view mercurial/exewrapper.c @ 25708:d3d32643c060

wireproto: correctly escape batched args and responses (issue4739)

This issue appears to be as old as wireproto batching itself: I can
reproduce the failure as far back as 08ef6b5f3715 trivially by
rebasing the test changes in this patch, which was back in the 1.9
era. I didn't test before that change, because prior to that the
testfile has a different name and I'm lazy.

Note that the test thought it was checking this case, but it actually
wasn't: it put a literal ; in the arg and response for its greet
command, but the mangle/unmangle step defined in the test meant that
instead of "Fo, =;o" going over the wire, "Gp-!><p" went instead,
which doesn't contain any special characters (those being [.=;]) and
thus not exercising the escaping. The test has been updated to use
pre-unmangled special characters, so the request is now "Fo+<:o",
which mangles to "Gp,=;p". I have confirmed that the test fails
without the adjustment to the escaping rules in wireproto.py.

No existing clients of RPC batching were depending on the old behavior
in any way. The only *actual* users of batchable RPCs in core were:

1) largefiles, wherein it batches up many statlfile calls. It sends
hexlified hashes over the wire and gets a 0, 1, or 2 back as a
response. No risk of special characters.

2) setdiscovery, which was using heads() and known(), both of which
communicate via hexlified nodes. Again, no risk of special characters.

Since the escaping functionality has been completely broken since it
was introduced, we know that it has no users. As such, we can change
the escaping mechanism without having to worry about backwards
compatibility issues.

For the curious, this was detected by chance: it happens that the
lz4-compressed text of a test file for remotefilelog compressed to
something containing a ;, which then caused the failure when I moved
remotefilelog to using batching for file content fetching.

/*
 exewrapper.c - wrapper for calling a python script on Windows

 Copyright 2012 Adrian Buehlmann <[e-mail]> and others

 This software may be used and distributed according to the terms of the
 GNU General Public License version 2 or any later version.
*/

#include <stdio.h>
#include <windows.h>

#include "hgpythonlib.h"

#ifdef __GNUC__
int strcat_s(char *d, size_t n, const char *s)
{
	return !strncat(d, s, n);
}
int strcpy_s(char *d, size_t n, const char *s)
{
	return !strncpy(d, s, n);
}
#endif


static char pyscript[MAX_PATH + 10];
static char pyhome[MAX_PATH + 10];
static char envpyhome[MAX_PATH + 10];
static char pydllfile[MAX_PATH + 10];

int main(int argc, char *argv[])
{
	char *p;
	int ret;
	int i;
	int n;
	char **pyargv;
	WIN32_FIND_DATA fdata;
	HANDLE hfind;
	const char *err;
	HMODULE pydll;
	void (__cdecl *Py_SetPythonHome)(char *home);
	int (__cdecl *Py_Main)(int argc, char *argv[]);

	if (GetModuleFileName(NULL, pyscript, sizeof(pyscript)) == 0)
	{
		err = "GetModuleFileName failed";
		goto bail;
	}

	p = strrchr(pyscript, '.');
	if (p == NULL) {
		err = "malformed module filename";
		goto bail;
	}
	*p = 0; /* cut trailing ".exe" */
	strcpy_s(pyhome, sizeof(pyhome), pyscript);

	hfind = FindFirstFile(pyscript, &fdata);
	if (hfind != INVALID_HANDLE_VALUE) {
		/* pyscript exists, close handle */
		FindClose(hfind);
	} else {
		/* file pyscript isn't there, take <pyscript>exe.py */
		strcat_s(pyscript, sizeof(pyscript), "exe.py");
	}

	pydll = NULL;
	if (GetEnvironmentVariable("PYTHONHOME", envpyhome,
				   sizeof(envpyhome)) == 0)
	{
		/* environment var PYTHONHOME is not set */

		p = strrchr(pyhome, '\\');
		if (p == NULL) {
			err = "can't find backslash in module filename";
			goto bail;
		}
		*p = 0; /* cut at directory */

		/* check for private Python of HackableMercurial */
		strcat_s(pyhome, sizeof(pyhome), "\\hg-python");

		hfind = FindFirstFile(pyhome, &fdata);
		if (hfind != INVALID_HANDLE_VALUE) {
			/* path pyhome exists, let's use it */
			FindClose(hfind);
			strcpy_s(pydllfile, sizeof(pydllfile), pyhome);
			strcat_s(pydllfile, sizeof(pydllfile), "\\" HGPYTHONLIB);
			pydll = LoadLibrary(pydllfile);
			if (pydll == NULL) {
				err = "failed to load private Python DLL";
				goto bail;
			}
			Py_SetPythonHome = (void*)GetProcAddress(pydll,
							"Py_SetPythonHome");
			if (Py_SetPythonHome == NULL) {
				err = "failed to get Py_SetPythonHome";
				goto bail;
			}
			Py_SetPythonHome(pyhome);
		}
	}

	if (pydll == NULL) {
		pydll = LoadLibrary(HGPYTHONLIB);
		if (pydll == NULL) {
			err = "failed to load Python DLL";
			goto bail;
		}
	}

	Py_Main = (void*)GetProcAddress(pydll, "Py_Main");
	if (Py_Main == NULL) {
		err = "failed to get Py_Main";
		goto bail;
	}

	/*
	Only add the pyscript to the args, if it's not already there. It may
	already be there, if the script spawned a child process of itself, in
	the same way as it got called, that is, with the pyscript already in
	place. So we optionally accept the pyscript as the first argument
	(argv[1]), letting our exe taking the role of the python interpreter.
	*/
	if (argc >= 2 && strcmp(argv[1], pyscript) == 0) {
		/*
		pyscript is already in the args, so there is no need to copy
		the args and we can directly call the python interpreter with
		the original args.
		*/
		return Py_Main(argc, argv);
	}

	/*
	Start assembling the args for the Python interpreter call. We put the
	name of our exe (argv[0]) in the position where the python.exe
	canonically is, and insert the pyscript next.
	*/
	pyargv = malloc((argc + 5) * sizeof(char*));
	if (pyargv == NULL) {
		err = "not enough memory";
		goto bail;
	}
	n = 0;
	pyargv[n++] = argv[0];
	pyargv[n++] = pyscript;

	/* copy remaining args from the command line */
	for (i = 1; i < argc; i++)
		pyargv[n++] = argv[i];
	/* argv[argc] is guaranteed to be NULL, so we forward that guarantee */
	pyargv[n] = NULL;

	ret = Py_Main(n, pyargv); /* The Python interpreter call */

	free(pyargv);
	return ret;

bail:
	fprintf(stderr, "abort: %s\n", err);
	return 255;
}