comparison mercurial/branchmap.py @ 43076:2372284d9457

formatting: blacken the codebase

This is using my patch to black
(https://github.com/psf/black/pull/826) so we don't un-wrap collection
literals.

Done with:

  hg files 'set:**.py - mercurial/thirdparty/** - "contrib/python-zstandard/**"' | xargs black -S

# skip-blame mass-reformatting only

# no-check-commit reformats foo_bar functions

Differential Revision: https://phab.mercurial-scm.org/D6971

43075:57875cf423c9

from .utils import (
    repoviewutil,
    stringutil,
)

subsettable = repoviewutil. subsettable

calcsize = struct.calcsize
pack_into = struct.pack_into
unpack_from = struct.unpack_from


class BranchMapCache(object):
    """mapping of filtered views of repo with their branchcache"""
    def __init__(self):
        self._per_filter = {}

    def __getitem__(self, repo):
        self.updatecache(repo)

                    closed.append(h)

        if rbheads:
            rtiprev = max((int(clrev(node)) for node in rbheads))
            cache = branchcache(
                remotebranchmap, repo[rtiprev].node(), rtiprev,
                closednodes=closed)

            # Try to stick it as low as possible
            # filter above served are unlikely to be fetch from a clone
            for candidate in ('base', 'immutable', 'served'):
                rview = repo.filtered(candidate)

                    return

    def clear(self):
        self._per_filter.clear()

def _unknownnode(node):
    """ raises ValueError when branchcache found a node which does not exists
    """
    raise ValueError(r'node %s does not exist' % pycompat.sysstr(hex(node)))

def _branchcachedesc(repo):
    if repo.filtername is not None:
        return 'branch cache (%s)' % repo.filtername
    else:
        return 'branch cache'

class branchcache(object):
    """A dict like object that hold branches heads cache.

    This cache is used to avoid costly computations to determine all the
    branch heads of a repo.

    The open/closed state is represented by a single letter 'o' or 'c'.
    This field can be used to avoid changelog reads when determining if a
    branch head closes a branch or not.
    """

    def __init__(self, entries=(), tipnode=nullid, tiprev=nullrev,
                 filteredhash=None, closednodes=None, hasnode=None):
        """ hasnode is a function which can be used to verify whether changelog
        has a given node or not. If it's not provided, we assume that every node
        we have exists in changelog """
        self.tipnode = tipnode
        self.tiprev = tiprev

            last, lrev = bin(last), int(lrev)
            filteredhash = None
            hasnode = repo.changelog.hasnode
            if len(cachekey) > 2:
                filteredhash = bin(cachekey[2])
            bcache = cls(tipnode=last, tiprev=lrev, filteredhash=filteredhash,
                         hasnode=hasnode)
            if not bcache.validfor(repo):
                # invalidate the cache
                raise ValueError(r'tip differs')
            bcache.load(repo, lineiter)
        except (IOError, OSError):
            return None

        except Exception as inst:
            if repo.ui.debugflag:
                msg = 'invalid %s: %s\n'
                repo.ui.debug(msg % (_branchcachedesc(repo),
                                     pycompat.bytestr(inst)))
            bcache = None

        finally:
            if f:
                f.close()

        """Is the cache content valid regarding a repo

        - False when cached tipnode is unknown or if we detect a strip.
        - True when cache is up to date or a subset of current repo."""
        try:
            return ((self.tipnode == repo.changelog.node(self.tiprev))
                    and (self.filteredhash ==
                         scmutil.filteredhash(repo, self.tiprev)))
        except IndexError:
            return False

    def _branchtip(self, heads):
        '''Return tuple with last open head in heads and false,

        return self._entries.itervalues()

    def copy(self):
        """return an deep copy of the branchcache object"""
        return type(self)(
            self._entries, self.tipnode, self.tiprev, self.filteredhash,
            self._closednodes)

    def write(self, repo):
        try:
            f = repo.cachevfs(self._filename(repo), "w", atomictemp=True)
            cachekey = [hex(self.tipnode), '%d' % self.tiprev]

                        state = 'c'
                    else:
                        state = 'o'
                    f.write("%s %s %s\n" % (hex(node), state, label))
            f.close()
            repo.ui.log('branchcache', 'wrote %s with %d labels and %d nodes\n',
                        _branchcachedesc(repo), len(self._entries), nodecount)
        except (IOError, OSError, error.Abort) as inst:
            # Abort may be raised by read only opener, so log and continue
            repo.ui.debug("couldn't write branch cache: %s\n" %
                          stringutil.forcebytestr(inst))

    def update(self, repo, revgen):
        """Given a branchhead cache, self, that may have extra nodes or be
        missing heads, and a generator of nodes that are strictly a superset of
        heads missing, this function updates self to be correct.

                    self.tipnode = cl.node(tiprev)
                    self.tiprev = tiprev
        self.filteredhash = scmutil.filteredhash(repo, self.tiprev)

        duration = util.timer() - starttime
        repo.ui.log('branchcache', 'updated %s in %.4f seconds\n',
                    _branchcachedesc(repo), duration)

        self.write(repo)


class remotebranchcache(branchcache):
    """Branchmap info for a remote connection, should not write locally"""
    def write(self, repo):
        pass


# Revision branch info cache

_rbcrevs = 'rbc-revs' + _rbcversion
# [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
_rbcrecfmt = '>4sI'
_rbcrecsize = calcsize(_rbcrecfmt)
_rbcnodelen = 4
_rbcbranchidxmask = 0x7fffffff
_rbccloseflag = 0x80000000

class revbranchcache(object):
    """Persistent cache, mapping from revision number to branch name and close.
    This is a low level cache, independent of filtering.

    """

    def __init__(self, repo, readonly=True):
        assert repo.filtername is None
        self._repo = repo
        self._names = [] # branch names in local encoding with static index
        self._rbcrevs = bytearray()
        self._rbcsnameslen = 0 # length of names read at _rbcsnameslen
        try:
            bndata = repo.cachevfs.read(_rbcnames)
            self._rbcsnameslen = len(bndata) # for verification before writing
            if bndata:
                self._names = [encoding.tolocal(bn)
                               for bn in bndata.split('\0')]
        except (IOError, OSError):
            if readonly:
                # don't try to use cache - fall back to the slow path
                self.branchinfo = self._branchinfo

        if self._names:
            try:
                data = repo.cachevfs.read(_rbcrevs)
                self._rbcrevs[:] = data
            except (IOError, OSError) as inst:
                repo.ui.debug("couldn't read revision branch cache: %s\n" %
                              stringutil.forcebytestr(inst))
        # remember number of good records on disk
        self._rbcrevslen = min(len(self._rbcrevs) // _rbcrecsize,
                               len(repo.changelog))
        if self._rbcrevslen == 0:
            self._names = []
        self._rbcnamescount = len(self._names) # number of names read at
                                               # _rbcsnameslen

    def _clear(self):
        self._rbcsnameslen = 0
        del self._names[:]
        self._rbcnamescount = 0

            return self._branchinfo(rev)

        # fast path: extract data from cache, use it if node is matching
        reponode = changelog.node(rev)[:_rbcnodelen]
        cachenode, branchidx = unpack_from(
            _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx)
        close = bool(branchidx & _rbccloseflag)
        if close:
            branchidx &= _rbcbranchidxmask
        if cachenode == '\0\0\0\0':
            pass
        elif cachenode == reponode:
            try:
                return self._names[branchidx], close
            except IndexError:
                # recover from invalid reference to unknown branch
                self._repo.ui.debug("referenced branch names not found"
                    " - rebuilding revision branch cache from scratch\n")
                self._clear()
        else:
            # rev/node map has changed, invalidate the cache from here up
            self._repo.ui.debug("history modification detected - truncating "
                "revision branch cache to revision %d\n" % rev)
            truncate = rbcrevidx + _rbcrecsize
            del self._rbcrevs[truncate:]
            self._rbcrevslen = min(self._rbcrevslen, truncate)

        # fall back to slow path and make sure it will be written to disk

        """Writes the node's branch data to the in-memory cache data."""
        if rev == nullrev:
            return
        rbcrevidx = rev * _rbcrecsize
        if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
            self._rbcrevs.extend('\0' *
                                 (len(self._repo.changelog) * _rbcrecsize -
                                  len(self._rbcrevs)))
        pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
        self._rbcrevslen = min(self._rbcrevslen, rev)

        tr = self._repo.currenttransaction()
        if tr:

                if wlock is None:
                    wlock = repo.wlock(wait=False)
                self._writerevs(repo, start)

        except (IOError, OSError, error.Abort, error.LockError) as inst:
            repo.ui.debug("couldn't write revision branch cache%s: %s\n"
                          % (step, stringutil.forcebytestr(inst)))
        finally:
            if wlock is not None:
                wlock.release()

    def _writenames(self, repo):

                self._rbcrevslen = 0
        if self._rbcnamescount == 0:
            # before rewriting names, make sure references are removed
            repo.cachevfs.unlinkpath(_rbcrevs, ignoremissing=True)
            f = repo.cachevfs.open(_rbcnames, 'wb')
        f.write('\0'.join(encoding.fromlocal(b)
                          for b in self._names[self._rbcnamescount:]))
        self._rbcsnameslen = f.tell()
        f.close()
        self._rbcnamescount = len(self._names)

    def _writerevs(self, repo, start):

43076:2372284d9457

from .utils import (
    repoviewutil,
    stringutil,
)

subsettable = repoviewutil.subsettable

calcsize = struct.calcsize
pack_into = struct.pack_into
unpack_from = struct.unpack_from


class BranchMapCache(object):
    """mapping of filtered views of repo with their branchcache"""

    def __init__(self):
        self._per_filter = {}

    def __getitem__(self, repo):
        self.updatecache(repo)

                    closed.append(h)

        if rbheads:
            rtiprev = max((int(clrev(node)) for node in rbheads))
            cache = branchcache(
                remotebranchmap,
                repo[rtiprev].node(),
                rtiprev,
                closednodes=closed,
            )

            # Try to stick it as low as possible
            # filter above served are unlikely to be fetch from a clone
            for candidate in ('base', 'immutable', 'served'):
                rview = repo.filtered(candidate)

                    return

    def clear(self):
        self._per_filter.clear()


def _unknownnode(node):
    """ raises ValueError when branchcache found a node which does not exists
    """
    raise ValueError(r'node %s does not exist' % pycompat.sysstr(hex(node)))


def _branchcachedesc(repo):
    if repo.filtername is not None:
        return 'branch cache (%s)' % repo.filtername
    else:
        return 'branch cache'


class branchcache(object):
    """A dict like object that hold branches heads cache.

    This cache is used to avoid costly computations to determine all the
    branch heads of a repo.

    The open/closed state is represented by a single letter 'o' or 'c'.
    This field can be used to avoid changelog reads when determining if a
    branch head closes a branch or not.
    """

    def __init__(
        self,
        entries=(),
        tipnode=nullid,
        tiprev=nullrev,
        filteredhash=None,
        closednodes=None,
        hasnode=None,
    ):
        """ hasnode is a function which can be used to verify whether changelog
        has a given node or not. If it's not provided, we assume that every node
        we have exists in changelog """
        self.tipnode = tipnode
        self.tiprev = tiprev

            last, lrev = bin(last), int(lrev)
            filteredhash = None
            hasnode = repo.changelog.hasnode
            if len(cachekey) > 2:
                filteredhash = bin(cachekey[2])
            bcache = cls(
                tipnode=last,
                tiprev=lrev,
                filteredhash=filteredhash,
                hasnode=hasnode,
            )
            if not bcache.validfor(repo):
                # invalidate the cache
                raise ValueError(r'tip differs')
            bcache.load(repo, lineiter)
        except (IOError, OSError):
            return None

        except Exception as inst:
            if repo.ui.debugflag:
                msg = 'invalid %s: %s\n'
                repo.ui.debug(
                    msg % (_branchcachedesc(repo), pycompat.bytestr(inst))
                )
            bcache = None

        finally:
            if f:
                f.close()

        """Is the cache content valid regarding a repo

        - False when cached tipnode is unknown or if we detect a strip.
        - True when cache is up to date or a subset of current repo."""
        try:
            return (self.tipnode == repo.changelog.node(self.tiprev)) and (
                self.filteredhash == scmutil.filteredhash(repo, self.tiprev)
            )
        except IndexError:
            return False

    def _branchtip(self, heads):
        '''Return tuple with last open head in heads and false,

        return self._entries.itervalues()

    def copy(self):
        """return an deep copy of the branchcache object"""
        return type(self)(
            self._entries,
            self.tipnode,
            self.tiprev,
            self.filteredhash,
            self._closednodes,
        )

    def write(self, repo):
        try:
            f = repo.cachevfs(self._filename(repo), "w", atomictemp=True)
            cachekey = [hex(self.tipnode), '%d' % self.tiprev]

                        state = 'c'
                    else:
                        state = 'o'
                    f.write("%s %s %s\n" % (hex(node), state, label))
            f.close()
            repo.ui.log(
                'branchcache',
                'wrote %s with %d labels and %d nodes\n',
                _branchcachedesc(repo),
                len(self._entries),
                nodecount,
            )
        except (IOError, OSError, error.Abort) as inst:
            # Abort may be raised by read only opener, so log and continue
            repo.ui.debug(
                "couldn't write branch cache: %s\n"
                % stringutil.forcebytestr(inst)
            )

    def update(self, repo, revgen):
        """Given a branchhead cache, self, that may have extra nodes or be
        missing heads, and a generator of nodes that are strictly a superset of
        heads missing, this function updates self to be correct.

                    self.tipnode = cl.node(tiprev)
                    self.tiprev = tiprev
        self.filteredhash = scmutil.filteredhash(repo, self.tiprev)

        duration = util.timer() - starttime
        repo.ui.log(
            'branchcache',
            'updated %s in %.4f seconds\n',
            _branchcachedesc(repo),
            duration,
        )

        self.write(repo)


class remotebranchcache(branchcache):
    """Branchmap info for a remote connection, should not write locally"""

    def write(self, repo):
        pass


# Revision branch info cache

_rbcrevs = 'rbc-revs' + _rbcversion
# [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
_rbcrecfmt = '>4sI'
_rbcrecsize = calcsize(_rbcrecfmt)
_rbcnodelen = 4
_rbcbranchidxmask = 0x7FFFFFFF
_rbccloseflag = 0x80000000


class revbranchcache(object):
    """Persistent cache, mapping from revision number to branch name and close.
    This is a low level cache, independent of filtering.

    """

    def __init__(self, repo, readonly=True):
        assert repo.filtername is None
        self._repo = repo
        self._names = []  # branch names in local encoding with static index
        self._rbcrevs = bytearray()
        self._rbcsnameslen = 0  # length of names read at _rbcsnameslen
        try:
            bndata = repo.cachevfs.read(_rbcnames)
            self._rbcsnameslen = len(bndata)  # for verification before writing
            if bndata:
                self._names = [
                    encoding.tolocal(bn) for bn in bndata.split('\0')
                ]
        except (IOError, OSError):
            if readonly:
                # don't try to use cache - fall back to the slow path
                self.branchinfo = self._branchinfo

        if self._names:
            try:
                data = repo.cachevfs.read(_rbcrevs)
                self._rbcrevs[:] = data
            except (IOError, OSError) as inst:
                repo.ui.debug(
                    "couldn't read revision branch cache: %s\n"
                    % stringutil.forcebytestr(inst)
                )
        # remember number of good records on disk
        self._rbcrevslen = min(
            len(self._rbcrevs) // _rbcrecsize, len(repo.changelog)
        )
        if self._rbcrevslen == 0:
            self._names = []
        self._rbcnamescount = len(self._names)  # number of names read at
        # _rbcsnameslen

    def _clear(self):
        self._rbcsnameslen = 0
        del self._names[:]
        self._rbcnamescount = 0

            return self._branchinfo(rev)

        # fast path: extract data from cache, use it if node is matching
        reponode = changelog.node(rev)[:_rbcnodelen]
        cachenode, branchidx = unpack_from(
            _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx
        )
        close = bool(branchidx & _rbccloseflag)
        if close:
            branchidx &= _rbcbranchidxmask
        if cachenode == '\0\0\0\0':
            pass
        elif cachenode == reponode:
            try:
                return self._names[branchidx], close
            except IndexError:
                # recover from invalid reference to unknown branch
                self._repo.ui.debug(
                    "referenced branch names not found"
                    " - rebuilding revision branch cache from scratch\n"
                )
                self._clear()
        else:
            # rev/node map has changed, invalidate the cache from here up
            self._repo.ui.debug(
                "history modification detected - truncating "
                "revision branch cache to revision %d\n" % rev
            )
            truncate = rbcrevidx + _rbcrecsize
            del self._rbcrevs[truncate:]
            self._rbcrevslen = min(self._rbcrevslen, truncate)

        # fall back to slow path and make sure it will be written to disk

        """Writes the node's branch data to the in-memory cache data."""
        if rev == nullrev:
            return
        rbcrevidx = rev * _rbcrecsize
        if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
            self._rbcrevs.extend(
                '\0'
                * (len(self._repo.changelog) * _rbcrecsize - len(self._rbcrevs))
            )
        pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
        self._rbcrevslen = min(self._rbcrevslen, rev)

        tr = self._repo.currenttransaction()
        if tr:

                if wlock is None:
                    wlock = repo.wlock(wait=False)
                self._writerevs(repo, start)

        except (IOError, OSError, error.Abort, error.LockError) as inst:
            repo.ui.debug(
                "couldn't write revision branch cache%s: %s\n"
                % (step, stringutil.forcebytestr(inst))
            )
        finally:
            if wlock is not None:
                wlock.release()

    def _writenames(self, repo):

                self._rbcrevslen = 0
        if self._rbcnamescount == 0:
            # before rewriting names, make sure references are removed
            repo.cachevfs.unlinkpath(_rbcrevs, ignoremissing=True)
            f = repo.cachevfs.open(_rbcnames, 'wb')
        f.write(
            '\0'.join(
                encoding.fromlocal(b)
                for b in self._names[self._rbcnamescount :]
            )
        )
        self._rbcsnameslen = f.tell()
        f.close()
        self._rbcnamescount = len(self._names)

    def _writerevs(self, repo, start):