Install czkawka via download in dockerfile + fix uvicorn dependency

.gitignore

@@ -159,8 +159,4 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-
-vendor/czkawka/*
-vendor/ffmpeg/*
+#.idea/

Dockerfile

@@ -14,16 +14,21 @@ RUN pip install --no-cache-dir -r requirements.txt
 RUN pip install gunicorn
 
 # Copy the FastAPI project files into the container
-COPY . .
+COPY src/ .
+COPY entrypoint.sh .
 
-# Copy the czkawka binary into the container
-COPY vendor/czkawka /bin/
+# Give execute permissions to the entrypoint script
+RUN chmod +x entrypoint.sh
 
-# Install ffmpeg with ffprobe
-RUN apt-get update && apt-get install -y ffmpeg
+# Copy the patterns.txt file into the container
+COPY config/patterns.txt /config/patterns.txt
+
+# Install binary dependencies
+RUN apt-get update && apt-get install -y wget ffmpeg
+RUN wget -O /usr/local/bin/czkawka https://github.com/qarmin/czkawka/releases/download/8.0.0/linux_czkawka_cli
+RUN chmod +x /usr/local/bin/czkawka
 
 # Expose the port the app runs on
 EXPOSE 8000
 
-# Command to run the FastAPI app using gunicorn with uvicorn workers
-CMD ["gunicorn", "-w", "4", "-k", "uvicorn.workers.UvicornWorker", "main:app", "--bind", "0.0.0.0:8000"]
+ENTRYPOINT ["./entrypoint.sh"]

entrypoint.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+
+# Create user and group using UID and GID from docker run command
+useradd -u $UID -o -m user
+groupadd -g $GID -o group
+
+# assign user to group
+usermod -aG group user
+
+# switch to user
+su user
+
+# launch the application
+gunicorn -w 4 -k uvicorn.workers.UvicornWorker main:app --bind 0.0.0.0:8000

requirements.txt

@@ -1,3 +1,5 @@
 requests
+python-dotenv
 fastapi
+uvicorn
 pytest ; extra == 'dev'

src/deduplication.py

@@ -1,6 +1,9 @@
 import subprocess
 import os
 from enum import Enum
+import logging
+
+logger = logging.getLogger(__name__)
 
 class CZKAWKA_DELETION_METHOD(Enum):
     ALL_EXCEPT_NEWEST = "AEN"
@@ -10,15 +13,7 @@ class CZKAWKA_DELETION_METHOD(Enum):
     NONE="NONE"
 
 def deduplicate_files(target_dir, exclude_files):
-    executables = {
-        "linux": "linux_czkawka_cli",
-        "win32": "windows_czkawka_cli.exe",
-        "darwin": "mac_czkawka_cli",
-        "docker": "linux_czkawka_cli"
-    }
-
-    platform = "docker" if os.path.exists("/.dockerenv") else os.sys.platform
-    czkawka_executable = executables.get(platform, "czkawka_cli")
+    czkawka_executable = "czkawka"
     czkawka_deletion_method = CZKAWKA_DELETION_METHOD.ALL_EXCEPT_SMALLEST
     czkawka_tolerance = os.environ.get("CK_DUPLICATE_TOLERANCE", "2")
     _remove_duplicates(czkawka_executable, target_dir, exclude_files, czkawka_deletion_method, czkawka_tolerance)
@@ -27,11 +22,12 @@ def _remove_duplicates(czkawka_path, target_dir, exclude_files, delete_method, t
     try:
         flags = _build_czkawka_flags(target_dir, exclude_files, delete_method, tolerance)
         
+        logger.info(f"Running czkawka with flags: {flags}")
         result = subprocess.run([czkawka_path, *flags], capture_output=True, text=True, check=True)
-        print(result.stdout)
+        logger.info(result.stdout)
 
     except subprocess.CalledProcessError as e:
-        print(f"Failed to find duplicates: {e.stderr}")
+        logger.error(f"Failed to find duplicates: {e.stderr}")
 
 def _build_czkawka_flags(target_dir, exclude_files, delete_method, tolerance):
     flags = ["video", "--directories", target_dir, "--not-recursive", "--delete-method", delete_method.value]

src/filemoving.py

@@ -1,10 +1,13 @@
 import os
 import shutil
 import re
+import logging
+
+logger = logging.getLogger(__name__)
 
 def group_files_by_prefix(directory, downloading_files, patterns):
     if not os.path.isdir(directory):
-        print(f"The directory {directory} does not exist.")
+        logger.error(f"The directory {directory} does not exist.")
         return
 
     files = [f for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f))]
@@ -13,7 +16,7 @@ def group_files_by_prefix(directory, downloading_files, patterns):
         skip = False
         for downloading_file in downloading_files:
             if file.startswith(downloading_file):
-                print(f"File {file} is downloading. Skipping...")
+                logger.info(f"File {file} is downloading. Skipping...")
                 skip = True
                 continue
 

src/main.py

@@ -7,8 +7,8 @@ from qbittorrent_api import get_qbittorrent_files_downloading
 from filemoving import group_files_by_prefix
 from deduplication import deduplicate_files
 import uuid
-import time
 
+logging.basicConfig(level=logging.INFO, format='[%(asctime)s] - %(name)s - %(levelname)s - %(message)s')
 logger = logging.getLogger(__name__)
 
 load_dotenv()

src/qbittorrent_api.py

@@ -1,5 +1,8 @@
 import requests
 from os import environ
+import logging
+
+logger = logging.getLogger(__name__)
 
 def get_qbittorrent_files_downloading(api_url, user, password):
     cookies = _login_qbittorrent(api_url, user, password)
@@ -10,7 +13,7 @@ def get_qbittorrent_files_downloading(api_url, user, password):
     response = requests.get(f'{api_url}/api/v2/torrents/info?filter=downloading', cookies=cookies)
     
     if response.status_code != 200:
-        print(f"Failed to fetch data from qBittorrent API: {response.status_code}")
+        logger.error(f"Failed to fetch data from qBittorrent API: {response.status_code}")
         return []
 
     torrents = response.json()
@@ -32,7 +35,7 @@ def _login_qbittorrent(api_url, username, password):
     response = requests.post(login_url, data=data)
     
     if response.status_code != 200 or response.text != 'Ok.':
-        print(f"Failed to login to qBittorrent: {response.status_code}")
+        logger.error(f"Failed to login to qBittorrent: {response.status_code}")
         return None
 
     return response.cookies
@@ -41,7 +44,7 @@ def _logout_qbittorrent(api_url, cookies):
     response = requests.get(f'{api_url}/api/v2/auth/logout', cookies=cookies)
     
     if response.status_code != 200 or response.text != 'Ok.':
-        print(f"Failed to logout from qBittorrent: {response.status_code}")
+        logger.error(f"Failed to logout from qBittorrent: {response.status_code}")
         return False
 
     return True