annotate contrib/undumprevlog @ 21564:2e91d4964ecd stable

subrepo: make "_sanitize()" work

"_sanitize()" was introduced by 224e96078708 on "stable" branch, but
it has done nothing for sanitizing since 224e96078708.

"_sanitize()" assumes "Visitor" design pattern:

    "os.walk()" should invoke specified function ("v" in this case)
    for each directory elements under specified path

but "os.walk()" assumes "Iterator" design pattern:

    callers of it should drive loop to scan each directory elements
    under specified path by themselves with the returned generator
    object

Because of this mismatching, "_sanitize()" just discards the generator
object returned by "os.walk()" and does nothing for sanitizing.

This patch makes "_sanitize()" work.

This patch also changes the format of warning message to show each
unlinked files, for multiple appearances of "potentially hostile
.hg/hgrc".

#!/usr/bin/env python
# Undump a dump from dumprevlog
# $ hg init
# $ undumprevlog < repo.dump

import sys
from mercurial import revlog, node, scmutil, util, transaction

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

opener = scmutil.opener('.', False)
tr = transaction.transaction(sys.stderr.write, opener, "undump.journal")
while True:
    l = sys.stdin.readline()
    if not l:
        break
    if l.startswith("file:"):
        f = l[6:-1]
        r = revlog.revlog(opener, f)
        print f
    elif l.startswith("node:"):
        n = node.bin(l[6:-1])
    elif l.startswith("linkrev:"):
        lr = int(l[9:-1])
    elif l.startswith("parents:"):
        p = l[9:-1].split()
        p1 = node.bin(p[0])
        p2 = node.bin(p[1])
    elif l.startswith("length:"):
        length = int(l[8:-1])
        sys.stdin.readline() # start marker
        d = sys.stdin.read(length)
        sys.stdin.readline() # end marker
        r.addrevision(d, tr, lr, p1, p2)

tr.close()