fileset: add a lightweight file filtering language
This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1]. We want a way to specify what
files will be converted to LFS at commit time. And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs. I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.
Yuya suggested farming out to fileset.parse(), which added support for more
symbols. The only fileset element not supported here is 'negate'. (List isn't
supported by filesets either.) I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config. The extension operator was changed from '.'
to '**', to match how recursive path globs are specified. Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher. Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2]. We should
probably revisit that, because it's seriously ugly. But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.
I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.
Sample filter settings:
all() # everything
size(">20MB") # larger than 20MB
!**.txt # except for .txt files
**.zip | **.tar.gz | **.7z # some types of compressed files
"path:bin" # files under "bin" in the project root
[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html
/*
exewrapper.c - wrapper for calling a python script on Windows
Copyright 2012 Adrian Buehlmann <adrian@cadifra.com> 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;
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 .\hg-python exists. We are probably in HackableMercurial
scenario, so let's load python dll from this dir. */
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;
}