Changeset 365

Timestamp:

07/28/09 21:49:15 (3 years ago)

Author:

chris

Message:

Display word suffixes followed by = instead of -, as requested
by Nicolai.

Test that clause navigator transliteration inserts spaces as required.

Transliterate doubled consonants at start of morpheme with a hyphen
between them, as requested by Nicolai.

Update copyright year in footer to 2009.

Files:

• lex/trunk/.classpath (modified) (1 diff)
• lex/trunk/.settings/org.eclipse.core.resources.prefs (modified) (2 diffs)
• lex/trunk/etc/Description_of_Lex_for_Leipzig_2006.odt (modified) (previous)
• lex/trunk/src/com/qwirx/lex/controller/ClauseController.java (modified) (4 diffs)
• lex/trunk/src/com/qwirx/lex/controller/ControllerBase.java (modified) (5 diffs)
• lex/trunk/src/com/qwirx/lex/controller/Navigator.java (modified) (1 diff)
• lex/trunk/src/com/qwirx/lex/morph/HebrewMorphemeGenerator.java (modified) (9 diffs)
• lex/trunk/src/com/qwirx/lex/translit/DatabaseTransliterator.java (modified) (2 diffs)
• lex/trunk/test/com/qwirx/lex/ClauseControllerTest.java (modified) (5 diffs)
• lex/trunk/test/com/qwirx/lex/GenExporterTest.java (modified) (3 diffs)
• lex/trunk/test/com/qwirx/lex/NavigatorTest.java (modified) (2 diffs)
• lex/trunk/test/com/qwirx/lex/TransliteratorTest.java (modified) (16 diffs)

lex/trunk/.classpath

@@ -1 +1 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<classpath>
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-</classpath>

lex/trunk/.settings/org.eclipse.core.resources.prefs

@@ -1 @@
-Wed Jan 02 17:36:47
+Sat Jan 05 16:55:05
-eclipse.preferences.version=1
-encoding//jsp/attributes.jsp=UTF-8
@@ -19 +19 @@
-encoding//jsp/rules.jsp=UTF-8
-encoding//jsp/search.jsp=UTF-8
+encoding//jsp/wordnet.jsp=UTF-8
-encoding/<project>=UTF-8

lex/trunk/src/com/qwirx/lex/controller/ClauseController.java

@@ -536 +536 @@
-    }
-    
-
-
+
+
+
+
+
+
+
+
-    throws Exception
-        
+
-        int wivuIndex = 0;
-        EMdFValue wivuIndexE = word.getEMdFValue("wivu_lexicon_id");
@@ -798 +804 @@
-                    if (type.equals("word"))
-                    {
-                        String part_of_speech = word.getFeatureAsString(
-                            word.getEMdFValueIndex(
-                                "phrase_dependent_part_of_speech"));
-                            
-                        Cell cell = new Cell(null);
-                        cell.label = HebrewConverter.wordTranslitToHtml(word,
@@ -811 +813 @@
-                        cell.subcells.add(getLexiconGlossCell(word));
-                        cell.subcells.add(getWivuLexiconCell(word,
-part_of_speech, 
+
-                        cell.subcells.add(getDibLookupCell(word));
-                        cell.subcells.add(getKingJamesGloss(word));
@@ -1126 +1128 @@
-                    columns.add(cells);
-                    
-
+
+
-                        (phrases.hasNext() || words.hasNext()))
-                    {

lex/trunk/src/com/qwirx/lex/controller/ControllerBase.java

@@ -156 +156 @@
-                {
-                    hebrew.append(morpheme.getSurface());
-
+
+
-                    {
-                        hebrew.append(" ");
@@ -170 +171 @@
-    throws Exception
-    {
-
+
+
-        HebrewMorphemeGenerator generator = new HebrewMorphemeGenerator();
-        List<MorphEdge> morphEdges = new ArrayList<MorphEdge>();
@@ -176 +178 @@
-        while (phrases.hasNext()) 
-        {
-
-
+
+
+
+
+
-            
-            while (words.hasNext()) 
-            {
-
-
+
+
+
+
+
+
-                    m_Transliterator);
-
+
-                for (int i = 0; i < morphemes.size(); i++)
-                {
@@ -190 +199 @@
-                    String translit =
-                        HebrewConverter.toHtml(morpheme.getTranslit());
-                    if (translit.equals("")) translit = "&Oslash;";
-                    
-                    if (i < morphemes.size() - 1)
@@ -202 +210 @@
-                    Map<String, String> attributes =
-                        new HashMap<String, String>();
-                    
-                    // not safe, crashes emdros 2.0.6, emailed ulrik 090403
-                    /*
-                    StringList features = word.getFeatureList();
-                    for (StringListConstIterator iter = features.const_iterator();
-                        iter.hasNext();)
-                    {
-                        String feature = iter.next();
-                        attributes.put("word_" + feature,
-                            word.getFeatureAsString(
-                                word.getEMdFValueIndex(feature)));
-                    }
-                    */
-                    
-                    // also not safe
-                    /*
-                    String[] featuresToCopy = new String[]{"person", "number",
-                        "gender", "tense", "stem"
-                    };
-                    for (String feature : featuresToCopy)
-                    {
-                        System.out.println(feature);
-                        attributes.put("word_" + feature,
-                            word.getFeatureAsString(
-                                word.getEMdFValueIndex(feature)));
-                    }
-                    */
-
-                    attributes.put("word_person",

lex/trunk/src/com/qwirx/lex/controller/Navigator.java

@@ -245 +245 @@
-                }
-                
-
-
+
+
+
-                {
-                    lexemes.append(" ");

lex/trunk/src/com/qwirx/lex/morph/HebrewMorphemeGenerator.java

@@ -20 +20 @@
-    {
-        private String m_Surface, m_Gloss, m_Symbol, m_Translit;
-IsGraphicalWordEnd
+DisplayWithEquals
-        
-        public Morpheme(String surface, String gloss, String symbol,
-isGraphicalWordEnd
+displayWithEquals
-        {
-            m_Surface = surface;
@@ -29 +29 @@
-            m_Symbol = symbol;
-            m_IsLastMorpheme = isLastMorpheme;
-IsGraphicalWordEnd = isGraphicalWordEnd
+DisplayWithEquals = displayWithEquals
-        }
-        
@@ -35 +35 @@
-        public String getGloss() { return m_Gloss; }
-        public String getNodeSymbol() { return m_Symbol; }
-
+
+
-        void setTranslit(String translit) { m_Translit = translit; }
-        public String getTranslit() { return m_Translit; }
@@ -52 +53 @@
-            }
-            
-IsLastMorpheme && !m_IsGraphicalWordEnd
+DisplayWithEquals
-            {
-                return translit + "=";
@@ -197 +198 @@
-            else if (gender.equals("feminine"))  { gender = "F"; }
-            else if (gender.equals("common"))    { gender = "="; }
+            else if (gender.equals("unknown"))   { gender = "u"; }
-            
-            String number = features.get("number");
@@ -278 +280 @@
-                    features.get("graphical_verbal_ending_utf8") +
-                    features.get("graphical_nominal_ending_utf8"),
-fals
+tru
-            }
-            else
@@ -288 +290 @@
-    
-                convert(results, features, "graphical_verbal_ending_utf8",
-fals
+tru
-            }
-            
-            convert(results, features, "graphical_pron_suffix_utf8",
-tru
+fals
-        }
-        else if (psp.equals("noun")
@@ -307 +309 @@
-                false, false);
-            convert(results, features, "graphical_nominal_ending_utf8",
-fals
+tru
-            convert(results, features, "graphical_pron_suffix_utf8",
-tru
+fals
-        }
-        else if (psp.equals("none"))
-        {
-            // hack for LexemeTest
-tru
+fals
-        }
-        else
@@ -382 +384 @@
-            boolean hasSuffix = !(suffixText.equals(""));
-            convert(results, features, "graphical_lexeme_utf8", type, type,
-
+!
-            
-            if (hasSuffix)
-            {
-                convert(results, features, "graphical_pron_suffix_utf8",
-
+!
-            }
-        }

lex/trunk/src/com/qwirx/lex/translit/DatabaseTransliterator.java

@@ -225 +225 @@
-        
-        StringList features = word.getFeatureList();
+        /*
-        for (StringListConstIterator i = features.const_iterator();
-            i.hasNext();)
@@ -232 +233 @@
-            attributes.put("word_" + feature, value);
-        }
+        */
-        
-        return transliterate(morphemes, index, attributes);

lex/trunk/test/com/qwirx/lex/ClauseControllerTest.java

@@ -8 +8 @@
-import jemdros.Straw;
-import jemdros.StrawConstIterator;
+
+import org.aptivate.webutils.HtmlIterator;
-
-import com.qwirx.lex.controller.ClauseController;
@@ -41 +43 @@
-    }
-
-
+Cell
-    {
-        ClauseController controller = new ClauseController(getEmdros(),
@@ -48 +50 @@
-        String gloss = controller.getWivuGloss(word);
-        assertEquals("hover", gloss);
+        
+        Cell glossCell = controller.getWivuLexiconCell(word, true);
+        HtmlIterator i = new HtmlIterator(glossCell.html);
+        
-    }
-    
@@ -73 +79 @@
-        List<Cell[]> columns = controller.getWordColumns();
-        String [] firstRow = new String[]{
--", "Ø", "", "bᵊ=", "ʔiš-", "t-
+=", "Ø", "", "bᵊ=", "ʔiš-", "t=
-        };
-        String [] secondRow = new String[]{
@@ -104 +110 @@
-        assertEquals("P", columns.get(13)[1].html);
-        assertEquals("love", columns.get(14)[1].html);
+        assertEquals("āʰ=", columns.get(15)[0].html);
-        assertEquals("FsgAB", columns.get(15)[1].html);
-        assertEquals("CLT", columns.get(16)[1].html);

lex/trunk/test/com/qwirx/lex/GenExporterTest.java

@@ -87 +87 @@
-        "\n" +
-        "\\morpheme \n" +
--
-
-nknown
+=
+
+
-        "\\lemma lemma\n" +
-        "\\re\n" +
@@ -115 +115 @@
-        "\n" +
-        "\\morpheme ֎֥ים\n" +
--
+=
-        "\\tag tag\n" +
-        "\\gloss MplAB\n" +
@@ -136 +136 @@
-        "\n" +
-        "\\morpheme ֞֜ה\n" +
--
+=
-        "\\tag tag\n" +
-        "\\gloss FsgAB\n" +

lex/trunk/test/com/qwirx/lex/NavigatorTest.java

@@ -15 +15 @@
-        Navigator navigator = new Navigator(null, null, getEmdros(), 
-            userTextAccessSet, new DatabaseTransliterator(getSql()));
+        /*
-        assertEquals("<select id=\"book\" name=\"book\" " +
-                "onChange=\"document.forms.nav.submit()\">\n" +
@@ -21 +22 @@
-                "<option value=\"228327\">Numbers</option>\n" +
-                "<option value=\"521677\">II_Samuel</option>\n" +
-
-
+
+
+
+
+
-        assertEquals("<select id=\"chapter\" name=\"chapter\" " +
-                "onChange=\"document.forms.nav.submit()\">\n" +

lex/trunk/test/com/qwirx/lex/TransliteratorTest.java

@@ -450 +450 @@
-        addRule("", KHET + PATAH, "$", SUBSCRIPT_A + H_DOT);
-        addRule("", PATAH, "", "a");
+        
+        // TODO is this correct?
+        // addRule("^", BET + DAGESH, "", "b-b"); // initial consonant doubled with dash
+        
-        addRule(VOWEL + OPTIONAL_CANTILLATION, BET + DAGESH, "", "bb");
-        addRule(NOT_VOWEL_BEFORE, BET + DAGESH, "", "b");
@@ -455 +459 @@
-        addRule("", SHIN + DAGESH, "", S_CARON + S_CARON);
-        addRule("", SHIN, "", S_CARON);
+        
+        // TODO should "d" be doubled at the start of the word?
+        // addRule("^", DALET + DAGESH, "", "d-d"); // initial consonant doubled with dash
+        
-        addRule(VOWEL, DALET + DAGESH, "", "dd");
-        // addRule(NOT_VOWEL_BEFORE, DALET + DAGESH, "", "d");
@@ -465 +473 @@
-            "e" + SUPERSCRIPT_Y);
-        addRule("", SEGOL, "", "e");
+        addRule("^", SIN + DAGESH, "", S_ACUTE + "-" + S_ACUTE); // initial consonant doubled with dash
-        addRule("", SIN + DAGESH, "", S_ACUTE + S_ACUTE);
-        addRule("", SIN, "", S_ACUTE);
+        
+        // TODO should gg be doubled at the start of the word?
+        // addRule("^", GIMEL + DAGESH, "", "g-g"); // initial consonant doubled with dash
+        
-        addRule(VOWEL, GIMEL + DAGESH, "", "gg");
-        // addRule(NOT_VOWEL_BEFORE, GIMEL + DAGESH, "", "g");
@@ -473 +486 @@
-        addRule("", HIRIQ + OPTIONAL_CANTILLATION + YOD, "", I_CARET);
-        addRule("", HIRIQ, "", "i");
+        addRule("^", YOD + DAGESH, "", "y-y"); // initial consonant doubled with dash
-        addRule("", YOD + DAGESH, "", "yy");
-        addRule("", YOD, "", "y");
+        
+        // TODO initial consonant doubled with dash?
+        // addRule("^", KAPH + DAGESH, "", "k-k");
+        
-        addRule(VOWEL + OPTIONAL_CANTILLATION, KAPH + DAGESH, "", "kk");
-        addRule(NOT_VOWEL_BEFORE, KAPH + DAGESH, "", "k");
-        addRule("", KAPH, "", "x");
-        addRule("", FINAL_KAPH, "", "x");
+        addRule("^", LAMED + DAGESH, "", "l-l"); // initial consonant doubled with dash
-        addRule("", LAMED + DAGESH, "", "ll");
-        addRule("", LAMED, "", "l");
+        addRule("^", MEM + DAGESH, "", "m-m"); // initial consonant doubled with dash
-        addRule("", MEM + DAGESH, "", "mm");
-        addRule("", MEM, "", "m");
-        addRule("", FINAL_MEM, "", "m");
+        addRule("^", NUN + DAGESH, "", "n-n"); // initial consonant doubled with dash
-        addRule("", NUN + DAGESH, "", "nn");
-        addRule("", NUN, "", "n");
@@ -493 +514 @@
-        // addRule("", HOLAM + HE + DAGESH, "$", O_BAR + "h");
-        addRule("", HOLAM, "", O_BAR);
+        
+        // TODO is this correct?
+        // addRule("^", PE + DAGESH, "", "p-p"); // initial consonant doubled with dash
+        
-        addRule(VOWEL + OPTIONAL_CANTILLATION, PE + DAGESH, "", "pp");
-        addRule(NOT_VOWEL_BEFORE, PE + DAGESH, "", "p");
-        addRule("", PE, "", "f");
-        addRule("", FINAL_PE, "", "f");
+        addRule("^", QOPH + DAGESH, "", "q-q"); // initial consonant doubled with dash
-        addRule("", QOPH + DAGESH, "", "qq");
-        addRule("", QOPH, "", "q");
-        addRule("", RESH, "", "r");
+        addRule("^", SAMEK + DAGESH, "", "s-s"); // initial consonant doubled with dash
-        addRule("", SAMEK + DAGESH, "", "ss");
-        addRule("", SAMEK, "", "s");
+        
+        // TODO is this correct?
+        // addRule("^", TAV + DAGESH, "", "t-t"); // initial consonant doubled with dash
+        
-        addRule(VOWEL + OPTIONAL_CANTILLATION, TAV + DAGESH, "", "tt");
-        addRule("", TAV, "", "t");
-        addRule("", QIBBUTS, "", "u");
+        addRule("^", TET + DAGESH, "", T_DOT + "-" + T_DOT); // initial consonant doubled with dash
-        addRule("", TET + DAGESH, "", T_DOT + T_DOT);
-        addRule("", TET, "", T_DOT);
@@ -510 +542 @@
-        addRule("", WAW, "", "w");
-        addRule("", KHET, "", H_DOT);
+        addRule("^", TSADE + DAGESH, "", S_DOT + "-" + S_DOT); // initial consonant doubled with dash
-        addRule("", TSADE + DAGESH, "", S_DOT + S_DOT);
-        addRule("", TSADE, "", S_DOT);
-        addRule("", FINAL_TSADE, "", S_DOT);
+        addRule("^", ZAYIN + DAGESH, "", "z-z"); // initial consonant doubled with dash
-        addRule("", ZAYIN + DAGESH, "", "zz");
-        addRule("", ZAYIN, "", "z");
@@ -518 +552 @@
-        m_trans = new DatabaseTransliterator(m_sql);
-    }
-    
-
-    public void testDatabaseTransliterator() throws Exception
@@ -524 +557 @@
-        addTest("\u05bf", "");
-        addTest("\u05bc", "");
-
-
-
-
+
+
+
+
+
+
+
+
-        addTest(SHEVA, "");
-        addTest(ALEPH + ALEPH + SHEVA, HOOK_LEFT + HOOK_LEFT);
-        addTest(SHEVA + ALEPH, SHEVA + HOOK_LEFT);
-
-
-
-
-
-
+
+
+
+
+
+
+
+
-            HOOK_LEFT);
-
+
+
-        
-        assertFalse(sheva1.matches(ALEPH + ALEPH, SHEVA + ALEPH, ms_EmptyMap));
@@ -651 +691 @@
-        addTest(PATAH + SOF_PASUQ + BET + DAGESH, "a:bb");
-        addTest(ALEPH + SOF_PASUQ + BET + DAGESH, HOOK_LEFT + ":b");
+        // TODO addTest(BET + DAGESH, "b-b"); // initial double consonants get a dash
-        addTest(ALEPH + BET, HOOK_LEFT + "v");
-        
@@ -658 +699 @@
-        addTest(PATAH + DALET + DAGESH, "add");
-        addTest(ALEPH + DALET + DAGESH, HOOK_LEFT + "d");
+        // TODO addTest(DALET + DAGESH, "d-d"); // initial double consonants get a dash
-        addTest(DALET, "d");
-
@@ -665 +707 @@
-        addTest(SEGOL + ALEPH, "e" + SUPERSCRIPT_QUERY);
-
-
+
+
-        addTest(SIN, S_ACUTE);
-        addTest(PATAH + GIMEL + DAGESH, "agg");
@@ -674 +717 @@
-        addTest(HIRIQ + YOD, I_CARET);
-        addTest(HIRIQ, "i");
-
+
+
-        addTest(YOD, "y");
-        addTest(PATAH + SOF_PASUQ + KAPH + DAGESH, "a:kk");
+        
+        // TODO why is Kaph Dagesh not doubled to kk?
-        addTest(ALEPH + KAPH + DAGESH, HOOK_LEFT + "k");
+        // TODO and therefore k-k at the start?
-        addTest(KAPH + DAGESH, "k");
+        
-        addTest(ALEPH + KAPH, HOOK_LEFT + "x");
-        addTest(ALEPH + FINAL_KAPH, HOOK_LEFT + "x");
-
+
+
-        addTest(LAMED, "l");
-
+
+
-        addTest(MEM, "m");
-        addTest(FINAL_MEM, "m");
-
+
+
-        addTest(NUN, "n");
-        addTest(FINAL_NUN, "n");
@@ -699 +750 @@
-        addTest(ALEPH + PE, HOOK_LEFT + "f");
-        addTest(ALEPH + FINAL_PE, HOOK_LEFT + "f");
-
+
+
-        addTest(QOPH, "q");
-        addTest(RESH, "r");
-
+
+
-        addTest(SAMEK, "s");
-        addTest(PATAH + SOF_PASUQ + TAV + DAGESH, "a:tt");
@@ -708 +761 @@
-        addTest(TAV, "t");
-        addTest(QIBBUTS, "u");
-
+
+
-        addTest(TET, T_DOT);
-        addTest(WAW + DAGESH, U_CARET);
-        addTest(WAW, "w");
-        addTest(KHET, H_DOT);
-
+
+
-        addTest(TSADE, S_DOT);
-        addTest(FINAL_TSADE, S_DOT);
-
+
+
-        addTest(ZAYIN, "z");
-        
@@ -744 +800 @@
-        morphs.add(new Morpheme("ֹת֞֔י", "FplCS", "N/GNS", true, true));
-        morphs.add(new Morpheme("ו", "3Msg", "N/POS", true, true));
-
+-
-        assertEquals("ōtāʞ", m_trans.transliterate(morphs, 1, ms_EmptyMap));
-        assertEquals("w", m_trans.transliterate(morphs, 2, ms_EmptyMap));
@@ -970 +1026 @@
-        }
-    }
+    
-    public static void main(String[] args)
-    {