package com.example.datacollect.command;

import com.example.datacollect.exception.CrawlerException;
import com.example.datacollect.exception.ErrorCode;
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 java.io.IOException;
import java.util.List;

public class AnalyzeCommand implements Command {

    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) {
            view.printError("[" + ErrorCode.INVALID_ARGUMENT.getCode() + "] " + ErrorCode.INVALID_ARGUMENT.getMessage() + "，格式：analyze <url>");
            return;
        }
        String url = args[1];

        CrawlStrategy strategy = strategyFactory.getStrategy(url);
        if (strategy == null) {
            throw new CrawlerException(ErrorCode.STRATEGY_NOT_FOUND, "不支持解析该URL：" + url);
        }

        Document doc;
        try {
            view.printInfo("正在分析: " + url);
            doc = Jsoup.connect(url)
                    .timeout(30000)
                    .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
                    .header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8")
                    .header("Accept-Language", "zh-CN,zh;q=0.9,en;q=0.8")
                    .header("Accept-Encoding", "gzip, deflate, br")
                    .header("Connection", "keep-alive")
                    .header("Cache-Control", "max-age=0")
                    .get();
        } catch (IOException e) {
            throw new CrawlerException(ErrorCode.NETWORK_ERROR, "网页爬取失败：" + e.getMessage(), e);
        }

        List<Article> articles;
        try {
            articles = strategy.parse(url, doc);
        } catch (Exception e) {
            throw new CrawlerException(ErrorCode.PARSE_ERROR, "网页解析失败：" + e.getMessage(), e);
        }

        printAnalysisResult(articles, url);
    }

    private void printAnalysisResult(List<Article> articles, String url) {
        view.printInfo("\n===== 网页分析结果（不存储数据） =====");
        view.printInfo("分析URL：" + url);
        view.printInfo("解析到文章数量：" + articles.size());

        if (!articles.isEmpty()) {
            int totalTitleLength = 0;
            for (Article article : articles) {
                totalTitleLength += article.getTitle().length();
            }
            double avgTitleLength = (double) totalTitleLength / articles.size();
            view.printInfo(String.format("文章标题平均长度：%.2f 字符", avgTitleLength));

            view.printInfo("\n前3篇文章标题预览：");
            for (int i = 0; i < Math.min(3, articles.size()); i++) {
                view.printInfo((i + 1) + ". " + articles.get(i).getTitle());
            }
        } else {
            view.printInfo("未解析到任何文章内容");
        }
        view.printInfo("=====================================\n");
    }
}