LegacyConsoleArchive/jpexs-decompiler
1
0
Fork 0
mirror of https://git.huckle.dev/Huckles-Minecraft-Archive/jpexs-decompiler.git synced 2026-09-27 04:30:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Character sets are limited to GB2312, Shift_JIS, Unicode, and all singlebyte.

Browse Source 
Fixed font code points - proper characters display, adding, etc.
This commit is contained in:
Jindra Petřík
2022-11-14 10:04:55 +01:00
parent c266037785
commit 4c6ccf0d63
20 changed files with 21146 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files
libsrc/ffdec_lib/src/com/jpexs/helpers/utf8/Utf8Helper.java
+117 -1
View File
@@ -16,10 +16,21 @@
*/
package com.jpexs.helpers.utf8;
import com.jpexs.helpers.Helper;
import com.jpexs.helpers.utf8.charset.Gb2312;
import com.jpexs.helpers.utf8.charset.ShiftJis;
import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.logging.Level;
import java.util.logging.Logger;
/**
*
@@ -28,8 +39,44 @@ import java.nio.charset.Charset;
public class Utf8Helper {
public static String charsetName = "UTF-8";
public static Charset charset = Charset.forName("UTF-8");
private static List<String> allowedVariableLengthCharsets = Arrays.asList(
"GB2312", "Shift_JIS", "UTF-8", "UTF-16", "UTF16-BE", "UTF-16-LE", "UTF-32", "UTF-32LE", "UTF-32BE");
/**
* Allowed charsets. They are limited to single byte charsets + allowedVariableLengthCharsets
*/
public static List<String> allowedCharsets = new ArrayList<>();
static {
Map<String, Charset> charsets = Charset.availableCharsets();
for (String s : charsets.keySet()) {
Charset charset = charsets.get(s);
int maxLen = 0;
int minLen = Integer.MAX_VALUE;
try {
for (int i = 0; i < 65536; i++) {
ByteBuffer buf = charset.encode("" + (char) i);
int len = buf.remaining();
if (len > maxLen) {
maxLen = len;
}
if (len < minLen) {
minLen = len;
}
}
if ((minLen == maxLen && minLen == 1) || allowedVariableLengthCharsets.contains(s)) {
allowedCharsets.add(s);
}
} catch (UnsupportedOperationException ex) {
//System.out.println(s + " ... ERROR");
}
}
}
public static String urlDecode(String s) {
try {
@@ -55,4 +102,73 @@ public class Utf8Helper {
// todo: make it faster without actually writing it to an array
return string.getBytes(charset).length;
}
public static char codePointToChar(int codePoint, String charsetName) {
int newCodePoint;
switch (charsetName) {
case "GB2312":
newCodePoint = new Gb2312().toUnicode(codePoint);
break;
case "Shift_JIS":
newCodePoint = new ShiftJis().toUnicode(codePoint);
break;
case "UTF-8":
case "UTF-16":
case "UTF-16BE":
case "UTF-16LE":
case "UTF-32":
case "UTF-32BE":
case "UTF-32LE":
newCodePoint = codePoint;
break;
default: {
//Assuming single byte - ANSI
newCodePoint = -1;
try {
newCodePoint = new String(new byte[]{(byte) codePoint}, charsetName).codePointAt(0);
} catch (UnsupportedEncodingException ex) {
Logger.getLogger(Utf8Helper.class.getName()).log(Level.SEVERE, null, ex);
}
}
}
if (newCodePoint >= 0) {
return (char) newCodePoint;
}
return '?';
}
public static int charToCodePoint(char character, String charsetName) {
int unicodeCodePoint = (int) character;
int codePoint;
switch (charsetName) {
case "GB2312":
codePoint = new Gb2312().fromUnicode(unicodeCodePoint);
break;
case "Shift_JIS":
codePoint = new ShiftJis().fromUnicode(unicodeCodePoint);
break;
case "UTF-8":
case "UTF-16":
case "UTF-16BE":
case "UTF-16LE":
case "UTF-32":
case "UTF-32BE":
case "UTF-32LE":
codePoint = unicodeCodePoint;
break;
default: {
codePoint = -1;
try {
//assuming single byte ANSI
codePoint = ("" + character).getBytes(charsetName)[0] & 0xff;
} catch (UnsupportedEncodingException ex) {
Logger.getLogger(Utf8Helper.class.getName()).log(Level.SEVERE, null, ex);
}
}
}
return codePoint;
}
}