# 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 (

    hex,

    nullid,

)

from . import (

    error,

    match as matchmod,

    merge as mergemod,

    pathutil,

    pycompat,

    scmutil,

    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()

    profiles = set()

    current = None

    havesection = False

    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.add(line)

        elif line == '[include]':

            if havesection and current != includes:

                # TODO pass filename into this API so we can report it.

                raise error.Abort(_('sparse config cannot have includes ' +

                                    'after excludes'))

            havesection = True

            current = includes

            continue

        elif line == '[exclude]':

            havesection = True

            current = excludes

        elif line:

            if current is None:

                raise error.Abort(_('sparse config entry outside of '

                                    'section: %s') % line,

                                  hint=_('add an [include] or [exclude] line '

                                         'to declare the entry type'))

            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(), set()

    raw = repo.vfs.tryread('sparse')

    if not raw:

        return set(), 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'):

                    repo.ui.warn(msg)

                else:

                    repo.ui.debug(msg)

                continue

            pincludes, pexcludes, subprofs = parseconfig(repo.ui, raw)

            includes.update(pincludes)

            excludes.update(pexcludes)

            profiles.update(subprofs)

        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 |= 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 = hex(hashlib.sha1(repo.vfs.tryread('sparse')).digest())

        cache['signature'] = signature

        if includetemp:

            raw = repo.vfs.tryread('tempsparse')

            tempsignature = hex(hashlib.sha1(raw).digest())

            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 forceincludematcher(matcher, includes):

    """Returns a matcher that returns true for any of the forced includes

    before testing against the actual matcher."""

    kindpats = [('path', include, '') for include in includes]

    includematcher = matchmod.includematcher('', '', kindpats)

    return matchmod.unionmatcher([includematcher, matcher])

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:

                matcher = matchmod.match(repo.root, '', [],

                                         include=includes, exclude=excludes,

                                         default='relpath')

                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 = 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.