* Added a new option OCR_REPLICATION_DELAY to allow the storage some time for replication before attempting to do OCR to a document

apps/ocr/conf/settings.py

@@ -3,3 +3,4 @@ from django.conf import settings
 TESSERACT_PATH = getattr(settings, 'OCR_TESSERACT_PATH', u'/usr/bin/tesseract')
 TESSERACT_LANGUAGE = getattr(settings, 'OCR_TESSERACT_LANGUAGE', None)
 MAX_CONCURRENT_EXECUTION = getattr(settings, 'OCR_MAX_CONCURRENT_EXECUTION', 2)
+REPLICATION_DELAY = getattr(settings, 'OCR_REPLICATION_DELAY', 360) #In seconds, 360 = 6 minutes

apps/ocr/tasks.py

@@ -10,6 +10,7 @@ from literals import QUEUEDOCUMENT_STATE_PENDING, \
     QUEUEDOCUMENT_STATE_ERROR
 from models import QueueDocument, DocumentQueue
 from ocr.conf.settings import MAX_CONCURRENT_EXECUTION
+from ocr.conf.settings import REPLICATION_DELAY
 
     
 @task
@@ -39,7 +40,7 @@ class DocumentQueueWatcher(PeriodicTask):
             if current_running_queues < MAX_CONCURRENT_EXECUTION:
                 try:
                     oldest_queued_document = document_queue.queuedocument_set.filter(
-                            state=QUEUEDOCUMENT_STATE_PENDING).order_by('datetime_submitted')[0]
+                            state=QUEUEDOCUMENT_STATE_PENDING).filter(datetime_submitted__lt=datetime.datetime.now()-datetime.timedelta(seconds=REPLICATION_DELAY)).order_by('datetime_submitted')[0]
 
                     task_process_queue_document(oldest_queued_document.id).delay()
                 except:

docs/Changelog.txt

@@ -1,5 +1,7 @@
 2011-Mar-21
 * Added a new diagnostics tab under the tools menu
+* Added a new option OCR_REPLICATION_DELAY to allow the storage some
+  time for replication before attempting to do OCR to a document
 
 2011-Mar-20
 * Added simple statistics page (total used storage, total docs, etc)

docs/TODO

@@ -46,6 +46,7 @@ TODO, WISHLIST
 * Change to model signals                                              - NOT NEEDED, found way to prevent save method recursion
 * Show current page in generic list template                           - DONE
 * Enable/disable ocr queue view & links                                - DONE
+* Android App                                                          - NOT NEEDED (Use CamSanner, (C) IntSig Information Co, Ltd.)
 
 * Receive documents via email
 * Mobile version

settings.py

@@ -244,6 +244,7 @@ LOGIN_EXEMPT_URLS = (
 #OCR_TESSERACT_PATH = u'/usr/bin/tesseract'
 #OCR_MAX_CONCURRENT_EXECUTION = 2
 #OCR_TESSERACT_LANGUAGE = None
+#OCR_REPLICATION_DELAY = 360
 
 # Permissions
 #ROLES_DEFAULT_ROLES = []