def test_non_ocr_pdf(self) :
"""
Access an valid pdf which hasn't been OCR'd
"""
file_name = 'non_ocr_file.pdf'
text_extractor = TextExtractor(
source_file = file_name,
source_directory= TextExtractorTest.test_directory,
working_directory = '/tmp',
testing = True)
actual_results = text_extractor.get_file_contents_as_array()
self.assertEquals(len(actual_results), 0)
def test_valid_pdf(self) :
"""
Access an empty file with .pdf suffix
This could well break when we test the file type properly
"""
expected_results = [
'Test 1\n',
'Test 2\n',
'\n'
]
file_name = 'test_file1.pdf'
text_extractor = TextExtractor(
source_file = file_name,
source_directory= TextExtractorTest.test_directory,
working_directory = '/tmp',
testing = True)
actual_results = text_extractor.get_file_contents_as_array()
self.assertEquals(expected_results, actual_results)
