本文摘自“和荣笔记 - GB2312 字符集与编码对照表”
简体中文有两种常用编码:GB2312 和 Unicode. 它们的对应关系可以用
下面的程式所生成:
/**
* GB2312Unicde.java
* Copyright (c) 2003 by Dr. Herong Yang, http://www.herongyang.com/
*/
import java.io.*;
import java.nio.*;
import java.nio.charset.*;
class GB2312Unicde {
static OutputStream out = null;
static char hexDigit[] = {'0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', 'A', 'B', 'C', 'D', 'E', 'F'};
static int b_out[] = {201,267,279,293,484,587,625,657,734,782,827,
874,901,980,5590};
static int e_out[] = {216,268,280,294,494,594,632,694,748,794,836,
894,903,994,5594};
public static void main(String[] args) {
try {
out = new FileOutputStream("gb2312.gb");
writeCode();
out.close();
} catch (IOException e) {
System.out.println(e.toString());
}
}
public static void writeCode() throws IOException {
boolean reserved = false;
String name = null;
// GB2312 is not supported by JDK. So I am using GBK.
CharsetDecoder gbdc = Charset.forName("GBK").newDecoder();
CharsetEncoder uxec = Charset.forName("UTF-16BE").newEncoder();
CharsetEncoder u8ec = Charset.forName("UTF-8").newEncoder();
ByteBuffer gbbb = null;
ByteBuffer uxbb = null;
ByteBuffer u8bb = null;
CharBuffer cb = null;
int count = 0;
for (int i=1; i<=94; i++) {
// Defining row settings
if (i>=1 && i<=9) {
reserved = false;
name = "Graphic symbols";
} else if (i>=10 && i<=15) {
reserved = true;
name = "Reserved";
} else if (i>=16 && i<=55) {
reserved = false;
name = "Level 1 characters";
} else if (i>=56 && i<=87) {
reserved = false;
name = "Level 2 characters";
} else if (i>=88 && i<=94) {
reserved = true;
name = "Reserved";
}
// writing row title
writeln();
writeString("<p>");
writeNumber(i);
writeString(" Row: "+name);
writeln();
writeString("</p>");
writeln();
if (!reserved) {
writeln();
writeHeader();
// looping through all characters in one row
for (int j=1; j<=94; j++) {
byte hi = (byte)(0xA0 + i);
byte lo = (byte)(0xA0 + j);
if (validGB(i,j)) {
// getting GB, UTF-16BE, UTF-8 codes
gbbb = ByteBuffer.wrap(new byte[]{hi,lo});
try {
cb = gbdc.decode(gbbb);
uxbb = uxec.encode(cb);
cb.rewind();
u8bb = u8ec.encode(cb);
} catch (CharacterCodingException e) {
cb = null;
uxbb = null;
u8bb = null;
}
} else {
cb = null;
uxbb = null;
u8bb = null;
}
writeNumber(i);
writeNumber(j);
writeString(" ");
if (cb!=null) {
writeByte(hi);
writeByte(lo);
writeString(" ");
writeHex(hi);
writeHex(lo);
count++;
} else {
writeGBSpace();
writeString(" null");
}
writeString(" ");
writeByteBuffer(uxbb,2);
writeString(" ");
writeByteBuffer(u8bb,3);
if (j%2 == 0) {
writeln();
} else {
writeString(" ");
}
}
writeFooter();
}
}
System.out.println("Number of GB characters worte: "+count);
}
public static void writeln() throws IOException {
out.write(0x0D);
out.write(0x0A);
}
public static void writeByte(byte b) throws IOException {
out.write(b & 0xFF);
}
public static void writeByteBuffer(ByteBuffer b, int l)
throws IOException {
int i = 0;
if (b==null) {
writeString("null");
i = 2;
} else {
for (i=0; i<b.limit(); i++) writeHex(b.get(i));
}
for (int j=i; j<l; j++) writeString(" ");
}
public static void writeGBSpace() throws IOException {
out.write(0xA1);
out.write(0xA1);
}
public static void writeString(String s) throws IOException {
if (s!=null) {
for (int i=0; i<s.length(); i++) {
out.write((int) (s.charAt(i) & 0xFF));
}
}
}
public static void writeNumber(int i) throws IOException {
String s = "00" + String.valueOf(i);
writeString(s.substring(s.length()-2,s.length()));
}
public static void writeHex(byte b) throws IOException {
out.write((int) hexDigit[(b >> 4) & 0x0F]);
out.write((int) hexDigit[b & 0x0F]);
}
public static void writeHeader() throws IOException {
writeString("<pre>");
writeln();
writeString("Q.W. ");
writeGBSpace();
writeString(" GB Uni. UTF-8 ");
writeString(" ");
writeString("Q.W. ");
writeGBSpace();
writeString(" GB Uni. UTF-8 ");
writeln();
writeln();
}
public static void writeFooter() throws IOException {
writeString("</pre>");
writeln();
}
public static boolean validGB(int i,int j) {
for (int l=0; l<b_out.length; l++) {
if (i*100+j>=b_out[l] && i*100+j<=e_out[l]) return false;
}
return true;
}
} |
程式输出的例表格式如下:
Q.W. GB Uni. UTF-8 Q.W. GB Uni. UTF-8
1601 啊 B0A1 554A E5958A 1602 阿 B0A2 963F E998BF
1603 埃 B0A3 57C3 E59F83 1604 挨 B0A4 6328 E68CA8
1605 哎 B0A5 54CE E5938E 1606 唉 B0A6 5509 E59489
1607 哀 B0A7 54C0 E59380 1608 皑 B0A8 7691 E79A91
1609 癌 B0A9 764C E7998C 1610 蔼 B0AA 853C E894BC
1611 矮 B0AB 77EE E79FAE 1612 艾 B0AC 827E E889BE
1613 碍 B0AD 788D E7A28D 1614 爱 B0AE 7231 E788B1
1615 隘 B0AF 9698 E99A98 1616 鞍 B0B0 978D E99E8D
1617 氨 B0B1 6C28 E6B0A8 1618 安 B0B2 5B89 E5AE89
1619 俺 B0B3 4FFA E4BFBA 1620 按 B0B4 6309 E68C89
1621 暗 B0B5 6697 E69A97 1622 岸 B0B6 5CB8 E5B2B8
1623 胺 B0B7 80FA E883BA 1624 案 B0B8 6848 E6A188
1625 肮 B0B9 80AE E882AE 1626 昂 B0BA 6602 E69882
1627 盎 B0BB 76CE E79B8E 1628 凹 B0BC 51F9 E587B9
1629 敖 B0BD 6556 E69596 1630 熬 B0BE 71AC E786AC
1631 翱 B0BF 7FF1 E7BFB1 1632 袄 B0C0 8884 E8A284
1633 傲 B0C1 50B2 E582B2 1634 奥 B0C2 5965 E5A5A5
1635 懊 B0C3 61CA E6878A 1636 澳 B0C4 6FB3 E6BEB3
。。。 |