tests/get-with-headers.py
author Pierre-Yves David <pierre-yves.david@octobus.net>
Fri, 05 Apr 2024 11:05:54 +0200
changeset 51576 de5bf3fe0233
parent 49905 cd125eef4388
permissions -rwxr-xr-x
revset: stop serializing node when using "%ln" Turning hundred of thousand of node from node to hex and back can be slow… what about we stop doing it? In many case were we are using node id we should be using revision id. However this is not a good reason to have a stupidly slow implementation of "%ln". This caught my attention again because the phase discovery during push make an extensive use of "%ln" or huge set. In absolute, that phase discovery probably should use "%ld" and need to improves its algorithmic complexity, but improving "%ln" seems simple and long overdue. This greatly speeds up `hg push` on repository with many drafts. Here are some relevant poulpe benchmarks: ### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog # benchmark.name = hg.command.push # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.explicit-rev = all-out-heads # benchmark.variants.issue6528 = disabled # benchmark.variants.protocol = ssh # benchmark.variants.reuse-external-delta-parent = default ## benchmark.variants.revs = any-1-extra-rev before: 44.235070 after: 20.416329 (-53.85%, -23.82) ## benchmark.variants.revs = any-100-extra-rev before: 49.234697 after: 26.519829 (-46.14%, -22.71) ### benchmark.name = hg.command.bundle # bin-env-vars.hg.flavor = default # bin-env-vars.hg.py-re2-module = default # benchmark.variants.revs = all # benchmark.variants.type = none-streamv2 ## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog before: 10.138396 after: 7.750458 (-23.55%, -2.39) ## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog before: 1.263859 after: 0.700229 (-44.60%, -0.56) ## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog before: 399.484481 after: 346.5089 (-13.26%, -52.98) ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog before: 4.540080 after: 3.401700 (-25.07%, -1.14) ## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog before: 2.975765 after: 1.870798 (-37.13%, -1.10)

#!/usr/bin/env python

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


import argparse
import json
import os
import sys

from mercurial import (
    pycompat,
    util,
)

httplib = util.httplib

try:
    import msvcrt

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

stdout = getattr(sys.stdout, 'buffer', sys.stdout)

parser = argparse.ArgumentParser()
parser.add_argument('--twice', action='store_true')
parser.add_argument('--headeronly', action='store_true')
parser.add_argument('--json', action='store_true')
parser.add_argument('--hgproto')
parser.add_argument(
    '--requestheader',
    nargs='*',
    default=[],
    help='Send an additional HTTP request header. Argument '
    'value is <header>=<value>',
)
parser.add_argument('--bodyfile', help='Write HTTP response body to a file')
parser.add_argument('--method', default='GET', help='HTTP method to use')
parser.add_argument('host')
parser.add_argument('path')
parser.add_argument('show', nargs='*')

args = parser.parse_args()

twice = args.twice
headeronly = args.headeronly
formatjson = args.json
hgproto = args.hgproto
requestheaders = args.requestheader

tag = None


def request(method, host, path, show):
    assert not path.startswith('/'), path
    global tag
    headers = {}
    if tag:
        headers['If-None-Match'] = tag
    if hgproto:
        headers['X-HgProto-1'] = hgproto

    for header in requestheaders:
        key, value = header.split('=', 1)
        headers[key] = value

    conn = httplib.HTTPConnection(host)
    conn.request(method, '/' + path, None, headers)
    response = conn.getresponse()
    stdout.write(
        b'%d %s\n' % (response.status, response.reason.encode('ascii'))
    )
    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:
            stdout.write(
                b"%s: %s\n"
                % (h.encode('ascii'), response.getheader(h).encode('ascii'))
            )
    if headeronly:
        # still read the body to prevent windows to be unhappy about that
        # (this might some flakyness in test-hgweb-filelog.t on Windows)
        data = response.read()
    else:
        stdout.write(b'\n')
        data = response.read()

        if args.bodyfile:
            bodyfh = open(args.bodyfile, 'wb')
        else:
            bodyfh = stdout

        # 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 = pycompat.json_loads(data)
            lines = json.dumps(data, sort_keys=True, indent=2).splitlines()
            for line in lines:
                bodyfh.write(pycompat.sysbytes(line.rstrip()))
                bodyfh.write(b'\n')
        else:
            bodyfh.write(data)

        if args.bodyfile:
            bodyfh.close()

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

    # further try to please the windows-flakyness deity
    conn.close()

    return response.status


status = request(args.method, args.host, args.path, args.show)
if twice:
    status = request(args.method, args.host, args.path, args.show)

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