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

Added UI for EWTS->Tibetan conversions. GUI is disabled except in

Browse source 
debug mode for now.

I tested against a really simple-but-real document, found a bug with '*', tried
to implement TMW vowel code but I don't trust it yet.  Differentiated EWTS
code from ACIP where needed.

Several bugs in ewts->tibetan have been exposed; see the TODO
comments.
This commit is contained in:
dchandler 2005-06-20 09:30:35 +00:00
parent 7198f23361
commit 2678fc134a
9 changed files with 150 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

1
source/org/thdl/tib/text/ttt/ACIPTraits.java
View file

@ -560,6 +560,7 @@ public final class ACIPTraits implements TTraits {
} else if (wowel.indexOf("'I") >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.I_VOWEL, context_added);
} else {
// TODO(dchandler): I don't understand why we go from else ifs to this form...
if (wowel.indexOf('\'') >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.A_VOWEL, context_added);
}

76
source/org/thdl/tib/text/ttt/EWTSTraits.java
View file

@ -23,6 +23,8 @@ package org.thdl.tib.text.ttt;
import java.util.ArrayList;
import org.thdl.tib.text.DuffCode;
import org.thdl.tib.text.THDLWylieConstants;
import org.thdl.tib.text.TibTextUtils;
import org.thdl.tib.text.TibetanMachineWeb;
import org.thdl.util.ThdlDebug;
@ -154,7 +156,70 @@ public final class EWTSTraits implements TTraits {
public TTshegBarScanner scanner() { return EWTSTshegBarScanner.instance(); }
public void getDuffForWowel(ArrayList duff, DuffCode preceding, String wowel) {
throw new Error("TODO(DLC)[EWTS->Tibetan]");
// TODO(DLC)[EWTS->Tibetan]: I have no confidence in this! test, test, test.
// Order matters here.
boolean context_added[] = new boolean[] { false };
if (wowel.equals(THDLWylieConstants.WYLIE_aVOWEL)) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.WYLIE_aVOWEL, context_added);
} else {
// TODO(DLC)[EWTS->Tibetan]: test vowel stacking
if (wowel.indexOf(THDLWylieConstants.U_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.U_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.reverse_I_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.reverse_I_VOWEL, context_added);
} else if (wowel.indexOf(THDLWylieConstants.I_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.I_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.A_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.A_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.ai_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.ai_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.au_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.au_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.reverse_i_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.reverse_i_VOWEL, context_added);
} else if (wowel.indexOf(THDLWylieConstants.i_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.i_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.e_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.e_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.o_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.o_VOWEL, context_added);
}
if (wowel.indexOf(THDLWylieConstants.u_VOWEL) >= 0) {
TibTextUtils.getVowel(duff, preceding, THDLWylieConstants.u_VOWEL, context_added);
}
if (wowel.indexOf("~X") >= 0) { // TODO(DLC)[EWTS->Tibetan]: introduce THDLWylieConstants.blah
duff.add(TibetanMachineWeb.getGlyph("~X"));
} else if (wowel.indexOf("X") >= 0) { // TODO(DLC)[EWTS->Tibetan]: introduce THDLWylieConstants.blah
duff.add(TibetanMachineWeb.getGlyph("X"));
}
}
// FIXME: Use TMW9.61, the "o'i" special combination, when appropriate.
if (wowel.indexOf('M') >= 0) {
DuffCode last = null;
if (duff.size() > 0) {
last = (DuffCode)duff.get(duff.size() - 1);
duff.remove(duff.size() - 1); // getBindu will add it back...
// TODO(DLC)[EWTS->Tibetan]: is this okay???? when is a bindu okay to be alone???
}
TibTextUtils.getBindu(duff, last);
}
if (wowel.indexOf('H') >= 0)
duff.add(TibetanMachineWeb.getGlyph("H"));
// TODO(DLC)[EWTS->Tibetan]: verify that no part of wowel is discarded! acip does that. 'jam~X I think we screw up, e.g.
// TODO(DLC)[EWTS->Tibetan]:: are bindus are screwed up in the unicode output? i see (with tmuni font) lone bindus without glyphs to stack on
}
public String getUnicodeForWowel(String wowel) {
@ -218,12 +283,17 @@ public final class EWTSTraits implements TTraits {
}
public String getUnicodeFor(String l, boolean subscribed) {
// First, handle "\u0f71\u0f84\u0f86", "", "\u0f74", etc.
{
boolean already_done = true;
for (int i = 0; i < l.length(); i++) {
if (!(l.charAt(0) >= '\u0f00' && l.charAt(0) <= '\u0fff')) {
char ch = l.charAt(i);
if ((ch < '\u0f00' || ch > '\u0fff')
&& '\n' != ch
&& '\r' != ch) {
// TODO(DLC)[EWTS->Tibetan]: Is this the place
// where we want to interpret how newlines work???
already_done = false;
break;
}

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

@ -61,6 +61,9 @@ class EWTSTshegBarScanner extends TTshegBarScanner {
StringBuffer sb = new StringBuffer(s);
ExpandEscapeSequences(sb);
int sl = sb.length();
// 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++) {
if (isValidInsideTshegBar(sb.charAt(i))) {
StringBuffer tbsb = new StringBuffer();
@ -75,7 +78,7 @@ class EWTSTshegBarScanner extends TTshegBarScanner {
al.add(new TString("EWTS", tbsb.toString(),
TString.TIBETAN_NON_PUNCTUATION));
} else {
if (" /;|!:=_@#$%<>()\r\n\t".indexOf(sb.charAt(i)) >= 0)
if (" /;|!:=_@#$%<>()\r\n\t*".indexOf(sb.charAt(i)) >= 0)
al.add(new TString("EWTS", sb.substring(i, i+1),
TString.TIBETAN_PUNCTUATION));
else

12
source/org/thdl/tib/text/ttt/TParseTree.java
View file

@ -327,14 +327,16 @@ class TParseTree {
translit,
traits);
} else {
if (bestParse.hasStackWithoutVowel(pl, isLastStack)) {
if (bestParse.hasStackWithoutVowel(traits.isACIP(),
pl, isLastStack)) {
if (isLastStack[0]) {
if (ErrorsAndWarnings.isEnabled(502, warningLevel))
return ErrorsAndWarnings.getMessage(502, shortMessages,
translit,
traits);
} else {
throw new Error("Can't happen now that we stack greedily");
if (traits.isACIP())
throw new Error("Can't happen now that we stack greedily");
}
}
if (ErrorsAndWarnings.isEnabled(503, warningLevel))
@ -343,14 +345,16 @@ class TParseTree {
traits);
}
} else {
if (nip.get(0).hasStackWithoutVowel(pl, isLastStack)) {
if (nip.get(0).hasStackWithoutVowel(traits.isACIP(),
pl, isLastStack)) {
if (isLastStack[0]) {
if (ErrorsAndWarnings.isEnabled(502, warningLevel))
return ErrorsAndWarnings.getMessage(502, shortMessages,
translit,
traits);
} else {
throw new Error("Can't happen now that we stack greedily [2]");
if (traits.isACIP())
throw new Error("Can't happen now that we stack greedily [2]");
}
}
}

10
source/org/thdl/tib/text/ttt/TStackList.java
View file

@ -193,14 +193,15 @@ class TStackList {
/** Returns true if and only if this stack list contains a stack
* that does not end in a vowel or disambiguator. Note that this
* is not erroneous for legal Tibetan like {BRTAN}, where {B} has
* is not erroneous for legal Tibetan like ACIP {BRTAN}, where {B} has
* no vowel, but it is a warning sign for Sanskrit stacks.
* @param isACIP true iff opl is ACIP (not EWTS)
* @param opl the pair list from which this stack list
* originated
* @param isLastStack if non-null, then isLastStack[0] will be
* set to true if and only if the very last stack is the only
* stack not to have a vowel or disambiguator on it */
boolean hasStackWithoutVowel(TPairList opl, boolean[] isLastStack) {
boolean hasStackWithoutVowel(boolean isACIP, TPairList opl, boolean[] isLastStack) {
int runningSize = 0;
// FIXME: MARDA is MARD==MAR-D to us, but is probably MAR+DA, warn -- see 838470
for (int i = 0; i < size(); i++) {
@ -213,15 +214,16 @@ class TStackList {
&& l.charAt(0) >= '0' && l.charAt(0) <= '9')) {
if (null != isLastStack) {
isLastStack[0] = (i + 1 == size());
if (!isLastStack[0]) {
if (!isLastStack[0] && isACIP) {
throw new Error("But we now stack greedily!");
}
}
return true;
}
}
if (runningSize != opl.sizeMinusDisambiguators())
if (runningSize != opl.sizeMinusDisambiguators()) {
throw new IllegalArgumentException("runningSize = " + runningSize + "; opl.sizeMinusDisambiguators = " + opl.sizeMinusDisambiguators() + "; opl (" + opl + ") is bad for this stack list (" + toString() + ")");
}
return false;
}

2
source/org/thdl/tib/text/ttt/TTraits.java
View file

@ -34,7 +34,7 @@ import org.thdl.tib.text.DuffCode;
*
* <p>It is very likely that classes that implement this interface
* will choose to use the design pattern 'singleton'. */
interface TTraits {
public interface TTraits {
/** Returns the disambiguator for this transliteration scheme,
* which had better be a string containing just one character
* lest {@link #disambiguatorChar()} become nonsensical for