def fsm_diagram(grammar, start_symbol=START_SYMBOL):
def left_align(label):
return dot_escape(label.replace('\n', r'\l')).replace(r'\\l', '\\l')
dot = Digraph(comment="Grammar as Finite State Machine")
symbols = deque([start_symbol])
symbols_seen = set()
while len(symbols) > 0:
symbol = symbols.popleft()
symbols_seen.add(symbol)
dot.node(symbol, dot_escape(unicode_escape(symbol)))
for expansion in grammar[symbol]:
nts = nonterminals(expansion)
if len(nts) > 0:
target_symbol = nts[-1]
if target_symbol not in symbols_seen:
symbols.append(target_symbol)
label = expansion.replace(target_symbol, '')
dot.edge(symbol, target_symbol, left_align(unicode_escape(label)))
return display(dot)
def expansion_cost(self, expansion, seen=set()):
symbols = nonterminals(expansion)
if len(symbols) == 0:
return 1 # no symbol
if any(s in seen for s in symbols):
return float('inf')
# the value of a expansion is the sum of all expandable variables
# inside + 1
return sum(self.symbol_cost(s, seen) for s in symbols) + 1
