def setUp(self):
super(TestPageExtractor, self).setUp()
self.visitor = PageVisitor()
def setUp(self):
super(TestPageExtractor, self).setUp()
self.visitor = PageVisitor()
class TestPageExtractor(BaseTestCase):
def setUp(self):
super(TestPageExtractor, self).setUp()
self.visitor = PageVisitor()
def assert_extract(
self, page, specs=None, compat=None, footnotes=None, issues=None):
parsed = kumascript_grammar.parse(page)
elements = self.visitor.visit(parsed)
extractor = PageExtractor(elements=elements, feature=self.feature)
extracted = extractor.extract()
self.assertEqual(specs or [], extracted['specs'])
self.assertEqual(compat or [], extracted['compat'])
self.assertEqual(footnotes, extracted['footnotes'])
self.assertEqual(issues or [], extracted['issues'])
def test_valid_spec_section(self):
sample_spec_section, expected_specs = self.get_sample_specs()
self.assert_extract(sample_spec_section, specs=expected_specs)
def test_invalid_spec_section(self):
page = '<h2>Specifications</h2><p>Incomplete</p>'
self.assert_extract(page, issues=[('skipped_content', 23, 40, {})])
def test_valid_compat_section(self):
sample_compat_section, expected_compat = self.get_sample_compat()
self.assert_extract(sample_compat_section, compat=expected_compat)
def test_invalid_compat_section(self):
page = '<h2>Browser Compatibility</h2><p>Not present</p>'
self.assert_extract(page, issues=[('skipped_content', 30, 48, {})])
def test_full_page(self):
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<h2>Other Text</h2>
<p>Here's some other content</p>
%s
%s
<h2>Other Pages</h2>
<p>See <a href="/foo">foo</a></p>
""" % (sample_spec_section, sample_compat_section)
self.assert_extract(page, specs=expected_specs, compat=expected_compat)
def test_full_page_reversed_sections(self):
# https://bugzilla.mozilla.org/show_bug.cgi?id=1175177
# https://developer.mozilla.org/en-US/docs/Web/API/Blob/slice
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<h2>Other Text</h2>
<p>Here's some other content</p>
<h3>More Detail</h3>
<p>Trigger <h3> check not in a compat section.</p>
%s
%s
<h2>Other Pages</h2>
<p>See <a href="/foo">foo</a></p>
""" % (sample_compat_section, sample_spec_section)
self.assert_extract(page, specs=expected_specs, compat=expected_compat)
def test_compat_h3(self):
# https://developer.mozilla.org/en-US/docs/Web/API/MozContact/key
sample_compat_section, expected_compat = self.get_sample_compat()
page = (
sample_compat_section +
'<h3 id="Gecko Gecko">Gecko Note</h3>\n<p>A note</p>')
issues = [('skipped_h3', 354, 390, {'h3': 'Gecko Note'})]
self.assert_extract(page, compat=expected_compat, issues=issues)
def test_div_wrapped(self):
# https://developer.mozilla.org/en-US/docs/Web/API/Document/execCommand
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<div>
%s
%s
</div>
""" % (sample_spec_section, sample_compat_section)
issue = ('no_data', 0, 24, {})
self.assert_extract(page, issues=[issue])
class TestPageExtractor(BaseTestCase):
def setUp(self):
super(TestPageExtractor, self).setUp()
self.visitor = PageVisitor()
def assert_extract(self,
page,
specs=None,
compat=None,
footnotes=None,
issues=None):
parsed = kumascript_grammar.parse(page)
elements = self.visitor.visit(parsed)
extractor = PageExtractor(elements=elements, feature=self.feature)
extracted = extractor.extract()
self.assertEqual(specs or [], extracted['specs'])
self.assertEqual(compat or [], extracted['compat'])
self.assertEqual(footnotes, extracted['footnotes'])
self.assertEqual(issues or [], extracted['issues'])
def test_valid_spec_section(self):
sample_spec_section, expected_specs = self.get_sample_specs()
self.assert_extract(sample_spec_section, specs=expected_specs)
def test_invalid_spec_section(self):
page = '<h2>Specifications</h2><p>Incomplete</p>'
self.assert_extract(page, issues=[('skipped_content', 23, 40, {})])
def test_valid_compat_section(self):
sample_compat_section, expected_compat = self.get_sample_compat()
self.assert_extract(sample_compat_section, compat=expected_compat)
def test_invalid_compat_section(self):
page = '<h2>Browser Compatibility</h2><p>Not present</p>'
self.assert_extract(page, issues=[('skipped_content', 30, 48, {})])
def test_full_page(self):
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<h2>Other Text</h2>
<p>Here's some other content</p>
%s
%s
<h2>Other Pages</h2>
<p>See <a href="/foo">foo</a></p>
""" % (sample_spec_section, sample_compat_section)
self.assert_extract(page, specs=expected_specs, compat=expected_compat)
def test_full_page_reversed_sections(self):
# https://bugzilla.mozilla.org/show_bug.cgi?id=1175177
# https://developer.mozilla.org/en-US/docs/Web/API/Blob/slice
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<h2>Other Text</h2>
<p>Here's some other content</p>
<h3>More Detail</h3>
<p>Trigger <h3> check not in a compat section.</p>
%s
%s
<h2>Other Pages</h2>
<p>See <a href="/foo">foo</a></p>
""" % (sample_compat_section, sample_spec_section)
self.assert_extract(page, specs=expected_specs, compat=expected_compat)
def test_compat_h3(self):
# https://developer.mozilla.org/en-US/docs/Web/API/MozContact/key
sample_compat_section, expected_compat = self.get_sample_compat()
page = (sample_compat_section +
'<h3 id="Gecko Gecko">Gecko Note</h3>\n<p>A note</p>')
issues = [('skipped_h3', 354, 390, {'h3': 'Gecko Note'})]
self.assert_extract(page, compat=expected_compat, issues=issues)
def test_div_wrapped(self):
# https://developer.mozilla.org/en-US/docs/Web/API/Document/execCommand
sample_spec_section, expected_specs = self.get_sample_specs()
sample_compat_section, expected_compat = self.get_sample_compat()
page = """\
<p>Some lead content</p>
<div>
%s
%s
</div>
""" % (sample_spec_section, sample_compat_section)
issue = ('no_data', 0, 24, {})
self.assert_extract(page, issues=[issue])