def test_is_namedtuple(self):
class AType:
pass
a_type = AType
a_tuple = type((1, 2, 3))
a_namedtuple = ANamedTuple
self.assertTrue(is_namedtuple(a_namedtuple))
self.assertFalse(is_namedtuple(a_type))
self.assertFalse(is_namedtuple(a_tuple))
def beam_sql(self, line: str, cell: str) -> Union[None, PValue]:
"""The beam_sql cell magic that executes a Beam SQL.
Args:
line: (optional) the string on the same line after the beam_sql magic.
Used as the output variable name in the __main__ module.
cell: everything else in the same notebook cell as a string. Used as a
Beam SQL query.
Returns None if running into an error, otherwise a PValue as if a
SqlTransform is applied.
"""
if line and not line.strip().isidentifier() or keyword.iskeyword(
line.strip()):
on_error(
'The output_name "%s" is not a valid identifier. Please supply a '
'valid identifier that is not a Python keyword.', line)
return
if not cell or cell.isspace():
on_error('Please supply the sql to be executed.')
return
found = find_pcolls(cell, pcoll_by_name())
for _, pcoll in found.items():
if not is_namedtuple(pcoll.element_type):
on_error(
'PCollection %s of type %s is not a NamedTuple. See '
'https://beam.apache.org/documentation/programming-guide/#schemas '
'for more details.', pcoll, pcoll.element_type)
return
register_coder_for_schema(pcoll.element_type)
output_name, output = apply_sql(cell, line, found)
cache_output(output_name, output)
return output
def beam_sql(self,
line: str,
cell: Optional[str] = None) -> Optional[PValue]:
"""The beam_sql line/cell magic that executes a Beam SQL.
Args:
line: the string on the same line after the beam_sql magic.
cell: everything else in the same notebook cell as a string. If None,
beam_sql is used as line magic. Otherwise, cell magic.
Returns None if running into an error, otherwise a PValue as if a
SqlTransform is applied.
"""
input_str = line
if cell:
input_str += ' ' + cell
parsed = self._parser.parse(input_str.strip().split())
if not parsed:
# Failed to parse inputs, let the parser handle the exit.
return
output_name = parsed.output_name
verbose = parsed.verbose
query = parsed.query
if output_name and not output_name.isidentifier() or keyword.iskeyword(
output_name):
on_error(
'The output_name "%s" is not a valid identifier. Please supply a '
'valid identifier that is not a Python keyword.', line)
return
if not query:
on_error('Please supply the SQL query to be executed.')
return
query = ' '.join(query)
found = find_pcolls(query, pcoll_by_name(), verbose=verbose)
for _, pcoll in found.items():
if not is_namedtuple(pcoll.element_type):
on_error(
'PCollection %s of type %s is not a NamedTuple. See '
'https://beam.apache.org/documentation/programming-guide/#schemas '
'for more details.', pcoll, pcoll.element_type)
return
register_coder_for_schema(pcoll.element_type, verbose=verbose)
output_name, output = apply_sql(query, output_name, found)
cache_output(output_name, output)
return output