def test_sort_buffered_independent():
table = (('foo', 'bar'),
('C', 2),
('A', 9),
('A', 6),
('F', 1),
('D', 10))
expectation = (('foo', 'bar'),
('F', 1),
('C', 2),
('A', 6),
('A', 9),
('D', 10))
result = sort(table, 'bar', buffersize=4)
nrows(result) # cause data to be cached
# check that two row iterators are independent, i.e., consuming rows
# from one does not affect the other
it1 = iter(result)
it2 = iter(result)
eq_(expectation[0], it1.next())
eq_(expectation[1], it1.next())
eq_(expectation[0], it2.next())
eq_(expectation[1], it2.next())
eq_(expectation[2], it2.next())
eq_(expectation[2], it1.next())
def test_progress():
# make sure progress doesn't raise exception
table = (('foo', 'bar', 'baz'),
('a', 1, True),
('b', 2, True),
('b', 3))
nrows(progress(table))
def test_sort_buffered_independent():
table = (("foo", "bar"), ("C", 2), ("A", 9), ("A", 6), ("F", 1), ("D", 10))
expectation = (("foo", "bar"), ("F", 1), ("C", 2), ("A", 6), ("A", 9), ("D", 10))
result = sort(table, "bar", buffersize=4)
nrows(result) # cause data to be cached
# check that two row iterators are independent, i.e., consuming rows
# from one does not affect the other
it1 = iter(result)
it2 = iter(result)
eq_(expectation[0], it1.next())
eq_(expectation[1], it1.next())
eq_(expectation[0], it2.next())
eq_(expectation[1], it2.next())
eq_(expectation[2], it2.next())
eq_(expectation[2], it1.next())
def test_sort_buffered_independent():
table = (('foo', 'bar'), ('C', 2), ('A', 9), ('A', 6), ('F', 1), ('D', 10))
expectation = (('foo', 'bar'), ('F', 1), ('C', 2), ('A', 6), ('A', 9),
('D', 10))
result = sort(table, 'bar', buffersize=4)
nrows(result) # cause data to be cached
# check that two row iterators are independent, i.e., consuming rows
# from one does not affect the other
it1 = iter(result)
it2 = iter(result)
eq_(expectation[0], next(it1))
eq_(expectation[1], next(it1))
eq_(expectation[0], next(it2))
eq_(expectation[1], next(it2))
eq_(expectation[2], next(it2))
eq_(expectation[2], next(it1))
def test_fromxml_url():
# check internet connection
try:
url = 'http://raw.githubusercontent.com/petl-developers/petl/master/.pydevproject'
urlopen(url)
except Exception as e:
print('SKIP test_fromxml_url: %s' % e, file=sys.stderr)
else:
actual = fromxml(url, 'pydev_property', {'name': ( '.', 'name'), 'prop': '.'})
assert nrows(actual) > 0
expect = fromxml('.pydevproject', 'pydev_property', {'name': ( '.', 'name'), 'prop': '.'})
ieq(expect, actual)
def test_fromxml_url():
# check internet connection
try:
url = 'http://raw.githubusercontent.com/petl-developers/petl/master/petl/test/resources/test.xml'
urlopen(url)
import pkg_resources
filename = pkg_resources.resource_filename('petl', 'test/resources/test.xml')
except Exception as e:
pytest.skip('SKIP test_fromxml_url: %s' % e)
else:
actual = fromxml(url, 'pydev_property', {'name': ( '.', 'name'), 'prop': '.'})
assert nrows(actual) > 0
expect = fromxml(filename, 'pydev_property', {'name': ( '.', 'name'), 'prop': '.'})
ieq(expect, actual)
def test_sort_buffered_cleanup():
table = (('foo', 'bar'), ('C', 2), ('A', 9), ('A', 6), ('F', 1), ('D', 10))
result = sort(table, 'bar', buffersize=2)
debug('initially filecache should be empty')
eq_(None, result._filecache)
debug('pull rows through, should populate file cache')
eq_(5, nrows(result))
eq_(3, len(result._filecache))
debug('check all files exist')
filenames = _get_names(result._filecache)
for fn in filenames:
assert os.path.exists(fn), fn
debug('delete object and garbage collect')
del result
gc.collect()
debug('check all files have been deleted')
for fn in filenames:
assert not os.path.exists(fn), fn
def test_sort_buffered_cleanup():
table = (("foo", "bar"), ("C", 2), ("A", 9), ("A", 6), ("F", 1), ("D", 10))
result = sort(table, "bar", buffersize=2)
debug("initially filecache should be empty")
eq_(None, result._filecache)
debug("pull rows through, should populate file cache")
eq_(5, nrows(result))
eq_(3, len(result._filecache))
debug("check all files exist")
filenames = _get_names(result._filecache)
for fn in filenames:
assert os.path.exists(fn), fn
debug("delete object and garbage collect")
del result
gc.collect()
debug("check all files have been deleted")
for fn in filenames:
assert not os.path.exists(fn), fn
def test_sort_buffered_cleanup_open_iterator():
table = (('foo', 'bar'), ('C', 2), ('A', 9), ('A', 6), ('F', 1), ('D', 10))
# check if cleanup is robust against open iterators
result = sort(table, 'bar', buffersize=2)
debug('pull rows through, should populate file cache')
eq_(5, nrows(result))
eq_(3, len(result._filecache))
debug('check all files exist')
filenames = _get_names(result._filecache)
for fn in filenames:
assert os.path.exists(fn), fn
debug(filenames)
debug('open an iterator')
it = iter(result)
next(it)
next(it)
debug('delete objects and garbage collect')
del result
del it
gc.collect()
for fn in filenames:
assert not os.path.exists(fn), fn
def test_sort_buffered_cleanup_open_iterator():
table = (("foo", "bar"), ("C", 2), ("A", 9), ("A", 6), ("F", 1), ("D", 10))
# check if cleanup is robust against open iterators
result = sort(table, "bar", buffersize=2)
debug("pull rows through, should populate file cache")
eq_(5, nrows(result))
eq_(3, len(result._filecache))
debug("check all files exist")
filenames = _get_names(result._filecache)
for fn in filenames:
assert os.path.exists(fn), fn
debug(filenames)
debug("open an iterator")
it = iter(result)
next(it)
next(it)
debug("delete objects and garbage collect")
del result
del it
gc.collect()
for fn in filenames:
assert not os.path.exists(fn), fn
def test_fromxml_url():
tbl = fromxml(url, './/item', 'title')
assert nrows(tbl) > 0
def test_fromxml_url():
tbl = fromxml('http://feeds.bbci.co.uk/news/rss.xml', './/item', 'title')
assert nrows(tbl) > 0
def test_fromxml_url():
tbl = fromxml('http://feeds.bbci.co.uk/news/rss.xml', './/item', 'title')
assert nrows(tbl) > 0
def test_fromgff3_region():
tbl_features = fromgff3('fixture/sample.sorted.gff.gz', region='apidb|MAL5')
eq_(7, nrows(tbl_features))
tbl_features = fromgff3('fixture/sample.sorted.gff.gz', region='apidb|MAL5:1289593-1289595')
eq_(4, nrows(tbl_features))
def test_fromxml_url():
tbl = fromxml(url, './/item', 'title')
assert nrows(tbl) > 0
