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

ACIP->TMW and ACIP->Unicode are now smart about when a newline is

Browse source 
really a newline and when a space is really a tsheg. The space in {KA
,MDO} is a tsheg, but the space in {GA ,MDO} is not.
This commit is contained in:
dchandler 2003-09-04 04:04:21 +00:00
parent 72e531e515
commit d2749cecd0
2 changed files with 100 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

24
source/org/thdl/tib/text/ttt/ACIPTshegBarScanner.java
View file

@ -767,13 +767,33 @@ public class ACIPTshegBarScanner {
case ';':
case '`':
case '#':
// The tsheg bar ends here; new token.
if (startOfString < i) {
al.add(new ACIPString(s.substring(startOfString, i),
currentType));
}
al.add(new ACIPString(s.substring(i, i+1),
ACIPString.TIBETAN_PUNCTUATION));
// Insert a tsheg if necessary. ACIP files aren't
// careful, so "KA\r\n" and "GA\n" appear where "KA
// \r\n" and "GA \n" should appear.
if (('\r' == ch
|| '\n' == ch)
&& !al.isEmpty()
&& ((ACIPString)al.get(al.size() - 1)).getType() == ACIPString.TIBETAN_NON_PUNCTUATION) {
al.add(new ACIPString(" ",
ACIPString.TIBETAN_PUNCTUATION));
}
// Don't add in a "\r\n" or "\n" unless there's a
// blank line.
boolean rn = false;
if (('\n' != ch && '\r' != ch)
|| ((rn = ('\n' == ch && i >= 3 && s.charAt(i-3) == '\r' && s.charAt(i-2) == '\n' && s.charAt(i-1) == '\r'))
|| ('\n' == ch && i >= 1 && s.charAt(i-1) == '\n'))) {
al.add(new ACIPString(rn ? s.substring(i - 1, i+1) : s.substring(i, i+1),
ACIPString.TIBETAN_PUNCTUATION));
}
startOfString = i+1;
currentType = ACIPString.ERROR;
break; // end TIBETAN_PUNCTUATION case