JAVA-汉字拼音处理

1、依赖jar包

maven仓库:

<repository>
    <id>alimaven</id>
    <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
</repository>

GAV:

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

2、工具类

package com.xxx.utils;

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 org.junit.Test;
import org.springframework.stereotype.Component;

import java.util.regex.Matcher;
import java.util.regex.Pattern;


@Component
public class PinyinUtil {


    @Test
    public void test(){
        String s="举个栗子,abc123";
        System.out.println(getAlpha(s));
        System.out.println(getPinYin(s));
        System.out.println(cleanChar(s));
        //JGLZabc123
        //jugeliziabc123
        //举个栗子abc123
    }

    /**
     * 获得汉语拼音首字母
     *
     * 例:   举个栗子,abc123
     * 返回值:JGLZabc123
     */
    public static String getAlpha(String chines) {
        chines = cleanChar(chines);
        String pinyinName = "";
        char[] nameChar = chines.toCharArray();
        HanyuPinyinOutputFormat defaultFormat = new HanyuPinyinOutputFormat();
        defaultFormat.setCaseType(HanyuPinyinCaseType.UPPERCASE);
        defaultFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
        for (int i = 0; i < nameChar.length; i++) {
            if (nameChar[i] > 128) {
                try {
                    pinyinName += PinyinHelper.toHanyuPinyinStringArray(nameChar[i], defaultFormat)[0].charAt(0);
                } catch (BadHanyuPinyinOutputFormatCombination e) {
                    e.printStackTrace();
                }
            } else {
                pinyinName += nameChar[i];
            }
        }
        return pinyinName;
    }

    /**
     * 将字符串中的中文转化为拼音,英文字符不变
     *
     * 例:    举个栗子,abc123
     * 返回值: jugeliziabc123
     */
    public static String getPinYin(String inputString) {
        inputString = cleanChar(inputString);
        HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
        format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
        format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
        format.setVCharType(HanyuPinyinVCharType.WITH_V);
        String output = "";
        if (inputString != null && inputString.length() > 0 && !"null".equals(inputString)) {
            char[] input = inputString.trim().toCharArray();
            try {
                for (int i = 0; i < input.length; i++) {
                    if (java.lang.Character.toString(input[i]).matches("[\\u4E00-\\u9FA5]+")) {
                        String[] temp = PinyinHelper.toHanyuPinyinStringArray(input[i], format);
                        output += temp[0];
                    } else {
                        output += java.lang.Character.toString(input[i]);
                    }
                }
            } catch (BadHanyuPinyinOutputFormatCombination e) {
                e.printStackTrace();
            }
        } else {
            return "*";
        }
        return output;
    }

    /**
     * 清理特殊字符以便得到
     * 
     * 例:    举个栗子,abc123
     * 返回值: 举个栗子abc123
     */
    public static String cleanChar(String chines) {
        chines = chines.replaceAll("[\\p{Punct}\\p{Space}]+", ""); // 正则去掉所有字符操作
        // 正则表达式去掉所有中文的特殊符号
        String regEx = "[`~!@#$%^&*()+=|{}':;',\\[\\].<>/?~!@#¥%……&*()——+|{}<>《》【】‘;:”“’。,、?]";
        Pattern pattern = Pattern.compile(regEx);
        Matcher matcher = pattern.matcher(chines);
        chines = matcher.replaceAll("").trim();
        return chines;
    }

}

 

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值