progress;
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Model/ScrapingJob.php b/src/Domain/Scraping/Domain/Model/ScrapingJob.php
new file mode 100644
index 0000000..5361c7f
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Model/ScrapingJob.php
@@ -0,0 +1,84 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Model;
+
+use App\Domain\Scraping\Domain\Model\ValueObject\ImageUrl;
+use App\Domain\Scraping\Domain\Model\ValueObject\PageNumber;
+
+class ScrapingJob
+{
+    private array $pages = [];
+    private ScrapingStatus $status;
+    private \DateTimeImmutable $createdAt;
+    private ?\DateTimeImmutable $completedAt = null;
+
+    public function __construct(
+        private readonly string $id,
+        private readonly string $chapterId,
+        private readonly string $mangaId,
+        private readonly string $sourceId
+    ) {
+        $this->status = ScrapingStatus::PENDING;
+        $this->createdAt = new \DateTimeImmutable();
+    }
+
+    public function addPage(PageNumber $pageNumber, ImageUrl $imageUrl): void
+    {
+        $this->pages[$pageNumber->getValue()] = $imageUrl->getValue();
+        if ($this->status === ScrapingStatus::PENDING) {
+            $this->status = ScrapingStatus::IN_PROGRESS;
+        }
+    }
+
+    public function complete(): void
+    {
+        $this->status = ScrapingStatus::COMPLETED;
+        $this->completedAt = new \DateTimeImmutable();
+    }
+
+    public function fail(): void
+    {
+        $this->status = ScrapingStatus::FAILED;
+        $this->completedAt = new \DateTimeImmutable();
+    }
+
+    public function getId(): string
+    {
+        return $this->id;
+    }
+
+    public function getChapterId(): string
+    {
+        return $this->chapterId;
+    }
+
+    public function getMangaId(): string
+    {
+        return $this->mangaId;
+    }
+
+    public function getSourceId(): string
+    {
+        return $this->sourceId;
+    }
+
+    public function getPages(): array
+    {
+        return $this->pages;
+    }
+
+    public function getStatus(): ScrapingStatus
+    {
+        return $this->status;
+    }
+
+    public function getCreatedAt(): \DateTimeImmutable
+    {
+        return $this->createdAt;
+    }
+
+    public function getCompletedAt(): ?\DateTimeImmutable
+    {
+        return $this->completedAt;
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Model/ScrapingProgress.php b/src/Domain/Scraping/Domain/Model/ScrapingProgress.php
new file mode 100644
index 0000000..b5861b3
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Model/ScrapingProgress.php
@@ -0,0 +1,19 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Model;
+
+class ScrapingProgress
+{
+    public function __construct(
+        private readonly int $pagesScraped,
+        private readonly int $totalPages
+    ) {}
+
+    public function getPercentage(): float
+    {
+        if ($this->totalPages === 0) {
+            return 0;
+        }
+        return ($this->pagesScraped / $this->totalPages) * 100;
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Model/ScrapingStatus.php b/src/Domain/Scraping/Domain/Model/ScrapingStatus.php
new file mode 100644
index 0000000..1d88c84
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Model/ScrapingStatus.php
@@ -0,0 +1,11 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Model;
+
+enum ScrapingStatus: string
+{
+    case PENDING = 'pending';
+    case IN_PROGRESS = 'in_progress';
+    case COMPLETED = 'completed';
+    case FAILED = 'failed';
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Model/ValueObject/ImageUrl.php b/src/Domain/Scraping/Domain/Model/ValueObject/ImageUrl.php
new file mode 100644
index 0000000..1f5f5ef
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Model/ValueObject/ImageUrl.php
@@ -0,0 +1,24 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Model\ValueObject;
+
+class ImageUrl
+{
+    public function __construct(
+        private readonly string $url
+    ) {
+        if (!filter_var($url, FILTER_VALIDATE_URL)) {
+            throw new \InvalidArgumentException('Invalid image URL provided');
+        }
+    }
+
+    public function getValue(): string
+    {
+        return $this->url;
+    }
+
+    public function getExtension(): string
+    {
+        return pathinfo(parse_url($this->url, PHP_URL_PATH), PATHINFO_EXTENSION);
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Domain/Model/ValueObject/PageNumber.php b/src/Domain/Scraping/Domain/Model/ValueObject/PageNumber.php
new file mode 100644
index 0000000..5c0fa9d
--- /dev/null
+++ b/src/Domain/Scraping/Domain/Model/ValueObject/PageNumber.php
@@ -0,0 +1,24 @@
+<?php
+
+namespace App\Domain\Scraping\Domain\Model\ValueObject;
+
+class PageNumber
+{
+    public function __construct(
+        private readonly int $number
+    ) {
+        if ($number < 1) {
+            throw new \InvalidArgumentException('Page number must be greater than 0');
+        }
+    }
+
+    public function getValue(): int
+    {
+        return $this->number;
+    }
+
+    public function getFormattedNumber(): string
+    {
+        return sprintf('%03d', $this->number);
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php b/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
new file mode 100644
index 0000000..20ee0b1
--- /dev/null
+++ b/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
@@ -0,0 +1,51 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Persistence;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Repository\ScrapingJobRepositoryInterface;
+use Doctrine\ORM\EntityManagerInterface;
+
+class DoctrineScrapingJobRepository implements ScrapingJobRepositoryInterface
+{
+    public function __construct(
+        private readonly EntityManagerInterface $entityManager
+    ) {}
+
+    public function save(ScrapingJob $job): void
+    {
+        $this->entityManager->persist($job);
+        $this->entityManager->flush();
+    }
+
+    public function findById(string $id): ?ScrapingJob
+    {
+        return $this->entityManager->getRepository(ScrapingJob::class)->find($id);
+    }
+
+    public function findByChapterId(string $chapterId): ?ScrapingJob
+    {
+        return $this->entityManager->getRepository(ScrapingJob::class)
+            ->findOneBy(['chapterId' => $chapterId]);
+    }
+
+    public function findPendingJobs(): array
+    {
+        return $this->entityManager->getRepository(ScrapingJob::class)
+            ->createQueryBuilder('sj')
+            ->where('sj.status = :status')
+            ->setParameter('status', 'pending')
+            ->getQuery()
+            ->getResult();
+    }
+
+    public function findInProgressJobs(): array
+    {
+        return $this->entityManager->getRepository(ScrapingJob::class)
+            ->createQueryBuilder('sj')
+            ->where('sj.status = :status')
+            ->setParameter('status', 'in_progress')
+            ->getQuery()
+            ->getResult();
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Persistence/Entity/ScrapingJobEntity.php b/src/Domain/Scraping/Infrastructure/Persistence/Entity/ScrapingJobEntity.php
new file mode 100644
index 0000000..6ed1e07
--- /dev/null
+++ b/src/Domain/Scraping/Infrastructure/Persistence/Entity/ScrapingJobEntity.php
@@ -0,0 +1,83 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Persistence\Entity;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Model\ScrapingStatus;
+use Doctrine\ORM\Mapping as ORM;
+
+#[ORM\Entity]
+#[ORM\Table(name: 'scraping_jobs')]
+class ScrapingJobEntity
+{
+    #[ORM\Id]
+    #[ORM\Column(type: 'string', length: 36)]
+    private string $id;
+
+    #[ORM\Column(type: 'string')]
+    private string $chapterId;
+
+    #[ORM\Column(type: 'string')]
+    private string $mangaId;
+
+    #[ORM\Column(type: 'string')]
+    private string $sourceId;
+
+    #[ORM\Column(type: 'json')]
+    private array $pages = [];
+
+    #[ORM\Column(type: 'string')]
+    private string $status;
+
+    #[ORM\Column(type: 'datetime_immutable')]
+    private \DateTimeImmutable $createdAt;
+
+    #[ORM\Column(type: 'datetime_immutable', nullable: true)]
+    private ?\DateTimeImmutable $completedAt = null;
+
+    public static function fromDomain(ScrapingJob $job): self
+    {
+        $entity = new self();
+        $entity->id = $job->getId();
+        $entity->chapterId = $job->getChapterId();
+        $entity->mangaId = $job->getMangaId();
+        $entity->sourceId = $job->getSourceId();
+        $entity->pages = $job->getPages();
+        $entity->status = $job->getStatus()->value;
+        $entity->createdAt = $job->getCreatedAt();
+        $entity->completedAt = $job->getCompletedAt();
+        
+        return $entity;
+    }
+
+    public function toDomain(): ScrapingJob
+    {
+        $job = new ScrapingJob(
+            $this->id,
+            $this->chapterId,
+            $this->mangaId,
+            $this->sourceId
+        );
+
+        // Reconstruire l'état du job à partir des données persistées
+        $reflection = new \ReflectionClass(ScrapingJob::class);
+        
+        $pagesProperty = $reflection->getProperty('pages');
+        $pagesProperty->setAccessible(true);
+        $pagesProperty->setValue($job, $this->pages);
+        
+        $statusProperty = $reflection->getProperty('status');
+        $statusProperty->setAccessible(true);
+        $statusProperty->setValue($job, ScrapingStatus::from($this->status));
+        
+        $createdAtProperty = $reflection->getProperty('createdAt');
+        $createdAtProperty->setAccessible(true);
+        $createdAtProperty->setValue($job, $this->createdAt);
+        
+        $completedAtProperty = $reflection->getProperty('completedAt');
+        $completedAtProperty->setAccessible(true);
+        $completedAtProperty->setValue($job, $this->completedAt);
+
+        return $job;
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php b/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
new file mode 100644
index 0000000..6939472
--- /dev/null
+++ b/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
@@ -0,0 +1,61 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
+
+use App\Domain\Scraping\Domain\Contract\ScraperInterface as ContractScraperInterface;
+use App\Domain\Scraping\Domain\Service\ScraperInterface;
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Model\ValueObject\ImageUrl;
+use App\Domain\Scraping\Domain\Model\ValueObject\PageNumber;
+use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
+use Symfony\Component\DomCrawler\Crawler;
+use Symfony\Component\EventDispatcher\EventDispatcherInterface;
+use Symfony\Contracts\HttpClient\HttpClientInterface;
+
+class HtmlScraper implements ContractScraperInterface
+{
+    public function __construct(
+        private readonly HttpClientInterface $httpClient,
+        private readonly EventDispatcherInterface $eventDispatcher
+    ) {}
+
+    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
+    {
+        return new ScrapingJob(
+            uniqid('scraping_'),
+            $chapterId,
+            $sourceId
+        );
+    }
+
+    public function scrape(ScrapingJob $job): void
+    {
+        $url = $this->buildUrl($job); // À implémenter selon votre logique
+        $response = $this->httpClient->request('GET', $url);
+        
+        $crawler = new Crawler($response->getContent());
+        $images = $crawler->filter('img.manga-page'); // Adapter selon le site cible
+        
+        $pageNumber = 1;
+        $images->each(function (Crawler $image) use ($job, $pageNumber) {
+            $imageUrl = new ImageUrl($image->attr('src'));
+            $job->addPage(new PageNumber($pageNumber), $imageUrl);
+            
+            $this->eventDispatcher->dispatch(
+                new PageScrapingProgressed($job->getId(), $job->getProgress())
+            );
+            
+            $pageNumber++;
+        });
+        
+        $this->eventDispatcher->dispatch(
+            new ChapterScrapingCompleted($job->getId(), $job->getPages())
+        );
+    }
+
+    public function supports(string $sourceType): bool
+    {
+        return $sourceType === 'html';
+    }
+} 
\ No newline at end of file

From 97d7bcf0614fdaf7616078ad081b90a57645e10b Mon Sep 17 00:00:00 2001
From: "ext.jeremy.guillot@maxicoffee.domains" <j.guillot_ext@maxicoffee.com>
Date: Sat, 1 Feb 2025 13:59:37 +0100
Subject: [PATCH 4/4] feat: suite du passage en DDD de Scraping

---
 .../DoctrineScrapingJobRepository.php         | 26 +++--
 .../Service/Scraper/AbstractScraper.php       | 94 +++++++++++++++++++
 .../Service/Scraper/HtmlScraper.php           | 76 +++++++--------
 .../Service/Scraper/JavascriptScraper.php     | 38 ++++++++
 4 files changed, 190 insertions(+), 44 deletions(-)
 create mode 100644 src/Domain/Scraping/Infrastructure/Service/Scraper/AbstractScraper.php
 create mode 100644 src/Domain/Scraping/Infrastructure/Service/Scraper/JavascriptScraper.php

diff --git a/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php b/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
index 20ee0b1..0b569f0 100644
--- a/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
+++ b/src/Domain/Scraping/Infrastructure/Persistence/DoctrineScrapingJobRepository.php
@@ -3,7 +3,9 @@
 namespace App\Domain\Scraping\Infrastructure\Persistence;
 
 use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Model\ScrapingStatus;
 use App\Domain\Scraping\Domain\Repository\ScrapingJobRepositoryInterface;
+use App\Domain\Scraping\Infrastructure\Persistence\Entity\ScrapingJobEntity;
 use Doctrine\ORM\EntityManagerInterface;
 
 class DoctrineScrapingJobRepository implements ScrapingJobRepositoryInterface
@@ -14,38 +16,48 @@ class DoctrineScrapingJobRepository implements ScrapingJobRepositoryInterface
 
     public function save(ScrapingJob $job): void
     {
-        $this->entityManager->persist($job);
+        $entity = ScrapingJobEntity::fromDomain($job);
+        $this->entityManager->persist($entity);
         $this->entityManager->flush();
     }
 
     public function findById(string $id): ?ScrapingJob
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)->find($id);
+        $entity = $this->entityManager->getRepository(ScrapingJobEntity::class)
+            ->find($id);
+
+        return $entity?->toDomain();
     }
 
     public function findByChapterId(string $chapterId): ?ScrapingJob
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entity = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->findOneBy(['chapterId' => $chapterId]);
+
+        return $entity?->toDomain();
     }
 
     public function findPendingJobs(): array
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entities = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->createQueryBuilder('sj')
             ->where('sj.status = :status')
-            ->setParameter('status', 'pending')
+            ->setParameter('status', ScrapingStatus::PENDING->value)
             ->getQuery()
             ->getResult();
+
+        return array_map(fn(ScrapingJobEntity $entity) => $entity->toDomain(), $entities);
     }
 
     public function findInProgressJobs(): array
     {
-        return $this->entityManager->getRepository(ScrapingJob::class)
+        $entities = $this->entityManager->getRepository(ScrapingJobEntity::class)
             ->createQueryBuilder('sj')
             ->where('sj.status = :status')
-            ->setParameter('status', 'in_progress')
+            ->setParameter('status', ScrapingStatus::IN_PROGRESS->value)
             ->getQuery()
             ->getResult();
+
+        return array_map(fn(ScrapingJobEntity $entity) => $entity->toDomain(), $entities);
     }
 } 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Service/Scraper/AbstractScraper.php b/src/Domain/Scraping/Infrastructure/Service/Scraper/AbstractScraper.php
new file mode 100644
index 0000000..75cef16
--- /dev/null
+++ b/src/Domain/Scraping/Infrastructure/Service/Scraper/AbstractScraper.php
@@ -0,0 +1,94 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
+
+use App\Domain\Scraping\Domain\Contract\ScraperInterface;
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
+use App\Domain\Scraping\Domain\Event\ChapterScrapingStarted;
+use App\Domain\Scraping\Domain\Model\ScrapingProgress;
+use Symfony\Component\EventDispatcher\EventDispatcherInterface;
+use Symfony\Contracts\HttpClient\HttpClientInterface;
+
+abstract class AbstractScraper implements ScraperInterface
+{
+    public function __construct(
+        protected readonly HttpClientInterface $httpClient,
+        protected readonly EventDispatcherInterface $eventDispatcher,
+        protected readonly string $tempDir
+    ) {}
+
+    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
+    {
+        return new ScrapingJob(
+            uniqid('scraping_'),
+            $chapterId,
+            $sourceId
+        );
+    }
+
+    public function scrape(ScrapingJob $job): void
+    {
+        try {
+            $this->eventDispatcher->dispatch(new ChapterScrapingStarted($job->getId()));
+            
+            $tempDir = $this->createTempDirectory($job);
+            $pageData = $this->scrapePages($job);
+            
+            foreach ($pageData as $page) {
+                $this->downloadPage($job, $page, $tempDir);
+            }
+            
+            $job->complete();
+            
+            $this->eventDispatcher->dispatch(
+                new ChapterScrapingCompleted($job->getId(), $job->getPages())
+            );
+            
+            $this->cleanupTempDirectory($tempDir);
+            
+        } catch (\Exception $e) {
+            $job->fail();
+            throw $e;
+        }
+    }
+
+    abstract protected function scrapePages(ScrapingJob $job): array;
+
+    protected function createTempDirectory(ScrapingJob $job): string
+    {
+        $tempDir = $this->tempDir . '/' . uniqid('scraping_' . $job->getId() . '_');
+        if (!mkdir($tempDir) && !is_dir($tempDir)) {
+            throw new \RuntimeException("Failed to create temporary directory: $tempDir");
+        }
+        return $tempDir;
+    }
+
+    protected function cleanupTempDirectory(string $tempDir): void
+    {
+        if (is_dir($tempDir)) {
+            $files = new \RecursiveIteratorIterator(
+                new \RecursiveDirectoryIterator($tempDir, \RecursiveDirectoryIterator::SKIP_DOTS),
+                \RecursiveIteratorIterator::CHILD_FIRST
+            );
+
+            foreach ($files as $file) {
+                if ($file->isDir()) {
+                    rmdir($file->getRealPath());
+                } else {
+                    unlink($file->getRealPath());
+                }
+            }
+            rmdir($tempDir);
+        }
+    }
+
+    protected function dispatchProgressEvent(ScrapingJob $job, int $current, int $total): void
+    {
+        $progress = new ScrapingProgress($current, $total);
+        $this->eventDispatcher->dispatch(
+            new PageScrapingProgressed($job->getId(), $progress)
+        );
+    }
+} 
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php b/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
index 6939472..385563c 100644
--- a/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
+++ b/src/Domain/Scraping/Infrastructure/Service/Scraper/HtmlScraper.php
@@ -2,60 +2,62 @@
 
 namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
 
-use App\Domain\Scraping\Domain\Contract\ScraperInterface as ContractScraperInterface;
-use App\Domain\Scraping\Domain\Service\ScraperInterface;
 use App\Domain\Scraping\Domain\Model\ScrapingJob;
 use App\Domain\Scraping\Domain\Model\ValueObject\ImageUrl;
 use App\Domain\Scraping\Domain\Model\ValueObject\PageNumber;
-use App\Domain\Scraping\Domain\Event\PageScrapingProgressed;
-use App\Domain\Scraping\Domain\Event\ChapterScrapingCompleted;
 use Symfony\Component\DomCrawler\Crawler;
-use Symfony\Component\EventDispatcher\EventDispatcherInterface;
-use Symfony\Contracts\HttpClient\HttpClientInterface;
 
-class HtmlScraper implements ContractScraperInterface
+class HtmlScraper extends AbstractScraper
 {
-    public function __construct(
-        private readonly HttpClientInterface $httpClient,
-        private readonly EventDispatcherInterface $eventDispatcher
-    ) {}
-
-    public function createScrapingJob(string $chapterId, string $sourceId): ScrapingJob
+    protected function scrapePages(ScrapingJob $job): array
     {
-        return new ScrapingJob(
-            uniqid('scraping_'),
-            $chapterId,
-            $sourceId
-        );
-    }
-
-    public function scrape(ScrapingJob $job): void
-    {
-        $url = $this->buildUrl($job); // À implémenter selon votre logique
+        $url = $this->buildUrl($job);
         $response = $this->httpClient->request('GET', $url);
         
         $crawler = new Crawler($response->getContent());
-        $images = $crawler->filter('img.manga-page'); // Adapter selon le site cible
+        $images = $crawler->filter('img.manga-page'); // Adapter selon le site
         
-        $pageNumber = 1;
-        $images->each(function (Crawler $image) use ($job, $pageNumber) {
-            $imageUrl = new ImageUrl($image->attr('src'));
-            $job->addPage(new PageNumber($pageNumber), $imageUrl);
-            
-            $this->eventDispatcher->dispatch(
-                new PageScrapingProgressed($job->getId(), $job->getProgress())
-            );
-            
-            $pageNumber++;
+        $pages = [];
+        $images->each(function (Crawler $image) use (&$pages) {
+            $pages[] = [
+                'url' => $image->attr('src'),
+                'number' => count($pages) + 1
+            ];
         });
         
-        $this->eventDispatcher->dispatch(
-            new ChapterScrapingCompleted($job->getId(), $job->getPages())
+        return $pages;
+    }
+
+    protected function downloadPage(ScrapingJob $job, array $page, string $tempDir): void
+    {
+        $imageUrl = new ImageUrl($page['url']);
+        $pageNumber = new PageNumber($page['number']);
+        
+        $fileName = sprintf('%s/%03d.%s', 
+            $tempDir,
+            $pageNumber->getValue(),
+            $imageUrl->getExtension()
         );
+        
+        $response = $this->httpClient->request('GET', $imageUrl->getValue());
+        file_put_contents($fileName, $response->getContent());
+        
+        $job->addPage($pageNumber, $imageUrl);
+        $this->dispatchProgressEvent($job, $page['number'], count($pages));
     }
 
     public function supports(string $sourceType): bool
     {
         return $sourceType === 'html';
     }
-} 
\ No newline at end of file
+
+    private function buildUrl(ScrapingJob $job): string
+    {
+        // À implémenter selon votre logique de construction d'URL
+        // Vous aurez probablement besoin d'injecter un service pour récupérer les informations du chapitre
+        return sprintf('https://example.com/manga/%s/chapter/%s', 
+            $job->getMangaId(), 
+            $job->getChapterId()
+        );
+    }
+}
\ No newline at end of file
diff --git a/src/Domain/Scraping/Infrastructure/Service/Scraper/JavascriptScraper.php b/src/Domain/Scraping/Infrastructure/Service/Scraper/JavascriptScraper.php
new file mode 100644
index 0000000..69dedc7
--- /dev/null
+++ b/src/Domain/Scraping/Infrastructure/Service/Scraper/JavascriptScraper.php
@@ -0,0 +1,38 @@
+<?php
+
+namespace App\Domain\Scraping\Infrastructure\Service\Scraper;
+
+use App\Domain\Scraping\Domain\Model\ScrapingJob;
+use Symfony\Component\Panther\Client as PantherClient;
+
+class JavascriptScraper extends AbstractScraper
+{
+    protected function scrapePages(ScrapingJob $job): array
+    {
+        $client = PantherClient::createChromeClient();
+        try {
+            $url = $this->buildUrl($job);
+            $crawler = $client->request('GET', $url);
+            
+            // Attendre que les images soient chargées
+            $crawler->waitFor('img.manga-page');
+            
+            $pages = [];
+            $crawler->filter('img.manga-page')->each(function ($image) use (&$pages) {
+                $pages[] = [
+                    'url' => $image->attr('src'),
+                    'number' => count($pages) + 1
+                ];
+            });
+            
+            return $pages;
+        } finally {
+            $client->quit();
+        }
+    }
+
+    public function supports(string $sourceType): bool
+    {
+        return $sourceType === 'javascript';
+    }
+} 
\ No newline at end of file