matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

PEP8, pylint cleanups and removal of relative imports

Browse Source
This commit is contained in:
Roberto Rosario
2011-04-23 02:49:07 -04:00
parent 4625e5d792
commit 2a744cefea
51 changed files with 290 additions and 290 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
apps/ocr/__init__.py
View File

@@ -10,8 +10,8 @@ from permissions.api import register_permissions
from documents.models import Document
from ocr.conf.settings import AUTOMATIC_OCR
from models import DocumentQueue, QueueDocument
from literals import QUEUEDOCUMENT_STATE_PROCESSING, \
from ocr.models import DocumentQueue, QueueDocument
from ocr.literals import QUEUEDOCUMENT_STATE_PROCESSING, \
QUEUEDOCUMENT_STATE_PENDING, DOCUMENTQUEUE_STATE_STOPPED, \
DOCUMENTQUEUE_STATE_ACTIVE

2
apps/ocr/admin.py
View File

@@ -1,6 +1,6 @@
from django.contrib import admin
from models import DocumentQueue, QueueDocument
from ocr.models import DocumentQueue, QueueDocument
class QueueDocumentInline(admin.StackedInline):

4
apps/ocr/api.py
View File

@@ -15,7 +15,7 @@ from documents.models import DocumentPage
from ocr.conf.settings import TESSERACT_PATH
from ocr.conf.settings import TESSERACT_LANGUAGE
from ocr.conf.settings import PDFTOTEXT_PATH
from exceptions import TesseractError, PdftotextError
from ocr.exceptions import TesseractError, PdftotextError
def get_language_backend():
@@ -59,7 +59,7 @@ def run_pdftotext(input_filename, output_filename, page_number=None):
if return_code != 0:
error_text = proc.stderr.read()
raise PdftotextError(error_text)
def do_document_ocr(document):
for page_index, document_page in enumerate(document.documentpage_set.all()):

4
apps/ocr/exceptions.py
View File

@@ -4,7 +4,7 @@ class AlreadyQueued(Exception):
class TesseractError(Exception):
pass
class PdftotextError(Exception):
pass

12
apps/ocr/lang/eng.py
View File

@@ -1,5 +1,6 @@
import re
def check_word(word):
ALL_ALPHANUM = re.compile('([0-9a-z])', re.I)
NON_ALPHANUM = re.compile('([^0-9a-z])', re.I)
@@ -13,7 +14,7 @@ def check_word(word):
if len(word) > 20:
return None
#(A) If a string's ratio of alphanumeric characters to total
#(A) If a string's ratio of alphanumeric characters to total
#characters is less than 50%, the string is garbage
if len(ALL_ALPHANUM.findall(word)) < len(word) / 2:
return None
@@ -21,18 +22,17 @@ def check_word(word):
#Remove word if all the letters in the word are non alphanumeric
if len(NON_ALPHANUM.findall(word)) == len(word):
return None
#Removed words with too many consecutie vowels
if TOO_MANY_VOWELS.findall(word):
return None
return None
#Removed words with too many consecutie consonants
if TOO_MANY_CONSONANTS.findall(word):
return None
return None
#Only allow specific single letter words
if len(word) == 1 and not SINGLE_LETTER_WORDS.findall(word):
return None
return word

14
apps/ocr/lang/spa.py
View File

@@ -1,6 +1,7 @@
# -*- coding: iso-8859-1 -*-
# -*- coding: utf-8 -*-
import re
def check_word(word):
ALL_ALPHANUM = re.compile('([0-9a-záéíóúüñ])', re.I)
NON_ALPHANUM = re.compile('([^0-9a-záéíóúüñ])', re.I)
@@ -14,7 +15,7 @@ def check_word(word):
if len(word) > 20:
return None
#(A) If a string’s ratio of alphanumeric characters to total
#(A) If a string’s ratio of alphanumeric characters to total
#characters is less than 50%, the string is garbage
if len(ALL_ALPHANUM.findall(word)) < len(word) / 2:
return None
@@ -22,18 +23,17 @@ def check_word(word):
#Remove word if all the letters in the word are non alphanumeric
if len(NON_ALPHANUM.findall(word)) == len(word):
return None
#Removed words with too many consecutie vowels
if TOO_MANY_VOWELS.findall(word):
return None
return None
#Removed words with too many consecutie consonants
if TOO_MANY_CONSONANTS.findall(word):
return None
return None
#Only allow specific single letter words
if len(word) == 1 and not SINGLE_LETTER_WORDS.findall(word):
return None
return word

4
apps/ocr/models.py
View File

@@ -5,10 +5,10 @@ from django.core.exceptions import ObjectDoesNotExist
from documents.models import Document
from literals import DOCUMENTQUEUE_STATE_STOPPED, \
from ocr.literals import DOCUMENTQUEUE_STATE_STOPPED, \
DOCUMENTQUEUE_STATE_CHOICES, QUEUEDOCUMENT_STATE_PENDING, \
QUEUEDOCUMENT_STATE_CHOICES
from exceptions import AlreadyQueued
from ocr.exceptions import AlreadyQueued
class DocumentQueueManager(models.Manager):

3
apps/ocr/statistics.py
View File

@@ -1,7 +1,6 @@
from django.utils.translation import ugettext as _
from models import DocumentQueue, QueueDocument
from ocr.models import DocumentQueue, QueueDocument
def get_statistics():

4
apps/ocr/tasks.py
View File

@@ -9,10 +9,10 @@ from celery.task import PeriodicTask
from celery.decorators import task
from ocr.api import do_document_ocr
from literals import QUEUEDOCUMENT_STATE_PENDING, \
from ocr.literals import QUEUEDOCUMENT_STATE_PENDING, \
QUEUEDOCUMENT_STATE_PROCESSING, DOCUMENTQUEUE_STATE_ACTIVE, \
QUEUEDOCUMENT_STATE_ERROR
from models import QueueDocument, DocumentQueue
from ocr.models import QueueDocument, DocumentQueue
from ocr.conf.settings import NODE_CONCURRENT_EXECUTION
from ocr.conf.settings import REPLICATION_DELAY

16
apps/ocr/views.py
View File

@@ -14,12 +14,12 @@ from documents.models import Document
from ocr import PERMISSION_OCR_DOCUMENT, PERMISSION_OCR_DOCUMENT_DELETE, \
PERMISSION_OCR_QUEUE_ENABLE_DISABLE, PERMISSION_OCR_CLEAN_ALL_PAGES
from models import DocumentQueue, QueueDocument
from literals import QUEUEDOCUMENT_STATE_PENDING, \
from ocr.models import DocumentQueue, QueueDocument
from ocr.literals import QUEUEDOCUMENT_STATE_PENDING, \
QUEUEDOCUMENT_STATE_PROCESSING, DOCUMENTQUEUE_STATE_STOPPED, \
DOCUMENTQUEUE_STATE_ACTIVE
from exceptions import AlreadyQueued
from api import clean_pages
from ocr.exceptions import AlreadyQueued
from ocr.api import clean_pages
def _display_thumbnail(ocr_document):
@@ -65,15 +65,13 @@ def queue_document_list(request, queue_name='default'):
)
def queue_document_delete(request, queue_document_id=None, queue_document_id_list=[]):
def queue_document_delete(request, queue_document_id=None, queue_document_id_list=None):
check_permissions(request.user, 'ocr', [PERMISSION_OCR_DOCUMENT_DELETE])
if queue_document_id:
queue_documents = [get_object_or_404(QueueDocument, pk=queue_document_id)]
post_redirect = None
elif queue_document_id_list:
queue_documents = [get_object_or_404(QueueDocument, pk=queue_document_id) for queue_document_id in queue_document_id_list.split(',')]
post_redirect = None
else:
messages.error(request, _(u'Must provide at least one queue document.'))
return HttpResponseRedirect(request.META.get('HTTP_REFERER', '/'))
@@ -138,15 +136,13 @@ def submit_document_to_queue(request, document, post_submit_redirect=None):
return HttpResponseRedirect(post_submit_redirect)
def re_queue_document(request, queue_document_id=None, queue_document_id_list=[]):
def re_queue_document(request, queue_document_id=None, queue_document_id_list=None):
check_permissions(request.user, 'ocr', [PERMISSION_OCR_DOCUMENT])
if queue_document_id:
queue_documents = [get_object_or_404(QueueDocument, pk=queue_document_id)]
post_redirect = None
elif queue_document_id_list:
queue_documents = [get_object_or_404(QueueDocument, pk=queue_document_id) for queue_document_id in queue_document_id_list.split(',')]
post_redirect = None
else:
messages.error(request, _(u'Must provide at least one queue document.'))
return HttpResponseRedirect(request.META.get('HTTP_REFERER', '/'))