def test_parse_output_schema_from_comment():
# partitionby_has: a, b
# partitionby_is: c , d
# presort_has: a, b desc
# presort_is: a asc, b desc
# input_has: a,b: str,c
# input_is: a: int , b : str
# dummy: ssdsfd
def t():
pass
# input_is:
def t2():
pass
assert {
"partitionby_has": ["a", "b"],
"partitionby_is": ["c", "d"],
"presort_has": [("a", True), ("b", False)],
"presort_is": [("a", True), ("b", False)],
"input_has": ["a", "b:str", "c"],
"input_is": "a:int,b:str",
} == parse_validation_rules_from_comment(t)
raises(SyntaxError, lambda: parse_validation_rules_from_comment(t2))
def from_func(func: Callable, schema: Any,
validation_rules: Dict[str, Any]) -> "_FuncAsProcessor":
if schema is None:
schema = parse_output_schema_from_comment(func)
validation_rules.update(parse_validation_rules_from_comment(func))
tr = _FuncAsProcessor()
tr._wrapper = FunctionWrapper(func, "^e?(c|[dlspq]+)x*z?$",
"^[dlspq]$") # type: ignore
tr._engine_param = (tr._wrapper._params.get_value_by_index(0) if
tr._wrapper.input_code.startswith("e") else None)
tr._use_dfs = "c" in tr._wrapper.input_code
tr._need_output_schema = tr._wrapper.need_output_schema
tr._validation_rules = validation_rules
tr._output_schema = Schema(schema)
if len(tr._output_schema) == 0:
assert_or_throw(
tr._need_output_schema is None or not tr._need_output_schema,
FugueInterfacelessError(
f"schema must be provided for return type {tr._wrapper._rt}"
),
)
else:
assert_or_throw(
tr._need_output_schema is None or tr._need_output_schema,
FugueInterfacelessError(
f"schema must not be provided for return type {tr._wrapper._rt}"
),
)
return tr
def from_func(
func: Callable, validation_rules: Dict[str, Any]
) -> "_FuncAsOutputter":
validation_rules.update(parse_validation_rules_from_comment(func))
tr = _FuncAsOutputter()
tr._wrapper = FunctionWrapper( # type: ignore
func, "^e?(c|[dlspq]+)x*z?$", "^n$"
)
tr._need_engine = tr._wrapper.input_code.startswith("e")
tr._use_dfs = "c" in tr._wrapper.input_code
tr._validation_rules = validation_rules
return tr
def from_func(
func: Callable, schema: Any,
validation_rules: Dict[str, Any]) -> "_FuncAsOutputTransformer":
assert_or_throw(schema is None,
"schema must be None for output transformers")
validation_rules.update(parse_validation_rules_from_comment(func))
tr = _FuncAsOutputTransformer()
tr._wrapper = FunctionWrapper( # type: ignore
func, "^[lspq][fF]?x*z?$", "^[lspnq]$")
tr._output_schema_arg = None # type: ignore
tr._validation_rules = validation_rules # type: ignore
tr._uses_callback = "f" in tr._wrapper.input_code.lower(
) # type: ignore
tr._requires_callback = "F" in tr._wrapper.input_code # type: ignore
return tr
def from_func(func: Callable, schema: Any,
validation_rules: Dict[str, Any]) -> "_FuncAsTransformer":
if schema is None:
schema = parse_output_schema_from_comment(func)
if isinstance(schema, Schema): # to be less strict on determinism
schema = str(schema)
validation_rules.update(parse_validation_rules_from_comment(func))
assert_arg_not_none(schema, "schema")
tr = _FuncAsTransformer()
tr._wrapper = FunctionWrapper( # type: ignore
func, "^[lspq][fF]?x*z?$", "^[lspq]$")
tr._output_schema_arg = schema # type: ignore
tr._validation_rules = validation_rules # type: ignore
tr._uses_callback = "f" in tr._wrapper.input_code.lower(
) # type: ignore
tr._requires_callback = "F" in tr._wrapper.input_code # type: ignore
return tr
