added option for polling

paperless.conf.example

@@ -165,6 +165,12 @@ PAPERLESS_EMAIL_SECRET=""
 # If you only specify PAPERLESS_TASK_WORKERS, paperless will adjust
 # PAPERLESS_THREADS_PER_WORKER automatically.
 
+# If paperless won't find documents added to your consume folder, it might
+# not be able to automatically detect filesystem changes. In that case,
+# specify a polling interval in seconds below, which will then cause paperless
+# to periodically check your consumption directory for changes.
+#PAPERLESS_CONSUMER_POLLING=10
+
 
 # When the consumer detects a duplicate document, it will not touch the
 # original document. This default behavior can be changed here.

src/documents/management/commands/document_consumer.py

@@ -6,6 +6,7 @@ from django.core.management.base import BaseCommand
 from django_q.tasks import async_task
 from watchdog.events import FileSystemEventHandler
 from watchdog.observers import Observer
+from watchdog.observers.polling import PollingObserver
 
 try:
     from inotify_simple import INotify, flags
@@ -75,7 +76,12 @@ class Command(BaseCommand):
                 async_task("documents.tasks.consume_file", entry.path, task_name=os.path.basename(entry.path))
 
         # Start the watchdog. Woof!
-        observer = Observer()
+        if settings.CONSUMER_POLLING > 0:
+            logging.getLogger(__name__).info('Using polling instead of file'
+                                             'system notifications.')
+            observer = PollingObserver(timeout=settings.CONSUMER_POLLING)
+        else:
+            observer = Observer()
         event_handler = Handler()
         observer.schedule(event_handler, directory, recursive=True)
         observer.start()

src/paperless/settings.py

@@ -286,13 +286,29 @@ TASK_WORKERS = int(os.getenv("PAPERLESS_TASK_WORKERS", default_task_workers()))
 Q_CLUSTER = {
     'name': 'paperless',
     'catch_up': False,
+    'workers': TASK_WORKERS,
     'redis': os.getenv("PAPERLESS_REDIS", "redis://localhost:6379")
 }
 
+
+def default_threads_per_worker():
+    try:
+        return max(
+            math.floor(multiprocessing.cpu_count() / TASK_WORKERS),
+            1
+        )
+    except NotImplementedError:
+        return 1
+
+
+THREADS_PER_WORKER = os.getenv("PAPERLESS_THREADS_PER_WORKER", default_threads_per_worker())
+
 ###############################################################################
 # Paperless Specific Settings                                                 #
 ###############################################################################
 
+CONSUMER_POLLING = int(os.getenv("PAPERLESS_CONSUMER_POLLING", 0))
+
 CONSUMER_DELETE_DUPLICATES = __get_boolean("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
 
 # The default language that tesseract will attempt to use when parsing