tests/logexceptions.py

convert: correctly convert paths to UTF-8 for Subversion

The previous code using encoding.tolocal() only worked by chance in these
situations:

* The string is ASCII: The fast path was triggered and the string was returned
  unmodified.
* The local encoding is UTF-8: The source and target encoding is the same.
* The string is not valid UTF-8 and the native encoding is ISO-8859-1: If the
  string doesn’t decode using UTF-8, ISO-8859-1 is tried as a fallback. During
  `hg convert`, the local encoding is always UTF-8. The irony is that in this
  case, encoding.tolocal() behaves like what someone would expect the reverse
  function, encoding.fromlocal(), to do.

When the locale encoding is ISO-8859-15, trying to convert a SVN repo `/tmp/a€`
failed before like this:

file:///tmp/a%C2%A4 does not look like a Subversion repository to libsvn version 1.14.0

The correct URL is `file:///tmp/a%E2%82%AC`.

Unlike previously (with the ISO-8859-1 fallback), decoding the path using the
locale encoding can fail. In this case, we have to bail out, as Subversion
won’t be able to do anything useful with the path.

# logexceptions.py - Write files containing info about Mercurial exceptions
#
# Copyright 2017 Matt Mackall <[e-mail]>
#
# 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

import inspect
import os
import sys
import traceback
import uuid

from mercurial import (
    dispatch,
    extensions,
)


def handleexception(orig, ui):
    res = orig(ui)

    if not ui.environ.get(b'HGEXCEPTIONSDIR'):
        return res

    dest = os.path.join(
        ui.environ[b'HGEXCEPTIONSDIR'], str(uuid.uuid4()).encode('ascii')
    )

    exc_type, exc_value, exc_tb = sys.exc_info()

    stack = []
    tb = exc_tb
    while tb:
        stack.append(tb)
        tb = tb.tb_next
    stack.reverse()

    hgframe = 'unknown'
    hgline = 'unknown'

    # Find the first Mercurial frame in the stack.
    for tb in stack:
        mod = inspect.getmodule(tb)
        if not mod.__name__.startswith(('hg', 'mercurial')):
            continue

        frame = tb.tb_frame

        try:
            with open(inspect.getsourcefile(tb), 'r') as fh:
                hgline = fh.readlines()[frame.f_lineno - 1].strip()
        except (IndexError, OSError):
            pass

        hgframe = '%s:%d' % (frame.f_code.co_filename, frame.f_lineno)
        break

    primary = traceback.extract_tb(exc_tb)[-1]
    primaryframe = '%s:%d' % (primary.filename, primary.lineno)

    with open(dest, 'wb') as fh:
        parts = [
            str(exc_value),
            primaryframe,
            hgframe,
            hgline,
            ui.environ[b'TESTNAME'].decode('utf-8', 'replace'),
        ]
        fh.write(b'\0'.join(p.encode('utf-8', 'replace') for p in parts))


def extsetup(ui):
    extensions.wrapfunction(dispatch, 'handlecommandexception', handleexception)