tests/test-demandimport.py

bundle2: implement consume() API on unbundlepart

We want bundle parts to not be seekable by default. That means
eliminating the generic seek() method.

A common pattern in bundle2.py is to seek to the end of the part
data. This is mainly used by the part iteration code to ensure
the underlying stream is advanced to the next bundle part.

In this commit, we establish a dedicated API for consuming a
bundle2 part data. We switch users of seek() to it.

The old implementation of seek(0, os.SEEK_END) would effectively
call self.read(). The new implementation calls self.read(32768)
in a loop. The old implementation would therefore assemble a
buffer to hold all remaining data being seeked over. For seeking
over large bundle parts, this would involve a large allocation and
a lot of overhead to collect intermediate data! This overhead can
be seen in the results for `hg perfbundleread`:

! bundle2 iterparts()
! wall 10.891305 comb 10.820000 user 7.990000 sys 2.830000 (best of 3)
! wall 8.070791 comb 8.060000 user 7.180000 sys 0.880000 (best of 3)
! bundle2 part seek()
! wall 12.991478 comb 10.390000 user 7.720000 sys 2.670000 (best of 3)
! wall 10.370142 comb 10.350000 user 7.430000 sys 2.920000 (best of 3)

Of course, skipping over large payload data isn't likely very common.
So I doubt the performance wins will be observed in the wild.

Differential Revision: https://phab.mercurial-scm.org/D1388

from __future__ import absolute_import, print_function

from mercurial import demandimport
demandimport.enable()

import os
import subprocess
import sys

# Only run if demandimport is allowed
if subprocess.call(['python', '%s/hghave' % os.environ['TESTDIR'],
                    'demandimport']):
    sys.exit(80)

if os.name != 'nt':
    try:
        import distutils.msvc9compiler
        print('distutils.msvc9compiler needs to be an immediate '
              'importerror on non-windows platforms')
        distutils.msvc9compiler
    except ImportError:
        pass

import re

rsub = re.sub
def f(obj):
    l = repr(obj)
    l = rsub("0x[0-9a-fA-F]+", "0x?", l)
    l = rsub("from '.*'", "from '?'", l)
    l = rsub("'<[a-z]*>'", "'<whatever>'", l)
    return l

import os

print("os =", f(os))
print("os.system =", f(os.system))
print("os =", f(os))

from mercurial import util

print("util =", f(util))
print("util.system =", f(util.system))
print("util =", f(util))
print("util.system =", f(util.system))

from mercurial import hgweb
print("hgweb =", f(hgweb))
print("hgweb_mod =", f(hgweb.hgweb_mod))
print("hgweb =", f(hgweb))

import re as fred
print("fred =", f(fred))

import re as remod
print("remod =", f(remod))

import sys as re
print("re =", f(re))

print("fred =", f(fred))
print("fred.sub =", f(fred.sub))
print("fred =", f(fred))

remod.escape  # use remod
print("remod =", f(remod))

print("re =", f(re))
print("re.stderr =", f(re.stderr))
print("re =", f(re))

# Test access to special attributes through demandmod proxy
from mercurial import pvec as pvecproxy
print("pvecproxy =", f(pvecproxy))
print("pvecproxy.__doc__ = %r"
      % (' '.join(pvecproxy.__doc__.split()[:3]) + ' ...'))
print("pvecproxy.__name__ = %r" % pvecproxy.__name__)
# __name__ must be accessible via __dict__ so the relative imports can be
# resolved
print("pvecproxy.__dict__['__name__'] = %r" % pvecproxy.__dict__['__name__'])
print("pvecproxy =", f(pvecproxy))

import contextlib
print("contextlib =", f(contextlib))
try:
    from contextlib import unknownattr
    print('no demandmod should be created for attribute of non-package '
          'module:\ncontextlib.unknownattr =', f(unknownattr))
except ImportError as inst:
    print('contextlib.unknownattr = ImportError: %s'
          % rsub(r"'", '', str(inst)))

# Unlike the import statement, __import__() function should not raise
# ImportError even if fromlist has an unknown item
# (see Python/import.c:import_module_level() and ensure_fromlist())
contextlibimp = __import__('contextlib', globals(), locals(), ['unknownattr'])
print("__import__('contextlib', ..., ['unknownattr']) =", f(contextlibimp))
print("hasattr(contextlibimp, 'unknownattr') =",
      util.safehasattr(contextlibimp, 'unknownattr'))

demandimport.disable()
os.environ['HGDEMANDIMPORT'] = 'disable'
# this enable call should not actually enable demandimport!
demandimport.enable()
from mercurial import node
print("node =", f(node))