def read_doc(doc, labels):
doc = SpaceTokenizer().tokenize(doc.strip())
# doc = doc.strip().split()
labels = labels.strip().split('|')
labels = [la.split() for la in labels]
for i in range(len(labels)):
for j in range(len(labels[i])):
labels[i][j] = int(labels[i][j])
res_labels = [0] * len(doc)
for la in labels:
if la[2] != 0:
start = la[0]
end = la[1]
res_labels[start:end + 1] = [1] * (end + 1 - start)
return [(doc[i], str(res_labels[i])) for i in range(len(doc))]
