view tests/get-with-headers.py @ 39270:37e56607cbb9

lfs: add a progress bar when searching for blobs to upload

The search itself can take an extreme amount of time if there are a lot of
revisions involved.  I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):

     \ 58.1%  wrapper.py:     extractpointers      line 297:  pointers = extractpointers(...
       | 57.7%  wrapper.py:     pointersfromctx    line 352:  for p in pointersfromctx(ct...
       | 57.4%  wrapper.py:     pointerfromctx     line 397:  p = pointerfromctx(ctx, f, ...
         \ 38.7%  context.py:     __contains__     line 368:  if f not in ctx:
           | 38.7%  util.py:        __get__        line 82:  return key in self._manifest
           | 38.7%  context.py:     _manifest      line 1416:  result = self.func(obj)
           | 38.7%  manifest.py:    read           line 472:  return self._manifestctx.re...
             \ 25.6%  revlog.py:      revision     line 1562:  text = rl.revision(self._node)
               \ 12.8%  revlog.py:      _chunks    line 2217:  bins = self._chunks(chain, ...
                 | 12.0%  revlog.py:      decompressline 2112:  ladd(decomp(buffer(data, ch...
               \  7.8%  revlog.py:      checkhash  line 2232:  self.checkhash(text, node, ...
                 |  7.8%  revlog.py:      hash     line 2315:  if node != self.hash(text, ...
                 |  7.8%  revlog.py:      hash     line 2242:  return hash(text, p1, p2)
             \ 12.0%  manifest.py:    __init__     line 1565:  self._data = manifestdict(t...
         \ 16.8%  context.py:     filenode         line 378:  if not _islfs(fctx.filelog(...
           | 15.7%  util.py:        __get__        line 706:  return self._filelog
           | 14.8%  context.py:     _filelog       line 1416:  result = self.func(obj)
           | 14.8%  localrepo.py:   file           line 629:  return self._repo.file(self...
           | 14.8%  filelog.py:     __init__       line 1134:  return filelog.filelog(self...
           | 14.5%  revlog.py:      __init__       line 24:  censorable=True)

#!/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 (
    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(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)