拼音排序工具类

jar包

        <dependency>
            <groupId>com.belerweb</groupId>
            <artifactId>pinyin4j</artifactId>
            <version>2.5.1</version>
        </dependency>

package com.*.utils;

import lombok.extern.slf4j.Slf4j;
import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;
import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;
import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;
import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType;
import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;

import java.text.Collator;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
import java.util.Locale;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @author ***
 * @Title: PinYinUtils
 * @Description:
 * @Copyright: *******
 * @Company: *******
 * @Date 2020-05-18-16:26
 */
@Slf4j
public class PinYinUtils {
    private static final Pattern CHINESE_PATTERN = Pattern.compile("[\u4e00-\u9fa5]");

    /**
     * 判读字符串是否存在中文
     *
     * @param str
     * @return
     */
    public static boolean isContainChinese(String str) {
        Matcher m = CHINESE_PATTERN.matcher(str);
        if (m.find()) {
            return true;
        }
        return false;
    }

    /**
     * 获取汉字串拼音，英文字符不变
     *
     * @param str
     * @return
     */
    public static String getAlphabet(String str) {
        StringBuffer pybf = new StringBuffer();
        char[] arr = str.toCharArray();
        HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
        // 输出拼音全部小写
        defaultFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
        // 不带声调
        defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
        //ü转换为v
        defaultFormat.setVCharType(HanyuPinyinVCharType.WITH_V);
        for (int i = 0; i < arr.length; i++) {
            if (arr[i] > 128) {
                try {
                    pybf.append(PinyinHelper.toHanyuPinyinStringArray(arr[i], defaultFormat)[0]);
                } catch (BadHanyuPinyinOutputFormatCombination e) {
                    log.error("获取中文字符串拼音异常", e);
                }
            } else {
                pybf.append(arr[i]);
            }
        }
        return pybf.toString();
    }

    /**
     * 开始排序
     *
     * @param data
     * @return
     */
    public static List<String> sort(List<String> data) {
        if (data == null || data.size() == 0) {
            return data;
        }
        Comparator<Object> comparator = Collator.getInstance(Locale.CHINA);
        Collections.sort(data, comparator);
        return data;
    }
    //测试
    public static void main(String[] args) {
        List<String> list = new ArrayList<>();
        list.add("H3C");
        list.add("hangming");
        list.add("汉明");
        list.add("han明");
        list.add("汉ming");
        list.add("烽火");
        list.add("烽火");
        list.add("汉明");
        list.add("han明");
        list.add("汉明");
        list.add("aaa");
        list.add("111");
        list.add("哎");
        System.out.println(list);
        //先排序解决同音字问题
        list = sort(list);
        System.out.println(list);
        List<String> sortList = new ArrayList<>();
        for (int i = 0; i < list.size(); i++) {
            String bir = Long.toBinaryString(i);
            String s = list.get(i);
            if (isContainChinese(s)) {
                s = getAlphabet(s) + bir;
            } else {
                s = s + bir;
            }
            sortList.add(s);
        }
        sortList = sort(sortList);
        System.out.println(sortList);
    }
}
//结果:
//[H3C, hangming, 汉明, han明, 汉ming, 烽火, 烽火, 汉明, han明, 汉明, aaa, 111, 哎]
//[111, aaa, H3C, hangming, han明, han明, 哎, 烽火, 烽火, 汉ming, 汉明, 汉明, 汉明]
//[1110, aaa1, ai110, fenghuo1000, fenghuo111, H3C10, hangming11, hanming100, hanming1001, hanming101, hanming1010, hanming1011, hanming1100]