bytrend.py

#!/usr/bin/env python3
import array
import sys

if __name__ != "__main__":
    print("the fuck you do")
    exit(1)

def bytestrm(filename, chunksize=8192):
    with open(filename, "rb") as f:
        while True:
            buf = f.read(chunksize)
            if buf:
                for b in buf:
                    yield b
            else:
                break

if len(sys.argv) < 2:
    print("usage: {} filename".format(sys.argv[0]))
    exit(1)

vmax = sys.maxsize-2
trend = array.array('L')
for i in range(0,256):
    trend.append(0)

last = 400;
for b in bytestrm(str(sys.argv[1])):
    if last == b:
        trend[b] = trend[b] + 1
        if trend[b] >= vmax:
            print("overflow in {}".format(b))
    last = b

for i in range(0,256):
    print("{} {}".format(i, trend[i]))





#0-010134-ed-ks3318945 <~> time mono bytecunt.exe "$file" > a; time ./bytrend.py "$file" > b; diff a b
#
#real   0m0.115s
#user   0m0.052s
#sys    0m0.024s
#
#real   0m5.733s
#user   0m5.708s
#sys    0m0.004s