Java中利用正则表达式与后处理精确提取复杂字符串中的动态分组数据

String s = "#Section250342,Main,First/HS/12345/Jack/M,200010 10.00 200011 -2.00,
"
        + "#Section250322,Main,First/HS/12345/Aaron/N,200010 17.00,
"
        + "#Section250399,Main,First/HS/12345/Jimmy/N,200010 12.00,
"
        + "#Section251234,Main,First/HS/12345/Jack/M,200011 11.00";

#Section(d+)(?:(?!#Sectiond).)*Jack/M,(d+h+[-+]?d+(?:.d+)?(?:s+d+h+[-+]?d+(?:.d+)?)*)

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RegexDataExtraction {

    public static void main(String[] args) {
        String regex = "#Section(\d+)\b(?:(?!#Section\d).)*\bJack/M,(\d+\h+[-+]?\d+(?:\.\d+)?(?:\s+\d+\h+[-+]?\d+(?:\.\d+)?)*)";
        String string = "#Section250342,Main,First/HS/12345/Jack/M,200010 10.00 200011 -2.00,
"
                + "#Section250322,Main,First/HS/12345/Aaron/N,200010 17.00,
"
                + "#Section250399,Main,First/HS/12345/Jimmy/N,200010 12.00,
"
                + "#Section251234,Main,First/HS/12345/Jack/M,200011 11.00";

        Pattern pattern = Pattern.compile(regex, Pattern.MULTILINE);
        Matcher matcher = pattern.matcher(string);

        // 逐个匹配并打印结果
        System.out.println("--- 按行匹配结果 ---");
        while (matcher.find()) {
            List<String> dates = new ArrayList<>();
            List<String> values = new ArrayList<>();

            // Group 1: Section 编号
            System.out.println("Group 1 (Section): " + matcher.group(1));

            // Group 2: 所有日期和数值的字符串
            String[] parts = matcher.group(2).split("\s+"); // 按空白字符分割
            for (int i = 0; i < parts.length; i++) {
                if (i % 2 == 0) { // 偶数索引是日期
                    dates.add(parts[i]);
                } else { // 奇数索引是数值
                    values.add(parts[i]);
                }
            }
            System.out.println("Group 2 (Dates): " + Arrays.toString(dates.toArray()));
            System.out.println("Group 3 (Values): " + Arrays.toString(values.toArray()));
        }

        // 重置matcher以进行第二次匹配，用于聚合所有结果
        matcher.reset(); 

        // 聚合所有匹配结果
        List<String> allSectionNumbers = new ArrayList<>();
        List<String> allDates = new ArrayList<>();
        List<String> allValues = new ArrayList<>();

        System.out.println("
--- 聚合所有匹配结果 ---");
        while (matcher.find()) {
            allSectionNumbers.add(matcher.group(1));
            String[] parts = matcher.group(2).split("\s+");
            for (int i = 0; i < parts.length; i++) {
                if (i % 2 == 0) {
                    allDates.add(parts[i]);
                } else {
                    allValues.add(parts[i]);
                }
            }
        }
        System.out.println("所有 Section 编号: " + Arrays.toString(allSectionNumbers.toArray()));
        System.out.println("所有日期: " + Arrays.toString(allDates.toArray()));
        System.out.println("所有数值: " + Arrays.toString(allValues.toArray()));
    }
}

--- 按行匹配结果 ---
Group 1 (Section): 250342
Group 2 (Dates): [200010, 200011]
Group 3 (Values): [10.00, -2.00]
Group 1 (Section): 251234
Group 2 (Dates): [200011]
Group 3 (Values): [11.00]

--- 聚合所有匹配结果 ---
所有 Section 编号: [250342, 251234]
所有日期: [200010, 200011, 200011]
所有数值: [10.00, -2.00, 11.00]