view mercurial/statichttprepo.py @ 29304:5e32852fa4bd

revset: make filteredset.__nonzero__ respect the order of the filteredset

This fix allows __nonzero__ to respect the direction of iteration of the
whole filteredset. Here's the case when it matters. Imagine that we have a
very large repository and we want to execute a command like:

    $ hg log --rev '(tip:0) and user(ikostia)' --limit 1

(we want to get the latest commit by me).

Mercurial will evaluate a filteredset lazy data structure, an
instance of the filteredset class, which will know that it has to iterate
in a descending order (isdescending() will return True if called). This
means that when some code iterates over the instance of this filteredset,
the 'and user(ikostia)' condition will be first checked on the latest
revision, then on the second latest and so on, allowing Mercurial to
print matches as it founds them. However, cmdutil.getgraphlogrevs
contains the following code:

    revs = _logrevs(repo, opts)
    if not revs:
        return revset.baseset(), None, None

The "not revs" expression is evaluated by calling filteredset.__nonzero__,
which in its current implementation will try to iterate the filteredset
in ascending order until it finds a revision that matches the 'and user(..'
condition. If the condition is only true on late revisions, a lot of
useless iterations will be done. These iterations could be avoided if
__nonzero__ followed the order of the filteredset, which in my opinion
is a sensible thing to do here.

The problem gets even worse when instead of 'user(ikostia)' some more
expensive check is performed, like grepping the commit diff.


I tested this fix on a very large repo where tip is my commit and my very
first commit comes fairly late in the revision history. Results of timing
of the above command on that very large repo.

-with my fix:
real    0m1.795s
user    0m1.657s
sys     0m0.135s

-without my fix:
real    1m29.245s
user    1m28.223s
sys     0m0.929s

I understand that this is a very specific kind of problem that presents
itself very rarely, only on very big repositories and with expensive
checks and so on. But I don't see any disadvantages to this kind of fix
either.

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import errno
import os

from .i18n import _
from . import (
    byterange,
    changelog,
    error,
    localrepo,
    manifest,
    namespaces,
    scmutil,
    store,
    url,
    util,
)

urlerr = util.urlerr
urlreq = util.urlreq

class httprangereader(object):
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url

    def __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.close()

    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urlreq.request(self.url)
        end = ''
        if bytes:
            end = self.pos + bytes - 1
        if self.pos or end:
            req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            code = f.code
        except urlerr.httperror as inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urlerr.urlerror as inst:
            raise IOError(None, inst.reason[1])

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos:self.pos + bytes]
            else:
                data = data[self.pos:]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data
    def readlines(self):
        return self.read().splitlines(True)
    def __iter__(self):
        return iter(self.readlines())
    def close(self):
        pass

def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(byterange.HTTPRangeHandler())

    class statichttpvfs(scmutil.abstractvfs):
        def __init__(self, base):
            self.base = base

        def __call__(self, path, mode='r', *args, **kw):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urlreq.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return os.path.join(self.base, path)
            else:
                return self.base

    return statichttpvfs

class statichttppeer(localrepo.localpeer):
    def local(self):
        return None
    def canpush(self):
        return False

class statichttprepository(localrepo.localrepository):
    supported = localrepo.localrepository._basesupported

    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = util.url(path.rstrip('/') + "/.hg")
        self.path, authinfo = u.authinfo()

        opener = build_opener(ui, authinfo)
        self.opener = opener(self.path)
        self.vfs = self.opener
        self._phasedefaults = []

        self.names = namespaces.namespaces()

        try:
            requirements = scmutil.readrequires(self.vfs, self.supported)
        except IOError as inst:
            if inst.errno != errno.ENOENT:
                raise
            requirements = set()

            # check if it is a non-empty old-style repository
            try:
                fp = self.vfs("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError as inst:
                if inst.errno != errno.ENOENT:
                    raise
                # we do not care about empty old-style repositories here
                msg = _("'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifest = manifest.manifest(self.svfs)
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self._revbranchcache = None
        self.encodepats = None
        self.decodepats = None
        self._transref = None

    def _restrictcapabilities(self, caps):
        caps = super(statichttprepository, self)._restrictcapabilities(caps)
        return caps.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def peer(self):
        return statichttppeer(self)

    def lock(self, wait=True):
        raise error.Abort(_('cannot lock static-http repository'))

def instance(ui, path, create):
    if create:
        raise error.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])