def test_tokenize_complex(self):
self.assertListEqual(
tokenize("^ENS(NEWS|)SSSEEN(WNSE|)EE(|SWEN)NNN$"),
[
"ENS",
"(",
"NEWS",
"|",
"",
")",
"SSSEEN",
"(",
"WNSE",
"|",
"",
")",
"EE",
"(",
"",
"|",
"SWEN",
")",
"NNN",
],
)
def parse(regex: str):
tokens = tokenize(regex)
stack: List[Node] = [Node()]
for token in tokens:
if token == "(":
stack.append(Node())
elif token == ")":
finished_node = stack.pop()
stack[len(stack) - 1].children.append(finished_node)
elif token == "|":
# before_or = stack[len(stack) - 1].children.pop()
stack[len(stack) - 1].children.append(token)
# stack[len(stack) - 1].children.append(before_or)
else:
stack[len(stack) - 1].children.append(token)
return stack.pop()
def test_tokenize_partly_empty_bracket(self):
self.assertListEqual(tokenize("^ENWW(NE|)$"), ["ENWW", "(", "NE", "|", "", ")"])
def test_tokenize_brackets(self):
self.assertListEqual(tokenize("^ENWW(NE|EW)$"), ["ENWW", "(", "NE", "|", "EW", ")"])
def test_tokenize_simple(self):
self.assertListEqual(tokenize("^ENWW$"), ["ENWW"])