annotate contrib/undumprevlog @ 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
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump


import sys
from mercurial.node import bin
from mercurial import (
    encoding,
    revlog,
    transaction,
    vfs as vfsmod,
)
from mercurial.utils import procutil

from mercurial.revlogutils import (
    constants as revlog_constants,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    procutil.setbinary(fp)

opener = vfsmod.vfs(b'.', False)
tr = transaction.transaction(
    sys.stderr.write, opener, {b'store': opener}, b"undump.journal"
)
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = encoding.strtolocal(l[6:-1])
        assert f.endswith(b'.i')
        r = revlog.revlog(
            opener,
            target=(revlog_constants.KIND_OTHER, b'undump-revlog'),
            radix=f[:-2],
        )
        procutil.stdout.write(b'%s\n' % f)
    elif l.startswith("node:"):
        n = bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = bin(p[0])
        p2 = bin(p[1])
    elif l.startswith("length:"):
        length = int(l[8:-1])
        sys.stdin.readline()  # start marker
        d = encoding.strtolocal(sys.stdin.read(length))
        sys.stdin.readline()  # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()