tests/test-issue4074.t

wrapfunction: use functools.partial if possible

Every `extensions.bind` call inserts a frame in traceback:

   ... in closure
     return func(*(args + a), **kw)

which makes traceback noisy.

The Python stdlib has a `functools.partial` which is backed by C code and
does not pollute traceback. However it does not support instancemethod and
sets `args` attribute which could be problematic for alias handling.

This patch makes `wrapfunction` use `functools.partial` if we are wrapping a
function directly exported by a module (so it's impossible to be a class or
instance method), and special handles `wrapfunction` results so alias
handling code could handle `args` just fine.

As an example, `hg rebase -s . -d . --traceback` got 6 lines removed in my
setup:

   File "hg/mercurial/dispatch.py", line 898, in _dispatch
     cmdpats, cmdoptions)
  -File "hg/mercurial/extensions.py", line 333, in closure
  -  return func(*(args + a), **kw)
   File "hg/hgext/journal.py", line 84, in runcommand
     return orig(lui, repo, cmd, fullargs, *args)
  -File "hg/mercurial/extensions.py", line 333, in closure
  -  return func(*(args + a), **kw)
   File "fb-hgext/hgext3rd/fbamend/hiddenoverride.py", line 119, in runcommand
     result = orig(lui, repo, cmd, fullargs, *args)
   File "hg/mercurial/dispatch.py", line 660, in runcommand
     ret = _runcommand(ui, options, cmd, d)
  -File "hg/mercurial/extensions.py", line 333, in closure
  -  return func(*(args + a), **kw)
   File "hg/hgext/pager.py", line 69, in pagecmd
     return orig(ui, options, cmd, cmdfunc)
   ....

Differential Revision: https://phab.mercurial-scm.org/D632

#require no-pure

A script to generate nasty diff worst-case scenarios:

  $ cat > s.py <<EOF
  > import random
  > for x in xrange(100000):
  >     print
  >     if random.randint(0, 100) >= 50:
  >         x += 1
  >     print(hex(x))
  > EOF

  $ hg init a
  $ cd a

Check in a big file:

  $ $PYTHON ../s.py > a
  $ hg ci -qAm0

Modify it:

  $ $PYTHON ../s.py > a

Time a check-in, should never take more than 10 seconds user time:

  $ hg ci --time -m1
  time: real .* secs .user [0-9][.].* sys .* (re)