view mercurial/minifileset.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload The search itself can take an extreme amount of time if there are a lot of revisions involved. I've got a local repo that took 6 minutes to push 1850 commits, and 60% of that time was spent here (there are ~70K files): \ 58.1% wrapper.py: extractpointers line 297: pointers = extractpointers(... | 57.7% wrapper.py: pointersfromctx line 352: for p in pointersfromctx(ct... | 57.4% wrapper.py: pointerfromctx line 397: p = pointerfromctx(ctx, f, ... \ 38.7% context.py: __contains__ line 368: if f not in ctx: | 38.7% util.py: __get__ line 82: return key in self._manifest | 38.7% context.py: _manifest line 1416: result = self.func(obj) | 38.7% manifest.py: read line 472: return self._manifestctx.re... \ 25.6% revlog.py: revision line 1562: text = rl.revision(self._node) \ 12.8% revlog.py: _chunks line 2217: bins = self._chunks(chain, ... | 12.0% revlog.py: decompressline 2112: ladd(decomp(buffer(data, ch... \ 7.8% revlog.py: checkhash line 2232: self.checkhash(text, node, ... | 7.8% revlog.py: hash line 2315: if node != self.hash(text, ... | 7.8% revlog.py: hash line 2242: return hash(text, p1, p2) \ 12.0% manifest.py: __init__ line 1565: self._data = manifestdict(t... \ 16.8% context.py: filenode line 378: if not _islfs(fctx.filelog(... | 15.7% util.py: __get__ line 706: return self._filelog | 14.8% context.py: _filelog line 1416: result = self.func(obj) | 14.8% localrepo.py: file line 629: return self._repo.file(self... | 14.8% filelog.py: __init__ line 1134: return filelog.filelog(self... | 14.5% revlog.py: __init__ line 24: censorable=True)
author Matt Harbison <matt_harbison@yahoo.com>
date Fri, 24 Aug 2018 17:45:46 -0400
parents e79a69af1593
children 57875cf423c9
line wrap: on
line source

# minifileset.py - a simple language to select files
#
# Copyright 2017 Facebook, Inc.
#
# 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

from .i18n import _
from . import (
    error,
    fileset,
    filesetlang,
    pycompat,
)

def _sizep(x):
    # i18n: "size" is a keyword
    expr = filesetlang.getstring(x, _("size requires an expression"))
    return fileset.sizematcher(expr)

def _compile(tree):
    if not tree:
        raise error.ParseError(_("missing argument"))
    op = tree[0]
    if op == 'withstatus':
        return _compile(tree[1])
    elif op in {'symbol', 'string', 'kindpat'}:
        name = filesetlang.getpattern(tree, {'path'}, _('invalid file pattern'))
        if name.startswith('**'): # file extension test, ex. "**.tar.gz"
            ext = name[2:]
            for c in pycompat.bytestr(ext):
                if c in '*{}[]?/\\':
                    raise error.ParseError(_('reserved character: %s') % c)
            return lambda n, s: n.endswith(ext)
        elif name.startswith('path:'): # directory or full path test
            p = name[5:] # prefix
            pl = len(p)
            f = lambda n, s: n.startswith(p) and (len(n) == pl
                                                  or n[pl:pl + 1] == '/')
            return f
        raise error.ParseError(_("unsupported file pattern: %s") % name,
                               hint=_('paths must be prefixed with "path:"'))
    elif op in {'or', 'patterns'}:
        funcs = [_compile(x) for x in tree[1:]]
        return lambda n, s: any(f(n, s) for f in funcs)
    elif op == 'and':
        func1 = _compile(tree[1])
        func2 = _compile(tree[2])
        return lambda n, s: func1(n, s) and func2(n, s)
    elif op == 'not':
        return lambda n, s: not _compile(tree[1])(n, s)
    elif op == 'func':
        symbols = {
            'all': lambda n, s: True,
            'none': lambda n, s: False,
            'size': lambda n, s: _sizep(tree[2])(s),
        }

        name = filesetlang.getsymbol(tree[1])
        if name in symbols:
            return symbols[name]

        raise error.UnknownIdentifier(name, symbols.keys())
    elif op == 'minus':     # equivalent to 'x and not y'
        func1 = _compile(tree[1])
        func2 = _compile(tree[2])
        return lambda n, s: func1(n, s) and not func2(n, s)
    elif op == 'list':
        raise error.ParseError(_("can't use a list in this context"),
                               hint=_('see \'hg help "filesets.x or y"\''))
    raise error.ProgrammingError('illegal tree: %r' % (tree,))

def compile(text):
    """generate a function (path, size) -> bool from filter specification.

    "text" could contain the operators defined by the fileset language for
    common logic operations, and parenthesis for grouping.  The supported path
    tests are '**.extname' for file extension test, and '"path:dir/subdir"'
    for prefix test.  The ``size()`` predicate is borrowed from filesets to test
    file size.  The predicates ``all()`` and ``none()`` are also supported.

    '(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
    example, will catch all php files whose size is greater than 10 MB, all
    files whose name ends with ".zip", and all files under "bin" in the repo
    root except for "bin/README".
    """
    tree = filesetlang.parse(text)
    tree = filesetlang.analyze(tree)
    tree = filesetlang.optimize(tree)
    return _compile(tree)