Code used to generate the Thunno 2 corpus

corpus.py

import collections


digraphs = collections.Counter()
trigraphs = collections.Counter()
quadgraphs = collections.Counter()


with open("programs.txt") as f:
    # List of all Thunno 2 programs collected by SEDE query
    programs = f.read().splitlines()


for prog in programs:
    
    # Digraphs (2 characters)
    for a, b in zip(prog, prog[1:]):
        digraphs[a, b] += 1

    # Trigraphs (3 characters)
    for a, b, c in zip(prog, prog[1:], prog[2:]):
        trigraphs[a, b, c] += 1

    # Quadgraphs (4 characters)
    for a, b, c, d in zip(prog, prog[1:], prog[2:], prog[3:]):
        quadgraphs[a, b, c, d] += 1


print("2-graphs:\n")
for d, n in digraphs.most_common(30):
    print("%4d %s" % (n, "".join(d)))

print("\n3-graphs:")
for d, n in trigraphs.most_common(25):
    print("%4d %s" % (n, "".join(d)))

print("\n4-graphs:\n")
for d, n in quadgraphs.most_common(20):
    print("%4d %s" % (n, "".join(d)))