mercurial/statichttprepo.py

revset: lower weight for _intlist function

The histedit command uses a revset like:

(_intlist('1234\x001235')) and merge()

Previously the optimizer gave a weight of 1.5 to the _intlist side (1 for the
function, 0.5 for the string) which caused it to process the merge() side first.
This caused it to evaluate merge against every commit in the repo, which took
2.5 seconds on a large repo.

I changed the weight of _intlist to 0, since it's a trivial calculation, which
makes it process intlist first, which makes merge apply only to the revs in the
list. Which makes the revset take 0.15 seconds now. Cutting off 2.4 seconds off
our histedit performance.

>From the revset benchmark:
revset #25: (_intlist('20000\x0020001')) and merge()
0) obsolete feature not enabled but 54243 markers found!
! wall 0.036767 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
1) obsolete feature not enabled but 54243 markers found!
! wall 0.000198 comb 0.000000 user 0.000000 sys 0.000000 (best of 9084)

# 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 i18n import _
import changelog, byterange, url, error
import localrepo, manifest, util, scmutil, store
import urllib, urllib2, errno, os

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 seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urllib2.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()
            # Python 2.6+ defines a getcode() function, and 2.4 and
            # 2.5 appear to always have an undocumented code attribute
            # set. If we can't read either of those, fall back to 206
            # and hope for the best.
            code = getattr(f, 'getcode', lambda : getattr(f, 'code', 206))()
        except urllib2.HTTPError, inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urllib2.URLError, 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", atomictemp=None):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urllib.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 = []

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

            # check if it is a non-empty old-style repository
            try:
                fp = self.opener("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError, 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.sopener = self.store.opener
        self.svfs = self.sopener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifest = manifest.manifest(self.sopener)
        self.changelog = changelog.changelog(self.sopener)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self.encodepats = None
        self.decodepats = 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 util.Abort(_('cannot lock static-http repository'))

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