Key distribution

key_distribution

#!/usr/bin/env python
#
import hashlib

def hasher(s):
    m=hashlib.sha1()
    m.update(s)
    return m.hexdigest()

def stringify_keyspace(a):
    s=''
    for i in a: s+=chr(i)
    return s[::-1]

def deserialize_hash(h):
    a=[]
    for i in h: a.append(i)
    return a

def stringify_block(h,b):
    s=''
    for i in range(0,b): s+=h[i]
    return s
"""
    Analyze frequency of starting blocks (of size b) in
    The hash (h) to determine optimal block size for 
    subtree roots.
"""
def analyze_distribution(h,b,a,grouping=0,blockcount=0):
    try:
        a[grouping][stringify_block(h,b)]+=1
    except:
        a[grouping][stringify_block(h,b)]=1
    return a
"""
    create the analysis table (empty)
"""
def init_analysis(groupingStart=0,groupingFinish=100):
    a=[]
    for i in range(groupingStart,groupingFinish):
        a.append({})
    return a

def increment_array(a,i,zeroState=0,highState=255):
    if a[i] == highState:
        try:
            increment_array(a,i+1)
        except:
            a.append(zeroState)
        a[i]=zeroState
    else:
        a[i]+=1

blocksize=4
keyspace=[0]
counter=0

groupingStart=0
groupingEnd=1

analysis=init_analysis(groupingStart,groupingEnd)   
while len(keyspace) <=2:
    increment_array(keyspace,0)
    hash_string=hasher(stringify_keyspace(keyspace))
    hash_array=deserialize_hash(hash_string)

    #Todo: determine grouping (e.g. tenths or 2TB blocks)
    grouping=0
    analysis=analyze_distribution(hash_array,blocksize,analysis,grouping)
    counter+=1

    print("{}: {}".format(hash_string,keyspace))



block_count=0
for group in analysis: 
    for i in group: 
        block_count+=1


print "="*60
print "Analysis:"
print "="*60
print "block count:{}".format(block_count)