Add support for downloading a document's OCR text.

Closes GitLab issue #215.

Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>
This commit is contained in:
Roberto Rosario
2017-07-01 01:07:23 -04:00
parent 610e10e85a
commit 916c3497c4
8 changed files with 165 additions and 9 deletions
+14
View File
@@ -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))