Update document parsing app

Update URL parameters to the "_id" forms. Add keyword arguments.
Remove use of is_path in the DOCUMENT_PARSING_PDFTOTEXT_PATH
setting.

Signed-off-by: Roberto Rosario <Roberto.Rosario@mayan-edms.com>

mayan/apps/document_parsing/api_views.py

@@ -17,7 +17,7 @@ class APIDocumentPageContentView(generics.RetrieveAPIView):
     """
     Returns the content of the selected document page.
     """
-    lookup_url_kwarg = 'page_pk'
+    lookup_url_kwarg = 'document_page_id'
     mayan_object_permissions = {
         'GET': (permission_content_view,),
     }
@@ -25,11 +25,12 @@ class APIDocumentPageContentView(generics.RetrieveAPIView):
     serializer_class = DocumentPageContentSerializer
 
     def get_document(self):
-        return get_object_or_404(klass=Document, pk=self.kwargs['document_pk'])
+        return get_object_or_404(klass=Document, pk=self.kwargs['document_id'])
 
     def get_document_version(self):
         return get_object_or_404(
-            klass=self.get_document().versions.all(), pk=self.kwargs['version_pk']
+            klass=self.get_document().versions.all(),
+            pk=self.kwargs['document_version_id']
         )
 
     def get_queryset(self):

mayan/apps/document_parsing/events.py

@@ -5,7 +5,7 @@ from django.utils.translation import ugettext_lazy as _
 from mayan.apps.events import EventTypeNamespace
 
 namespace = EventTypeNamespace(
-    name='document_parsing', label=_('Document parsing')
+    label=_('Document parsing'), name='document_parsing'
 )
 
 event_parsing_document_version_submit = namespace.add_event_type(

mayan/apps/document_parsing/exceptions.py

@@ -5,4 +5,3 @@ class ParserError(Exception):
     """
     Base exception for file parsers
     """
-    pass

mayan/apps/document_parsing/links.py

@@ -16,22 +16,26 @@ from .permissions import (
 )
 
 link_document_content = Link(
-    args='resolved_object.id', icon_class=icon_document_content,
+    icon_class=icon_document_content,
+    kwargs={'document_id': 'resolved_object.id'},
     permissions=(permission_content_view,), text=_('Content'),
     view='document_parsing:document_content',
 )
 link_document_page_content = Link(
-    args='resolved_object.id', icon_class=icon_document_content,
+    icon_class=icon_document_content,
+    kwargs={'document_page_id': 'resolved_object.id'},
     permissions=(permission_content_view,), text=_('Content'),
     view='document_parsing:document_page_content',
 )
 link_document_parsing_errors_list = Link(
-    args='resolved_object.id', icon_class=icon_document_parsing_errors_list,
+    icon_class=icon_document_parsing_errors_list,
+    kwargs={'document_id': 'resolved_object.id'},
     permissions=(permission_content_view,), text=_('Parsing errors'),
     view='document_parsing:document_parsing_error_list'
 )
 link_document_content_download = Link(
-    args='resolved_object.id', icon_class=icon_document_content_download,
+    icon_class=icon_document_content_download,
+    kwargs={'document_id': 'resolved_object.id'},
     permissions=(permission_content_view,), text=_('Download content'),
     view='document_parsing:document_content_download'
 )
@@ -40,13 +44,14 @@ link_document_multiple_submit = Link(
     view='document_parsing:document_multiple_submit'
 )
 link_document_submit = Link(
-    args='resolved_object.id', icon_class=icon_document_submit,
+    icon_class=icon_document_submit,
+    kwargs={'document_id': 'resolved_object.id'},
     permissions=(permission_parse_document,),
     text=_('Submit for parsing'), view='document_parsing:document_submit'
 )
 link_document_type_parsing_settings = Link(
-    args='resolved_object.id',
     icon_class=icon_document_type_parsing_settings,
+    kwargs={'document_type_id': 'resolved_object.id'},
     permissions=(permission_document_type_parsing_setup,),
     text=_('Setup parsing'),
     view='document_parsing:document_type_parsing_settings',

mayan/apps/document_parsing/permissions.py

@@ -7,12 +7,12 @@ from mayan.apps.permissions import PermissionNamespace
 namespace = PermissionNamespace(label=_('Document parsing'), name='document_parsing')
 
 permission_content_view = namespace.add_permission(
-    name='content_view', label=_('View the content of a document')
+    label=_('View the content of a document'), name='content_view'
 )
 permission_document_type_parsing_setup = namespace.add_permission(
-    name='document_type_setup',
+    label=_('Change document type parsing settings'),
-    label=_('Change document type parsing settings')
+    name='document_type_setup'
 )
 permission_parse_document = namespace.add_permission(
-    name='parse_document', label=_('Parse the content of a document')
+    label=_('Parse the content of a document'), name='parse_document'
 )

mayan/apps/document_parsing/queues.py

@@ -4,8 +4,9 @@ from django.utils.translation import ugettext_lazy as _
 
 from mayan.apps.task_manager.classes import CeleryQueue
 
-queue_ocr = CeleryQueue(name='parsing', label=_('Parsing'))
+queue_ocr = CeleryQueue(label=_('Parsing'), name='parsing')
+
 queue_ocr.add_task_type(
-    name='mayan.apps.document_parsing.tasks.task_parse_document_version',
+    label=_('Document version parsing'),
-    label=_('Document version parsing')
+    name='mayan.apps.document_parsing.tasks.task_parse_document_version'
 )

mayan/apps/document_parsing/settings.py

@@ -6,7 +6,7 @@ from mayan.apps.smart_settings import Namespace
 
 from .literals import DEFAULT_PDFTOTEXT_PATH
 
-namespace = Namespace(name='document_parsing', label=_('Document parsing'))
+namespace = Namespace(label=_('Document parsing'), name='document_parsing')
 
 setting_auto_parsing = namespace.add_setting(
     global_name='DOCUMENT_PARSING_AUTO_PARSING', default=True,
@@ -21,5 +21,4 @@ setting_pdftotext_path = namespace.add_setting(
         'File path to poppler\'s pdftotext program used to extract text '
         'from PDF files.'
     ),
-    is_path=True
 )

mayan/apps/document_parsing/tests/test_api.py

@@ -16,17 +16,14 @@ TEST_DOCUMENT_CONTENT = 'Sample text'
 class DocumentParsingAPITestCase(DocumentTestMixin, BaseAPITestCase):
     test_document_filename = TEST_HYBRID_DOCUMENT
 
-    def setUp(self):
-        super(DocumentParsingAPITestCase, self).setUp()
-        self.login_user()
-
     def _request_document_page_content_view(self):
         return self.get(
             viewname='rest_api:document-page-content-view',
-            args=(
+            kargs={
-                self.document.pk, self.document.latest_version.pk,
+                'document_id': self.document.pk,
-                self.document.latest_version.pages.first().pk,
+                'version_id': self.document.latest_version.pk,
-            )
+                'page_id': self.document.latest_version.pages.first().pk
+            }
         )
 
     def test_get_document_version_page_content_no_access(self):

mayan/apps/document_parsing/tests/test_views.py

@@ -22,19 +22,16 @@ class DocumentContentViewsTestCase(GenericDocumentViewTestCase):
     # Ensure we use a PDF file
     test_document_filename = TEST_HYBRID_DOCUMENT
 
-    def setUp(self):
-        super(DocumentContentViewsTestCase, self).setUp()
-        self.login_user()
-
     def _request_document_content_view(self):
         return self.get(
-            'document_parsing:document_content', args=(self.document.pk,)
+            viewname='document_parsing:document_content',
+            kwargs={'document_id': self.document.pk}
         )
 
     def test_document_content_view_no_permissions(self):
         response = self._request_document_content_view()
 
-        self.assertEqual(response.status_code, 403)
+        self.assertEqual(response.status_code, 404)
 
     def test_document_content_view_with_access(self):
         self.grant_access(
@@ -48,15 +45,15 @@ class DocumentContentViewsTestCase(GenericDocumentViewTestCase):
 
     def _request_document_page_content_view(self):
         return self.get(
-            viewname='document_parsing:document_page_content', args=(
+            viewname='document_parsing:document_page_content', kwargs={
-                self.document.pages.first().pk,
+                'document_page_id': self.document.pages.first().pk
-            )
+            }
         )
 
     def test_document_page_content_view_no_permissions(self):
         response = self._request_document_page_content_view()
 
-        self.assertEqual(response.status_code, 403)
+        self.assertEqual(response.status_code, 404)
 
     def test_document_page_content_view_with_access(self):
         self.grant_access(
@@ -71,12 +68,12 @@ class DocumentContentViewsTestCase(GenericDocumentViewTestCase):
     def _request_document_content_download_view(self):
         return self.get(
             viewname='document_parsing:document_content_download',
-            args=(self.document.pk,)
+            kwargs={'document_id': self.document.pk}
         )
 
     def test_document_parsing_download_view_no_permission(self):
         response = self._request_document_content_download_view()
-        self.assertEqual(response.status_code, 403)
+        self.assertEqual(response.status_code, 404)
 
     def test_download_view_with_access(self):
         self.expected_content_type = 'application/octet-stream; charset=utf-8'
@@ -98,14 +95,10 @@ class DocumentTypeViewsTestCase(GenericDocumentViewTestCase):
     # Ensure we use a PDF file
     test_document_filename = TEST_HYBRID_DOCUMENT
 
-    def setUp(self):
-        super(DocumentTypeViewsTestCase, self).setUp()
-        self.login_user()
-
     def _request_document_type_parsing_settings_view(self):
         return self.get(
             viewname='document_parsing:document_type_parsing_settings',
-            args=(self.document.document_type.pk,)
+            kwargs={'document_type_id': self.document.document_type.pk}
         )
 
     def test_document_type_parsing_settings_view_no_permission(self):

mayan/apps/document_parsing/urls.py

@@ -11,46 +11,50 @@ from .views import (
 
 urlpatterns = [
     url(
-        r'^documents/(?P<pk>\d+)/content/$', DocumentContentView.as_view(),
+        regex=r'^documents/(?P<document_id>\d+)/content/$',
-        name='document_content'
+        name='document_content', view=DocumentContentView.as_view()
     ),
     url(
-        r'^documents/pages/(?P<pk>\d+)/content/$',
+        regex=r'^documents/pages/(?P<document_page_id>\d+)/content/$',
-        DocumentPageContentView.as_view(), name='document_page_content'
+        name='document_page_content', view=DocumentPageContentView.as_view()
     ),
     url(
-        r'^documents/(?P<pk>\d+)/content/download/$',
+        regex=r'^documents/(?P<document_id>\d+)/content/download/$',
-        DocumentContentDownloadView.as_view(), name='document_content_download'
+        name='document_content_download',
+        view=DocumentContentDownloadView.as_view()
     ),
     url(
-        r'^documents/(?P<pk>\d+)/submit/$', DocumentSubmitView.as_view(),
+        regex=r'^documents/(?P<document_id>\d+)/submit/$',
-        name='document_submit'
+        name='document_submit', view=DocumentSubmitView.as_view()
     ),
     url(
-        r'^documents/multiple/submit/$', DocumentSubmitView.as_view(),
+        regex=r'^documents/multiple/submit/$', name='document_multiple_submit',
-        name='document_multiple_submit'
+        view=DocumentSubmitView.as_view()
     ),
     url(
-        r'^documents/(?P<pk>\d+)/errors/$',
+        regex=r'^documents/(?P<document_id>\d+)/errors/$',
-        DocumentParsingErrorsListView.as_view(),
+        name='document_parsing_error_list',
-        name='document_parsing_error_list'
+        view=DocumentParsingErrorsListView.as_view()
     ),
     url(
-        r'^document_types/submit/$', DocumentTypeSubmitView.as_view(),
+        regex=r'^document_types/submit/$', name='document_type_submit',
-        name='document_type_submit'
+        view=DocumentTypeSubmitView.as_view()
     ),
     url(
-        r'^document_types/(?P<pk>\d+)/parsing/settings/$',
+        regex=r'^document_types/(?P<document_type_id>\d+)/parsing/settings/$',
-        DocumentTypeSettingsEditView.as_view(),
+        name='document_type_parsing_settings',
-        name='document_type_parsing_settings'
+        view=DocumentTypeSettingsEditView.as_view()
     ),
-    url(r'^errors/all/$', ParseErrorListView.as_view(), name='error_list'),
+    url(
+        regex=r'^errors/all/$', name='error_list',
+        view=ParseErrorListView.as_view()
+    )
 ]
 
 api_urls = [
     url(
-        r'^documents/(?P<document_pk>\d+)/versions/(?P<version_pk>\d+)/pages/(?P<page_pk>\d+)/content/$',
+        regex=r'^documents/(?P<document_id>\d+)/versions/(?P<document_version_id>\d+)/pages/(?P<document_page_id>\d+)/content/$',
-        APIDocumentPageContentView.as_view(),
+        view=APIDocumentPageContentView.as_view(),
         name='document-page-content-view'
-    ),
+    )
 ]

mayan/apps/document_parsing/views.py

@@ -28,6 +28,7 @@ class DocumentContentView(SingleObjectDetailView):
     form_class = DocumentContentForm
     model = Document
     object_permission = permission_content_view
+    pk_url_kwarg = 'document_id'
 
     def dispatch(self, request, *args, **kwargs):
         result = super(DocumentContentView, self).dispatch(
@@ -48,6 +49,7 @@ class DocumentContentView(SingleObjectDetailView):
 class DocumentContentDownloadView(SingleObjectDownloadView):
     model = Document
     object_permission = permission_content_view
+    pk_url_kwarg = 'document_id'
 
     def get_file(self):
         file_object = DocumentContentDownloadView.TextIteratorIO(
@@ -62,6 +64,7 @@ class DocumentPageContentView(SingleObjectDetailView):
     form_class = DocumentPageContentForm
     model = DocumentPage
     object_permission = permission_content_view
+    pk_url_kwarg = 'document_page_id'
 
     def dispatch(self, request, *args, **kwargs):
         result = super(DocumentPageContentView, self).dispatch(
@@ -84,7 +87,7 @@ class DocumentParsingErrorsListView(SingleObjectListView):
     view_permission = permission_content_view
 
     def get_document(self):
-        return get_object_or_404(klass=Document, pk=self.kwargs['pk'])
+        return get_object_or_404(klass=Document, pk=self.kwargs['document_id'])
 
     def get_extra_context(self):
         return {
@@ -141,10 +144,12 @@ class DocumentSubmitView(MultipleObjectConfirmActionView):
 class DocumentTypeSettingsEditView(SingleObjectEditView):
     fields = ('auto_parsing',)
     object_permission = permission_document_type_parsing_setup
-    post_action_redirect = reverse_lazy('documents:document_type_list')
+    post_action_redirect = reverse_lazy(viewname='documents:document_type_list')
 
     def get_document_type(self):
-        return get_object_or_404(klass=DocumentType, pk=self.kwargs['pk'])
+        return get_object_or_404(
+            klass=DocumentType, pk=self.kwargs['document_type_id']
+        )
 
     def get_extra_context(self):
         return {
@@ -163,7 +168,7 @@ class DocumentTypeSubmitView(FormView):
         'title': _('Submit all documents of a type for parsing')
     }
     form_class = DocumentTypeFilteredSelectForm
-    post_action_redirect = reverse_lazy('common:tools_list')
+    post_action_redirect = reverse_lazy(viewname='common:tools_list')
 
     def get_form_extra_kwargs(self):
         return {