def test_row_and_no_schema(self):
coder = TableRowJsonCoder()
test_row = bigquery.TableRow(
f=[bigquery.TableCell(v=to_json_value(e))
for e in ['abc', 123, 123.456, True]])
with self.assertRaisesRegexp(AttributeError,
r'^The TableRowJsonCoder requires'):
coder.encode(test_row)
def json_compliance_exception(self, value):
with self.assertRaisesRegexp(ValueError, re.escape(JSON_COMPLIANCE_ERROR)):
schema_definition = [('f', 'FLOAT')]
schema = bigquery.TableSchema(
fields=[bigquery.TableFieldSchema(name=k, type=v)
for k, v in schema_definition])
coder = TableRowJsonCoder(table_schema=schema)
test_row = bigquery.TableRow(
f=[bigquery.TableCell(v=to_json_value(value))])
coder.encode(test_row)
def test_row_and_no_schema(self):
coder = TableRowJsonCoder()
test_row = bigquery.TableRow(f=[
bigquery.TableCell(v=to_json_value(e))
for e in ['abc', 123, 123.456, True]
])
with self.assertRaises(AttributeError) as ctx:
coder.encode(test_row)
self.assertTrue(
ctx.exception.message.startswith('The TableRowJsonCoder requires'))
def test_row_as_table_row(self):
schema_definition = [('s', 'STRING'), ('i', 'INTEGER'), ('f', 'FLOAT'),
('b', 'BOOLEAN'), ('n', 'NUMERIC'), ('r', 'RECORD'),
('g', 'GEOGRAPHY')]
data_definition = [
'abc',
123,
123.456,
True,
decimal.Decimal('987654321.987654321'), {
'a': 'b'
},
'LINESTRING(1 2, 3 4, 5 6, 7 8)'
]
str_def = (
'{"s": "abc", '
'"i": 123, '
'"f": 123.456, '
'"b": true, '
'"n": "987654321.987654321", '
'"r": {"a": "b"}, '
'"g": "LINESTRING(1 2, 3 4, 5 6, 7 8)"}')
schema = bigquery.TableSchema(
fields=[
bigquery.TableFieldSchema(name=k, type=v) for k,
v in schema_definition
])
coder = TableRowJsonCoder(table_schema=schema)
def value_or_decimal_to_json(val):
if isinstance(val, decimal.Decimal):
return to_json_value(str(val))
else:
return to_json_value(val)
test_row = bigquery.TableRow(
f=[
bigquery.TableCell(v=value_or_decimal_to_json(e))
for e in data_definition
])
self.assertEqual(str_def, coder.encode(test_row))
self.assertEqual(test_row, coder.decode(coder.encode(test_row)))
# A coder without schema can still decode.
self.assertEqual(
test_row, TableRowJsonCoder().decode(coder.encode(test_row)))
def test_row_as_table_row(self):
schema_definition = [('s', 'STRING'), ('i', 'INTEGER'), ('f', 'FLOAT'),
('b', 'BOOLEAN'), ('r', 'RECORD')]
data_defination = ['abc', 123, 123.456, True, {'a': 'b'}]
str_def = '{"s": "abc", "i": 123, "f": 123.456, "b": true, "r": {"a": "b"}}'
schema = bigquery.TableSchema(fields=[
bigquery.TableFieldSchema(name=k, type=v)
for k, v in schema_definition
])
coder = TableRowJsonCoder(table_schema=schema)
test_row = bigquery.TableRow(f=[
bigquery.TableCell(v=to_json_value(e)) for e in data_defination
])
self.assertEqual(str_def, coder.encode(test_row))
self.assertEqual(test_row, coder.decode(coder.encode(test_row)))
# A coder without schema can still decode.
self.assertEqual(test_row,
TableRowJsonCoder().decode(coder.encode(test_row)))
def decode(self, encoded_table_row):
od = json.loads(encoded_table_row,
object_pairs_hook=collections.OrderedDict)
return bigquery.TableRow(
f=[bigquery.TableCell(v=to_json_value(e)) for e in itervalues(od)])
def get_test_rows(self):
now = time.time()
dt = datetime.datetime.utcfromtimestamp(float(now))
ts = dt.strftime('%Y-%m-%d %H:%M:%S.%f UTC')
expected_rows = [{
'i':
1,
's':
'abc',
'f':
2.3,
'b':
True,
't':
ts,
'dt':
'2016-10-31',
'ts':
'22:39:12.627498',
'dt_ts':
'2008-12-25T07:30:00',
'r': {
's2': 'b'
},
'rpr': [{
's3': 'c',
'rpr2': [{
'rs': ['d', 'e'],
's4': None
}]
}]
}, {
'i': 10,
's': 'xyz',
'f': -3.14,
'b': False,
'rpr': [],
't': None,
'dt': None,
'ts': None,
'dt_ts': None,
'r': None,
}]
nested_schema = [
bigquery.TableFieldSchema(name='s2',
type='STRING',
mode='NULLABLE')
]
nested_schema_2 = [
bigquery.TableFieldSchema(name='s3',
type='STRING',
mode='NULLABLE'),
bigquery.TableFieldSchema(
name='rpr2',
type='RECORD',
mode='REPEATED',
fields=[
bigquery.TableFieldSchema(name='rs',
type='STRING',
mode='REPEATED'),
bigquery.TableFieldSchema(name='s4',
type='STRING',
mode='NULLABLE')
])
]
schema = bigquery.TableSchema(fields=[
bigquery.TableFieldSchema(
name='b', type='BOOLEAN', mode='REQUIRED'),
bigquery.TableFieldSchema(name='f', type='FLOAT', mode='REQUIRED'),
bigquery.TableFieldSchema(
name='i', type='INTEGER', mode='REQUIRED'),
bigquery.TableFieldSchema(name='s', type='STRING',
mode='REQUIRED'),
bigquery.TableFieldSchema(
name='t', type='TIMESTAMP', mode='NULLABLE'),
bigquery.TableFieldSchema(name='dt', type='DATE', mode='NULLABLE'),
bigquery.TableFieldSchema(name='ts', type='TIME', mode='NULLABLE'),
bigquery.TableFieldSchema(
name='dt_ts', type='DATETIME', mode='NULLABLE'),
bigquery.TableFieldSchema(
name='r', type='RECORD', mode='NULLABLE',
fields=nested_schema),
bigquery.TableFieldSchema(name='rpr',
type='RECORD',
mode='REPEATED',
fields=nested_schema_2)
])
table_rows = [
bigquery.TableRow(f=[
bigquery.TableCell(v=to_json_value('true')),
bigquery.TableCell(v=to_json_value(str(2.3))),
bigquery.TableCell(v=to_json_value(str(1))),
bigquery.TableCell(v=to_json_value('abc')),
# For timestamps cannot use str() because it will truncate the
# number representing the timestamp.
bigquery.TableCell(v=to_json_value('%f' % now)),
bigquery.TableCell(v=to_json_value('2016-10-31')),
bigquery.TableCell(v=to_json_value('22:39:12.627498')),
bigquery.TableCell(v=to_json_value('2008-12-25T07:30:00')),
# For record we cannot use dict because it doesn't create nested
# schemas correctly so we have to use this f,v based format
bigquery.TableCell(v=to_json_value({'f': [{
'v': 'b'
}]})),
bigquery.TableCell(v=to_json_value([{
'v': {
'f': [{
'v': 'c'
}, {
'v': [{
'v': {
'f': [{
'v': [{
'v': 'd'
}, {
'v': 'e'
}]
}, {
'v': None
}]
}
}]
}]
}
}]))
]),
bigquery.TableRow(f=[
bigquery.TableCell(v=to_json_value('false')),
bigquery.TableCell(v=to_json_value(str(-3.14))),
bigquery.TableCell(v=to_json_value(str(10))),
bigquery.TableCell(v=to_json_value('xyz')),
bigquery.TableCell(v=None),
bigquery.TableCell(v=None),
bigquery.TableCell(v=None),
bigquery.TableCell(v=None),
bigquery.TableCell(v=None),
# REPEATED field without any values.
bigquery.TableCell(v=None)
])
]
return table_rows, schema, expected_rows
