ragchat/src/main/java/cn/jlsxwkj/common/reader/ParagraphTextReader.java

package cn.jlsxwkj.common.reader;


import cn.jlsxwkj.common.utils.SplitDocument;
import lombok.Data;
import org.springframework.ai.document.Document;
import org.springframework.ai.document.DocumentReader;
import org.springframework.core.io.DefaultResourceLoader;
import org.springframework.core.io.Resource;
import org.springframework.util.StreamUtils;

import java.io.IOException;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.util.List;
import java.util.Objects;

/**
 * @author zh
 * 文本读取
 */
@Data
public class ParagraphTextReader implements DocumentReader {

    private final Resource resource;
    private final Charset charset = StandardCharsets.UTF_8;

    /**
     * 窗口大小，为段落的数量，用于滚动读取
     */
    private final int windowSize;

    public ParagraphTextReader(String resourceUrl,
                               int windowSize) {
        this(new DefaultResourceLoader().getResource(resourceUrl), windowSize);
    }

    public ParagraphTextReader(Resource resource, int windowSize) {
        Objects.requireNonNull(resource, "The Spring Resource must not be null");
        this.resource = resource;
        this.windowSize = windowSize;
    }

    /**
     * 读取文本内容,并根据换行进行分段,采用窗口模式,窗口为段落的数量
     *
     * @return 文档信息列表
     */
    @Override
    public List<Document> get() {
        try {
            var document = StreamUtils.copyToString(this.resource.getInputStream(), this.charset);
            return SplitDocument.splitStringToListDocument(document, this.windowSize, this.resource.getFilename());
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

}