view mercurial/namespaces.py @ 26117:4dc5b51f38fe

revlog: change generaldelta delta parent heuristic The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text, use it, otherwise use prev". This was problematic when a repo contained multiple branches that were very different. If commits to branch A were pushed, and the last full text was branch B, it would generate a fulltext. Then if branch B was pushed, it would generate another fulltext. The problem is that the last fulltext (and delta'ing against `prev` in general) has no correlation with the contents of the incoming revision, and therefore will always have degenerate cases. According to the blame, that algorithm was chosen to minimize the chain length. Since there is already code that protects against that (the delta-vs-fulltext code), and since it has been improved since the original generaldelta algorithm went in (2011), I believe the chain length criteria will still be preserved. The new algorithm always diffs against p1 (or p2 if it's closer), unless the resulting delta will fail the delta-vs-fulltext check, in which case we delta against prev. Some before and after stats on manifest.d size. internal large repo old heuristic - 2.0 GB new heuristic - 1.2 GB mozilla-central old heuristic - 242 MB new heuristic - 261 MB The regression in mozilla central is due to the new heuristic choosing p2r as the delta when it's closer to the tip. Switching the algorithm to always prefer p1r brings the size back down (242 MB). This is result of the way in which mozilla does merges and pushes, and the result could easily swing the other direction in other repos (depending on if they merge X into Y or Y into X), but will never be as degenerate as before. I future patch will address the regression by introducing an optional, even more aggressive delta heuristic which will knock the mozilla manifest size down dramatically.
author Durham Goode <durham@fb.com>
date Sun, 30 Aug 2015 13:58:11 -0700
parents c0c89b2d07be
children ca52512ac709
line wrap: on
line source

from __future__ import absolute_import

from .i18n import _
from . import (
    templatekw,
    util,
)

def tolist(val):
    """
    a convenience method to return an empty list instead of None
    """
    if val is None:
        return []
    else:
        return [val]

class namespaces(object):
    """provides an interface to register and operate on multiple namespaces. See
    the namespace class below for details on the namespace object.

    """

    _names_version = 0

    def __init__(self):
        self._names = util.sortdict()

        # we need current mercurial named objects (bookmarks, tags, and
        # branches) to be initialized somewhere, so that place is here
        bmknames = lambda repo: repo._bookmarks.keys()
        bmknamemap = lambda repo, name: tolist(repo._bookmarks.get(name))
        bmknodemap = lambda repo, name: repo.nodebookmarks(name)
        n = namespace("bookmarks", templatename="bookmark",
                      # i18n: column positioning for "hg log"
                      logfmt=_("bookmark:    %s\n"),
                      listnames=bmknames,
                      namemap=bmknamemap, nodemap=bmknodemap)
        self.addnamespace(n)

        tagnames = lambda repo: [t for t, n in repo.tagslist()]
        tagnamemap = lambda repo, name: tolist(repo._tagscache.tags.get(name))
        tagnodemap = lambda repo, name: repo.nodetags(name)
        n = namespace("tags", templatename="tag",
                      # i18n: column positioning for "hg log"
                      logfmt=_("tag:         %s\n"),
                      listnames=tagnames,
                      namemap=tagnamemap, nodemap=tagnodemap,
                      deprecated=set(['tip']))
        self.addnamespace(n)

        bnames = lambda repo: repo.branchmap().keys()
        bnamemap = lambda repo, name: tolist(repo.branchtip(name, True))
        bnodemap = lambda repo, node: [repo[node].branch()]
        n = namespace("branches", templatename="branch",
                      # i18n: column positioning for "hg log"
                      logfmt=_("branch:      %s\n"),
                      listnames=bnames,
                      namemap=bnamemap, nodemap=bnodemap)
        self.addnamespace(n)

    def __getitem__(self, namespace):
        """returns the namespace object"""
        return self._names[namespace]

    def __iter__(self):
        return self._names.__iter__()

    def iteritems(self):
        return self._names.iteritems()

    def addnamespace(self, namespace, order=None):
        """register a namespace

        namespace: the name to be registered (in plural form)
        order: optional argument to specify the order of namespaces
               (e.g. 'branches' should be listed before 'bookmarks')

        """
        if order is not None:
            self._names.insert(order, namespace.name, namespace)
        else:
            self._names[namespace.name] = namespace

        # we only generate a template keyword if one does not already exist
        if namespace.name not in templatekw.keywords:
            def generatekw(**args):
                return templatekw.shownames(namespace.name, **args)

            templatekw.keywords[namespace.name] = generatekw

    def singlenode(self, repo, name):
        """
        Return the 'best' node for the given name. Best means the first node
        in the first nonempty list returned by a name-to-nodes mapping function
        in the defined precedence order.

        Raises a KeyError if there is no such node.
        """
        for ns, v in self._names.iteritems():
            n = v.namemap(repo, name)
            if n:
                # return max revision number
                if len(n) > 1:
                    cl = repo.changelog
                    maxrev = max(cl.rev(node) for node in n)
                    return cl.node(maxrev)
                return n[0]
        raise KeyError(_('no such name: %s') % name)

class namespace(object):
    """provides an interface to a namespace

    Namespaces are basically generic many-to-many mapping between some
    (namespaced) names and nodes. The goal here is to control the pollution of
    jamming things into tags or bookmarks (in extension-land) and to simplify
    internal bits of mercurial: log output, tab completion, etc.

    More precisely, we define a mapping of names to nodes, and a mapping from
    nodes to names. Each mapping returns a list.

    Furthermore, each name mapping will be passed a name to lookup which might
    not be in its domain. In this case, each method should return an empty list
    and not raise an error.

    This namespace object will define the properties we need:
      'name': the namespace (plural form)
      'templatename': name to use for templating (usually the singular form
                      of the plural namespace name)
      'listnames': list of all names in the namespace (usually the keys of a
                   dictionary)
      'namemap': function that takes a name and returns a list of nodes
      'nodemap': function that takes a node and returns a list of names
      'deprecated': set of names to be masked for ordinary use

    """

    def __init__(self, name, templatename=None, logname=None, colorname=None,
                 logfmt=None, listnames=None, namemap=None, nodemap=None,
                 deprecated=None):
        """create a namespace

        name: the namespace to be registered (in plural form)
        templatename: the name to use for templating
        logname: the name to use for log output; if not specified templatename
                 is used
        colorname: the name to use for colored log output; if not specified
                   logname is used
        logfmt: the format to use for (i18n-ed) log output; if not specified
                it is composed from logname
        listnames: function to list all names
        namemap: function that inputs a node, output name(s)
        nodemap: function that inputs a name, output node(s)
        deprecated: set of names to be masked for ordinary use

        """
        self.name = name
        self.templatename = templatename
        self.logname = logname
        self.colorname = colorname
        self.logfmt = logfmt
        self.listnames = listnames
        self.namemap = namemap
        self.nodemap = nodemap

        # if logname is not specified, use the template name as backup
        if self.logname is None:
            self.logname = self.templatename

        # if colorname is not specified, just use the logname as a backup
        if self.colorname is None:
            self.colorname = self.logname

        # if logfmt is not specified, compose it from logname as backup
        if self.logfmt is None:
            # i18n: column positioning for "hg log"
            self.logfmt = ("%s:" % self.logname).ljust(13) + "%s\n"

        if deprecated is None:
            self.deprecated = set()
        else:
            self.deprecated = deprecated

    def names(self, repo, node):
        """method that returns a (sorted) list of names in a namespace that
        match a given node"""
        return sorted(self.nodemap(repo, node))

    def nodes(self, repo, name):
        """method that returns a list of nodes in a namespace that
        match a given name.

        """
        return sorted(self.namemap(repo, name))