def test_pdf_to_text_all():
'''test type textbox is dict'''
cwd = os.getcwd()
loc = '{}/pdf2textbox/data'.format(cwd)
file_loc = '{}/Id=MMP15%2F57_5694_5696.pdf'.format(loc)
with open(file_loc, 'br') as pdf:
textbox = _pdf_to_text_all(pdf, verbose=False)
assert isinstance(textbox, dict)
def test_convert_text_only():
'''assert that this file has one column and no header'''
cwd = os.getcwd()
loc = '{}/pdf2textbox/data'.format(cwd)
pdf_loc = '{}/01a_only_text.pdf'.format(loc)
pdf = _get_pdf_file(pdf_loc, verbose=False)
boxes = _pdf_to_text_all(pdf, verbose=False)
assert boxes[1]['column']
assert boxes[2]['column']
def test_convert_two_cols():
'''assert that this file has two columns'''
cwd = os.getcwd()
loc = '{}/pdf2textbox/data'.format(cwd)
pdf_loc = '{}/02a_two_cols.pdf'.format(loc)
pdf = _get_pdf_file(pdf_loc, verbose=False)
boxes = _pdf_to_text_all(pdf, verbose=False)
assert boxes[1]['left_column']
assert boxes[1]['right_column']
assert boxes[2]['column']
def test_textbox_structure():
'''test if textbox contains pages, header, left and right column'''
cwd = os.getcwd()
loc = '{}/pdf2textbox/data'.format(cwd)
file_loc = '{}/Id=MMP15%2F57_5694_5696.pdf'.format(loc)
with open(file_loc, 'br') as pdf:
textbox = _pdf_to_text_all(pdf, verbose=False)
for key, val in textbox.items():
assert isinstance(key, int)
assert isinstance(val, dict)
for subkey, subval in val.items():
assert subkey in ['header', 'left_column', 'right_column']
assert isinstance(subval, list)
def test_convert_three_cols_and_header():
'''assert that this file has three columns and a header'''
cwd = os.getcwd()
loc = '{}/pdf2textbox/data'.format(cwd)
pdf_loc = '{}/06a_three_cols_and_header.pdf'.format(loc)
pdf = _get_pdf_file(pdf_loc, verbose=False)
boxes = _pdf_to_text_all(pdf, verbose=False)
assert boxes[1]['header']
assert boxes[1]['left_column']
assert boxes[1]['center_column']
assert boxes[1]['right_column']
assert boxes[2]['header']
assert boxes[2]['left_column']
assert boxes[2]['right_column']
