view mercurial/hgweb/protocol.py @ 30308:d500ddae7494

bdiff: don't check border condition in loop

`plast = a + len - 1`. So, this "for" loop iterates from "a" to "plast",
inclusive. So, `p == plast` can only be true on the final iteration
of the loop. So checking for it on every loop iteration is wasteful.

This patch simply decreases the upper bound of the loop by 1 and
adds an explicit check after iteration for the `p == plast` case.
We can't simply add 1 to the initial value for "i" because that
doesn't do the correct thing on empty input strings.

`perfbdiff -m 3041e4d59df2` on the Firefox repo becomes significantly
faster:

! wall 0.072763 comb 0.070000 user 0.070000 sys 0.000000 (best of 100)
! wall 0.053221 comb 0.060000 user 0.060000 sys 0.000000 (best of 100)

For the curious, this code has its origins in 8b067bde6679, which is
the changeset that introduced bdiff.c in 2005.

Also, GNU diffutils is able to perform a similar line-based diff in
under 20ms. So there's likely more perf wins to be found in this code.
One of them is the hashing algorithm. But it looks like mpm spent
some time testing hash collisions in d0c48891dd4a. I'd like to do the
same before switching away from lyhash, just to be on the safe side.

#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# 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 cgi
import zlib

from .common import (
    HTTP_OK,
)

from .. import (
    util,
    wireproto,
)
stringio = util.stringio

urlerr = util.urlerr
urlreq = util.urlreq

HGTYPE = 'application/mercurial-0.1'
HGERRTYPE = 'application/hg-error'

class webproto(wireproto.abstractserverproto):
    def __init__(self, req, ui):
        self.req = req
        self.response = ''
        self.ui = ui
    def getargs(self, args):
        knownargs = self._args()
        data = {}
        keys = args.split()
        for k in keys:
            if k == '*':
                star = {}
                for key in knownargs.keys():
                    if key != 'cmd' and key not in keys:
                        star[key] = knownargs[key][0]
                data['*'] = star
            else:
                data[k] = knownargs[k][0]
        return [data[k] for k in keys]
    def _args(self):
        args = self.req.form.copy()
        postlen = int(self.req.env.get('HTTP_X_HGARGS_POST', 0))
        if postlen:
            args.update(cgi.parse_qs(
                self.req.read(postlen), keep_blank_values=True))
            return args
        chunks = []
        i = 1
        while True:
            h = self.req.env.get('HTTP_X_HGARG_' + str(i))
            if h is None:
                break
            chunks += [h]
            i += 1
        args.update(cgi.parse_qs(''.join(chunks), keep_blank_values=True))
        return args
    def getfile(self, fp):
        length = int(self.req.env['CONTENT_LENGTH'])
        for s in util.filechunkiter(self.req, limit=length):
            fp.write(s)
    def redirect(self):
        self.oldio = self.ui.fout, self.ui.ferr
        self.ui.ferr = self.ui.fout = stringio()
    def restore(self):
        val = self.ui.fout.getvalue()
        self.ui.ferr, self.ui.fout = self.oldio
        return val

    def groupchunks(self, fh):
        def getchunks():
            while True:
                chunk = fh.read(32768)
                if not chunk:
                    break
                yield chunk

        return self.compresschunks(getchunks())

    def compresschunks(self, chunks):
        # Don't allow untrusted settings because disabling compression or
        # setting a very high compression level could lead to flooding
        # the server's network or CPU.
        z = zlib.compressobj(self.ui.configint('server', 'zliblevel', -1))
        for chunk in chunks:
            data = z.compress(chunk)
            # Not all calls to compress() emit data. It is cheaper to inspect
            # that here than to send it via the generator.
            if data:
                yield data
        yield z.flush()

    def _client(self):
        return 'remote:%s:%s:%s' % (
            self.req.env.get('wsgi.url_scheme') or 'http',
            urlreq.quote(self.req.env.get('REMOTE_HOST', '')),
            urlreq.quote(self.req.env.get('REMOTE_USER', '')))

def iscmd(cmd):
    return cmd in wireproto.commands

def call(repo, req, cmd):
    p = webproto(req, repo.ui)
    rsp = wireproto.dispatch(repo, p, cmd)
    if isinstance(rsp, str):
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.streamres):
        req.respond(HTTP_OK, HGTYPE)
        return rsp.gen
    elif isinstance(rsp, wireproto.pushres):
        val = p.restore()
        rsp = '%d\n%s' % (rsp.res, val)
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.pusherr):
        # drain the incoming bundle
        req.drain()
        p.restore()
        rsp = '0\n%s\n' % rsp.res
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.ooberror):
        rsp = rsp.message
        req.respond(HTTP_OK, HGERRTYPE, body=rsp)
        return []