def test_get_plaintext_document_body(tmpdir):
input = [u"Some text\n", u"on multiple lines\n"]
f = tmpdir.join("plain.txt")
f.write("".join(input))
assert input == get_plaintext_document_body(str(f))
with pytest.raises(UnknownDocumentTypeError) as excinfo:
html = "<html><body>Some page</body></html>"
f = tmpdir.join("page.html")
f.write(html)
get_plaintext_document_body(str(f))
assert 'text/html' in excinfo.value.args
def test_clean_pdf_before_run(tmp_path, pdf_files):
tmp_file_path = tmp_path / "packed.pdf"
pdf = pdf_files[7]
with open(pdf, 'rb') as input, open(tmp_file_path, 'wb') as tmp_out:
tmp_out.write(input.read())
text = get_plaintext_document_body(tmp_file_path.as_posix())
assert text == ['Test\n', '\x0c']