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

EWTS->Unicode for // now produces \u0f0e as it should.

This commit is contained in:
dchandler 2005-07-10 05:01:03 +00:00
parent 64625fd445
commit 33fc836e81
3 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
source/org/thdl/tib/text/ttt/EWTSTest.java
View File

@ -676,7 +676,9 @@ public class EWTSTest extends TestCase {
ewts2uni_test(" ", "\u0F0B");
ewts2uni_test("*", "\u0F0C");
ewts2uni_test("/", "\u0F0D");
if (RUN_FAILING_TESTS) ewts2uni_test("//", "\u0F0E");
ewts2uni_test("//", "\u0F0E");
ewts2uni_test("////", "\u0F0E\u0f0e");
ewts2uni_test("/////", "\u0F0E\u0f0e\u0f0d");
ewts2uni_test(";", "\u0F0F");
ewts2uni_test("\\u0F10", "\u0F10");
ewts2uni_test("|", "\u0F11");

1
source/org/thdl/tib/text/ttt/EWTSTraits.java
View File

@ -397,6 +397,7 @@ public final class EWTSTraits implements TTraits {
if ("R".equals(l)) return "\u0f6a";
if ("Y".equals(l)) return "\u0f61";
if ("W".equals(l)) return "\u0f5d";
if ("//".equals(l)) return "\u0f0e";
if (!TibetanMachineWeb.isKnownHashKey(l)) {
// System.err.println("Getting unicode for the following is hard: '"

28
source/org/thdl/tib/text/ttt/EWTSTshegBarScanner.java
View File

@ -79,7 +79,7 @@ class EWTSTshegBarScanner extends TTshegBarScanner {
// TODO(DLC)[EWTS->Tibetan]:: '@#', in ewts->tmw, is not working
// TODO(DLC)[EWTS->Tibetan]:: 'jamX 'jam~X one is not working in ->tmw mode
// TODO(DLC)[EWTS->Tibetan]:: dzaHsogs is not working
for (int i = 0; i < sl; i++) {
for (int i = 0; i < sl; i++) { // i is modified in the loop, also
if (isValidInsideTshegBar(sb.charAt(i))) {
StringBuffer tbsb = new StringBuffer();
for (; i < sl; i++) {
@ -96,16 +96,22 @@ class EWTSTshegBarScanner extends TTshegBarScanner {
// NOTE: It's questionable, but we treat
// \u0f00 like punctuation because it was
// easier coding that way.
if ((sb.charAt(i) >= EWTSTraits.PUA_MIN
&& sb.charAt(i) <= EWTSTraits.PUA_MAX)
|| (sb.charAt(i) >= '\u0f00' && sb.charAt(i) <= '\u0f17')
|| (sb.charAt(i) >= '\u0f1a' && sb.charAt(i) <= '\u0f1f')
|| (sb.charAt(i) >= '\u0fbe' && sb.charAt(i) <= '\u0fcc')
|| (sb.charAt(i) >= '\u0fcf' && sb.charAt(i) <= '\u0fd1')
|| (EWTSTraits.SAUVASTIKA == sb.charAt(i))
|| (EWTSTraits.SWASTIKA == sb.charAt(i))
|| (" /;|!:=_@#$%<>()*&\r\n\t\u0f36\u0f38\u0f89\u0f8a\u0f8b".indexOf(sb.charAt(i))
>= 0)) {
if (i + 1 < sl
&& sb.charAt(i) == '/'
&& sb.charAt(i + 1) == '/') {
al.add(new TString("EWTS", "//",
TString.TIBETAN_PUNCTUATION));
++i;
} else if ((sb.charAt(i) >= EWTSTraits.PUA_MIN
&& sb.charAt(i) <= EWTSTraits.PUA_MAX)
|| (sb.charAt(i) >= '\u0f00' && sb.charAt(i) <= '\u0f17')
|| (sb.charAt(i) >= '\u0f1a' && sb.charAt(i) <= '\u0f1f')
|| (sb.charAt(i) >= '\u0fbe' && sb.charAt(i) <= '\u0fcc')
|| (sb.charAt(i) >= '\u0fcf' && sb.charAt(i) <= '\u0fd1')
|| (EWTSTraits.SAUVASTIKA == sb.charAt(i))
|| (EWTSTraits.SWASTIKA == sb.charAt(i))
|| (" /;|!:=_@#$%<>()*&\r\n\t\u0f36\u0f38\u0f89\u0f8a\u0f8b".indexOf(sb.charAt(i))
>= 0)) {
al.add(new TString("EWTS", sb.substring(i, i+1),
TString.TIBETAN_PUNCTUATION));
} else {