##// END OF EJS Templates
match: match explicit file using a set...
match: match explicit file using a set The matcher as all the logic to do quick comparison against explicit patterns, however the pattern matcher was shadowing the code using that set and used the compiled regex pattern in all cases, which is quite slow. We restore the usage of the set based matching to boost performance. Building the regexp is still consuming a large amount of time (actually, the majority of the time), which is still silly. Maybe using re2 would help that, but this is a quest for another adventure. Another path to improve this is to have a pattern type dedicated to match the exact path to a file only (not a directory). This pattern could use the set matching only and be skipped in the regex all together. Benchmarks ========== In the following benchmark we are comparing the `hg cat` and `hg files` run time when matching against all files in the repository. They are run: - without the rust extensions - with the standard python engine (so without re2) Performance improvement in this series -------------------------------------- ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.230092 seconds prev-changeset: 0.230069 seconds this-changeset: 0.211425 seconds (-8.36%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.234235 seconds prev-changeset: 0.231165 seconds (-1.38%) this-changeset: 0.212300 seconds (-9.43%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.613567 seconds prev-changeset: 0.616799 seconds this-changeset: 0.510852 seconds (-16.82%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.801880 seconds prev-changeset: 0.616393 seconds (-23.22%) this-changeset: 0.511903 seconds (-36.23%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 21.541828 seconds prev-changeset: 21.586773 seconds this-changeset: 13.648347 seconds (-36.76%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 172.759857 seconds prev-changeset: 21.908197 seconds (-87.32%) this-changeset: 13.945110 seconds (-91.93%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 62.474221 seconds prev-changeset: 61.279490 seconds (-1.22%) this-changeset: 29.529469 seconds (-52.40%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1364.180218 seconds prev-changeset: 62.473549 seconds (-95.40%) this-changeset: 30.625249 seconds (-97.75%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 0.764407 seconds prev-changeset: 0.763883 seconds this-changeset: 0.737326 seconds (-3.68%) ### mercurial-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 0.768924 seconds prev-changeset: 0.765848 seconds this-changeset: 0.174d0b seconds (-4.44%) ### pypy-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 2.065220 seconds prev-changeset: 2.070498 seconds this-changeset: 1.939482 seconds (-6.08%) ### pypy-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 2.276388 seconds prev-changeset: 2.069197 seconds (-9.15%) this-changeset: 1.931746 seconds (-15.19%) ### netbeans-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 40.967983 seconds prev-changeset: 41.392423 seconds this-changeset: 32.181681 seconds (-22.20%) ### netbeans-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 216.388709 seconds prev-changeset: 41.648689 seconds (-80.88%) this-changeset: 32.580817 seconds (-85.04%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### sorted base-changeset: 105.228510 seconds prev-changeset: 103.315670 seconds (-1.23%) this-changeset: 69.416118 seconds (-33.64%) ### mozilla-central-2018-08-01-zstd-sparse-revlog ### shuffled base-changeset: 1448.722784 seconds prev-changeset: 104.369358 seconds (-92.80%) this-changeset: 70.554789 seconds (-95.13%) Different way to list the same data with this revision ------------------------------------------------------ ###### hg files ############################################################### ### mercurial-2018-08-01-zstd-sparse-revlog root: 0.119182 seconds glob: 0.120697 seconds (+1.27%) sorted: 0.211425 seconds (+77.40%) shuffled: 0.212300 seconds (+78.13%) ### pypy-2018-08-01-zstd-sparse-revlog root: 0.121986 seconds glob: 0.124822 seconds (+2.32%) sorted: 0.510852 seconds (+318.78%) shuffled: 0.511903 seconds (+319.64%) ### netbeans-2018-08-01-zstd-sparse-revlog root: 0.173984 seconds glob: 0.227203 seconds (+30.59%) sorted: 13.648347 seconds (+7744.59%) shuffled: 13.945110 seconds (+7915.16%) ### mozilla-central-2018-08-01-zstd-sparse-revlog root: 0.366463 seconds glob: 0.491030 seconds (+33.99%) sorted: 29.529469 seconds (+7957.96%) shuffled: 30.625249 seconds (+8256.97%) ###### hg cat ################################################################# ### mercurial-2018-08-01-zstd-sparse-revlog glob: 0.647471 seconds root: 0.643120 seconds shuffled: 0.174d0b seconds (+13.92%) sorted: 0.737326 seconds (+13.88%) ### mozilla-central-2018-08-01-zstd-sparse-revlog glob: 40.596983 seconds root: 40.129136 seconds shuffled: 70.554789 seconds (+73.79%) sorted: 69.416118 seconds (+70.99%) ### netbeans-2018-08-01-zstd-sparse-revlog glob: 18.777924 seconds root: 18.613905 seconds shuffled: 32.580817 seconds (+73.51%) sorted: 32.181681 seconds (+71.38%) ### pypy-2018-08-01-zstd-sparse-revlog glob: 1.555319 seconds root: 1.536534 seconds shuffled: 1.931746 seconds (+24.20%) sorted: 1.939482 seconds (+24.70%)

File last commit:

r49801:642e31cb default
r51286:81c7d04f stable
Show More
namespaces.py
242 lines | 8.1 KiB | text/x-python | PythonLexer
from .i18n import _
from . import (
registrar,
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:
"""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()
columns = templatekw.getlogcolumns()
# 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(
b"bookmarks",
templatename=b"bookmark",
logfmt=columns[b'bookmark'],
listnames=bmknames,
namemap=bmknamemap,
nodemap=bmknodemap,
builtin=True,
)
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(
b"tags",
templatename=b"tag",
logfmt=columns[b'tag'],
listnames=tagnames,
namemap=tagnamemap,
nodemap=tagnodemap,
deprecated={b'tip'},
builtin=True,
)
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(
b"branches",
templatename=b"branch",
logfmt=columns[b'branch'],
listnames=bnames,
namemap=bnamemap,
nodemap=bnodemap,
builtin=True,
)
self.addnamespace(n)
def __getitem__(self, namespace):
"""returns the namespace object"""
return self._names[namespace]
def __iter__(self):
return self._names.__iter__()
def get(self, namespace, default=None):
return self._names.get(namespace, default)
def items(self):
return self._names.items()
iteritems = items
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:
templatekeyword = registrar.templatekeyword(templatekw.keywords)
@templatekeyword(namespace.name, requires={b'repo', b'ctx'})
def generatekw(context, mapping):
return templatekw.shownames(context, mapping, namespace.name)
def singlenode(self, repo, name):
"""
Return the 'best' node for the given name. What's best is defined
by the namespace's singlenode() function. The first match returned by
a namespace in the defined precedence order is used.
Raises a KeyError if there is no such node.
"""
for ns, v in self._names.items():
n = v.singlenode(repo, name)
if n:
return n
raise KeyError(_(b'no such name: %s') % name)
class namespace:
"""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
'builtin': bool indicating if this namespace is supported by core
Mercurial.
"""
def __init__(
self,
name,
templatename=None,
logname=None,
colorname=None,
logfmt=None,
listnames=None,
namemap=None,
nodemap=None,
deprecated=None,
builtin=False,
singlenode=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
builtin: whether namespace is implemented by core Mercurial
singlenode: function that inputs a name, output best node (or None)
"""
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 singlenode:
self.singlenode = singlenode
# 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 = (b"%s:" % self.logname).ljust(13) + b"%s\n"
if deprecated is None:
self.deprecated = set()
else:
self.deprecated = deprecated
self.builtin = builtin
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))
def singlenode(self, repo, name):
"""returns the best node for the given name
By default, the best node is the node from nodes() with the highest
revision number. It can be overriden by the namespace."""
n = self.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]
return None