tests/get-with-headers.py

obsolete: use parsers.fm1readmarker if it exists for a ~38% perf win

This moves perfloadmarkers on my linux workstation (63494 markers from
mpm, crew, and myself) performance from
! wall 0.357657 comb 0.360000 user 0.350000 sys 0.010000 (best of 28)
to
! wall 0.222345 comb 0.220000 user 0.210000 sys 0.010000 (best of 41)
which is a pretty good improvement.

On my BSD machine, which is ancient and slow, before:
! wall 3.584964 comb 3.578125 user 3.539062 sys 0.039062 (best of 3)
after:
! wall 2.267974 comb 2.265625 user 2.195312 sys 0.070312 (best of 5)


I feel like we could do better by moving the whole generator function
into C, but I didn't want to tackle that right away.

#!/usr/bin/env python

"""This does HTTP GET requests given a host:port and path and returns
a subset of the headers plus the body of the result."""

import httplib, sys

try:
    import msvcrt, os
    msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
    msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
    pass

twice = False
if '--twice' in sys.argv:
    sys.argv.remove('--twice')
    twice = True
headeronly = False
if '--headeronly' in sys.argv:
    sys.argv.remove('--headeronly')
    headeronly = True

reasons = {'Not modified': 'Not Modified'} # python 2.4

tag = None
def request(host, path, show):
    assert not path.startswith('/'), path
    global tag
    headers = {}
    if tag:
        headers['If-None-Match'] = tag

    conn = httplib.HTTPConnection(host)
    conn.request("GET", '/' + path, None, headers)
    response = conn.getresponse()
    print response.status, reasons.get(response.reason, response.reason)
    if show[:1] == ['-']:
        show = sorted(h for h, v in response.getheaders()
                      if h.lower() not in show)
    for h in [h.lower() for h in show]:
        if response.getheader(h, None) is not None:
            print "%s: %s" % (h, response.getheader(h))
    if not headeronly:
        print
        data = response.read()
        sys.stdout.write(data)

        if twice and response.getheader('ETag', None):
            tag = response.getheader('ETag')

    return response.status

status = request(sys.argv[1], sys.argv[2], sys.argv[3:])
if twice:
    status = request(sys.argv[1], sys.argv[2], sys.argv[3:])

if 200 <= status <= 305:
    sys.exit(0)
sys.exit(1)