Tools/texdoclet
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

encoding issues fix

Browse Source
This commit is contained in:
stfm
2013-05-07 12:07:27 +02:00
parent 746ed12019
commit 997e7b7007
1 changed files with 59 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
src/main/java/org/stfm/texdoclet/HTMLtoLaTeXBackEnd.java
View File

@@ -10,6 +10,7 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.Reader;
import java.io.StringReader;
import java.nio.charset.Charset;
import java.text.NumberFormat;
import java.text.ParseException;
import java.util.Hashtable;
@@ -559,59 +560,81 @@ public class HTMLtoLaTeXBackEnd extends HTMLEditorKit.ParserCallback {
i++;
}
break;
// case 'æ':
case '¾':
// case 0xc38a:
case 0xc3a6:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\ae\\ ");
i++;
} else {
ret.append("\\ae ");
}
} else {
ret.append((char) c);
}
break;
// case 'Æ':
case '®':
case 0xc386:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\AE\\ ");
i++;
} else {
ret.append("\\AE ");
}
} else {
ret.append((char) c);
}
break;
// case 'å':
case 'Œ':
// case 0xc382:
case 0xc3a5:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\aa\\ ");
i++;
} else {
ret.append("\\aa ");
}
} else {
ret.append((char) c);
}
break;
// case 'Å':
case '<27>':
case 0xc385:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\AA\\ ");
i++;
} else {
ret.append("\\AA ");
}
} else {
ret.append((char) c);
}
break;
// case 'ø':
case '¿':
// case 0xc2af:
case 0xc3b8:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\o\\ ");
i++;
} else {
ret.append("\\o ");
}
} else {
ret.append((char) c);
}
break;
// case 'Ø':
case '¯':
// case 0xc3bf:
case 0xc398:
if (Charset.defaultCharset().name().equals("UTF-8")) {
if (i < str.length() - 1 && str.charAt(i + 1) == ' ') {
ret.append("\\O\\ ");
i++;
} else {
ret.append("\\O ");
}
} else {
ret.append((char) c);
}
break;
case '^':
ret.append("$\\wedge$");