view tests/get-with-headers.py @ 42377:0546ead39a7e stable

manifest: avoid corruption by dropping removed files with pure (issue5801) Previously, removed files would simply be marked by overwriting the first byte with NUL and dropping their entry in `self.position`. But no effort was made to ignore them when compacting the dictionary into text form. This allowed them to slip into the manifest revision, since the code seems to be trying to minimize the string operations by copying as large a chunk as possible. As part of this, compact() walks the existing text based on entries in the `positions` list, and consumed everything up to the next position entry. This typically resulted in a ValueError complaining about unsorted manifest entries. Sometimes it seems that files do get dropped in large repos- it seems to correspond to there being a new entry that would take the same slot. A much more trivial problem is that if the only changes were removals, `_compact()` didn't even run because `__delitem__` doesn't add anything to `self.extradata`. Now there's an explicit variable to flag this, both to allow `_compact()` to run, and to avoid searching the manifest in cases where there are no removals. In practice, this behavior was mostly obscured by the check in fastdelta() which takes a different path that explicitly drops removed files if there are fewer than 1000 changes. However, timeless has a repo where after rebasing tens of commits, a totally different path[1] is taken that bypasses the change count check and hits this problem. [1] https://www.mercurial-scm.org/repo/hg/file/2338bdea4474/mercurial/manifest.py#l1511
author Matt Harbison <matt_harbison@yahoo.com>
date Thu, 23 May 2019 21:54:24 -0400
parents fe11fc7e541f
children 2372284d9457
line wrap: on
line source

#!/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

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('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(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("GET", '/' + 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 not headeronly:
        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 = 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')

    return response.status

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

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