public void SparseAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms_AddWhitespace_LT5313() { // First set sparse analyses on wordforms that have multiple occurrences. ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.SimpleSegmentPara); pb.ParseParagraph(); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); string gloss; var gloss0_1 = tapb.SetDefaultWordGloss(0, 1, out gloss); // xxxyalola 1 var gloss1_1 = tapb.SetDefaultWordGloss(1, 1, out gloss); // xxxpus 2 var gloss2_1 = tapb.SetDefaultWordGloss(2, 1, out gloss); // xxxnihimbilira 3 tapb.ValidateAnnotations(); // precondition testing. // Append whitespace in the text, and see if the analyses still show up in the right place // (cf. LT-5313). pb.ReplaceTrailingWhitepace(0, 0, 1); pb.RebuildParagraphContentFromAnnotations(); pb.ParseParagraph(); Assert.AreEqual(gloss0_1, tapb.GetAnalysis(0, 1)); Assert.AreEqual(gloss1_1, tapb.GetAnalysis(1, 1)); Assert.AreEqual(gloss2_1, tapb.GetAnalysis(2, 1)); tapb.ValidateAnnotations(); }
public void SparseAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms() { // First set sparse analyses on wordforms that have multiple occurrences. ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.SimpleSegmentPara); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); pb.ParseParagraph(); IWfiGloss gloss_xxxyalola0_1 = tapb.SetDefaultWordGloss("xxxyalola", 0); // gloss first occurrence. IWfiGloss gloss_xxxpus1_1 = tapb.SetDefaultWordGloss("xxxpus", 1); // gloss second occurrence. IWfiGloss gloss_xxxnihimbilira2_1 = tapb.SetDefaultWordGloss("xxxnihimbilira", 2); // gloss third occurrence. pb.ParseParagraph(); var actualAnalysis_xxxyalola0_1 = tapb.GetAnalysis(0, 1); var actualAnalysis_xxxpus1_1 = tapb.GetAnalysis(1, 1); var actualAnalysis_xxxnihimbilira2_1 = tapb.GetAnalysis(2, 1); Assert.AreEqual(gloss_xxxyalola0_1, actualAnalysis_xxxyalola0_1); Assert.AreEqual(gloss_xxxpus1_1, actualAnalysis_xxxpus1_1); Assert.AreEqual(gloss_xxxnihimbilira2_1, actualAnalysis_xxxnihimbilira2_1); // verify the rest tapb.ValidateAnnotations(); // Replace some occurrences of these wordforms from the text to validate the analysis does not show up on the wrong occurrence. // Remove the first occurrence of 'xxxnihimbilira'; the (newly) second occurrence should still have the gloss. pb.ReplaceSegmentForm("xxxnihimbilira", 0, ""); pb.RebuildParagraphContentFromAnnotations(); pb.ParseParagraph(); actualAnalysis_xxxnihimbilira2_1 = tapb.GetAnalysis(2, 1); Assert.AreEqual(gloss_xxxnihimbilira2_1, actualAnalysis_xxxnihimbilira2_1); tapb.ValidateAnnotations(); // Remove first occurrence of 'xxxpus'; the next one should still have the gloss. pb.ReplaceSegmentForm("xxxpus", 0, ""); pb.RebuildParagraphContentFromAnnotations(); pb.ParseParagraph(); actualAnalysis_xxxpus1_1 = tapb.GetAnalysis(1, 1); Assert.AreEqual(gloss_xxxpus1_1, actualAnalysis_xxxpus1_1); tapb.ValidateAnnotations(); }
public void SparseAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms_RemoveSegment_LT5376() { // First set sparse analyses on wordforms that have multiple occurrences. ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.SimpleSegmentPara); pb.ParseParagraph(); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); tapb.SetDefaultWordGloss("xxxyalola", 0); // gloss first occurrence. tapb.ValidateAnnotations(); // Remove first sentence containing 'xxxyalola'; its annotation should be removed. pb.RemoveSegment(0); pb.RebuildParagraphContentFromAnnotations(); pb.ParseParagraph(); tapb.ValidateAnnotations(); }
public void NoAnalyses_SimpleEdits_MultipleWritingSystemsParagraph() { ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.MultipleWritingSystems); // verify that our wfics point to wordforms in the expected wss. pb.ParseParagraph(); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); FdoValidator.ValidateCbaWordToBaselineWord(tapb, 0, 0); //FdoValidator.ValidateCbaWordToBaselineWord(tapb, 0, 1); // currently considered punctuation. //FdoValidator.ValidateCbaWordToBaselineWord(tapb, 1, 0); // french word considered punctuation. //FdoValidator.ValidateCbaWordToBaselineWord(tapb, 1, 1); // eng word considered punctuation // FdoValidator.ValidateCbaWordToBaselineWord(tapb, 1, 4); // german word considered punctuation. // validate the rest tapb.ValidateAnnotations(); // xxxpus xxes xxxnihimbilira. xxfr xxen xxxnihimbilira xxxpus xxde. xxkal xxkal xxxxhesyla xxxxhesyla. // xxkal: German (de) -- occurrence 0 // xxkal: Kalaba (xkal) -- occurrence 1 Dictionary<string, int> expectedOccurrences = pb.ExpectedWordformsAndOccurrences; CheckExpectedWordformsAndOccurrences(pb.ActualParagraph, expectedOccurrences); // replace the german occurrence of "xxkal" with a xkal version. int wsDe; FdoValidator.GetTssStringValue(tapb, 2, 0, out wsDe); int wsVernDef = Cache.DefaultVernWs; Assert.AreNotEqual(wsVernDef, wsDe, "Precondition: did not expect to have a default vern ws."); pb.ReplaceSegmentForm(2, 0, "xxkal", wsVernDef); var segformNode = pb.SegmentFormNode(2, 0); // Now it should parse as a wfic. var linkNode = segformNode.SelectSingleNode("AnnotationType34/Link"); linkNode.Attributes["guid"].Value = ParagraphBuilder.WficGuid; linkNode.Attributes["name"].Value = "Wordform In Context"; expectedOccurrences.Remove("xxkal" + wsDe.ToString()); expectedOccurrences["xxkal" + wsVernDef.ToString()] += 1; pb.RebuildParagraphContentFromAnnotations(true); pb.ParseParagraph(); int wsAnalysis2_0; FdoValidator.GetTssStringValue(tapb, 2, 0, out wsAnalysis2_0); Assert.AreEqual(Cache.DefaultVernWs, wsAnalysis2_0, "Precondition: expected to have default vern ws."); FdoValidator.ValidateCbaWordToBaselineWord(tapb, 2, 0); // validate the rest. tapb.ValidateAnnotations(); CheckExpectedWordformsAndOccurrences(pb.ActualParagraph, expectedOccurrences); }
public void NoAnalyses_NoEdits_PhraseWordforms() { // 1. Setup Tests with a basic phrase ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int) Text1ParaIndex.PhraseWordforms); // first do a basic phrase (without secondary phrases (guesses)) // xxxpus xxxyalola xxxnihimbilira. [xxxpus xxxyalola] xxxhesyla xxxnihimbilira. xxxpus xxxyalola xxxnihimbilira pb.MergeAdjacentAnnotations(1, 0); // generate mock ids pb.RebuildParagraphContentFromAnnotations(); // now produce a guess to establish the phrase annotation. var tapb = new ParagraphAnnotatorForParagraphBuilder(pb); pb.ParseParagraph(); pb.ActualParagraph.SegmentsOS[1].AnalysesRS.RemoveAt(0); // delete "xxxpus" // now replace "xxxyalola" with the new phrase form "xxxpus xxxyalola" IAnalysis beforeParse_phrase1_0 = pb.ExportCbaNodeToReal(1, 0); //string gloss; //IWfiGloss wg_phrase1_0 = tapb.SetDefaultWordGloss(1, 0, out gloss); // NOTE: Precondition checks to make sure we set up the annotation properly // The real test: now parse and verify that we maintained the expected result for the phrase annotation. pb.ParseParagraph(); var afterParse_actualWordform = tapb.GetAnalysis(1, 0); Assert.AreEqual(beforeParse_phrase1_0, afterParse_actualWordform, "word mismatch"); // verify the rest. tapb.ValidateAnnotations(); }
public void SparseTwficAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms_AddWhitespace_LT5313() { CheckDisposed(); // First set sparse analyses on wordforms that have multiple occurrences. ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.SimpleSegmentPara); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); tapb.SetDefaultWordGloss("xxxyalola", 0); // gloss first occurrence. tapb.SetDefaultWordGloss("xxxpus", 1); // gloss second occurrence. tapb.SetDefaultWordGloss("xxxnihimbilira", 2); // gloss third occurrence. tapb.ValidateAnnotations(); // Append whitespace in the text, and see if the analyses still show up in the right place // (cf. LT-5313). pb.ReplaceTrailingWhitepace(0, 0, 1); pb.RebuildParagraphContentFromAnnotations(); tapb.ValidateAnnotations(); }
public void SparseTwficAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms() { CheckDisposed(); // First set sparse analyses on wordforms that have multiple occurrences. ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.SimpleSegmentPara); ParagraphAnnotatorForParagraphBuilder tapb = new ParagraphAnnotatorForParagraphBuilder(pb); tapb.SetDefaultWordGloss("xxxyalola", 0); // gloss first occurrence. tapb.SetDefaultWordGloss("xxxpus", 1); // gloss second occurrence. tapb.SetDefaultWordGloss("xxxnihimbilira", 2); // gloss third occurrence. tapb.ValidateAnnotations(); // Replace some occurrences of these wordforms from the text to validate the analysis does not show up on the wrong occurrence. // Remove the first occurrence of 'xxxnihimbilira'; the second occurrence should have the gloss. pb.ReplaceSegmentForm("xxxnihimbilira", 0, ""); pb.RebuildParagraphContentFromAnnotations(); tapb.ValidateAnnotations(); // Remove first occurrence of 'xxxpus'; the next one should still have the gloss. pb.ReplaceSegmentForm("xxxpus", 0, ""); pb.RebuildParagraphContentFromAnnotations(); tapb.ValidateAnnotations(); //SparseTwficAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms_RemoveSegment_LT5376() //SparseTwficAnalyses_SimpleEdits_SimpleSegmentParagraph_DuplicateWordforms_AddWhitespace_LT5313() }
public void NoAnalyses_SimpleEdits_MultipleWritingSystemsParagraph() { CheckDisposed(); ParagraphBuilder pb = new ParagraphBuilder(m_textsDefn, m_text1, (int)Text1ParaIndex.MultipleWritingSystems); pb.ParseParagraph(true, true); // xxxpus xxes xxxnihimbilira. xxfr xxen xxxnihimbilira xxxpus xxde. xxkal xxkal xxxxhesyla xxxxhesyla. // xxkal: German (de) -- occurrence 0 // xxkal: Kalaba (xkal) -- occurrence 1 Dictionary<string, int> expectedOccurrences = pb.ExpectedWordformsAndOccurrences; WordformInventory wfi = Cache.LangProject.WordformInventoryOA as WordformInventory; CheckExpectedWordformsAndOccurrences(wfi, expectedOccurrences); // replace the german occurrence of "xxkal" with a xkal version. int hvoSeg2 = pb.ActualParagraph.Segments[2]; int hvoSegForm2_0 = pb.ActualParagraph.SegmentForms(hvoSeg2)[0]; StTxtPara.TwficInfo ti2_0 = new StTxtPara.TwficInfo(Cache, hvoSegForm2_0); int wsDe = StringUtils.GetWsAtOffset(pb.ActualParagraph.Contents.UnderlyingTsString, ti2_0.Object.BeginOffset); int wsVernDef = Cache.DefaultVernWs; Assert.AreNotEqual(wsVernDef, wsDe, "did not expect to have a default vern ws."); pb.ReplaceSegmentForm(2, 0, "xxkal", wsVernDef); expectedOccurrences.Remove("xxkal" + wsDe.ToString()); expectedOccurrences["xxkal" + wsVernDef.ToString()] += 1; pb.RebuildParagraphContentFromAnnotations(true, true); CheckExpectedWordformsAndOccurrences(wfi, expectedOccurrences); }