将HTML中的特殊字符转化为可显示的字符

/**
* Convert HTML character enitities(Unicode) to part of a Java String
*/
import java.util.regex.*;

public class UnicodeCeToJavaString {
static final String mbs = "&#(\\d+);"; // like "ロ"

public static String EncodeCesToChars(String paramStr) {
paramStr = paramStr.replace("&","&")
.replace("<","<")
.replace(">",">")
.replace(""","\"")
.replace(" "," ")
.replace("'","'");

String mbChar;
StringBuffer sb = new StringBuffer();
Pattern pat = Pattern.compile(mbs);
Matcher mat = pat.matcher(paramStr);
while (mat.find()) {
mbChar = getMbCharStr(mat.group(1)); // pass the digit part
mat.appendReplacement(sb, mbChar);
}
mat.appendTail(sb);
return new String(sb);
}

/* worker method */
static String getMbCharStr(String digits) { // handle "12525" part which is
// a
char[] cha = new char[1]; // Unicode value stringnized
try {
int val = Integer.parseInt(digits);
char ch = (char) val;
cha[0] = ch;
} catch (Exception e) {
System.err.println("Error from getMbCharStr:");
e.printStackTrace(System.err);
}
return new String(cha); // easy!, because Java uses Unicode
}

public static void main(String[] args) {
System.out.println(UnicodeCeToJavaString.EncodeCesToChars("George's War in North America"));
}
}