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

ACIP->Tibetan converters now warn every time {%} is encountered that U+0F14 might've been intended.

Browse source 
The Unicode for ACIP {o} is U+0F37.
This commit is contained in:
dchandler 2003-11-09 23:15:58 +00:00
parent 084e12a02c
commit 2cb90bd231
2 changed files with 10 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
source/org/thdl/tib/text/ttt/ACIPRules.java
View file

@ -501,7 +501,8 @@ public class ACIPRules {
superACIP2unicode.put("`", "\u0F08"); superACIP2unicode.put("`", "\u0F08");
superACIP2unicode.put("*", "\u0F04\u0F05"); superACIP2unicode.put("*", "\u0F04\u0F05");
superACIP2unicode.put("#", "\u0F04\u0F05\u0F05"); superACIP2unicode.put("#", "\u0F04\u0F05\u0F05");
superACIP2unicode.put("%", "\u0F35"); // FIXME: could be U+0F37 or U+0F35 according to RC if I understand correctly. superACIP2unicode.put("%", "\u0F35"); // but might be U+0F14, so we warn.
superACIP2unicode.put("o", "\u0F37");
superACIP2unicode.put(";", "\u0F11"); superACIP2unicode.put(";", "\u0F11");
superACIP2unicode.put("\r", "\r"); superACIP2unicode.put("\r", "\r");
superACIP2unicode.put("\t", "\t"); superACIP2unicode.put("\t", "\t");
@ -511,7 +512,7 @@ public class ACIPRules {
superACIP2unicode.put("^", "\u0F38"); superACIP2unicode.put("^", "\u0F38");
// DLC FIXME: "^ GONG" is "^GONG", right? // DLC FIXME: "^ GONG" is "^GONG", right?
// DLC FIXME: what's the Unicode for x? for o? RC said there is none in plain-text Unicode for x. But what about in RTF Unicode? // DLC FIXME: what's the Unicode for x? RC said there is none in plain-text Unicode for x. But what about in RTF Unicode?
} }
if (subscribed) { if (subscribed) {
String u = (String)subACIP2unicode.get(acip); String u = (String)subACIP2unicode.get(acip);

8
source/org/thdl/tib/text/ttt/ACIPTshegBarScanner.java
View file

@ -160,7 +160,7 @@ public class ACIPTshegBarScanner {
continue; continue;
} }
switch (ch) { switch (ch) {
case '}': case '}': // fall through...
case ']': case ']':
if (bracketTypeStack.empty()) { if (bracketTypeStack.empty()) {
// Error. // Error.
@ -218,6 +218,8 @@ public class ACIPTshegBarScanner {
case '{': // NOTE WELL: KX0016I.ACT, KD0095M.ACT, and a case '{': // NOTE WELL: KX0016I.ACT, KD0095M.ACT, and a
// host of other ACIP files use {} brackets like // host of other ACIP files use {} brackets like
// [] brackets. I treat both the same. // [] brackets. I treat both the same.
// fall through...
case '[': case '[':
// This definitely indicates a new token. // This definitely indicates a new token.
if (startOfString < i) { if (startOfString < i) {
@ -824,6 +826,10 @@ public class ACIPTshegBarScanner {
} }
} }
} }
if ('%' == ch) {
al.add(new TString("The ACIP {%} is treated by this converter as U+0F35, but sometimes might represent U+0F14 in practice",
TString.WARNING));
}
startOfString = i+1; startOfString = i+1;
currentType = TString.ERROR; currentType = TString.ERROR;
break; // end TIBETAN_PUNCTUATION case break; // end TIBETAN_PUNCTUATION case