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

Changed converters from unicode non-breaking tsheg to unicode non-breaking wylie space.

Browse source
This commit is contained in:
amontano 2009-02-20 23:11:17 +00:00
parent ffb32b3207
commit 835e74c0cd
7 changed files with 56 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

19
source/org/thdl/tib/scanner/BasicTibetanTranscriptionConverter.java
View file

@ -46,7 +46,6 @@ 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)
@ -253,19 +252,7 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
nuevaPalabra = Manipulate.fixWazur(nuevaPalabra);
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)
{
@ -274,9 +261,9 @@ public class BasicTibetanTranscriptionConverter implements FontConverterConstant
TibetanDocument tibDoc;
StringBuffer errors;
int posStart=0, posEnd;
while((posStart = getTibetanUnicodeStart(unicode, posStart))>=0)
while((posStart = Manipulate.getTibetanUnicodeStart(unicode, posStart))>=0)
{
posEnd = getTibetanUnicodeEnd(unicode, posStart+1);
posEnd = Manipulate.getTibetanUnicodeEnd(unicode, posStart+1);
startString = unicode.substring(0, posStart);
tibetanString = unicode.substring(posStart, posEnd);
endString = unicode.substring(posEnd);

45
source/org/thdl/tib/scanner/Manipulate.java
View file

@ -28,6 +28,7 @@ public class Manipulate
private static String bracketMarks = "<>(){}[]";
private static String endOfSyllableMarks = " _\t";
private static String allStopMarkers = endOfSyllableMarks + endOfParagraphMarks + bracketMarks;
private static final int TIBETAN_UNICODE_RANGE[] = {3840, 4095};
/* public static String[] parseFields (String s, char delimiter)
{
@ -204,6 +205,18 @@ public class Manipulate
return ch>=0xF00 && ch<=0xFFF;
}
public static boolean isTibetanUnicodeLetter(char ch)
{
return ch>=0xF40 && ch<=0xFBC || ch>=0xF00 && ch<=0xF03;
}
public static boolean isTibetanUnicodeDigit(char ch)
{
return ch>=0xF20 && ch<=0xF33;
}
public static boolean guessIfUnicode(String line)
{
char ch;
@ -415,4 +428,36 @@ public class Manipulate
}
return ncr.toString();
}
public static String unescape(String s) {
int i=0,len=s.length();
char c;
StringBuffer sb = new StringBuffer(len);
while (i<len) {
c = s.charAt(i++);
if (c=='\\') {
if (i<len) {
c = s.charAt(i++);
if (c=='u') {
c = (char) Integer.parseInt(s.substring(i,i+4),16);
i += 4;
} // add other cases here as desired...
}} // fall through: \ escapes itself, quotes any character but u
sb.append(c);
}
return sb.toString();
}
public 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;
}
public 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;
}
}