def _build_filter(self, q):
result = None
if type(q) is not list:
return unicode(q)
if not q:
raise_malformed("Empty expression not allowed", q)
op = q[0]
if op == "!":
assert_len(q, 2, "! is a single arity operator, invalid number of arguments")
result = "not " + self._build_filter(q[1])
elif op == "isnull":
assert_len(q, 2, "isnull is a single arity operator, invalid number of arguments")
# Slightly hacky but the only way I've come up with so far.
result = "({arg} != {arg})".format(arg=q[1])
elif op in COMPARISON_OPERATORS:
assert_len(q, 3)
_, arg1, arg2 = q
result = self._build_filter(arg1) + " " + op + " " + self._build_filter(arg2)
elif op in JOINING_OPERATORS:
if len(q) < 2:
raise_malformed("Invalid number of arguments", q)
elif len(q) == 2:
# Conjunctions and disjunctions with only one clause are OK
result = self._build_filter(q[1])
else:
result = ' {op} '.format(op=op).join(self._build_filter(x) for x in q[1:])
elif op == 'in':
col_name, args = prepare_in_clause(q, FILTER_ENGINE_NUMEXPR)
var_name = self._insert_in_env(args)
result = '{col_name} in @env.{var_name}'.format(col_name=col_name, var_name=var_name)
else:
raise_malformed("Unknown operator", q)
return "({result})".format(result=result)
def _in_filter(df, q):
col_name, args = prepare_in_clause(q, FILTER_ENGINE_PANDAS)
return df[col_name].isin(args)