view mercurial/namespaces.py @ 32532:e4f514627514

perf: benchmark command for revlog indexes

We didn't have explicit microbenchmark coverage for loading revlog
indexes. That seems like a useful thing to have, so let's add it.

We currently measure the low-level nodemap APIs. There is room to
hook in at the actual revlog layer. This could be done as a follow-up.

The hackiest thing about this patch is specifying revlog paths.
Other commands have arguments that allow resolution of changelog,
manifest, and filelog. I needed to hook in at a lower level of
the revlog API than what the existing helper functions to resolve
revlogs allowed. I was too lazy to write some new APIs. This could
be done as a follow-up easily enough.

Example output for `hg perfrevlogindex 00changelog.i` on my
Firefox repo (404418 revisions):

! revlog constructor
! wall 0.003106 comb 0.000000 user 0.000000 sys 0.000000 (best of 912)
! read
! wall 0.003077 comb 0.000000 user 0.000000 sys 0.000000 (best of 924)
! create index object
! wall 0.000000 comb 0.000000 user 0.000000 sys 0.000000 (best of 1803994)
! retrieve index entry for rev 0
! wall 0.000193 comb 0.000000 user 0.000000 sys 0.000000 (best of 14037)
! look up missing node
! wall 0.003313 comb 0.000000 user 0.000000 sys 0.000000 (best of 865)
! look up node at rev 0
! wall 0.003295 comb 0.010000 user 0.010000 sys 0.000000 (best of 858)
! look up node at 1/4 len
! wall 0.002598 comb 0.010000 user 0.010000 sys 0.000000 (best of 1103)
! look up node at 1/2 len
! wall 0.001909 comb 0.000000 user 0.000000 sys 0.000000 (best of 1507)
! look up node at 3/4 len
! wall 0.001213 comb 0.000000 user 0.000000 sys 0.000000 (best of 2275)
! look up node at tip
! wall 0.000453 comb 0.000000 user 0.000000 sys 0.000000 (best of 5697)
! look up all nodes (forward)
! wall 0.094615 comb 0.100000 user 0.100000 sys 0.000000 (best of 100)
! look up all nodes (reverse)
! wall 0.045889 comb 0.050000 user 0.050000 sys 0.000000 (best of 100)
! retrieve all index entries (forward)
! wall 0.078398 comb 0.080000 user 0.060000 sys 0.020000 (best of 100)
! retrieve all index entries (reverse)
! wall 0.079376 comb 0.080000 user 0.070000 sys 0.010000 (best of 100)

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, node: repo.nodebookmarks(node)
        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, node: repo.nodetags(node)
        n = namespace("tags", templatename="tag",
                      # i18n: column positioning for "hg log"
                      logfmt=_("tag:         %s\n"),
                      listnames=tagnames,
                      namemap=tagnamemap, nodemap=tagnodemap,
                      deprecated={'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 name, output node(s)
        nodemap: function that inputs a node, output name(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))