Java 读取汉字拼音

╰+哭是因爲堅強的太久メ 2022-10-11 00:41 287阅读 0赞

pom.xml导入pinyin4j的依赖

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

汉字转拼音工具类

package org.fh.util;
    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;
    
    /**汉字解析拼音处理
     * 说明：Freemarker 模版引擎类
     * 作者：FH Admin
     * from：www.fhadmin.org
     */
    public class GetPinyin {
    
    	/**
    	 * 得到 全拼
    	 * @param src
    	 * @return
    	 */
    	public static String getPingYin(String src) {
    		char[] t1 = null;
    		t1 = src.toCharArray();
    		String[] t2 = new String[t1.length];
    		HanyuPinyinOutputFormat t3 = new HanyuPinyinOutputFormat();
    		t3.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    		t3.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    		t3.setVCharType(HanyuPinyinVCharType.WITH_V);
    		String t4 = "";
    		int t0 = t1.length;
    		try {
    			for (int i = 0; i < t0; i++) {
    				// 判断是否为汉字字符
    				if (java.lang.Character.toString(t1[i]).matches(
    						"[\\u4E00-\\u9FA5]+")) {
    					t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);
    					t4 += t2[0];
    				} else {
    					t4 += java.lang.Character.toString(t1[i]);
    				}
    			}
    			return t4;
    		} catch (BadHanyuPinyinOutputFormatCombination e1) {
    			e1.printStackTrace();
    		}
    		return t4;
    	}
    
    	/**
    	 * 得到中文首字母
    	 * @param str
    	 * @return
    	 */
    	public static String getPinYinHeadChar(String str) {
    
    		String convert = "";
    		for (int j = 0; j < str.length(); j++) {
    			char word = str.charAt(j);
    			String[] pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word);
    			if (pinyinArray != null) {
    				convert += pinyinArray[0].charAt(0);
    			} else {
    				convert += word;
    			}
    		}
    		return convert;
    	}
    
    	/**
    	 * 将字符串转移为ASCII码
    	 * @param cnStr
    	 * @return
    	 */
    	public static String getCnASCII(String cnStr) {
    		StringBuffer strBuf = new StringBuffer();
    		byte[] bGBK = cnStr.getBytes();
    		for (int i = 0; i < bGBK.length; i++) {
    			// System.out.println(Integer.toHexString(bGBK[i]&0xff));
    			strBuf.append(Integer.toHexString(bGBK[i] & 0xff));
    		}
    		return strBuf.toString();
    	}
    
    	public static void main(String[] args) {
    
    		String cnStr = "中国";
    		System.out.println(getPingYin(cnStr));
    		System.out.println(getPinYinHeadChar(cnStr));
    	}
    
    }