view mercurial/demandimport.py @ 25561:50a6c3c55db1 stable

parsers: do not cache RevlogError type (issue4451)

Index lookups raise RevlogError when the lookup fails. The previous
implementation was caching a reference to the RevlogError type in a
static variable. This assumed that the "mercurial.error" module was
only loaded once and there was only a single copy of it floating
around in memory. Unfortunately, in some situations - including
certain mod_wsgi configurations - this was not the case: the
"mercurial.error" module could be reloaded. It was possible for a
"RevlogError" reference from the first interpreter to be used by
a second interpreter. While the underlying thing was a
"mercurial.error.RevlogError," the object IDs were different, so
the Python code in revlog.py was failing to catch the exception! This
error has existed since the C index lookup code was implemented in
changeset e8d37b78acfb, which was first released in Mercurial 2.2 in
2012.
http://emptysqua.re/blog/python-c-extensions-and-mod-wsgi/#static-variables-are-shared
contains more details.

This patch removes the caching of the RevlogError type from the
function.

Since pretty much the entire function was refactored and the return
value of the function wasn't used, I changed the function signature
to not return anything.

For reasons unknown to me, we were calling PyErr_SetObject()
with the type of RevlogError and an instance of RevlogError. This
was equivalent to the Python code "raise RevlogError(RevlogError)".
This seemed wonky and completely unnecessary. The Python code only
cares about the type of the exception, not its contents. So I got
rid of this complexity.

This is my first Python C extension patch. Please give extra scrutiny
to it during review.

# demandimport.py - global demand-loading of modules for Mercurial
#
# Copyright 2006, 2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

'''
demandimport - automatic demandloading of modules

To enable this module, do:

  import demandimport; demandimport.enable()

Imports of the following forms will be demand-loaded:

  import a, b.c
  import a.b as c
  from a import b,c # a will be loaded immediately

These imports will not be delayed:

  from a import *
  b = __import__(a)
'''

import __builtin__, os, sys
_origimport = __import__

nothing = object()

try:
    # Python 3 doesn't have relative imports nor level -1.
    level = -1
    if sys.version_info[0] >= 3:
        level = 0
    _origimport(__builtin__.__name__, {}, {}, None, level)
except TypeError: # no level argument
    def _import(name, globals, locals, fromlist, level):
        "call _origimport with no level argument"
        return _origimport(name, globals, locals, fromlist)
else:
    _import = _origimport

def _hgextimport(importfunc, name, globals, *args):
    try:
        return importfunc(name, globals, *args)
    except ImportError:
        if not globals:
            raise
        # extensions are loaded with "hgext_" prefix
        hgextname = 'hgext_%s' % name
        nameroot = hgextname.split('.', 1)[0]
        contextroot = globals.get('__name__', '').split('.', 1)[0]
        if nameroot != contextroot:
            raise
        # retry to import with "hgext_" prefix
        return importfunc(hgextname, globals, *args)

class _demandmod(object):
    """module demand-loader and proxy"""
    def __init__(self, name, globals, locals, level=level):
        if '.' in name:
            head, rest = name.split('.', 1)
            after = [rest]
        else:
            head = name
            after = []
        object.__setattr__(self, "_data",
                           (head, globals, locals, after, level))
        object.__setattr__(self, "_module", None)
    def _extend(self, name):
        """add to the list of submodules to load"""
        self._data[3].append(name)
    def _load(self):
        if not self._module:
            head, globals, locals, after, level = self._data
            mod = _hgextimport(_import, head, globals, locals, None, level)
            # load submodules
            def subload(mod, p):
                h, t = p, None
                if '.' in p:
                    h, t = p.split('.', 1)
                if getattr(mod, h, nothing) is nothing:
                    setattr(mod, h, _demandmod(p, mod.__dict__, mod.__dict__))
                elif t:
                    subload(getattr(mod, h), t)

            for x in after:
                subload(mod, x)

            # are we in the locals dictionary still?
            if locals and locals.get(head) == self:
                locals[head] = mod
            object.__setattr__(self, "_module", mod)

    def __repr__(self):
        if self._module:
            return "<proxied module '%s'>" % self._data[0]
        return "<unloaded module '%s'>" % self._data[0]
    def __call__(self, *args, **kwargs):
        raise TypeError("%s object is not callable" % repr(self))
    def __getattribute__(self, attr):
        if attr in ('_data', '_extend', '_load', '_module'):
            return object.__getattribute__(self, attr)
        self._load()
        return getattr(self._module, attr)
    def __setattr__(self, attr, val):
        self._load()
        setattr(self._module, attr, val)

def _demandimport(name, globals=None, locals=None, fromlist=None, level=level):
    if not locals or name in ignore or fromlist == ('*',):
        # these cases we can't really delay
        return _hgextimport(_import, name, globals, locals, fromlist, level)
    elif not fromlist:
        # import a [as b]
        if '.' in name: # a.b
            base, rest = name.split('.', 1)
            # email.__init__ loading email.mime
            if globals and globals.get('__name__', None) == base:
                return _import(name, globals, locals, fromlist, level)
            # if a is already demand-loaded, add b to its submodule list
            if base in locals:
                if isinstance(locals[base], _demandmod):
                    locals[base]._extend(rest)
                return locals[base]
        return _demandmod(name, globals, locals, level)
    else:
        if level != -1:
            # from . import b,c,d or from .a import b,c,d
            return _origimport(name, globals, locals, fromlist, level)
        # from a import b,c,d
        mod = _hgextimport(_origimport, name, globals, locals)
        # recurse down the module chain
        for comp in name.split('.')[1:]:
            if getattr(mod, comp, nothing) is nothing:
                setattr(mod, comp, _demandmod(comp, mod.__dict__, mod.__dict__))
            mod = getattr(mod, comp)
        for x in fromlist:
            # set requested submodules for demand load
            if getattr(mod, x, nothing) is nothing:
                setattr(mod, x, _demandmod(x, mod.__dict__, locals))
        return mod

ignore = [
    '_hashlib',
    '_xmlplus',
    'fcntl',
    'win32com.gen_py',
    '_winreg', # 2.7 mimetypes needs immediate ImportError
    'pythoncom',
    # imported by tarfile, not available under Windows
    'pwd',
    'grp',
    # imported by profile, itself imported by hotshot.stats,
    # not available under Windows
    'resource',
    # this trips up many extension authors
    'gtk',
    # setuptools' pkg_resources.py expects "from __main__ import x" to
    # raise ImportError if x not defined
    '__main__',
    '_ssl', # conditional imports in the stdlib, issue1964
    'rfc822',
    'mimetools',
    # setuptools 8 expects this module to explode early when not on windows
    'distutils.msvc9compiler'
    ]

def isenabled():
    return __builtin__.__import__ == _demandimport

def enable():
    "enable global demand-loading of modules"
    if os.environ.get('HGDEMANDIMPORT') != 'disable':
        __builtin__.__import__ = _demandimport

def disable():
    "disable global demand-loading of modules"
    __builtin__.__import__ = _origimport