Merge pull request #3 from squ1rr3lly/fix_archiving

Fix archiving/backup, update pdf library, clean up Dockerfile

.gitignore

@@ -14,3 +14,4 @@ Homestead.yaml
 npm-debug.log
 package-lock.json
 yarn-error.log
+docker-compose.override.yml

Dockerfile.shaark

@@ -0,0 +1,93 @@
+FROM php:alpine
+MAINTAINER Shaark contributors <https://github.com/MarceauKa/shaark>
+
+WORKDIR /app
+COPY . /app
+
+# Install packages needed for shaark
+RUN apk add --no-cache \
+      bash \
+      openssl \
+      zip \
+      unzip \
+      oniguruma-dev \
+      zlib-dev \
+      libpng-dev \
+      libzip-dev \
+      postgresql-dev \
+      gmp \
+      gmp-dev \
+      python3 \
+      git \
+      libcap \
+      mariadb-client \
+      nodejs \
+      npm \
+      busybox-suid
+
+# Set inheritied capabilities on entrypoint
+RUN setcap cap_net_raw+eip /app/app/entrypoint-shaark.sh && \
+    setcap cap_sys_admin+eip /app/app/entrypoint-shaark.sh && \
+    setcap cap_net_bind_service=+ep `which php`
+
+# Installs latest Chromium (83) package.
+RUN apk add --no-cache \
+      chromium \
+      nss \
+      freetype \
+      freetype-dev \
+      harfbuzz \
+      ca-certificates \
+      ttf-freefont
+
+# Set environment variables
+ENV PUPPETEER_SKIP_CHROMIUM_DOWNLOAD=true \
+    PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser \
+    DB_HOST="mariadb" \
+    REDIS_HOST="redis" \
+    APP_ENV="production" \
+    APP_DEBUG="false" \
+    APP_MIGRATE_DB="true" \
+    CACHE_DRIVER="redis" \
+    QUEUE_CONNECTION="redis" \
+    SESSION_DRIVER="redis" \
+    REDIS_HOST="redis" 
+
+# Puppeteer v3.1.0 works with Chromium 83.
+RUN npm install puppeteer@3.1.0
+
+# Add user so we don't have to run everything as root
+RUN addgroup -S shaark && adduser -S -G shaark shaarkuser \
+    && mkdir -p /home/shaarkuser/Downloads \
+    && chown -R shaarkuser:shaark /home/shaarkuser \
+    && chown -R shaarkuser:shaark /app
+
+# Install youtube-dl binary
+RUN curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/bin/youtube-dl && \
+    chmod a+rx /usr/bin/youtube-dl
+
+# Make sure python binary is python3
+RUN if [ ! -e /usr/bin/python ]; then ln -sf /usr/bin/python3 /usr/bin/python; fi
+
+# Install composer and php extensions
+RUN curl -sS https://getcomposer.org/installer | php -- --install-dir=/usr/local/bin --filename=composer && \
+    docker-php-ext-install pdo mbstring gd exif zip sockets pdo_mysql pgsql pdo_pgsql gmp bcmath
+
+# Configure Backups cron
+RUN crontab -u shaarkuser app/crontab
+
+# Run everything after as non-privileged user.
+USER shaarkuser
+
+RUN composer install --no-dev -o
+
+RUN cp .env.example .env && \
+    \
+    php artisan optimize && \
+    php artisan view:clear && \
+    \
+    php artisan key:generate && \
+    php artisan storage:link
+
+EXPOSE 80
+ENTRYPOINT [ "app/entrypoint-shaark.sh" ]

app/Http/Controllers/Api/Manage/FeaturesController.php

@@ -59,14 +59,14 @@ protected function checkArchivePdf(Shaark $shaark)
             return $this->sendError(__('Your node path is unreachable: :path', ['path' => $exec]));
         }
 
-        $dir = base_path('node_modules/puppeteer/.local-chromium');
+        $dir = base_path('vendor/spatie/browsershot');
 
         if (false === is_dir($dir)) {
-            return $this->sendError(__('Puppeteer dependencies not installed, run `npm install @nesk/puphpeteer --no-save`'));
+            return $this->sendError(__('Puppeteer dependencies not installed, run `composer require spatie/browsershot`'));
         }
 
         try {
-            $name = LinkArchive::archive(url()->route('home'), 'pdf');
+            $name = LinkArchive::archive('http://example.com', 'pdf');
         } catch (\Exception $e) {
             return $this->sendError(__('Unable to create archive, error is: :message', ['message' => $e->getMessage()]));
         }

app/Services/LinkArchive/BrowsershotProvider.php

@@ -0,0 +1,53 @@
+<?php
+
+namespace App\Services\LinkArchive;
+
+use Spatie\Browsershot\Browsershot;
+
+class BrowsershotProvider extends BaseProvider
+{
+    public function makeArchive(): ?string
+    {
+        $name = md5($this->url) . '.pdf';
+        $filename = sprintf('app/archives/%s', $name);
+        $windowWidth = app('shaark')->getArchivePdfWidth();
+        $windowHeight = app('shaark')->getArchivePdfHeight();
+        $nodeBin = app('shaark')->getNodeBin();
+
+        try {
+            $browsershot = new Browsershot($this->url, true);
+            $browsershot
+                ->windowSize($windowWidth, $windowHeight)
+                ->margins(0,0,0,0)
+                ->setNodeBinary($nodeBin)
+                ->setNodeModulePath('node_modules/')
+                ->setIncludePath('/usr/bin/')
+                ->showBackground()
+                ->addChromiumArguments([
+                    'disable-dev-shm-usage'
+                ])
+                ->noSandbox()
+                ->ignoreHttpsErrors()
+                ->dismissDialogs()
+                ->waitUntilNetworkIdle()
+                ->emulateMedia('screen')
+                ->save(storage_path($filename))
+                ;
+        } catch (\Exception $e) {
+            throw new \RuntimeException("Unable to create link archive", 0, $e);
+        }
+
+        return $name;
+    }
+
+    public function isEnabled(): bool
+    {
+        return app('shaark')->getLinkArchivePdf() === true;
+    }
+
+    public function canArchive(): bool
+    {
+        return true;
+    }
+}
+

app/Services/LinkArchive/LinkArchive.php

@@ -7,7 +7,7 @@ class LinkArchive
     /** @var array $providers */
     public static $providers = [
         'media' => YoutubeDlProvider::class,
-        'pdf' => PuppeteerProvider::class,
+        'pdf' => BrowsershotProvider::class,
     ];
 
     public static function availableFor(string $url): array

app/crontab

@@ -0,0 +1,10 @@
+# do daily/weekly/monthly maintenance
+# min   hour    day     month   weekday command
+*/15    *       *       *       *       run-parts /etc/periodic/15min
+0       *       *       *       *       run-parts /etc/periodic/hourly
+0       2       *       *       *       run-parts /etc/periodic/daily
+0       3       *       *       6       run-parts /etc/periodic/weekly
+0       5       1       *       *       run-parts /etc/periodic/monthly
+# run backups configured by Shaark
+* * * * * cd /app && php artisan schedule:run >> /dev/null 2>&1
+

app/entrypoint-shaark.sh

@@ -1,19 +1,27 @@
 #!/bin/bash
-FILE=.app_initialized
 
 cd /app
 echo "Clearing any cached config."
 php artisan config:clear
-if [ ! -f $FILE ]; then
-  echo "Migrating database and creating default Admin user."
-  php artisan migrate --seed --force
-  echo "Admin Username: admin@example.com"
-  echo "Admin Password: secret"
-  touch $FILE
-elif [ "${APP_MIGRATE_DB}" = 'true' ]; then
+if [ "`php artisan migrate:status`" = "Migration table not found." ]; then
+    echo "Migrating database and creating default Admin user."
+    php artisan migrate --seed --force
+    echo "Admin Username: admin@example.com"
+    echo "Admin Password: "${APP_ADMIN_PASSWORD}
+elif [ "${APP_MIGRATE_DB}" = 'true' ] && \
+    [ `php artisan migrate:status|cut -d'|' -f2 |grep -c "No"` -gt 0 ]; then
     echo "Migrating database."
     php artisan migrate --force
 else
   echo "Database migration skipped."
 fi
-php artisan serve --host=0.0.0.0 --port=80
+
+if [ "${APP_DEBUG}" = 'true' ]; then
+    echo "Debugging enabled: creating verbose logs at /app/storage/logs/"
+    php artisan queue:work >> storage/logs/artisan_queue.log &
+    php artisan serve --host=0.0.0.0 --port=80 -vvv >> storage/logs/artisan_serve.log
+else
+    echo "Starting Shaark!"
+    php artisan queue:work &
+    php artisan serve --host=0.0.0.0 --port=80
+fi

composer.json

@@ -34,9 +34,9 @@
         "laravel/tinker": "^1.0",
         "maatwebsite/excel": "^3.1",
         "mews/captcha": "^3.0",
-        "nesk/puphpeteer": "^1.6",
         "norkunas/youtube-dl-php": "^1.6",
         "predis/predis": "^1.1",
+        "spatie/browsershot": "^3.37",
         "spatie/laravel-backup": "^6.11",
         "spatie/laravel-medialibrary": "^7.0.0",
         "spatie/valuestore": "^1.2",

database/seeds/DatabaseSeeder.php

@@ -18,7 +18,7 @@ public function run()
         DB::table('users')->insert([
             'name' => 'Admin',
             'email' => 'admin@example.com',
-            'password' => Hash::make('secret'),
+            'password' => Hash::make(env('APP_ADMIN_PASSWORD', 'secret')),
             'api_token' => 'api-token-secret',
             'is_admin' => 1,
             'created_at' => now()->toDateTimeString(),

docker-compose.yml

@@ -1,12 +1,14 @@
 version: '3.7'
 services:
   shaark:
-    image: shaark
-    build: .
+    image: shaark:${SHAARK_IMAGE_TAG:-latest}
+    build:
+      context: ./
+      dockerfile: Dockerfile.shaark
     restart: unless-stopped
     ports:
       - target: 80
-        published: ${SHAARK_PORT:-80}
+        published: ${SHAARK_PORT:-8080}
         protocol: tcp
         mode: host
     depends_on:
@@ -18,9 +20,12 @@ services:
       APP_ENV: "production"
       APP_DEBUG: ${SHAARK_DEBUG:-false}
       APP_URL: ${SHAARK_URL:-http://localhost}
+      APP_ADMIN_PASSWORD: ${SHAARK_ADMIN_PASSWORD:-secret}
       DB_PASSWORD: ${SHAARK_DATABASE_PASSWORD:-secret}
       DB_USER: ${SHAARK_DATABASE_USER:-homestead}
       DB_DATABASE: ${SHAARK_DATABASE_NAME:-homestead}
+    volumes:
+      - storage:/app/storage
     logging:
       driver: "json-file"
       options:
@@ -33,7 +38,7 @@ services:
     volumes:
       - mariadb:/var/lib/mysql
     environment:
-      MYSQL_ROOT_PASSWORD: ${SHAARK_MYSQL_ROOT_PASSWORD:-rootpassword9867ow3q459087w980}
+      MYSQL_RANDOM_ROOT_PASSWORD: 'true'
       MYSQL_PASSWORD: ${SHAARK_DATABASE_PASSWORD:-secret}
       MYSQL_USER: ${SHAARK_DATABASE_USER:-homestead}
       MYSQL_DATABASE: ${SHAARK_DATABASE_NAME:-homestead}
@@ -55,5 +60,6 @@ services:
         max-file: "5"
 
 volumes:
-  redis: {}
-  mariadb: {}
+  redis:
+  mariadb:
+  storage: