Merge remote-tracking branch 'origin/investigate_alignment_deuterocanonical_books' into investigate_alignment_deuterocanonical_books

Author: mudiagaobrikisil

src/SIL.Machine.Morphology.HermitCrab/AnalysisStratumRule.cs

@@ -34,7 +34,11 @@ public AnalysisStratumRule(Morpher morpher, Stratum stratum)
             switch (stratum.MorphologicalRuleOrder)
             {
                 case MorphologicalRuleOrder.Linear:
-                    _mrulesRule = new LinearRuleCascade<Word, ShapeNode>(
+                    // Use PermutationRuleCascade instead of LinearRuleCascade
+                    // because morphological rules should be considered optional
+                    // during unapplication (they are obligatory during application,
+                    // but we don't know they have been applied during unapplication).
+                    _mrulesRule = new PermutationRuleCascade<Word, ShapeNode>(
                         mrules,
                         true,
                         FreezableEqualityComparer<Word>.Default
@@ -69,17 +73,8 @@ public IEnumerable<Word> Apply(Word input)
             _prulesRule.Apply(input);
             input.Freeze();
 
-            IEnumerable<Word> mruleOutWords = null;
-            switch (_stratum.MorphologicalRuleOrder)
-            {
-                case MorphologicalRuleOrder.Linear:
-                    mruleOutWords = ApplyTemplates(input);
-                    break;
-
-                case MorphologicalRuleOrder.Unordered:
-                    mruleOutWords = ApplyTemplates(input).Concat(ApplyMorphologicalRules(input));
-                    break;
-            }
+            // AnalysisStratumRule.Apply should cover the inverse of SynthesisStratumRule.Apply.
+            IEnumerable<Word> mruleOutWords = ApplyTemplates(input).Concat(ApplyMorphologicalRules(input));
             Debug.Assert(mruleOutWords != null);
 
             var output = new HashSet<Word>(FreezableEqualityComparer<Word>.Default) { input };

tests/SIL.Machine.Morphology.HermitCrab.Tests/HermitCrabTestBase.cs

@@ -813,6 +813,15 @@ public void TestCleanup()
             stratum.MorphologicalRules.Clear();
             stratum.AffixTemplates.Clear();
         }
+        SetRuleOrder(MorphologicalRuleOrder.Unordered);
+    }
+
+    protected void SetRuleOrder(MorphologicalRuleOrder ruleOrder)
+    {
+        foreach (Stratum stratum in Language.Strata)
+        {
+            stratum.MorphologicalRuleOrder = ruleOrder;
+        }
     }
 
     public LexEntry AddEntry(string gloss, FeatureStruct syntacticFS, Stratum stratum, params string[] forms)

tests/SIL.Machine.Morphology.HermitCrab.Tests/MorpherTests.cs

@@ -3,6 +3,7 @@
 using SIL.Machine.FeatureModel;
 using SIL.Machine.Matching;
 using SIL.Machine.Morphology.HermitCrab.MorphologicalRules;
+using SIL.Machine.Morphology.HermitCrab.PhonologicalRules;
 
 namespace SIL.Machine.Morphology.HermitCrab;
 
@@ -38,6 +39,65 @@ public void AnalyzeWord_CanAnalyze_ReturnsCorrectAnalysis()
         );
     }
 
+    [Test]
+    public void AnalyzeWord_CanAnalyzeLinear_ReturnsCorrectAnalysis()
+    {
+        var any = FeatureStruct.New().Symbol(HCFeatureSystem.Segment).Value;
+
+        var edSuffix = new AffixProcessRule
+        {
+            Id = "PAST",
+            Name = "ed_suffix",
+            Gloss = "PAST",
+            RequiredSyntacticFeatureStruct = FeatureStruct.New(Language.SyntacticFeatureSystem).Symbol("V").Value
+        };
+        edSuffix.Allomorphs.Add(
+            new AffixProcessAllomorph
+            {
+                Lhs = { Pattern<Word, ShapeNode>.New("1").Annotation(any).OneOrMore.Value },
+                Rhs = { new CopyFromInput("1"), new InsertSegments(Table3, "+d") }
+            }
+        );
+        Morphophonemic.MorphologicalRules.Add(edSuffix);
+
+        // Adding rules shouldn't block sagd analysis when Linear.
+        var tSuffix = new AffixProcessRule
+        {
+            Id = "PLURAL",
+            Name = "t_suffix",
+            Gloss = "PLURAL",
+            RequiredSyntacticFeatureStruct = FeatureStruct.New(Language.SyntacticFeatureSystem).Symbol("N").Value
+        };
+        tSuffix.Allomorphs.Add(
+            new AffixProcessAllomorph
+            {
+                Lhs = { Pattern<Word, ShapeNode>.New("1").Annotation(any).OneOrMore.Value },
+                Rhs = { new CopyFromInput("1"), new InsertSegments(Table3, "+t") }
+            }
+        );
+        Morphophonemic.MorphologicalRules.Add(tSuffix);
+
+        // Add a phonological rule so that "sagd" becomes "sag[dt]" during unapplication.
+        // This is to verify that unapplication works correctly.
+        var rule1 = new RewriteRule
+        {
+            Name = "rule1",
+            Lhs = Pattern<Word, ShapeNode>.New().Annotation(Character(Table1, "t")).Value
+        };
+        rule1.Subrules.Add(
+            new RewriteSubrule { Rhs = Pattern<Word, ShapeNode>.New().Annotation(Character(Table1, "d")).Value }
+        );
+        Morphophonemic.PhonologicalRules.Add(rule1);
+
+        SetRuleOrder(MorphologicalRuleOrder.Linear);
+        var morpher = new Morpher(TraceManager, Language);
+
+        Assert.That(
+            morpher.AnalyzeWord("sagd"),
+            Is.EquivalentTo(new[] { new WordAnalysis(new IMorpheme[] { Entries["32"], edSuffix }, 0, "V") })
+        );
+    }
+
     [Test]
     public void AnalyzeWord_CannotAnalyze_ReturnsEmptyEnumerable()
     {