Python grammar.is_nonterminal函数代码示例

    def apply(self, chart, grammar, edge):
        if edge.is_complete(): return
        nextsym, index = edge.nextsym(), edge.end()
        if not is_nonterminal(nextsym): return

        # If we've already applied this rule to an edge with the same
        # next & end, and the chart & grammar have not changed, then
        # just return (no new edges to add).
        nextsym_with_bindings = edge.next_with_bindings()
        done = self._done.get((nextsym_with_bindings, index), (None, None))
        if done[0] is chart and done[1] is grammar:
            return

        for prod in grammar.productions(lhs=nextsym):
            # If the left corner in the predicted production is
            # leaf, it must match with the input.
            if prod.rhs():
                first = prod.rhs()[0]
                if is_terminal(first):
                    if index >= chart.num_leaves(): continue
                    if first != chart.leaf(index): continue

            # We rename vars here, because we don't want variables
            # from the two different productions to match.
            if unify(prod.lhs(), nextsym_with_bindings, rename_vars=True):
                new_edge = FeatureTreeEdge.from_production(prod, edge.end())
                if chart.insert(new_edge, ()):
                    yield new_edge

        # Record the fact that we've applied this rule.
        self._done[nextsym_with_bindings, index] = (chart, grammar)

def remove_unitary_productions(cfg_grammar):
	"""
	Remove unitary-productions that aren't terminals, by making sure all 
	downstream productions get trickled up

	unfortunately, this is recursive, because you might create singletons as you're shifting things
	Note, this does NOT detect cycles
	"""
	unary = False
	productions = cfg_grammar.productions()
	for production in productions:
		if len(production) == 1:
			# Identity the first unary productions
			if is_nonterminal(production.rhs()[0]):
				unary = production
				break

	if not unary:
		# Base Case
		return cfg_grammar
	else:
		# get all productions of B, so we can make them all productions of A
		b_prods = cfg_grammar.productions(lhs=unary.rhs()[0])
		b_rhses = [b_prod.rhs() for b_prod in b_prods]

		existing_productions = [prod for prod in productions if prod != unary]
		new_productions = [Production(unary.lhs(), b_rhs) for b_rhs in b_rhses]

		new_grammar = CFG(cfg_grammar.start(), existing_productions+new_productions)
		return remove_unitary_productions(new_grammar)

    def apply(self, chart, grammar, edge):
        if edge.is_incomplete():
            return
        found = edge.lhs()
        for prod in grammar.productions(rhs=found):
            bindings = {}
            if isinstance(edge, FeatureTreeEdge):
                _next = prod.rhs()[0]
                if not is_nonterminal(_next):
                    continue

                # We rename vars here, because we don't want variables
                # from the two different productions to match.
                used_vars = find_variables(
                    (prod.lhs(),) + prod.rhs(), fs_class=FeatStruct
                )
                found = found.rename_variables(used_vars=used_vars)

                result = unify(_next, found, bindings, rename_vars=False)
                if result is None:
                    continue

            new_edge = FeatureTreeEdge.from_production(
                prod, edge.start()
            ).move_dot_forward(edge.end(), bindings)
            if chart.insert(new_edge, (edge,)):
                yield new_edge

def _expand(symbol,grammar):
	if is_nonterminal(symbol):
		rules = grammar.productions(lhs=symbol)
		probs = [r.prob() for r in rules]
		rule = choice(rules,p=probs)
		return (rule.rhs(),log(rule.prob()))
	else:
		return ((symbol,),0.0)

def SampleFromPCFG(grammar,start=None):
	if start==None:
		tupleSymbols = (grammar.start(),)
	else:
		tupleSymbols = (start,)
	lprob = 0.0
	while any(is_nonterminal(symbol) for symbol in tupleSymbols):
		tupleSymbols,lprob1 = _expand_seq(tupleSymbols,grammar)
		lprob += lprob1
	return (tupleSymbols,lprob)

 def gen_frame_line(self, nt):
     sentence = ''
     prods = random.sample(self.cfg.productions(lhs=nt),len(self.cfg.productions(lhs=nt)))
     valid = True
     for prod in prods:
         #valid = True
         for sym in prod.rhs():
             if is_nonterminal(sym):
                 if len(self.cfg.productions(lhs=sym)) < 1:
                     valid = False
         if valid == True:
             for sym in prod.rhs():
                 if is_nonterminal(sym):
                     sentence += self.gen_frame_line(sym)
                 else:
                     sentence += sym + ' '
             break
     if valid == False:
         return "ERROR"
     else:
         return sentence #removed capitalize

def check_is_nonterminal(*nts):
    """
    Asserts that all of one or more objects are Nonterminals.

    :param nts: An object, which may or may not be a Nonterminal

    :return: None
    """
    for nt in nts:
        if not gr.is_nonterminal(nt):
            raise TypeError("{} must be a nonterminal".format({}))
    return

    def _get_arg_product_rules(self, a_doc_id, a_arg, a_rel, a_parses):
        """Extract syntactic production rules for the given arg.

        Args:
          a_doc_id (str):
            id of the document
          a_arg (str):
            argument to extract productions for
          a_rel (dict):
            discourse relation to extract features for
          a_parses (dict):
            parsed sentences

        Returns:
          set:
            set of syntactic productions

        """
        ret = set()
        # obtain token indices for each arg sentence
        snt_id = None
        snt2tok = self._get_snt2tok(a_rel[a_arg][TOK_LIST])
        # obtain set of leaves corresponding to that argument
        arg_leaves = set()
        subt_leaves = set()
        processed_leaves = set()
        itree = itree_str = inode_path = None
        for snt_id, toks in snt2tok.iteritems():
            itree_str = a_parses[a_doc_id][SENTENCES][snt_id][PARSE_TREE]
            itree = Tree.fromstring(itree_str)
            if not itree.leaves():
                print("Invalid parse tree for sentence {:d}".format(snt_id),
                      file=sys.stderr)
                continue
            # obtain all terminal syntactic nodes from the arg
            for itok in toks:
                inode_path = itree.leaf_treeposition(itok)
                arg_leaves.add(itree[inode_path])
            # check all subtrees (not efficient, but easy to implement)
            for s_t in itree.subtrees():
                subt_leaves.update(s_t.leaves())
                if subt_leaves.issubset(arg_leaves) and \
                   not subt_leaves.issubset(processed_leaves):
                    ret.update(str(p) for p in itree.productions()
                               if any(is_nonterminal(n)
                                      for n in p.rhs()))
                    processed_leaves.update(subt_leaves)
                subt_leaves.clear()
                if processed_leaves == arg_leaves:
                    break
            arg_leaves.clear()
            processed_leaves.clear()
        return ret

def pcky(sentence, grammar):
    tokens = word_tokenize(sentence)
    ts = '[0]'
    for i, token in enumerate(tokens):
        ts += ' ' + token + ' [{}]'.format(i + 1)
    print(ts)
    non_terminal = set([prod.lhs() for prod in grammar.productions() if is_nonterminal(prod.lhs())])
    table = [[{nt: 0 for nt in non_terminal} for i in range(len(tokens) + 1)] for j in range(len(tokens) + 1)]
    for i, token in enumerate(tokens):
        productions = grammar.productions(rhs=token)
        for prod in productions:
            table[i][i + 1][prod.lhs()] = prod.prob()

    for span in range(2, len(tokens) + 1):
        for start in range(len(tokens) - span + 1):
            end = start + span
            for split in range(start + 1, end):
                non_term1 = table[start][split]
                non_term2 = table[split][end]
                for nt1 in non_term1:
                    for nt2 in non_term2:
                        if non_term1[nt1] > 0 and non_term2[nt2] > 0:
                            prodlist = grammar.productions(rhs=nt1)
                            for prod in prodlist:
                                if prod.rhs() == (nt1, nt2):
                                    table[start][end][prod.lhs()] = prod.prob() * non_term1[nt1] * non_term2[nt2]
                                    print('[{}] {}:({:.2f}) [{}] {}:({:.2f}) [{}] -> [{}] {}:({:.5f}) [{}]'.format(start, nt1,
                                                                                                       non_term1[nt1],
                                                                                                       split, nt2,
                                                                                                       non_term2[nt2],
                                                                                                       end,
                                                                                                       start,
                                                                                                       prod.lhs(),
                                                                                                       table[start][end][prod.lhs()],
                                                                                                       end))

    if table[0][len(tokens)][grammar.start()] > 0:
        print('The sentence is derived from the grammar')
        return True
    else:
        print('The sentence is not derived from the grammar')
        return False