tests/test-url.py

url: verify correctness of https server certificates (issue2407)

Pythons SSL module verifies that certificates received for HTTPS are valid
according to the specified cacerts, but it doesn't verify that the certificate
is for the host we connect to.

We now explicitly verify that the commonName in the received certificate
matches the requested hostname and is valid for the time being.

This is a minimal patch where we try to fail to the safe side, but we do still
rely on Python's SSL functionality and do not try to implement the standards
fully and correctly. CRLs and subjectAltName are not handled and proxies
haven't been considered.

This change might break connections to some sites if cacerts is specified and
the certificates (by our definition) isn't correct. The workaround is to
disable cacerts which in most cases isn't much worse than it was before with
cacerts.

#!/usr/bin/env python

def check(a, b):
    if a != b:
        print (a, b)

from mercurial.url import _verifycert

# Test non-wildcard certificates        
check(_verifycert({'subject': ((('commonName', 'example.com'),),)}, 'example.com'),
    None)
check(_verifycert({'subject': ((('commonName', 'example.com'),),)}, 'www.example.com'),
    'certificate is for example.com')
check(_verifycert({'subject': ((('commonName', 'www.example.com'),),)}, 'example.com'),
    'certificate is for www.example.com')

# Test wildcard certificates
check(_verifycert({'subject': ((('commonName', '*.example.com'),),)}, 'www.example.com'),
    None)
check(_verifycert({'subject': ((('commonName', '*.example.com'),),)}, 'example.com'),
    'certificate is for *.example.com')
check(_verifycert({'subject': ((('commonName', '*.example.com'),),)}, 'w.w.example.com'),
    'certificate is for *.example.com')

# Avoid some pitfalls
check(_verifycert({'subject': ((('commonName', '*.foo'),),)}, 'foo'),
    'certificate is for *.foo')
check(_verifycert({'subject': ((('commonName', '*o'),),)}, 'foo'),
    'certificate is for *o')

import time
lastyear = time.gmtime().tm_year - 1
nextyear = time.gmtime().tm_year + 1
check(_verifycert({'notAfter': 'May  9 00:00:00 %s GMT' % lastyear}, 'example.com'),
    'certificate expired May  9 00:00:00 %s GMT' % lastyear)
check(_verifycert({'notBefore': 'May  9 00:00:00 %s GMT' % nextyear}, 'example.com'),
    'certificate not valid before May  9 00:00:00 %s GMT' % nextyear)
check(_verifycert({'notAfter': 'Sep 29 15:29:48 %s GMT' % nextyear, 'subject': ()}, 'example.com'),
    'no commonName found in certificate')
check(_verifycert(None, 'example.com'),
    'no certificate received')