view mercurial/cffi/osutil.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

# osutil.py - CFFI version of osutil.c
#
# Copyright 2016 Maciej Fijalkowski <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os
import stat as statmod

from ..pure.osutil import *

from .. import (
    pycompat,
)

if pycompat.isdarwin:
    from . import _osutil

    ffi = _osutil.ffi
    lib = _osutil.lib

    listdir_batch_size = 4096
    # tweakable number, only affects performance, which chunks
    # of bytes do we get back from getattrlistbulk

    attrkinds = [None] * 20 # we need the max no for enum VXXX, 20 is plenty

    attrkinds[lib.VREG] = statmod.S_IFREG
    attrkinds[lib.VDIR] = statmod.S_IFDIR
    attrkinds[lib.VLNK] = statmod.S_IFLNK
    attrkinds[lib.VBLK] = statmod.S_IFBLK
    attrkinds[lib.VCHR] = statmod.S_IFCHR
    attrkinds[lib.VFIFO] = statmod.S_IFIFO
    attrkinds[lib.VSOCK] = statmod.S_IFSOCK

    class stat_res(object):
        def __init__(self, st_mode, st_mtime, st_size):
            self.st_mode = st_mode
            self.st_mtime = st_mtime
            self.st_size = st_size

    tv_sec_ofs = ffi.offsetof("struct timespec", "tv_sec")
    buf = ffi.new("char[]", listdir_batch_size)

    def listdirinternal(dfd, req, stat, skip):
        ret = []
        while True:
            r = lib.getattrlistbulk(dfd, req, buf, listdir_batch_size, 0)
            if r == 0:
                break
            if r == -1:
                raise OSError(ffi.errno, os.strerror(ffi.errno))
            cur = ffi.cast("val_attrs_t*", buf)
            for i in range(r):
                lgt = cur.length
                assert lgt == ffi.cast('uint32_t*', cur)[0]
                ofs = cur.name_info.attr_dataoffset
                str_lgt = cur.name_info.attr_length
                base_ofs = ffi.offsetof('val_attrs_t', 'name_info')
                name = str(ffi.buffer(ffi.cast("char*", cur) + base_ofs + ofs,
                           str_lgt - 1))
                tp = attrkinds[cur.obj_type]
                if name == "." or name == "..":
                    continue
                if skip == name and tp == statmod.S_ISDIR:
                    return []
                if stat:
                    mtime = cur.mtime.tv_sec
                    mode = (cur.accessmask & ~lib.S_IFMT)| tp
                    ret.append((name, tp, stat_res(st_mode=mode, st_mtime=mtime,
                                st_size=cur.datalength)))
                else:
                    ret.append((name, tp))
                cur = ffi.cast("val_attrs_t*", int(ffi.cast("intptr_t", cur))
                    + lgt)
        return ret

    def listdir(path, stat=False, skip=None):
        req = ffi.new("struct attrlist*")
        req.bitmapcount = lib.ATTR_BIT_MAP_COUNT
        req.commonattr = (lib.ATTR_CMN_RETURNED_ATTRS |
                          lib.ATTR_CMN_NAME |
                          lib.ATTR_CMN_OBJTYPE |
                          lib.ATTR_CMN_ACCESSMASK |
                          lib.ATTR_CMN_MODTIME)
        req.fileattr = lib.ATTR_FILE_DATALENGTH
        dfd = lib.open(path, lib.O_RDONLY, 0)
        if dfd == -1:
            raise OSError(ffi.errno, os.strerror(ffi.errno))

        try:
            ret = listdirinternal(dfd, req, stat, skip)
        finally:
            try:
                lib.close(dfd)
            except BaseException:
                pass # we ignore all the errors from closing, not
                # much we can do about that
        return ret