ontonotes-duplicate-document-cluster.py

from collections import defaultdict
import re

s=open('/Users/cumeo/Downloads/dup-docs.txt').read()
pairs = [re.sub(' +', ' ', line).strip().split(' ') for line in s.strip().split('\n')]
clusters = defaultdict(set)
for doc1, doc2 in pairs:
    c = clusters[doc1]
    c.update(clusters[doc2])
    c.update({doc1, doc2})
    del clusters[doc2]
for v in clusters.values(): print(', '.join(v))