procutil: make stream detection in make_line_buffered more correct and strict
In make_line_buffered(), we don’t want to wrap the stream if we know that lines
get flushed to the underlying raw stream already.
Previously, the heuristic was too optimistic. It assumed that any stream which
is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there
are buffered streams that aren’t instances of io.BufferedIOBase, like
Mercurial’s own winstdout.
The new logic is different in two ways:
First, only for the check, if unwraps any combination of WriteAllWrapper and
winstdout.
Second, it skips wrapping the stream only if it is an instance of io.RawIOBase
(or already wrapped). If it is an instance of io.BufferedIOBase, it gets
wrapped. In any other case, the function raises an exception. This ensures
that, if an unknown stream is passed or we add another wrapper in the future,
we don’t wrap the stream if it’s already line buffered or not wrap the stream
if it’s not line buffered. In fact, this was already helpful during development
of this change. Without it, I possibly would have forgot that WriteAllWrapper
needs to be ignored for the check, leading to unnecessary wrapping if stdout is
unbuffered.
The alternative would have been to always wrap unknown streams. However, I
don’t think that anyone would benefit from being less strict. We can expect
streams from the standard library to be subclassing either io.RawIOBase or
io.BufferedIOBase, so running Mercurial in the standard way should not regress
by this change. Py2exe might replace sys.stdout and sys.stderr, but that
currently breaks Mercurial anyway and also these streams don’t claim to be
interactive, so this function is not called for them.
# urllibcompat.py - adapters to ease using urllib2 on Py2 and urllib on Py3
#
# Copyright 2017 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import http.server
import urllib.error
import urllib.parse
import urllib.request
import urllib.response
from .pycompat import getattr
from . import pycompat
_sysstr = pycompat.sysstr
class _pycompatstub:
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('_', '').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()
urlreq._registeraliases(
urllib.parse,
(
b"splitattr",
b"splitpasswd",
b"splitport",
b"splituser",
b"urlparse",
b"urlunparse",
),
)
urlreq._registeralias(urllib.parse, b"parse_qs", b"parseqs")
urlreq._registeralias(urllib.parse, b"parse_qsl", b"parseqsl")
urlreq._registeralias(urllib.parse, b"unquote_to_bytes", b"unquote")
urlreq._registeraliases(
urllib.request,
(
b"AbstractHTTPHandler",
b"BaseHandler",
b"build_opener",
b"FileHandler",
b"FTPHandler",
b"ftpwrapper",
b"HTTPHandler",
b"HTTPSHandler",
b"install_opener",
b"pathname2url",
b"HTTPBasicAuthHandler",
b"HTTPDigestAuthHandler",
b"HTTPPasswordMgrWithDefaultRealm",
b"ProxyHandler",
b"Request",
b"url2pathname",
b"urlopen",
),
)
urlreq._registeraliases(
urllib.response,
(
b"addclosehook",
b"addinfourl",
),
)
urlerr._registeraliases(
urllib.error,
(
b"HTTPError",
b"URLError",
),
)
httpserver._registeraliases(
http.server,
(
b"HTTPServer",
b"BaseHTTPRequestHandler",
b"SimpleHTTPRequestHandler",
b"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='/'):
# bytestr has an __iter__ that emits characters. quote_from_bytes()
# does an iteration and expects ints. We coerce to bytes to appease it.
if isinstance(s, pycompat.bytestr):
s = bytes(s)
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
def getfullurl(req):
return req.full_url
def gethost(req):
return req.host
def getselector(req):
return req.selector
def getdata(req):
return req.data
def hasdata(req):
return req.data is not None