Java/w12/datacollect/command/AnalyzeCommand.java

package com.example.datacollect.command;

import com.example.datacollect.model.Article;
import com.example.datacollect.repository.ArticleRepository;
import com.example.datacollect.strategy.CrawlStrategy;
import com.example.datacollect.strategy.StrategyFactory;
import com.example.datacollect.view.ConsoleView;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.List;
import java.util.stream.Collectors;

public class AnalyzeCommand implements Command {

    // 1. 添加 Logger 成员
    private static final Logger logger = LoggerFactory.getLogger(AnalyzeCommand.class);

    private final ConsoleView view;
    private final StrategyFactory strategyFactory;

    public AnalyzeCommand(ConsoleView view, StrategyFactory strategyFactory) {
        this.view = view;
        this.strategyFactory = strategyFactory;
    }

    @Override
    public String getName() {
        return "analyze";
    }

    @Override
    public void execute(String[] args, ArticleRepository repository) {
        if (args.length < 2) {
            logger.error("指令参数错误，正确用法: analyze <url>");
            view.printError("Usage: analyze <url>"); // 保留控制台提示，方便用户直接看到
            return;
        }

        String url = args[1];
        CrawlStrategy strategy = strategyFactory.getStrategy(url);
        if (strategy == null) {
            logger.error("未找到适用于 URL [{}] 的抓取策略", url);
            view.printError("No strategy found for: " + url);
            return;
        }

        try {
            logger.info("开始分析目标网站: {}", url);
            Document doc = Jsoup.connect(url).get();

            // 调用策略解析，但不存入 Repository
            List<Article> articles = strategy.parse(url, doc);

            // 统计信息
            int total = articles.size();
            double avgTitleLen = articles.stream()
                    .mapToInt(a -> a.getTitle().length())
                    .average()
                    .orElse(0.0);

            // Top 5 按标题长度排序
            List<Article> top5 = articles.stream()
                    .sorted((a, b) -> Integer.compare(b.getTitle().length(), a.getTitle().length()))
                    .limit(5)
                    .collect(Collectors.toList());

            // 输出结果到日志
            logger.info("=== 分析结果 ===");
            logger.info("提取文章总数: {}", total);
            logger.info("平均标题长度: {:.2f} 字符", avgTitleLen);
            logger.info("Top 5 文章 (按标题长度排序):");

            int rank = 1;
            for (Article a : top5) {
                logger.info("{}. {} ({} 字符)", rank, a.getTitle(), a.getTitle().length());
                rank++;
            }
            logger.info("==================");

            // 保留原有的控制台输出，确保用户交互体验不受影响
            view.printInfo("=== Analysis Result ===");
            view.printInfo("Total Articles: " + total);
            view.printInfo("Avg Title Length: " + String.format("%.2f", avgTitleLen));
            view.printInfo("Top 5 Articles (by Title Length):");
            rank = 1;
            for (Article a : top5) {
                view.printInfo(rank + ". " + a.getTitle() + " (" + a.getTitle().length() + " chars)");
                rank++;
            }
            view.printInfo("========================");

        } catch (Exception e) {
            logger.error("分析 URL [{}] 时发生异常: ", url, e); // 传入异常对象 e，以便记录完整堆栈
            view.printError("Failed to analyze: " + e.getMessage());
        }
    }
}