Install ffmpeg in Dockerfile

.gitignore

@@ -162,4 +162,5 @@ cython_debug/
 #.idea/
 
 
-vendor/czkawka/*
+vendor/czkawka/*
+vendor/ffmpeg/*

Dockerfile

@@ -16,6 +16,12 @@ RUN pip install gunicorn
 # Copy the FastAPI project files into the container
 COPY . .
 
+# Copy the czkawka binary into the container
+COPY vendor/czkawka /bin/
+
+# Install ffmpeg with ffprobe
+RUN apt-get update && apt-get install -y ffmpeg
+
 # Expose the port the app runs on
 EXPOSE 8000
 

src/deduplication.py

@@ -10,23 +10,37 @@ class CZKAWKA_DELETION_METHOD(Enum):
     NONE="NONE"
 
 def deduplicate_files(target_dir, exclude_files):
-    czkawka_path = os.environ.get("CZKAWKA_PATH", "/app/vendor/czkawka/czkawka_cli")
+    executables = {
-    duplicates = _remove_duplicates(
+        "linux": "linux_czkawka_cli",
-        czkawka_path, target_dir, exclude_files, CZKAWKA_DELETION_METHOD.ALL_EXCEPT_SMALLEST)
+        "win32": "windows_czkawka_cli.exe",
+        "darwin": "mac_czkawka_cli",
+        "docker": "linux_czkawka_cli"
+    }
 
-def _remove_duplicates(czkawka_path, target_dir, exclude_files, delete_method: CZKAWKA_DELETION_METHOD):
+    platform = "docker" if os.path.exists("/.dockerenv") else os.sys.platform
+    czkawka_executable = executables.get(platform, "czkawka_cli")
+    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)
+
+def _remove_duplicates(czkawka_path, target_dir, exclude_files, delete_method, tolerance):
     try:
-        flags = ["video", "--directories", target_dir, "--not-recursive", "--delete-method", delete_method.value]
+        flags = _build_czkawka_flags(target_dir, exclude_files, delete_method, tolerance)
-        for file in exclude_files:
-            flags.append("--excluded-items")
-            flags.append(file)
-                
-        flags.append("--tolerance")
-        flags.append(os.environ.get("CK_DUPLICATE_TOLERANCE", "2"))
-        print(flags)
         
         result = subprocess.run([czkawka_path, *flags], capture_output=True, text=True, check=True)
         print(result.stdout)
 
     except subprocess.CalledProcessError as e:
         print(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]
+    
+
+    for file in exclude_files:
+            flags.append("--excluded-items")
+            flags.append(file)
+            
+    flags.append("--tolerance")
+    flags.append(tolerance)
+    return flags

src/main.py

@@ -1,14 +1,16 @@
 import os
 from fastapi import BackgroundTasks, FastAPI
+import logging
 from dotenv import load_dotenv
 from os import path
-
 from qbittorrent_api import get_qbittorrent_files_downloading
 from filemoving import group_files_by_prefix
 from deduplication import deduplicate_files
 import uuid
 import time
 
+logger = logging.getLogger(__name__)
+
 load_dotenv()
 
 qbit_url = os.getenv('QB_URL')
@@ -16,33 +18,39 @@ qbit_user = os.getenv('QB_USER')
 qbit_password = os.getenv('QB_PASSWORD')
 target_dir = os.getenv('TARGET_DIR')
 if not qbit_url or not qbit_user or not qbit_password or not target_dir:
-    print("Please provide all the required environment variables.")
+    logger.error("Please provide all the required environment variables.")
     exit(1)
 
+
 app = FastAPI()
 
 @app.get("/")
 def root(background_tasks: BackgroundTasks):
     job_id = str(uuid.uuid4())
+    logger.info(f"[{job_id}] Received request to start job.")
     background_tasks.add_task(launch_job, job_id)
     return job_id
 
 def launch_job(job_id):
-    # WARNING: Temporary code for testing purposes
+    logger.info(f"[{job_id}] Fetching downloading files from qBittorrent.")
-    time.sleep(5)
+    downloading =  get_qbittorrent_files_downloading(qbit_url, qbit_user, qbit_password)
+    logger.info(f"[{job_id}] Found {len(downloading)} downloading files.")
 
-    with open("jobs.txt", "a") as f:
+    logger.info(f"[{job_id}] Deduplicating files.")
-        f.write(f"{job_id}\n")
+    deduplicate_files(target_dir, downloading)
     
-    patterns = _load_patterns_file()
+    logger.info(f"[{job_id}] Loading patterns.")
-    # downloading =  get_qbittorrent_files_downloading(qbit_url, qbit_user, qbit_password)
+    patterns = _load_patterns_file(job_id)
-    # deduplicate_files(target_dir, downloading)
+    logger.info(f"[{job_id}] Using patterns: {patterns}")
-    # group_files_by_prefix(target_dir, downloading)
+    logger.info(f"[{job_id}] Creating subdirectories and moving files.")
+    group_files_by_prefix(target_dir, downloading, patterns)
 
-def _load_patterns_file():
+    logger.info(f"[{job_id}] Job completed.")
-    config_file_path = os.path.join(os.getcwd(), 'config', 'patterns.txt')
+
+def _load_patterns_file(job_id):
+    config_file_path = os.path.join(os.getcwd(), '..', 'config', 'patterns.txt')
     if not path.exists(config_file_path):
-        print(f"The config file {config_file_path} does not exist.")
+        logger.error(f"[{job_id}] The config file {config_file_path} does not exist.")
         return []
     with open(config_file_path, 'r') as file:
         return [line.strip() for line in file if line.strip()]