def test_iter_with_mismatch_row_metadata(self):
# self.headers and csv file headers contains mismatch row metadata
data = "ROW_ID,ROW_VERSION,ROW_ETAG,col\n" \
"1,2,etag1,\"I like trains\"\n" \
"5,1,etag2,\"weeeeeeeeeeee\"\n"
cols = as_table_columns(StringIOContextManager(data))
headers = [SelectColumn(name="ROW_ID", columnType="STRING"),
SelectColumn(name="ROW_VERSION", columnType="STRING")] + \
[SelectColumn.from_column(col) for col in cols]
with patch.object(io, "open", return_value=StringIOContextManager(data)):
table = CsvFileTable("syn123", "/fake/file/path", headers=headers)
iter = table.__iter__()
pytest.raises(ValueError, next, iter)
def test_iter_row_metadata_mismatch_in_headers(self):
# csv file does not contain row metadata, self.headers does
data = "col1,col2\n" \
"1,2\n" \
"2,1\n"
cols = as_table_columns(StringIOContextManager(data))
headers = [SelectColumn(name="ROW_ID", columnType="STRING"),
SelectColumn(name="ROW_VERSION", columnType="STRING")] + \
[SelectColumn.from_column(col) for col in cols]
with patch.object(io, "open", return_value=StringIOContextManager(data)):
table = CsvFileTable("syn123", "/fake/file/path", headers=headers)
iter = table.__iter__()
pytest.raises(ValueError, next, iter)
def test_iter_with_file_view_row_metadata(self):
# csv file and self.headers contain matching row metadata
data = "ROW_ID,ROW_VERSION,ROW_ETAG,col\n" \
"1,2,etag1,\"I like trains\"\n" \
"5,1,etag2,\"weeeeeeeeeeee\"\n"
cols = as_table_columns(StringIOContextManager(data))
headers = [SelectColumn(name="ROW_ID", columnType="STRING"),
SelectColumn(name="ROW_VERSION", columnType="STRING"),
SelectColumn(name="ROW_ETAG", columnType="STRING")] + \
[SelectColumn.from_column(col) for col in cols]
with patch.object(io, "open", return_value=StringIOContextManager(data)):
table = CsvFileTable("syn123", "/fake/file/path", headers=headers)
expected_rows = [['1', '2', "etag1", "I like trains"],
['5', '1', "etag2", "weeeeeeeeeeee"]]
for expected_row, table_row in zip(expected_rows, table):
assert expected_row == table_row
def test_SelectColumn_forward_compatibility():
sc = SelectColumn(id=1,
columnType="STRING",
name="my_col",
columnSQL="new")
assert_equals(1, sc.get("id"))
assert_equals("STRING", sc.get("columnType"))
assert_equals("my_col", sc.get("name"))
assert_equals("new", sc.get("columnSQL"))
def test_csv_table():
## Maybe not truly a unit test, but here because it doesn't do
## network IO to synapse
data = [["1", "1", "John Coltrane", 1926, 8.65, False],
["2", "1", "Miles Davis", 1926, 9.87, False],
["3", "1", "Bill Evans", 1929, 7.65, False],
["4", "1", "Paul Chambers", 1935, 5.14, False],
["5", "1", "Jimmy Cobb", 1929, 5.78, True],
["6", "1", "Scott LaFaro", 1936, 4.21, False],
["7", "1", "Sonny Rollins", 1930, 8.99, True],
["8", "1", "Kenny Burrel", 1931, 4.37, True]]
filename = None
cols = []
cols.append(Column(id='1', name='Name', columnType='STRING'))
cols.append(Column(id='2', name='Born', columnType='INTEGER'))
cols.append(Column(id='3', name='Hipness', columnType='DOUBLE'))
cols.append(Column(id='4', name='Living', columnType='BOOLEAN'))
schema1 = Schema(id='syn1234',
name='Jazz Guys',
columns=cols,
parent="syn1000001")
#TODO: use StringIO.StringIO(data) rather than writing files
try:
## create CSV file
with tempfile.NamedTemporaryFile(delete=False) as temp:
filename = temp.name
with io.open(filename, mode='w', encoding="utf-8", newline='') as temp:
writer = csv.writer(temp,
quoting=csv.QUOTE_NONNUMERIC,
lineterminator=str(os.linesep))
headers = ['ROW_ID', 'ROW_VERSION'] + [col.name for col in cols]
writer.writerow(headers)
for row in data:
writer.writerow(row)
table = Table(schema1, filename)
assert isinstance(table, CsvFileTable)
## need to set column headers to read a CSV file
table.setColumnHeaders([
SelectColumn(name="ROW_ID", columnType="STRING"),
SelectColumn(name="ROW_VERSION", columnType="STRING")
] + [SelectColumn.from_column(col) for col in cols])
## test iterator
for table_row, expected_row in zip(table, data):
assert table_row == expected_row
## test asRowSet
rowset = table.asRowSet()
for rowset_row, expected_row in zip(rowset.rows, data):
assert rowset_row['values'] == expected_row[2:]
assert rowset_row['rowId'] == expected_row[0]
assert rowset_row['versionNumber'] == expected_row[1]
## test asDataFrame
try:
import pandas as pd
df = table.asDataFrame()
assert all(df['Name'] == [row[2] for row in data])
assert all(df['Born'] == [row[3] for row in data])
assert all(df['Living'] == [row[5] for row in data])
assert all(df.index == ['%s_%s' % tuple(row[0:2]) for row in data])
assert df.shape == (8, 4)
except ImportError as e1:
sys.stderr.write(
'Pandas is apparently not installed, skipping asDataFrame portion of test_csv_table.\n\n'
)
except Exception as ex1:
if filename:
try:
if os.path.isdir(filename):
shutil.rmtree(filename)
else:
os.remove(filename)
except Exception as ex:
print(ex)
raise
def test_SelectColumn_forward_compatibility():
sc = SelectColumn(id=1, columnType="STRING", name="my_col", columnSQL="new")
assert 1 == sc.get("id")
assert "STRING" == sc.get("columnType")
assert "my_col" == sc.get("name")
assert "new" == sc.get("columnSQL")
