def _tree_helper(t, antvalues):
t = tree.str_to_tree(t)
for node in t.frontier():
x = rule.Nonterminal.from_str(node.label)
if isinstance(x, rule.Nonterminal):
node.insert_child(0, antvalues[x.getindex() - 1])
return t
def _tree_helper(t, antvalues):
t = tree.str_to_tree(t)
for node in t.frontier():
x = sym.fromstring(node.label)
if sym.isvar(x):
node.insert_child(0, antvalues[sym.getindex(x) - 1])
return t
def _tree_helper(t, antvalues):
t = tree.str_to_tree(t)
for node in t.frontier():
x = sym.fromstring(node.label)
if sym.isvar(x):
node.insert_child(0, antvalues[sym.getindex(x)-1])
return t
def _tree_helper(t, antvalues):
t = tree.str_to_tree(t)
for node in t.frontier():
x = rule.Nonterminal.from_str(node.label)
if isinstance(x, rule.Nonterminal):
node.insert_child(0, antvalues[x.getindex()-1])
return t
def __init__(self, file):
self.parses = {}
for line in file:
t = tree.str_to_tree(line)
if t is None:
log.write("warning: couldn't read tree\n")
continue
s = tuple([sym.fromstring(node.label) for node in t.frontier()])
self.parses[s] = t
def raduparse(t,radu=True):
if radu: t=radu2ptb(t)
return tree.str_to_tree(t)
def raduparse(t):
t=radu2ptb(t)
return tree.str_to_tree(t)
if opts.tags:
a.ftags = ftfile.readline().split()
a.etags = etfile.readline().split()
if len(a.ftags) != len(a.fwords):
sys.stderr.write(
"warning: length mismatch between French words and tags (%d != %d)\n"
% (len(a.ftags), len(a.fwords)))
if len(a.etags) != len(a.ewords):
sys.stderr.write(
"warning: length mismatch between English words and tags (%d != %d)\n"
% (len(a.etags), len(a.ewords)))
a.espans = None
if opts.trees:
if ebfile is not None:
etree = tree.str_to_tree(ebfile.readline())
if etree is None:
sys.stderr.write("warning, line %d: null tree" % a.lineno)
a.espans = {}
elif etree.length != len(a.ewords):
sys.stderr.write(
"warning, line %d: length mismatch between English words and trees (%d != %d)\n"
% (a.lineno, len(a.ewords), etree.length))
sys.stderr.write(
" start of English sentence: %s\n" %
" ".join([sym.tostring(x) for x in a.ewords[:5]]))
a.espans = {}
else:
remove_req(etree)
a.espans = etree.spans()
for (span, labels) in a.espans.iteritems():
a.write(log.file)
a.write_visual(log.file)
log.file.flush()
if opts.tags:
a.ftags = ftfile.readline().split()
a.etags = etfile.readline().split()
if len(a.ftags) != len(a.fwords):
sys.stderr.write("warning: length mismatch between French words and tags (%d != %d)\n" % (len(a.ftags), len(a.fwords)))
if len(a.etags) != len(a.ewords):
sys.stderr.write("warning: length mismatch between English words and tags (%d != %d)\n" % (len(a.etags), len(a.ewords)))
a.espans = None
if opts.trees:
if ebfile is not None:
etree = tree.str_to_tree(ebfile.readline())
if etree is None:
sys.stderr.write("warning, line %d: null tree" % a.lineno)
a.espans = {}
elif etree.length != len(a.ewords):
sys.stderr.write("warning, line %d: length mismatch between English words and trees (%d != %d)\n" % (a.lineno, len(a.ewords), etree.length))
sys.stderr.write(" start of English sentence: %s\n" % " ".join([sym.tostring(x) for x in a.ewords[:5]]))
a.espans = {}
else:
remove_req(etree)
a.espans = etree.spans()
for (span, labels) in a.espans.iteritems():
a.espans[span] = [sym.fromtag(x) for x in labels]
# done reading all input lines
if opts.discard_long_sentences and len(a.fwords) > opts.maxabslen:
relabeler2 = re.compile('-\d+-BAR$')
relabeler3 = re.compile('^@')
def relabel(label):
#sys.stderr.write("%sA\n" % label)
label=relabeler2.sub('-BAR', label)
label=relabeler1.sub('', label)
label=relabeler3.sub('', label)
return label
if __name__ == "__main__":
for l in sys.stdin:
(rid, trline) = l.split(' ', 1)
node=tree.str_to_tree(trline)
#sys.stdout.write("%s\n" % node.__str__())
begin=0
n_bad_rewrites=0
for n in node.preorder():
if(len(n.children)):
#if begin!=0:
# sys.stdout.write(" ### ")
begin=1
rewrite="%s(" % relabel(n.label)
ch=[]
for c in n.children:
ch.append(relabel(c.label))
#sys.stdout.write("%s" % ' '.join(ch))
rewrite+= "%s" % ' '.join(ch)
rewrite+=")"
for li, line in enumerate(sys.stdin):
fields = line.rstrip().split('\t')
try:
fstr, estr, astr = fields[:3]
except:
log.write("bad line, skipped: %s\n" % line.rstrip('\r\n'))
continue
if len(fields) == 4:
provenance = list(fields[3].split())
else:
provenance = []
if opts.french_trees:
try:
ftree = prepare_tree(tree.str_to_tree(fstr))
if ftree is None:
log.write("bad tree, skipped line\n")
continue
#fspans = label_spans(ftree)
fleaves = list(ftree.frontier())
fwords = [leaf.label for leaf in fleaves]
ftags = [leaf.parent.label for leaf in fleaves]
fcb = crossing_brackets(ftree)
except Exception as e:
log.write("bad ftree, skipped: %s\n" % fstr)
log.write("reason: %s\n" % e)
continue
else:
fwords = fstr.split()
