#!/bin/bash

# 清空或创建result-3.csv文件
> result-3.csv

# 遍历result-2.csv文件的每一行
while IFS=',' read -r sdf_file compound_id; do
    # 提取化合物编号，例如450
    compound_num=$(echo "$sdf_file" | grep -oP '\d+')

    # 在result.csv中查找精确匹配的行
    match=$(grep -E "dock-result_Compound_$compound_num," result.csv)
    
    if [ -n "$match" ]; then
        # 提取result.csv中的最后一列数值
        value=$(echo "$match" | awk -F',' '{print $NF}')
        # 将数值追加到result-2.csv的对应行
        echo "$sdf_file,$compound_id,$value" >> result-3.csv
    else
        # 如果没有匹配到，保留原有行
        echo "$sdf_file,$compound_id" >> result-3.csv
    fi
done < result-2.csv