tests/get-with-headers.py

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

#!/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 json
import os
import sys

from mercurial import (
    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

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

hgproto = None
if '--hgproto' in sys.argv:
    idx = sys.argv.index('--hgproto')
    hgproto = sys.argv[idx + 1]
    sys.argv.pop(idx)
    sys.argv.pop(idx)

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

    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)