PEP8 cleanups, remove OCR_CACHE_URI

apps/ocr/__init__.py

@@ -1,15 +1,14 @@
 from __future__ import absolute_import
 
 import logging
-        
+
 from django.db import transaction
 from django.utils.translation import ugettext_lazy as _
 from django.utils.translation import ugettext
 from django.db.models.signals import post_save
 from django.dispatch import receiver
 
-from navigation.api import register_links, register_top_menu, register_multi_item_links
+from navigation.api import register_links, register_multi_item_links
-from permissions.models import Permission, PermissionNamespace
 from documents.models import Document, DocumentVersion
 from main.api import register_maintenance_links
 from project_tools.api import register_tool
@@ -18,7 +17,7 @@ from acls.api import class_permissions
 from scheduler.api import register_interval_job
 
 from .conf.settings import (AUTOMATIC_OCR, QUEUE_PROCESSING_INTERVAL)
-from .models import DocumentQueue, QueueTransformation, QueueDocument
+from .models import DocumentQueue, QueueTransformation
 from .tasks import task_process_document_queues
 from .permissions import (PERMISSION_OCR_DOCUMENT,
     PERMISSION_OCR_DOCUMENT_DELETE, PERMISSION_OCR_QUEUE_ENABLE_DISABLE,
@@ -85,7 +84,7 @@ def document_post_save(sender, instance, **kwargs):
 # the OCR process completes which could take several minutes :/
 #@receiver(post_save, dispatch_uid='call_queue', sender=QueueDocument)
 #def call_queue(sender, **kwargs):
-#    if kwargs.get('created', False):    
+#    if kwargs.get('created', False):
 #        logger.debug('got call_queue signal: %s' % kwargs)
 #        task_process_document_queues()
 

apps/ocr/conf/settings.py

@@ -14,7 +14,6 @@ register_settings(
         {'name': u'NODE_CONCURRENT_EXECUTION', 'global_name': u'OCR_NODE_CONCURRENT_EXECUTION', 'default': 1, 'description': _(u'Maximum amount of concurrent document OCRs a node can perform.')},
         {'name': u'AUTOMATIC_OCR', 'global_name': u'OCR_AUTOMATIC_OCR', 'default': False, 'description': _(u'Automatically queue newly created documents for OCR.')},
         {'name': u'QUEUE_PROCESSING_INTERVAL', 'global_name': u'OCR_QUEUE_PROCESSING_INTERVAL', 'default': 10},
-        {'name': u'CACHE_URI', 'global_name': u'OCR_CACHE_URI', 'default': None, 'description': _(u'URI in the form: "memcached://127.0.0.1:11211/" to specify a cache backend to use for locking. Multiple hosts can be specified separated by a semicolon.')},
         {'name': u'UNPAPER_PATH', 'global_name': u'OCR_UNPAPER_PATH', 'default': u'/usr/bin/unpaper', 'description': _(u'File path to unpaper program.'), 'exists': True},
     ]
 )

apps/ocr/exceptions.py

@@ -1,21 +1,21 @@
 class AlreadyQueued(Exception):
-    '''
+    """
     Raised when a trying to queue document already in the queue
-    '''    
+    """
     pass
 
 
 class TesseractError(Exception):
-    '''
+    """
     Raised by tesseract
-    '''    
+    """
     pass
 
 
 class UnpaperError(Exception):
-    '''
+    """
     Raised by unpaper
-    '''
+    """
     pass
 
 

apps/ocr/parsers/__init__.py

@@ -3,10 +3,9 @@ import logging
 
 from django.utils.translation import ugettext as _
 
-from converter import office_converter
 from converter import office_converter
 from converter.office_converter import OfficeConverter
-from converter.exceptions import OfficeBackendError, OfficeConversionError
+from converter.exceptions import OfficeConversionError
 from documents.utils import document_save_to_temp_dir
 
 from ocr.parsers.exceptions import ParserError, ParserUnknownFile
@@ -27,7 +26,7 @@ def register_parser(function, mimetype=None, mimetypes=None):
 def pdf_parser(document_page, descriptor=None):
     if not descriptor:
         descriptor = document_page.document_version.open()
-    
+
     pdf_pages = slate.PDF(descriptor)
     descriptor.close()
 
@@ -45,7 +44,7 @@ def office_parser(document_page):
         office_converter = OfficeConverter()
         document_file = document_save_to_temp_dir(document_page.document, document_page.document.checksum)
         logger.debug('document_file: %s', document_file)
-        
+
         office_converter.convert(document_file, mimetype=document_page.document.file_mimetype)
         if office_converter.exists:
             input_filepath = office_converter.output_filepath
@@ -58,7 +57,7 @@ def office_parser(document_page):
     except OfficeConversionError, msg:
         print msg
         raise ParserError
-    
+
 
 def parse_document_page(document_page):
     logger.debug('executing')

apps/ocr/tasks.py

@@ -2,8 +2,6 @@ from __future__ import absolute_import
 
 from datetime import timedelta, datetime
 import platform
-from time import sleep
-from random import random
 import logging
 
 from django.db.models import Q
@@ -17,7 +15,7 @@ from .literals import (QUEUEDOCUMENT_STATE_PENDING,
     QUEUEDOCUMENT_STATE_ERROR)
 from .models import QueueDocument, DocumentQueue
 from .conf.settings import (NODE_CONCURRENT_EXECUTION, REPLICATION_DELAY,
-    CACHE_URI, QUEUE_PROCESSING_INTERVAL)
+	QUEUE_PROCESSING_INTERVAL)
 
 LOCK_EXPIRE = 60 * 10  # Lock expires in 10 minutes
 # TODO: Tie LOCK_EXPIRATION with hard task timeout
@@ -100,7 +98,7 @@ def task_process_document_queues():
                 #print 'DocumentQueueWatcher exception: %s' % e
             finally:
                 # Don't process anymore from this queryset, might be stale
-                break;
+                break
         else:
             logger.debug('already processing maximun')
     else:

docs/changelog.rst

@@ -1,5 +1,6 @@
 Version 0.12
 ------------
+* Removal of the OCR_CACHE_URI configuration option
 * Upgrade commands:
 
     * ./manage.py syncdb

docs/settings.rst

@@ -270,14 +270,6 @@ OCR
     Default: ``10``               
 
 
-.. data:: OCR_CACHE_URI    
-    
-    Default: ``None``       
-
-    URI in the form: ``"memcached://127.0.0.1:11211/"`` to specify a cache
-    backend to use for locking. Multiple hosts can be specified separated
-    by a semicolon.    
-    
 
 .. data:: OCR_UNPAPER_PATH