首页 诗词 字典 板报 句子 名言 友答 励志 学校 网站地图
当前位置: 首页 > 教程频道 > 开发语言 > 编程 >

pinyin4j 汉语转成拼音(支持多音字输出)

2012-09-21 
pinyin4j 中文转成拼音(支持多音字输出)最近要做一个中文转为拼音,于是联想到 pinyin4j,网络上很多资料,可

pinyin4j 中文转成拼音(支持多音字输出)

最近要做一个中文转为拼音,于是联想到 pinyin4j,网络上很多资料,可是不全,整理一下中文转成拼音(支持多音字输出)

详细代码:

?

package com.baison.util;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;/******************************************************************************* * pinyin4j is a plug-in, you can kind of Chinese characters into phonetic.Multi-tone character,Tone * Detailed view http://pinyin4j.sourceforge.net/ *  * @author Administrator * @ClassName: Pinyin4jUtil * @Description: TODO * @author wang_china@foxmail.com * @date Jan 13, 2012 9:28:28 AM */public class Pinyin4jUtil {/*************************************************************************** * 获取中文汉字拼音 默认输出 * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:54:01 AM * @param chinese * @return */public static String getPinyin(String chinese) {return getPinyinZh_CN(makeStringByStringSet(chinese));}/*************************************************************************** * 拼音大写输出 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:58:45 AM * @param chinese * @return */public static String getPinyinToUpperCase(String chinese) {return getPinyinZh_CN(makeStringByStringSet(chinese)).toUpperCase();}/*************************************************************************** * 拼音小写输出 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:58:45 AM * @param chinese * @return */public static String getPinyinToLowerCase(String chinese) {return getPinyinZh_CN(makeStringByStringSet(chinese)).toLowerCase();}/*************************************************************************** * 首字母大写输出 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 10:00:54 AM * @param chinese * @return */public static String getPinyinFirstToUpperCase(String chinese) {return getPinyin(chinese);}/*************************************************************************** * 拼音简拼输出 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 11:08:15 AM * @param chinese * @return */public static String getPinyinJianPin(String chinese) {return getPinyinConvertJianPin(getPinyin(chinese));}/*************************************************************************** * 字符集转换 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:34:11 AM * @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 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @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;}/*************************************************************************** *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:39:54 AM * @param strJaggedArray * @return */public static String[] Exchange(String[][] strJaggedArray) {String[][] temp = DoExchange(strJaggedArray);return temp[0];}/*************************************************************************** *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:39:47 AM * @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 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:36:18 AM * @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) *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:37:57 AM * @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 *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 11:05:58 AM * @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;}/*************************************************************************** * Test *  * @Name: Pinyin4jUtil.java * @Description: TODO * @author: wang_chian@foxmail.com * @version: Jan 13, 2012 9:49:27 AM * @param args */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));}}
public static String capitalize(String s) { char ch[]; ch = s.toCharArray(); [color=red] if (ch!= null && ch.length > 0) { //修改[/color] if (ch[0] >= 'a' && ch[0] <= 'z') { ch[0] = (char) (ch[0] - 32); } } String newString = new String(ch); return newString; }

但是输出还是没数字
修改一下这

     else {                       temp[i] = new String[] { String.valueOf(srcChar[i]) };                   }  

热点排行