获取汉字拼音 Java
两种方法：一个是使用btye数组（GB2312仅包含常用字，所以会存在失败的情况，推荐使用jar包），一个是引入jar包进行操作。
1、
public class CharacterParser {
private static int[] pyvalue = new int[] { -20319, -20317, -20304, -20295,
-20292, -20283, -20265, -20257, -20242, -20230, -20051, -20036,
-20032, -20026, -20002, -19990, -19986, -19982, -19976, -19805,
-19784, -19775, -19774, -19763, -19756, -19751, -19746, -19741,
-19739, -19728, -19725, -19715, -19540, -19531, -19525, -19515,
-19500, -19484, -19479, -19467, -19289, -19288, -19281, -19275,
-19270, -19263, -19261, -19249, -19243, -19242, -19238, -19235,
-19227, -19224, -19218, -19212, -19038, -19023, -19018, -19006,
-19003, -18996, -18977, -18961, -18952, -18783, -18774, -18773,
-18763, -18756, -18741, -18735, -18731, -18722, -18710, -18697,
-18696, -18526, -18518, -18501, -18490, -18478, -18463, -18448,
-18447, -18446, -18239, -18237, -18231, -18220, -18211, -18201,
-18184, -18183, -18181, -18012, -17997, -17988, -17970, -17964,
-17961, -17950, -17947, -17931, -17928, -17922, -17759, -17752,
-17733, -17730, -17721, -17703, -17701, -17697, -17692, -17683,
-17676, -17496, -17487, -17482, -17468, -17454, -17433, -17427,
-17417, -17202, -17185, -16983, -16970, -16942, -16915, -16733,
-16708, -16706, -16689, -16664, -16657, -16647, -16474, -16470,
-16465, -16459, -16452, -16448, -16433, -16429, -16427, -16423,
-16419, -16412, -16407, -16403, -16401, -16393, -16220, -16216,
-16212, -16205, -16202, -16187, -16180, -16171, -16169, -16158,
-16155, -15959, -15958, -15944, -15933, -15920, -15915, -15903,
-15889, -15878, -15707, -15701, -15681, -15667, -15661, -15659,
-15652, -15640, -15631, -15625, -15454, -15448, -15436, -15435,
-15419, -15416, -15408, -15394, -15385, -15377, -15375, -15369,
-15363, -15362, -15183, -15180, -15165, -15158, -15153, -15150,
-15149, -15144, -15143, -15141, -15140, -15139, -15128, -15121,
-15119, -15117, -15110, -15109, -14941, -14937, -14933, -14930,
-14929, -14928, -14926, -14922, -14921, -14914, -14908, -14902,
-14894, -14889, -14882, -14873, -14871, -14857, -14678, -14674,
-14670, -14668, -14663, -14654, -14645, -14630, -14594, -14429,
-14407, -14399, -14384, -14379, -14368, -14355, -14353, -14345,
-14170, -14159, -14151, -14149, -14145, -14140, -14137, -14135,
-14125, -14123, -14122, -14112, -14109, -14099, -14097, -14094,
-14092, -14090, -14087, -14083, -13917, -13914, -13910, -13907,
-13906, -13905, -13896, -13894, -13878, -13870, -13859, -13847,
-13831, -13658, -13611, -13601, -13406, -13404, -13400, -13398,
-13395, -13391, -13387, -13383, -13367, -13359, -13356, -13343,
-13340, -13329, -13326, -13318, -13147, -13138, -13120, -13107,
-13096, -13095, -13091, -13076, -13068, -13063, -13060, -12888,
-12875, -12871, -12860, -12858, -12852, -12849, -12838, -12831,
-12829, -12812, -12802, -12607, -12597, -12594, -12585, -12556,
-12359, -12346, -12320, -12300, -12120, -12099, -12089, -12074,
-12067, -12058, -12039, -11867, -11861, -11847, -11831, -11798,
-11781, -11604, -11589, -11536, -11358, -11340, -11339, -11324,
-11303, -11097, -11077, -11067, -11055, -11052, -11045, -11041,
-11038, -11024, -11020, -11019, -11018, -11014, -10838, -10832,
-10815, -10800, -10790, -10780, -10764, -10587, -10544, -10533,
-10519, -10331, -10329, -10328, -10322, -10315, -10309, -10307,
-10296, -10281, -10274, -10270, -10262, -10260, -10256, -10254 };
public static String[] pystr = new String[] { "a", "ai", "an", "ang", "ao",
"ba", "bai", "ban", "bang", "bao", "bei", "ben", "beng", "bi",
"bian", "biao", "bie", "bin", "bing", "bo", "bu", "ca", "cai",
"can", "cang", "cao", "ce", "ceng", "cha", "chai", "chan", "chang",
"chao", "che", "chen", "cheng", "chi", "chong", "chou", "chu",
"chuai", "chuan", "chuang", "chui", "chun", "chuo", "ci", "cong",
"cou", "cu", "cuan", "cui", "cun", "cuo", "da", "dai", "dan",
"dang", "dao", "de", "deng", "di", "dian", "diao", "die", "ding",
"diu", "dong", "dou", "du", "duan", "dui", "dun", "duo", "e", "en",
"er", "fa", "fan", "fang", "fei", "fen", "feng", "fo", "fou", "fu",
"ga", "gai", "gan", "gang", "gao", "ge", "gei", "gen", "geng",
"gong", "gou", "gu", "gua", "guai", "guan", "guang", "gui", "gun",
"guo", "ha", "hai", "han", "hang", "hao", "he", "hei", "hen",
"heng", "hong", "hou", "hu", "hua", "huai", "huan", "huang", "hui",
"hun", "huo", "ji", "jia", "jian", "jiang", "jiao", "jie", "jin",
"jing", "jiong", "jiu", "ju", "juan", "jue", "jun", "ka", "kai",
"kan", "kang", "kao", "ke", "ken", "keng", "kong", "kou", "ku",
"kua", "kuai", "kuan", "kuang", "kui", "kun", "kuo", "la", "lai",
"lan", "lang", "lao", "le", "lei", "leng", "li", "lia", "lian",
"liang", "liao", "lie", "lin", "ling", "liu", "long", "lou", "lu",
"lv", "luan", "lue", "lun", "luo", "ma", "mai", "man", "mang",
"mao", "me", "mei", "men", "meng", "mi", "mian", "miao", "mie",
"min", "ming", "miu", "mo", "mou", "mu", "na", "nai", "nan",
"nang", "nao", "ne", "nei", "nen", "neng", "ni", "nian", "niang",
"niao", "nie", "nin", "ning", "niu", "nong", "nu", "nv", "nuan",
"nue", "nuo", "o", "ou", "pa", "pai", "pan", "pang", "pao", "pei",
"pen", "peng", "pi", "pian", "piao", "pie", "pin", "ping", "po",
"pu", "qi", "qia", "qian", "qiang", "qiao", "qie", "qin", "qing",
"qiong", "qiu", "qu", "quan", "que", "qun", "ran", "rang", "rao",
"re", "ren", "reng", "ri", "rong", "rou", "ru", "ruan", "rui",
"run", "ruo", "sa", "sai", "san", "sang", "sao", "se", "sen",
"seng", "sha", "shai", "shan", "shang", "shao", "she", "shen",
"sheng", "shi", "shou", "shu", "shua", "shuai", "shuan", "shuang",
"shui", "shun", "shuo", "si", "song", "sou", "su", "suan", "sui",
"sun", "suo", "ta", "tai", "tan", "tang", "tao", "te", "teng",
"ti", "tian", "tiao", "tie", "ting", "tong", "tou", "tu", "tuan",
"tui", "tun", "tuo", "wa", "wai", "wan", "wang", "wei", "wen",
"weng", "wo", "wu", "xi", "xia", "xian", "xiang", "xiao", "xie",
"xin", "xing", "xiong", "xiu", "xu", "xuan", "xue", "xun", "ya",
"yan", "yang", "yao", "ye", "yi", "yin", "ying", "yo", "yong",
"you", "yu", "yuan", "yue", "yun", "za", "zai", "zan", "zang",
"zao", "ze", "zei", "zen", "zeng", "zha", "zhai", "zhan", "zhang",
"zhao", "zhe", "zhen", "zheng", "zhi", "zhong", "zhou", "zhu",
"zhua", "zhuai", "zhuan", "zhuang", "zhui", "zhun", "zhuo", "zi",
"zong", "zou", "zu", "zuan", "zui", "zun", "zuo" };
private StringBuilder buffer;
private String resource;
private static CharacterParser characterParser;
public static CharacterParser getInstance() {
if (characterParser == null) {
characterParser = new CharacterParser();
}
return characterParser;
}
public String getResource() {
return resource;
}
public void setResource(String resource) {
this.resource = resource;
}
/**
* 汉字转成ASCII码
* @param chs 汉字字符串
* @return
*/
private int getChsAscii(String chs) {
int asc = 0;
try {
byte[] bytes = chs.getBytes("gb2312");
if (bytes == null || bytes.length > 2 || bytes.length <= 0) {
throw new RuntimeException("illegal resource string");
}
if (bytes.length == 1) {
asc = bytes[0];
}
if (bytes.length == 2) {
int hightByte = 256 + bytes[0];
int lowByte = 256 + bytes[1];
asc = (256 * hightByte + lowByte) - 256 * 256;
}
}
catch (Exception e) {
System.out
.println("ERROR:ChineseSpelling.class-getChsAscii(String chs)"
+ e);
}
return asc;
}
/**
* 单字解析
* @param str
* @return
*/
public String convert(String str) {
String result = null;
int ascii = getChsAscii(str);
if (ascii > 0 && ascii < 160) {
result = String.valueOf((char) ascii);
}
else {
for (int i = (pyvalue.length - 1); i >= 0; i--) {
if (pyvalue[i] <= ascii) {
result = pystr[i];
break;
}
}
}
return result;
}
/**
* 获取汉字字符串的拼音
* @param chs
* @return
*/
public String getSpelling(String chs) {
chs = chs.toLowerCase(Locale.getDefault());
String key, value;
buffer = new StringBuilder();
for (int i = 0; i < chs.length(); i++) {
key = chs.substring(i, i + 1);
value = getSpellingByWord(key);
buffer.append(value);
}
return buffer.toString();
}
public String getSpelling() {
return this.getSpelling(this.getResource());
}
/**
* 获取汉字字符串的首字母
* @param chs
* @return
*/
public String getSpellingHeadChar(String chs) {
chs = chs.toLowerCase(Locale.getDefault());
String key, value;
buffer = new StringBuilder();
for (int i = 0; i < chs.length(); i++) {
key = chs.substring(i, i + 1);
value = getSpellingByWord(key);
buffer.append(value.charAt(0));
}
return buffer.toString();
}
/**
* 获取一个汉字的拼音
* @param word
* @return
*/
private String getSpellingByWord(String word) {
String value;
if (word.getBytes().length >= 2) {
value = (String) convert(word);
if (value == null) {
value = "unknown";
}
}
else {
value = word;
}
return value;
}
}
2、
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 GetPinyin { 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 (Exception e1) {
e1.printStackTrace();
}
return t4;
} public static String getPinYinHeadChar(String str)
throws BadHanyuPinyinOutputFormatCombination { String convert = "";
for (int j = 0; j < str.length(); j++) {
char word = str.charAt(j);
String[] pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word,
new HanyuPinyinOutputFormat());
if (pinyinArray != null) {
convert += pinyinArray[0].charAt(0);
}
else {
convert += word;
}
}
return convert;
} 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 = "重庆";
System.out.println(getPingYin(cnStr));
try {
System.out.println(getPinYinHeadChar(cnStr));
}
catch (BadHanyuPinyinOutputFormatCombination e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
} }
pinyin4j-2.5.0.jar：
获取汉字拼音 Java的更多相关文章
- C# 获取汉字拼音首字母
最近悟出来一个道理,在这儿分享给大家:学历代表你的过去,能力代表你的现在,学习代表你的将来. 十年河东十年河西,莫欺少年穷 学无止境,精益求精 本节探讨C#获取汉字拼音首字母的方法: 代码类东西, ...
- C/C++ 获取汉字拼音
参考文章:http://blog.csdn.net/thenile/article/details/6318521 在参考文章的基础上,去掉了代码中C++特有的语法和数据类型,用纯C语言实现了获取汉字 ...
- C/C++ 获取汉字拼音首字母
#include <stdint.h> #include <stdio.h> #include <ctype.h> #include <string.h> ...
- C#获取汉字拼音
C#获取汉字拼音 using System; using System.Collections.Generic; using System.Text; using System.Text.Reg ...
- C# 获取汉字拼音首字母/全拼
最近悟出来一个道理,在这儿分享给大家:学历代表你的过去,能力代表你的现在,学习代表你的将来. 十年河东十年河西,莫欺少年穷 学无止境,精益求精 本节探讨C#获取汉字拼音首字母的方法: 代码类东西, ...
- php获取汉字拼音首字母的方法
现实中我们经常看到这样的说明,排名不分先后,按姓名首字母进行排序.这是中国人大多数使用的排序方法.那么在php程序中该如何操作呢? 下面就分享一下在php程序中获取汉字拼音的首字母的方法,在网上搜到的 ...
- ASP.NET获取汉字拼音的首字母
代码 #region GetChineseSpell获取汉字拼音的第一个字母 //获取汉字拼音的第一个字母 static public string GetChineseSpell(string st ...
- C#获取汉字拼音和首字母
C#获取汉字拼音和首字母 引入NPinyin using NPinyin; 调用 /// <summary> /// 中文首字母大写 /// </summary> /// &l ...
- Java 获取汉字拼音的方法
package lius.util; import java.io.Serializable; import java.util.ArrayList; public class JString ...
随机推荐
- SPOJ3267 D-query 离线+树状数组 在线主席树
分析:这个题,离线的话就是水题,如果强制在线,其实和离线一个思路,然后硬上主席树就行了 离线的代码 #include <iostream> #include <stdio.h> ...
- [liu yanling]软件开发的过程按阶段划分有：单元测试 集成测试 系统测试 验收测试
从软件开发的过程按阶段划分有:单元测试 集成测试 系统测试 验收测试测试过程按 4 个步骤进行,概念内容如下:单元测试:单元测试是对软件基本组成单元(如函数.类的方法等)进行的测试.集成测试:集成测试 ...
- 如何从Windows Phone 生成PDF文档
我需要从我的Windows Phone应用程序生成PDF. 遗憾的是没有标准的免费的PDF生成库在Windows Phone上运行. 我不得不自己生成PDF,通过直接写入到文件格式. 这竟然是真的很容 ...
- WebView相关设置
//定义一个WebView的WebSetting WebSettings mWebSettings = mWebView.getSettings(); // 让网页自适应屏幕宽度 ...
- HW2.16
import java.util.Scanner; public class Solution { public static void main(String[] args) { final int ...
- C# Adomd Connection Analysis Service View Cube
首先需要先引用 C:\Program Files\Microsoft.NET\ADOMD.NET\100\Microsoft.AnalysisServices.AdomdClient.dll ...
- 2015年10个最佳Web开发JavaScript库
2015年10个最佳Web开发JavaScript库 现在的互联网可谓是无所不有,有大量的JavaScript项目开发工具充斥于网络中.我们可以参考网上的指导来获取构建代码项目的各种必要信息.如果你是 ...
- SQL Server:OA权限管理设计的实现 下
SQL Server:OA权限管理设计的实现 下 OA系统权限管理设计方案 不同职责的人员,对于系统操作的权限应该是不同的.优秀的业务系统,这是最基本的功能. 可以对“组”进行权限 ...
- 如何用Java进行3DES加密解
原文地址: http://weavesky.com/2008/01/05/java-3des/ 最近一个合作商提出使用3DES交换数据,本来他们有现成的代码,可惜只有.net版本,我们的服务器都是Li ...
- Java获取泛型的Class对象
工作中瞄到的,在此收集了 public class RawDao<T> { protected Class<T> clazz; @SuppressWarnings(" ...