下面类中的getBeginCharacter()方法是根据传入的字符串参数,将字符串转化为拼音首字母的简称,比如: 参数为"中国",返回: zg 参数为:"中国yxz" 返回: zgyxz
请问下列方法为什么在中文Windows NT系统下能够正确的返回,,而在英文Unix系统下返回的是乱码?
请各位高手指点迷津,,,急!!!!public class StringUitls{
private static String _FromEncode_ = "GBK";
private static String _ToEncode_ = "GBK"; /**
* 被getBeginCharacter方法调用
*
* @param str1 String
* @param str2 String
* @return result
*/
private static int compare(String str1, String str2) {
int result = 0;
String m_s1 = null;
String m_s2 = null;
try {
m_s1 = new String(str1.getBytes(_FromEncode_), _ToEncode_);
m_s2 = new String(str2.getBytes(_FromEncode_), _ToEncode_); } catch (Exception e) {
return str1.compareTo(str2);
}
result = chineseCompareTo(m_s1, m_s2); return result;
} /**
* 被getBeginCharacter方法调用
*
* @param s String
* @return value int
*/ private static int getCharCode(String s) {
if (s == null && s.equals("")) {
return -1;
}
byte b[] = s.getBytes();
int value = 0;
for (int i = 0; i < b.length && i <= 2; i++) {
value = value * 100 + b[i];
} return value;
} /**
* 被getBeginCharacter方法调用
*
* @param s1 String
* @param s2 String
* @return int len1 - len2
*/ public static int chineseCompareTo(String s1, String s2) {
int len1 = s1.length();
int len2 = s2.length();
int n = Math.min(len1, len2);
for (int i = 0; i < n; i++) {
int s1_code = getCharCode(s1.charAt(i) + "");
int s2_code = getCharCode(s2.charAt(i) + ""); if (s1_code * s2_code < 0) {
return Math.min(s1_code, s2_code);
}
if (s1_code != s2_code) {
return s1_code - s2_code;
}
} return len1 - len2;
} /**
* 将中文名称转化为拼音首字母的简称
*
* @param String res 中文名称
* @return String result 拼音首字母的简称
*/
public static String getBeginCharacter(String res) {
String a = res;
String result = "";
for (int i = 0; i < a.length(); i++) {
String current = a.substring(i, i + 1);
if (compare(current, "\u554A") < 0) {
result = result + current; } else if (compare(current, "\u554A") >= 0
&& compare(current, "\u5EA7") <= 0) {
if (compare(current, "\u531D") >= 0) {
result = result + "z";
} else if (compare(current, "\u538B") >= 0) {
result = result + "y";
} else if (compare(current, "\u6614") >= 0) {
result = result + "x";
} else if (compare(current, "\u6316") >= 0) {
result = result + "w";
} else if (compare(current, "\u584C") >= 0) {
result = result + "t";
} else if (compare(current, "\u6492") >= 0) {
result = result + "s";
} else if (compare(current, "\u7136") >= 0) {
result = result + "r";
} else if (compare(current, "\u671F") >= 0) {
result = result + "q";
} else if (compare(current, "\u556A") >= 0) {
result = result + "p";
} else if (compare(current, "\u54E6") >= 0) {
result = result + "o";
} else if (compare(current, "\u62FF") >= 0) {
result = result + "n";
} else if (compare(current, "\u5988") >= 0) {
result = result + "m";
} else if (compare(current, "\u5783") >= 0) {
result = result + "l";
} else if (compare(current, "\u5580") >= 0) {
result = result + "k";
} else if (compare(current, "\u51FB") > 0) {
result = result + "j";
} else if (compare(current, "\u54C8") >= 0) {
result = result + "h";
} else if (compare(current, "\u5676") >= 0) {
result = result + "g";
} else if (compare(current, "\u53D1") >= 0) {
result = result + "f";
} else if (compare(current, "\u86FE") >= 0) {
result = result + "e";
} else if (compare(current, "\u642D") >= 0) {
result = result + "d";
} else if (compare(current, "\u64E6") >= 0) {
result = result + "c";
} else if (compare(current, "\u82AD") >= 0) {
result = result + "b";
} else if (compare(current, "\u554A") >= 0) {
result = result + "a";
}
}
}
return result;
} public static void main(String[] args) {
StringUitls t = new StringUitls();
System.out.println("简拼 = : "+ t.getBeginCharacter("中国"));
}}
请问下列方法为什么在中文Windows NT系统下能够正确的返回,,而在英文Unix系统下返回的是乱码?
请各位高手指点迷津,,,急!!!!public class StringUitls{
private static String _FromEncode_ = "GBK";
private static String _ToEncode_ = "GBK"; /**
* 被getBeginCharacter方法调用
*
* @param str1 String
* @param str2 String
* @return result
*/
private static int compare(String str1, String str2) {
int result = 0;
String m_s1 = null;
String m_s2 = null;
try {
m_s1 = new String(str1.getBytes(_FromEncode_), _ToEncode_);
m_s2 = new String(str2.getBytes(_FromEncode_), _ToEncode_); } catch (Exception e) {
return str1.compareTo(str2);
}
result = chineseCompareTo(m_s1, m_s2); return result;
} /**
* 被getBeginCharacter方法调用
*
* @param s String
* @return value int
*/ private static int getCharCode(String s) {
if (s == null && s.equals("")) {
return -1;
}
byte b[] = s.getBytes();
int value = 0;
for (int i = 0; i < b.length && i <= 2; i++) {
value = value * 100 + b[i];
} return value;
} /**
* 被getBeginCharacter方法调用
*
* @param s1 String
* @param s2 String
* @return int len1 - len2
*/ public static int chineseCompareTo(String s1, String s2) {
int len1 = s1.length();
int len2 = s2.length();
int n = Math.min(len1, len2);
for (int i = 0; i < n; i++) {
int s1_code = getCharCode(s1.charAt(i) + "");
int s2_code = getCharCode(s2.charAt(i) + ""); if (s1_code * s2_code < 0) {
return Math.min(s1_code, s2_code);
}
if (s1_code != s2_code) {
return s1_code - s2_code;
}
} return len1 - len2;
} /**
* 将中文名称转化为拼音首字母的简称
*
* @param String res 中文名称
* @return String result 拼音首字母的简称
*/
public static String getBeginCharacter(String res) {
String a = res;
String result = "";
for (int i = 0; i < a.length(); i++) {
String current = a.substring(i, i + 1);
if (compare(current, "\u554A") < 0) {
result = result + current; } else if (compare(current, "\u554A") >= 0
&& compare(current, "\u5EA7") <= 0) {
if (compare(current, "\u531D") >= 0) {
result = result + "z";
} else if (compare(current, "\u538B") >= 0) {
result = result + "y";
} else if (compare(current, "\u6614") >= 0) {
result = result + "x";
} else if (compare(current, "\u6316") >= 0) {
result = result + "w";
} else if (compare(current, "\u584C") >= 0) {
result = result + "t";
} else if (compare(current, "\u6492") >= 0) {
result = result + "s";
} else if (compare(current, "\u7136") >= 0) {
result = result + "r";
} else if (compare(current, "\u671F") >= 0) {
result = result + "q";
} else if (compare(current, "\u556A") >= 0) {
result = result + "p";
} else if (compare(current, "\u54E6") >= 0) {
result = result + "o";
} else if (compare(current, "\u62FF") >= 0) {
result = result + "n";
} else if (compare(current, "\u5988") >= 0) {
result = result + "m";
} else if (compare(current, "\u5783") >= 0) {
result = result + "l";
} else if (compare(current, "\u5580") >= 0) {
result = result + "k";
} else if (compare(current, "\u51FB") > 0) {
result = result + "j";
} else if (compare(current, "\u54C8") >= 0) {
result = result + "h";
} else if (compare(current, "\u5676") >= 0) {
result = result + "g";
} else if (compare(current, "\u53D1") >= 0) {
result = result + "f";
} else if (compare(current, "\u86FE") >= 0) {
result = result + "e";
} else if (compare(current, "\u642D") >= 0) {
result = result + "d";
} else if (compare(current, "\u64E6") >= 0) {
result = result + "c";
} else if (compare(current, "\u82AD") >= 0) {
result = result + "b";
} else if (compare(current, "\u554A") >= 0) {
result = result + "a";
}
}
}
return result;
} public static void main(String[] args) {
StringUitls t = new StringUitls();
System.out.println("简拼 = : "+ t.getBeginCharacter("中国"));
}}
m_s2 = new String(str2.getBytes(), _ToEncode_);
在创建String的时候指定
中文系统下当然是GBK,so str1.getBytes()和str1.getBytes("GBK")结果是一样的
new String(str1.getBytes("GBK"), "GBK"),GBK转GBK根本没有任何意义。
unix下如果str1.getBytes("GBK")的化,编码不符了
m_s2 = new String(str2.getBytes(_FromEncode_));