Exemplo n.º 1
0
def test_optional_indexing(store, fcs):
    store.put(fcs)
    foo1 = FC({
        'NAME': {
            'Foo Bar': 1
        },
        'boNAME': {
            'bruce': 1,
            'patti': 1,
            'foo': 1,
            'bar': 1
        },
    })
    foo2 = FC({
        'NAME': {
            'Foo Baz': 1
        },
        'boNAME': {
            'foo': 1,
            'baz': 1
        },
    })
    store.put([('foo1', foo1), ('foo2', foo2)], indexes=False)

    # Are they really there?
    assert store.get('foo1') == foo1
    assert store.get('foo2') == foo2

    assert frozenset(store.keyword_scan_ids('foo1')) \
        == frozenset(['boss', 'patti'])
    assert frozenset(store.index_scan_ids('boNAME', 'patti')) \
        == frozenset(['patti'])
Exemplo n.º 2
0
def test_index_key_flip(fcstore):
    # Make sure only values from the specified index are returned.
    fca, fcb = FC(), FC()
    fca[u'a']['foo'] = 1
    fca[u'b']['foo'] = 1

    fcstore.define_index(u'a', feature_index('a'),
                         lambda s: s.lower().encode('utf-8'))
    fcstore.define_index(u'b', feature_index('b'),
                         lambda s: s.lower().encode('utf-8'))

    fcstore.put([('fca', fca), ('fcb', fcb)])

    assert list(fcstore.index_scan(u'a', u'foo')) == ['fca']
Exemplo n.º 3
0
def fcs_texts(fcs):
    return [('boss',
             FC({
                 'NAME': {
                     'Bruce Springsteen': 2,
                     'The Boss': 1,
                 },
                 'boNAME': {
                     'bruce': 2,
                     'springsteen': 5,
                     'the': 1,
                     'boss': 1,
                 },
                 'body': {
                     u"The screen door slams, Mary's dress sways": 1
                 },
                 'body2': {
                     u"Like a vision she dances across the porch": 1
                 },
             })),
            ('patti',
             FC({
                 'NAME': {
                     'Patti Scialfa': 1,
                 },
                 'boNAME': {
                     'patti': 10,
                     'scialfa': 1,
                 },
                 'body': {
                     u"I come from down in the valley": 1
                 },
             })),
            ('big-man',
             FC({
                 'NAME': {
                     'Clarence Clemons': 8,
                     'The Big Man': 1,
                 },
                 'boNAME': {
                     'clarence': 8,
                     'clemons': 8,
                     'the': 1,
                     'big': 1,
                     'man': 1,
                 },
                 'body': {
                     u"Drinking warm beer in the soft summer rain": 1
                 },
             }))]
Exemplo n.º 4
0
def mk_fc_names(*names):
    assert len(names) > 0
    feat = FC()
    feat[u'canonical_name'][names[0]] = 1
    for name in names:
        feat[u'NAME'][name] += 1
    return feat
Exemplo n.º 5
0
def test_fulltext_scan(store, fcs_texts):
    store.put(fcs_texts)

    query = FC({u'body': {u'valley': 1}})
    assert frozenset(map(itemgetter(1),
                         store.fulltext_scan_ids(query_fc=query))) \
        == frozenset(['patti'])

    query = FC({u'body': {u'in': 1}})
    assert frozenset(map(itemgetter(1),
                         store.fulltext_scan_ids(query_fc=query))) \
        == frozenset(['patti', 'big-man'])

    query = FC({u'body': {u"mary's": 1}})
    assert frozenset(map(itemgetter(1),
                         store.fulltext_scan_ids(query_fc=query))) \
        == frozenset(['boss'])
Exemplo n.º 6
0
def test_scan_all_weird(store):
    ids = [
        '99bc49e2492a48cb9179d70d3c11ea13',
        'd858432fd50f4cb5a01af290358cb0d1',
        'be75888da4854c15859692b6db590f55',
    ]
    assert len(list(store.scan_ids())) == 0
    store.put([(id, FC()) for id in ids])
    assert list(store.scan_ids()) == sorted(ids)
Exemplo n.º 7
0
def test_one_to_many_indexing(kvl):  # noqa
    # This config defines an index named `foo` that automatically indexes
    # values in the `bar` and `baz` features. This means that an index scan
    # on the `foo` index will check values in the `bar` and `baz` features.
    index_config = [{'foo': ['bar', 'baz']}]
    store = Store(kvl, feature_indexes=index_config)

    fcx, fcy, fcz = FC(), FC(), FC()
    fcx['unrelated']['a'] = 1
    fcy['bar']['a'] = 1
    fcy['baz']['a'] = 1
    fcz['baz']['a'] = 1
    fcy['baz']['c'] = 1
    fcz['baz']['b'] = 1

    store.put([('x', fcx), ('y', fcy), ('z', fcz)])

    assert list(store.index_scan('foo', 'a')) == ['y', 'z']
    assert list(store.index_scan('foo', 'b')) == ['z']
    assert list(store.index_scan('foo', 'c')) == ['y']
Exemplo n.º 8
0
def test_fulltext_scan_indexes(store, fcs_texts):
    store.put(fcs_texts)

    # Make sure we search features in whitelist.
    query = FC({u'body': {u'valley': 1}})
    assert frozenset(map(itemgetter(1),
                         store.fulltext_scan_ids(query_fc=query,
                                                 indexes=['body']))) \
        == frozenset(['patti'])

    # Make sure we dont search features out of whitelist.
    query = FC({u'body': {u'in': 1}})
    ids = list(store.fulltext_scan_ids(query_fc=query, indexes=[]))
    assert len(ids) == 0

    # Make sure we raise ValueError when trying to scan non-indexed feature.
    query = FC({u'body': {u'in': 1}})
    with pytest.raises(ValueError):
        ids = list(
            store.fulltext_scan_ids(query_fc=query,
                                    indexes=['body', 'i-dont-exist']))
Exemplo n.º 9
0
def test_keyword_scan_emphemeral(store, fcs):
    store.put(fcs)
    query_id = 'pattim'

    query_fc = FC({'NAME': {'Patti Mayonnaise': 1}})
    assert frozenset(store.keyword_scan_ids(query_id, query_fc)) \
        == frozenset()

    query_fc['boNAME']['patti'] += 1
    query_fc['boNAME']['mayonnaise'] += 1
    assert frozenset(store.keyword_scan_ids(query_id, query_fc)) \
        == frozenset(['patti'])
Exemplo n.º 10
0
def test_keyword_scan_partial(store, fcs):
    store.put(fcs)
    assert_set_eq(store.keyword_scan('boss'),
                  [('big-man', fcget(fcs, 'big-man'))])

    expected = FC({
        'NAME': {
            'Clarence Clemons': 8,
            'The Big Man': 1
        },
    })
    assert_set_eq(store.keyword_scan('boss', feature_names=['NAME']),
                  [('big-man', expected)])
Exemplo n.º 11
0
def test_geotime_filter():
    fname = '!both_co_LOC_1'
    gc1 = GeoCoords({'foo': [(10, 10, 10, None)]})
    gc2 = GeoCoords({'foo': [(10, 10, 10, None), (-10, 10, 10, 10)]})
    gc3 = GeoCoords({'foo': [(-10, 10, 10, None), (10, 10, 10, 10)]})

    fc1 = FC()
    fc1[fname] = gc1
    fc2 = FC()
    fc2[fname] = gc2
    fc3 = FC()
    fc3[fname] = gc3

    pred = geotime().set_query_params({
        'min_lat': 0, 'max_lat': 20,
        'min_lon': -20, 'max_lon': 0,
        'min_time': 0,
    }).create_predicate()

    results = filter(pred, [('', fc1), ('', fc2), ('', fc3)])
    assert len(results) == 1
    assert results[0][1] == fc2
Exemplo n.º 12
0
def fcs():
    return [('boss',
             FC({
                 'NAME': {
                     'Bruce Springsteen': 2,
                     'The Boss': 1,
                 },
                 'boNAME': {
                     'bruce': 2,
                     'springsteen': 5,
                     'the': 1,
                     'boss': 1,
                 },
             })),
            ('patti',
             FC({
                 'NAME': {
                     'Patti Scialfa': 1,
                 },
                 'boNAME': {
                     'patti': 10,
                     'scialfa': 1,
                 },
             })),
            ('big-man',
             FC({
                 'NAME': {
                     'Clarence Clemons': 8,
                     'The Big Man': 1,
                 },
                 'boNAME': {
                     'clarence': 8,
                     'clemons': 8,
                     'the': 1,
                     'big': 1,
                     'man': 1,
                 },
             }))]
Exemplo n.º 13
0
def test_scan_all_random(store):
    import random
    ids = []
    for _ in xrange(100):
        s = ''.join([
            chr(random.randrange(ord('a'),
                                 ord('z') + 1))
            for _ in xrange(random.randrange(2, 20))
        ])
        ids.append(s)
    ids = list(set(ids))

    assert len(list(store.scan_ids())) == 0
    store.put([(id, FC()) for id in ids])
    assert list(store.scan_ids()) == sorted(ids)
Exemplo n.º 14
0
def test_fulltext_mapping_keyword(elastic_address, namespace_string,
                                  fcs_texts):
    store = ElasticStoreSync(hosts=elastic_address,
                             namespace=NAMESPACE,
                             type=namespace_string,
                             fulltext_indexes=[{
                                 'body': ['body2'],
                             }])
    try:
        store.put(fcs_texts)

        query = FC({'body': {'vision': 1}})
        assert frozenset(map(itemgetter(1),
                             store.fulltext_scan_ids(query_fc=query))) \
            == frozenset(['boss'])
    finally:
        store.delete_all()
Exemplo n.º 15
0
def test_index_mapping_keyword(elastic_address, namespace_string, fcs):
    store = ElasticStoreSync(hosts=elastic_address,
                             namespace=NAMESPACE,
                             type=namespace_string,
                             feature_indexes=[{
                                 'NAME': {
                                     'es_index_type': 'string',
                                     'feature_names': ['NAME', 'boNAME'],
                                 },
                             }, {
                                 'boNAME': {
                                     'es_index_type': 'string',
                                     'feature_names': []
                                 },
                             }])
    try:
        store.put(fcs)

        query = FC({'NAME': {'The Boss': 1, 'clarence': 1}})
        assert frozenset(store.keyword_scan_ids('ephemeral', query)) \
            == frozenset(['boss', 'big-man'])
    finally:
        store.delete_all()
Exemplo n.º 16
0
def test_put_overwrite(store, fcs):
    store.put(fcs)
    newfc = FC({'NAME': {'foo': 1, 'bar': 1}})
    store.put([('boss', newfc)])
    got = store.get('boss')
    assert got == newfc
Exemplo n.º 17
0
def test_scan_ids(store):
    store.put([
        ('a', FC()),
        ('b', FC()),
        ('c', FC()),
        ('d', FC()),
        ('e', FC()),
        ('f', FC()),
        ('g', FC()),
        ('h', FC()),
        ('i', FC()),
        ('j', FC()),
        ('k', FC()),
        ('l', FC()),
        ('m', FC()),
        ('n', FC()),
        ('o', FC()),
    ])
    expected = 'abcdefghijklmno'
    got = ''.join(sorted(store.scan_ids()))
    assert expected == got
Exemplo n.º 18
0
def test_byte_keys(store):
    fc = FC({'NAME': {'Foo Bar': 1}})
    store.put([('\x00\xff\xf4', fc)])
Exemplo n.º 19
0
 def fc_from_dict(self, fc_dict):
     d = {}
     for name, feat in fc_dict.iteritems():
         d[name] = cbor.loads(base64.b64decode(feat))
     return FC(d)