tests/get-with-headers.py
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
Sat, 21 May 2016 02:48:51 +0900
branchstable
changeset 29180 8c5e880c7e25
parent 28726 f4b31fcd5e72
child 29455 0c741fd6158a
permissions -rwxr-xr-x
tests: escape bytes setting MSB in input of grep for portability GNU grep (2.21-2 or later) assumes that input is encoded in LC_CTYPE, and input is binary if it contains byte sequence not valid for that encoding. For example, if locale is configured as C, a byte setting most significant bit (MSB) makes such GNU grep show "Binary file <FILENAME> matches" message instead of matched lines unintentionally. This behavior is recognized as a bug, and fixed in GNU grep 2.25-1 or later. But some distributions are shipped with such buggy version (e.g. Ubuntu xenial, which is used by launchpad buildbot). http://debbugs.gnu.org/cgi/bugreport.cgi?bug=19230 https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=800670 http://packages.ubuntu.com/xenial/grep This causes failure of test-commit-interactive.t, which applies grep on CP932 byte sequence since 1111e84de635. But, explicit setting LC_CTYPE for CP932 might cause another problem, because it can't be assumed that all environment running Mercurial tests allows arbitrary locale setting. To resolve this issue, this patch escapes bytes setting MSB in input of grep. For this purpose: - str.encode('string-escape') isn't useful, because it escapes also control code (less than 0x20), and makes EOL handling complicated - "f --hexdump" isn't useful, because it isn't line-oriented - "sed -n" seems reasonable, but "sed" itself sometimes causes portability issue, too (e.g. 900767dfa80d or afb86ee925bf) This patch is posted with "stable" flag, because 1111e84de635 is on stable branch.

#!/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."""

from __future__ import absolute_import, print_function

import httplib
import json
import os
import sys

try:
    import msvcrt
    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
formatjson = False
if '--json' in sys.argv:
    sys.argv.remove('--json')
    formatjson = True

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, 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()

        # Pretty print JSON. This also has the beneficial side-effect
        # of verifying emitted JSON is well-formed.
        if formatjson:
            # json.dumps() will print trailing newlines. Eliminate them
            # to make tests easier to write.
            data = json.loads(data)
            lines = json.dumps(data, sort_keys=True, indent=2).splitlines()
            for line in lines:
                print(line.rstrip())
        else:
            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)