view contrib/fixpax.py @ 33928:6c119dbfd0c0

encoding: add fast path of from/toutf8b() for ASCII strings

See the previous patch for why.

The added test seems not making much sense because ASCII strings should
never contain "\xed" and be valid UTF-8.

  (with mercurial repo)
  $ export HGRCPATH=/dev/null HGPLAIN=
  $ hg log --time --config experimental.stabilization=all -Tjson > /dev/null

  (original)
  time: real 6.830 secs (user 6.740+0.000 sys 0.080+0.000)
  time: real 6.690 secs (user 6.650+0.000 sys 0.040+0.000)
  time: real 6.700 secs (user 6.640+0.000 sys 0.060+0.000)

  (fast jsonescape)
  time: real 5.630 secs (user 5.550+0.000 sys 0.070+0.000)
  time: real 5.700 secs (user 5.650+0.000 sys 0.050+0.000)
  time: real 5.690 secs (user 5.640+0.000 sys 0.050+0.000)

  (this patch)
  time: real 5.190 secs (user 5.120+0.000 sys 0.070+0.000)
  time: real 5.230 secs (user 5.170+0.000 sys 0.050+0.000)
  time: real 5.220 secs (user 5.150+0.000 sys 0.070+0.000)

#!/usr/bin/env python
# fixpax - fix ownership in bdist_mpkg output
#
# Copyright 2015 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# MIT license (http://opensource.org/licenses/MIT)

"""Set file ownership to 0 in an Archive.pax.gz.
Suitable for fixing files bdist_mpkg output:
*.mpkg/Contents/Packages/*.pkg/Contents/Archive.pax.gz
"""

from __future__ import absolute_import, print_function
import gzip
import os
import sys

def fixpax(iname, oname):
    i = gzip.GzipFile(iname)
    o = gzip.GzipFile(oname, "w")

    while True:
        magic = i.read(6)
        dev = i.read(6)
        ino = i.read(6)
        mode = i.read(6)
        i.read(6) # uid
        i.read(6) # gid
        nlink = i.read(6)
        rdev = i.read(6)
        mtime = i.read(11)
        namesize = i.read(6)
        filesize = i.read(11)
        name = i.read(int(namesize, 8))
        data = i.read(int(filesize, 8))

        o.write(magic)
        o.write(dev)
        o.write(ino)
        o.write(mode)
        o.write("000000")
        o.write("000000")
        o.write(nlink)
        o.write(rdev)
        o.write(mtime)
        o.write(namesize)
        o.write(filesize)
        o.write(name)
        o.write(data)

        if name.startswith("TRAILER!!!"):
            o.write(i.read())
            break

    o.close()
    i.close()

if __name__ == '__main__':
    for iname in sys.argv[1:]:
        print('fixing file ownership in %s' % iname)
        oname = sys.argv[1] + '.tmp'
        fixpax(iname, oname)
        os.rename(oname, iname)