view contrib/hgclient.py @ 44651:00e0c5c06ed5

pycompat: change argv conversion semantics

Use of os.fsencode() to convert Python's sys.argv back to bytes
was not correct because it isn't the logically inverse operation
from what CPython was doing under the hood.

This commit changes the logic for doing the str -> bytes
conversion. This required a separate implementation for
POSIX and Windows.

The Windows behavior is arguably not ideal. The previous
behavior on Windows was leading to failing tests, such as
test-http-branchmap.t, which defines a utf-8 branch name
via a command argument. Previously, Mercurial's argument
parser looked to be receiving wchar_t bytes in some cases.
After this commit, behavior on Windows is compatible with
Python 2, where CPython did not implement `int wmain()` and
Windows was performing a Unicode to ANSI conversion on the
wchar_t native command line.

Arguably better behavior on Windows would be for Mercurial to
preserve the original Unicode sequence coming from Python and
to wrap this in a bytes-like type so we can round trip safely.
But, this would be new, backwards incompatible behavior. My
goal for this commit was to converge Mercurial behavior on
Python 3 on Windows to fix busted tests. And I believe I was
successful, as this commit fixes 9 tests on my Windows
machine and 14 tests in the AWS CI environment!

Differential Revision: https://phab.mercurial-scm.org/D8337

# A minimal client for Mercurial's command server

from __future__ import absolute_import, print_function

import io
import os
import re
import signal
import socket
import struct
import subprocess
import sys
import time

if sys.version_info[0] >= 3:
    stdout = sys.stdout.buffer
    stderr = sys.stderr.buffer
    stringio = io.BytesIO

    def bprint(*args):
        # remove b'' as well for ease of test migration
        pargs = [re.sub(br'''\bb(['"])''', br'\1', b'%s' % a) for a in args]
        stdout.write(b' '.join(pargs) + b'\n')


else:
    import cStringIO

    stdout = sys.stdout
    stderr = sys.stderr
    stringio = cStringIO.StringIO
    bprint = print


def connectpipe(path=None, extraargs=()):
    cmdline = [b'hg', b'serve', b'--cmdserver', b'pipe']
    if path:
        cmdline += [b'-R', path]
    cmdline.extend(extraargs)

    def tonative(cmdline):
        if os.name != 'nt':
            return cmdline
        return [arg.decode("utf-8") for arg in cmdline]

    server = subprocess.Popen(
        tonative(cmdline), stdin=subprocess.PIPE, stdout=subprocess.PIPE
    )

    return server


class unixconnection(object):
    def __init__(self, sockpath):
        self.sock = sock = socket.socket(socket.AF_UNIX)
        sock.connect(sockpath)
        self.stdin = sock.makefile('wb')
        self.stdout = sock.makefile('rb')

    def wait(self):
        self.stdin.close()
        self.stdout.close()
        self.sock.close()


class unixserver(object):
    def __init__(self, sockpath, logpath=None, repopath=None):
        self.sockpath = sockpath
        cmdline = [b'hg', b'serve', b'--cmdserver', b'unix', b'-a', sockpath]
        if repopath:
            cmdline += [b'-R', repopath]
        if logpath:
            stdout = open(logpath, 'a')
            stderr = subprocess.STDOUT
        else:
            stdout = stderr = None
        self.server = subprocess.Popen(cmdline, stdout=stdout, stderr=stderr)
        # wait for listen()
        while self.server.poll() is None:
            if os.path.exists(sockpath):
                break
            time.sleep(0.1)

    def connect(self):
        return unixconnection(self.sockpath)

    def shutdown(self):
        os.kill(self.server.pid, signal.SIGTERM)
        self.server.wait()


def writeblock(server, data):
    server.stdin.write(struct.pack(b'>I', len(data)))
    server.stdin.write(data)
    server.stdin.flush()


def readchannel(server):
    data = server.stdout.read(5)
    if not data:
        raise EOFError
    channel, length = struct.unpack('>cI', data)
    if channel in b'IL':
        return channel, length
    else:
        return channel, server.stdout.read(length)


def sep(text):
    return text.replace(b'\\', b'/')


def runcommand(
    server, args, output=stdout, error=stderr, input=None, outfilter=lambda x: x
):
    bprint(b'*** runcommand', b' '.join(args))
    stdout.flush()
    server.stdin.write(b'runcommand\n')
    writeblock(server, b'\0'.join(args))

    if not input:
        input = stringio()

    while True:
        ch, data = readchannel(server)
        if ch == b'o':
            output.write(outfilter(data))
            output.flush()
        elif ch == b'e':
            error.write(data)
            error.flush()
        elif ch == b'I':
            writeblock(server, input.read(data))
        elif ch == b'L':
            writeblock(server, input.readline(data))
        elif ch == b'm':
            bprint(b"message: %r" % data)
        elif ch == b'r':
            (ret,) = struct.unpack('>i', data)
            if ret != 0:
                bprint(b' [%d]' % ret)
            return ret
        else:
            bprint(b"unexpected channel %c: %r" % (ch, data))
            if ch.isupper():
                return


def check(func, connect=connectpipe):
    stdout.flush()
    server = connect()
    try:
        return func(server)
    finally:
        server.stdin.close()
        server.wait()


def checkwith(connect=connectpipe, **kwargs):
    def wrap(func):
        return check(func, lambda: connect(**kwargs))

    return wrap