def _like_filter(df, q):
assert_len(q, 3)
op, column, raw_expr = q
if not is_quoted(raw_expr):
raise_malformed("like expects a quoted string as second argument", q)
regexp = unquote(raw_expr)
if not regexp.startswith('%'):
regexp = '^' + regexp
else:
regexp = regexp[1:]
if not regexp.endswith('%'):
regexp += '$'
else:
regexp = regexp[:-1]
# 'like' is case sensitive, 'ilike' is case insensitive
case = op == 'like'
try:
return df[column].str.contains(regexp, case=case)
except AttributeError:
raise_malformed("Invalid column type for (i)like", q)
def _prepare_arg(df, arg):
if isinstance(arg, basestring):
if is_quoted(arg):
return unquote(arg)
return getattr(df, arg)
return arg
def _add_stand_in_columns(df, stand_in_columns):
if not stand_in_columns:
return df
for column_name, stand_in_value in stand_in_columns:
if column_name not in df:
if stand_in_value in df:
df.loc[:, column_name] = df[stand_in_value]
else:
dtype = _get_dtype(stand_in_value)
stand_in_value = unquote(stand_in_value)
arr = numpy.full(len(df), stand_in_value, dtype=dtype)
df.loc[:, column_name] = pandas.Series(arr, index=df.index)