sparse: move code for importing rules from files into core

This is a pretty straightforward port. Some code cleanup was
performed. But no major changes to the logic were made.

I'm not a huge fan of this function because it does multiple
things. I'd like to get things into core first to facilitate
refactoring later.

Please also note the added inline comment about the oddities
of writeconfig() and the try..except to undo it. This is because
of the hackiness in which the sparse matcher is obtained by
various consumers, notably dirstate. We'll need a massive
refactor to address this. That refactor is effectively blocked
on having the sparse dirstate hacks live in core.

hgext/sparse.py

@@ -1,494 +1,446 b''
 # sparse.py - allow sparse checkouts of the working directory
 #
 # Copyright 2014 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.
 
 """allow sparse checkouts of the working directory (EXPERIMENTAL)
 
 (This extension is not yet protected by backwards compatibility
 guarantees. Any aspect may break in future releases until this
 notice is removed.)
 
 This extension allows the working directory to only consist of a
 subset of files for the revision. This allows specific files or
 directories to be explicitly included or excluded. Many repository
 operations have performance proportional to the number of files in
 the working directory. So only realizing a subset of files in the
 working directory can improve performance.
 
 Sparse Config Files
 -------------------
 
 The set of files that are part of a sparse checkout are defined by
 a sparse config file. The file defines 3 things: includes (files to
 include in the sparse checkout), excludes (files to exclude from the
 sparse checkout), and profiles (links to other config files).
 
 The file format is newline delimited. Empty lines and lines beginning
 with ``#`` are ignored.
 
 Lines beginning with ``%include `` denote another sparse config file
 to include. e.g. ``%include tests.sparse``. The filename is relative
 to the repository root.
 
 The special lines ``[include]`` and ``[exclude]`` denote the section
 for includes and excludes that follow, respectively. It is illegal to
 have ``[include]`` after ``[exclude]``. If no sections are defined,
 entries are assumed to be in the ``[include]`` section.
 
 Non-special lines resemble file patterns to be added to either includes
 or excludes. The syntax of these lines is documented by :hg:`help patterns`.
 Patterns are interpreted as ``glob:`` by default and match against the
 root of the repository.
 
 Exclusion patterns take precedence over inclusion patterns. So even
 if a file is explicitly included, an ``[exclude]`` entry can remove it.
 
 For example, say you have a repository with 3 directories, ``frontend/``,
 ``backend/``, and ``tools/``. ``frontend/`` and ``backend/`` correspond
 to different projects and it is uncommon for someone working on one
 to need the files for the other. But ``tools/`` contains files shared
 between both projects. Your sparse config files may resemble::
 
   # frontend.sparse
   frontend/**
   tools/**
 
   # backend.sparse
   backend/**
   tools/**
 
 Say the backend grows in size. Or there's a directory with thousands
 of files you wish to exclude. You can modify the profile to exclude
 certain files::
 
   [include]
   backend/**
   tools/**
 
   [exclude]
   tools/tests/**
 """
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     dirstate,
     error,
     extensions,
     hg,
     localrepo,
     match as matchmod,
     registrar,
     sparse,
     util,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 def extsetup(ui):
     sparse.enabled = True
 
     _setupclone(ui)
     _setuplog(ui)
     _setupadd(ui)
     _setupdirstate(ui)
 
 def reposetup(ui, repo):
     if not util.safehasattr(repo, 'dirstate'):
         return
 
     if 'dirstate' in repo._filecache:
         repo.dirstate.repo = repo
 
 def replacefilecache(cls, propname, replacement):
     """Replace a filecache property with a new class. This allows changing the
     cache invalidation condition."""
     origcls = cls
     assert callable(replacement)
     while cls is not object:
         if propname in cls.__dict__:
             orig = cls.__dict__[propname]
             setattr(cls, propname, replacement(orig))
             break
         cls = cls.__bases__[0]
 
     if cls is object:
         raise AttributeError(_("type '%s' has no property '%s'") % (origcls,
                              propname))
 
 def _setuplog(ui):
     entry = commands.table['^log|history']
     entry[1].append(('', 'sparse', None,
         "limit to changesets affecting the sparse checkout"))
 
     def _logrevs(orig, repo, opts):
         revs = orig(repo, opts)
         if opts.get('sparse'):
             sparsematch = sparse.matcher(repo)
             def ctxmatch(rev):
                 ctx = repo[rev]
                 return any(f for f in ctx.files() if sparsematch(f))
             revs = revs.filter(ctxmatch)
         return revs
     extensions.wrapfunction(cmdutil, '_logrevs', _logrevs)
 
 def _clonesparsecmd(orig, ui, repo, *args, **opts):
     include_pat = opts.get('include')
     exclude_pat = opts.get('exclude')
     enableprofile_pat = opts.get('enable_profile')
     include = exclude = enableprofile = False
     if include_pat:
         pat = include_pat
         include = True
     if exclude_pat:
         pat = exclude_pat
         exclude = True
     if enableprofile_pat:
         pat = enableprofile_pat
         enableprofile = True
     if sum([include, exclude, enableprofile]) > 1:
         raise error.Abort(_("too many flags specified."))
     if include or exclude or enableprofile:
         def clonesparse(orig, self, node, overwrite, *args, **kwargs):
             _config(self.ui, self.unfiltered(), pat, {}, include=include,
                     exclude=exclude, enableprofile=enableprofile)
             return orig(self, node, overwrite, *args, **kwargs)
         extensions.wrapfunction(hg, 'updaterepo', clonesparse)
     return orig(ui, repo, *args, **opts)
 
 def _setupclone(ui):
     entry = commands.table['^clone']
     entry[1].append(('', 'enable-profile', [],
                     'enable a sparse profile'))
     entry[1].append(('', 'include', [],
                     'include sparse pattern'))
     entry[1].append(('', 'exclude', [],
                     'exclude sparse pattern'))
     extensions.wrapcommand(commands.table, 'clone', _clonesparsecmd)
 
 def _setupadd(ui):
     entry = commands.table['^add']
     entry[1].append(('s', 'sparse', None,
                     'also include directories of added files in sparse config'))
 
     def _add(orig, ui, repo, *pats, **opts):
         if opts.get('sparse'):
             dirs = set()
             for pat in pats:
                 dirname, basename = util.split(pat)
                 dirs.add(dirname)
             _config(ui, repo, list(dirs), opts, include=True)
         return orig(ui, repo, *pats, **opts)
 
     extensions.wrapcommand(commands.table, 'add', _add)
 
 def _setupdirstate(ui):
     """Modify the dirstate to prevent stat'ing excluded files,
     and to prevent modifications to files outside the checkout.
     """
 
     def _dirstate(orig, repo):
         dirstate = orig(repo)
         dirstate.repo = repo
         return dirstate
     extensions.wrapfunction(
         localrepo.localrepository.dirstate, 'func', _dirstate)
 
     # The atrocity below is needed to wrap dirstate._ignore. It is a cached
     # property, which means normal function wrapping doesn't work.
     class ignorewrapper(object):
         def __init__(self, orig):
             self.orig = orig
             self.origignore = None
             self.func = None
             self.sparsematch = None
 
         def __get__(self, obj, type=None):
             repo = obj.repo
             origignore = self.orig.__get__(obj)
 
             sparsematch = sparse.matcher(repo)
             if sparsematch.always():
                 return origignore
 
             if self.sparsematch != sparsematch or self.origignore != origignore:
                 self.func = matchmod.unionmatcher([
                     origignore, matchmod.negatematcher(sparsematch)])
                 self.sparsematch = sparsematch
                 self.origignore = origignore
             return self.func
 
         def __set__(self, obj, value):
             return self.orig.__set__(obj, value)
 
         def __delete__(self, obj):
             return self.orig.__delete__(obj)
 
     replacefilecache(dirstate.dirstate, '_ignore', ignorewrapper)
 
     # dirstate.rebuild should not add non-matching files
     def _rebuild(orig, self, parent, allfiles, changedfiles=None):
         matcher = sparse.matcher(self.repo)
         if not matcher.always():
             allfiles = allfiles.matches(matcher)
             if changedfiles:
                 changedfiles = [f for f in changedfiles if matcher(f)]
 
             if changedfiles is not None:
                 # In _rebuild, these files will be deleted from the dirstate
                 # when they are not found to be in allfiles
                 dirstatefilestoremove = set(f for f in self if not matcher(f))
                 changedfiles = dirstatefilestoremove.union(changedfiles)
 
         return orig(self, parent, allfiles, changedfiles)
     extensions.wrapfunction(dirstate.dirstate, 'rebuild', _rebuild)
 
     # Prevent adding files that are outside the sparse checkout
     editfuncs = ['normal', 'add', 'normallookup', 'copy', 'remove', 'merge']
     hint = _('include file with `hg debugsparse --include <pattern>` or use ' +
              '`hg add -s <file>` to include file directory while adding')
     for func in editfuncs:
         def _wrapper(orig, self, *args):
             repo = self.repo
             sparsematch = sparse.matcher(repo)
             if not sparsematch.always():
                 dirstate = repo.dirstate
                 for f in args:
                     if (f is not None and not sparsematch(f) and
                         f not in dirstate):
                         raise error.Abort(_("cannot add '%s' - it is outside "
                                             "the sparse checkout") % f,
                                           hint=hint)
             return orig(self, *args)
         extensions.wrapfunction(dirstate.dirstate, func, _wrapper)
 
 @command('^debugsparse', [
     ('I', 'include', False, _('include files in the sparse checkout')),
     ('X', 'exclude', False, _('exclude files in the sparse checkout')),
     ('d', 'delete', False, _('delete an include/exclude rule')),
     ('f', 'force', False, _('allow changing rules even with pending changes')),
     ('', 'enable-profile', False, _('enables the specified profile')),
     ('', 'disable-profile', False, _('disables the specified profile')),
     ('', 'import-rules', False, _('imports rules from a file')),
     ('', 'clear-rules', False, _('clears local include/exclude rules')),
     ('', 'refresh', False, _('updates the working after sparseness changes')),
     ('', 'reset', False, _('makes the repo full again')),
     ] + commands.templateopts,
     _('[--OPTION] PATTERN...'))
 def debugsparse(ui, repo, *pats, **opts):
     """make the current checkout sparse, or edit the existing checkout
 
     The sparse command is used to make the current checkout sparse.
     This means files that don't meet the sparse condition will not be
     written to disk, or show up in any working copy operations. It does
     not affect files in history in any way.
 
     Passing no arguments prints the currently applied sparse rules.
 
     --include and --exclude are used to add and remove files from the sparse
     checkout. The effects of adding an include or exclude rule are applied
     immediately. If applying the new rule would cause a file with pending
     changes to be added or removed, the command will fail. Pass --force to
     force a rule change even with pending changes (the changes on disk will
     be preserved).
 
     --delete removes an existing include/exclude rule. The effects are
     immediate.
 
     --refresh refreshes the files on disk based on the sparse rules. This is
     only necessary if .hg/sparse was changed by hand.
 
     --enable-profile and --disable-profile accept a path to a .hgsparse file.
     This allows defining sparse checkouts and tracking them inside the
     repository. This is useful for defining commonly used sparse checkouts for
     many people to use. As the profile definition changes over time, the sparse
     checkout will automatically be updated appropriately, depending on which
     changeset is checked out. Changes to .hgsparse are not applied until they
     have been committed.
 
     --import-rules accepts a path to a file containing rules in the .hgsparse
     format, allowing you to add --include, --exclude and --enable-profile rules
     in bulk. Like the --include, --exclude and --enable-profile switches, the
     changes are applied immediately.
 
     --clear-rules removes all local include and exclude rules, while leaving
     any enabled profiles in place.
 
     Returns 0 if editing the sparse checkout succeeds.
     """
     include = opts.get('include')
     exclude = opts.get('exclude')
     force = opts.get('force')
     enableprofile = opts.get('enable_profile')
     disableprofile = opts.get('disable_profile')
     importrules = opts.get('import_rules')
     clearrules = opts.get('clear_rules')
     delete = opts.get('delete')
     refresh = opts.get('refresh')
     reset = opts.get('reset')
     count = sum([include, exclude, enableprofile, disableprofile, delete,
                  importrules, refresh, clearrules, reset])
     if count > 1:
         raise error.Abort(_("too many flags specified"))
 
     if count == 0:
         if repo.vfs.exists('sparse'):
             ui.status(repo.vfs.read("sparse") + "\n")
             temporaryincludes = sparse.readtemporaryincludes(repo)
             if temporaryincludes:
                 ui.status(_("Temporarily Included Files (for merge/rebase):\n"))
                 ui.status(("\n".join(temporaryincludes) + "\n"))
         else:
             ui.status(_('repo is not sparse\n'))
         return
 
     if include or exclude or delete or reset or enableprofile or disableprofile:
         _config(ui, repo, pats, opts, include=include, exclude=exclude,
                 reset=reset, delete=delete, enableprofile=enableprofile,
                 disableprofile=disableprofile, force=force)
 
     if importrules:
-        _import(ui, repo, pats, opts, force=force)
+        sparse.importfromfiles(repo, opts, pats, force=force)
 
     if clearrules:
         sparse.clearrules(repo, force=force)
 
     if refresh:
         try:
             wlock = repo.wlock()
             fcounts = map(
                 len,
                 sparse.refreshwdir(repo, repo.status(), sparse.matcher(repo),
                                    force=force))
             sparse.printchanges(ui, opts, added=fcounts[0], dropped=fcounts[1],
                                 conflicting=fcounts[2])
         finally:
             wlock.release()
 
 def _config(ui, repo, pats, opts, include=False, exclude=False, reset=False,
             delete=False, enableprofile=False, disableprofile=False,
             force=False):
     """
     Perform a sparse config update. Only one of the kwargs may be specified.
     """
     wlock = repo.wlock()
     try:
         oldsparsematch = sparse.matcher(repo)
 
         raw = repo.vfs.tryread('sparse')
         if raw:
             oldinclude, oldexclude, oldprofiles = map(
                 set, sparse.parseconfig(ui, raw))
         else:
             oldinclude = set()
             oldexclude = set()
             oldprofiles = set()
 
         try:
             if reset:
                 newinclude = set()
                 newexclude = set()
                 newprofiles = set()
             else:
                 newinclude = set(oldinclude)
                 newexclude = set(oldexclude)
                 newprofiles = set(oldprofiles)
 
             oldstatus = repo.status()
 
             if any(pat.startswith('/') for pat in pats):
                 ui.warn(_('warning: paths cannot start with /, ignoring: %s\n')
                           % ([pat for pat in pats if pat.startswith('/')]))
             elif include:
                 newinclude.update(pats)
             elif exclude:
                 newexclude.update(pats)
             elif enableprofile:
                 newprofiles.update(pats)
             elif disableprofile:
                 newprofiles.difference_update(pats)
             elif delete:
                 newinclude.difference_update(pats)
                 newexclude.difference_update(pats)
 
             sparse.writeconfig(repo, newinclude, newexclude, newprofiles)
 
             fcounts = map(
                 len,
                 sparse.refreshwdir(repo, oldstatus, oldsparsematch,
                                    force=force))
 
             profilecount = (len(newprofiles - oldprofiles) -
                             len(oldprofiles - newprofiles))
             includecount = (len(newinclude - oldinclude) -
                             len(oldinclude - newinclude))
             excludecount = (len(newexclude - oldexclude) -
                             len(oldexclude - newexclude))
             sparse.printchanges(ui, opts, profilecount, includecount,
                                 excludecount, *fcounts)
         except Exception:
             sparse.writeconfig(repo, oldinclude, oldexclude, oldprofiles)
             raise
     finally:
         wlock.release()
-
-def _import(ui, repo, files, opts, force=False):
-    with repo.wlock():
-        # read current configuration
-        raw = repo.vfs.tryread('sparse')
-        oincludes, oexcludes, oprofiles = sparse.parseconfig(ui, raw)
-        includes, excludes, profiles = map(
-                set, (oincludes, oexcludes, oprofiles))
-
-        aincludes, aexcludes, aprofiles = sparse.activeconfig(repo)
-
-        # import rules on top; only take in rules that are not yet
-        # part of the active rules.
-        changed = False
-        for file in files:
-            with util.posixfile(util.expandpath(file)) as importfile:
-                iincludes, iexcludes, iprofiles = sparse.parseconfig(
-                    ui, importfile.read())
-                oldsize = len(includes) + len(excludes) + len(profiles)
-                includes.update(iincludes - aincludes)
-                excludes.update(iexcludes - aexcludes)
-                profiles.update(set(iprofiles) - aprofiles)
-                if len(includes) + len(excludes) + len(profiles) > oldsize:
-                    changed = True
-
-        profilecount = includecount = excludecount = 0
-        fcounts = (0, 0, 0)
-
-        if changed:
-            profilecount = len(profiles - aprofiles)
-            includecount = len(includes - aincludes)
-            excludecount = len(excludes - aexcludes)
-
-            oldstatus = repo.status()
-            oldsparsematch = sparse.matcher(repo)
-            sparse.writeconfig(repo, includes, excludes, profiles)
-
-            try:
-                fcounts = map(
-                    len,
-                    sparse.refreshwdir(repo, oldstatus, oldsparsematch,
-                                       force=force))
-            except Exception:
-                sparse.writeconfig(repo, oincludes, oexcludes, oprofiles)
-                raise
-
-        sparse.printchanges(ui, opts, profilecount, includecount, excludecount,
-                            *fcounts)

mercurial/sparse.py

@@ -1,545 +1,607 b''
 # sparse.py - functionality for sparse checkouts
 #
 # Copyright 2014 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
 
 import collections
 import hashlib
 import os
 
 from .i18n import _
 from .node import nullid
 from . import (
     error,
     match as matchmod,
     merge as mergemod,
     pycompat,
+    util,
 )
 
 # Whether sparse features are enabled. This variable is intended to be
 # temporary to facilitate porting sparse to core. It should eventually be
 # a per-repo option, possibly a repo requirement.
 enabled = False
 
 def parseconfig(ui, raw):
     """Parse sparse config file content.
 
     Returns a tuple of includes, excludes, and profiles.
     """
     includes = set()
     excludes = set()
     current = includes
     profiles = []
     for line in raw.split('\n'):
         line = line.strip()
         if not line or line.startswith('#'):
             # empty or comment line, skip
             continue
         elif line.startswith('%include '):
             line = line[9:].strip()
             if line:
                 profiles.append(line)
         elif line == '[include]':
             if current != includes:
                 # TODO pass filename into this API so we can report it.
                 raise error.Abort(_('sparse config cannot have includes ' +
                                     'after excludes'))
             continue
         elif line == '[exclude]':
             current = excludes
         elif line:
             if line.strip().startswith('/'):
                 ui.warn(_('warning: sparse profile cannot use' +
                           ' paths starting with /, ignoring %s\n') % line)
                 continue
             current.add(line)
 
     return includes, excludes, profiles
 
 # Exists as separate function to facilitate monkeypatching.
 def readprofile(repo, profile, changeid):
     """Resolve the raw content of a sparse profile file."""
     # TODO add some kind of cache here because this incurs a manifest
     # resolve and can be slow.
     return repo.filectx(profile, changeid=changeid).data()
 
 def patternsforrev(repo, rev):
     """Obtain sparse checkout patterns for the given rev.
 
     Returns a tuple of iterables representing includes, excludes, and
     patterns.
     """
     # Feature isn't enabled. No-op.
     if not enabled:
         return set(), set(), []
 
     raw = repo.vfs.tryread('sparse')
     if not raw:
         return set(), set(), []
 
     if rev is None:
         raise error.Abort(_('cannot parse sparse patterns from working '
                             'directory'))
 
     includes, excludes, profiles = parseconfig(repo.ui, raw)
     ctx = repo[rev]
 
     if profiles:
         visited = set()
         while profiles:
             profile = profiles.pop()
             if profile in visited:
                 continue
 
             visited.add(profile)
 
             try:
                 raw = readprofile(repo, profile, rev)
             except error.ManifestLookupError:
                 msg = (
                     "warning: sparse profile '%s' not found "
                     "in rev %s - ignoring it\n" % (profile, ctx))
                 # experimental config: sparse.missingwarning
                 if repo.ui.configbool(
                         'sparse', 'missingwarning', True):
                     repo.ui.warn(msg)
                 else:
                     repo.ui.debug(msg)
                 continue
 
             pincludes, pexcludes, subprofs = parseconfig(repo.ui, raw)
             includes.update(pincludes)
             excludes.update(pexcludes)
             for subprofile in subprofs:
                 profiles.append(subprofile)
 
         profiles = visited
 
     if includes:
         includes.add('.hg*')
 
     return includes, excludes, profiles
 
 def activeconfig(repo):
     """Determine the active sparse config rules.
 
     Rules are constructed by reading the current sparse config and bringing in
     referenced profiles from parents of the working directory.
     """
     revs = [repo.changelog.rev(node) for node in
             repo.dirstate.parents() if node != nullid]
 
     allincludes = set()
     allexcludes = set()
     allprofiles = set()
 
     for rev in revs:
         includes, excludes, profiles = patternsforrev(repo, rev)
         allincludes |= includes
         allexcludes |= excludes
         allprofiles |= set(profiles)
 
     return allincludes, allexcludes, allprofiles
 
 def configsignature(repo, includetemp=True):
     """Obtain the signature string for the current sparse configuration.
 
     This is used to construct a cache key for matchers.
     """
     cache = repo._sparsesignaturecache
 
     signature = cache.get('signature')
 
     if includetemp:
         tempsignature = cache.get('tempsignature')
     else:
         tempsignature = '0'
 
     if signature is None or (includetemp and tempsignature is None):
         signature = hashlib.sha1(repo.vfs.tryread('sparse')).hexdigest()
         cache['signature'] = signature
 
         if includetemp:
             raw = repo.vfs.tryread('tempsparse')
             tempsignature = hashlib.sha1(raw).hexdigest()
             cache['tempsignature'] = tempsignature
 
     return '%s %s' % (signature, tempsignature)
 
 def writeconfig(repo, includes, excludes, profiles):
     """Write the sparse config file given a sparse configuration."""
     with repo.vfs('sparse', 'wb') as fh:
         for p in sorted(profiles):
             fh.write('%%include %s\n' % p)
 
         if includes:
             fh.write('[include]\n')
             for i in sorted(includes):
                 fh.write(i)
                 fh.write('\n')
 
         if excludes:
             fh.write('[exclude]\n')
             for e in sorted(excludes):
                 fh.write(e)
                 fh.write('\n')
 
     repo._sparsesignaturecache.clear()
 
 def readtemporaryincludes(repo):
     raw = repo.vfs.tryread('tempsparse')
     if not raw:
         return set()
 
     return set(raw.split('\n'))
 
 def writetemporaryincludes(repo, includes):
     repo.vfs.write('tempsparse', '\n'.join(sorted(includes)))
     repo._sparsesignaturecache.clear()
 
 def addtemporaryincludes(repo, additional):
     includes = readtemporaryincludes(repo)
     for i in additional:
         includes.add(i)
     writetemporaryincludes(repo, includes)
 
 def prunetemporaryincludes(repo):
     if not enabled or not repo.vfs.exists('tempsparse'):
         return
 
     s = repo.status()
     if s.modified or s.added or s.removed or s.deleted:
         # Still have pending changes. Don't bother trying to prune.
         return
 
     sparsematch = matcher(repo, includetemp=False)
     dirstate = repo.dirstate
     actions = []
     dropped = []
     tempincludes = readtemporaryincludes(repo)
     for file in tempincludes:
         if file in dirstate and not sparsematch(file):
             message = _('dropping temporarily included sparse files')
             actions.append((file, None, message))
             dropped.append(file)
 
     typeactions = collections.defaultdict(list)
     typeactions['r'] = actions
     mergemod.applyupdates(repo, typeactions, repo[None], repo['.'], False)
 
     # Fix dirstate
     for file in dropped:
         dirstate.drop(file)
 
     repo.vfs.unlink('tempsparse')
     repo._sparsesignaturecache.clear()
     msg = _('cleaned up %d temporarily added file(s) from the '
             'sparse checkout\n')
     repo.ui.status(msg % len(tempincludes))
 
 def matcher(repo, revs=None, includetemp=True):
     """Obtain a matcher for sparse working directories for the given revs.
 
     If multiple revisions are specified, the matcher is the union of all
     revs.
 
     ``includetemp`` indicates whether to use the temporary sparse profile.
     """
     # If sparse isn't enabled, sparse matcher matches everything.
     if not enabled:
         return matchmod.always(repo.root, '')
 
     if not revs or revs == [None]:
         revs = [repo.changelog.rev(node)
                 for node in repo.dirstate.parents() if node != nullid]
 
     signature = configsignature(repo, includetemp=includetemp)
 
     key = '%s %s' % (signature, ' '.join(map(pycompat.bytestr, revs)))
 
     result = repo._sparsematchercache.get(key)
     if result:
         return result
 
     matchers = []
     for rev in revs:
         try:
             includes, excludes, profiles = patternsforrev(repo, rev)
 
             if includes or excludes:
                 # Explicitly include subdirectories of includes so
                 # status will walk them down to the actual include.
                 subdirs = set()
                 for include in includes:
                     # TODO consider using posix path functions here so Windows
                     # \ directory separators don't come into play.
                     dirname = os.path.dirname(include)
                     # basename is used to avoid issues with absolute
                     # paths (which on Windows can include the drive).
                     while os.path.basename(dirname):
                         subdirs.add(dirname)
                         dirname = os.path.dirname(dirname)
 
                 matcher = matchmod.match(repo.root, '', [],
                                          include=includes, exclude=excludes,
                                          default='relpath')
                 if subdirs:
                     matcher = matchmod.forceincludematcher(matcher, subdirs)
                 matchers.append(matcher)
         except IOError:
             pass
 
     if not matchers:
         result = matchmod.always(repo.root, '')
     elif len(matchers) == 1:
         result = matchers[0]
     else:
         result = matchmod.unionmatcher(matchers)
 
     if includetemp:
         tempincludes = readtemporaryincludes(repo)
         result = matchmod.forceincludematcher(result, tempincludes)
 
     repo._sparsematchercache[key] = result
 
     return result
 
 def filterupdatesactions(repo, wctx, mctx, branchmerge, actions):
     """Filter updates to only lay out files that match the sparse rules."""
     if not enabled:
         return actions
 
     oldrevs = [pctx.rev() for pctx in wctx.parents()]
     oldsparsematch = matcher(repo, oldrevs)
 
     if oldsparsematch.always():
         return actions
 
     files = set()
     prunedactions = {}
 
     if branchmerge:
         # If we're merging, use the wctx filter, since we're merging into
         # the wctx.
         sparsematch = matcher(repo, [wctx.parents()[0].rev()])
     else:
         # If we're updating, use the target context's filter, since we're
         # moving to the target context.
         sparsematch = matcher(repo, [mctx.rev()])
 
     temporaryfiles = []
     for file, action in actions.iteritems():
         type, args, msg = action
         files.add(file)
         if sparsematch(file):
             prunedactions[file] = action
         elif type == 'm':
             temporaryfiles.append(file)
             prunedactions[file] = action
         elif branchmerge:
             if type != 'k':
                 temporaryfiles.append(file)
                 prunedactions[file] = action
         elif type == 'f':
             prunedactions[file] = action
         elif file in wctx:
             prunedactions[file] = ('r', args, msg)
 
     if len(temporaryfiles) > 0:
         repo.ui.status(_('temporarily included %d file(s) in the sparse '
                          'checkout for merging\n') % len(temporaryfiles))
         addtemporaryincludes(repo, temporaryfiles)
 
         # Add the new files to the working copy so they can be merged, etc
         actions = []
         message = 'temporarily adding to sparse checkout'
         wctxmanifest = repo[None].manifest()
         for file in temporaryfiles:
             if file in wctxmanifest:
                 fctx = repo[None][file]
                 actions.append((file, (fctx.flags(), False), message))
 
         typeactions = collections.defaultdict(list)
         typeactions['g'] = actions
         mergemod.applyupdates(repo, typeactions, repo[None], repo['.'],
                               False)
 
         dirstate = repo.dirstate
         for file, flags, msg in actions:
             dirstate.normal(file)
 
     profiles = activeconfig(repo)[2]
     changedprofiles = profiles & files
     # If an active profile changed during the update, refresh the checkout.
     # Don't do this during a branch merge, since all incoming changes should
     # have been handled by the temporary includes above.
     if changedprofiles and not branchmerge:
         mf = mctx.manifest()
         for file in mf:
             old = oldsparsematch(file)
             new = sparsematch(file)
             if not old and new:
                 flags = mf.flags(file)
                 prunedactions[file] = ('g', (flags, False), '')
             elif old and not new:
                 prunedactions[file] = ('r', [], '')
 
     return prunedactions
 
 def refreshwdir(repo, origstatus, origsparsematch, force=False):
     """Refreshes working directory by taking sparse config into account.
 
     The old status and sparse matcher is compared against the current sparse
     matcher.
 
     Will abort if a file with pending changes is being excluded or included
     unless ``force`` is True.
     """
     # Verify there are no pending changes
     pending = set()
     pending.update(origstatus.modified)
     pending.update(origstatus.added)
     pending.update(origstatus.removed)
     sparsematch = matcher(repo)
     abort = False
 
     for f in pending:
         if not sparsematch(f):
             repo.ui.warn(_("pending changes to '%s'\n") % f)
             abort = not force
 
     if abort:
         raise error.Abort(_('could not update sparseness due to pending '
                             'changes'))
 
     # Calculate actions
     dirstate = repo.dirstate
     ctx = repo['.']
     added = []
     lookup = []
     dropped = []
     mf = ctx.manifest()
     files = set(mf)
 
     actions = {}
 
     for file in files:
         old = origsparsematch(file)
         new = sparsematch(file)
         # Add files that are newly included, or that don't exist in
         # the dirstate yet.
         if (new and not old) or (old and new and not file in dirstate):
             fl = mf.flags(file)
             if repo.wvfs.exists(file):
                 actions[file] = ('e', (fl,), '')
                 lookup.append(file)
             else:
                 actions[file] = ('g', (fl, False), '')
                 added.append(file)
         # Drop files that are newly excluded, or that still exist in
         # the dirstate.
         elif (old and not new) or (not old and not new and file in dirstate):
             dropped.append(file)
             if file not in pending:
                 actions[file] = ('r', [], '')
 
     # Verify there are no pending changes in newly included files
     abort = False
     for file in lookup:
         repo.ui.warn(_("pending changes to '%s'\n") % file)
         abort = not force
     if abort:
         raise error.Abort(_('cannot change sparseness due to pending '
                             'changes (delete the files or use '
                             '--force to bring them back dirty)'))
 
     # Check for files that were only in the dirstate.
     for file, state in dirstate.iteritems():
         if not file in files:
             old = origsparsematch(file)
             new = sparsematch(file)
             if old and not new:
                 dropped.append(file)
 
     # Apply changes to disk
     typeactions = dict((m, []) for m in 'a f g am cd dc r dm dg m e k'.split())
     for f, (m, args, msg) in actions.iteritems():
         if m not in typeactions:
             typeactions[m] = []
         typeactions[m].append((f, args, msg))
 
     mergemod.applyupdates(repo, typeactions, repo[None], repo['.'], False)
 
     # Fix dirstate
     for file in added:
         dirstate.normal(file)
 
     for file in dropped:
         dirstate.drop(file)
 
     for file in lookup:
         # File exists on disk, and we're bringing it back in an unknown state.
         dirstate.normallookup(file)
 
     return added, dropped, lookup
 
 def aftercommit(repo, node):
     """Perform actions after a working directory commit."""
     # This function is called unconditionally, even if sparse isn't
     # enabled.
     ctx = repo[node]
 
     profiles = patternsforrev(repo, ctx.rev())[2]
 
     # profiles will only have data if sparse is enabled.
     if set(profiles) & set(ctx.files()):
         origstatus = repo.status()
         origsparsematch = matcher(repo)
         refreshwdir(repo, origstatus, origsparsematch, force=True)
 
     prunetemporaryincludes(repo)
 
 def clearrules(repo, force=False):
     """Clears include/exclude rules from the sparse config.
 
     The remaining sparse config only has profiles, if defined. The working
     directory is refreshed, as needed.
     """
     with repo.wlock():
         raw = repo.vfs.tryread('sparse')
         includes, excludes, profiles = parseconfig(repo.ui, raw)
 
         if not includes and not excludes:
             return
 
         oldstatus = repo.status()
         oldmatch = matcher(repo)
         writeconfig(repo, set(), set(), profiles)
         refreshwdir(repo, oldstatus, oldmatch, force=force)
 
+def importfromfiles(repo, opts, paths, force=False):
+    """Import sparse config rules from files.
+
+    The updated sparse config is written out and the working directory
+    is refreshed, as needed.
+    """
+    with repo.wlock():
+        # read current configuration
+        raw = repo.vfs.tryread('sparse')
+        oincludes, oexcludes, oprofiles = parseconfig(repo.ui, raw)
+        includes, excludes, profiles = map(
+                set, (oincludes, oexcludes, oprofiles))
+
+        aincludes, aexcludes, aprofiles = activeconfig(repo)
+
+        # Import rules on top; only take in rules that are not yet
+        # part of the active rules.
+        changed = False
+        for p in paths:
+            with util.posixfile(util.expandpath(p)) as fh:
+                raw = fh.read()
+
+            iincludes, iexcludes, iprofiles = parseconfig(repo.ui, raw)
+            oldsize = len(includes) + len(excludes) + len(profiles)
+            includes.update(iincludes - aincludes)
+            excludes.update(iexcludes - aexcludes)
+            profiles.update(set(iprofiles) - aprofiles)
+            if len(includes) + len(excludes) + len(profiles) > oldsize:
+                changed = True
+
+        profilecount = includecount = excludecount = 0
+        fcounts = (0, 0, 0)
+
+        if changed:
+            profilecount = len(profiles - aprofiles)
+            includecount = len(includes - aincludes)
+            excludecount = len(excludes - aexcludes)
+
+            oldstatus = repo.status()
+            oldsparsematch = matcher(repo)
+
+            # TODO remove this try..except once the matcher integrates better
+            # with dirstate. We currently have to write the updated config
+            # because that will invalidate the matcher cache and force a
+            # re-read. We ideally want to update the cached matcher on the
+            # repo instance then flush the new config to disk once wdir is
+            # updated. But this requires massive rework to matcher() and its
+            # consumers.
+            writeconfig(repo, includes, excludes, profiles)
+
+            try:
+                fcounts = map(
+                    len,
+                    refreshwdir(repo, oldstatus, oldsparsematch, force=force))
+            except Exception:
+                writeconfig(repo, oincludes, oexcludes, oprofiles)
+                raise
+
+        printchanges(repo.ui, opts, profilecount, includecount, excludecount,
+                     *fcounts)
+
 def printchanges(ui, opts, profilecount=0, includecount=0, excludecount=0,
                  added=0, dropped=0, conflicting=0):
     """Print output summarizing sparse config changes."""
     with ui.formatter('sparse', opts) as fm:
         fm.startitem()
         fm.condwrite(ui.verbose, 'profiles_added', _('Profiles changed: %d\n'),
                      profilecount)
         fm.condwrite(ui.verbose, 'include_rules_added',
                      _('Include rules changed: %d\n'), includecount)
         fm.condwrite(ui.verbose, 'exclude_rules_added',
                      _('Exclude rules changed: %d\n'), excludecount)
 
         # In 'plain' verbose mode, mergemod.applyupdates already outputs what
         # files are added or removed outside of the templating formatter
         # framework. No point in repeating ourselves in that case.
         if not fm.isplain():
             fm.condwrite(ui.verbose, 'files_added', _('Files added: %d\n'),
                          added)
             fm.condwrite(ui.verbose, 'files_dropped', _('Files dropped: %d\n'),
                          dropped)
             fm.condwrite(ui.verbose, 'files_conflicting',
                          _('Files conflicting: %d\n'), conflicting)