view contrib/undumprevlog @ 15065:24a6c3f903bb stable

util: wrap lines with multi-byte characters correctly (issue2943)

This re-introduces the unicode conversion what was lost in d320e70442a5 5 years
ago and had the comment:
  To avoid corrupting multi-byte characters in line, we must wrap
  a Unicode string instead of a bytestring.

#!/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 1:
    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()