Mercurial > hg
view mercurial/dagutil.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
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Wed, 10 Jan 2018 22:23:34 -0500 |
parents | f77121b6bf1b |
children | 0e46b92b37b1 |
line wrap: on
line source
# dagutil.py - dag utilities for mercurial # # Copyright 2010 Benoit Boissinot <bboissin@gmail.com> # and Peter Arrenbrecht <peter@arrenbrecht.ch> # # 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 .node import nullrev class basedag(object): '''generic interface for DAGs terms: "ix" (short for index) identifies a nodes internally, "id" identifies one externally. All params are ixs unless explicitly suffixed otherwise. Pluralized params are lists or sets. ''' def __init__(self): self._inverse = None def nodeset(self): '''set of all node ixs''' raise NotImplementedError def heads(self): '''list of head ixs''' raise NotImplementedError def parents(self, ix): '''list of parents ixs of ix''' raise NotImplementedError def inverse(self): '''inverse DAG, where parents becomes children, etc.''' raise NotImplementedError def ancestorset(self, starts, stops=None): ''' set of all ancestors of starts (incl), but stop walk at stops (excl) ''' raise NotImplementedError def descendantset(self, starts, stops=None): ''' set of all descendants of starts (incl), but stop walk at stops (excl) ''' return self.inverse().ancestorset(starts, stops) def headsetofconnecteds(self, ixs): ''' subset of connected list of ixs so that no node has a descendant in it By "connected list" we mean that if an ancestor and a descendant are in the list, then so is at least one path connecting them. ''' raise NotImplementedError def externalize(self, ix): '''return a node id''' return self._externalize(ix) def externalizeall(self, ixs): '''return a list of (or set if given a set) of node ids''' ids = self._externalizeall(ixs) if isinstance(ixs, set): return set(ids) return list(ids) def internalize(self, id): '''return a node ix''' return self._internalize(id) def internalizeall(self, ids, filterunknown=False): '''return a list of (or set if given a set) of node ixs''' ixs = self._internalizeall(ids, filterunknown) if isinstance(ids, set): return set(ixs) return list(ixs) class genericdag(basedag): '''generic implementations for DAGs''' def ancestorset(self, starts, stops=None): if stops: stops = set(stops) else: stops = set() seen = set() pending = list(starts) while pending: n = pending.pop() if n not in seen and n not in stops: seen.add(n) pending.extend(self.parents(n)) return seen def headsetofconnecteds(self, ixs): hds = set(ixs) if not hds: return hds for n in ixs: for p in self.parents(n): hds.discard(p) assert hds return hds class revlogbaseddag(basedag): '''generic dag interface to a revlog''' def __init__(self, revlog, nodeset): basedag.__init__(self) self._revlog = revlog self._heads = None self._nodeset = nodeset def nodeset(self): return self._nodeset def heads(self): if self._heads is None: self._heads = self._getheads() return self._heads def _externalize(self, ix): return self._revlog.index[ix][7] def _externalizeall(self, ixs): idx = self._revlog.index return [idx[i][7] for i in ixs] def _internalize(self, id): ix = self._revlog.rev(id) if ix == nullrev: raise LookupError(id, self._revlog.indexfile, _('nullid')) return ix def _internalizeall(self, ids, filterunknown): rl = self._revlog if filterunknown: return [r for r in map(rl.nodemap.get, ids) if (r is not None and r != nullrev and r not in rl.filteredrevs)] return [self._internalize(i) for i in ids] class revlogdag(revlogbaseddag): '''dag interface to a revlog''' def __init__(self, revlog, localsubset=None): revlogbaseddag.__init__(self, revlog, set(revlog)) self._heads = localsubset def _getheads(self): return [r for r in self._revlog.headrevs() if r != nullrev] def parents(self, ix): rlog = self._revlog idx = rlog.index revdata = idx[ix] prev = revdata[5] if prev != nullrev: prev2 = revdata[6] if prev2 == nullrev: return [prev] return [prev, prev2] prev2 = revdata[6] if prev2 != nullrev: return [prev2] return [] def inverse(self): if self._inverse is None: self._inverse = inverserevlogdag(self) return self._inverse def ancestorset(self, starts, stops=None): rlog = self._revlog idx = rlog.index if stops: stops = set(stops) else: stops = set() seen = set() pending = list(starts) while pending: rev = pending.pop() if rev not in seen and rev not in stops: seen.add(rev) revdata = idx[rev] for i in [5, 6]: prev = revdata[i] if prev != nullrev: pending.append(prev) return seen def headsetofconnecteds(self, ixs): if not ixs: return set() rlog = self._revlog idx = rlog.index headrevs = set(ixs) for rev in ixs: revdata = idx[rev] for i in [5, 6]: prev = revdata[i] if prev != nullrev: headrevs.discard(prev) assert headrevs return headrevs def linearize(self, ixs): '''linearize and topologically sort a list of revisions The linearization process tries to create long runs of revs where a child rev comes immediately after its first parent. This is done by visiting the heads of the given revs in inverse topological order, and for each visited rev, visiting its second parent, then its first parent, then adding the rev itself to the output list. ''' sorted = [] visit = list(self.headsetofconnecteds(ixs)) visit.sort(reverse=True) finished = set() while visit: cur = visit.pop() if cur < 0: cur = -cur - 1 if cur not in finished: sorted.append(cur) finished.add(cur) else: visit.append(-cur - 1) visit += [p for p in self.parents(cur) if p in ixs and p not in finished] assert len(sorted) == len(ixs) return sorted class inverserevlogdag(revlogbaseddag, genericdag): '''inverse of an existing revlog dag; see revlogdag.inverse()''' def __init__(self, orig): revlogbaseddag.__init__(self, orig._revlog, orig._nodeset) self._orig = orig self._children = {} self._roots = [] self._walkfrom = len(self._revlog) - 1 def _walkto(self, walkto): rev = self._walkfrom cs = self._children roots = self._roots idx = self._revlog.index while rev >= walkto: data = idx[rev] isroot = True for prev in [data[5], data[6]]: # parent revs if prev != nullrev: cs.setdefault(prev, []).append(rev) isroot = False if isroot: roots.append(rev) rev -= 1 self._walkfrom = rev def _getheads(self): self._walkto(nullrev) return self._roots def parents(self, ix): if ix is None: return [] if ix <= self._walkfrom: self._walkto(ix) return self._children.get(ix, []) def inverse(self): return self._orig