I guess something like this... maybe? Surely someone has already done this much better, but I thought it might be a fun puzzle.
# Let's call it aggregate.py. You should test/validate this and not trust it at all because I don't. It does look like it works, but I can't promise anything like that. This was "for fun." For me in my world, it's not a problem that needs solving,
but if it helps someone, that'd be pretty cool. No follow-up questions, please.
./aggregate.py gen 100000 ips.txt # Make up some random IPs for testing
./aggregate.py aggregate 2 ips.txt # Aggregate... second argument is the "gap", third is the filename...
Most are still going to be /32s.
Some might look like this - maybe even bigger:
63.81.88.112/28 # This is your example set of IPs with a gap (difference) of 2.
"max gap" is the distance between IP addresses that can be clustered... an improvement might include "coverage" - a parameter indicating how many IPs must appear (ratio) in a cluster to create the aggregate (more meaningful with bigger gaps).
#!/your/path/to/python
import random
import sys
def inet_aton(ip_string):
octs = ip_string.split('.')
n = int(int(octs[0]) << 24) + int(int(octs[1]) << 16) + int(int(octs[2]) << 8) + int(octs[3])
return n
def inet_ntoa(ip):
octs = ( ip >> 24, (ip >> 16 & 255), (ip >> 8) & 255, ip & 255 )
return str(octs[0]) + "." + str(octs[1]) + "." + str(octs[2]) + "." + str(octs[3])
def gen_ips(num):
ips = []
for x in range(num):
ips.append(inet_ntoa(random.randint(0,pow(2,32)-1)))
# To make sure we have at least SOME nearlyconsecutive IPs...
ips += "63.81.88.116,63.81.88.118,63.81.88.120,63.81.88.122,63.81.88.124,63.81.88.126".split(",") # I added your example IPs.
return ips
def write_random_ips(num,fname):
ips = gen_ips(int(num))
f = open(fname,'w')
for ip in ips:
f.write(ip+'\n')
f.close()
def read_ips(fname):
return open(fname,'r').read(99999999).split('\n')
class Cluster():
def __init__(self):
self.ips = []
def add_ip(self,ip):
self.ips.append(ip)
def find_common_bits(ipa,ipb):
for bits in range(0,32):
mask = pow(2,32)-1 << bits & (pow(2,32)-1)
if ipa & mask == ipb & mask:
return 32-bits
else:
pass # print(f"{ipa} & (pow(2,{bits})-1) == {ipa & (pow(2,bits)-1)} ==!=== {ipb} & (pow(2,{bits})-1) == {ipb & (pow(2,bits)-1)}")
if len(sys.argv) == 4 and sys.argv[1] == "generate":
write_random_ips(sys.argv[2],sys.argv[3])
elif len(sys.argv) == 4 and sys.argv[1] == "aggregate": # TODO: Let's imagine a "coverage" field that augments the max_gap field... does the prefix cover too many IPs?
max_gap = int(sys.argv[2])
fname = sys.argv[3]
ips = [ inet_aton(ip) for ip in read_ips(fname) if ip!='' ] # ... it'd be a good idea to make sure it looks like an IP. Oh, this only does IPv4 btw.
ips.sort()
clusters=[Cluster()] # Add first (empty) cluster.. is this necessary? Who cares, moving on....
last_ip=None
for ip in ips:
if last_ip != None:
#print(f"Gap of {ip-last_ip} between {ip} and {last_ip}... {inet_ntoa(ip)} / {inet_ntoa(last_ip)}")
if ip - last_ip <= max_gap:
#print(f"Gap of {ip-last_ip} between {ip} and {last_ip}...")
clusters[-1].add_ip(ip)
else:
cluster=Cluster()
cluster.add_ip(ip)
clusters.append(cluster)
last_ip = ip
for cluster in clusters:
if len(cluster.ips) == 0:
continue
if len(cluster.ips) > 1:
first_ip=cluster.ips[0]
last_ip=cluster.ips[-1]
num_bits = find_common_bits(first_ip,last_ip)
mask = pow(2,32)-1 << (32-num_bits) & (pow(2,32)-1)
network = first_ip & mask
print(f"{inet_ntoa(network)}/{num_bits}")
else:
print(f"{inet_ntoa(cluster.ips[0])}/32")
else:
print("Usage:")
print("{0} generate [number of IPs] [file name] # Generate specified number of IPs, save to [file name]")
print("{0} aggregate [max gap] [file name] # Aggregate prefixes based on overlapping subnets/IPs per the max gap permitted...")