view tests/check-perf-code.py @ 40053:8c692a6b5ad1

fuzz: new fuzzer for cext/manifest.c

This is a bit messy, because lazymanifest is tightly coupled to the
cpython API for performance reasons. As a result, we have to build a
whole Python without pymalloc (so ASAN can help us out) and link
against that. Then we have to use an embedded Python interpreter. We
could manually drive the lazymanifest in C from that point, but
experimentally just using PyEval_EvalCode isn't really any slower so
we may as well do that and write the innermost guts of the fuzzer in
Python.

Leak detection is currently disabled for this fuzzer because there are
a few global-lifetime things in our extensions that we more or less
intentionally leak and I didn't want to take the detour to work around
that for now.

This should not be pushed to our repo until
https://github.com/google/oss-fuzz/pull/1853 is merged, as this
depends on having the Python tarball around.

Differential Revision: https://phab.mercurial-scm.org/D4879

#!/usr/bin/env python
#
# check-perf-code - (historical) portability checker for contrib/perf.py

from __future__ import absolute_import

import os
import sys

# write static check patterns here
perfpypats = [
  [
    (r'(branchmap|repoview)\.subsettable',
     "use getbranchmapsubsettable() for early Mercurial"),
    (r'\.(vfs|svfs|opener|sopener)',
     "use getvfs()/getsvfs() for early Mercurial"),
    (r'ui\.configint',
     "use getint() instead of ui.configint() for early Mercurial"),
  ],
  # warnings
  [
  ]
]

def modulewhitelist(names):
    replacement = [('.py', ''), ('.c', ''), # trim suffix
                   ('mercurial%s' % (os.sep), ''), # trim "mercurial/" path
                  ]
    ignored = {'__init__'}
    modules = {}

    # convert from file name to module name, and count # of appearances
    for name in names:
        name = name.strip()
        for old, new in replacement:
            name = name.replace(old, new)
        if name not in ignored:
            modules[name] = modules.get(name, 0) + 1

    # list up module names, which appear multiple times
    whitelist = []
    for name, count in modules.items():
        if count > 1:
            whitelist.append(name)

    return whitelist

if __name__ == "__main__":
    # in this case, it is assumed that result of "hg files" at
    # multiple revisions is given via stdin
    whitelist = modulewhitelist(sys.stdin)
    assert whitelist, "module whitelist is empty"

    # build up module whitelist check from file names given at runtime
    perfpypats[0].append(
        # this matching pattern assumes importing modules from
        # "mercurial" package in the current style below, for simplicity
        #
        #    from mercurial import (
        #        foo,
        #        bar,
        #        baz
        #    )
        ((r'from mercurial import [(][a-z0-9, \n#]*\n(?! *%s,|^[ #]*\n|[)])'
          % ',| *'.join(whitelist)),
         "import newer module separately in try clause for early Mercurial"
         ))

    # import contrib/check-code.py as checkcode
    assert 'RUNTESTDIR' in os.environ, "use check-perf-code.py in *.t script"
    contribpath = os.path.join(os.environ['RUNTESTDIR'], '..', 'contrib')
    sys.path.insert(0, contribpath)
    checkcode = __import__('check-code')

    # register perf.py specific entry with "checks" in check-code.py
    checkcode.checks.append(('perf.py', r'contrib/perf.py$', '',
                             checkcode.pyfilters, perfpypats))

    sys.exit(checkcode.main())