pinyin4j 中文转成拼音(支持多音字输出)

ゝ一世哀愁。 2023-07-01 05:27 34阅读 0赞

## 1. 引入maven依赖 ##

<dependency>
    	<groupId>net.sourceforge.pinyin4j</groupId>
    	<artifactId>pinyin4j</artifactId>
    	<version>2.5.0</version>
    </dependency>

## 2. PinYin4j工具类及其使用 ##

import java.util.HashSet;
    import java.util.Set;
    
    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;
    
    public class PinYin4jUtil {
    	
    	public static void main(String[] args) {
    		String str = "张三";
    		System.out.println("小写输出：" + getPinyinToLowerCase(str));
    		System.out.println("大写输出：" + getPinyinToUpperCase(str));
    		System.out.println("首字母大写输出：" + getPinyinFirstToUpperCase(str));
    		System.out.println("简拼输出：" + getPinyinJianPin(str));
     
    	}
    	
        /*
    	 * 获取汉字的拼音（默认输出）
    	 * 
    	 * @param chinese 汉字 如：中国
    	 * @return 返回拼音 如：zhongguo
    	 */
    	public static String getPinyin(String chinese) {
    		return getPinyinZh_CN(makeStringByStringSet(chinese));
    	}
     
    	/*
    	 * 拼音大写输出
    	 * 
    	 * @param chinese
    	 * @return
    	 */
    	public static String getPinyinToUpperCase(String chinese) {
    		return getPinyinZh_CN(makeStringByStringSet(chinese)).toUpperCase();
    	}
     
    	/*
    	 * 拼音小写输出
    	 * 
    	 * @param chinese
    	 * @return
    	 */
    	public static String getPinyinToLowerCase(String chinese) {
    		return getPinyinZh_CN(makeStringByStringSet(chinese)).toLowerCase();
    	}
     
    	/*
    	 * 首字母大写输出
    	 * 
    	 * @param chinese
    	 * @return
    	 */
    	public static String getPinyinFirstToUpperCase(String chinese) {
    		return getPinyin(chinese);
    	}
     
    	/*
    	 * 拼音简拼输出
    	 * 
    	 * @param chinese
    	 * @return
    	 */
    	public static String getPinyinJianPin(String chinese) {
    		return getPinyinConvertJianPin(getPinyin(chinese));
    	}
     
    	/*
    	 * 字符集转换
    	 * 
    	 * @param chinese 中文汉字
    	 * @throws BadHanyuPinyinOutputFormatCombination
    	 */
    	public static Set<String> makeStringByStringSet(String chinese) {
    		char[] chars = chinese.toCharArray();
    		if (chinese != null && !chinese.trim().equalsIgnoreCase("")) {
    			char[] srcChar = chinese.toCharArray();
    			String[][] temp = new String[chinese.length()][];
    			for (int i = 0; i < srcChar.length; i++) {
    				char c = srcChar[i];
     
    				// 是中文或者a-z或者A-Z转换拼音
    				if (String.valueOf(c).matches("[\\u4E00-\\u9FA5]+")) {
     
    					try {
    						temp[i] = PinyinHelper.toHanyuPinyinStringArray(
    								chars[i], getDefaultOutputFormat());
     
    					} catch (BadHanyuPinyinOutputFormatCombination e) {
    						e.printStackTrace();
    					}
    				} else if (((int) c >= 65 && (int) c <= 90)
    						|| ((int) c >= 97 && (int) c <= 122)) {
    					temp[i] = new String[] { String.valueOf(srcChar[i]) };
    				} else {
    					temp[i] = new String[] { "" };
    				}
    			}
    			String[] pingyinArray = exchange(temp);
    			Set<String> zhongWenPinYin = new HashSet<String>();
    			for (int i = 0; i < pingyinArray.length; i++) {
    				zhongWenPinYin.add(pingyinArray[i]);
    			}
    			return zhongWenPinYin;
    		}
    		return null;
    	}
     
    	/*
    	 * Default Format 默认输出格式
    	 * 
    	 * @version: Jan 13, 2012 9:35:51 AM
    	 * @return
    	 */
    	public static HanyuPinyinOutputFormat getDefaultOutputFormat() {
    		HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    		format.setCaseType(HanyuPinyinCaseType.LOWERCASE);// 小写
    		format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);// 没有音调数字
    		format.setVCharType(HanyuPinyinVCharType.WITH_U_AND_COLON);// u显示
    		return format;
    	}
     
    	/*
    	 * 
    	 * @param strJaggedArray
    	 * @return
    	 */
    	public static String[] exchange(String[][] strJaggedArray) {
    		String[][] temp = doExchange(strJaggedArray);
    		return temp[0];
    	}
     
    	/*
    	 * 
    	 * @param strJaggedArray
    	 * @return
    	 */
    	private static String[][] doExchange(String[][] strJaggedArray) {
    		int len = strJaggedArray.length;
    		if (len >= 2) {
    			int len1 = strJaggedArray[0].length;
    			int len2 = strJaggedArray[1].length;
    			int newlen = len1 * len2;
    			String[] temp = new String[newlen];
    			int Index = 0;
    			for (int i = 0; i < len1; i++) {
    				for (int j = 0; j < len2; j++) {
    					temp[Index] = capitalize(strJaggedArray[0][i])
    							+ capitalize(strJaggedArray[1][j]);
    					Index++;
    				}
    			}
    			String[][] newArray = new String[len - 1][];
    			for (int i = 2; i < len; i++) {
    				newArray[i - 1] = strJaggedArray[i];
    			}
    			newArray[0] = temp;
    			return doExchange(newArray);
    		} else {
    			return strJaggedArray;
    		}
    	}
     
    	/*
    	 * 首字母大写
    	 * 
    	 * @param s
    	 * @return
    	 */
    	public static String capitalize(String s) {
    		char ch[];
    		ch = s.toCharArray();
    		if (ch[0] >= 'a' && ch[0] <= 'z') {
    			ch[0] = (char) (ch[0] - 32);
    		}
    		String newString = new String(ch);
    		return newString;
    	}
     
    	/*
    	 * 字符串集合转换字符串(逗号分隔)
    	 * 
    	 * @param stringSet
    	 * @return
    	 */
    	public static String getPinyinZh_CN(Set<String> stringSet) {
    		StringBuilder str = new StringBuilder();
    		int i = 0;
    		for (String s : stringSet) {
    			if (i == stringSet.size() - 1) {
    				str.append(s);
    			} else {
    				str.append(s + ",");
    			}
    			i++;
    		}
    		return str.toString();
    	}
     
    	/*
    	 * 获取每个拼音的简称
    	 * 
    	 * @param chinese
    	 * @return
    	 */
    	public static String getPinyinConvertJianPin(String chinese) {
    		String[] strArray = chinese.split(",");
    		String strChar = "";
    		for (String str : strArray) {
    			char arr[] = str.toCharArray(); // 将字符串转化成char型数组
    			for (int i = 0; i < arr.length; i++) {
    				if (arr[i] >= 65 && arr[i] < 91) { // 判断是否是大写字母
    					strChar += new String(arr[i] + "");
    				}
    			}
    			strChar += ",";
    		}
    		return strChar;
    	}
    }

运行结果：

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V4cGVjdDUyMQ_size_16_color_FFFFFF_t_70]

参考：https://blog.csdn.net/jojo\_wen/article/details/84128200  
https://www.e-learn.cn/topic/2624707  
https://blog.csdn.net/jojo\_wen/article/details/84128200

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V4cGVjdDUyMQ_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200119140535594.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2V4cGVjdDUyMQ==,size_16,color_FFFFFF,t_70