mercurial/demandimport.py

util._matcher: speed up regexp matching.

In 4babaa52badf, Benoit made a change that substantially slows matching
when a big .hgignore file is in play, because it calls into the regexp
matching engine potentially hundreds of times per file to be matched.

I've partly rolled back his change, so that we only call into the matcher
once per file, but preserved the ability to report a meaningful error
message if there's a syntax error in the regexp.

# demandimport.py - global demand-loading of modules for Mercurial
#
# Copyright 2006 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms
# of the GNU General Public License, incorporated herein by reference.

'''
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)
'''

_origimport = __import__

class _demandmod(object):
    """module demand-loader and proxy"""
    def __init__(self, name, globals, locals):
        if '.' in name:
            head, rest = name.split('.', 1)
            after = [rest]
        else:
            head = name
            after = []
        object.__setattr__(self, "_data", (head, globals, locals, after))
        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 = self._data
            mod = _origimport(head, globals, locals)
            # load submodules
            def subload(mod, p):
                h, t = p, None
                if '.' in p:
                    h, t = p.split('.', 1)
                if not hasattr(mod, h):
                    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):
        return "<unloaded module '%s'>" % self._data[0]
    def __call__(self, *args, **kwargs):
        raise TypeError("'unloaded module' object is not callable")
    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):
    if not locals or name in ignore or fromlist == ('*',):
        # these cases we can't really delay
        return _origimport(name, globals, locals, fromlist)
    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 _origimport(name, globals, locals, fromlist)
            # 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)
    else:
        # from a import b,c,d
        mod = _origimport(name, globals, locals)
        # recurse down the module chain
        for comp in name.split('.')[1:]:
            mod = getattr(mod, comp)
        for x in fromlist:
            # set requested submodules for demand load
            if not(hasattr(mod, x)):
                setattr(mod, x, _demandmod(x, mod.__dict__, mod.__dict__))
        return mod

ignore = ['_hashlib', '_xmlplus', 'fcntl', 'win32com.gen_py']

def enable():
    "enable global demand-loading of modules"
    __builtins__["__import__"] = _demandimport

def disable():
    "disable global demand-loading of modules"
    __builtins__["__import__"] = _origimport