hgext/remotefilelog/remotefilectx.py

43075:57875cf423c9

from . import shallowutil

propertycache = util.propertycache
FASTLOG_TIMEOUT_IN_SECS = 0.5

class remotefilectx(context.filectx):
    def __init__(self, repo, path, changeid=None, fileid=None,
                 filelog=None, changectx=None, ancestormap=None):
        if fileid == nullrev:
            fileid = nullid
        if fileid and len(fileid) == 40:
            fileid = bin(fileid)
        super(remotefilectx, self).__init__(repo, path, changeid,
            fileid, filelog, changectx)
        self._ancestormap = ancestormap

    def size(self):
        return self._filelog.size(self._filenode)

        elif r'_changectx' in self.__dict__:
            return self._changectx.rev()
        elif r'_descendantrev' in self.__dict__:
            # this file context was created from a revision with a known
            # descendant, we can (lazily) correct for linkrev aliases
            linknode = self._adjustlinknode(self._path, self._filelog,
                                            self._filenode, self._descendantrev)
            return self._repo.unfiltered().changelog.rev(linknode)
        else:
            return self.linkrev()

    def filectx(self, fileid, changeid=None):
        '''opens an arbitrary revision of the file without
        opening a new filelog'''
        return remotefilectx(self._repo, self._path, fileid=fileid,
                             filelog=self._filelog, changeid=changeid)

    def linkrev(self):
        return self._linkrev

    @propertycache

        cl = self._repo.unfiltered().changelog
        mfl = self._repo.manifestlog

        for rev in range(len(cl) - 1, 0, -1):
            node = cl.node(rev)
            data = cl.read(node) # get changeset data (we avoid object creation)
            if path in data[3]: # checking the 'files' field.
                # The file has been touched, check if the hash is what we're
                # looking for.
                if fileid == mfl[data[0]].readfast().get(path):
                    return rev

        lkr = self.linkrev()
        attrs = vars(self)
        noctx = not (r'_changeid' in attrs or r'_changectx' in attrs)
        if noctx or self.rev() == lkr:
            return lkr
        linknode = self._adjustlinknode(self._path, self._filelog,
                                        self._filenode, self.rev(),
                                        inclusive=True)
        return self._repo.changelog.rev(linknode)

    def renamed(self):
        """check if file was actually renamed in this changeset revision

        p1, p2, linknode, copyfrom = ancestormap[self._filenode]
        results = []
        if p1 != nullid:
            path = copyfrom or self._path
            flog = repo.file(path)
            p1ctx = remotefilectx(repo, path, fileid=p1, filelog=flog,
                                  ancestormap=ancestormap)
            p1ctx._descendantrev = self.rev()
            results.append(p1ctx)

        if p2 != nullid:
            path = self._path
            flog = repo.file(path)
            p2ctx = remotefilectx(repo, path, fileid=p2, filelog=flog,
                                  ancestormap=ancestormap)
            p2ctx._descendantrev = self.rev()
            results.append(p2ctx)

        return results

    def _nodefromancrev(self, ancrev, cl, mfl, path, fnode):
        """returns the node for <path> in <ancrev> if content matches <fnode>"""
        ancctx = cl.read(ancrev) # This avoids object creation.
        manifestnode, files = ancctx[0], ancctx[3]
        # If the file was touched in this ancestor, and the content is similar
        # to the one we are searching for.
        if path in files and fnode == mfl[manifestnode].readfast().get(path):
            return cl.node(ancrev)

        linknode = ancestormap[fnode][2]

        if srcrev is None:
            # wctx case, used by workingfilectx during mergecopy
            revs = [p.rev() for p in self._repo[None].parents()]
            inclusive = True # we skipped the real (revless) source
        else:
            revs = [srcrev]

        if self._verifylinknode(revs, linknode):
            return linknode

            # prefetch
            if not seenpublic and pc.phase(repo, ancrev) == phases.public:
                # TODO: there used to be a codepath to fetch linknodes
                # from a server as a fast path, but it appeared to
                # depend on an API FB added to their phabricator.
                lnode = self._forceprefetch(repo, path, fnode, revs,
                                            commonlogkwargs)
                if lnode:
                    return lnode
                seenpublic = True

        return linknode

    def _forceprefetch(self, repo, path, fnode, revs,
                       commonlogkwargs):
        # This next part is super non-obvious, so big comment block time!
        #
        # It is possible to get extremely bad performance here when a fairly
        # common set of circumstances occur when this extension is combined
        # with a server-side commit rewriting extension like pushrebase.

            # Now that we've downloaded a new blob from the server,
            # we need to rebuild the ancestor map to recompute the
            # linknodes.
            self._ancestormap = None
            linknode = self.ancestormap()[fnode][2] # 2 is linknode
            if self._verifylinknode(revs, linknode):
                logmsg = 'remotefilelog prefetching succeeded'
                return linknode
            logmsg = 'remotefilelog prefetching not found'
            return None
        except Exception as e:
            logmsg = 'remotefilelog prefetching failed (%s)' % e
            return None
        finally:
            elapsed = time.time() - start
            repo.ui.log('linkrevfixup', logmsg + '\n', elapsed=elapsed * 1000,
                        **commonlogkwargs)

    def _verifylinknode(self, revs, linknode):
        """
        Check if a linknode is correct one for the current history.

        # Remove self
        ancestors.pop(0)

        # Sort by linkrev
        # The copy tracing algorithm depends on these coming out in order
        ancestors = sorted(ancestors, reverse=True, key=lambda x:x.linkrev())

        for ancestor in ancestors:
            yield ancestor

    def ancestor(self, fc2, actx):

        a = (self.path(), self.filenode())
        b = (fc2.path(), fc2.filenode())
        result = ancestor.genericancestor(a, b, parents)
        if result:
            f, n = result
            r = remotefilectx(self._repo, f, fileid=n,
                                 ancestormap=amap)
            return r

        return None

    def annotate(self, *args, **kwargs):

        prefetchskip = kwargs.pop(r'prefetchskip', None)
        if prefetchskip:
            # use introrev so prefetchskip can be accurately tested
            introrev = self.introrev()
            if self.rev() != introrev:
                introctx = remotefilectx(self._repo, self._path,
                                         changeid=introrev,
                                         fileid=self._filenode,
                                         filelog=self._filelog,
                                         ancestormap=self._ancestormap)

        # like self.ancestors, but append to "fetch" and skip visiting parents
        # of nodes in "prefetchskip".
        fetch = []
        seen = set()

            for parent in current.parents():
                if parent.node() not in seen:
                    seen.add(parent.node())
                    queue.append(parent)

        self._repo.ui.debug('remotefilelog: prefetching %d files '
                            'for annotate\n' % len(fetch))
        if fetch:
            self._repo.fileservice.prefetch(fetch)
        return super(remotefilectx, self).annotate(*args, **kwargs)

    # Return empty set so that the hg serve and thg don't stack trace
    def children(self):
        return []

class remoteworkingfilectx(context.workingfilectx, remotefilectx):
    def __init__(self, repo, path, filelog=None, workingctx=None):
        self._ancestormap = None
        super(remoteworkingfilectx, self).__init__(repo, path, filelog,
                                                   workingctx)

    def parents(self):
        return remotefilectx.parents(self)

    def ancestormap(self):

43076:2372284d9457

from . import shallowutil

propertycache = util.propertycache
FASTLOG_TIMEOUT_IN_SECS = 0.5


class remotefilectx(context.filectx):
    def __init__(
        self,
        repo,
        path,
        changeid=None,
        fileid=None,
        filelog=None,
        changectx=None,
        ancestormap=None,
    ):
        if fileid == nullrev:
            fileid = nullid
        if fileid and len(fileid) == 40:
            fileid = bin(fileid)
        super(remotefilectx, self).__init__(
            repo, path, changeid, fileid, filelog, changectx
        )
        self._ancestormap = ancestormap

    def size(self):
        return self._filelog.size(self._filenode)

        elif r'_changectx' in self.__dict__:
            return self._changectx.rev()
        elif r'_descendantrev' in self.__dict__:
            # this file context was created from a revision with a known
            # descendant, we can (lazily) correct for linkrev aliases
            linknode = self._adjustlinknode(
                self._path, self._filelog, self._filenode, self._descendantrev
            )
            return self._repo.unfiltered().changelog.rev(linknode)
        else:
            return self.linkrev()

    def filectx(self, fileid, changeid=None):
        '''opens an arbitrary revision of the file without
        opening a new filelog'''
        return remotefilectx(
            self._repo,
            self._path,
            fileid=fileid,
            filelog=self._filelog,
            changeid=changeid,
        )

    def linkrev(self):
        return self._linkrev

    @propertycache

        cl = self._repo.unfiltered().changelog
        mfl = self._repo.manifestlog

        for rev in range(len(cl) - 1, 0, -1):
            node = cl.node(rev)
            data = cl.read(
                node
            )  # get changeset data (we avoid object creation)
            if path in data[3]:  # checking the 'files' field.
                # The file has been touched, check if the hash is what we're
                # looking for.
                if fileid == mfl[data[0]].readfast().get(path):
                    return rev

        lkr = self.linkrev()
        attrs = vars(self)
        noctx = not (r'_changeid' in attrs or r'_changectx' in attrs)
        if noctx or self.rev() == lkr:
            return lkr
        linknode = self._adjustlinknode(
            self._path,
            self._filelog,
            self._filenode,
            self.rev(),
            inclusive=True,
        )
        return self._repo.changelog.rev(linknode)

    def renamed(self):
        """check if file was actually renamed in this changeset revision

        p1, p2, linknode, copyfrom = ancestormap[self._filenode]
        results = []
        if p1 != nullid:
            path = copyfrom or self._path
            flog = repo.file(path)
            p1ctx = remotefilectx(
                repo, path, fileid=p1, filelog=flog, ancestormap=ancestormap
            )
            p1ctx._descendantrev = self.rev()
            results.append(p1ctx)

        if p2 != nullid:
            path = self._path
            flog = repo.file(path)
            p2ctx = remotefilectx(
                repo, path, fileid=p2, filelog=flog, ancestormap=ancestormap
            )
            p2ctx._descendantrev = self.rev()
            results.append(p2ctx)

        return results

    def _nodefromancrev(self, ancrev, cl, mfl, path, fnode):
        """returns the node for <path> in <ancrev> if content matches <fnode>"""
        ancctx = cl.read(ancrev)  # This avoids object creation.
        manifestnode, files = ancctx[0], ancctx[3]
        # If the file was touched in this ancestor, and the content is similar
        # to the one we are searching for.
        if path in files and fnode == mfl[manifestnode].readfast().get(path):
            return cl.node(ancrev)

        linknode = ancestormap[fnode][2]

        if srcrev is None:
            # wctx case, used by workingfilectx during mergecopy
            revs = [p.rev() for p in self._repo[None].parents()]
            inclusive = True  # we skipped the real (revless) source
        else:
            revs = [srcrev]

        if self._verifylinknode(revs, linknode):
            return linknode

            # prefetch
            if not seenpublic and pc.phase(repo, ancrev) == phases.public:
                # TODO: there used to be a codepath to fetch linknodes
                # from a server as a fast path, but it appeared to
                # depend on an API FB added to their phabricator.
                lnode = self._forceprefetch(
                    repo, path, fnode, revs, commonlogkwargs
                )
                if lnode:
                    return lnode
                seenpublic = True

        return linknode

    def _forceprefetch(self, repo, path, fnode, revs, commonlogkwargs):
        # This next part is super non-obvious, so big comment block time!
        #
        # It is possible to get extremely bad performance here when a fairly
        # common set of circumstances occur when this extension is combined
        # with a server-side commit rewriting extension like pushrebase.

            # Now that we've downloaded a new blob from the server,
            # we need to rebuild the ancestor map to recompute the
            # linknodes.
            self._ancestormap = None
            linknode = self.ancestormap()[fnode][2]  # 2 is linknode
            if self._verifylinknode(revs, linknode):
                logmsg = 'remotefilelog prefetching succeeded'
                return linknode
            logmsg = 'remotefilelog prefetching not found'
            return None
        except Exception as e:
            logmsg = 'remotefilelog prefetching failed (%s)' % e
            return None
        finally:
            elapsed = time.time() - start
            repo.ui.log(
                'linkrevfixup',
                logmsg + '\n',
                elapsed=elapsed * 1000,
                **commonlogkwargs
            )

    def _verifylinknode(self, revs, linknode):
        """
        Check if a linknode is correct one for the current history.

        # Remove self
        ancestors.pop(0)

        # Sort by linkrev
        # The copy tracing algorithm depends on these coming out in order
        ancestors = sorted(ancestors, reverse=True, key=lambda x: x.linkrev())

        for ancestor in ancestors:
            yield ancestor

    def ancestor(self, fc2, actx):

        a = (self.path(), self.filenode())
        b = (fc2.path(), fc2.filenode())
        result = ancestor.genericancestor(a, b, parents)
        if result:
            f, n = result
            r = remotefilectx(self._repo, f, fileid=n, ancestormap=amap)
            return r

        return None

    def annotate(self, *args, **kwargs):

        prefetchskip = kwargs.pop(r'prefetchskip', None)
        if prefetchskip:
            # use introrev so prefetchskip can be accurately tested
            introrev = self.introrev()
            if self.rev() != introrev:
                introctx = remotefilectx(
                    self._repo,
                    self._path,
                    changeid=introrev,
                    fileid=self._filenode,
                    filelog=self._filelog,
                    ancestormap=self._ancestormap,
                )

        # like self.ancestors, but append to "fetch" and skip visiting parents
        # of nodes in "prefetchskip".
        fetch = []
        seen = set()

            for parent in current.parents():
                if parent.node() not in seen:
                    seen.add(parent.node())
                    queue.append(parent)

        self._repo.ui.debug(
            'remotefilelog: prefetching %d files ' 'for annotate\n' % len(fetch)
        )
        if fetch:
            self._repo.fileservice.prefetch(fetch)
        return super(remotefilectx, self).annotate(*args, **kwargs)

    # Return empty set so that the hg serve and thg don't stack trace
    def children(self):
        return []


class remoteworkingfilectx(context.workingfilectx, remotefilectx):
    def __init__(self, repo, path, filelog=None, workingctx=None):
        self._ancestormap = None
        super(remoteworkingfilectx, self).__init__(
            repo, path, filelog, workingctx
        )

    def parents(self):
        return remotefilectx.parents(self)

    def ancestormap(self):