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;
022
023/**
024 * An interface for things that can pre-process documents before they are 
025 * broken into features.
026 */
027public interface DocumentPreprocessor extends Configurable, Provenancable<ConfiguredObjectProvenance> {
028    /**
029     * Processes the content of part of a document stored as a string, returning a 
030     * new string. 
031     * @param doc the document to process
032     * @return the processed string. Note that the return value may be {@code null},
033     * in which case the resulting string will be ignored.
034     */
035    public String processDoc(String doc);
036}