mercurial/statichttprepo.py

url: move URL parsing functions into util to improve startup time

The introduction of the new URL parsing code has created a startup
time regression. This is mainly due to the use of url.hasscheme() in
the ui class. It ends up importing many libraries that the url module
requires.

This fix helps marginally, but if we can get rid of the urllib import
in the URL parser all together, startup time will go back to normal.

perfstartup time before the URL refactoring (8796fb6af67e):

! wall 0.050692 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

current startup time (139fb11210bb):

! wall 0.070685 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

after this change:

! wall 0.064667 comb 0.000000 user 0.000000 sys 0.000000 (best of 100)

# 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, store
import urllib, urllib2, errno

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
        req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            if hasattr(f, 'getcode'):
                # python 2.6+
                code = f.getcode()
            elif hasattr(f, 'code'):
                # undocumented attribute, seems to be set in 2.4 and 2.5
                code = f.code
            else:
                # Don't know how to check, hope for the best.
                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 __iter__(self):
        return iter(self.read().splitlines(1))
    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())

    def opener(base):
        """return a function that opens files over http"""
        p = base
        def o(path, mode="r", atomictemp=None):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((p, urllib.quote(path)))
            return httprangereader(f, urlopener)
        return o

    return opener

class statichttprepository(localrepo.localrepository):
    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)

        # find requirements
        try:
            requirements = self.opener("requires").read().splitlines()
        except IOError, inst:
            if inst.errno != errno.ENOENT:
                raise
            # 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)
            requirements = []

        # check them
        for r in requirements:
            if r not in self.supported:
                raise error.RequirementError(
                        _("requirement '%s' not supported") % r)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.sopener = self.store.opener
        self.sjoin = self.store.join

        self.manifest = manifest.manifest(self.sopener)
        self.changelog = changelog.changelog(self.sopener)
        self._tags = None
        self.nodetagscache = None
        self._branchcache = None
        self._branchcachetip = None
        self.encodepats = None
        self.decodepats = None
        self.capabilities = self.capabilities.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    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:])