def test_counts_correct_amount_of_paragraphs_for_complex_56(self):
result = interleave.zip_sentences(
interleave.build_paragraphs(
interleave.sanitize_text(self.complex_PDF_5)),
interleave.build_paragraphs(
interleave.sanitize_text(self.complex_PDF_6)))
self.assertEqual(69, len(result))
def test_zip_sentences_to_tuple(self):
list1 = '\n\n' + self.short_text
list2 = '\n\n' + self.short_text
self.assertEqual(
self.processed_text,
interleave.zip_sentences(
interleave.build_paragraphs(interleave.sanitize_text(list1)),
interleave.build_paragraphs(interleave.sanitize_text(list2))))
def test_edge_valid_nonroman_string(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.edge_complex_7))
self.assertEqual(4, len(result))
def test_edge_marks_bad_paragraph_parse(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.edge_bad_parse))
self.assertEqual(3, len(result))
self.assertIn('2. PARSE ERROR', result)
def test_edge_case_ignore_trailing_tables(self):
result = interleave.sanitize_text(self.edge_final_paragraph)[0]
self.assertNotIn(self.table_title, result)
def test_edge_case_isolate_first_paragraph(self):
result = interleave.build_paragraphs(
interleave.sanitize_text(self.edge_first_paragraph))
self.assertEqual(1, len(result))
def test_edge_case_missing_paragraphs(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.edge_missing_paragraphs))
self.assertEqual(7, len(result)) # Expect seven paragraphs
def test_edge_case_line_starts_with_numeric_sentence_end(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.edge_numbers))
self.assertEqual(7, len(result)) # Expect seven paragraphs
def test_counts_up_to_1000_paragraphs(self):
result = interleave.build_paragraphs(
interleave.sanitize_text(self.thousand_paragraphs))
self.assertEqual(1000, len(result))
def test_edge_case_strip_EPA_sigblock_2(self):
result = '\n'.join(interleave.sanitize_text(self.edge_EPA_sigblock_2))
self.assertNotIn(self.EPA_signature_2, result)
def test_removes_nbsp_formfeed_page_breaks(self):
result = interleave.sanitize_text(self.nbsp_formfeed)
self.assertNotIn(chr(160), result)
self.assertNotIn(chr(12), result)
def test_removes_page_headers(self):
self.assertNotRegex('\n'.join(interleave.sanitize_text(self.headers)),
r'(\fC.*\d\n)')
def test_removes_page_numbers(self):
self.assertNotRegex(
'\n'.join(interleave.sanitize_text(self.pagenumbers)), r'\n\d+ \n')
def test_splits_multipage_paragraphs(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.multipage_text))
self.assertEqual(self.split_multipage_text, result)
def test_splits_short_sentences(self):
result = interleave.build_paragraphs(
interleave.sanitize_text('\n\n' + self.short_text))
self.assertEqual(self.split_simple_text, result)