def automaton_to_regex(automaton):
automaton = nfa_to_dfa(automaton)
states, transitions = __automaton_to_gnfa(automaton)
regex = __gnfa_to_regex(list(range(states)), transitions)
ast = __get_regex_ast(regex)
return __simplify_regex(ast)
def build_automaton(cls, regex, skip_whitespaces=False):
tokens = regex_tokenizer(regex, cls.grammar, skip_whitespaces=skip_whitespaces)
parse = cls.parser([t.ttype for t in tokens])
ast = evaluate_parse(parse, tokens)
nfa = ast.evaluate()
dfa = nfa_to_dfa(nfa)
minimized = automata_minimization(dfa)
return minimized
def test_automata_concatenation_recognize(a1, a2, text, recognize):
concatenation = automata_concatenation(a1, a2)
concatenation = nfa_to_dfa(concatenation)
assert recognize == concatenation.recognize(text)
def automaton_to_regex(automaton):
automaton = nfa_to_dfa(automaton)
states, transitions = __automaton_to_gnfa(automaton)
return __gnfa_to_regex(list(range(states)), transitions)
def test_automata_union_recognize(a1, a2, text, recognize):
union = automata_union(a1, a2)
union = nfa_to_dfa(union)
assert recognize == union.recognize(text)
def test_nfa_to_dfa_recognize(nfa, text, recognize):
dfa = nfa_to_dfa(nfa)
assert recognize == dfa.recognize(text)
def test_nfa_to_dfa_finals(nfa, finals):
dfa = nfa_to_dfa(nfa)
assert finals == len(dfa.finals)
def test_nfa_to_dfa_states(nfa, states):
dfa = nfa_to_dfa(nfa)
assert states == dfa.states
def test_automata_closure_recognize(automaton, text, recognize):
closure = automata_closure(automaton)
closure = nfa_to_dfa(closure)
assert recognize == closure.recognize(text)