def _parse(toklist: Iterable[Tok]) -> Tuple[ResponseDict, Dict[int, str]]:
""" Parse a token list as a query """
bp = Query._parser
assert bp is not None
num_sent = 0
num_parsed_sent = 0
rdc = Reducer(bp.grammar)
trees: Dict[int, str] = dict()
sent: List[Tok] = []
for t in toklist:
if t[0] == TOK.S_BEGIN:
if num_sent > 0:
# A second sentence is beginning: this is not valid for a query
raise ParseError(
"A query cannot contain more than one sentence")
sent = []
elif t[0] == TOK.S_END:
slen = len(sent)
if not slen:
continue
num_sent += 1
# Parse the accumulated sentence
num = 0
try:
# Parse the sentence
forest = bp.go(sent)
if forest is not None:
num = Fast_Parser.num_combinations(forest)
if num > 1:
# Reduce the resulting forest
forest = rdc.go(forest)
except ParseError:
forest = None
num = 0
if num > 0:
num_parsed_sent += 1
# Obtain a text representation of the parse tree
assert forest is not None
trees[num_sent] = ParseForestDumper.dump_forest(forest)
elif t[0] == TOK.P_BEGIN:
pass
elif t[0] == TOK.P_END:
pass
else:
sent.append(t)
result: ResponseDict = dict(num_sent=num_sent,
num_parsed_sent=num_parsed_sent)
return result, trees
def _parse(toklist):
""" Parse a token list as a query """
# Parse with the nonterminal 'QueryRoot' as the grammar root
with Fast_Parser(verbose=False, root=_QUERY_ROOT) as bp:
sent_begin = 0
num_sent = 0
num_parsed_sent = 0
rdc = Reducer(bp.grammar)
trees = dict()
sent = []
for ix, t in enumerate(toklist):
if t[0] == TOK.S_BEGIN:
sent = []
sent_begin = ix
elif t[0] == TOK.S_END:
slen = len(sent)
if not slen:
continue
num_sent += 1
# Parse the accumulated sentence
num = 0
try:
# Parse the sentence
forest = bp.go(sent)
if forest is not None:
num = Fast_Parser.num_combinations(forest)
if num > 1:
# Reduce the resulting forest
forest = rdc.go(forest)
except ParseError as e:
forest = None
if num > 0:
num_parsed_sent += 1
# Obtain a text representation of the parse tree
trees[num_sent] = ParseForestDumper.dump_forest(forest)
# ParseForestPrinter.print_forest(forest)
elif t[0] == TOK.P_BEGIN:
pass
elif t[0] == TOK.P_END:
pass
else:
sent.append(t)
result = dict(num_sent=num_sent, num_parsed_sent=num_parsed_sent)
return result, trees
def _parse(toklist):
""" Parse a token list as a query """
# Parse with the nonterminal 'QueryRoot' as the grammar root
with Fast_Parser(verbose=False, root=_QUERY_ROOT) as bp:
sent_begin = 0
num_sent = 0
num_parsed_sent = 0
rdc = Reducer(bp.grammar)
trees = dict()
sent = []
for ix, t in enumerate(toklist):
if t[0] == TOK.S_BEGIN:
sent = []
sent_begin = ix
elif t[0] == TOK.S_END:
slen = len(sent)
if not slen:
continue
num_sent += 1
# Parse the accumulated sentence
num = 0
try:
# Parse the sentence
forest = bp.go(sent)
if forest is not None:
num = Fast_Parser.num_combinations(forest)
if num > 1:
# Reduce the resulting forest
forest = rdc.go(forest)
except ParseError as e:
forest = None
if num > 0:
num_parsed_sent += 1
# Obtain a text representation of the parse tree
trees[num_sent] = ParseForestDumper.dump_forest(forest)
#ParseForestPrinter.print_forest(forest)
elif t[0] == TOK.P_BEGIN:
pass
elif t[0] == TOK.P_END:
pass
else:
sent.append(t)
result = dict(num_sent=num_sent, num_parsed_sent=num_parsed_sent)
return result, trees
def parse(self):
""" Parse the sentence """
num = 0
score = 0
try:
forest = self._ip._parser.go(self._s)
if forest is not None:
num = Fast_Parser.num_combinations(forest)
if num > 1:
forest, score = self._ip._reducer.go_with_score(forest)
except ParseError as e:
forest = None
self._err_index = e.token_index
self._tree = forest
self._score = score
self._ip._add_sentence(self, num)
return num > 0
def _parse(toklist):
""" Parse a token list as a query """
bp = Query._parser
num_sent = 0
num_parsed_sent = 0
rdc = Reducer(bp.grammar)
trees = dict()
sent = []
for t in toklist:
if t[0] == TOK.S_BEGIN:
sent = []
elif t[0] == TOK.S_END:
slen = len(sent)
if not slen:
continue
num_sent += 1
# Parse the accumulated sentence
num = 0
try:
# Parse the sentence
forest = bp.go(sent)
if forest is not None:
num = Fast_Parser.num_combinations(forest)
if num > 1:
# Reduce the resulting forest
forest = rdc.go(forest)
except ParseError:
forest = None
if num > 0:
num_parsed_sent += 1
# Obtain a text representation of the parse tree
trees[num_sent] = ParseForestDumper.dump_forest(forest)
elif t[0] == TOK.P_BEGIN:
pass
elif t[0] == TOK.P_END:
pass
else:
sent.append(t)
result = dict(num_sent=num_sent, num_parsed_sent=num_parsed_sent)
return result, trees