mds/gtbook/src/main/java/org/cnnlp/data/splitter/IMdChunking.java

package org.cnnlp.data.splitter;

import org.cnnlp.data.document.GDocument;
import org.cnnlp.data.util.BaseParameters;

import java.io.IOException;
import java.util.List;

public interface IMdChunking {
    // simple/faq/tagged
    //public static final String MD_TYPE = "mdType";

    //输出的是 章节
    List<GDocument> splitSimple(String text, BaseParameters params) throws IOException;

    //输出的是 章节
    List<GDocument> splitFaq(String text, BaseParameters params) throws IOException;

    //输出的是 章节
    List<GDocument> split(String text, BaseParameters params) throws IOException;

    // 输出的是 chunk
    List<GDocument> chunking(String text, BaseParameters params) throws IOException;
}