pycompat.py
412 lines
| 12.2 KiB
| text/x-python
|
PythonLexer
/ mercurial / pycompat.py
timeless
|
r28818 | # 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 | ||||
Pulkit Goyal
|
r30578 | import getopt | ||
Pulkit Goyal
|
r30302 | import os | ||
Pulkit Goyal
|
r30678 | import shlex | ||
Pulkit Goyal
|
r29584 | import sys | ||
Yuya Nishihara
|
r30030 | ispy3 = (sys.version_info[0] >= 3) | ||
if not ispy3: | ||||
Gregory Szorc
|
r31934 | import cookielib | ||
Pulkit Goyal
|
r29324 | import cPickle as pickle | ||
Pulkit Goyal
|
r29455 | import httplib | ||
Pulkit Goyal
|
r29584 | import Queue as _queue | ||
Pulkit Goyal
|
r29433 | import SocketServer as socketserver | ||
Pulkit Goyal
|
r29432 | import xmlrpclib | ||
Pulkit Goyal
|
r29584 | else: | ||
Gregory Szorc
|
r31934 | import http.cookielib as cookielib | ||
Pulkit Goyal
|
r29584 | import http.client as httplib | ||
import pickle | ||||
import queue as _queue | ||||
import socketserver | ||||
Pulkit Goyal
|
r29432 | import xmlrpc.client as xmlrpclib | ||
Pulkit Goyal
|
r29431 | |||
Yuya Nishihara
|
r31774 | def identity(a): | ||
return a | ||||
Yuya Nishihara
|
r30030 | if ispy3: | ||
Yuya Nishihara
|
r29797 | import builtins | ||
Yuya Nishihara
|
r29799 | import functools | ||
Yuya Nishihara
|
r31372 | import io | ||
Martin von Zweigbergk
|
r31424 | import struct | ||
Yuya Nishihara
|
r31372 | |||
Martijn Pieters
|
r30119 | fsencode = os.fsencode | ||
Pulkit Goyal
|
r30300 | fsdecode = os.fsdecode | ||
Pulkit Goyal
|
r30302 | # A bytes version of os.name. | ||
Yuya Nishihara
|
r31775 | oslinesep = os.linesep.encode('ascii') | ||
Pulkit Goyal
|
r30302 | osname = os.name.encode('ascii') | ||
Pulkit Goyal
|
r30303 | ospathsep = os.pathsep.encode('ascii') | ||
ossep = os.sep.encode('ascii') | ||||
Pulkit Goyal
|
r30623 | osaltsep = os.altsep | ||
if osaltsep: | ||||
osaltsep = osaltsep.encode('ascii') | ||||
Pulkit Goyal
|
r30500 | # os.getcwd() on Python 3 returns string, but it has os.getcwdb() which | ||
# returns bytes. | ||||
getcwd = os.getcwdb | ||||
Pulkit Goyal
|
r30624 | sysplatform = sys.platform.encode('ascii') | ||
Pulkit Goyal
|
r30668 | sysexecutable = sys.executable | ||
if sysexecutable: | ||||
sysexecutable = os.fsencode(sysexecutable) | ||||
Pulkit Goyal
|
r31359 | stringio = io.BytesIO | ||
Augie Fackler
|
r31501 | maplist = lambda *args: list(map(*args)) | ||
Yuya Nishihara
|
r30334 | |||
Yuya Nishihara
|
r30472 | # 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 | ||||
Yuya Nishihara
|
r30334 | # 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. | ||||
Augie Fackler
|
r31277 | if getattr(sys, 'argv', None) is not None: | ||
sysargv = list(map(os.fsencode, sys.argv)) | ||||
Yuya Nishihara
|
r29797 | |||
Martin von Zweigbergk
|
r31424 | bytechr = struct.Struct('>B').pack | ||
Yuya Nishihara
|
r31253 | |||
Yuya Nishihara
|
r31439 | 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) | ||||
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)): | ||||
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)) | ||||
Yuya Nishihara
|
r31382 | def iterbytestr(s): | ||
"""Iterate bytes as if it were a str object of Python 2""" | ||||
Martin von Zweigbergk
|
r31425 | return map(bytechr, s) | ||
Yuya Nishihara
|
r31382 | |||
Yuya Nishihara
|
r31820 | 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') | ||||
Yuya Nishihara
|
r30032 | 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') | ||||
Yuya Nishihara
|
r29799 | def _wrapattrfunc(f): | ||
@functools.wraps(f) | ||||
def w(object, name, *args): | ||||
Yuya Nishihara
|
r30032 | return f(object, sysstr(name), *args) | ||
Yuya Nishihara
|
r29799 | return w | ||
Yuya Nishihara
|
r29800 | # these wrappers are automagically imported by hgloader | ||
Yuya Nishihara
|
r29799 | delattr = _wrapattrfunc(builtins.delattr) | ||
getattr = _wrapattrfunc(builtins.getattr) | ||||
hasattr = _wrapattrfunc(builtins.hasattr) | ||||
setattr = _wrapattrfunc(builtins.setattr) | ||||
Yuya Nishihara
|
r29800 | xrange = builtins.range | ||
Pulkit Goyal
|
r31843 | unicode = str | ||
Yuya Nishihara
|
r29799 | |||
Pulkit Goyal
|
r31149 | def open(name, mode='r', buffering=-1): | ||
return builtins.open(name, sysstr(mode), buffering) | ||||
Pulkit Goyal
|
r30578 | # getopt.getopt() on Python 3 deals with unicodes internally so we cannot | ||
# pass bytes there. Passing unicodes will result in unicodes as return | ||||
# values which we need to convert again to bytes. | ||||
def getoptb(args, shortlist, namelist): | ||||
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 | ||||
Pulkit Goyal
|
r30579 | # keys of keyword arguments in Python need to be strings which are unicodes | ||
# Python 3. This function takes keyword arguments, convert the keys to str. | ||||
def strkwargs(dic): | ||||
dic = dict((k.decode('latin-1'), v) for k, v in dic.iteritems()) | ||||
return dic | ||||
# keys of keyword arguments need to be unicode while passing into | ||||
# a function. This function helps us to convert those keys back to bytes | ||||
# again as we need to deal with bytes. | ||||
def byteskwargs(dic): | ||||
dic = dict((k.encode('latin-1'), v) for k, v in dic.iteritems()) | ||||
return dic | ||||
Pulkit Goyal
|
r30678 | # shlex.split() accepts unicodes on Python 3. This function takes bytes | ||
# argument, convert it into unicodes, pass into shlex.split(), convert the | ||||
# returned value to bytes and return that. | ||||
# TODO: handle shlex.shlex(). | ||||
def shlexsplit(s): | ||||
ret = shlex.split(s.decode('latin-1')) | ||||
return [a.encode('latin-1') for a in ret] | ||||
Yuya Nishihara
|
r30032 | else: | ||
Yuya Nishihara
|
r31372 | import cStringIO | ||
Yuya Nishihara
|
r31253 | bytechr = chr | ||
Yuya Nishihara
|
r31439 | bytestr = str | ||
Yuya Nishihara
|
r31382 | iterbytestr = iter | ||
Yuya Nishihara
|
r31820 | sysbytes = identity | ||
Yuya Nishihara
|
r31774 | sysstr = identity | ||
Yuya Nishihara
|
r30032 | |||
Martijn Pieters
|
r30133 | # 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. | ||||
def fsencode(filename): | ||||
if isinstance(filename, str): | ||||
return filename | ||||
Martijn Pieters
|
r30119 | else: | ||
Martijn Pieters
|
r30133 | raise TypeError( | ||
"expect str, not %s" % type(filename).__name__) | ||||
Martijn Pieters
|
r30119 | |||
Pulkit Goyal
|
r30300 | # 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. | ||||
Yuya Nishihara
|
r31774 | fsdecode = identity | ||
Pulkit Goyal
|
r30300 | |||
Pulkit Goyal
|
r30578 | def getoptb(args, shortlist, namelist): | ||
return getopt.getopt(args, shortlist, namelist) | ||||
Yuya Nishihara
|
r31774 | strkwargs = identity | ||
byteskwargs = identity | ||||
Pulkit Goyal
|
r30579 | |||
Yuya Nishihara
|
r31775 | oslinesep = os.linesep | ||
Pulkit Goyal
|
r30302 | osname = os.name | ||
Pulkit Goyal
|
r30303 | ospathsep = os.pathsep | ||
ossep = os.sep | ||||
Pulkit Goyal
|
r30623 | osaltsep = os.altsep | ||
Yuya Nishihara
|
r30472 | stdin = sys.stdin | ||
stdout = sys.stdout | ||||
stderr = sys.stderr | ||||
Augie Fackler
|
r31277 | if getattr(sys, 'argv', None) is not None: | ||
sysargv = sys.argv | ||||
Pulkit Goyal
|
r30624 | sysplatform = sys.platform | ||
Pulkit Goyal
|
r30500 | getcwd = os.getcwd | ||
Pulkit Goyal
|
r30668 | sysexecutable = sys.executable | ||
Pulkit Goyal
|
r30678 | shlexsplit = shlex.split | ||
Yuya Nishihara
|
r31372 | stringio = cStringIO.StringIO | ||
Augie Fackler
|
r31501 | maplist = map | ||
Pulkit Goyal
|
r30302 | |||
timeless
|
r28818 | empty = _queue.Empty | ||
queue = _queue.Queue | ||||
timeless
|
r28834 | |||
timeless
|
r28882 | class _pycompatstub(object): | ||
Yuya Nishihara
|
r29801 | def __init__(self): | ||
self._aliases = {} | ||||
timeless
|
r28882 | |||
Yuya Nishihara
|
r29801 | def _registeraliases(self, origin, items): | ||
"""Add items that will be populated at the first access""" | ||||
Augie Fackler
|
r30086 | items = map(sysstr, items) | ||
self._aliases.update( | ||||
(item.replace(sysstr('_'), sysstr('')).lower(), (origin, item)) | ||||
for item in items) | ||||
timeless
|
r28882 | |||
Gregory Szorc
|
r31566 | def _registeralias(self, origin, attr, name): | ||
"""Alias ``origin``.``attr`` as ``name``""" | ||||
self._aliases[sysstr(name)] = (origin, sysstr(attr)) | ||||
Yuya Nishihara
|
r29801 | def __getattr__(self, name): | ||
timeless
|
r28882 | try: | ||
Yuya Nishihara
|
r29801 | origin, item = self._aliases[name] | ||
except KeyError: | ||||
raise AttributeError(name) | ||||
self.__dict__[name] = obj = getattr(origin, item) | ||||
return obj | ||||
timeless
|
r28882 | |||
Pulkit Goyal
|
r29566 | httpserver = _pycompatstub() | ||
timeless
|
r28882 | urlreq = _pycompatstub() | ||
urlerr = _pycompatstub() | ||||
Yuya Nishihara
|
r30030 | if not ispy3: | ||
Pulkit Goyal
|
r29566 | import BaseHTTPServer | ||
import CGIHTTPServer | ||||
import SimpleHTTPServer | ||||
timeless
|
r28882 | import urllib2 | ||
import urllib | ||||
Gregory Szorc
|
r31569 | import urlparse | ||
Yuya Nishihara
|
r29801 | urlreq._registeraliases(urllib, ( | ||
timeless
|
r28882 | "addclosehook", | ||
"addinfourl", | ||||
"ftpwrapper", | ||||
"pathname2url", | ||||
"quote", | ||||
"splitattr", | ||||
"splitpasswd", | ||||
"splitport", | ||||
"splituser", | ||||
"unquote", | ||||
"url2pathname", | ||||
"urlencode", | ||||
)) | ||||
Yuya Nishihara
|
r29801 | urlreq._registeraliases(urllib2, ( | ||
timeless
|
r28882 | "AbstractHTTPHandler", | ||
"BaseHandler", | ||||
"build_opener", | ||||
"FileHandler", | ||||
"FTPHandler", | ||||
"HTTPBasicAuthHandler", | ||||
"HTTPDigestAuthHandler", | ||||
"HTTPHandler", | ||||
"HTTPPasswordMgrWithDefaultRealm", | ||||
"HTTPSHandler", | ||||
"install_opener", | ||||
"ProxyHandler", | ||||
"Request", | ||||
"urlopen", | ||||
)) | ||||
Gregory Szorc
|
r31569 | urlreq._registeraliases(urlparse, ( | ||
"urlparse", | ||||
"urlunparse", | ||||
)) | ||||
Yuya Nishihara
|
r29801 | urlerr._registeraliases(urllib2, ( | ||
timeless
|
r28882 | "HTTPError", | ||
"URLError", | ||||
)) | ||||
Yuya Nishihara
|
r29801 | httpserver._registeraliases(BaseHTTPServer, ( | ||
Pulkit Goyal
|
r29566 | "HTTPServer", | ||
"BaseHTTPRequestHandler", | ||||
)) | ||||
Yuya Nishihara
|
r29801 | httpserver._registeraliases(SimpleHTTPServer, ( | ||
Pulkit Goyal
|
r29566 | "SimpleHTTPRequestHandler", | ||
)) | ||||
Yuya Nishihara
|
r29801 | httpserver._registeraliases(CGIHTTPServer, ( | ||
Pulkit Goyal
|
r29566 | "CGIHTTPRequestHandler", | ||
)) | ||||
timeless
|
r28882 | |||
Yuya Nishihara
|
r29801 | else: | ||
Gregory Szorc
|
r31399 | import urllib.parse | ||
urlreq._registeraliases(urllib.parse, ( | ||||
"splitattr", | ||||
"splitpasswd", | ||||
"splitport", | ||||
"splituser", | ||||
Gregory Szorc
|
r31569 | "urlparse", | ||
"urlunparse", | ||||
Gregory Szorc
|
r31399 | )) | ||
Gregory Szorc
|
r31566 | urlreq._registeralias(urllib.parse, "unquote_to_bytes", "unquote") | ||
timeless
|
r28882 | import urllib.request | ||
Yuya Nishihara
|
r29801 | urlreq._registeraliases(urllib.request, ( | ||
timeless
|
r28882 | "AbstractHTTPHandler", | ||
"BaseHandler", | ||||
"build_opener", | ||||
"FileHandler", | ||||
"FTPHandler", | ||||
"ftpwrapper", | ||||
"HTTPHandler", | ||||
"HTTPSHandler", | ||||
"install_opener", | ||||
"pathname2url", | ||||
"HTTPBasicAuthHandler", | ||||
"HTTPDigestAuthHandler", | ||||
Gregory Szorc
|
r29414 | "HTTPPasswordMgrWithDefaultRealm", | ||
timeless
|
r28882 | "ProxyHandler", | ||
"Request", | ||||
"url2pathname", | ||||
"urlopen", | ||||
)) | ||||
Gregory Szorc
|
r31399 | import urllib.response | ||
urlreq._registeraliases(urllib.response, ( | ||||
"addclosehook", | ||||
"addinfourl", | ||||
)) | ||||
timeless
|
r28882 | import urllib.error | ||
Yuya Nishihara
|
r29801 | urlerr._registeraliases(urllib.error, ( | ||
timeless
|
r28882 | "HTTPError", | ||
"URLError", | ||||
)) | ||||
Pulkit Goyal
|
r29566 | import http.server | ||
Yuya Nishihara
|
r29801 | httpserver._registeraliases(http.server, ( | ||
Pulkit Goyal
|
r29566 | "HTTPServer", | ||
"BaseHTTPRequestHandler", | ||||
"SimpleHTTPRequestHandler", | ||||
"CGIHTTPRequestHandler", | ||||
)) | ||||
Gregory Szorc
|
r31400 | |||
# 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') | ||||
Pulkit Goyal
|
r31842 | # 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') | ||||
Gregory Szorc
|
r31400 | urlreq.quote = quote | ||
Pulkit Goyal
|
r31842 | urlreq.urlencode = urlencode | ||