def test_docx_writing():
filename = 'test_data/small_table.docx'
xml = get_docx_xml(filename)
output = ''.join([random.choice('abcdef')
for _ in range(10)]) + '.docx' # noqa: S311
write_new_document(filename, str(xml), output)
xml_2 = get_docx_xml(output)
assert xml == xml_2
os.remove(output)
def test_remove_tables_and_bodies():
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
new_soup, references_tb, references_body = _remove_tables_and_bodies(soup)
assert len(references_tb) == 0
assert len(references_body) == 4
for ref in references_body:
assert ref in str(new_soup)
def test_extract_tags():
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
new_soup, references = _extract_tags(soup, _find_first_r_tag)
assert len(references) == 1
assert list(references.keys())[0] in str(new_soup)
assert len(list(new_soup.stripped_strings)) != len(
list(soup.stripped_strings))
def test_extract_headers():
assert extract_headers(BeautifulSoup('', 'html.parser')) == []
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
assert extract_headers(soup) == [
'Article 6.2.3. Auto surveillance des niveaux sonores',
'Chapitre 6.3 – Vibrations',
]
def test_guess_body_font_size():
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
assert _guess_body_font_size(soup) == 24
xml = '<w></w>'
soup = BeautifulSoup(xml, 'lxml-xml')
with pytest.raises(DocxNoTextError):
_guess_body_font_size(soup)
def test_build_structured_text_from_docx_xml():
xml = get_docx_xml('test_data/small_text.docx')
res = build_structured_text_from_docx_xml(xml)
assert res.title.text == ''
assert len(res.sections) == 2
assert len(res.sections[0].sections) == 0
assert res.sections[
0].title.text == 'Article 6.2.3. Auto surveillance des niveaux sonores'
assert len(res.sections[1].sections) == 0
assert res.sections[1].title.text == 'Chapitre 6.3 – Vibrations'
def test_replace_small_tables():
filename = 'test_data/small_table.docx'
xml_str = get_docx_xml(filename)
soup = BeautifulSoup(xml_str, 'lxml-xml')
assert len(list(soup.find_all('w:tbl'))) == 1
assert len(list(soup.find_all('w:p'))) == 5
assert len(list(soup.find_all('w:tc'))) == 3
soup = _replace_small_tables(soup)
assert len(list(soup.find_all('w:tbl'))) == 0
assert len(list(soup.find_all('w:p'))) == 5
assert len(list(soup.find_all('w:tc'))) == 0
def test_replace_tables_and_body_text_with_empty_p():
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
new_soup = _replace_tables_and_body_text_with_empty_p(soup)
assert list(new_soup.stripped_strings) == [
'Article 6.2.3. Auto surveillance des niveaux sonores',
'Chapitre 6.3 – Vibrations',
]
xml = ''
soup = BeautifulSoup(xml, 'lxml-xml')
new_soup = _replace_tables_and_body_text_with_empty_p(soup, 10)
assert list(new_soup.stripped_strings) == []
def test_extract_elements():
xml = get_docx_xml('test_data/small_text.docx')
soup = BeautifulSoup(xml, 'lxml-xml')
elements = _extract_elements(soup)
assert len(elements) == 6
for element in elements:
assert not isinstance(element, Table)
assert isinstance(elements[0], str)
assert isinstance(elements[1], str)
assert isinstance(elements[2], Title) and check_is_title(
elements[2]).level == 3
assert isinstance(elements[3], str)
assert isinstance(elements[4], Title) and check_is_title(
elements[4]).level == 2
assert isinstance(elements[5], str)
def test_copy_soup():
filename = 'test_data/small_table.docx'
xml_str = get_docx_xml(filename)
soup = BeautifulSoup(xml_str, 'lxml-xml')
soup_copy = _copy_soup(soup)
assert id(soup) != id(soup_copy)
def test_get_docx_xml():
xml = get_docx_xml('test_data/simple_table.docx')
assert len(xml) == 6580