java 生成汉字同音字,拼音相同(二)

小咪咪 2022-06-07 08:19 225阅读 0赞

汉字内码,如涡,内码为CED0,而CED1,CED2皆与涡同音.

代码如下:

import java.io.UnsupportedEncodingException;  
import java.util.regex.Matcher;  
import java.util.regex.Pattern;  
  
  
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 test4 \{  
  
  
  
public static void main(String\[\] args) \{  
System.out.println(test("个"));  
\}  
public static String test(String s)\{  
char\[\] c = getCode(s).toCharArray();  
String test =""+ c\[0\] + c\[1\] + c\[2\];  
for (int i = 0; i < 9; i++) \{  
  
  
String access = getCharacter(test + i);  
  
if(translation(access).equals(translation(s))&&(char)(i + 48)!=c\[3\])\{  
return access;  
\}  
\}  
int ii = c\[2\];  
c\[2\] = (char)(ii + 49);  
test =""+ c\[0\] + c\[1\] + c\[2\];  
for (int i = 0; i < 9; i++) \{  
  
  
String access = getCharacter(test + i);  
  
if(translation(access).equals(translation(s))&&(char)(i + 48)!=c\[3\])\{  
return access;  
\}  
\}  
  
c\[2\] = (char)(ii + 47);  
for (int i = 0; i < 9; i++) \{  
  
  
String access = getCharacter(test + i);  
  
if(translation(access).equals(translation(s))&&(char)(i + 48)!=c\[3\])\{  
return access;  
\}  
\}  
return null;  
\}   
  
private static byte charToByteAscii(char ch) \{  
byte byteAscii = (byte) ch;  
  
  
return byteAscii;  
\}  
private static char byteAsciiToChar(int ascii) \{  
  
  
char ch = (char) ascii;  
;  
return ch;  
\}  
private static String getCode(String chineseName) \{  
StringBuffer sb = new StringBuffer();  
try \{  
char\[\] ch = chineseName.toCharArray();  
for (char c : ch) \{  
if (isCharacter(String.valueOf(c))) \{  
byte\[\] by = String.valueOf(c).getBytes("GBK");  
for (byte b : by) \{  
sb.append(Integer.toHexString(b & 0xff));  
\}  
\} else \{  
byte b = (byte) c;  
sb.append(Integer.toHexString(b & 0xff));  
\}  
\}  
\} catch (Exception e) \{  
e.printStackTrace();  
\}  
  
  
return sb.toString().toUpperCase().trim();  
\}  
private static String getCharacter(String jiNeiMa)\{    
        byte b1 = (byte) Integer.parseInt(jiNeiMa.substring(0, 2), 16);    
        byte b2 = (byte) Integer.parseInt(jiNeiMa.substring(2, 4), 16);    
            
        String str = "";    
        try \{    
            str += new String(new byte\[\]\{b1,b2\}, "GBK");    
        \} catch (UnsupportedEncodingException e) \{    
            e.printStackTrace();    
        \}    
        return str;    
    \}  
private static boolean isCharacter(String str) \{  
Pattern p\_str = Pattern.compile("\[\\\\u4e00-\\\\u9fa5\]+");  
Matcher m = p\_str.matcher(str);  
if (m.find() && m.group(0).equals(str)) \{  
return true;  
\}  
return false;  
\}  
public static String translation(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\[i\]);  
\}  
// System.out.println(t4);  
return t4;  
\} catch (BadHanyuPinyinOutputFormatCombination e1) \{  
e1.printStackTrace();  
\}  
return t4;  
\}  
\}