use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.DelimitedUTF8StringBinaryTokenizer in project asterixdb by apache.
the class HashedWordTokensDescriptor 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 HashedUTF8WordTokenFactory();
IBinaryTokenizer tokenizer = new DelimitedUTF8StringBinaryTokenizer(true, true, tokenFactory);
return new WordTokensEvaluator(args, ctx, tokenizer, BuiltinType.AINT32);
}
};
}
use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.DelimitedUTF8StringBinaryTokenizer in project asterixdb by apache.
the class WordTokensDescriptor 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 UTF8WordTokenFactory();
IBinaryTokenizer tokenizer = new DelimitedUTF8StringBinaryTokenizer(true, true, tokenFactory);
return new WordTokensEvaluator(args, ctx, tokenizer, BuiltinType.ASTRING);
}
};
}
use of org.apache.hyracks.storage.am.lsm.invertedindex.tokenizers.DelimitedUTF8StringBinaryTokenizer in project asterixdb by apache.
the class CountHashedWordTokensDescriptor 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 HashedUTF8WordTokenFactory();
IBinaryTokenizer tokenizer = new DelimitedUTF8StringBinaryTokenizer(false, true, tokenFactory);
return new WordTokensEvaluator(args, ctx, tokenizer, BuiltinType.AINT32);
}
};
}
Aggregations