view contrib/revsetbenchmarks.py @ 22506:6e1fbcb18a75 stable

hgweb: fail if an invalid command was supplied in url path (issue4071)

Traditionally, the way to specify a command for hgweb was to use url query
arguments (e.g. "?cmd=batch"). If the command is unknown to hgweb, it gives an
error (e.g. "400 no such method: badcmd").

But there's also another way to specify a command: as a url path fragment (e.g.
"/graph"). Before, hgweb was made forgiving (looks like it was made in
44c5157474e7) and user could put any unknown command in the url. If hgweb
couldn't understand it, it would just silently fall back to the default
command, which depends on the actual style (e.g. for paper it's shortlog, for
monoblue it's summary). This was inconsistent and was breaking some tools that
rely on http status codes (as noted in the issue4071). So this patch changes
that behavior to the more consistent one, i.e. hgweb will now return "400 no
such method: badcmd".

So if some tool was relying on having an invalid command return http status
code 200 and also have some information, then it will stop working. That is, if
somebody typed foobar when they really meant shortlog (and the user was lucky
enough to choose a style where the default command is shortlog too), that fact
will now be revealed.

Code-wise, the changed if block is only relevant when there's no "?cmd" query
parameter (i.e. only when command is specified as a url path fragment), and
looks like the removed else branch was there only for falling back to default
command. With that removed, the rest of the code works as expected: it looks at
the command, and if it's not known, raises a proper ErrorResponse exception
with an appropriate message.

Evidently, there were no tests that required the old behavior. But, frankly, I
don't know any way to tell if anyone actually exploited such forgiving behavior
in some in-house tool.

#!/usr/bin/env python

# Measure the performance of a list of revsets against multiple revisions
# defined by parameter. Checkout one by one and run perfrevset with every
# revset in the list to benchmark its performance.
#
# - First argument is a revset of mercurial own repo to runs against.
# - Second argument is the file from which the revset array will be taken
#   If second argument is omitted read it from standard input
#
# You should run this from the root of your mercurial repository.
#
# This script also does one run of the current version of mercurial installed
# to compare performance.

import sys
import os
from subprocess import check_call, Popen, CalledProcessError, STDOUT, PIPE
# cannot use argparse, python 2.7 only
from optparse import OptionParser



def check_output(*args, **kwargs):
    kwargs.setdefault('stderr', PIPE)
    kwargs.setdefault('stdout', PIPE)
    proc = Popen(*args, **kwargs)
    output, error = proc.communicate()
    if proc.returncode != 0:
        raise CalledProcessError(proc.returncode, ' '.join(args[0]))
    return output

def update(rev):
    """update the repo to a revision"""
    try:
        check_call(['hg', 'update', '--quiet', '--check', str(rev)])
    except CalledProcessError, exc:
        print >> sys.stderr, 'update to revision %s failed, aborting' % rev
        sys.exit(exc.returncode)

def perf(revset, target=None):
    """run benchmark for this very revset"""
    try:
        cmd = ['./hg',
               '--config',
               'extensions.perf='
               + os.path.join(contribdir, 'perf.py'),
               'perfrevset',
               revset]
        if target is not None:
            cmd.append('-R')
            cmd.append(target)
        output = check_output(cmd, stderr=STDOUT)
        output = output.lstrip('!') # remove useless ! in this context
        return output.strip()
    except CalledProcessError, exc:
        print >> sys.stderr, 'abort: cannot run revset benchmark'
        sys.exit(exc.returncode)

def printrevision(rev):
    """print data about a revision"""
    sys.stdout.write("Revision: ")
    sys.stdout.flush()
    check_call(['hg', 'log', '--rev', str(rev), '--template',
               '{desc|firstline}\n'])

def getrevs(spec):
    """get the list of rev matched by a revset"""
    try:
        out = check_output(['hg', 'log', '--template={rev}\n', '--rev', spec])
    except CalledProcessError, exc:
        print >> sys.stderr, "abort, can't get revision from %s" % spec
        sys.exit(exc.returncode)
    return [r for r in out.split() if r]


parser = OptionParser(usage="usage: %prog [options] <revs>")
parser.add_option("-f", "--file",
                  help="read revset from FILE", metavar="FILE")
parser.add_option("-R", "--repo",
                  help="run benchmark on REPO", metavar="REPO")

(options, args) = parser.parse_args()

if len(sys.argv) < 2:
    parser.print_help()
    sys.exit(255)

# the directory where both this script and the perf.py extension live.
contribdir = os.path.dirname(__file__)

target_rev = args[0]

revsetsfile = sys.stdin
if options.file:
    revsetsfile = open(options.file)

revsets = [l.strip() for l in revsetsfile]

print "Revsets to benchmark"
print "----------------------------"

for idx, rset in enumerate(revsets):
    print "%i) %s" % (idx, rset)

print "----------------------------"
print


revs = getrevs(target_rev)

results = []
for r in revs:
    print "----------------------------"
    printrevision(r)
    print "----------------------------"
    update(r)
    res = []
    results.append(res)
    for idx, rset in enumerate(revsets):
        data = perf(rset, target=options.repo)
        res.append(data)
        print "%i)" % idx, data
        sys.stdout.flush()
    print "----------------------------"


print """

Result by revset
================
"""

print 'Revision:', revs
for idx, rev in enumerate(revs):
    sys.stdout.write('%i) ' % idx)
    sys.stdout.flush()
    printrevision(rev)

print
print

for ridx, rset in enumerate(revsets):

    print "revset #%i: %s" % (ridx, rset)
    for idx, data in enumerate(results):
        print '%i) %s' % (idx, data[ridx])
    print