#!/bin/bash
# 检查 refine_domains.py 的处理进度

echo "========================================="
echo "Domain Refinement 进度检查"
echo "========================================="
echo ""

# 检查进程是否还在运行
if pgrep -f "refine_domains.py" > /dev/null; then
    echo "✅ 脚本正在运行中..."
else
    echo "⚠️  脚本未运行"
fi

echo ""
echo "最新处理进度："
echo "========================================="
tail -30 /home/lizhen/ChartPipeline/icon_generation/refine_log.txt | grep -E "(处理进度|已用时间|当前字段|Value filtering 完成)"

echo ""
echo "========================================="
echo "临时文件信息："
if [ -f "/home/lizhen/ChartPipeline/icon_generation/refined_domains_temp.json" ]; then
    temp_size=$(wc -l < /home/lizhen/ChartPipeline/icon_generation/refined_domains_temp.json)
    echo "📄 临时文件行数: $temp_size"
    
    # 统计已处理的字段数
    processed=$(grep -c '"domain":' /home/lizhen/ChartPipeline/icon_generation/refined_domains_temp.json)
    echo "✅ 已处理字段数: $processed"
else
    echo "⚠️  临时文件不存在"
fi

echo ""
echo "最后更新时间："
ls -lh /home/lizhen/ChartPipeline/icon_generation/refine_log.txt | awk '{print $6, $7, $8}'