Java中获取GBK编码汉字的拼音首字母
网上关于Java中获取汉字的拼音首字母的方法很多,但大多基于GB2312的汉字所属编码位置判断方法,现有一种基于GBK编码计算拼音首字母的方法,参考http://blog.csdn.net/z3h/article/details/6302890
笔者出的源码是读取文件默认编码格式,默认是GBK,如果文件默认格式不是GBK将报错,现在代码读取的格式默认设置为GBK,如下:
package com;
import java.io.UnsupportedEncodingException;
/**
* 取得汉字拼音码.
* 支持GBK大字符集.
* @author Zhao Honghui
* @version 1.0
*/
public class GetPy {
private static final String GB_2312 =
"aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaabbbbbbbbbbbbbp" +
"bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbpbbbbbbbbbbbbbbbbbb" +
"bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb" +
"pbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb" +
"bbbbbbbbbbbbbbbbbbbbcccccccccccccccccccccccccccccc" +
"ccccccccccccccccccccccccccccccccccczcccccccccccccc" +
"ccccccccccccccccccccccccccccccccccccsccccccccccccc" +
"cccccccccccccccccccccccccccccccccccccccccczccccccc" +
"cccccccccccccccccccccccccccccccccccccccccccccccccc" +
"cccddddddddddddddddddddddddddddddddddddddddddddddd" +
"dddddddddddddddddddddzdddddddddddddddddddddddddddd" +
"dddddddddddddddddddddddddddddddtdddddddddddddddddd" +
"dddddddddddddddddddddddddddddddddddddeeeeeeeeeeeee" +
"eeeeeeeeefffffffffffffffffffffffffffffffffffffffff" +
"ffffffffffffffffffffffffffffffffffffffffffffffffff" +
"fffffffffffffpffffffffffffffffffffgggggggggggggggg" +
"ggggggggggggggggggghggggggggggggghgggggggggggggggg" +
"gggggggggggggggggggggggggggggggggggggggggggggggggg" +
"ggggggggggggggggggggggggggggggggggggggghhhhhhhhhhh" +
"hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhmhhhhhhhhhhh" +
"hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh" +
"hhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh" +
"hhhhhhhhhhhhhhhhhhhhjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjjjjjjjjkjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjyjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj" +
"jjjjjjjjjjjjjjjkkkgkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkh" +
"kkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkkk" +
"kkkkkkkkkkkkkkklllllllllllllllllllllllllllllllllll" +
"llllllllllllllllllllllllllllllllllllllllllllllllll" +
"llllllllllllllllllllllllllllllllllllllllllllllllll" +
"llllllllllllllllllllllllllllllllllllllllllllllllll" +
"llllllllllllllllllllllllllllllllllllllllllllllllll" +
"lllllllllllllmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm" +
"mmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm" +
"mmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmmm" +
"mmmmmmmmmmmmmmnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnn" +
"nnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnnooooo" +
"oooppppppppppppppppppppppppppppppppppppppppppppppp" +
"pppppppppppppppppppppppppppppppppppppppppppppppppp" +
"ppppppppppppppppppppppppbqqqqqqqqqqqqqqqqqqqqqqqqq" +
"qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq" +
"qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq" +
"qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqrrrrrrrrrrrrrrrrrr" +
"rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrsssssssss" +
"ssssssssssssssssssssssssssssssssssssssssssssssssss" +
"ssssssssssssssssssssssssssssssssssssssssssssssssss" +
"ssssssssssssssssssssssssssssssssssssssssssssssssss" +
"ssssssssssssssssssssssssssssssssssssssssssssssssss" +
"sssssssssssssssssssssssssssssssssssssssssssssssssx" +
"sssssssssssssssssssssssssssttttttttttttttttttttttt" +
"tttttttttttttttttttttttttttttttttttttttttttttttttt" +
"tttttttttttttttttttttttttttttttttttttttttttttttttt" +
"tttttttttttttttttttttttttttttttttwwwwwwwwwwwwwwwww" +
"wwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwww" +
"wwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwwww" +
"wwwxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxsx" +
"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" +
"xxxxxxxxxxxxxxxxxxxxxjxxxxxxxxxxxxxxxxxxxxxxxxxxxx" +
"xxxxxhxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxcxxxxxxxxx" +
"xxxxxxxxxxxxxxxxxxxxxxxxxxyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyxyyyyyyyyyyyyyyyyyyyyyyyyy" +
"yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzczzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz" +
"zzzzz cjwgnspgcgnesypbtyyzdxykygtdjnnjqmbsjzsc" +
"yjsyyfpgkbzgylywjkgkljywkpjqhytwddzlsymrypywwcckzn" +
"kyygttngjnykkzytcjnmcylqlypysfqrpzslwbtgkjfyxjwzlt" +
"bncxjjjjtxdttsqzycdxxhgckbphffsswybgmxlpbylllhlxst" +
"zmyjhsojnghdzqyklgjhsgqzhxqgkxzzwyscscjxyeyxadzpmd" +
"ssmzjzqjyzcdjzwqjbyzbjgznzcpwhwxhqkmwfbpbydtjzzkxx" +
"ylygxfptyjyyzpszlfchmqshgmxxsxjyqdcsbbqbefsjyhxwgz" +
"kpylqbgldlcdtnmaeddkssngycsgxlyzaypnptsdkdylhgymyl" +
"cxpycjndqjwxqxfyyfjlejpzrxccqwqqsbzkymgplbmjrqcfln" &