def test_sorter_with_sort_order_args(self):
lines = [
"chr1\t248956422\t112\t70\t71"
"chr2\t242193529\t252513167\t70\t71",
"chr3\t198295559\t498166716\t70\t71",
"chr4\t190214555\t699295181\t70\t71",
"chr5\t181538259\t892227221\t70\t71",
"chr6\t170805979\t1076358996\t70\t71",
"chr7\t159345973\t1249605173\t70\t71",
"chr8\t145138636\t1411227630\t70\t71",
"chr9\t138394717\t1558439788\t70\t71",
"chr10\t133797422\t1698811686\t70\t71",
]
fd, fn = tmp_file(lines=lines)
sorter = MafSorter(
sort_order_name=BarcodesAndCoordinate.name(),
max_objects_in_ram=100,
fasta_index=fn,
)
self.__test_sorter(sorter=sorter, chromosome="chr5")
with self.assertRaises(ValueError):
self.__test_sorter(sorter=sorter, chromosome="1")
fd.close()
os.remove(fn)
def test_empty_file(self):
fh, fn = tmp_file(lines=[])
reader = LineReader(fh=fh)
self.assertEqual(reader.peek_line(), "")
self.assertEqual(reader.read_line(), "")
self.assertEqual(reader.line_number(), 0)
reader.close()
os.remove(fn)
def test_single_line(self):
line = "A single line"
fh, fn = tmp_file(lines=[line])
reader = LineReader(fh=fh)
self.assertEqual(reader.line_number(), 0)
self.assertEqual(reader.peek_line(), line)
self.assertEqual(reader.read_line(), line)
self.assertEqual(reader.line_number(), 1)
self.assertEqual(reader.peek_line(), "")
self.assertEqual(reader.read_line(), "")
self.assertEqual(reader.line_number(), 1)
reader.close()
os.remove(fn)
def test_multiple_line(self):
lines = ["A few", "good", "lines"]
fh, fn = tmp_file(lines=lines)
reader = LineReader(fh=fh)
num_lines = 0
for i, line in enumerate(reader):
line_number = i + 1
self.assertEqual(line, lines[i])
self.assertEqual(line_number, reader.line_number())
if line_number < len(lines):
self.assertEqual(reader.peek_line(), lines[i + 1])
num_lines += 1
self.assertEqual(num_lines, len(lines))
reader.close()
os.remove(fn)
def test_load_all_scheme_data(self):
# silly test to make sure we can load ll the built-in scheme data
filenames = get_built_in_filenames()
data = load_all_scheme_data(
filenames, column_types=TestSchemeFactory.column_types
)
self.assertTrue(len(data) > 1)
# test malformed JSON
fd, fn = tmp_file("blah blah")
fd.close()
with self.assertRaises(ValueError):
load_all_schemes([fn])
os.remove(fn)
# no column types, so we can't find the column
with self.assertRaises(ValueError) as e:
data = load_all_scheme_data(filenames, column_types=[])
self.assertTrue("Could not find a column type with name" in str(e))
def test_reader_out_of_order(self):
column_names = ["Chromosome", "Start_Position", "End_Position"]
scheme = NoRestrictionsScheme(column_names)
header_version = "%s%s %s" % (
MafHeader.HeaderLineStartSymbol,
MafHeader.VersionKey,
scheme.version(),
)
header_sort_order = "%s%s %s" % (
MafHeader.HeaderLineStartSymbol,
MafHeader.SortOrderKey,
Coordinate(),
)
lines = [
header_version,
header_sort_order,
"\t".join(column_names),
"\t".join(["A", "1", "1"]),
"\t".join(["A", "4", "4"]),
"\t".join(["A", "2", "2"]),
]
fh, fn = tmp_file(lines=lines)
fh.close()
reader = MafReader.reader_from(
path=fn,
validation_stringency=ValidationStringency.Silent,
scheme=scheme)
self.assertEqual(reader.scheme().version(), scheme.version())
self.assertEqual(reader.header().version(), scheme.version())
self.assertEqual(reader.header().sort_order().name(),
Coordinate().name())
with self.assertRaises(ValueError):
records = [record for record in reader]
reader.close()
def test_from_line_reader_ok(self):
fh, fn = tmp_file([
TestMafHeader.__version_line,
TestMafHeader.__annotation_line,
TestMafHeader.__sort_order_line,
"#key1 value1",
"#key2 value2",
])
line_reader = LineReader(fh)
header = MafHeader.from_line_reader(
line_reader=line_reader,
validation_stringency=ValidationStringency.Silent)
fh.close()
self.assertTrue(len(header.validation_errors) == 0)
self.assertTrue(len(header) == 5)
self.assertEqual(
list(header.keys()),
[
MafHeader.VersionKey,
MafHeader.AnnotationSpecKey,
MafHeader.SortOrderKey,
"key1",
"key2",
],
)
self.assertEqual(
[str(record.value) for record in header.values()],
[
TestMafHeader.Version,
TestMafHeader.AnnotationSpec,
Coordinate.name(),
"value1",
"value2",
],
)
self.assertEqual(header.version(), TestMafHeader.Version)
os.remove(fn)
def test_reader_from_with_scheme(self):
scheme = TestMafReader.TestScheme()
header = "%s%s %s" % (
MafHeader.HeaderLineStartSymbol,
MafHeader.VersionKey,
scheme.version(),
)
column_names = scheme.column_names()
lines = [
header,
"\t".join(column_names),
"\t".join(["cell-1-1", "1.314", "cell-1-2"]),
"\t".join(["cell-2-1", "2.314", "cell-2-2"]),
"\t".join(["cell-3-1", "3.314", "cell-3-2"]),
]
fh, fn = tmp_file(lines=lines)
fh.close()
reader = MafReader.reader_from(
path=fn,
validation_stringency=ValidationStringency.Silent,
scheme=scheme)
records = [record for record in reader]
self.assertEqual(reader.scheme().version(), scheme.version())
self.assertEqual(reader.header().version(), scheme.version())
self.assertEqual(len(reader.header()), 1)
self.assertEqual(len(records), 3)
self.assertListEqual([r["str1"].value for r in records],
["cell-1-1", "cell-2-1", "cell-3-1"])
self.assertListEqual([r["float"].value for r in records],
[1.314, 2.314, 3.314])
reader.close()
