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

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.

source/org/thdl/tib/input/ConvertDialog.java

@@ -223,10 +223,13 @@ class ConvertDialog extends JDialog
             JButton src = (JButton)ae.getSource();
             if (src == browseOld) {
                 jfc.setFileFilter((ACIP_TO_UNI_TEXT.equals((String)choices.getSelectedItem())
-                                   || ACIP_TO_TMW.equals((String)choices.getSelectedItem()))
+                                   || WYLIE_TO_UNI_TEXT.equals((String)choices.getSelectedItem())
+                                   || ACIP_TO_TMW.equals((String)choices.getSelectedItem())
+                                   || WYLIE_TO_TMW.equals((String)choices.getSelectedItem()))
                                   ? acipff : rtfff);
             } else {
                 jfc.setFileFilter((ACIP_TO_UNI_TEXT.equals((String)choices.getSelectedItem())
+                                   || WYLIE_TO_UNI_TEXT.equals((String)choices.getSelectedItem())
                                    || TMW_TO_ACIP_TEXT.equals((String)choices.getSelectedItem())
                                    || TMW_TO_WYLIE_TEXT.equals((String)choices.getSelectedItem()))
                                   ? acipff : rtfff);
@@ -457,7 +460,7 @@ class ConvertDialog extends JDialog
         } else if (FIND_ALL_NON_TM == ct) {
             newFileNamePrefix = "AllNonTM__";
             newFileNameExtension = ".TXT";
-        } else if (TMW_TO_SAME_TWM == ct) {
+        } else if (TMW_TO_SAME_TMW == ct) {
             newFileNamePrefix = "TMW_to_same_TMW__";
             newFileNameExtension = ".RTF";
         } else { // conversion mode
@@ -471,13 +474,15 @@ class ConvertDialog extends JDialog
             } else if (TMW_TO_ACIP_TEXT == ct) {
                 newFileNamePrefix = suggested_ACIP_prefix;
                 newFileNameExtension = ".TXT";
-            } else if (TMW_TO_UNI == ct || ACIP_TO_UNI_TEXT == ct) {
+            } else if (TMW_TO_UNI == ct || ACIP_TO_UNI_TEXT == ct
+                       || WYLIE_TO_UNI_TEXT == ct) {
                 newFileNamePrefix = suggested_TO_UNI_prefix;
-                if (ACIP_TO_UNI_TEXT == ct)
+                if (ACIP_TO_UNI_TEXT == ct || WYLIE_TO_UNI_TEXT == ct)
                     newFileNameExtension = ".TXT";
-            } else if (TM_TO_TMW == ct || ACIP_TO_TMW == ct) {
+            } else if (TM_TO_TMW == ct || ACIP_TO_TMW == ct
+                       || WYLIE_TO_TMW == ct) {
                 newFileNamePrefix = suggested_TO_TMW_prefix;
-                if (ACIP_TO_TMW == ct)
+                if (ACIP_TO_TMW == ct || WYLIE_TO_TMW == ct)
                     newFileNameExtension = ".RTF";
             } else {
                 ThdlDebug.verify(TMW_TO_TM == ct);
@@ -509,6 +514,7 @@ class ConvertDialog extends JDialog
         }
     }
 
+    // TODO(DLC)[EWTS->Tibetan]: we use for wylie (ewts) too...
     public class ACIPFileFilter extends javax.swing.filechooser.FileFilter
     {
         public boolean accept(File f)

source/org/thdl/tib/input/FontConverterConstants.java

@@ -26,7 +26,9 @@ import java.awt.*;
     @author Nathaniel Garson, Tibetan and Himalayan Digital Library */
 interface FontConverterConstants
 {
-    final String TMW_TO_SAME_TWM = "TMW to the same TMW (for testing only) (RTF->RTF)";
+    final String WYLIE_TO_UNI_TEXT = "Wylie to Unicode (Text->Text)";
+    final String WYLIE_TO_TMW = "Wylie to TMW (Text->RTF)";
+    final String TMW_TO_SAME_TMW = "TMW to the same TMW (for testing only) (RTF->RTF)";
     final String ACIP_TO_UNI_TEXT = "ACIP to Unicode (Text->Text)";
     final String ACIP_TO_TMW = "ACIP to TMW (Text->RTF)";
     final String TMW_TO_ACIP = "TMW to ACIP (RTF->RTF)";
@@ -42,6 +44,10 @@ interface FontConverterConstants
     final String FIND_ALL_NON_TM = "Find all non-TM (in RTF)";
 
     final String[] CHOICES = new String[] {
+        /* TODO(DLC)[EWTS->Tibetan]: once we're done debugging:
+        WYLIE_TO_UNI_TEXT,
+        WYLIE_TO_TMW,
+        */
         ACIP_TO_UNI_TEXT,
         ACIP_TO_TMW,
         TMW_TO_ACIP,
@@ -58,7 +64,9 @@ interface FontConverterConstants
     };
 
     final String[] DEBUG_CHOICES = new String[] {
-        TMW_TO_SAME_TWM,
+        TMW_TO_SAME_TMW,
+        WYLIE_TO_UNI_TEXT,
+        WYLIE_TO_TMW,
         ACIP_TO_UNI_TEXT,
         ACIP_TO_TMW,
         TMW_TO_ACIP,

source/org/thdl/tib/input/TibetanConverter.java

@@ -28,6 +28,8 @@ import org.thdl.tib.text.*;
 
 import org.thdl.tib.text.ttt.TConverter;
 import org.thdl.tib.text.ttt.ACIPTraits;
+import org.thdl.tib.text.ttt.EWTSTraits;
+import org.thdl.tib.text.ttt.TTraits;
 import java.util.ArrayList;
 
 /** TibetanConverter is a command-line utility for converting to and
@@ -71,6 +73,8 @@ public class TibetanConverter implements FontConverterConstants {
             boolean convertToTMMode = false;
             boolean convertACIPToUniMode = false;
             boolean convertACIPToTMWMode = false;
+            boolean convertWylieToUniMode = false;
+            boolean convertWylieToTMWMode = false;
             boolean convertToTMWMode = false;
             boolean convertToWylieRTFMode = false;
             boolean convertToWylieTextMode = false;
@@ -116,6 +120,10 @@ public class TibetanConverter implements FontConverterConstants {
                                  = args[numArgs - 2].equals("--acip-to-unicode"))
                              || (convertACIPToTMWMode
                                  = args[numArgs - 2].equals("--acip-to-tmw"))
+                             || (convertWylieToUniMode
+                                 = args[numArgs - 2].equals("--wylie-to-unicode"))
+                             || (convertWylieToTMWMode
+                                 = args[numArgs - 2].equals("--wylie-to-tmw"))
                              || (convertToUnicodeMode
                                  = args[numArgs - 2].equals("--to-unicode"))
                              || (convertToWylieRTFMode
@@ -147,6 +155,7 @@ public class TibetanConverter implements FontConverterConstants {
                 out.println("                   | --to-tibetan-machine | --to-tibetan-machine-web");
                 out.println("                   | --to-unicode | --to-wylie | --to-acip");
                 out.println("                   | --to-wylie-text | --to-acip-text");
+                out.println("                   | --wylie-to-unicode | --wylie-to-tmw");
                 out.println("                   | --acip-to-unicode | --acip-to-tmw RTF_file|TXT_file");
                 out.println(" | TibetanConverter [--version | -v | --help | -h]");
                 out.println("");
@@ -251,13 +260,17 @@ public class TibetanConverter implements FontConverterConstants {
                 } else if (convertToUnicodeMode) {
                     conversionTag = TMW_TO_UNI;
                 } else if (convertTmwToTmwMode) {
-                    conversionTag = TMW_TO_SAME_TWM;
+                    conversionTag = TMW_TO_SAME_TMW;
                 } else if (convertToTMWMode) {
                     conversionTag = TM_TO_TMW;
                 } else if (convertACIPToUniMode) {
                     conversionTag = ACIP_TO_UNI_TEXT;
                 } else if (convertACIPToTMWMode) {
                     conversionTag = ACIP_TO_TMW;
+                } else if (convertWylieToUniMode) {
+                    conversionTag = WYLIE_TO_UNI_TEXT;
+                } else if (convertWylieToTMWMode) {
+                    conversionTag = WYLIE_TO_TMW;
                 } else {
                     ThdlDebug.verify(convertToTMMode);
                     conversionTag = TMW_TO_TM;
@@ -294,20 +307,28 @@ public class TibetanConverter implements FontConverterConstants {
     static int reallyConvert(InputStream in, PrintStream out, String ct,
                              String warningLevel, boolean shortMessages,
                              boolean colors) {
-        if (ACIP_TO_UNI_TEXT == ct || ACIP_TO_TMW == ct) {
+        if (ACIP_TO_UNI_TEXT == ct || ACIP_TO_TMW == ct
+            || WYLIE_TO_UNI_TEXT == ct || WYLIE_TO_TMW == ct) {
             try {
                 ArrayList al
-                    = ACIPTraits.instance().scanner().scanStream(in, null,
+                    = ((ACIP_TO_UNI_TEXT == ct || ACIP_TO_TMW == ct)
-                                                                 ThdlOptions.getIntegerOption("thdl.most.errors.a.tibetan.acip.document.can.have",
+                       ? (TTraits)ACIPTraits.instance()
-                                                                                              1000 - 1),
+                       : (TTraits)EWTSTraits.instance()).scanner().scanStream(in, null,
-                                                                 shortMessages,
+                                                                              ThdlOptions.getIntegerOption((ACIP_TO_UNI_TEXT == ct || ACIP_TO_TMW == ct)
-                                                                 warningLevel);
+                                                                                                           ? "thdl.most.errors.a.tibetan.acip.document.can.have"
+                                                                                                           : "thdl.most.errors.a.tibetan.ewts.document.can.have",
+                                                                                                           1000 - 1),
+                                                                              shortMessages,
+                                                                              warningLevel);
                 if (null == al)
                     return 47;
                 boolean embeddedWarnings = (warningLevel != "None");
                 boolean hasWarnings[] = new boolean[] { false };
-                if (ACIP_TO_UNI_TEXT == ct) {
+                if (ACIP_TO_UNI_TEXT == ct
-                    if (!TConverter.convertToUnicodeText(ACIPTraits.instance(),
+                    || WYLIE_TO_UNI_TEXT == ct) {
+                    if (!TConverter.convertToUnicodeText((WYLIE_TO_UNI_TEXT == ct)
+                                                         ? (TTraits)EWTSTraits.instance()
+                                                         : (TTraits)ACIPTraits.instance(),
                                                          al, out, null,
                                                          null, hasWarnings,
                                                          embeddedWarnings,
@@ -315,8 +336,9 @@ public class TibetanConverter implements FontConverterConstants {
                                                          shortMessages))
                         return 46;
                 } else {
-                    if (ct != ACIP_TO_TMW) throw new Error("badness");
+                    if (!TConverter.convertToTMW((WYLIE_TO_TMW == ct)
-                    if (!TConverter.convertToTMW(ACIPTraits.instance(),
+                                                 ? (TTraits)EWTSTraits.instance()
+                                                 : (TTraits)ACIPTraits.instance(),
                                                  al, out, null, null,
                                                  hasWarnings,
                                                  embeddedWarnings,
@@ -402,7 +424,7 @@ public class TibetanConverter implements FontConverterConstants {
 
                 int exitCode = 0;
                 ThdlDebug.verify(((TMW_TO_TM == ct) ? 1 : 0)
-                                 + ((TMW_TO_SAME_TWM == ct) ? 1 : 0)
+                                 + ((TMW_TO_SAME_TMW == ct) ? 1 : 0)
                                  + ((TMW_TO_UNI == ct) ? 1 : 0)
                                  + ((TM_TO_TMW == ct) ? 1 : 0)
                                  + ((TMW_TO_ACIP == ct) ? 1 : 0)
@@ -411,7 +433,7 @@ public class TibetanConverter implements FontConverterConstants {
                                  + ((TMW_TO_WYLIE_TEXT == ct) ? 1 : 0)
                                  == 1);
                 long numAttemptedReplacements[] = new long[] { 0 };
-                if (TMW_TO_SAME_TWM == ct) {
+                if (TMW_TO_SAME_TMW == ct) {
                     // Identity conversion for testing
                     if (tdoc.identityTmwToTmwConversion(0,
                                                         tdoc.getLength(),

source/org/thdl/tib/text/ttt/ACIPTraits.java

@@ -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);
             }

source/org/thdl/tib/text/ttt/EWTSTraits.java

@@ -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;
                 }

source/org/thdl/tib/text/ttt/EWTSTshegBarScanner.java

@@ -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

source/org/thdl/tib/text/ttt/TParseTree.java

@@ -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]");
                     }
                 }
             }

source/org/thdl/tib/text/ttt/TStackList.java

@@ -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;
     }
 

source/org/thdl/tib/text/ttt/TTraits.java

@@ -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