contrib/fuzz/pyutil.cc
author C. Masloch <pushbx@ulukai.org>
Wed, 20 Apr 2022 19:24:39 +0200
changeset 49449 cfff73cab721
parent 44961 ee5f27d7b9fb
permissions -rw-r--r--
rebase: add boolean config item rebase.store-source This allows to use rebase without recording a rebase_source extra field. This is useful for example to build a mirror converted from another SCM (such as svn) by converting only new revisions, and then incrementally add them to the destination by pulling from the newly converted (unrelated) repo and rebasing the new revisions onto the last old already stored changeset. Without this patch the rebased changesets would always receive some rebase_source that would depend on the particular history of the conversion process, instead of only depending on the original source revisions. This is used to implement a hg mirror repo of SvarDOS (a partially nonfree but completely redistributable DOS distribution) in the scripts at https://hg.pushbx.org/ecm/svardos.scr/ In particular, cre.sh creates an svn mirror, upd.sh recreates an entire hg repo from the svn mirror (which takes too long to do in a regular job), and akt.sh uses hg convert with the config item convert.svn.startrev to incrementally convert only the two most recent revisions already found in the mirror destination plus any possible new revisions. If any are found, the temporary repo's changesets are pulled into the destination (as changesets from an unrelated repository). Then the changesets corresponding to the new revisions are rebased onto the prior final changeset. (Finally, the two remaining duplicates of the prior head and its parent are stripped from the destination repository.) Without this patch, the particular rebase_source extra field would depend on the order and times at which akt.sh was used, instead of only depending on the source repository. In other words, whatever sequence of upd.sh and akt.sh is used at whatever times, it is desired that the final output repositories always match each other exactly.

#include "pyutil.h"

#include <iostream>
#include <string>

namespace contrib
{

#if PY_MAJOR_VERSION >= 3
#define HG_FUZZER_PY3 1
PyMODINIT_FUNC PyInit_parsers(void);
#else
PyMODINIT_FUNC initparsers(void);
#endif

static char cpypath[8192] = "\0";

static PyObject *mainmod;
static PyObject *globals;

void initpy(const char *cselfpath)
{
#ifdef HG_FUZZER_PY3
	const std::string subdir = "/sanpy/lib/python3.8";
#else
	const std::string subdir = "/sanpy/lib/python2.7";
#endif

	/* HACK ALERT: we need a full Python installation built without
	   pymalloc and with ASAN, so we dump one in
	   $OUT/sanpy/lib/python2.7. This helps us wire that up. */
	std::string selfpath(cselfpath);
	std::string pypath;
	auto pos = selfpath.rfind("/");
	if (pos == std::string::npos) {
		char wd[8192];
		if (!getcwd(wd, 8192)) {
			std::cerr << "Failed to call getcwd: errno " << errno
			          << std::endl;
			exit(1);
		}
		pypath = std::string(wd) + subdir;
	} else {
		pypath = selfpath.substr(0, pos) + subdir;
	}
	strncpy(cpypath, pypath.c_str(), pypath.size());
	setenv("PYTHONPATH", cpypath, 1);
	setenv("PYTHONNOUSERSITE", "1", 1);
	/* prevent Python from looking up users in the fuzz environment */
	setenv("PYTHONUSERBASE", cpypath, 1);
#ifdef HG_FUZZER_PY3
	std::wstring wcpypath(pypath.begin(), pypath.end());
	Py_SetPythonHome(wcpypath.c_str());
#else
	Py_SetPythonHome(cpypath);
#endif
	Py_InitializeEx(0);
	mainmod = PyImport_AddModule("__main__");
	globals = PyModule_GetDict(mainmod);

#ifdef HG_FUZZER_PY3
	PyObject *mod = PyInit_parsers();
#else
	initparsers();
	PyObject *mod = PyImport_ImportModule("parsers");
#endif

	PyDict_SetItemString(globals, "parsers", mod);
}

PyObject *pyglobals()
{
	return globals;
}

} // namespace contrib