def test_iter_no_row_metadata(self):
# both csv headers and self.headers do not contains row metadata
data = "col1,col2\n" \
"1,2\n" \
"2,1\n"
cols = as_table_columns(StringIOContextManager(data))
headers = [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], [2, 1]]
for expected_row, table_row in zip(expected_rows, table):
assert expected_row == table_row
def test_iter_with_table_row_metadata(self):
# csv file has row metadata, self.headers does not
data = "ROW_ID,ROW_VERSION,col\n" \
"1,2,\"I like trains\"\n" \
"5,1,\"weeeeeeeeeeee\"\n"
cols = as_table_columns(StringIOContextManager(data))
headers = [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 = [["I like trains"], ["weeeeeeeeeeee"]]
for expected_row, table_row in zip(expected_rows, table):
assert expected_row == table_row
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_iter_with_no_headers_in_csv(self):
# csv file does not have headers
string_io = StringIOContextManager("1,2,etag1,\"I like trains\"\n"
"5,1,etag2,\"weeeeeeeeeeee\"\n")
with patch.object(io, "open", return_value=string_io):
table = CsvFileTable("syn123", "/fake/file/path", header=False)
iter = table.__iter__()
assert_raises(ValueError, next, iter)
def test_iter_with_no_headers(self):
# self.headers is None
string_io = StringIOContextManager("ROW_ID,ROW_VERSION,ROW_ETAG,col\n"
"1,2,etag1,\"I like trains\"\n"
"5,1,etag2,\"weeeeeeeeeeee\"\n")
with patch.object(io, "open", return_value=string_io):
table = CsvFileTable("syn123", "/fake/file/path")
iter = table.__iter__()
assert_raises(ValueError, next, iter)
def test_iter_metadata__no_etag(self):
string_io = StringIOContextManager("ROW_ID,ROW_VERSION,asdf\n"
"1,2,\"I like trains\"\n"
"5,1,\"weeeeeeeeeeee\"\n")
with patch.object(io, "open", return_value=string_io):
csv_file_table = CsvFileTable("syn123", "/fake/file/path")
metadata = [x for x in csv_file_table.iter_row_metadata()]
assert_equals(2, len(metadata))
assert_equals((1, 2, None), metadata[0])
assert_equals((5, 1, None), metadata[1])
def test_iter_metadata__has_etag(self):
string_io = StringIOContextManager("ROW_ID,ROW_VERSION,ROW_ETAG,asdf\n"
"1,2,etag1,\"I like trains\"\n"
"5,1,etag2,\"weeeeeeeeeeee\"\n")
with patch.object(io, "open", return_value=string_io):
csv_file_table = CsvFileTable("syn123", "/fake/file/path")
metadata = [x for x in csv_file_table.iter_row_metadata()]
assert 2 == len(metadata)
assert (1, 2, "etag1") == metadata[0]
assert (5, 1, "etag2") == metadata[1]
def test_as_table_columns__with_csv_file():
string_io = StringIOContextManager(
'ROW_ID,ROW_VERSION,Name,Born,Hipness,Living\n'
'"1", "1", "John Coltrane", 1926, 8.65, False\n'
'"2", "1", "Miles Davis", 1926, 9.87, False')
cols = as_table_columns(string_io)
assert_equals(cols[0]['name'], 'Name')
assert_equals(cols[0]['columnType'], 'STRING')
assert_equals(cols[1]['name'], 'Born')
assert_equals(cols[1]['columnType'], 'INTEGER')
assert_equals(cols[2]['name'], 'Hipness')
assert_equals(cols[2]['columnType'], 'DOUBLE')
assert_equals(cols[3]['name'], 'Living')
assert_equals(cols[3]['columnType'], 'STRING')
def test_build_table__with_csv():
string_io = StringIOContextManager('a,b\n' '1,c\n' '2,d\n' '3,e')
with patch.object(synapseclient.table, "as_table_columns",
return_value=[Column(name="a", columnType="INTEGER"),
Column(name="b", columnType="STRING")]),\
patch.object(io, "open", return_value=string_io):
table = build_table("test", "syn123", "some_file_name")
for col, row in enumerate(table):
assert_equals(row[0], (col + 1))
assert_equals(row[1], ["c", "d", "e"][col])
assert_equals(len(table), 3)
headers = [{
'name': 'a',
'columnType': 'INTEGER'
}, {
'name': 'b',
'columnType': 'STRING'
}]
assert_equals(headers, table.headers)
