Added support for the command line program pdftotext from the poppler-utils packages to extract text from PDF documents without doing OCR
This commit is contained in:
@@ -6,3 +6,4 @@ TESSERACT_LANGUAGE = getattr(settings, 'OCR_TESSERACT_LANGUAGE', u'eng')
|
||||
REPLICATION_DELAY = getattr(settings, 'OCR_REPLICATION_DELAY', 10) # In seconds
|
||||
NODE_CONCURRENT_EXECUTION = getattr(settings, 'OCR_NODE_CONCURRENT_EXECUTION', 1)
|
||||
AUTOMATIC_OCR = getattr(settings, 'OCR_AUTOMATIC_OCR', False)
|
||||
PDFTOTEXT_PATH = getattr(settings, 'OCR_PDFTOTEXT_PATH', u'/usr/bin/pdftotext')
|
||||
|
||||
Reference in New Issue
Block a user