Beispiel #1
0
def test_mailman_chain():
    name = "bigbang-dev-test.txt"

    #archive loaded from mbox
    arx = archive.Archive(name,archive_dir="tests/data",mbox=True)

    arx.save("test.csv")

    #archive loaded from stored csv
    arx2 = archive.load("test.csv")

    print arx.data.dtypes
    print arx.data.shape

    assert arx.data.shape == arx2.data.shape, \
        "Original and restored archives are different shapes"

    assert (arx2.data.index == arx.data.index).all(), \
        "Original and restored archives have nonidentical indices"

    assert [t.get_num_messages() for t in arx.get_threads()] == [3,1,2], \
        "Thread message count in mbox archive is off"
    assert [t.get_num_messages() for t in arx2.get_threads()] == [3,1,2], \
        "Thread message count in restored archive is off"

    # smoke test entity resolution
    arx2.resolve_entities()

    os.remove("test.csv")
Beispiel #2
0
def test_mailman_chain():
    name = "bigbang-dev-test.txt"

    #archive loaded from mbox
    arx = archive.Archive(name, archive_dir="tests/data", mbox=True)

    arx.save("test.csv")

    #archive loaded from stored csv
    arx2 = archive.load("test.csv")

    print arx.data.dtypes
    print arx.data.shape

    assert arx.data.shape == arx2.data.shape, \
        "Original and restored archives are different shapes"

    assert (arx2.data.index == arx.data.index).all(), \
        "Original and restored archives have nonidentical indices"

    assert [t.get_num_messages() for t in arx.get_threads()] == [3,1,2], \
        "Thread message count in mbox archive is off"
    assert [t.get_num_messages() for t in arx2.get_threads()] == [3,1,2], \
        "Thread message count in restored archive is off"

    # smoke test entity resolution
    arx2.resolve_entities()

    os.remove("test.csv")
Beispiel #3
0
def test_mailman_chain():
    url = "http://mail.scipy.org/pipermail/ipython-dev/"

    arx = archive.Archive(url)

    arx.save("test.csv")

    arx2 = archive.load("test.csv")

    arx3 = archive.Archive("ipython-dev")

    assert arx.data.shape == arx.data.shape

    os.remove("test.csv")
Beispiel #4
0
def test_mailman_chain():
    url = "http://mail.scipy.org/pipermail/ipython-dev/"

    mailman.collect_from_url(url)
    mailman.unzip_archive(url)

    arx = archive.Archive(url)

    arx.save("test.csv")

    arx2 = archive.load("test.csv")

    assert arx.data.shape == arx.data.shape

    os.remove("test.csv")
Beispiel #5
0
    def test_mailman_chain(self):
        name = "bigbang-dev-test.txt"

        # archive loaded from mbox
        arx = archive.Archive(name,
                              archive_dir=CONFIG.test_data_path,
                              mbox=True)

        arx.save("test.csv")

        # archive loaded from stored csv
        arx2 = archive.load("test.csv")

        print(arx.data.dtypes)
        print(arx.data.shape)

        self.assertTrue(
            arx.data.shape == arx2.data.shape,
            msg="Original and restored archives are different shapes",
        )

        self.assertTrue(
            (arx2.data.index == arx.data.index).all(),
            msg="Original and restored archives have nonidentical indices",
        )

        self.assertTrue(
            [t.get_num_messages() for t in arx.get_threads()] == [3, 1, 2],
            msg="Thread message count in mbox archive is off",
        )
        self.assertTrue(
            [t.get_num_messages() for t in arx2.get_threads()] == [3, 1, 2],
            msg="Thread message count in restored archive is off",
        )

        # smoke test entity resolution
        arx2.resolve_entities()

        os.remove("test.csv")