view mercurial/exewrapper.c @ 29322:66dbdd3cc2b9 stable

bdiff: extend matches across popular lines

For very large diffs that have large numbers of identical lines (JSON
dumps) that also have large blocks of identical text, bdiff could become
confused about which block matches which because it can only match
very limited regions. The result is very large diffs for small sets of edits.

The earlier recursion rebalancing fix made this behavior more frequent because
it's now more prone to match block 1 to block 2. One frequent user of
large JSON files reported being unable to pass the resulting diffs
through their code review system.

Prior to this change, bdiff would calculate the length of a match at
(i, j) as 1 + length found at (i-1, j-1). With large number of popular
(ignored) lines, this often meant matches couldn't be extended
backwards at all and thus all matching regions were very small.
Disabling the popularity threshold is not an option because it brings
back quadratic behavior.

Instead, we extend a match backwards until we either found a previously
discovered match or we find a mismatching line. This thus successfully
bridges over any popular lines inside and before a matching region.
The larger regions then significant reduce the probability of confusion.

/*
 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;
	/*
	We first check, that environment variable PYTHONHOME is *not* set.
	This just mimicks the behavior of the regular python.exe, which uses
	PYTHONHOME to find its installation directory (if it has been set).
	Note: Users of HackableMercurial are expected to *not* set PYTHONHOME!
	*/
	if (GetEnvironmentVariable("PYTHONHOME", envpyhome,
				   sizeof(envpyhome)) == 0)
	{
		/*
		Environment var PYTHONHOME is *not* set. Let's see if we are
		running inside a HackableMercurial.
		*/

		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 ".dll");
			pydll = LoadLibrary(pydllfile);
			if (pydll == NULL) {
				err = "failed to load private Python DLL "
				      HGPYTHONLIB ".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 ".dll");
		if (pydll == NULL) {
			err = "failed to load Python DLL " HGPYTHONLIB ".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;
}