[PATCH 1 of 5 import-refactor] hg: implement import hook for handling C/Python modules

[Gregory Szorc]

# HG changeset patch
# User Gregory Szorc <gregory.szorc at gmail.com>
# Date 1442115288 25200
#      Sat Sep 12 20:34:48 2015 -0700
# Node ID 3d32b988b6d49f95d507e456b3e627f27e816ba8
# Parent  df9b73d2d444ae82fe8d3fe6cf682a93b2c4a7ef
hg: implement import hook for handling C/Python modules

There are a handful of modules that have both pure Python and C
extension implementations. Currently, setup.py copies files from
mercurial/pure/*.py to mercurial/ during the install process if C
extensions are not available. This way, "import mercurial.X" will
work whether C extensions are available or not.

This approach has a few drawbacks. First, there aren't run-time checks
verifying the C extensions are loaded when they should be. This could
lead to accidental use of the slower pure Python modules. Second, the
C extensions aren't compatible with PyPy and running Mercurial with
PyPy requires installing Mercurial - you can't run ./hg from a source
checkout. This makes developing while running PyPy somewhat difficult.

This patch implements a PEP-302 import hook for finding and loading the
modules with both C and Python implementations. When a module with dual
implementations is requested for import, its import is handled by our
import hook.

This patch should be backwards compatible: we are merely reimplementing
what Python does behind the scenes when an import occurs.

Future patches will add functionality to the import hook to plug some
of the aforementioned deficiencies with the import mechanism.

diff --git a/hg b/hg
--- a/hg
+++ b/hg
@@ -2,16 +2,17 @@
 #
 # mercurial - scalable distributed SCM
 #
 # Copyright 2005-2007 Matt Mackall <mpm at selenic.com>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
+import imp
 import os
 import sys
 
 if os.environ.get('HGUNICODEPEDANTRY', False):
     reload(sys)
     sys.setdefaultencoding("undefined")
 
 
@@ -29,15 +30,59 @@ try:
     from mercurial import demandimport; demandimport.enable()
 except ImportError:
     import sys
     sys.stderr.write("abort: couldn't find mercurial libraries in [%s]\n" %
                      ' '.join(sys.path))
     sys.stderr.write("(check your install and PYTHONPATH)\n")
     sys.exit(-1)
 
+# Install a PEP-302 custom module finder and loader that knows how to
+# import modules with implementations in both Python and C.
+
+# List of modules that have both Python and C implementations. See also the
+# set of .py files under mercurial/pure/.
+dualmodules = set([
+    'mercurial.base85',
+    'mercurial.bdiff',
+    'mercurial.diffhelpers',
+    'mercurial.mpatch',
+    'mercurial.osutil',
+    'mercurial.parsers',
+])
+
+import mercurial
+
+class hgimporter(object):
+    def find_module(self, name, path=None):
+        # We only care about modules that have both C and pure implementations.
+        if name in dualmodules:
+            return self
+        return None
+
+    def load_module(self, name):
+        mod = sys.modules.get(name, None)
+        if mod:
+            return mod
+
+        # imp.find_module doesn't support submodules (modules with ".").
+        # Instead you have to pass the parent package's __path__ attribute
+        # as the path argument.
+        stem = name.split('.')[-1]
+
+        # C extensions are available under mercurial.*.
+        # Pure Python available under mercurial.* if they are installed there
+        # or mercurial.pure.* if they aren't installed.
+        modinfo = imp.find_module(stem, mercurial.__path__)
+
+        mod = imp.load_module(name, *modinfo)
+        sys.modules[name] = mod
+        return mod
+
+sys.meta_path.insert(0, hgimporter())
+
 import mercurial.util
 import mercurial.dispatch
 
 for fp in (sys.stdin, sys.stdout, sys.stderr):
     mercurial.util.setbinary(fp)
 
 mercurial.dispatch.run()