def test_rfc_minimal():
expected_entry = AtomEntry(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Atom-Powered Robots Run Amok'),
id_='urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a',
updated=datetime.datetime(2003, 12, 13, 18, 30, 2, tzinfo=tzutc()),
authors=[AtomPerson(name='John Doe', uri=None, email=None)],
contributors=[],
links=[
AtomLink(href='http://example.org/2003/12/13/atom03',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[],
published=None,
rights=None,
summary=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Some text.'),
content=None,
source=None)
expected = AtomFeed(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Example Feed'),
id_='urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6',
updated=datetime.datetime(2003, 12, 13, 18, 30, 2, tzinfo=tzutc()),
authors=[AtomPerson(name='John Doe', uri=None, email=None)],
contributors=[],
links=[
AtomLink(href='http://example.org/',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[],
generator=None,
subtitle=None,
rights=None,
icon=None,
logo=None,
entries=[expected_entry])
assert parse_atom_file('tests/atom/rfc-minimal.xml') == expected
def test_broken_empty_fields():
# As a general rule, XML tags should not be empty. In practice optional
# fields are sometimes present in the feed but with an empty tag
parsed = parse_atom_file('tests/atom/broken-empty-summary.xml')
assert parsed.entries[0].summary is None
parsed = parse_atom_file('tests/atom/broken-empty-title.xml')
assert parsed.title is None
parsed = parse_atom_file('tests/atom/broken-empty-updated.xml')
assert parsed.updated is None
parsed = parse_atom_file('tests/atom/broken-empty-author.xml')
assert parsed.authors == []
assert parsed.entries[0].authors == []
parsed = parse_atom_file('tests/atom/broken-missing-author-name.xml')
assert parsed.authors == []
assert parsed.entries[0].authors == []
# Require fields (id...) that have empty tags should throw an error
with pytest.raises(FeedParseError):
parse_atom_file('tests/atom/broken-empty-id.xml')
def test_rfc_unicode():
expected_entry_1 = AtomEntry(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Article n°1'),
id_='http://richard.plop/2017/6/5/article-1',
updated=datetime.datetime(2017, 6, 5, 0, 0, tzinfo=tzutc()),
authors=[AtomPerson(name='Rïchàrd Plop', uri=None, email=None)],
contributors=[],
links=[
AtomLink(href='http://richard.plop/2017/6/5/article-1',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[],
published=None,
rights=None,
summary=None,
content=AtomTextConstruct(text_type=AtomTextType.html,
lang=None,
value='<p></p>'),
source=None)
expected_entry_2 = AtomEntry(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Unicode snowman'),
id_='http://richard.plop/2017/6/5/article-2',
updated=datetime.datetime(2016, 12, 29, 0, 0, tzinfo=tzutc()),
authors=[AtomPerson(name='Rïchàrd Plop', uri=None, email=None)],
contributors=[],
links=[
AtomLink(href='http://richard.plop/2017/6/5/unicode-snowman',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[],
published=None,
rights=None,
summary=None,
content=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='☃'),
source=None)
source_feed = AtomFeed(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Example, Inc.'),
id_='http://example.org/',
updated=datetime.datetime(2003, 12, 13, 18, 30, 2, tzinfo=tzutc()),
authors=[AtomPerson(name='Foo Bar', uri=None, email=None)],
contributors=[],
links=[],
categories=[],
generator=None,
subtitle=None,
rights=None,
icon=None,
logo=None,
entries=[])
expected_entry_3 = AtomEntry(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Unicode snowman 3'),
id_='http://richard.plop/2017/6/5/article-3',
updated=datetime.datetime(2016, 12, 29, 0, 0, tzinfo=tzutc()),
authors=[AtomPerson(name='Foo Bar', uri=None, email=None)],
contributors=[],
links=[
AtomLink(href='http://richard.plop/2017/6/5/unicode-snowman',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[],
published=None,
rights=None,
summary=None,
content=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='☃'),
source=source_feed)
expected = AtomFeed(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value="Rïchàrd Plop's blog"),
id_='http://richard.plop/feed.atom',
updated=datetime.datetime(2017, 6, 5, 0, 0, tzinfo=tzutc()),
authors=[],
contributors=[],
links=[
AtomLink(href='http://richard.plop/',
rel=None,
type_=None,
hreflang=None,
title=None,
length=None),
AtomLink(href='http://richard.plop/feed.atom',
rel='self',
type_=None,
hreflang=None,
title=None,
length=None)
],
categories=[AtomCategory(term='python', scheme=None, label='Python')],
generator=AtomGenerator(name='Werkzeug', uri=None, version=None),
subtitle=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value="Rïchàrd Plop's personal blog."),
rights=None,
icon=None,
logo=None,
entries=[expected_entry_1, expected_entry_2, expected_entry_3])
assert parse_atom_file('tests/atom/unicode.xml') == expected
def test_rfc_more_extensive():
expected_entry = AtomEntry(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Atom draft-07 snapshot'),
id_='tag:example.org,2003:3.2397',
updated=datetime.datetime(2005, 7, 31, 12, 29, 29, tzinfo=tzutc()),
authors=[
AtomPerson(name='Mark Pilgrim',
uri='http://example.org/',
email='*****@*****.**')
],
contributors=[
AtomPerson(name='Sam Ruby', uri=None, email=None),
AtomPerson(name='Joe Gregorio', uri=None, email=None)
],
links=[
AtomLink(href='http://example.org/2005/04/02/atom',
rel='alternate',
type_='text/html',
hreflang=None,
title=None,
length=None),
AtomLink(href='http://example.org/audio/ph34r_my_podcast.mp3',
rel='enclosure',
type_='audio/mpeg',
hreflang=None,
title=None,
length=1337)
],
categories=[],
published=datetime.datetime(2003,
12,
13,
8,
29,
29,
tzinfo=tzoffset(None, -14400)),
rights=None,
summary=None,
content=AtomTextConstruct(text_type=AtomTextType.xhtml,
lang=None,
value=''),
source=None)
expected = AtomFeed(
title=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='dive into mark'),
id_='tag:example.org,2003:3',
updated=datetime.datetime(2005, 7, 31, 12, 29, 29, tzinfo=tzutc()),
authors=[],
contributors=[],
links=[
AtomLink(href='http://example.org/',
rel='alternate',
type_='text/html',
hreflang='en',
title=None,
length=None),
AtomLink(href='http://example.org/feed.atom',
rel='self',
type_='application/atom+xml',
hreflang=None,
title=None,
length=None)
],
categories=[],
generator=AtomGenerator(name='Example Toolkit',
uri='http://www.example.com/',
version='1.0'),
subtitle=AtomTextConstruct(text_type=AtomTextType.html,
lang=None,
value='A <em>lot</em> of effort\n '
'went into making this effortless'),
rights=AtomTextConstruct(text_type=AtomTextType.text,
lang=None,
value='Copyright (c) 2003, Mark Pilgrim'),
icon=None,
logo=None,
entries=[expected_entry])
assert (parse_atom_file('tests/atom/rfc-more-extensive.xml') == expected)
def test_broken_missing_updated():
# The RFC mandates that feed and entries have an updated date
# but this is rarely the case in practice.
parsed = parse_atom_file('tests/atom/broken-missing-updated.xml')
assert parsed.updated is None
assert parsed.entries[0].updated is None
def test_broken_missing_author():
# The RFC mandates that at least one of feed or entries must have an author
# but this is rarely the case in practice.
parsed = parse_atom_file('tests/atom/broken-xkcd.xml')
assert parsed.authors == list()
assert parsed.entries[0].authors == list()
def test_broken_missing_author_name():
with pytest.raises(FeedParseError):
parse_atom_file('tests/atom/broken-missing-author-name.xml')
def test_broken_missing_id():
with pytest.raises(FeedParseError):
parse_atom_file('tests/atom/broken-missing-id.xml')