check.py

import sys

f = open(sys.argv[1], 'r')
txt = f.readline().strip()
patterns = [p.strip() for p in f]

f = open(sys.argv[2], 'r')
answers = [int(i) for i in f.readline().strip().split(' ')]
anset = set()

for ans in answers:
    good = False
    for p in patterns:
        if txt[ans:ans+len(p)] == p:
            good = True
    if not good:
        print "=== BAD: ", ans
    if ans in anset:
        print "=== DUPLICATE: ", ans
    anset.add(ans)
#    print ans

for p in patterns:
#    print p
    idx = 0
    while True:
        idx = txt.find(p, idx)
        if idx == -1:
            break
        if idx not in anset:
            print "=== MISSING: ", p, idx
        idx += 1

Use: check.py dataset.txt answers.txt