thdltools/Jskad
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Updated unicode to wylie converter to only convert chars in the tibetan range and ignore other chars.

Browse source
This commit is contained in:
amontano 2008-12-15 06:08:19 +00:00
parent 36e222fccc
commit ffb32b3207
1 changed files with 474 additions and 446 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java
View file

@ -46,6 +46,7 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
private static final int WYLIE_TO_ACIP=2;
private static final int UNICODE_TO_WYLIE=3;
private static final int WYLIE_TO_UNICODE=4;
private static final int TIBETAN_UNICODE_RANGE[] = {3840, 4095};
/** Converts from the Acip transliteration scheme to EWTS.*/
public static String acipToWylie(String acip)
@ -253,14 +254,36 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
return nuevaPalabra;*/
}
private static int getTibetanUnicodeStart(String unicode, int pos)
{
for(; pos < unicode.length(); pos++ ) if(unicode.codePointAt(pos)>=TIBETAN_UNICODE_RANGE[0] && unicode.codePointAt(pos)<=TIBETAN_UNICODE_RANGE[1]) return pos;
return -1;
}
private static int getTibetanUnicodeEnd(String unicode, int pos)
{
for(; pos < unicode.length(); pos++ ) if(unicode.codePointAt(pos)<TIBETAN_UNICODE_RANGE[0] || unicode.codePointAt(pos)>TIBETAN_UNICODE_RANGE[1]) return pos;
return pos;
}
/** Converts Tibetan Unicode to EWTS. */
public static String unicodeToWylie(String unicode)
{
String machineWylie;
TibetanDocument tibDoc = new TibetanDocument();
StringBuffer errors = new StringBuffer();
machineWylie = Converter.convertToEwtsForComputers(unicode, errors);
String machineWylie, startString, tibetanString, endString;
TibetanDocument tibDoc;
StringBuffer errors;
int posStart=0, posEnd;
while((posStart = getTibetanUnicodeStart(unicode, posStart))>=0)
{
posEnd = getTibetanUnicodeEnd(unicode, posStart+1);
startString = unicode.substring(0, posStart);
tibetanString = unicode.substring(posStart, posEnd);
endString = unicode.substring(posEnd);
tibDoc = new TibetanDocument();
errors = new StringBuffer();
machineWylie = Converter.convertToEwtsForComputers(tibetanString, errors);
try
{
TibTextUtils.insertTibetanMachineWebForTranslit(true, machineWylie, tibDoc, 0, false);
@ -269,7 +292,9 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
{
return null;
}
return tibDoc.getWylie(new boolean[] { false });
unicode = startString + tibDoc.getWylie(new boolean[] { false }) + endString;
}
return unicode;
}
/** Converts EWTS to Tibetan Unicode. */
@ -424,10 +449,13 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
break;
default: result = linea;
}
if (result!=null) out.println(result);
}
if (result!=null)
{
out.println(result);
out.flush();
}
}
}
public static BufferedReader getBufferedReader(String s, String format) throws Exception
{