Java/w12/datacollect/persist/JsonImporter.java

package com.example.datacollect.persist;

import com.example.datacollect.model.Article;
import com.example.datacollect.repository.ArticleRepository;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.datatype.jsr310.JavaTimeModule;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

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

public class JsonImporter {
    private static final Logger logger = LoggerFactory.getLogger(JsonImporter.class);
    private final ObjectMapper objectMapper;

    public JsonImporter() {
        this.objectMapper = new ObjectMapper();
        objectMapper.registerModule(new JavaTimeModule());
    }

    /**
     * 从JSON文件增量导入文章（跳过已存在URL）
     * @param repository 文章仓库
     * @param filePath 导入文件路径
     */
    public void importArticles(ArticleRepository repository, String filePath) throws IOException {
        logger.info("开始从文件导入文章: {}", filePath);
        File file = new File(filePath);

        if (!file.exists()) {
            String errorMsg = "导入文件不存在: " + filePath;
            logger.error(errorMsg);
            throw new IOException(errorMsg);
        }

        // try-with-resources 自动关闭FileReader
        try (FileReader reader = new FileReader(file)) {
            // 反序列化为Article列表
            List<Article> importedArticles = objectMapper.readValue(
                    reader,
                    objectMapper.getTypeFactory().constructCollectionType(List.class, Article.class)
            );

            // 增量导入：过滤已存在的URL
            int importedCount = 0;
            int skippedCount = 0;
            for (Article article : importedArticles) {
                if (article == null || article.getUrl() == null || article.getUrl().isBlank()) {
                    logger.warn("跳过无效文章（URL为空）");
                    skippedCount++;
                    continue;
                }
                if (repository.containsUrl(article.getUrl())) {
                    logger.debug("URL已存在，跳过: {}", article.getUrl());
                    skippedCount++;
                    continue;
                }
                repository.add(article);
                importedCount++;
            }

            logger.info("导入完成 | 成功: {} 篇 | 跳过: {} 篇", importedCount, skippedCount);
        } catch (IOException e) {
            logger.error("导入失败: {}", filePath, e);
            throw e;
        }
    }
}