Python elasticsearch_dsl.Keyword() Examples

def create_doctype(index_name, similarity):
    if similarity == 'default':
        wiki_content_field = Text()
        qb_content_field = Text()
    else:
        wiki_content_field = Text(similarity=similarity)
        qb_content_field = Text(similarity=similarity)

    class Answer(Document):
        page = Text(fields={'raw': Keyword()})
        wiki_content = wiki_content_field
        qb_content = qb_content_field

        class Meta:
            index = index_name

    return Answer 

def __init__(
        self,
        name,
        es_field: str = None,
        elastic_mapping_type: Field = None,
        length_quantity: "Quantity" = None,
        has_only_quantity: "Quantity" = None,
        nested_quantity: "Quantity" = None,
    ):

        self.name = name
        self.es_field = es_field if es_field is not None else name
        self.elastic_mapping_type = (
            Keyword if elastic_mapping_type is None else elastic_mapping_type
        )
        self.length_quantity = length_quantity
        self.has_only_quantity = has_only_quantity
        self.nested_quantity = nested_quantity 

def _query(self, quantity, o, value, nested=None):
        field = self._field(quantity, nested=nested)
        if o in _cmp_operators:
            return Q("range", **{field: {_cmp_operators[o]: value}})

        if quantity.elastic_mapping_type == Text:
            query_type = "match"
        elif quantity.elastic_mapping_type in [Keyword, Integer]:
            query_type = "term"
        else:
            raise NotImplementedError("Quantity has unsupported ES field type")

        if o in ["=", ""]:
            return Q(query_type, **{field: value})

        if o == "!=":
            return ~Q(
                query_type, **{field: value}
            )  # pylint: disable=invalid-unary-operand-type

        raise Exception("Unknown operator %s" % o) 

def test_properties_can_iterate_over_all_the_fields():
    m = mapping.Mapping()
    m.field('f1', 'text', test_attr='f1', fields={'f2': Keyword(test_attr='f2')})
    m.field('f3', Nested(test_attr='f3', properties={
            'f4': Text(test_attr='f4')}))

    assert {'f1', 'f2', 'f3', 'f4'} == {f.test_attr for f in m.properties._collect_fields()} 

def test_mapping_can_collect_multiple_analyzers():
    a1 = analysis.analyzer(
        'my_analyzer1',
        tokenizer='keyword',
        filter=['lowercase', analysis.token_filter('my_filter1', 'stop', stopwords=['a', 'b'])],
    )
    a2 = analysis.analyzer(
        'my_analyzer2',
        tokenizer=analysis.tokenizer('trigram', 'nGram', min_gram=3, max_gram=3),
        filter=[analysis.token_filter('my_filter2', 'stop', stopwords=['c', 'd'])],
    )
    m = mapping.Mapping()
    m.field('title', 'text', analyzer=a1, search_analyzer=a2)
    m.field(
        'text', 'text', analyzer=a1,
        fields={
            'english': Text(analyzer=a1),
            'unknown': Keyword(analyzer=a1, search_analyzer=a2),
        }
    )
    assert {
       'analyzer': {
           'my_analyzer1': {'filter': ['lowercase', 'my_filter1'],
                            'tokenizer': 'keyword',
                            'type': 'custom'},
           'my_analyzer2': {'filter': ['my_filter2'],
                            'tokenizer': 'trigram',
                            'type': 'custom'}},
       'filter': {
           'my_filter1': {'stopwords': ['a', 'b'], 'type': 'stop'},
           'my_filter2': {'stopwords': ['c', 'd'], 'type': 'stop'}},
       'tokenizer': {'trigram': {'max_gram': 3, 'min_gram': 3, 'type': 'nGram'}}
    } == m._collect_analysis() 

def test_resolve_field_can_resolve_multifields():
    m = mapping.Mapping()
    m.field('title', 'text', fields={'keyword': Keyword()})

    assert isinstance(m.resolve_field('title.keyword'), Keyword) 

def test_resolve_nested():
    m = mapping.Mapping()
    m.field('n1', 'nested', properties={'n2': Nested(properties={'k1': Keyword()})})
    m.field('k2', 'keyword')

    nested, field = m.resolve_nested('n1.n2.k1')
    assert nested == ['n1', 'n1.n2']
    assert isinstance(field, Keyword)

    nested, field = m.resolve_nested('k2')
    assert nested == []
    assert isinstance(field, Keyword) 

def test_mapping_can_collect_all_analyzers_and_normalizers():
    a1 = analysis.analyzer('my_analyzer1',
        tokenizer='keyword',
        filter=['lowercase', analysis.token_filter('my_filter1', 'stop', stopwords=['a', 'b'])],
    )
    a2 = analysis.analyzer('english')
    a3 = analysis.analyzer('unknown_custom')
    a4 = analysis.analyzer('my_analyzer2',
        tokenizer=analysis.tokenizer('trigram', 'nGram', min_gram=3, max_gram=3),
        filter=[analysis.token_filter('my_filter2', 'stop', stopwords=['c', 'd'])],
    )
    a5 = analysis.analyzer('my_analyzer3', tokenizer='keyword')
    n1 = analysis.normalizer('my_normalizer1',
        filter=['lowercase']
    )
    n2 = analysis.normalizer('my_normalizer2',
        filter=['my_filter1', 'my_filter2', analysis.token_filter('my_filter3', 'stop', stopwords=['e', 'f'])]
    )
    n3 = analysis.normalizer('unknown_custom')

    m = mapping.Mapping()
    m.field('title', 'text', analyzer=a1,
        fields={
            'english': Text(analyzer=a2),
            'unknown': Keyword(search_analyzer=a3),
        }
    )
    m.field('comments', Nested(properties={
        'author': Text(analyzer=a4)
    }))
    m.field('normalized_title', 'keyword', normalizer=n1)
    m.field('normalized_comment', 'keyword', normalizer=n2)
    m.field('unknown', 'keyword', normalizer=n3)
    m.meta('_all', analyzer=a5)

    assert {
        'analyzer': {
            'my_analyzer1': {'filter': ['lowercase', 'my_filter1'], 'tokenizer': 'keyword', 'type': 'custom'},
            'my_analyzer2': {'filter': ['my_filter2'], 'tokenizer': 'trigram', 'type': 'custom'},
            'my_analyzer3': {'tokenizer': 'keyword', 'type': 'custom'},
        },
        'normalizer': {
            'my_normalizer1': {'filter': ['lowercase'], 'type': 'custom'},
            'my_normalizer2': {'filter': ['my_filter1', 'my_filter2', 'my_filter3'], 'type': 'custom'},
        },
        'filter': {
            'my_filter1': {'stopwords': ['a', 'b'], 'type': 'stop'},
            'my_filter2': {'stopwords': ['c', 'd'], 'type': 'stop'},
            'my_filter3': {'stopwords': ['e', 'f'], 'type': 'stop'},
        },
        'tokenizer': {
            'trigram': {'max_gram': 3, 'min_gram': 3, 'type': 'nGram'},
        }
    } == m._collect_analysis()

    assert json.loads(json.dumps(m.to_dict())) == m.to_dict()