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:
Roberto Rosario
2011-04-15 23:59:52 -04:00
parent 73a52293e8
commit eaaaa5b645
5 changed files with 49 additions and 13 deletions
+1
View File
@@ -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')