def fx_test_feeds():
authors = [Person(name='vio')]
feed = Feed(id='http://feedone.com/',
authors=authors,
title='Feed One',
updated_at=datetime.datetime(2013,
10,
29,
20,
55,
30,
tzinfo=utc))
updated_feed = Feed(id='http://feedone.com/',
authors=authors,
title=Text(value='Feed One'),
updated_at=datetime.datetime(2013,
10,
30,
20,
55,
30,
tzinfo=utc))
entry = Entry(id='http://feedone.com/1',
authors=authors,
title=Text(value='Test Entry'),
updated_at=datetime.datetime(2013,
10,
30,
20,
55,
30,
tzinfo=utc))
updated_feed.entries.append(entry)
return feed, updated_feed
def test_text_str():
assert text_type(Text(type='text', value='Hello world')) == 'Hello world'
assert (text_type(Text(type='text', value='<p>Hello <em>world</em></p>'))
== '<p>Hello <em>world</em></p>')
assert text_type(Text(type='html', value='Hello world')) == 'Hello world'
assert (text_type(Text(type='html', value='<p>Hello <em>world</em></p>'))
== 'Hello world')
def fx_test_entries():
entry1 = Entry(
id='http://feed.com/entry1', title=Text(value='new1'),
updated_at=datetime.datetime(2013, 1, 1, 0, 0, 0, tzinfo=utc))
entry2 = Entry(
id='http://feed.com/entry2', title=Text(value='new2'),
updated_at=datetime.datetime(2013, 1, 1, 0, 0, 1, tzinfo=utc))
return entry1, entry2
def test_subscription_set_subscribe(subs):
feed = Feed(id='urn:earthreader:test:test_subscription_set_subscribe',
title=Text(value='Feed title'))
feed.links.extend([
Link(uri='http://example.com/index.xml',
relation='self',
mimetype='application/atom+xml'),
Link(uri='http://example.com/',
relation='alternate',
mimetype='text/html')
])
rv = subs.subscribe(feed, icon_uri='http://example.com/favicon.ico')
sub = next(iter(subs))
assert rv is sub
assert sub.feed_id == '0691e2f0c3ea1d7fa9da48e14a46ac8077815ad3'
assert sub.icon_uri == 'http://example.com/favicon.ico'
assert sub.label == 'Feed title'
assert sub.feed_uri == 'http://example.com/index.xml'
assert sub.alternate_uri == 'http://example.com/'
subs.remove(sub)
assert not subs
feed.links.append(
Link(uri='http://example.com/favicon.ico', relation='shortcut icon'))
rv = subs.subscribe(feed)
assert rv is next(iter(subs))
assert rv == sub
def test_source():
entry = read(Entry, [b'''
<entry xmlns="http://www.w3.org/2005/Atom">
<source>
<title>Source of all knowledge</title>
<id>urn:uuid:28213c50-f84c-11d9-8cd6-0800200c9a66</id>
<updated>2003-12-13T17:46:27Z</updated>
<category term="technology"/>
<category term="business"/>
</source>
<title>Atom-Powered Robots Run Amok</title>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
'''])
source = entry.source
assert isinstance(source, Source)
assert source.title == Text(value='Source of all knowledge')
assert source.id == 'urn:uuid:28213c50-f84c-11d9-8cd6-0800200c9a66'
assert source.updated_at == datetime.datetime(2003, 12, 13, 17, 46, 27,
tzinfo=utc)
categories = source.categories
assert isinstance(categories[0], Category)
assert categories[0].term == 'technology'
assert isinstance(categories[1], Category)
assert categories[1].term == 'business'
assert len(categories) == 2
def fx_filtering_entries(fx_test_stage):
authors = [Person(name='vio')]
now = datetime.datetime(2013, 10, 30, 20, 55, 30, tzinfo=utc)
feed = Feed(id='http://feedone.com/feed/atom/', authors=authors,
title=Text(value='Feed One'),
updated_at=now)
for i in range(10):
feed.entries.append(
Entry(id='http://feedone.com/feed/atom/' + str(i) + '/',
authors=authors,
title=Text(value=str(i + 1)),
updated_at=now + datetime.timedelta(days=1) * i)
)
for i in range(5):
feed.entries[i].read = Mark(marked=True, updated_at=now)
for i in range(3, 7):
feed.entries[i].starred = Mark(marked=True, updated_at=now)
with fx_test_stage as stage:
stage.feeds[get_hash('http://feedone.com/feed/atom/')] = feed
stage.subscriptions = read(SubscriptionList, opml_for_filtering)
def test_feed_read(fx_feed):
feed = fx_feed
assert feed.title == Text(value='Example Feed')
link = feed.links[0]
assert isinstance(link, Link)
assert link.relation == 'alternate'
assert link.uri == 'http://example.org/'
assert len(feed.links) == 1
assert feed.updated_at == datetime.datetime(2003,
12,
13,
18,
30,
2,
tzinfo=utc)
authors = feed.authors
assert isinstance(authors[0], Person)
assert authors[0].name == 'John Doe'
assert isinstance(authors[1], Person)
assert authors[1].name == 'Jane Doe'
assert len(feed.authors) == 2
assert feed.id == 'urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6'
categories = feed.categories
assert isinstance(categories[0], Category)
assert categories[0].term == 'technology'
assert isinstance(categories[1], Category)
assert categories[1].term == 'business'
assert len(categories) == 2
assert feed.rights == Text(value='Public Domain')
entries = feed.entries
assert isinstance(entries[0], Entry)
assert entries[0].title == Text(value='Atom-Powered Robots Run Amok')
assert (list(entries[0].links) == [
Link(uri='http://example.org/2003/12/13/atom03')
])
assert entries[0].id == 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a'
assert entries[0].updated_at == datetime.datetime(2003,
12,
13,
18,
30,
2,
tzinfo=utc)
assert entries[0].summary == Text(value='Some text.')
assert list(entries[0].authors) == [Person(name='Jane Doe')]
assert isinstance(entries[1], Entry)
assert entries[1].title == Text(value='Danger, Will Robinson!')
assert (list(
entries[1].links) == [Link(uri='http://example.org/2003/12/13/lost')])
assert entries[1].id == 'urn:uuid:b12f2c10-ffc1-11d9-8cd6-0800200c9a66'
assert entries[1].updated_at == datetime.datetime(2003,
12,
13,
18,
30,
2,
tzinfo=utc)
assert entries[1].summary == Text(value="Don't Panic!")
assert len(entries) == 2
def test_entry_read():
# http://www.intertwingly.net/wiki/pie/FormatTests
entry = read(Entry, [
b'''
<entry xmlns="http://www.w3.org/2005/Atom">
<title>Atom-Powered Robots Run Amok</title>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
<category term="technology"/>
<category term="business"/>
<contributor>
<name>John Smith</name>
</contributor>
<contributor>
<name>Jane Doe</name>
</contributor>
</entry>
'''
])
assert entry.id == 'urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a'
assert entry.title == Text(value='Atom-Powered Robots Run Amok')
assert entry.updated_at == datetime.datetime(2003,
12,
13,
18,
30,
2,
tzinfo=utc)
assert isinstance(entry.links[0], Link)
assert entry.links[0].uri == 'http://example.org/2003/12/13/atom03'
assert entry.links[0].relation == 'alternate'
assert len(entry.links) == 1
assert isinstance(entry.summary, Text)
assert entry.summary.type == 'text'
assert entry.summary.value == 'Some text.'
assert isinstance(entry.categories[0], Category)
assert entry.categories[0].term == 'technology'
assert entry.categories[1].term == 'business'
assert len(entry.categories) == 2
assert isinstance(entry.contributors[0], Person)
assert entry.contributors[0].name == 'John Smith'
assert entry.contributors[1].name == 'Jane Doe'
assert len(entry.contributors) == 2
def test_add_as_subscription(subs):
feed = Feed(id='urn:earthreader:test:test_subscription_set_subscribe',
title=Text(value='Feed title'),
links=[
Link(relation='self',
mimetype='application/atom+xml',
uri='http://example.com/atom.xml')
])
result = CrawlResult('http://example.com/atom.xml',
feed,
hints={},
icon_url='http://example.com/favicon.ico')
sub = result.add_as_subscription(subs)
assert len(subs) == 1
assert next(iter(subs)) is sub
assert sub.feed_uri == result.url
assert sub.label == feed.title.value
assert sub.icon_uri == result.icon_url
def test_sanitized_html():
assert (Text(type='text',
value='Hello world').sanitized_html == 'Hello world')
assert (Text(type='text',
value='Hello\nworld').sanitized_html == 'Hello<br>\nworld')
assert (Text(type='text',
value='<p>Hello <em>world</em></p>').sanitized_html ==
'<p>Hello <em>world</em></p>')
assert (Text(type='html',
value='Hello world').sanitized_html == 'Hello world')
assert (Text(type='html',
value='<p>Hello <em>world</em></p>').sanitized_html ==
'<p>Hello <em>world</em></p>')
assert (Text(type='html',
value='<p>Hello</p><script>alert(1);</script>').sanitized_html
== '<p>Hello</p>')
assert (Text(type='html', value='<p>Hello</p><hr noshade>').sanitized_html
== '<p>Hello</p><hr noshade>')
def test_get_sanitized_html():
text = Text(type='text', value='Hello world')
assert text.get_sanitized_html() == text.sanitized_html == 'Hello world'
text = Text(type='text', value='Hello\nworld')
assert (text.get_sanitized_html() == text.sanitized_html ==
'Hello<br>\nworld')
text = Text(type='text', value='<p>Hello <em>world</em></p>')
assert (text.get_sanitized_html() == text.sanitized_html ==
'<p>Hello <em>world</em></p>')
text = Text(type='html', value='Hello world')
assert (text.get_sanitized_html() == text.sanitized_html == 'Hello world')
text = Text(type='html', value='<p>Hello <em>world</em></p>')
assert (text.get_sanitized_html() == text.sanitized_html ==
'<p>Hello <em>world</em></p>')
text = Text(type='html', value='<p>Hello</p><script>alert(1);</script>')
assert text.get_sanitized_html() == text.sanitized_html == '<p>Hello</p>'
text = Text(type='html', value='<p>Hello</p><hr noshade>')
assert (text.get_sanitized_html() == text.sanitized_html ==
'<p>Hello</p><hr noshade>')
text = Text(type='html', value='<a href="/abspath">abspath</a>')
assert (text.get_sanitized_html(base_uri='http://localhost/path/') ==
'<a href="http://localhost/abspath">abspath</a>')
def test_entry_str():
assert text_type(Entry(title=Text(value='Title desu'))) == 'Title desu'
assert text_type(Entry()) == ''
def xmls_for_next(request, fx_test_stage):
opml = '''
<opml version="1.0">
<head>
<title>test opml</title>
</head>
<body>
<outline text="categoryone" title="categoryone">
<outline type="atom" text="Feed One" title="Feed One"
xmlUrl="http://feedone.com/" />
<outline type="atom" text="Feed Two" title="Feed Two"
xmlUrl="http://feedtwo.com/" />
</outline>
<outline type="atom" text="Feed Three" title="Feed Three"
xmlUrl="http://feedthree.com/" />
<outline type="atom" text="Feed Four" title="Feed Three"
xmlUrl="http://feedthree.com/" />
</body>
</opml>
'''
authors = [Person(name='vio')]
feed_one = Feed(id='http://feedone.com/', authors=authors,
title=Text(value='Feed One'),
updated_at=datetime.datetime(2013, 10, 30, 20, 55, 30,
tzinfo=utc))
feed_two = Feed(id='http://feedtwo.com/', authors=authors,
title=Text(value='Feed Two'),
updated_at=datetime.datetime(2013, 10, 30, 21, 55, 30,
tzinfo=utc))
feed_three = Feed(id='http://feedthree.com/', authors=authors,
title=Text(value='Feed Three'),
updated_at=datetime.datetime(2013, 10, 30, 21, 55, 30,
tzinfo=utc))
feed_four = Feed(id='http://feedfour.com/', authors=authors,
title=Text(value='Feed Four'),
updated_at=datetime.datetime(2013, 10, 30, 21, 55, 30,
tzinfo=utc))
for i in range(25):
feed_one.entries.append(
Entry(id='http://feedone.com/' + str(24 - i),
authors=authors,
title=Text(value='Feed One: Entry ' + str(24 - i)),
updated_at=datetime.datetime(2013, 10, 30, 20, 55, 30,
tzinfo=utc) +
datetime.timedelta(days=-1)*i)
)
feed_two.entries.append(
Entry(id='http://feedtwo.com/' + str(24 - i),
authors=authors,
title=Text(value='Feed Two: Entry ' + str(24 - i)),
updated_at=datetime.datetime(2013, 10, 30, 19, 55, 30,
tzinfo=utc) +
datetime.timedelta(days=-1)*i)
)
for i in range(20):
feed_three.entries.append(
Entry(id='http://feedthree.com/' + str(19 - i),
authors=authors,
title=Text(value='Feed Three: Entry ' + str(19 - i)),
updated_at=datetime.datetime(2013, 10, 30, 20, 55, 30,
tzinfo=utc) +
datetime.timedelta(days=-1)*i)
)
for i in range(50):
feed_four.entries.append(
Entry(id='http://feedfour.com/' + str(49 - i),
authors=authors,
title=Text(value='Feed Four: Entry ' + str(49 - i)),
updated_at=datetime.datetime(2013, 10, 30, 20, 55, 30,
tzinfo=utc) +
datetime.timedelta(days=-1)*i)
)
for i in range(5):
feed_two.entries[i].read = True
feed_two.entries[i+15].read = True
for i in range(20, 50):
feed_four.entries[i].read = True
subscriptions = read(SubscriptionList, opml)
with fx_test_stage as stage:
stage.subscriptions = subscriptions
stage.feeds[get_hash('http://feedone.com/')] = feed_one
stage.feeds[get_hash('http://feedtwo.com/')] = feed_two
stage.feeds[get_hash('http://feedthree.com/')] = feed_three
stage.feeds[get_hash('http://feedfour.com/')] = feed_four
