Added GUI support for color-coding. Added support for color-coding

and choosing the warning level to TibetanConverter.

Better error checking in the GUI converter.

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

@@ -37,6 +37,9 @@ class ConvertDialog extends JDialog
 {
     private static final boolean debug = false;
 
+    private JCheckBox colors;
+    private static final String colorDesc = "Color-coding (ACIP to RTF only)";
+
     // Attributes
     private FontConversion controller;
 
@@ -95,6 +98,11 @@ class ConvertDialog extends JDialog
         updateWarningLevels();
 
         temp.add(warningLevels);
+        this.colors = new JCheckBox(colorDesc, false);
+        this.colors.addActionListener(tal);
+        updateWarningLevels();
+
+        temp.add(colors);
         content.add(temp);
 
         temp = new JPanel(new FlowLayout(FlowLayout.CENTER,5,5));
@@ -151,7 +159,7 @@ class ConvertDialog extends JDialog
         content.add(buttonBox);
         setContentPane(content);
         pack();
-        setSize(new Dimension(620,200));
+        setSize(new Dimension(640,235));
     }
 
     private void setChoices(String[] choices)
@@ -226,6 +234,13 @@ class ConvertDialog extends JDialog
                                               JOptionPane.ERROR_MESSAGE);
                 return;
             }
+            if ("".equals(newTextField.getText())) {
+                JOptionPane.showMessageDialog(this,
+                                              "Choose a target file.",
+                                              "No target chosen",
+                                              JOptionPane.ERROR_MESSAGE);
+                return;
+            }
             File convertedFile = new File(newTextField.getText());
             if(null == convertedFile) {
                 JOptionPane.showMessageDialog(this,
@@ -274,7 +289,8 @@ class ConvertDialog extends JDialog
                                         origFile,
                                         convertedFile,
                                         (String)choices.getSelectedItem(),
-                                        (String)warningLevels.getSelectedItem());
+                                        (String)warningLevels.getSelectedItem(),
+                                        colors.isSelected());
             } catch (OutOfMemoryError e) {
                 JOptionPane.showMessageDialog(this,
                                               "The converter ran out of memory.  Please give the\nJVM more memory by using java -XmxYYYm where YYY\nis the amount of memory your system has, or\nsomething close to it.  E.g., try\n'java -Xmx512m -jar Jskad.jar'.",

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

@@ -48,15 +48,23 @@ public class ConverterGUI implements FontConversion, FontConverterConstants {
     }
 
     public boolean doConversion(ConvertDialog cd, File oldFile, File newFile,
-                                String whichConversion, String warningLevel) {
+                                String whichConversion, String warningLevel,
+                                boolean colors) {
         PrintStream ps;
         try {
+            if (whichConversion == ACIP_TO_UNI_TEXT) {
+                JOptionPane.showMessageDialog(cd,
+                                              "This conversion will lose information about relative font sizes.\n{KA (KHA) GA} will be treated like {KA KHA GA}, that is.",
+                                              "Loss of information may result",
+                                              JOptionPane.WARNING_MESSAGE);
+            }
             returnCode
                 = TibetanConverter.reallyConvert(new FileInputStream(oldFile),
                                                  ps = new PrintStream(new FileOutputStream(newFile),
                                                                       false),
                                                  whichConversion,
-                                                 warningLevel);
+                                                 warningLevel,
+                                                 colors);
             ps.close();
         } catch (FileNotFoundException e) {
             returnCode = 39;

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

@@ -35,8 +35,10 @@ interface FontConversion
         displaying the results if you want happy users.  The
         conversion performed is specified by the interned String
         whichConversion, which must be one of the known conversions.
+        If you want colors to be used in the output (which is only
+        supported by a few conversions), then colors must be true.
         @return true on success, false otherwise */
     boolean doConversion(ConvertDialog cd, File oldFile,
                          File newFile, String whichConversion,
-                         String warningLevel);
+                         String warningLevel, boolean colors);
 }

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

@@ -99,6 +99,10 @@ public class TMW_RTF_TO_THDL_WYLIETest extends TestCase {
 
     private void helper(String mode, String extension, int erc) {
         String[] args = new String[] {
+            "--colors",
+            "no",
+            "--warning-level",
+            "All",
             mode,
             getTestFileName("Test1")
         };

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

@@ -79,39 +79,50 @@ public class TibetanConverter implements FontConverterConstants {
             boolean findSomeNonTMMode = false;
             boolean findAllNonTMMode = false;
 
+            boolean colors = false;
+            
             // Process arguments:
-            if ((args.length != 1 && args.length != 2)
+            final int numArgs = 6;
+            if ((args.length != 1 && args.length != numArgs)
                 || (args.length == 1
                     && !(args[0].equals("-v")
                          || args[0].equals("--version")))
-                || (args.length == 2
+                || (args.length == numArgs
-                    && !((findAllNonTMWMode
+                    && (!(args[numArgs - 6].equals("--colors"))
-                          = args[0].equals("--find-all-non-tmw"))
+                        || !((colors = args[numArgs - 5].equals("yes"))
+                             || args[numArgs - 5].equals("no"))
+                        || !(args[numArgs - 4].equals("--warning-level"))
+                        || !(args[numArgs - 3].equals("Most")
+                             || args[numArgs - 3].equals("Some")
+                             || args[numArgs - 3].equals("All")
+                             || args[numArgs - 3].equals("None"))
+                        || !((findAllNonTMWMode
+                              = args[numArgs - 2].equals("--find-all-non-tmw"))
                              || (convertToTMMode
-                             = args[0].equals("--to-tibetan-machine"))
+                                 = args[numArgs - 2].equals("--to-tibetan-machine"))
                              || (convertToTMWMode
-                             = args[0].equals("--to-tibetan-machine-web"))
+                                 = args[numArgs - 2].equals("--to-tibetan-machine-web"))
                              || (convertACIPToUniMode
-                             = args[0].equals("--acip-to-unicode"))
+                                 = args[numArgs - 2].equals("--acip-to-unicode"))
                              || (convertACIPToTMWMode
-                             = args[0].equals("--acip-to-tmw"))
+                                 = args[numArgs - 2].equals("--acip-to-tmw"))
                              || (convertToUnicodeMode
-                             = args[0].equals("--to-unicode"))
+                                 = args[numArgs - 2].equals("--to-unicode"))
                              || (convertToWylieRTFMode
-                             = args[0].equals("--to-wylie"))
+                                 = args[numArgs - 2].equals("--to-wylie"))
                              || (convertToWylieTextMode
-                             = args[0].equals("--to-wylie-text"))
+                                 = args[numArgs - 2].equals("--to-wylie-text"))
                              || (convertToACIPRTFMode
-                             = args[0].equals("--to-acip"))
+                                 = args[numArgs - 2].equals("--to-acip"))
                              || (convertToACIPTextMode
-                             = args[0].equals("--to-acip-text"))
+                                 = args[numArgs - 2].equals("--to-acip-text"))
                              || (findSomeNonTMWMode
-                             = args[0].equals("--find-some-non-tmw"))
+                                 = args[numArgs - 2].equals("--find-some-non-tmw"))
                              || (findSomeNonTMMode
-                             = args[0].equals("--find-some-non-tm"))
+                                 = args[numArgs - 2].equals("--find-some-non-tm"))
                              || (findAllNonTMMode
-                             = args[0].equals("--find-all-non-tm"))
+                                 = args[numArgs - 2].equals("--find-all-non-tm"))
-                ))) {
+                             )))) {
                 out.println("TibetanConverter --find-all-non-tmw | --find-some-non-tmw");
                 out.println("                 | --to-tibetan-machine | --to-tibetan-machine-web");
                 out.println("                 | --to-unicode | --to-wylie | --to-acip");
@@ -224,8 +235,7 @@ public class TibetanConverter implements FontConverterConstants {
                 }
             }
             return reallyConvert(in, out, conversionTag,
-                                 "Most" // DLC make me configurable
+                                 args[numArgs - 3].intern(), colors);
-                                 );
         } catch (ThdlLazyException e) {
             out.println("TibetanConverter has a BUG:");
             e.getRealException().printStackTrace(out);
@@ -243,11 +253,12 @@ public class TibetanConverter implements FontConverterConstants {
         return code so that TibetanConverter's usage message is
         honored. */
     static int reallyConvert(InputStream in, PrintStream out, String ct,
-                             String warningLevel) {
+                             String warningLevel, boolean colors) {
         if (ACIP_TO_UNI_TEXT == ct || ACIP_TO_TMW == ct) {
             try {
                 ArrayList al = ACIPTshegBarScanner.scanStream(in, null,
-                                                              250 - 1 // DLC FIXME: make me configurable
+                                                              ThdlOptions.getIntegerOption("thdl.most.errors.a.tibetan.acip.document.can.have",
+                                                                                           250 - 1)
                                                               );
                 if (null == al)
                     return 47;
@@ -259,9 +270,10 @@ public class TibetanConverter implements FontConverterConstants {
                                                         warningLevel))
                         return 46;
                 } else {
+                    if (ct != ACIP_TO_TMW) throw new Error("badness");
                     if (!ACIPConverter.convertToTMW(al, out, null, warnings,
                                                     embeddedWarnings,
-                                                    warningLevel))
+                                                    warningLevel, colors))
                         return 46;
                 }
                 if (embeddedWarnings && warnings.length() > 0)
@@ -295,7 +307,6 @@ public class TibetanConverter implements FontConverterConstants {
                             + rtfErrorMessage);
                 return 3;
             }
-
             try {
                 in.close();
             } catch (IOException e) {

source/org/thdl/tib/text/TibetanDocument.java

@@ -145,9 +145,14 @@ public class TibetanDocument extends DefaultStyledDocument {
         }
     }
 
-    private static boolean allowColors = true; // DLC FIXME: make me configurable
+    private static boolean allowColors = false;
+    /** Enables the use of colors. */
     public static void enableColors() { allowColors = true; }
+    /** Disables the use of colors. */
     public static void disableColors() { allowColors = false; }
+    /** Returns true if and only if the use of colors is currently
+     *  enabled. */
+    public static boolean colorsEnabled() { return allowColors; }
 
 
 /**
@@ -167,6 +172,8 @@ public class TibetanDocument extends DefaultStyledDocument {
 * automatically, according to the current Roman font size.
 * @param offset the position at which you want to insert text
 * @param s the string you want to insert
+* @param color the color in which to insert, which is used if and only
+* if {@link #colorsEnabled() colors are enabled}
 * @see #setRomanAttributeSet(AttributeSet)
 */
 	public void appendRoman(int offset, String s, Color color) throws BadLocationException {
@@ -180,6 +187,8 @@ public class TibetanDocument extends DefaultStyledDocument {
 * Inserts Latin text at the end of the document. The font size is
 * applied automatically, according to the current Roman font size.
 * @param s the string you want to insert
+* @param color the color in which to insert, which is used if and only
+* if {@link #colorsEnabled() colors are enabled}
 * @see #setRomanAttributeSet(AttributeSet)
 */
 	public void appendRoman(String s, Color color) {
@@ -203,8 +212,10 @@ public class TibetanDocument extends DefaultStyledDocument {
 
 /**
 * Inserts a stretch of TibetanMachineWeb data into the document.
-* @param glyphs the array of Tibetan data you want to insert
 * @param pos the position at which you want to insert text
+* @param glyphs the array of Tibetan data you want to insert
+* @param color the color in which to insert, which is used if and only
+* if {@link #colorsEnabled() colors are enabled}
 */
 	public int insertDuff(int pos, DuffData[] glyphs, Color color) {
         return insertDuff(tibetanFontSize, pos, glyphs, true, color);
@@ -216,6 +227,9 @@ public class TibetanDocument extends DefaultStyledDocument {
 
 /**
 * Appends all DuffCodes in glyphs to the end of this document.
+* @param glyphs the array of Tibetan data you want to insert
+* @param color the color in which to insert, which is used if and only
+* if {@link #colorsEnabled() colors are enabled}
 */
 	public void appendDuffCodes(DuffCode[] glyphs, Color color) {
         // PERFORMANCE FIXME: this isn't so speedy, but it reuses

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

@@ -38,6 +38,14 @@ import org.thdl.tib.text.DuffCode;
 public class ACIPConverter {
     // DLC NOW: (KA)'s info is lost when you convert to Unicode text instead of Unicode RTF.  Give an ERROR.
 
+    // DLC NOW: IMPLEMENT (KA) font shrinking
+
+    // DLC NOW: BAo isn't converting.
+
+    // DLC NOW: tRAStA is not converter correctly to Unicode, and no
+    // warning is given when converting to TMW (Wait!  isn't the "a
+    // stack occurs w/o a vowel" warning given?)
+
     /** Command-line converter.  Gives error messages on standard
      *  output about why we can't convert the document perfectly and
      *  exits with non-zero return code, or is silent otherwise and
@@ -51,8 +59,6 @@ public class ACIPConverter {
         ThdlOptions.setUserPreference("thdl.rely.on.system.tm.fonts", true);
         ThdlOptions.setUserPreference("thdl.debug", true);
 
-        TibetanDocument.enableColors();
-
         boolean verbose = true;
         if (args.length != 1) {
             System.out.println("Bad args!  Need just the name of the ACIP text file.");
@@ -74,7 +80,6 @@ public class ACIPConverter {
             System.exit(1);
         }
         final boolean abortUponScanningError = false;
-        // DLC NOW: BAo isn't converting.
         if (errors.length() > 0) {
             System.err.println("Errors scanning ACIP input file: ");
             System.err.println(errors);
@@ -84,7 +89,8 @@ public class ACIPConverter {
             }
         }
 
-        String warningLevel = "Most"; // DLC make me configurable.
+        String warningLevel = "Most";
+        boolean colors = true;
         StringBuffer warnings = null;
         boolean putWarningsInOutput = false;
         if ("None" != warningLevel) {
@@ -92,7 +98,7 @@ public class ACIPConverter {
             putWarningsInOutput = true;
         }
         convertToTMW(al, System.out, errors, warnings,
-                     putWarningsInOutput, warningLevel);
+                     putWarningsInOutput, warningLevel, colors);
         int retCode = 0;
         if (errors.length() > 0) {
             System.err.println("Errors converting ACIP input file: ");
@@ -112,8 +118,6 @@ public class ACIPConverter {
             if (verbose) System.err.println("Converted " + args[0] + " perfectly.");
         }
         System.exit(retCode);
-        // DLC NOW: tRAStA is not converter correctly to Unicode, and
-        // no warning is given when converting to TMW.
     }
 
     /** Writes TMW/Latin to out.  If errors occur in converting a
@@ -124,6 +128,9 @@ public class ACIPConverter {
      *  warnings if warnings is non-null.  Returns true upon perfect
      *  success or if there were merely warnings, false if errors
      *  occurred.
+     *  @param colors true if and only if you want Sanskrit in one
+     *  color, errors/warnings in another, and tsheg-bars affected by
+     *  prefix rules in another
      *  @throws IOException if we cannot write to out
      */
     public static boolean convertToTMW(ArrayList scan,
@@ -131,7 +138,8 @@ public class ACIPConverter {
                                        StringBuffer errors,
                                        StringBuffer warnings,
                                        boolean writeWarningsToResult,
-                                       String warningLevel)
+                                       String warningLevel,
+                                       boolean colors)
         throws IOException
     {
         TibetanDocument tdoc = new TibetanDocument();
@@ -141,7 +149,7 @@ public class ACIPConverter {
                                                                20));
         boolean rv
             = convertToTMW(scan, tdoc, errors, warnings,
-                           writeWarningsToResult, warningLevel);
+                           writeWarningsToResult, warningLevel, colors);
         tdoc.writeRTFOutputStream(out);
         return rv;
     }
@@ -151,17 +159,14 @@ public class ACIPConverter {
                                         StringBuffer errors,
                                         StringBuffer warnings,
                                         boolean writeWarningsToResult,
-                                        String warningLevel)
+                                        String warningLevel,
+                                        boolean colors)
         throws IOException
     {
         return convertTo(false, scan, null, tdoc, errors, warnings,
-                         writeWarningsToResult, warningLevel);
+                         writeWarningsToResult, warningLevel, colors);
     }
 
-    // DLC FIXME: sometimes { } is \u0F0B, and sometimes it is a
-    // space.  Treat it as a tsheg only when it appears after a
-    // syllable or another tsheg.
-
     /** Returns UTF-8 encoded Unicode.  A bit indirect, so use this
      *  for testing only if performance is a concern.  If errors occur
      *  in scanning the ACIP or in converting a tsheg bar, then they
@@ -194,16 +199,20 @@ public class ACIPConverter {
         }
     }
 
-    /** Writes Unicode to out.  If errors occur in converting a tsheg
+    /** Writes Unicode text (not RTF) to out.  <em>NOTE WELL: This
-     *  bar, then they are appended to errors if errors is non-null.
+     *  inherently cannot describe the ACIP {(KA) KHA} properly, as
-     *  Furthermore, errors are written to out.  If writeWarningsToOut
+     *  that requires showing KA in a smaller font than KHA, which is
-     *  is true, then warnings also will be written to out.
+     *  not possible in plain text.</em> If errors occur in converting
+     *  a tsheg bar, then they are appended to errors if errors is
+     *  non-null.  Furthermore, errors are written to out.  If
+     *  writeWarningsToOut is true, then warnings also will be written
+     *  to out.
      *  @return true upon perfect success, false if errors occurred.
      *  @param scan result of ACIPTshegBarScanner.scan(..)
      *  @param out stream to which to write converted text
      *  @param errors if non-null, all error messages are appended
-     *  @param warnings if non-null, all warning messages are appended
+     *  @param warnings if non-null, all warning messages appropriate
-     *  to this
+     *  to warningLevel are appended
      *  @param writeWarningsToOut if true, then all warning messages
      *  are written to out in the appropriate places
      *  @throws IOException if we cannot write to out
@@ -217,7 +226,7 @@ public class ACIPConverter {
         throws IOException
     {
         return convertTo(true, scan, out, null, errors, warnings,
-                         writeWarningsToOut, warningLevel);
+                         writeWarningsToOut, warningLevel, false);
     }
 
     private static boolean peekaheadFindsSpacesAndComma(ArrayList /* of ACIPString */ scan,
@@ -245,9 +254,14 @@ public class ACIPConverter {
                                      StringBuffer errors,
                                      StringBuffer warnings,
                                      boolean writeWarningsToOut,
-                                     String warningLevel)
+                                     String warningLevel,
+                                     boolean colors)
         throws IOException
     {
+        if (colors)
+            tdoc.enableColors();
+        else
+            tdoc.disableColors();
         int sz = scan.size();
         boolean hasErrors = false;
         BufferedWriter writer = null;
@@ -276,7 +290,6 @@ public class ACIPConverter {
                     if (null != writer) writer.write(text);
                     if (null != tdoc) tdoc.appendRoman(text, Color.RED);
                 }
-                // DLC NOW: Warning: We're going with {'}{R}{DA}, but only because our knowledge of prefix rules says that {'}{R+DA} is not a legal Tibetan tsheg bar ("syllable")
 
                 if (null != warnings) {
                     warnings.append("Warning: Lexical warning: ");
@@ -357,6 +370,8 @@ public class ACIPConverter {
                                             color = Color.BLACK;
                                         } else {
                                             // Sanskrit
+
+                                            // DLC FIXME: a funny vowel, the presence of a sanskrit-only stack, and a funny mark like ACIP ':' should cause green too.
                                             color = Color.GREEN;
                                         }
 
@@ -453,7 +468,6 @@ public class ACIPConverter {
                     if (null != tdoc) {
                         if (null != duff && 0 != duff.length) {
                             tdoc.appendDuffCodes(duff, color);
-                            // DLC NOW FIXME: use TibTextUtils.getVowel logic to make the output beautiful.
                         } else {
                             // this happens when you have an
                             // [#ERROR]-producing tsheg bar.
@@ -471,6 +485,3 @@ public class ACIPConverter {
         return !hasErrors;
     }
 }
-// DLC FIXME: putting Tibetan in black, Sanskrit in green, and Latin
-// in yellow would help you quickly decide if ZHIGN maybe should've
-// been ZHING.

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

@@ -276,6 +276,7 @@ class TParseTree {
 
         TStackListList up = getUniqueParse(false);
         if (null == up || up.size() != 1) {
+            // DLC FIXME: code duplication
             boolean isLastStack[] = new boolean[1];
             TStackListList nip = getNonIllegalParses();
             if (nip.size() != 1) {
@@ -285,9 +286,9 @@ class TParseTree {
                     if (getBestParse().hasStackWithoutVowel(pl, isLastStack)) {
                         if (isLastStack[0]) {
                             if (warningLevel == "All" || warningLevel == "Most")
-                                return "Warning: The last stack does not have a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}";
+                                return "Warning: The last stack does not have a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}; this may indicate a typo, because Sanskrit, which this is (because it's not legal Tibetan), should have a vowel after each stack.";
                         } else {
-                            return "Warning: There is a stack, before the last stack, without a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}";
+                            return "Warning: There is a stack, before the last stack, without a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}; this may indicate a typo, because Sanskrit, which this is (because it's not legal Tibetan), should have a vowel after each stack.";
                         }
                     }
                     if ("All" == warningLevel) {
@@ -298,9 +299,9 @@ class TParseTree {
                 if (nip.get(0).hasStackWithoutVowel(pl, isLastStack)) {
                     if (isLastStack[0]) {
                         if (warningLevel == "All" || warningLevel == "Most")
-                            return "Warning: The last stack does not have a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}";
+                            return "Warning: The last stack does not have a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}; this may indicate a typo, because Sanskrit, which this is (because it's not legal Tibetan), should have a vowel after each stack.";
                     } else {
-                        return "Warning: There is a stack, before the last stack, without a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}";
+                        return "Warning: There is a stack, before the last stack, without a vowel in the ACIP {" + ((null != originalACIP) ? originalACIP : recoverACIP()) + "}; this may indicate a typo, because Sanskrit, which this is (because it's not legal Tibetan), should have a vowel after each stack.";
                     }
                 }
             }