Add support for downloading a document's OCR text.

Closes GitLab issue #215.

Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>

HISTORY.rst

@@ -1,3 +1,8 @@
+2.5 (2017-07-XX)
+===============
+- Add view to download a document's OCR text. GitLab #215
+
+
 2.4 (2017-06-23)
 ================
 - Add Django-mathfilters.
@@ -9,7 +14,7 @@
 - Make tags, metadata types and cabinets searchable via the dynamic search API. GitLab issue #344.
 - Add support for updating configuration options from environment variables.
 - Add purgelocks management command. GitLab issue #221.
-- Fix index rebuilding for multi value first levels. GitLab issue #391. 
+- Fix index rebuilding for multi value first levels. GitLab issue #391.
 - Truncate views titles via the APPEARANCE_MAXIMUM_TITLE_LENGTH setting. GitLab issue #217.
 - Add background task manager app. GitLab issue #132.
 - Add link to show a document's OCR errors. GitLab issue #291.

docs/releases/2.5.rst

@@ -0,0 +1,84 @@
+=============================
+Mayan EDMS v2.5 release notes
+=============================
+
+Released: July XX, 2017
+
+What's new
+==========
+
+
+Other Changes
+-------------
+- Add view to download a document's OCR text. GitLab issue #215.
+- Add missing OCR migration.
+- Improve error output of the performupgrade command to debug upgrade errors
+  that could stop an upgrade (missing document files, etc).
+- Enable the django-mathfilters app added in version 2.4.
+- Do a complete pull and synchronization of the translations to fix missing
+  translations for Polish. Thanks to Wojtek Warczakowski for the report.
+- Allow null for the SANE source resolution field. Even though the field was
+  marked as allowing blank values it was failing because it is a number field
+  and number fields need to allow explicit null values when left blank.
+- Rename the mayan_task_manager app to task_manager.
+- Make the task manager translatable.
+- Add Turkish to the list of processes languages.
+
+
+Removals
+--------
+* None
+
+Upgrading from a previous version
+---------------------------------
+
+Using PIP
+~~~~~~~~~
+
+Type in the console::
+
+    $ pip install -U mayan-edms
+
+the requirements will also be updated automatically.
+
+Using Git
+~~~~~~~~~
+
+If you installed Mayan EDMS by cloning the Git repository issue the commands::
+
+    $ git reset --hard HEAD
+    $ git pull
+
+otherwise download the compressed archived and uncompress it overriding the
+existing installation.
+
+Next upgrade/add the new requirements::
+
+    $ pip install --upgrade -r requirements.txt
+
+Common steps
+~~~~~~~~~~~~
+
+Migrate existing database schema with::
+
+    $ mayan-edms.py performupgrade
+
+Add new static media::
+
+    $ mayan-edms.py collectstatic --noinput
+
+The upgrade procedure is now complete.
+
+
+Backward incompatible changes
+=============================
+
+* None
+
+Bugs fixed or issues closed
+===========================
+
+* `GitLab issue #215 <https://gitlab.com/mayan-edms/mayan-edms/issues/215>`_ Download text contents
+
+
+.. _PyPI: https://pypi.python.org/pypi/mayan-edms/

mayan/apps/ocr/apps.py

@@ -23,7 +23,8 @@ from rest_api.classes import APIEndPoint
 
 from .handlers import initialize_new_ocr_settings, post_version_upload_ocr
 from .links import (
-    link_document_content, link_document_ocr_erros_list, link_document_submit,
+    link_document_content, link_document_ocr_download,
+    link_document_ocr_erros_list, link_document_submit,
     link_document_submit_all, link_document_submit_multiple,
     link_document_type_ocr_settings, link_document_type_submit,
     link_entry_list
@@ -130,9 +131,13 @@ class OCRApp(MayanAppConfig):
             links=(link_document_type_ocr_settings,), sources=(DocumentType,)
         )
         menu_secondary.bind_links(
-            links=(link_document_content, link_document_ocr_erros_list,),
+            links=(
+                link_document_content, link_document_ocr_erros_list,
+                link_document_ocr_download
+            ),
             sources=(
-                'ocr:document_content', 'ocr:document_ocr_error_list'
+                'ocr:document_content', 'ocr:document_ocr_error_list',
+                'ocr:document_ocr_download',
             )
         )
         menu_secondary.bind_links(

mayan/apps/ocr/links.py

@@ -41,3 +41,8 @@ link_document_ocr_erros_list = Link(
     permissions=(permission_ocr_content_view,), text=_('OCR errors'),
     view='ocr:document_ocr_error_list'
 )
+link_document_ocr_download = Link(
+    args='resolved_object.id', icon='fa fa-file-text-o',
+    permissions=(permission_ocr_content_view,), text=_('Download OCR text'),
+    view='ocr:document_ocr_download'
+)

mayan/apps/ocr/tests/test_views.py

@@ -1,10 +1,12 @@
 from __future__ import unicode_literals
 
 from django.test import override_settings
+from django.utils.encoding import force_text
 
 from documents.tests.test_views import GenericDocumentViewTestCase
 
 from ..permissions import permission_ocr_content_view
+from ..utils import get_document_ocr_content
 
 
 @override_settings(OCR_AUTO_OCR=True)
@@ -35,3 +37,26 @@ class OCRViewsTestCase(GenericDocumentViewTestCase):
         self.assertContains(
             response, 'Mayan EDMS Documentation', status_code=200
         )
+
+    def test_document_ocr_download_view_no_permission(self):
+        response = self.get(
+            'ocr:document_ocr_download', args=(self.document.pk,)
+        )
+
+        self.assertEqual(response.status_code, 403)
+
+    def test_document_download_view_with_permission(self):
+        self.expected_content_type = 'application/octet-stream; charset=utf-8'
+
+        self.grant(permission=permission_ocr_content_view)
+        response = self.get(
+            'ocr:document_ocr_download', args=(self.document.pk,)
+        )
+
+        self.assertEqual(response.status_code, 200)
+
+        self.assert_download_response(
+            response, content=(
+                ''.join(get_document_ocr_content(document=self.document))
+            ),
+        )

mayan/apps/ocr/urls.py

@@ -6,9 +6,9 @@ from .api_views import (
     APIDocumentOCRView, APIDocumentPageContentView, APIDocumentVersionOCRView
 )
 from .views import (
-    DocumentAllSubmitView, DocumentOCRContent, DocumentOCRErrorsListView,
-    DocumentSubmitView, DocumentSubmitManyView, DocumentTypeSettingsEditView,
-    DocumentTypeSubmitView, EntryListView
+    DocumentAllSubmitView, DocumentOCRContent, DocumentOCRDownloadView,
+    DocumentOCRErrorsListView, DocumentSubmitView, DocumentSubmitManyView,
+    DocumentTypeSettingsEditView, DocumentTypeSubmitView, EntryListView
 )
 
 urlpatterns = [
@@ -41,6 +41,10 @@ urlpatterns = [
         r'^documents/(?P<pk>\d+)/ocr/errors/$',
         DocumentOCRErrorsListView.as_view(), name='document_ocr_error_list'
     ),
+    url(
+        r'^documents/(?P<pk>\d+)/ocr/download/$',
+        DocumentOCRDownloadView.as_view(), name='document_ocr_download'
+    ),
     url(r'^all/$', EntryListView.as_view(), name='entry_list'),
 ]
 

mayan/apps/ocr/utils.py

@@ -0,0 +1,14 @@
+from __future__ import unicode_literals
+
+from django.utils.encoding import force_unicode
+from django.utils.html import conditional_escape
+
+
+def get_document_ocr_content(document):
+    for page in document.pages.all():
+        try:
+            page_content = page.ocr_content.content
+        except DocumentPageContent.DoesNotExist:
+            pass
+        else:
+            yield conditional_escape(force_unicode(page_content))

mayan/apps/ocr/views.py

@@ -8,8 +8,8 @@ from django.utils.translation import ugettext_lazy as _
 
 from acls.models import AccessControlList
 from common.generics import (
-    ConfirmView, FormView, SingleObjectDetailView, SingleObjectEditView,
-    SingleObjectListView
+    ConfirmView, FormView, SingleObjectDetailView, SingleObjectDownloadView,
+    SingleObjectEditView, SingleObjectListView
 )
 from common.mixins import MultipleInstanceActionMixin
 from documents.models import Document, DocumentType
@@ -20,6 +20,7 @@ from .permissions import (
     permission_ocr_content_view, permission_ocr_document,
     permission_document_type_ocr_setup
 )
+from .utils import get_document_ocr_content
 
 
 class DocumentAllSubmitView(ConfirmView):
@@ -174,3 +175,16 @@ class DocumentOCRErrorsListView(SingleObjectListView):
 
     def get_queryset(self):
         return self.get_document().latest_version.ocr_errors.all()
+
+
+class DocumentOCRDownloadView(SingleObjectDownloadView):
+    model = Document
+    object_permission = permission_ocr_content_view
+
+    def get_file(self):
+        file_object = DocumentOCRDownloadView.TextIteratorIO(
+            iterator=get_document_ocr_content(document=self.get_object())
+        )
+        return DocumentOCRDownloadView.VirtualFile(
+            file=file_object, name='{}-OCR'.format(self.get_object())
+        )