contrib/python-zstandard/tests/test_buffer_util.py

zstandard: vendor python-zstandard 0.10.1

This was just released.

The upstream source distribution from PyPI was extracted. Unwanted
files were removed.

The clang-format ignore list was updated to reflect the new source
of files.

setup.py was updated to pass a new argument to python-zstandard's
function for returning an Extension instance. Upstream had to change
to use relative paths because Python 3.7's packaging doesn't
seem to like absolute paths when defining sources, includes, etc.
The default relative path calculation is relative to setup_zstd.py
which is different from the directory of Mercurial's setup.py.

The project contains a vendored copy of zstandard 1.3.6. The old
version was 1.3.4.

The API should be backwards compatible and nothing in core should
need adjusted. However, there is a new "chunker" API that we
may find useful in places where we want to emit compressed chunks
of a fixed size.

There are a pair of bug fixes in 0.10.0 with regards to
compressobj() and decompressobj() when block flushing is used. I
actually found these bugs when introducing these APIs in Mercurial!
But existing Mercurial code is not affected because we don't
perform block flushing.

# no-check-commit because 3rd party code has different style guidelines

Differential Revision: https://phab.mercurial-scm.org/D4911

import struct
import unittest

import zstandard as zstd

ss = struct.Struct('=QQ')


class TestBufferWithSegments(unittest.TestCase):
    def test_arguments(self):
        with self.assertRaises(TypeError):
            zstd.BufferWithSegments()

        with self.assertRaises(TypeError):
            zstd.BufferWithSegments(b'foo')

        # Segments data should be a multiple of 16.
        with self.assertRaisesRegexp(ValueError, 'segments array size is not a multiple of 16'):
            zstd.BufferWithSegments(b'foo', b'\x00\x00')

    def test_invalid_offset(self):
        with self.assertRaisesRegexp(ValueError, 'offset within segments array references memory'):
            zstd.BufferWithSegments(b'foo', ss.pack(0, 4))

    def test_invalid_getitem(self):
        b = zstd.BufferWithSegments(b'foo', ss.pack(0, 3))

        with self.assertRaisesRegexp(IndexError, 'offset must be non-negative'):
            test = b[-10]

        with self.assertRaisesRegexp(IndexError, 'offset must be less than 1'):
            test = b[1]

        with self.assertRaisesRegexp(IndexError, 'offset must be less than 1'):
            test = b[2]

    def test_single(self):
        b = zstd.BufferWithSegments(b'foo', ss.pack(0, 3))
        self.assertEqual(len(b), 1)
        self.assertEqual(b.size, 3)
        self.assertEqual(b.tobytes(), b'foo')

        self.assertEqual(len(b[0]), 3)
        self.assertEqual(b[0].offset, 0)
        self.assertEqual(b[0].tobytes(), b'foo')

    def test_multiple(self):
        b = zstd.BufferWithSegments(b'foofooxfooxy', b''.join([ss.pack(0, 3),
                                                               ss.pack(3, 4),
                                                               ss.pack(7, 5)]))
        self.assertEqual(len(b), 3)
        self.assertEqual(b.size, 12)
        self.assertEqual(b.tobytes(), b'foofooxfooxy')

        self.assertEqual(b[0].tobytes(), b'foo')
        self.assertEqual(b[1].tobytes(), b'foox')
        self.assertEqual(b[2].tobytes(), b'fooxy')


class TestBufferWithSegmentsCollection(unittest.TestCase):
    def test_empty_constructor(self):
        with self.assertRaisesRegexp(ValueError, 'must pass at least 1 argument'):
            zstd.BufferWithSegmentsCollection()

    def test_argument_validation(self):
        with self.assertRaisesRegexp(TypeError, 'arguments must be BufferWithSegments'):
            zstd.BufferWithSegmentsCollection(None)

        with self.assertRaisesRegexp(TypeError, 'arguments must be BufferWithSegments'):
            zstd.BufferWithSegmentsCollection(zstd.BufferWithSegments(b'foo', ss.pack(0, 3)),
                                              None)

        with self.assertRaisesRegexp(ValueError, 'ZstdBufferWithSegments cannot be empty'):
            zstd.BufferWithSegmentsCollection(zstd.BufferWithSegments(b'', b''))

    def test_length(self):
        b1 = zstd.BufferWithSegments(b'foo', ss.pack(0, 3))
        b2 = zstd.BufferWithSegments(b'barbaz', b''.join([ss.pack(0, 3),
                                                          ss.pack(3, 3)]))

        c = zstd.BufferWithSegmentsCollection(b1)
        self.assertEqual(len(c), 1)
        self.assertEqual(c.size(), 3)

        c = zstd.BufferWithSegmentsCollection(b2)
        self.assertEqual(len(c), 2)
        self.assertEqual(c.size(), 6)

        c = zstd.BufferWithSegmentsCollection(b1, b2)
        self.assertEqual(len(c), 3)
        self.assertEqual(c.size(), 9)

    def test_getitem(self):
        b1 = zstd.BufferWithSegments(b'foo', ss.pack(0, 3))
        b2 = zstd.BufferWithSegments(b'barbaz', b''.join([ss.pack(0, 3),
                                                          ss.pack(3, 3)]))

        c = zstd.BufferWithSegmentsCollection(b1, b2)

        with self.assertRaisesRegexp(IndexError, 'offset must be less than 3'):
            c[3]

        with self.assertRaisesRegexp(IndexError, 'offset must be less than 3'):
            c[4]

        self.assertEqual(c[0].tobytes(), b'foo')
        self.assertEqual(c[1].tobytes(), b'bar')
        self.assertEqual(c[2].tobytes(), b'baz')