view tests/seq.py @ 50400:95acba2c29f6

encoding: avoid quadratic time complexity when json-encoding non-UTF8 strings

Apparently the code uses "+=" with a bytes object, which is linear-time, so the
whole encoding is quadratic-time. This patch makes us use a bytearray object,
instead, which has a(n amortized-)constant-time append operation.

The encoding is still not particularly fast, but at least a 10MB file
takes tens of seconds, not many hours to encode.

#!/usr/bin/env python3
#
# A portable replacement for 'seq'
#
# Usage:
#   seq STOP              [1, STOP] stepping by 1
#   seq START STOP        [START, STOP] stepping by 1
#   seq START STEP STOP   [START, STOP] stepping by STEP

import os
import sys

try:
    import msvcrt

    msvcrt.setmode(sys.stdin.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

start = 1
if len(sys.argv) > 2:
    start = int(sys.argv[1])

step = 1
if len(sys.argv) > 3:
    step = int(sys.argv[2])

stop = int(sys.argv[-1]) + 1

for i in range(start, stop, step):
    print(i)