Mercurial > hg
view mercurial/urllibcompat.py @ 45095:8e04607023e5
procutil: ensure that procutil.std{out,err}.write() writes all bytes
Python 3 offers different kind of streams and it’s not guaranteed for all of
them that calling write() writes all bytes.
When Python is started in unbuffered mode, sys.std{out,err}.buffer are
instances of io.FileIO, whose write() can write less bytes for
platform-specific reasons (e.g. Linux has a 0x7ffff000 bytes maximum and could
write less if interrupted by a signal; when writing to Windows consoles, it’s
limited to 32767 bytes to avoid the "not enough space" error). This can lead to
silent loss of data, both when using sys.std{out,err}.buffer (which may in fact
not be a buffered stream) and when using the text streams sys.std{out,err}
(I’ve created a CPython bug report for that:
https://bugs.python.org/issue41221).
Python may fix the problem at some point. For now, we implement our own wrapper
for procutil.std{out,err} that calls the raw stream’s write() method until all
bytes have been written. We don’t use sys.std{out,err} for larger writes, so I
think it’s not worth the effort to patch them.
author | Manuel Jacob <me@manueljacob.de> |
---|---|
date | Fri, 10 Jul 2020 12:27:58 +0200 |
parents | 9f70512ae2cf |
children | 89a2afe31e82 |
line wrap: on
line source
# 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. from __future__ import absolute_import from .pycompat import getattr from . import pycompat _sysstr = pycompat.sysstr 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('_', '').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 pycompat.ispy3: import urllib.parse 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") import urllib.request 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", ), ) import urllib.response urlreq._registeraliases(urllib.response, (b"addclosehook", b"addinfourl",)) import urllib.error urlerr._registeraliases(urllib.error, (b"HTTPError", b"URLError",)) import http.server 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 else: import BaseHTTPServer import CGIHTTPServer import SimpleHTTPServer import urllib2 import urllib import urlparse urlreq._registeraliases( urllib, ( b"addclosehook", b"addinfourl", b"ftpwrapper", b"pathname2url", b"quote", b"splitattr", b"splitpasswd", b"splitport", b"splituser", b"unquote", b"url2pathname", b"urlencode", ), ) urlreq._registeraliases( urllib2, ( b"AbstractHTTPHandler", b"BaseHandler", b"build_opener", b"FileHandler", b"FTPHandler", b"HTTPBasicAuthHandler", b"HTTPDigestAuthHandler", b"HTTPHandler", b"HTTPPasswordMgrWithDefaultRealm", b"HTTPSHandler", b"install_opener", b"ProxyHandler", b"Request", b"urlopen", ), ) urlreq._registeraliases(urlparse, (b"urlparse", b"urlunparse",)) urlreq._registeralias(urlparse, b"parse_qs", b"parseqs") urlreq._registeralias(urlparse, b"parse_qsl", b"parseqsl") urlerr._registeraliases(urllib2, (b"HTTPError", b"URLError",)) httpserver._registeraliases( BaseHTTPServer, (b"HTTPServer", b"BaseHTTPRequestHandler",) ) httpserver._registeraliases( SimpleHTTPServer, (b"SimpleHTTPRequestHandler",) ) httpserver._registeraliases(CGIHTTPServer, (b"CGIHTTPRequestHandler",)) def gethost(req): return req.get_host() def getselector(req): return req.get_selector() def getfullurl(req): return req.get_full_url() def getdata(req): return req.get_data() def hasdata(req): return req.has_data()