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 _leaf_node(df, q):
if isinstance(q, basestring):
if is_quoted(q):
return q[1:-1].encode('utf-8')
try:
return df[q]
except KeyError:
raise_malformed("Unknown column", q)
return q
