aaf9f7a8be
Add the 'ocr_content' attribute to documents to allow access to a document's OCR content for indexing and other purposes. Fixes the OCR indexing failing test. Signed-off-by: Roberto Rosario <roberto.rosario.gonzalez@gmail.com>
24 lines
608 B
Python
24 lines
608 B
Python
from __future__ import unicode_literals
|
|
|
|
from django.apps import apps
|
|
from django.utils.encoding import force_text
|
|
|
|
|
|
def get_document_ocr_content(document):
|
|
DocumentPageOCRContent = apps.get_model(
|
|
app_label='ocr', model_name='DocumentPageOCRContent'
|
|
)
|
|
|
|
for page in document.pages.all():
|
|
try:
|
|
page_content = page.ocr_content.content
|
|
except DocumentPageOCRContent.DoesNotExist:
|
|
yield ''
|
|
else:
|
|
yield force_text(page_content)
|
|
|
|
|
|
@property
|
|
def document_property_ocr_content(self):
|
|
return ' '.join(get_document_ocr_content(self))
|