view mercurial/cffi/osutilbuild.py @ 35616:706aa203b396

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

from __future__ import absolute_import

import cffi

ffi = cffi.FFI()
ffi.set_source("mercurial.cffi._osutil", """
#include <sys/attr.h>
#include <sys/vnode.h>
#include <unistd.h>
#include <fcntl.h>
#include <time.h>

typedef struct val_attrs {
    uint32_t          length;
    attribute_set_t   returned;
    attrreference_t   name_info;
    fsobj_type_t      obj_type;
    struct timespec   mtime;
    uint32_t          accessmask;
    off_t             datalength;
} __attribute__((aligned(4), packed)) val_attrs_t;
""", include_dirs=['mercurial'])
ffi.cdef('''

typedef uint32_t attrgroup_t;

typedef struct attrlist {
    uint16_t     bitmapcount; /* number of attr. bit sets in list */
    uint16_t   reserved;    /* (to maintain 4-byte alignment) */
    attrgroup_t commonattr;  /* common attribute group */
    attrgroup_t volattr;     /* volume attribute group */
    attrgroup_t dirattr;     /* directory attribute group */
    attrgroup_t fileattr;    /* file attribute group */
    attrgroup_t forkattr;    /* fork attribute group */
    ...;
};

typedef struct attribute_set {
    ...;
} attribute_set_t;

typedef struct attrreference {
    int attr_dataoffset;
    int attr_length;
    ...;
} attrreference_t;

typedef int ... off_t;

typedef struct val_attrs {
    uint32_t          length;
    attribute_set_t   returned;
    attrreference_t   name_info;
    uint32_t          obj_type;
    struct timespec   mtime;
    uint32_t          accessmask;
    off_t             datalength;
    ...;
} val_attrs_t;

/* the exact layout of the above struct will be figured out during build time */

typedef int ... time_t;

typedef struct timespec {
    time_t tv_sec;
    ...;
};

int getattrlist(const char* path, struct attrlist * attrList, void * attrBuf,
                size_t attrBufSize, unsigned int options);

int getattrlistbulk(int dirfd, struct attrlist * attrList, void * attrBuf,
                    size_t attrBufSize, uint64_t options);

#define ATTR_BIT_MAP_COUNT ...
#define ATTR_CMN_NAME ...
#define ATTR_CMN_OBJTYPE ...
#define ATTR_CMN_MODTIME ...
#define ATTR_CMN_ACCESSMASK ...
#define ATTR_CMN_ERROR ...
#define ATTR_CMN_RETURNED_ATTRS ...
#define ATTR_FILE_DATALENGTH ...

#define VREG ...
#define VDIR ...
#define VLNK ...
#define VBLK ...
#define VCHR ...
#define VFIFO ...
#define VSOCK ...

#define S_IFMT ...

int open(const char *path, int oflag, int perm);
int close(int);

#define O_RDONLY ...
''')

if __name__ == '__main__':
    ffi.compile()