view hgext/fsmonitor/pywatchman/encoding.py @ 39772:ae531f5e583c

testing: add interface unit tests for file storage

Our strategy for supporting alternate storage backends is to define
interfaces for everything then "code to the interface."

We already have interfaces for various primitives, including file
and manifest storage.

What we don't have is generic unit tests for those interfaces. Up
to this point we've been relying on high-level integration tests
(mainly in the form of existing .t tests) to test alternate storage
backends. And my experience with developing the "simple store" test
extension is that such testing is very tedious: it takes several
minutes to run all tests and when you find a failure, it is often
non-trivial to debug.

This commit starts to change that.

This commit introduces the mercurial.testing.storage module. It
contains testing code for storage. Currently, it defines some
unittest.TestCase classes for testing the file storage interfaces.
It also defines some factory functions that allow a caller to easily
spawn a custom TestCase "bound" to a specific file storage backend
implementation.

A new .py test has been added. It simply defines a callable to produce
filelog and transaction instances on demand and then "registers" the
various test classes so the filelog class can be tested with the
storage interface unit tests.

As part of writing the tests, I identified a couple of apparent
bugs in revlog.py and filelog.py! These are tracked with inline
TODO comments.

Writing the tests makes it more obvious where the storage interface
is lacking. For example, we raise either IndexError or
error.LookupError for missing revisions depending on whether we
use an integer revision or a node. Also, we raise error.RevlogError
in various places when we should be raising a storage-agnostic
error type.

The storage interfaces are currently far from perfect and there is much
work to be done to improve them. But at least with this commit we
finally have the start of unit tests that can be used to "qualify"
the behavior of a storage backend. And when implementing and debugging
new storage backends, we now have an obvious place to define new
tests and have obvious places to insert breakpoints to facilitate
debugging. This should be invaluable when implementing new storage
backends.

I added the mercurial.testing package because these interface
conformance tests are generic and need to be usable by all storage
backends. Having the code live in tests/ would make it difficult for
storage backends implemented in extensions to test their interface
conformance. First, it would require obtaining a copy of Mercurial's
storage test code in order to test. Second, it would make testing
against multiple Mercurial versions difficult, as you would need to
import N copies of the storage testing code in order to achieve test
coverage. By making the test code part of the Mercurial distribution
itself, extensions can `import mercurial.testing.*` to access and run
the test code. The test will run against whatever Mercurial version
is active.

FWIW I've always wanted to move parts of run-tests.py into the
mercurial.* package to make the testing story simpler (e.g. imagine an
`hg debugruntests` command that could invoke the test harness). While I
have no plans to do that in the near future, establishing the
mercurial.testing package does provide a natural home for that code
should someone do this in the future.

Differential Revision: https://phab.mercurial-scm.org/D4650

# Copyright 2016-present Facebook, Inc.
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
#  * Redistributions of source code must retain the above copyright notice,
#    this list of conditions and the following disclaimer.
#
#  * Redistributions in binary form must reproduce the above copyright notice,
#    this list of conditions and the following disclaimer in the documentation
#    and/or other materials provided with the distribution.
#
#  * Neither the name Facebook nor the names of its contributors may be used to
#    endorse or promote products derived from this software without specific
#    prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
# no unicode literals

'''Module to deal with filename encoding on the local system, as returned by
Watchman.'''

import sys

from . import (
    compat,
)

if compat.PYTHON3:
    default_local_errors = 'surrogateescape'

    def get_local_encoding():
        if sys.platform == 'win32':
            # Watchman always returns UTF-8 encoded strings on Windows.
            return 'utf-8'
        # On the Python 3 versions we support, sys.getfilesystemencoding never
        # returns None.
        return sys.getfilesystemencoding()
else:
    # Python 2 doesn't support surrogateescape, so use 'strict' by
    # default. Users can register a custom surrogateescape error handler and use
    # that if they so desire.
    default_local_errors = 'strict'

    def get_local_encoding():
        if sys.platform == 'win32':
            # Watchman always returns UTF-8 encoded strings on Windows.
            return 'utf-8'
        fsencoding = sys.getfilesystemencoding()
        if fsencoding is None:
            # This is very unlikely to happen, but if it does, just use UTF-8
            fsencoding = 'utf-8'
        return fsencoding

def encode_local(s):
    return s.encode(get_local_encoding(), default_local_errors)

def decode_local(bs):
    return bs.decode(get_local_encoding(), default_local_errors)