001/*
002 * Copyright (c) 2015-2020, Oracle and/or its affiliates. All rights reserved.
003 *
004 * Licensed under the Apache License, Version 2.0 (the "License");
005 * you may not use this file except in compliance with the License.
006 * You may obtain a copy of the License at
007 *
008 *     http://www.apache.org/licenses/LICENSE-2.0
009 *
010 * Unless required by applicable law or agreed to in writing, software
011 * distributed under the License is distributed on an "AS IS" BASIS,
012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express implied.
013 * See the License for the specific language governing permissions and
014 * limitations under the License.
015 */
016
017package org.tribuo.data.text;
018
019import com.oracle.labs.mlrg.olcut.config.Configurable;
020import com.oracle.labs.mlrg.olcut.provenance.ConfiguredObjectProvenance;
021import com.oracle.labs.mlrg.olcut.provenance.Provenancable;
022import org.tribuo.Example;
023import org.tribuo.Output;
024
025/**
026 * An interface for things that take text and turn them into examples that we
027 * can use to train or evaluate a classifier.
028 * @param <T> The type of the features that will be produced by the text
029 * processing.
030 */
031public interface TextFeatureExtractor<T extends Output<T>> extends Configurable, Provenancable<ConfiguredObjectProvenance> {
032
033    /**
034     * Extracts an example from the supplied input text and output object.
035     * @param output The output object.
036     * @param data The input text.
037     * @return An example
038     */
039    public Example<T> extract(T output, String data);
040
041}