def test_to_cfg(self):
regex = Regex("a")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains(["a"]))
regex = Regex("a|b")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains(["b"]))
regex = Regex("a b")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains(["a", "b"]))
regex = Regex("a*")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains([]))
self.assertTrue(cfg.contains(["a"]))
self.assertTrue(cfg.contains(["a", "a"]))
regex = Regex("epsilon")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains([]))
regex = Regex("")
cfg = regex.to_cfg()
self.assertTrue(cfg.is_empty())
regex = Regex("(a|b)* c")
cfg = regex.to_cfg()
self.assertTrue(cfg.contains(["c"]))
self.assertTrue(cfg.contains(["a", "c"]))
self.assertTrue(cfg.contains(["a", "b", "c"]))
def read_cfgrammar(name):
file = open(name, 'r')
s = ''
cfg_from_regex = []
for line in file:
if 'regexp' in line:
line = line.replace('regexp', "")
head = line.split(" -> ")[0]
regex = Regex(line.split(" -> ")[1][:-1])
cfg_from_regex.append(regex.to_cfg(starting_symbol=head))
else:
s += line
file.close()
cfg = CFG.from_text(s)
for c in cfg_from_regex:
cfg = CFG(cfg.variables.union(c.variables),
cfg.terminals.union(c.terminals), cfg.start_symbol,
cfg.productions.union(c.productions))
return cfg
