def test_parse_several_paragraph_norm():
BGB_27_DIV = html.fromstring(HTML_BGB_27)
result = extract_from_div(BGB_27_DIV)
paragraphs = result["paragraphs"]
assert 3 == len(paragraphs)
def test_parse_norm():
BGB_13_DIV = html.fromstring(HTML_BGB_13)
result = extract_from_div(BGB_13_DIV)
assert isinstance(result, dict)
assert result.keys() == {"type", "norm", "title", "paragraphs"}
assert result["type"] == "norm"
assert result["norm"] == "§ 13"
assert result["title"] == "Verbraucher"
assert len(result["paragraphs"]) == 1
def test_parse_subsub_paragraph_norm():
BGB_207_DIV = html.fromstring(HTML_BGB_207)
result = extract_from_div(BGB_207_DIV)
lens = [0, 2, 0, 0, 0]
subs = result["paragraphs"][0]["sub"]
assert 5 == len(subs)
assert lens == [len(sub["sub"]) for sub in subs]
def test_very_complex_norm():
BGB_308_DIV = html.fromstring(HTML_BGB_308)
result = extract_from_div(BGB_308_DIV)
subs = result["paragraphs"][0]["sub"]
assert 10 == len(subs)
assert 2 == len(subs[6]["sub"])
assert 2 == len(subs[8]["sub"])
assert 2 == len(subs[9]["sub"])
def test_parse_sub_paragraph_norm():
BGB_81_DIV = html.fromstring(HTML_BGB_81)
result = extract_from_div(BGB_81_DIV)
paragraphs = result["paragraphs"]
assert 2 == len(paragraphs)
first_paragraph = paragraphs[0]
assert len(first_paragraph["sub"]) == 5
assert len(first_paragraph["text"]) > 42