def test_mutate_element_list():
doc = TestDoc()
assert not doc.multi_attr
assert len(doc.multi_attr) == 0
with raises(IndexError):
doc.multi_attr[0]
doc.multi_attr.append(TextElement(value='First element'))
assert doc.multi_attr
assert doc.multi_attr[0].value == 'First element'
assert len(doc.multi_attr) == 1
doc.multi_attr.insert(1, TextElement(value='Second element'))
assert doc.multi_attr[1].value == 'Second element'
assert len(doc.multi_attr) == 2
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 2
assert elements[0].text == 'First element'
assert elements[1].text == 'Second element'
doc.multi_attr[0] = TextElement(value='Replacing element')
assert doc.multi_attr[0].value == 'Replacing element'
assert len(doc.multi_attr) == 2
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 2
assert elements[0].text == 'Replacing element'
assert elements[1].text == 'Second element'
del doc.multi_attr[0]
assert doc.multi_attr[0].value == 'Second element'
assert len(doc.multi_attr) == 1
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 1
assert elements[0].text == 'Second element'
def test_mutate_element_list():
doc = TestDoc()
assert not doc.multi_attr
assert len(doc.multi_attr) == 0
with raises(IndexError):
doc.multi_attr[0]
doc.multi_attr.append(TextElement(value='First element'))
assert doc.multi_attr
assert doc.multi_attr[0].value == 'First element'
assert len(doc.multi_attr) == 1
doc.multi_attr.insert(1, TextElement(value='Second element'))
assert doc.multi_attr[1].value == 'Second element'
assert len(doc.multi_attr) == 2
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 2
assert elements[0].text == 'First element'
assert elements[1].text == 'Second element'
doc.multi_attr[0] = TextElement(value='Replacing element')
assert doc.multi_attr[0].value == 'Replacing element'
assert len(doc.multi_attr) == 2
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 2
assert elements[0].text == 'Replacing element'
assert elements[1].text == 'Second element'
del doc.multi_attr[0]
assert doc.multi_attr[0].value == 'Second element'
assert len(doc.multi_attr) == 1
tree = fromstringlist(write(doc, validate=False))
elements = tree.findall('multi')
assert len(elements) == 1
assert elements[0].text == 'Second element'
def test_parse(input_, expected):
with open(os.path.join(test_suite_dir, input_), 'rb') as f:
xml = f.read()
if IRON_PYTHON:
xml = bytes(xml)
parse = get_format(xml)
assert callable(parse)
uri_filename = input_.rstrip('.xml') + '.uri.txt'
try:
with open(os.path.join(test_suite_dir, uri_filename)) as f:
base_uri = f.read().strip()
except (IOError, OSError):
base_uri = 'http://example.com/'
parsed_feed, _ = parse(xml, feed_url=base_uri)
parsed_tree = fromstringlist(
write(parsed_feed, canonical_order=True, hints=False))
if IRON_PYTHON:
open_ = functools.partial(io.open, encoding='utf-8')
elif PY3 and sys.platform == 'win32':
open_ = functools.partial(open, encoding='utf-8')
else:
open_ = open
with open_(os.path.join(test_suite_dir, expected)) as f:
expected_tree = fromstringlist(f.read() if IRON_PYTHON else f)
compare_tree(expected_tree, parsed_tree)
def test_parse(input_, expected):
with open(os.path.join(test_suite_dir, input_), 'rb') as f:
xml = f.read()
if IRON_PYTHON:
xml = bytes(xml)
parse = get_format(xml)
assert callable(parse)
uri_filename = input_.rstrip('.xml') + '.uri.txt'
try:
with open(os.path.join(test_suite_dir, uri_filename)) as f:
base_uri = f.read().strip()
except (IOError, OSError):
base_uri = 'http://example.com/'
parsed_feed, _ = parse(xml, feed_url=base_uri)
parsed_tree = fromstringlist(
write(parsed_feed, canonical_order=True, hints=False)
)
if IRON_PYTHON:
open_ = functools.partial(io.open, encoding='utf-8')
elif PY3:
open_ = functools.partial(open, encoding='utf-8')
else:
open_ = open
with open_(os.path.join(test_suite_dir, expected)) as f:
expected_tree = fromstringlist(f.read() if IRON_PYTHON else f)
compare_tree(expected_tree, parsed_tree)
def test_write_hints(fx_test_doc):
doc, _ = fx_test_doc
doc._hints.update({
TestDoc.ns_element_attr: {
'abc': '123',
'def': '456'
},
TestDoc.title_attr: {
'ghi': '789',
'jkl': '012'
}
})
g = write(doc, canonical_order=True)
tree = fromstringlist(g)
hint_tag = '{' + SCHEMA_XMLNS + '}hint'
assert tree[0].tag == hint_tag
assert tree[0].attrib['tag'] == 'ns-element'
assert tree[0].attrib['tag-xmlns'] == 'http://earthreader.github.io/'
assert tree[0].attrib['id'] == 'abc'
assert tree[0].attrib['value'] == '123'
assert tree[1].tag == hint_tag
assert tree[1].attrib['tag'] == 'ns-element'
assert tree[1].attrib['tag-xmlns'] == 'http://earthreader.github.io/'
assert tree[1].attrib['id'] == 'def'
assert tree[1].attrib['value'] == '456'
assert tree[2].tag == hint_tag
assert tree[2].attrib['tag'] == 'title'
assert 'tag-xmlns' not in tree[2].attrib
assert tree[2].attrib['id'] == 'ghi'
assert tree[2].attrib['value'] == '789'
assert tree[3].tag == hint_tag
assert tree[3].attrib['tag'] == 'title'
assert 'tag-xmlns' not in tree[3].attrib
assert tree[3].attrib['id'] == 'jkl'
assert tree[3].attrib['value'] == '012'
def test_write_hints(fx_test_doc):
doc, _ = fx_test_doc
doc._hints.update({
TestDoc.ns_element_attr: {'abc': '123', 'def': '456'},
TestDoc.title_attr: {'ghi': '789', 'jkl': '012'}
})
g = write(doc, canonical_order=True)
tree = fromstringlist(g)
hint_tag = '{' + SCHEMA_XMLNS + '}hint'
assert tree[0].tag == hint_tag
assert tree[0].attrib['tag'] == 'ns-element'
assert tree[0].attrib['tag-xmlns'] == 'http://earthreader.github.io/'
assert tree[0].attrib['id'] == 'abc'
assert tree[0].attrib['value'] == '123'
assert tree[1].tag == hint_tag
assert tree[1].attrib['tag'] == 'ns-element'
assert tree[1].attrib['tag-xmlns'] == 'http://earthreader.github.io/'
assert tree[1].attrib['id'] == 'def'
assert tree[1].attrib['value'] == '456'
assert tree[2].tag == hint_tag
assert tree[2].attrib['tag'] == 'title'
assert 'tag-xmlns' not in tree[2].attrib
assert tree[2].attrib['id'] == 'ghi'
assert tree[2].attrib['value'] == '789'
assert tree[3].tag == hint_tag
assert tree[3].attrib['tag'] == 'title'
assert 'tag-xmlns' not in tree[3].attrib
assert tree[3].attrib['id'] == 'jkl'
assert tree[3].attrib['value'] == '012'
def test_element_initialize():
doc = TestDoc(title_attr=TextElement(value='Title test'),
content_attr=TextElement(value=u('내용 테스트')),
attr_attr='Attribute value',
text_content_attr='Text content',
multi_attr=(TextElement(value='a'), TextElement(value='b')))
assert doc.title_attr.value == 'Title test'
assert doc.content_attr.value == u('내용 테스트')
assert doc.attr_attr == 'Attribute value'
assert doc.text_content_attr == 'Text content'
assert len(doc.multi_attr) == 2
assert doc.multi_attr[0].value == 'a'
assert doc.multi_attr[1].value == 'b'
doc.multi_attr.append(TextElement(value='c'))
assert doc.multi_attr[2].value == 'c'
assert len(doc.multi_attr) == 3
tree = fromstringlist(write(doc))
assert tree.find('title').text == 'Title test'
assert tree.find('content').text == u('내용 테스트')
assert tree.attrib['attr'] == 'Attribute value'
elements = tree.findall('multi')
assert len(elements) == 3
assert elements[0].text == 'a'
assert elements[1].text == 'b'
assert elements[2].text == 'c'
def test_element_initialize():
doc = TestDoc(title_attr=TextElement(value='Title test'),
content_attr=TextElement(value=u('내용 테스트')),
attr_attr='Attribute value',
text_content_attr='Text content',
multi_attr=(TextElement(value='a'), TextElement(value='b')))
assert doc.title_attr.value == 'Title test'
assert doc.content_attr.value == u('내용 테스트')
assert doc.attr_attr == 'Attribute value'
assert doc.text_content_attr == 'Text content'
assert len(doc.multi_attr) == 2
assert doc.multi_attr[0].value == 'a'
assert doc.multi_attr[1].value == 'b'
doc.multi_attr.append(TextElement(value='c'))
assert doc.multi_attr[2].value == 'c'
assert len(doc.multi_attr) == 3
tree = fromstringlist(write(doc))
assert tree.find('title').text == 'Title test'
assert tree.find('content').text == u('내용 테스트')
assert tree.attrib['attr'] == 'Attribute value'
elements = tree.findall('multi')
assert len(elements) == 3
assert elements[0].text == 'a'
assert elements[1].text == 'b'
assert elements[2].text == 'c'
def apply_timestamp(stage, feed_id, timestamp):
with stage:
feed = stage.feeds[feed_id]
feed.entries[0].read = Mark(marked=True, updated_at=timestamp)
assert feed.entries[0].read.updated_at == timestamp
written = read(Feed, write(feed, as_bytes=True))
assert written.entries[0].read.updated_at == timestamp, repr((written.entries[0].read.updated_at, timestamp))
stage.feeds[feed_id] = feed
def test_write_test_doc_tree(fx_test_doc):
doc, _ = fx_test_doc
g = write(doc, canonical_order=True)
tree = fromstringlist(g)
assert tree.tag == 'test'
assert tree.attrib == {
'attr': u'속성 값',
'attr-decoder': 'decoder test'
}
assert tree[0].tag == 'title'
assert not tree[0].attrib
assert tree[0].text == u'제목 test'
assert tree[1].tag == 'content'
assert tree[1].text == 'Content test'
assert not tree[1].attrib
assert tree[2].tag == tree[3].tag == tree[4].tag == 'multi'
assert tree[2].attrib == tree[3].attrib == tree[4].attrib == {}
assert tree[2].text == 'a'
assert tree[3].text == 'b'
assert tree[4].text == 'c'
assert tree[5].tag == tree[6].tag == tree[7].tag == 's-multi'
assert tree[5].attrib == tree[6].attrib == tree[7].attrib == {}
assert tree[5].text == 'a'
assert tree[6].text == 'b'
assert tree[7].text == 'c'
assert tree[8].tag == 'text-content'
assert not tree[8].attrib
assert tree[8].text == u'텍스트 내용'
assert tree[9].tag == tree[10].tag == 'text-multi'
assert tree[9].attrib == tree[10].attrib == {}
assert tree[9].text == 'a'
assert tree[10].text == 'b'
assert tree[11].tag == tree[12].tag == tree[13].tag == 's-text-multi'
assert tree[11].attrib == tree[12].attrib == tree[13].attrib == {}
assert tree[11].text == 'c'
assert tree[12].text == 'b'
assert tree[13].text == 'a'
assert tree[14].tag == 'text-decoder'
assert not tree[14].attrib
assert tree[14].text == '123.456'
assert tree[15].tag == 'text-decoder-decorator'
assert not tree[15].attrib
assert tree[15].text == '123'
assert tree[16].tag == 'text-combined-decoder'
assert not tree[16].attrib
assert tree[16].text == '1234'
assert tree[17].tag == '{http://earthreader.github.io/}ns-element'
assert tree[17].attrib == {
'{http://earthreader.github.io/}ns-attr': 'namespace attribute value'
}
assert tree[17].text == 'Namespace test'
assert tree[18].tag == '{http://earthreader.github.io/}ns-text'
assert not tree[18].attrib
assert tree[18].text == 'Namespace test'
assert tree[19].tag == 'content-decoder'
assert tree[19].text == 'CONTENT DECODER'
assert not tree[19].attrib
assert len(tree) == 20
def test_write_test_doc_tree(fx_test_doc):
doc, _ = fx_test_doc
g = write(doc, canonical_order=True)
tree = fromstringlist(g)
assert tree.tag == 'test'
assert tree.attrib == {
'attr': u('속성 값'),
'attr-decoder': 'decoder test'
}
assert tree[0].tag == 'title'
assert not tree[0].attrib
assert tree[0].text == u('제목 test')
assert tree[1].tag == 'content'
assert tree[1].text == 'Content test'
assert not tree[1].attrib
assert tree[2].tag == tree[3].tag == tree[4].tag == 'multi'
assert tree[2].attrib == tree[3].attrib == tree[4].attrib == {}
assert tree[2].text == 'a'
assert tree[3].text == 'b'
assert tree[4].text == 'c'
assert tree[5].tag == tree[6].tag == tree[7].tag == 's-multi'
assert tree[5].attrib == tree[6].attrib == tree[7].attrib == {}
assert tree[5].text == 'a'
assert tree[6].text == 'b'
assert tree[7].text == 'c'
assert tree[8].tag == 'text-content'
assert not tree[8].attrib
assert tree[8].text == u('텍스트 내용')
assert tree[9].tag == tree[10].tag == 'text-multi'
assert tree[9].attrib == tree[10].attrib == {}
assert tree[9].text == 'a'
assert tree[10].text == 'b'
assert tree[11].tag == tree[12].tag == tree[13].tag == 's-text-multi'
assert tree[11].attrib == tree[12].attrib == tree[13].attrib == {}
assert tree[11].text == 'c'
assert tree[12].text == 'b'
assert tree[13].text == 'a'
assert tree[14].tag == 'text-decoder'
assert not tree[14].attrib
assert tree[14].text == '123.456'
assert tree[15].tag == 'text-decoder-decorator'
assert not tree[15].attrib
assert tree[15].text == '123'
assert tree[16].tag == 'text-combined-decoder'
assert not tree[16].attrib
assert tree[16].text == '1234'
assert tree[17].tag == '{http://earthreader.github.io/}ns-element'
assert tree[17].attrib == {
'{http://earthreader.github.io/}ns-attr': 'namespace attribute value'
}
assert tree[17].text == 'Namespace test'
assert tree[18].tag == '{http://earthreader.github.io/}ns-text'
assert not tree[18].attrib
assert tree[18].text == 'Namespace test'
assert tree[19].tag == 'content-decoder'
assert tree[19].text == 'CONTENT DECODER'
assert not tree[19].attrib
assert len(tree) == 20
def test_rss_parser():
my_opener = urllib2.build_opener(TestHTTPHandler)
urllib2.install_opener(my_opener)
crawled_feed, data_for_crawl = rss2.parse_rss(
rss_xml,
'http://sourcetest.com/rss.xml'
)
feed = read(Feed, write(crawled_feed, as_bytes=True))
assert crawled_feed.id == feed.id
title = crawled_feed.title
assert title.type == feed.title.type
assert title.value == feed.title.value
links = crawled_feed.links
assert links[1].mimetype == feed.links[1].mimetype
assert links[1].relation == feed.links[1].relation
assert links[1].uri == feed.links[1].uri
rights = crawled_feed.rights
assert rights.type == feed.rights.type
assert rights.value == feed.rights.value
contributors = crawled_feed.contributors
assert contributors[0].name == feed.contributors[0].name
assert contributors[0].email == feed.contributors[0].email
assert contributors[1].name == feed.contributors[1].name
assert contributors[1].email == feed.contributors[1].email
updated_at = crawled_feed.updated_at
assert updated_at == feed.updated_at
categories = crawled_feed.categories
assert categories[0].term == feed.categories[0].term
entries = crawled_feed.entries
assert entries[0].title.type == feed.entries[0].title.type
assert entries[0].title.value == feed.entries[0].title.value
assert entries[0].links[0].mimetype == feed.entries[0].links[0].mimetype
assert entries[0].links[0].relation == feed.entries[0].links[0].relation
assert entries[0].links[0].uri == feed.entries[0].links[0].uri
assert entries[0].content.value == feed.entries[0].content.value
assert entries[0].authors[0].name == feed.entries[0].authors[0].name
assert entries[0].authors[0].email == feed.entries[0].authors[0].email
assert entries[0].links[1].mimetype == feed.entries[0].links[1].mimetype
assert entries[0].links[1].uri == feed.entries[0].links[1].uri
assert entries[0].id == feed.entries[0].id
assert (entries[0].published_at ==
entries[0].updated_at ==
feed.entries[0].published_at ==
feed.entries[0].updated_at)
assert data_for_crawl == {
'lastBuildDate': datetime.datetime(2002, 9, 7, 0, 0, 1, tzinfo=utc),
'ttl': '10',
}
source = entries[0].source
assert source.title.type == feed.entries[0].source.title.type
assert source.title.value == feed.entries[0].source.title.value
assert source.links[1].mimetype == feed.entries[0].source.links[1].mimetype
assert source.links[1].uri == feed.entries[0].source.links[1].uri
assert source.links[1].relation == feed.entries[0].source.links[1].relation
assert source.subtitle.type == feed.entries[0].source.subtitle.type
assert source.subtitle.value == feed.entries[0].source.subtitle.value
assert not source.entries
def apply_timestamp(stage, feed_id, timestamp):
with stage:
feed = stage.feeds[feed_id]
feed.entries[0].read = Mark(marked=True, updated_at=timestamp)
assert feed.entries[0].read.updated_at == timestamp
written = read(Feed, write(feed, as_bytes=True))
assert written.entries[0].read.updated_at == timestamp, repr(
(written.entries[0].read.updated_at, timestamp))
stage.feeds[feed_id] = feed
def test_write_xmlns_doc(fx_xmlns_doc):
doc = fx_xmlns_doc
g = write(doc, indent=' ', canonical_order=True)
assert ''.join(g) == text_type('''\
<?xml version="1.0" encoding="utf-8"?>
<ns0:nstest xmlns:ns0="http://earthreader.github.io/"\
xmlns:ns1="https://github.com/earthreader/libearth">
<ns0:samens>Same namespace</ns0:samens>
<ns1:otherns>Other namespace</ns1:otherns>
</ns0:nstest>''')
def test_write_subscription_with_ascii_title():
rss = rss_template_with_title.format('english')
feed, _ = parse_rss2(rss)
feed.id = 'id'
sublist = SubscriptionList()
sublist.subscribe(feed)
g = write(sublist)
assert ''.join(g)
def test_write_subscription_with_ascii_title():
rss = rss_template_with_title.format('english')
feed, _ = parse_rss(rss)
feed.id = 'id'
sublist = SubscriptionList()
sublist.subscribe(feed)
g = write(sublist)
assert ''.join(g)
def test_write_xmlns_doc(fx_xmlns_doc):
doc = fx_xmlns_doc
g = write(doc, indent=' ', canonical_order=True)
assert ''.join(g) == text_type('''\
<?xml version="1.0" encoding="utf-8"?>
<ns0:nstest xmlns:ns0="http://earthreader.github.io/"\
xmlns:libearth="http://earthreader.org/schema/"\
xmlns:ns1="https://github.com/earthreader/libearth">
<ns0:samens>Same namespace</ns0:samens>
<ns1:otherns>Other namespace</ns1:otherns>
</ns0:nstest>''')
def test_rss_parser():
my_opener = urllib2.build_opener(TestHTTPHandler)
urllib2.install_opener(my_opener)
crawled_feed, data_for_crawl = parse_rss(rss_xml,
'http://sourcetest.com/rss.xml')
feed = read(Feed, write(crawled_feed, as_bytes=True))
assert crawled_feed.id == feed.id
title = crawled_feed.title
assert title.type == feed.title.type
assert title.value == feed.title.value
links = crawled_feed.links
assert links[1].mimetype == feed.links[1].mimetype
assert links[1].relation == feed.links[1].relation
assert links[1].uri == feed.links[1].uri
rights = crawled_feed.rights
assert rights.type == feed.rights.type
assert rights.value == feed.rights.value
contributors = crawled_feed.contributors
assert contributors[0].name == feed.contributors[0].name
assert contributors[0].email == feed.contributors[0].email
assert contributors[1].name == feed.contributors[1].name
assert contributors[1].email == feed.contributors[1].email
updated_at = crawled_feed.updated_at
assert updated_at == feed.updated_at
categories = crawled_feed.categories
assert categories[0].term == feed.categories[0].term
entries = crawled_feed.entries
assert entries[0].title.type == feed.entries[0].title.type
assert entries[0].title.value == feed.entries[0].title.value
assert entries[0].links[0].mimetype == feed.entries[0].links[0].mimetype
assert entries[0].links[0].relation == feed.entries[0].links[0].relation
assert entries[0].links[0].uri == feed.entries[0].links[0].uri
assert entries[0].content.value == feed.entries[0].content.value
assert entries[0].authors[0].name == feed.entries[0].authors[0].name
assert entries[0].authors[0].email == feed.entries[0].authors[0].email
assert entries[0].links[1].mimetype == feed.entries[0].links[1].mimetype
assert entries[0].links[1].uri == feed.entries[0].links[1].uri
assert entries[0].id == feed.entries[0].id
assert (entries[0].published_at == entries[0].updated_at ==
feed.entries[0].published_at == feed.entries[0].updated_at)
assert data_for_crawl == {
'lastBuildDate': datetime.datetime(2002, 9, 7, 0, 0, 1, tzinfo=utc),
'ttl': '10',
}
source = entries[0].source
assert source.title.type == feed.entries[0].source.title.type
assert source.title.value == feed.entries[0].source.title.value
assert source.links[1].mimetype == feed.entries[0].source.links[1].mimetype
assert source.links[1].uri == feed.entries[0].source.links[1].uri
assert source.links[1].relation == feed.entries[0].source.links[1].relation
assert source.subtitle.type == feed.entries[0].source.subtitle.type
assert source.subtitle.value == feed.entries[0].source.subtitle.value
assert not source.entries
def test_write_subscription_with_nonascii_title():
'''SubscriptionList convert the feed title to :class:`str`, and
:class:`write` try to encode the title in utf8.
When non-ascii characters are in the title, UnicodeDecodeError is raised.
'''
rss = rss_template_with_title.format('한글')
feed, _ = parse_rss2(rss)
feed.id = 'id'
sublist = SubscriptionList()
sublist.subscribe(feed)
g = write(sublist)
assert ''.join(g)
def test_write_subscription_with_nonascii_title():
'''SubscriptionList convert the feed title to :class:`str`, and
:class:`write` try to encode the title in utf8.
When non-ascii characters are in the title, UnicodeDecodeError is raised.
'''
rss = rss_template_with_title.format('한글')
feed, _ = parse_rss(rss)
feed.id = 'id'
sublist = SubscriptionList()
sublist.subscribe(feed)
g = write(sublist)
assert ''.join(g)
def test_mutate_read_element_list(fx_test_doc):
doc, _ = fx_test_doc
doc.multi_attr.insert(2, TextElement(value='inserted'))
assert doc.multi_attr[0].value == 'a'
assert doc.multi_attr[1].value == 'b'
assert doc.multi_attr[2].value == 'inserted'
assert doc.multi_attr[3].value == 'c'
assert len(doc.multi_attr) == 4
tree = fromstringlist(write(doc))
elements = tree.findall('multi')
assert len(elements) == 4
assert elements[0].text == 'a'
assert elements[1].text == 'b'
assert elements[2].text == 'inserted'
assert elements[3].text == 'c'
def test_mutate_read_element_list(fx_test_doc):
doc, _ = fx_test_doc
doc.multi_attr.insert(2, TextElement(value='inserted'))
assert doc.multi_attr[0].value == 'a'
assert doc.multi_attr[1].value == 'b'
assert doc.multi_attr[2].value == 'inserted'
assert doc.multi_attr[3].value == 'c'
assert len(doc.multi_attr) == 4
tree = fromstringlist(write(doc))
elements = tree.findall('multi')
assert len(elements) == 4
assert elements[0].text == 'a'
assert elements[1].text == 'b'
assert elements[2].text == 'inserted'
assert elements[3].text == 'c'
def test_validate_recurse(element, recur_valid, valid):
assert validate(element, recurse=True, raise_error=False) is recur_valid
try:
validate(element, recurse=True, raise_error=True)
except IntegrityError:
assert not recur_valid
else:
assert recur_valid
assert validate(element, recurse=False, raise_error=False) is valid
try:
validate(element, recurse=False, raise_error=True)
except IntegrityError:
assert not valid
else:
assert valid
try:
for _ in write(element):
pass
except IntegrityError:
assert not recur_valid
else:
assert recur_valid
def test_validate_recurse(element, recur_valid, valid):
assert validate(element, recurse=True, raise_error=False) is recur_valid
try:
validate(element, recurse=True, raise_error=True)
except IntegrityError:
assert not recur_valid
else:
assert recur_valid
assert validate(element, recurse=False, raise_error=False) is valid
try:
validate(element, recurse=False, raise_error=True)
except IntegrityError:
assert not valid
else:
assert valid
try:
for _ in write(element):
pass
except IntegrityError:
assert not recur_valid
else:
assert recur_valid
def test_attribute_codec():
doc = CodecTestDoc(attr=(1, 2))
tree = fromstringlist(write(doc))
assert tree.attrib['attr'] == '1,2'
doc2 = read(CodecTestDoc, etree_tobyteslist(tree))
assert doc2.attr == (1, 2)
def test_write_test_doc(fx_test_doc):
doc, _ = fx_test_doc
gf = lambda: write(doc, indent=' ', canonical_order=True, hints=False)
print(''.join(gf()))
assert ''.join(gf()) == '''\
def test_write_test_doc(fx_test_doc):
doc, _ = fx_test_doc
gf = lambda: write(doc, indent=' ', canonical_order=True, hints=False)
print(''.join(gf()))
assert ''.join(gf()) == '''\
def test_text_codec():
doc = CodecTestDoc(text=(3, 4))
tree = fromstringlist(write(doc))
assert tree.find('text').text == '3,4'
doc2 = read(CodecTestDoc, etree_tobyteslist(tree))
assert doc2.text == (3, 4)
def test_write_none_text():
doc = CodecTestDoc(attr=(1, 2), text=None)
tree = fromstringlist(write(doc))
assert tree.find('text') is None
assert tree.attrib['attr'] == '1,2'
def test_attribute_encode_error():
doc = EncodeErrorDoc(attr=True)
with raises(EncodeError):
for _ in write(doc):
pass
logging.basicConfig(level=logging.DEBUG)
formats = {}
for filename in missing_inputs:
print(filename)
with open(os.path.join(test_suite_dir, filename)) as f:
xml = f.read()
try:
parse = get_format(xml)
except Exception:
print('Failed to detect the format of', filename, file=sys.stderr)
raise
uri_filename = filename.rstrip('.xml') + '.uri.txt'
try:
with open(os.path.join(test_suite_dir, uri_filename)) as f:
base_uri = f.read().strip()
except (IOError, OSError):
base_uri = 'http://example.com/'
try:
feed, _ = parse(xml, feed_url=base_uri)
except Exception:
print('Failed to parse', filename, file=sys.stderr)
raise
out_filename = filename.rstrip('.xml') + '.out.xml'
try:
expected = ''.join(write(feed, canonical_order=True, hints=False))
with open(os.path.join(test_suite_dir, out_filename), 'w') as f:
f.write(expected)
except Exception:
print('Failed to write', out_filename, file=sys.stderr)
raise
def test_atom_parser():
url = 'http://vio.atomtest.com/feed/atom'
crawled_feed, _ = parse_atom(atom_xml, url)
feed = read(Feed, write(crawled_feed, as_bytes=True))
title = crawled_feed.title
assert title.type == feed.title.type
assert title.value == feed.title.value
subtitle = crawled_feed.subtitle
assert subtitle.type == feed.subtitle.type
assert subtitle.value == feed.subtitle.value
links = crawled_feed.links
assert links[0].relation == feed.links[0].relation
assert links[0].mimetype == feed.links[0].mimetype
assert links[0].uri == feed.links[0].uri
assert links[1].relation == feed.links[1].relation
assert links[1].mimetype == feed.links[1].mimetype
assert links[1].uri == feed.links[1].uri
authors = crawled_feed.authors
assert authors[0].name == feed.authors[0].name
assert authors[0].email == feed.authors[0].email
categories = crawled_feed.categories
assert categories[0].term == feed.categories[0].term
contributors = crawled_feed.contributors
assert contributors[0].name == feed.contributors[0].name
generator = crawled_feed.generator
assert generator.uri == feed.generator.uri
assert generator.value == feed.generator.value
icon = crawled_feed.icon
assert icon == feed.icon
logo = crawled_feed.logo
assert logo == feed.logo
rights = crawled_feed.rights
assert rights.type == feed.rights.type
assert rights.value == feed.rights.value
updated_at = crawled_feed.updated_at
assert updated_at == feed.updated_at
entries = crawled_feed.entries
assert entries[0].id == feed.entries[0].id
assert entries[0].authors[0].name == feed.entries[0].authors[0].name
assert entries[0].title.type == feed.entries[0].title.type
assert entries[0].title.value == feed.entries[0].title.value
assert entries[0].links[0].relation == feed.entries[0].links[0].relation
assert entries[0].links[0].uri == feed.entries[0].links[0].uri
assert entries[0].updated_at == feed.entries[0].updated_at
assert entries[0].published_at == feed.entries[0].published_at
assert entries[0].categories[0].scheme_uri == \
feed.entries[0].categories[0].scheme_uri
assert entries[0].categories[0].term == feed.entries[0].categories[0].term
assert entries[0].categories[1].scheme_uri == \
feed.entries[0].categories[1].scheme_uri
assert entries[0].categories[1].term == feed.entries[0].categories[1].term
assert entries[0].content.type == feed.entries[0].content.type
assert entries[0].content.value == feed.entries[0].content.value
assert entries[0].content.source_uri == feed.entries[0].content.source_uri
assert entries[0].summary.type == feed.entries[0].summary.type
assert entries[0].summary.value == feed.entries[0].summary.value
assert entries[1].id == feed.entries[1].id
assert entries[1].authors[0].name == feed.entries[1].authors[0].name
assert entries[1].title.type == feed.entries[1].title.type
assert entries[1].title.value == feed.entries[1].title.value
assert entries[1].updated_at == feed.entries[1].updated_at
assert entries[2].id == feed.entries[2].id
assert entries[2].authors[0].name == feed.entries[2].authors[0].name
assert entries[2].title.type == feed.entries[2].title.type
assert entries[2].title.value == feed.entries[2].title.value
assert entries[2].updated_at == feed.entries[2].updated_at
source = entries[2].source
feed_source = feed.entries[2].source
assert source.authors[0].name == feed_source.authors[0].name
assert source.categories[0].term == feed_source.categories[0].term
assert source.contributors[0].name == feed_source.contributors[0].name
assert source.links[0] == feed_source.links[0]
assert source.id == feed_source.id
assert source.generator == feed_source.generator
assert source.icon == feed_source.icon
assert source.logo == feed_source.logo
assert source.rights == feed_source.rights
assert source.subtitle == feed_source.subtitle
def test_content_encode_error():
doc = ContentEncodeErrorDoc()
with raises(EncodeError):
for _ in write(doc):
pass
logging.basicConfig(level=logging.DEBUG)
formats = {}
for filename in missing_inputs:
print(filename)
with open(os.path.join(test_suite_dir, filename)) as f:
xml = f.read()
try:
parse = get_format(xml)
except Exception:
print('Failed to detect the format of', filename, file=sys.stderr)
raise
uri_filename = filename.rstrip('.xml') + '.uri.txt'
try:
with open(os.path.join(test_suite_dir, uri_filename)) as f:
base_uri = f.read().strip()
except (IOError, OSError):
base_uri = 'http://example.com/'
try:
feed, _ = parse(xml, feed_url=base_uri)
except Exception:
print('Failed to parse', filename, file=sys.stderr)
raise
out_filename = filename.rstrip('.xml') + '.out.xml'
try:
expected = ''.join(write(feed, canonical_order=True, hints=False))
with open(os.path.join(test_suite_dir, out_filename), 'w') as f:
f.write(expected)
except Exception:
print('Failed to write', out_filename, file=sys.stderr)
raise
def test_text_codec():
doc = CodecTestDoc(text=(3, 4))
tree = fromstringlist(write(doc))
assert tree.find('text').text == '3,4'
doc2 = read(CodecTestDoc, etree_tobyteslist(tree))
assert doc2.text == (3, 4)
def test_content_encode_error():
doc = ContentEncodeErrorDoc()
with raises(EncodeError):
for _ in write(doc):
pass
def test_write_none_attribute():
doc = CodecTestDoc(attr=None, text=(1, 2))
tree = fromstringlist(write(doc))
assert tree.find('text').text == '1,2'
assert 'attr' not in tree.attrib
def test_write_test_doc(fx_test_doc):
doc, _ = fx_test_doc
g = write(doc, indent=' ', canonical_order=True)
assert ''.join(g) == '''\
def test_atom_parser():
url = 'http://vio.atomtest.com/feed/atom'
crawled_feed, _ = parse_atom(atom_xml, url)
feed = read(Feed, write(crawled_feed, as_bytes=True))
title = crawled_feed.title
assert title.type == feed.title.type
assert title.value == feed.title.value
subtitle = crawled_feed.subtitle
assert subtitle.type == feed.subtitle.type
assert subtitle.value == feed.subtitle.value
links = crawled_feed.links
assert links[0].relation == feed.links[0].relation
assert links[0].mimetype == feed.links[0].mimetype
assert links[0].uri == feed.links[0].uri
assert links[1].relation == feed.links[1].relation
assert links[1].mimetype == feed.links[1].mimetype
assert links[1].uri == feed.links[1].uri
authors = crawled_feed.authors
assert authors[0].name == feed.authors[0].name
assert authors[0].email == feed.authors[0].email
categories = crawled_feed.categories
assert categories[0].term == feed.categories[0].term
contributors = crawled_feed.contributors
assert contributors[0].name == feed.contributors[0].name
generator = crawled_feed.generator
assert generator.uri == feed.generator.uri
assert generator.value == feed.generator.value
icon = crawled_feed.icon
assert icon == feed.icon
logo = crawled_feed.logo
assert logo == feed.logo
rights = crawled_feed.rights
assert rights.type == feed.rights.type
assert rights.value == feed.rights.value
updated_at = crawled_feed.updated_at
assert updated_at == feed.updated_at
entries = crawled_feed.entries
assert entries[0].id == feed.entries[0].id
assert entries[0].authors[0].name == feed.entries[0].authors[0].name
assert entries[0].title.type == feed.entries[0].title.type
assert entries[0].title.value == feed.entries[0].title.value
assert entries[0].links[0].relation == feed.entries[0].links[0].relation
assert entries[0].links[0].uri == feed.entries[0].links[0].uri
assert entries[0].updated_at == feed.entries[0].updated_at
assert entries[0].published_at == feed.entries[0].published_at
assert entries[0].categories[0].scheme_uri == \
feed.entries[0].categories[0].scheme_uri
assert entries[0].categories[0].term == feed.entries[0].categories[0].term
assert entries[0].categories[1].scheme_uri == \
feed.entries[0].categories[1].scheme_uri
assert entries[0].categories[1].term == feed.entries[0].categories[1].term
assert entries[0].content.type == feed.entries[0].content.type
assert entries[0].content.value == feed.entries[0].content.value
assert entries[0].content.source_uri == feed.entries[0].content.source_uri
assert entries[0].summary.type == feed.entries[0].summary.type
assert entries[0].summary.value == feed.entries[0].summary.value
assert entries[1].id == feed.entries[1].id
assert entries[1].authors[0].name == feed.entries[1].authors[0].name
assert entries[1].title.type == feed.entries[1].title.type
assert entries[1].title.value == feed.entries[1].title.value
assert entries[1].updated_at == feed.entries[1].updated_at
assert entries[2].id == feed.entries[2].id
assert entries[2].authors[0].name == feed.entries[2].authors[0].name
assert entries[2].title.type == feed.entries[2].title.type
assert entries[2].title.value == feed.entries[2].title.value
assert entries[2].updated_at == feed.entries[2].updated_at
source = entries[2].source
feed_source = feed.entries[2].source
assert source.authors[0].name == feed_source.authors[0].name
assert source.categories[0].term == feed_source.categories[0].term
assert source.contributors[0].name == feed_source.contributors[0].name
assert source.links[0] == feed_source.links[0]
assert source.id == feed_source.id
assert source.generator == feed_source.generator
assert source.icon == feed_source.icon
assert source.logo == feed_source.logo
assert source.rights == feed_source.rights
assert source.subtitle == feed_source.subtitle
def test_write_test_doc(fx_test_doc):
doc, _ = fx_test_doc
result = write(doc, indent=' ', canonical_order=True, hints=False)
print(''.join(result))
assert ''.join(result) == '''\
def test_write_none_attribute():
doc = CodecTestDoc(attr=None, text=(1, 2))
tree = fromstringlist(write(doc))
assert tree.find('text').text == '1,2'
assert 'attr' not in tree.attrib
def test_write_none_text():
doc = CodecTestDoc(attr=(1, 2), text=None)
tree = fromstringlist(write(doc))
assert tree.find('text') is None
assert tree.attrib['attr'] == '1,2'
def test_content_codec():
doc = ContentCodecTestDoc(c=(5, 6))
tree = fromstringlist(write(doc, as_bytes=True))
assert tree.text == '5,6'
doc2 = read(ContentCodecTestDoc, etree_tobyteslist(tree))
assert doc2.c == (5, 6)
def test_text_encode_error():
doc = EncodeErrorDoc(text=True)
with raises(EncodeError):
for _ in write(doc):
pass
def test_write_test_doc(fx_test_doc):
doc, _ = fx_test_doc
result = write(doc, indent=' ', canonical_order=True, hints=False)
print(''.join(result))
assert ''.join(result) == '''\
def test_attribute_codec():
doc = CodecTestDoc(attr=(1, 2))
tree = fromstringlist(write(doc))
assert tree.attrib['attr'] == '1,2'
doc2 = read(CodecTestDoc, etree_tobyteslist(tree))
assert doc2.attr == (1, 2)
def test_attribute_encode_error():
doc = EncodeErrorDoc(attr=True)
with raises(EncodeError):
for _ in write(doc):
pass
def test_content_codec():
doc = ContentCodecTestDoc(c=(5, 6))
tree = fromstringlist(write(doc, as_bytes=True))
assert tree.text == '5,6'
doc2 = read(ContentCodecTestDoc, etree_tobyteslist(tree))
assert doc2.c == (5, 6)
def test_text_encode_error():
doc = EncodeErrorDoc(text=True)
with raises(EncodeError):
for _ in write(doc):
pass
