view tests/heredoctest.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.

import sys


def flush():
    sys.stdout.flush()
    sys.stderr.flush()


globalvars = {}
lines = sys.stdin.readlines()
while lines:
    l = lines.pop(0)
    if l.startswith('SALT'):
        print(l[:-1])
    elif l.startswith('>>> '):
        snippet = l[4:]
        while lines and lines[0].startswith('... '):
            l = lines.pop(0)
            snippet += l[4:]
        c = compile(snippet, '<heredoc>', 'single')
        try:
            flush()
            exec(c, globalvars)
            flush()
        except Exception as inst:
            flush()
            print(repr(inst))