pull: remove inadequate use of operations records to update stepdone
The 'stepdone' set is design to be a client side mechanism. If the client used
some advanced capabilities to request necessary information (changeset,
obsmarkers, phases, etc). It marks the steps as done to avoid having a less
advanced mechanism issue a duplicated request.
So, the "stepdone.add('phases')" should be the result of a client choice,
because only the client can know it has requested all it needed to request. In
4a08cf1a2cfe this principle was broken because any phase-heads part sent by
the server to the client would declare the phases retrieval complete.
Now that there is an official phases related capability and code associated to
it. We do not need the change in 4a08cf1a2cfe anymore and we can back it out.
This brings back 'stepdone' management for 'phases' in line with the rest of
the code (including other phases handing).
Here is an example of potential misbehavior that 4a08cf1a2cfe introduced:
Imagine a server that pre-computes bundles. The bundles contains a changegroup
part and an (advisory) 'phase-heads' part. When a pull occurs, precomputed
bundled are reused if available. As the phase part is advisory it can be sent
to all clients. However they could be relevant changesets without phase
information. Either because they are already common or because they had no
precomputed bundle for them yet.
If receiving any 'phase-heads' parts disable subsequent phases re-trivial
parts, the client will not request phase data for all relevant changesets. For
example common changesets will not turn public.
# pycompat.py - portability shim for python 3
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""Mercurial portability shim for python 3.
This contains aliases to hide python version-specific details from the core.
"""
from __future__ import absolute_import
import getopt
import os
import shlex
import sys
ispy3 = (sys.version_info[0] >= 3)
ispypy = (r'__pypy__' in sys.builtin_module_names)
if not ispy3:
import cookielib
import cPickle as pickle
import httplib
import Queue as _queue
import SocketServer as socketserver
import xmlrpclib
else:
import http.cookiejar as cookielib
import http.client as httplib
import pickle
import queue as _queue
import socketserver
import xmlrpc.client as xmlrpclib
empty = _queue.Empty
queue = _queue.Queue
def identity(a):
return a
if ispy3:
import builtins
import functools
import io
import struct
fsencode = os.fsencode
fsdecode = os.fsdecode
oslinesep = os.linesep.encode('ascii')
osname = os.name.encode('ascii')
ospathsep = os.pathsep.encode('ascii')
ossep = os.sep.encode('ascii')
osaltsep = os.altsep
if osaltsep:
osaltsep = osaltsep.encode('ascii')
# os.getcwd() on Python 3 returns string, but it has os.getcwdb() which
# returns bytes.
getcwd = os.getcwdb
sysplatform = sys.platform.encode('ascii')
sysexecutable = sys.executable
if sysexecutable:
sysexecutable = os.fsencode(sysexecutable)
stringio = io.BytesIO
maplist = lambda *args: list(map(*args))
rawinput = input
# TODO: .buffer might not exist if std streams were replaced; we'll need
# a silly wrapper to make a bytes stream backed by a unicode one.
stdin = sys.stdin.buffer
stdout = sys.stdout.buffer
stderr = sys.stderr.buffer
# Since Python 3 converts argv to wchar_t type by Py_DecodeLocale() on Unix,
# we can use os.fsencode() to get back bytes argv.
#
# https://hg.python.org/cpython/file/v3.5.1/Programs/python.c#l55
#
# TODO: On Windows, the native argv is wchar_t, so we'll need a different
# workaround to simulate the Python 2 (i.e. ANSI Win32 API) behavior.
if getattr(sys, 'argv', None) is not None:
sysargv = list(map(os.fsencode, sys.argv))
bytechr = struct.Struct('>B').pack
class bytestr(bytes):
"""A bytes which mostly acts as a Python 2 str
>>> bytestr(), bytestr(bytearray(b'foo')), bytestr(u'ascii'), bytestr(1)
(b'', b'foo', b'ascii', b'1')
>>> s = bytestr(b'foo')
>>> assert s is bytestr(s)
__bytes__() should be called if provided:
>>> class bytesable(object):
... def __bytes__(self):
... return b'bytes'
>>> bytestr(bytesable())
b'bytes'
There's no implicit conversion from non-ascii str as its encoding is
unknown:
>>> bytestr(chr(0x80)) # doctest: +ELLIPSIS
Traceback (most recent call last):
...
UnicodeEncodeError: ...
Comparison between bytestr and bytes should work:
>>> assert bytestr(b'foo') == b'foo'
>>> assert b'foo' == bytestr(b'foo')
>>> assert b'f' in bytestr(b'foo')
>>> assert bytestr(b'f') in b'foo'
Sliced elements should be bytes, not integer:
>>> s[1], s[:2]
(b'o', b'fo')
>>> list(s), list(reversed(s))
([b'f', b'o', b'o'], [b'o', b'o', b'f'])
As bytestr type isn't propagated across operations, you need to cast
bytes to bytestr explicitly:
>>> s = bytestr(b'foo').upper()
>>> t = bytestr(s)
>>> s[0], t[0]
(70, b'F')
Be careful to not pass a bytestr object to a function which expects
bytearray-like behavior.
>>> t = bytes(t) # cast to bytes
>>> assert type(t) is bytes
"""
def __new__(cls, s=b''):
if isinstance(s, bytestr):
return s
if (not isinstance(s, (bytes, bytearray))
and not hasattr(s, u'__bytes__')): # hasattr-py3-only
s = str(s).encode(u'ascii')
return bytes.__new__(cls, s)
def __getitem__(self, key):
s = bytes.__getitem__(self, key)
if not isinstance(s, bytes):
s = bytechr(s)
return s
def __iter__(self):
return iterbytestr(bytes.__iter__(self))
def iterbytestr(s):
"""Iterate bytes as if it were a str object of Python 2"""
return map(bytechr, s)
def sysbytes(s):
"""Convert an internal str (e.g. keyword, __doc__) back to bytes
This never raises UnicodeEncodeError, but only ASCII characters
can be round-trip by sysstr(sysbytes(s)).
"""
return s.encode(u'utf-8')
def sysstr(s):
"""Return a keyword str to be passed to Python functions such as
getattr() and str.encode()
This never raises UnicodeDecodeError. Non-ascii characters are
considered invalid and mapped to arbitrary but unique code points
such that 'sysstr(a) != sysstr(b)' for all 'a != b'.
"""
if isinstance(s, builtins.str):
return s
return s.decode(u'latin-1')
def strurl(url):
"""Converts a bytes url back to str"""
return url.decode(u'ascii')
def bytesurl(url):
"""Converts a str url to bytes by encoding in ascii"""
return url.encode(u'ascii')
def raisewithtb(exc, tb):
"""Raise exception with the given traceback"""
raise exc.with_traceback(tb)
def getdoc(obj):
"""Get docstring as bytes; may be None so gettext() won't confuse it
with _('')"""
doc = getattr(obj, u'__doc__', None)
if doc is None:
return doc
return sysbytes(doc)
def _wrapattrfunc(f):
@functools.wraps(f)
def w(object, name, *args):
return f(object, sysstr(name), *args)
return w
# these wrappers are automagically imported by hgloader
delattr = _wrapattrfunc(builtins.delattr)
getattr = _wrapattrfunc(builtins.getattr)
hasattr = _wrapattrfunc(builtins.hasattr)
setattr = _wrapattrfunc(builtins.setattr)
xrange = builtins.range
unicode = str
def open(name, mode='r', buffering=-1):
return builtins.open(name, sysstr(mode), buffering)
def getoptb(args, shortlist, namelist):
"""
Takes bytes arguments, converts them to unicode, pass them to
getopt.getopt(), convert the returned values back to bytes and then
return them for Python 3 compatibility as getopt.getopt() don't accepts
bytes on Python 3.
"""
args = [a.decode('latin-1') for a in args]
shortlist = shortlist.decode('latin-1')
namelist = [a.decode('latin-1') for a in namelist]
opts, args = getopt.getopt(args, shortlist, namelist)
opts = [(a[0].encode('latin-1'), a[1].encode('latin-1'))
for a in opts]
args = [a.encode('latin-1') for a in args]
return opts, args
def strkwargs(dic):
"""
Converts the keys of a python dictonary to str i.e. unicodes so that
they can be passed as keyword arguments as dictonaries with bytes keys
can't be passed as keyword arguments to functions on Python 3.
"""
dic = dict((k.decode('latin-1'), v) for k, v in dic.iteritems())
return dic
def byteskwargs(dic):
"""
Converts keys of python dictonaries to bytes as they were converted to
str to pass that dictonary as a keyword argument on Python 3.
"""
dic = dict((k.encode('latin-1'), v) for k, v in dic.iteritems())
return dic
# TODO: handle shlex.shlex().
def shlexsplit(s):
"""
Takes bytes argument, convert it to str i.e. unicodes, pass that into
shlex.split(), convert the returned value to bytes and return that for
Python 3 compatibility as shelx.split() don't accept bytes on Python 3.
"""
ret = shlex.split(s.decode('latin-1'))
return [a.encode('latin-1') for a in ret]
else:
import cStringIO
bytechr = chr
bytestr = str
iterbytestr = iter
sysbytes = identity
sysstr = identity
strurl = identity
bytesurl = identity
# this can't be parsed on Python 3
exec('def raisewithtb(exc, tb):\n'
' raise exc, None, tb\n')
def fsencode(filename):
"""
Partial backport from os.py in Python 3, which only accepts bytes.
In Python 2, our paths should only ever be bytes, a unicode path
indicates a bug.
"""
if isinstance(filename, str):
return filename
else:
raise TypeError(
"expect str, not %s" % type(filename).__name__)
# In Python 2, fsdecode() has a very chance to receive bytes. So it's
# better not to touch Python 2 part as it's already working fine.
fsdecode = identity
def getdoc(obj):
return getattr(obj, '__doc__', None)
def getoptb(args, shortlist, namelist):
return getopt.getopt(args, shortlist, namelist)
strkwargs = identity
byteskwargs = identity
oslinesep = os.linesep
osname = os.name
ospathsep = os.pathsep
ossep = os.sep
osaltsep = os.altsep
stdin = sys.stdin
stdout = sys.stdout
stderr = sys.stderr
if getattr(sys, 'argv', None) is not None:
sysargv = sys.argv
sysplatform = sys.platform
getcwd = os.getcwd
sysexecutable = sys.executable
shlexsplit = shlex.split
stringio = cStringIO.StringIO
maplist = map
rawinput = raw_input
class _pycompatstub(object):
def __init__(self):
self._aliases = {}
def _registeraliases(self, origin, items):
"""Add items that will be populated at the first access"""
items = map(sysstr, items)
self._aliases.update(
(item.replace(sysstr('_'), sysstr('')).lower(), (origin, item))
for item in items)
def _registeralias(self, origin, attr, name):
"""Alias ``origin``.``attr`` as ``name``"""
self._aliases[sysstr(name)] = (origin, sysstr(attr))
def __getattr__(self, name):
try:
origin, item = self._aliases[name]
except KeyError:
raise AttributeError(name)
self.__dict__[name] = obj = getattr(origin, item)
return obj
httpserver = _pycompatstub()
urlreq = _pycompatstub()
urlerr = _pycompatstub()
if not ispy3:
import BaseHTTPServer
import CGIHTTPServer
import SimpleHTTPServer
import urllib2
import urllib
import urlparse
urlreq._registeraliases(urllib, (
"addclosehook",
"addinfourl",
"ftpwrapper",
"pathname2url",
"quote",
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"unquote",
"url2pathname",
"urlencode",
))
urlreq._registeraliases(urllib2, (
"AbstractHTTPHandler",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPHandler",
"HTTPPasswordMgrWithDefaultRealm",
"HTTPSHandler",
"install_opener",
"ProxyHandler",
"Request",
"urlopen",
))
urlreq._registeraliases(urlparse, (
"urlparse",
"urlunparse",
))
urlerr._registeraliases(urllib2, (
"HTTPError",
"URLError",
))
httpserver._registeraliases(BaseHTTPServer, (
"HTTPServer",
"BaseHTTPRequestHandler",
))
httpserver._registeraliases(SimpleHTTPServer, (
"SimpleHTTPRequestHandler",
))
httpserver._registeraliases(CGIHTTPServer, (
"CGIHTTPRequestHandler",
))
else:
import urllib.parse
urlreq._registeraliases(urllib.parse, (
"splitattr",
"splitpasswd",
"splitport",
"splituser",
"urlparse",
"urlunparse",
))
urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote")
import urllib.request
urlreq._registeraliases(urllib.request, (
"AbstractHTTPHandler",
"BaseHandler",
"build_opener",
"FileHandler",
"FTPHandler",
"ftpwrapper",
"HTTPHandler",
"HTTPSHandler",
"install_opener",
"pathname2url",
"HTTPBasicAuthHandler",
"HTTPDigestAuthHandler",
"HTTPPasswordMgrWithDefaultRealm",
"ProxyHandler",
"Request",
"url2pathname",
"urlopen",
))
import urllib.response
urlreq._registeraliases(urllib.response, (
"addclosehook",
"addinfourl",
))
import urllib.error
urlerr._registeraliases(urllib.error, (
"HTTPError",
"URLError",
))
import http.server
httpserver._registeraliases(http.server, (
"HTTPServer",
"BaseHTTPRequestHandler",
"SimpleHTTPRequestHandler",
"CGIHTTPRequestHandler",
))
# urllib.parse.quote() accepts both str and bytes, decodes bytes
# (if necessary), and returns str. This is wonky. We provide a custom
# implementation that only accepts bytes and emits bytes.
def quote(s, safe=r'/'):
s = urllib.parse.quote_from_bytes(s, safe=safe)
return s.encode('ascii', 'strict')
# urllib.parse.urlencode() returns str. We use this function to make
# sure we return bytes.
def urlencode(query, doseq=False):
s = urllib.parse.urlencode(query, doseq=doseq)
return s.encode('ascii')
urlreq.quote = quote
urlreq.urlencode = urlencode