Search in sources :

Example 1 with NGramUTF8StringBinaryTokenizer

use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer in project asterixdb by apache.

the class GramTokensDescriptor method createEvaluatorFactory.

@Override
public IScalarEvaluatorFactory createEvaluatorFactory(final IScalarEvaluatorFactory[] args) {
    return new IScalarEvaluatorFactory() {

        private static final long serialVersionUID = 1L;

        @Override
        public IScalarEvaluator createScalarEvaluator(IHyracksTaskContext ctx) throws HyracksDataException {
            ITokenFactory tokenFactory = new UTF8NGramTokenFactory();
            NGramUTF8StringBinaryTokenizer tokenizer = new NGramUTF8StringBinaryTokenizer(3, true, true, true, tokenFactory);
            return new GramTokensEvaluator(args, ctx, tokenizer, BuiltinType.ASTRING);
        }
    };
}
Also used : IHyracksTaskContext(org.apache.hyracks.api.context.IHyracksTaskContext) GramTokensEvaluator(org.apache.asterix.runtime.evaluators.common.GramTokensEvaluator) UTF8NGramTokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.UTF8NGramTokenFactory) NGramUTF8StringBinaryTokenizer(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer) ITokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.ITokenFactory) IScalarEvaluatorFactory(org.apache.hyracks.algebricks.runtime.base.IScalarEvaluatorFactory)

Example 2 with NGramUTF8StringBinaryTokenizer

use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer in project asterixdb by apache.

the class HashedGramTokensDescriptor method createEvaluatorFactory.

@Override
public IScalarEvaluatorFactory createEvaluatorFactory(final IScalarEvaluatorFactory[] args) {
    return new IScalarEvaluatorFactory() {

        private static final long serialVersionUID = 1L;

        @Override
        public IScalarEvaluator createScalarEvaluator(IHyracksTaskContext ctx) throws HyracksDataException {
            ITokenFactory tokenFactory = new HashedUTF8NGramTokenFactory();
            NGramUTF8StringBinaryTokenizer tokenizer = new NGramUTF8StringBinaryTokenizer(3, true, true, true, tokenFactory);
            return new GramTokensEvaluator(args, ctx, tokenizer, BuiltinType.AINT32);
        }
    };
}
Also used : IHyracksTaskContext(org.apache.hyracks.api.context.IHyracksTaskContext) GramTokensEvaluator(org.apache.asterix.runtime.evaluators.common.GramTokensEvaluator) NGramUTF8StringBinaryTokenizer(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer) ITokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.ITokenFactory) HashedUTF8NGramTokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.HashedUTF8NGramTokenFactory) IScalarEvaluatorFactory(org.apache.hyracks.algebricks.runtime.base.IScalarEvaluatorFactory)

Example 3 with NGramUTF8StringBinaryTokenizer

use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer in project asterixdb by apache.

the class CountHashedGramTokensDescriptor method createEvaluatorFactory.

@Override
public IScalarEvaluatorFactory createEvaluatorFactory(final IScalarEvaluatorFactory[] args) throws AlgebricksException {
    return new IScalarEvaluatorFactory() {

        private static final long serialVersionUID = 1L;

        @Override
        public IScalarEvaluator createScalarEvaluator(IHyracksTaskContext ctx) throws HyracksDataException {
            ITokenFactory tokenFactory = new HashedUTF8NGramTokenFactory();
            NGramUTF8StringBinaryTokenizer tokenizer = new NGramUTF8StringBinaryTokenizer(3, true, false, true, tokenFactory);
            return new GramTokensEvaluator(args, ctx, tokenizer, BuiltinType.AINT32);
        }
    };
}
Also used : IHyracksTaskContext(org.apache.hyracks.api.context.IHyracksTaskContext) GramTokensEvaluator(org.apache.asterix.runtime.evaluators.common.GramTokensEvaluator) NGramUTF8StringBinaryTokenizer(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer) ITokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.ITokenFactory) HashedUTF8NGramTokenFactory(org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.HashedUTF8NGramTokenFactory) IScalarEvaluatorFactory(org.apache.hyracks.algebricks.runtime.base.IScalarEvaluatorFactory)

Aggregations

GramTokensEvaluator (org.apache.asterix.runtime.evaluators.common.GramTokensEvaluator)3 IScalarEvaluatorFactory (org.apache.hyracks.algebricks.runtime.base.IScalarEvaluatorFactory)3 IHyracksTaskContext (org.apache.hyracks.api.context.IHyracksTaskContext)3 ITokenFactory (org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.ITokenFactory)3 NGramUTF8StringBinaryTokenizer (org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.NGramUTF8StringBinaryTokenizer)3 HashedUTF8NGramTokenFactory (org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.HashedUTF8NGramTokenFactory)2 UTF8NGramTokenFactory (org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.UTF8NGramTokenFactory)1