/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
var textFactory = Cache.ServiceLocator.GetInstance <ITextFactory>();
var stTextFactory = Cache.ServiceLocator.GetInstance <IStTextFactory>();
m_text1 = textFactory.Create();
//Cache.LangProject.TextsOC.Add(m_text1);
var stText1 = stTextFactory.Create();
m_text1.ContentsOA = stText1;
var para1 = stText1.AddNewTextPara(null);
(m_text1.ContentsOA[0]).Contents =
TsStringUtils.MakeTss("xxxa xxxb xxxc xxxd xxxe, xxxa xxxb.", Cache.DefaultVernWs);
InterlinMaster.LoadParagraphAnnotationsAndGenerateEntryGuessesIfNeeded(stText1, false);
// setup language project parts of speech
var partOfSpeechFactory = Cache.ServiceLocator.GetInstance <IPartOfSpeechFactory>();
var adjunct = partOfSpeechFactory.Create();
var noun = partOfSpeechFactory.Create();
var verb = partOfSpeechFactory.Create();
var transitiveVerb = partOfSpeechFactory.Create();
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(adjunct);
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(noun);
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(verb);
verb.SubPossibilitiesOS.Add(transitiveVerb);
adjunct.Name.set_String(Cache.DefaultAnalWs, "adjunct");
noun.Name.set_String(Cache.DefaultAnalWs, "noun");
verb.Name.set_String(Cache.DefaultAnalWs, "verb");
transitiveVerb.Name.set_String(Cache.DefaultAnalWs, "transitive verb");
}
public void TestImportCreatesReusesExistingSpeaker()
{
string xml = "<document><interlinear-text guid=\"AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA\">" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase speaker=\"Jimmy Dorante\" media-file=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" guid=\"BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB\" begin-time-offset=\"1\" end-time-offset=\"2\">" +
"<item type=\"text\">This is a test with text.</item><word>This</word></phrase></phrases></paragraph></paragraphs>" +
"<languages><language lang=\"en\" font=\"latin\" vernacular=\"false\"/></languages>" +
"<media-files offset-type=\"milliseconds\"><media guid=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" location=\"file:\\\\test.wav\"/></media-files></interlinear-text></document>";
ICmPerson newPerson = null;
//Create and add Jimmy to the project.
NonUndoableUnitOfWorkHelper.Do(Cache.ActionHandlerAccessor,
() => {
Cache.LanguageProject.PeopleOA = Cache.ServiceLocator.GetInstance <ICmPossibilityListFactory>().Create();
//person not found create one and add it.
newPerson = Cache.ServiceLocator.GetInstance <ICmPersonFactory>().Create();
Cache.LanguageProject.PeopleOA.PossibilitiesOS.Add(newPerson);
newPerson.Name.set_String(Cache.DefaultVernWs, "Jimmy Dorante");
});
Assert.NotNull(newPerson);
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
//If the import sets the speaker in the segment to our Jimmy, and not a new Jimmy then all is well
Assert.AreEqual(newPerson, text.ContentsOA[0].SegmentsOS[0].SpeakerRA, "Speaker not reused.");
}
}
public void OneOfEachElementTypeTest()
{
string title = "atrocious";
string abbr = "atroc";
//an interliner text example xml string
string xml = "<document><interlinear-text>" +
"<item type=\"title\" lang=\"en\">" + title + "</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">" + abbr + "</item>" +
"<paragraphs><paragraph><phrases><phrase>" +
"<item type=\"reference-number\" lang=\"en\">1 Musical</item>" +
"<item type=\"note\" lang=\"pt\">origem: mary poppins</item>" +
"<words><word><item type=\"txt\" lang=\"en\">supercalifragilisticexpialidocious</item>" +
"<item type=\"gls\" lang=\"pt\">absurdo</item></word>" +
"</words></phrase></phrases></paragraph></paragraphs></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
//The title imported
Assert.True(imported.Name.get_String(Cache.WritingSystemFactory.get_Engine("en").Handle).Text.Equals(title));
//The title abbreviation imported
Assert.True(imported.Abbreviation.get_String(Cache.WritingSystemFactory.get_Engine("en").Handle).Text.Equals(abbr));
}
}
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
// setup default vernacular ws.
IWritingSystem wsXkal = Cache.ServiceLocator.WritingSystemManager.Set("qaa-x-kal");
wsXkal.DefaultFontName = "Times New Roman";
Cache.ServiceLocator.WritingSystems.VernacularWritingSystems.Add(wsXkal);
Cache.ServiceLocator.WritingSystems.CurrentVernacularWritingSystems.Insert(0, wsXkal);
var textFactory = Cache.ServiceLocator.GetInstance <ITextFactory>();
var stTextFactory = Cache.ServiceLocator.GetInstance <IStTextFactory>();
m_text0 = textFactory.Create();
//Cache.LangProject.TextsOC.Add(m_text0);
m_stText0 = stTextFactory.Create();
m_text0.ContentsOA = m_stText0;
m_para0_0 = m_stText0.AddNewTextPara(null);
m_para0_0.Contents = TsStringUtils.MakeTss("Xxxhope xxxthis xxxwill xxxdo. xxxI xxxhope.", wsXkal.Handle);
InterlinMaster.LoadParagraphAnnotationsAndGenerateEntryGuessesIfNeeded(m_stText0, false);
// paragraph 0_0 simply has wordforms as analyses
foreach (var occurence in SegmentServices.GetAnalysisOccurrences(m_para0_0))
{
if (occurence.HasWordform)
{
m_analysis_para0_0.Add(new AnalysisTree(occurence.Analysis));
}
}
}
public DiscourseTestHelper(FdoCache cache)
{
m_cache = cache;
#region Load Factories and Repositories
m_servLoc = m_cache.ServiceLocator;
m_tsf = cache.TsStrFactory;
m_wAnalysisFact = m_servLoc.GetInstance <IWfiAnalysisFactory>();
m_wGlossFact = m_servLoc.GetInstance <IWfiGlossFactory>();
m_rowFact = m_servLoc.GetInstance <IConstChartRowFactory>();
m_wordGrpFact = m_servLoc.GetInstance <IConstChartWordGroupFactory>();
m_ccTagFact = m_servLoc.GetInstance <IConstChartTagFactory>();
m_mtmFact = m_servLoc.GetInstance <IConstChartMovedTextMarkerFactory>();
m_clauseMrkrFact = m_servLoc.GetInstance <IConstChartClauseMarkerFactory>();
m_partRepo = m_servLoc.GetInstance <IConstituentChartCellPartRepository>();
m_rowRepo = m_servLoc.GetInstance <IConstChartRowRepository>();
#endregion
m_text = m_servLoc.GetInstance <ITextFactory>().Create();
//Cache.LangProject.TextsOC.Add(m_text);
m_stText = m_servLoc.GetInstance <IStTextFactory>().Create();
m_text.ContentsOA = m_stText;
m_allOccurrences = new Dictionary <IStTxtPara, AnalysisOccurrence[]>();
m_firstPara = MakeParagraph();
}
public void TestImportFullELANData()
{
string xml = "<document><interlinear-text guid=\"AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA\">" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase media-file=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" guid=\"BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB\" begin-time-offset=\"1\" end-time-offset=\"2\">" +
"<item type=\"text\">This is a test with text.</item><word>This</word></phrase></phrases></paragraph></paragraphs>" +
"<languages><language lang=\"en\" font=\"latin\" vernacular=\"false\"/></languages>" +
"<media-files offset-type=\"milliseconds\"><media guid=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" location=\"file:\\\\test.wav\"/></media-files></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
Assert.True(imported.ContentsOA.ParagraphsOS.Count > 0, "Paragraph was not imported as text content.");
var para = imported.ContentsOA[0];
Assert.NotNull(para, "The imported paragraph is null?");
Assert.True(para.SegmentsOS[0].Guid.ToString().ToUpper().Equals("BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB"), "Segment guid not maintained on import.");
VerifyMediaLink(imported);
}
}
}
public void TestProvidedTextUsedIfPresent()
{
string xml = "<document><interlinear-text>" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase>" +
"<item type=\"txt\" lang=\"en\">Text not built from words.</item>" +
"<item type=\"note\" lang=\"pt\">origem: mary poppins</item>" +
"<words><word><item type=\"txt\" lang=\"en\">a</item></word>" +
"<word><item type=\"txt\" lang=\"en\">space</item></word>" +
"<word><item type=\"txt\" lang=\"en\">space</item></word>" +
"</words></phrase></phrases></paragraph></paragraphs></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
var para = imported.ContentsOA[0];
Assert.IsTrue(para.Contents.Text.Equals("Text not built from words."));
}
}
}
public void TestImportMergeInELANData()
{
string firstxml = "<document><interlinear-text guid=\"AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA\"><item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item><paragraphs><paragraph><phrases><phrase guid=\"BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB\">" +
"<word guid=\"CCCCCCCC-CCCC-CCCC-CCCC-CCCCCCCCCCCC\"><item type=\"txt\" lang=\"fr\">Word</item></word></phrase></phrases></paragraph></paragraphs></interlinear-text></document>";
string secondxml = "<document><interlinear-text guid=\"AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA\"><item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item><paragraphs><paragraph><phrases><phrase guid=\"BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB\" media-file=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" begin-time-offset=\"1\" end-time-offset=\"2\">" +
"<word guid=\"CCCCCCCC-CCCC-CCCC-CCCC-CCCCCCCCCCCC\"><item type=\"txt\" lang=\"fr\">Word</item></word></phrase></phrases></paragraph></paragraphs>" +
"<media-files offset-type=\"milliseconds\"><media guid=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" location=\"file:\\\\test.wav\"/></media-files></interlinear-text></document>";
LinguaLinksImport li = new LLIMergeExtension(Cache, null, null);
FDO.IText text = null;
using (var firstStream = new MemoryStream(Encoding.ASCII.GetBytes(firstxml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), firstStream, 0, ref text);
Assert.True(text.Guid.ToString().ToUpper().Equals("AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA"), "Guid not maintained during import.");
using (var secondStream = new MemoryStream(Encoding.ASCII.GetBytes(secondxml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), secondStream, 0, ref text);
Assert.True(text.Guid.ToString().ToUpper().Equals("AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA"), "Guid not maintained during import.");
Assert.True(Cache.LanguageProject.Texts.Count == 1, "Second text not merged with the first.");
Assert.True(text.ContentsOA.ParagraphsOS.Count == 1 && text.ContentsOA[0].SegmentsOS.Count == 1, "Segments from second import not merged with the first.");
VerifyMediaLink(text);
}
}
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
var textFactory = Cache.ServiceLocator.GetInstance<ITextFactory>();
var stTextFactory = Cache.ServiceLocator.GetInstance<IStTextFactory>();
m_text1 = textFactory.Create();
//Cache.LangProject.TextsOC.Add(m_text1);
var stText1 = stTextFactory.Create();
m_text1.ContentsOA = stText1;
var para1 = stText1.AddNewTextPara(null);
(m_text1.ContentsOA[0]).Contents =
TsStringUtils.MakeTss("xxxa xxxb xxxc xxxd xxxe, xxxa xxxb.", Cache.DefaultVernWs);
InterlinMaster.LoadParagraphAnnotationsAndGenerateEntryGuessesIfNeeded(stText1, false);
// setup language project parts of speech
var partOfSpeechFactory = Cache.ServiceLocator.GetInstance<IPartOfSpeechFactory>();
var adjunct = partOfSpeechFactory.Create();
var noun = partOfSpeechFactory.Create();
var verb = partOfSpeechFactory.Create();
var transitiveVerb = partOfSpeechFactory.Create();
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(adjunct);
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(noun);
Cache.LangProject.PartsOfSpeechOA.PossibilitiesOS.Add(verb);
verb.SubPossibilitiesOS.Add(transitiveVerb);
adjunct.Name.set_String(Cache.DefaultAnalWs, "adjunct");
noun.Name.set_String(Cache.DefaultAnalWs, "noun");
verb.Name.set_String(Cache.DefaultAnalWs, "verb");
transitiveVerb.Name.set_String(Cache.DefaultAnalWs, "transitive verb");
}
internal static AnalysisOccurrence GetNewAnalysisOccurence(FDO.IText text, int iPara, int iSeg, int iSegForm)
{
IStTxtPara para = text.ContentsOA.ParagraphsOS[iPara] as IStTxtPara;
var seg = para.SegmentsOS[iSeg];
return(new AnalysisOccurrence(seg, iSegForm));
}
public void SandBoxWithGlossConfig_LoadsGuessForGlossFromAnalysis()
{
var mockRb = MockRepository.GenerateMock <IVwRootBox>();
mockRb.Expect(rb => rb.DataAccess).Return(Cache.MainCacheAccessor);
var textFactory = Cache.ServiceLocator.GetInstance <ITextFactory>();
var stTextFactory = Cache.ServiceLocator.GetInstance <IStTextFactory>();
text = textFactory.Create();
var stText1 = stTextFactory.Create();
text.ContentsOA = stText1;
var para1 = stText1.AddNewTextPara(null);
(text.ContentsOA[0]).Contents = TsStringUtils.MakeTss("xxxa xxxa xxxa.", Cache.DefaultVernWs);
InterlinMaster.LoadParagraphAnnotationsAndGenerateEntryGuessesIfNeeded(stText1, true);
using (var mockInterlinDocForAnalyis = new MockInterlinDocForAnalyis(stText1)
{
MockedRootBox = mockRb
})
{
m_sandbox.SetInterlinDocForTest(mockInterlinDocForAnalyis);
var cba0_0 = AddWordsToLexiconTests.GetNewAnalysisOccurence(text, 0, 0, 0);
var wf = Cache.ServiceLocator.GetInstance <IWfiWordformFactory>().Create(TsStringUtils.MakeTss("xxxa", Cache.DefaultVernWs));
cba0_0.Analysis = Cache.ServiceLocator.GetInstance <IWfiAnalysisFactory>().Create(wf, Cache.ServiceLocator.GetInstance <IWfiGlossFactory>());
var gloss = cba0_0.Analysis.Analysis.MeaningsOC.First();
var glossTss = TsStringUtils.MakeTss("I did it", Cache.DefaultAnalWs);
gloss.Form.set_String(Cache.DefaultAnalWs, glossTss);
m_sandbox.SwitchWord(cba0_0);
// Verify that the wordgloss was loaded into the m_sandbox
Assert.AreNotEqual(0, m_sandbox.WordGlossHvo, "The gloss was not set to Default gloss from the analysis.");
Assert.AreEqual(m_sandbox.WordGlossHvo, gloss.Hvo, "The gloss was not set to Default gloss from the analysis.");
}
}
public override void Initialize()
{
CheckDisposed();
base.Initialize();
m_text1 = SetupDataForText1();
m_choices = new InterlinLineChoices(0, Cache.DefaultAnalWs, Cache.LangProject);
}
public override void Exit()
{
CheckDisposed();
m_text1 = null;
m_choices = null;
base.Exit();
}
internal void MakeTextAndCcl()
{
using (new UndoRedoTaskHelper(Cache, "ConstituentChartDatabaseTests - MakeText()", "ConstituentChartDatabaseTests - MakeText()"))
{
m_text1 = Cache.LangProject.TextsOC.Add(new Text());
m_text1.ContentsOA = new StText();
m_ccl = new TestCCLogic(Cache, m_chart, m_text1.ContentsOAHvo);
MakeTemplate();
}
}
public void TestSpacesAroundSpanishPunct()
{
string xml = "<document><interlinear-text>" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase>" +
"<item type=\"reference-number\" lang=\"en\">1 Musical</item>" +
"<item type=\"note\" lang=\"pt\">origem: mary poppins</item>" +
"<words>" +
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">.¡</item></word>" + // spanish begin exclamation
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">!¿</item></word>" + // spanish begin question
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">?</item></word>" +
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">. ¿</item></word>" +
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">? "¿</item></word>" +
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"<word><item type=\"punct\" lang=\"en\">¿</item></word>" +
"<word><item type=\"txt\" lang=\"en\">s</item></word>" +
"</words></phrase></phrases></paragraph></paragraphs></interlinear-text></document>";
// --------------------------
// 01234567890123456789012345
// s. es! qs? s. qs? "qs qs (e=spanish beg. exclamation, q=spanish beg. question)
// --------------------------
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current; // why is this null?!
var para = imported.ContentsOA[0];
var spaceArray = new char[] { ' ' };
var spaceOne = para.Contents.Text.Substring(2, 1); //should be: " "
var spaceTwo = para.Contents.Text.Substring(6, 1); //should be: " "
var spaceThree = para.Contents.Text.Substring(10, 1);
var spaceFour = para.Contents.Text.Substring(13, 1);
var spaceFive = para.Contents.Text.Substring(17, 1);
var spaceSix = para.Contents.Text.Substring(21, 1);
//test to make sure no space was inserted before the comma, this is probably captured by the other assert
Assert.AreEqual(7, para.Contents.Text.Split(spaceArray).Length); //capture correct number of spaces, and no double spaces
//test to make sure spaces were inserted in each expected place
CollectionAssert.AreEqual(new[] { " ", " ", " ", " ", " ", " " },
new[] { spaceOne, spaceTwo, spaceThree, spaceFour, spaceFive, spaceSix });
}
}
}
private ITextTag MakeTag(FDO.IText text, ICmPossibility tag, ISegment beginSeg, int begin, ISegment endSeg, int end)
{
ITextTag ttag = Cache.ServiceLocator.GetInstance <ITextTagFactory>().Create();
text.ContentsOA.TagsOC.Add(ttag);
ttag.TagRA = tag;
ttag.BeginSegmentRA = beginSeg;
ttag.BeginAnalysisIndex = begin;
ttag.EndSegmentRA = endSeg;
ttag.EndAnalysisIndex = end;
return(ttag);
}
public override void Exit()
{
CheckDisposed();
// UndoEverything before we clear our wordform table, so we can make sure
// the real wordform list is what we want to start with the next time.
base.Exit();
// clear the wordform table.
m_text1.Cache.LangProject.WordformInventoryOA.ResetAllWordformOccurrences();
m_text1 = null;
// Dispose the sandbox
m_sandbox.Dispose();
m_sandbox = null;
}
private static void VerifyMediaLink(FDO.IText imported)
{
var mediaFilesContainer = imported.MediaFilesOA;
var para = imported.ContentsOA[0];
Assert.NotNull(mediaFilesContainer, "Media Files not being imported.");
Assert.True(mediaFilesContainer.MediaURIsOC.Count == 1, "Media file not imported.");
using (var enumerator = para.SegmentsOS.GetEnumerator())
{
enumerator.MoveNext();
var seg = enumerator.Current;
Assert.True(seg.BeginTimeOffset.Equals("1"), "Begin offset not imported correctly");
Assert.True(seg.EndTimeOffset.Equals("2"), "End offset not imported correctly");
Assert.True(seg.MediaURIRA == mediaFilesContainer.MediaURIsOC.First(), "Media not correctly linked to segment.");
}
}
public override void Initialize()
{
CheckDisposed();
base.Initialize();
m_text1 = Cache.LangProject.TextsOC.Add(new Text());
m_text1.ContentsOA = new StText();
m_text1.ContentsOA.ParagraphsOS.Append(new StTxtPara());
(m_text1.ContentsOA.ParagraphsOS[0] as StTxtPara).Contents.UnderlyingTsString =
StringUtils.MakeTss("xxxa xxxb xxxc xxxd xxxe, xxxa xxxb.", Cache.DefaultVernWs);
bool fDidParse;
ParagraphParser.ParseText(m_text1.ContentsOA, new NullProgressState(), out fDidParse);
InterlinLineChoices lineChoices = InterlinLineChoices.DefaultChoices(0, Cache.DefaultAnalWs, Cache.LangProject,
InterlinLineChoices.InterlinMode.GlossAddWordsToLexicon);
m_sandbox = new SandboxForTests(Cache, lineChoices);
}
public void SetupTexts()
{
// First make a regular text.
using (new UndoRedoTaskHelper(Cache, "ConstituentChartDatabaseTests - SetupTexts()", "ConstituentChartDatabaseTests - SetupTexts()"))
{
m_text1 = Cache.LangProject.TextsOC.Add(new Text());
m_text1.ContentsOA = new StText();
StTxtPara para0 = new StTxtPara();
m_text1.ContentsOA.ParagraphsOS.Append(para0);
//m_text1.ContentsOA.ParagraphsOS.Append(para1);
// 1 2 3 4 5 6
// 0123456789012345678901234567890123456789012345678901234567890123456789
// this is the first paragraph for our constituent chart database tests.
para0.Contents.UnderlyingTsString = m_tsf.MakeString("this is the first paragraph for our constituent chart database tests.",
Cache.DefaultVernWs);
}
}
public void ImportParatextExportBasic()
{
string path = Path.Combine(DirectoryFinder.FwSourceDirectory, @"LexText/Interlinear/ITextDllTests/FlexTextImport");
string file = Path.Combine(path, "FlexTextExportOutput.flextext");
using (var fileStream = new FileStream(file, FileMode.Open, FileAccess.Read))
{
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
var options = new LinguaLinksImport.ImportInterlinearOptions {
Progress = new DummyProgressDlg(),
BirdData = fileStream, AllottedProgress = 0,
CheckAndAddLanguages = DummyCheckAndAddLanguagesInternal
};
bool result = li.ImportInterlinear(options, ref text);
Assert.True(result, "ImportInterlinear was not successful.");
}
}
private void GetTextProps()
{
IStText txt = CmObject.CreateFromDBObject(m_cache, m_hvoRoot) as IStText;
if (txt != null)
{
int hvoOwner = txt.OwnerHVO;
m_text = CmObject.CreateFromDBObject(m_cache, hvoOwner) as FDO.IText;
if (m_text != null)
{
m_tssTextName = m_text.Name.BestVernacularAnalysisAlternative;
m_tssTextAbbreviation = m_text.Abbreviation.BestVernacularAnalysisAlternative;
}
else if (SIL.FieldWorks.FDO.Scripture.Scripture.IsResponsibleFor(txt as SIL.FieldWorks.FDO.Cellar.StText))
{
m_tssTextName = txt.ShortNameTSS;
// sorry, no abbreviation...
}
}
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Executes in two distinct scenarios.
///
/// 1. If disposing is true, the method has been called directly
/// or indirectly by a user's code via the Dispose method.
/// Both managed and unmanaged resources can be disposed.
///
/// 2. If disposing is false, the method has been called by the
/// runtime from inside the finalizer and you should not reference (access)
/// other managed objects, as they already have been garbage collected.
/// Only unmanaged resources can be disposed.
/// </summary>
/// <param name="disposing"></param>
/// <remarks>
/// If any exceptions are thrown, that is fine.
/// If the method is being done in a finalizer, it will be ignored.
/// If it is thrown by client code calling Dispose,
/// it needs to be handled by fixing the bug.
///
/// If subclasses override this method, they should call the base implementation.
/// </remarks>
/// ------------------------------------------------------------------------------------
protected override void Dispose(bool disposing)
{
//Debug.WriteLineIf(!disposing, "****************** " + GetType().Name + " 'disposing' is false. ******************");
// Must not be run more than once.
if (IsDisposed)
return;
if (disposing)
{
// Dispose managed resources here.
if (m_sandbox != null)
m_sandbox.Dispose();
}
// Dispose unmanaged resources here, whether disposing is true or false.
m_text1 = null;
base.Dispose(disposing);
}
private void GetTextProps()
{
IStText txt = CmObject.CreateFromDBObject(m_cache, m_hvoRoot) as IStText;
if (txt != null)
{
int hvoOwner = txt.OwnerHVO;
m_text = CmObject.CreateFromDBObject(m_cache, hvoOwner) as FDO.IText;
if (m_text != null)
{
m_tssTextName = m_text.Name.BestVernacularAnalysisAlternative;
m_tssTextAbbreviation = m_text.Abbreviation.BestVernacularAnalysisAlternative;
}
else if (SIL.FieldWorks.FDO.Scripture.Scripture.IsResponsibleFor(txt as SIL.FieldWorks.FDO.Cellar.StText))
{
m_tssTextName = txt.ShortNameTSS;
// sorry, no abbreviation...
}
}
}
protected override void CreateTestData()
{
m_noun = MakePartOfSpeech("noun");
m_verb = MakePartOfSpeech("verb");
m_adj = MakePartOfSpeech("adj");
IFsFeatureSystem msFeatSys = Cache.LanguageProject.MsFeatureSystemOA;
m_inflType = AddFSType(msFeatSys, "infl",
AddComplexFeature(msFeatSys, "nounAgr", AddClosedFeature(msFeatSys, "num", "sg", "pl")),
AddClosedFeature(msFeatSys, "tense", "pres"));
m_np = Cache.LangProject.GetDefaultTextTagList().ReallyReallyAllPossibilities.Single(poss => poss.Abbreviation.BestAnalysisAlternative.Text == "Noun Phrase");
ILexEntry ni = MakeEntry("ni-", m_verb, "1SgSubj");
ILexEntry him = MakeEntry("him-", m_verb, "3SgObj");
ILexEntry bili = MakeEntry("bili", m_verb, "to see");
ILexEntry ra = MakeEntry("-ra", m_verb, "Pres", new FS {
{ GetFeature("tense"), GetValue("pres") }
});
ILexEntry pus = MakeEntry("pus", m_adj, "green");
ILexEntry yalo = MakeEntry("yalo", m_noun, "mat");
ILexEntry la = MakeEntry("-la", m_noun, "1SgPoss", new FS {
{ GetFeature("nounAgr"), new FS {
{ GetFeature("num"), GetValue("sg") }
} }
});
MakeWordform("nihimbilira", "I see", m_verb, ni, him, bili, ra);
MakeWordform("pus", "green", m_adj, pus);
MakeWordform("yalola", "my mat", m_noun, yalo, la);
MakeWordform("ban", "test", MakePartOfSpeech("pos"));
m_text = MakeText("nihimbilira pus, yalola ban.");
var para = (IStTxtPara)m_text.ContentsOA.ParagraphsOS.First();
MakeTag(m_text, m_np, para.SegmentsOS.First(), 1, para.SegmentsOS.First(), 3);
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
// setup default vernacular ws.
m_wsXkal = Cache.ServiceLocator.WritingSystemManager.Set("qaa-x-kal");
m_wsXkal.DefaultFontName = "Times New Roman";
Cache.ServiceLocator.WritingSystems.VernacularWritingSystems.Add(m_wsXkal);
Cache.ServiceLocator.WritingSystems.CurrentVernacularWritingSystems.Insert(0, m_wsXkal);
m_textsDefn = new XmlDocument();
m_tagRepo = Cache.ServiceLocator.GetInstance <ITextTagRepository>();
ConfigurationFilePath("Language Explorer/Configuration/Words/AreaConfiguration.xml");
m_text1 = LoadTestText("FDO/FDOTests/TestData/ParagraphParserTestTexts.xml", 1, m_textsDefn);
m_para1 = m_text1.ContentsOA.ParagraphsOS[0] as IStTxtPara;
ParseTestText();
m_tagChild = new TestTaggingChild(Cache);
m_tagChild.SetText(m_text1.ContentsOA);
// This could change, but at least it gives a reasonably stable list to test from.
m_textMarkupTags = Cache.LangProject.GetDefaultTextTagList();
LoadTagListPossibilities();
}
public void TestImportCreatesPersonForSpeaker()
{
string xml = "<document><interlinear-text guid=\"AAAAAAAA-AAAA-AAAA-AAAA-AAAAAAAAAAAA\">" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase speaker=\"Jimmy Dorante\" media-file=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" guid=\"BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB\" begin-time-offset=\"1\" end-time-offset=\"2\">" +
"<item type=\"text\">This is a test with text.</item><word>This</word></phrase></phrases></paragraph></paragraphs>" +
"<languages><language lang=\"en\" font=\"latin\" vernacular=\"false\"/></languages>" +
"<media-files offset-type=\"milliseconds\"><media guid=\"FFFFFFFF-FFFF-FFFF-FFFF-FFFFFFFFFFFF\" location=\"file:\\\\test.wav\"/></media-files></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
Assert.AreEqual("Jimmy Dorante",
(Cache.LanguageProject.PeopleOA.PossibilitiesOS[0] as ICmPerson).Name.get_String(Cache.DefaultVernWs).Text,
"Speaker was not created during the import.");
}
}
/// <summary>
/// Do the conversion. The signature of this method is required for use with ProgressDialogWithTask.RunTask,
/// but the parameters and return result are not actually used.
/// </summary>
private object DoConversion(IThreadedProgress dlg, object[] parameters)
{
m_firstNewText = null;
foreach (var path1 in m_fileListBox.Text.Split(new char[] { ',' }, StringSplitOptions.RemoveEmptyEntries))
{
var path = path1.Trim();
if (!File.Exists(path))
{
continue; // report?
}
var input = new ByteReader(path);
var converterStage1 = GetSfmConverter();
var stage1 = converterStage1.Convert(input, m_mappings, m_cache.WritingSystemFactory);
// Skip actual import if SHIFT was held down.
if (secretShiftText.Visible == true)
{
continue;
}
DoStage2Conversion(stage1, dlg);
}
return(null);
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Executes in two distinct scenarios.
///
/// 1. If disposing is true, the method has been called directly
/// or indirectly by a user's code via the Dispose method.
/// Both managed and unmanaged resources can be disposed.
///
/// 2. If disposing is false, the method has been called by the
/// runtime from inside the finalizer and you should not reference (access)
/// other managed objects, as they already have been garbage collected.
/// Only unmanaged resources can be disposed.
/// </summary>
/// <param name="disposing"></param>
/// <remarks>
/// If any exceptions are thrown, that is fine.
/// If the method is being done in a finalizer, it will be ignored.
/// If it is thrown by client code calling Dispose,
/// it needs to be handled by fixing the bug.
///
/// If subclasses override this method, they should call the base implementation.
/// </remarks>
/// ------------------------------------------------------------------------------------
protected override void Dispose(bool disposing)
{
//Debug.WriteLineIf(!disposing, "****************** " + GetType().Name + " 'disposing' is false. ******************");
// Must not be run more than once.
if (IsDisposed)
{
return;
}
if (disposing)
{
// Dispose managed resources here.
if (m_vc != null)
{
m_vc.Dispose();
}
if (m_writer != null)
{
m_writer.Close();
}
if (m_stream != null)
{
m_stream.Close();
}
}
// Dispose unmanaged resources here, whether disposing is true or false.
m_vc = null;
m_textsDefn = null;
m_text1 = null;
m_exportedXml = null;
m_writer = null;
m_exporter = null;
m_choices = null;
m_stream = null;
base.Dispose(disposing);
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Executes in two distinct scenarios.
///
/// 1. If disposing is true, the method has been called directly
/// or indirectly by a user's code via the Dispose method.
/// Both managed and unmanaged resources can be disposed.
///
/// 2. If disposing is false, the method has been called by the
/// runtime from inside the finalizer and you should not reference (access)
/// other managed objects, as they already have been garbage collected.
/// Only unmanaged resources can be disposed.
/// </summary>
/// <param name="disposing"></param>
/// <remarks>
/// If any exceptions are thrown, that is fine.
/// If the method is being done in a finalizer, it will be ignored.
/// If it is thrown by client code calling Dispose,
/// it needs to be handled by fixing the bug.
///
/// If subclasses override this method, they should call the base implementation.
/// </remarks>
/// ------------------------------------------------------------------------------------
protected override void Dispose(bool disposing)
{
//Debug.WriteLineIf(!disposing, "****************** " + GetType().Name + " 'disposing' is false. ******************");
// Must not be run more than once.
if (IsDisposed)
{
return;
}
if (disposing)
{
// Dispose managed resources here.
if (m_sandbox != null)
{
m_sandbox.Dispose();
}
}
// Dispose unmanaged resources here, whether disposing is true or false.
m_text1 = null;
base.Dispose(disposing);
}
public void TestEmptyParagraph()
{
string xml = "<document><interlinear-text>" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph/></paragraphs></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
Assert.True(imported.ContentsOA.ParagraphsOS.Count > 0, "Empty paragraph was not imported as text content.");
var para = imported.ContentsOA[0];
Assert.NotNull(para, "The imported paragraph is null?");
}
}
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
// setup default vernacular ws.
IWritingSystem wsXkal = Cache.ServiceLocator.WritingSystemManager.Set("qaa-x-kal");
wsXkal.DefaultFontName = "Times New Roman";
Cache.ServiceLocator.WritingSystems.VernacularWritingSystems.Add(wsXkal);
Cache.ServiceLocator.WritingSystems.CurrentVernacularWritingSystems.Insert(0, wsXkal);
var textFactory = Cache.ServiceLocator.GetInstance<ITextFactory>();
var stTextFactory = Cache.ServiceLocator.GetInstance<IStTextFactory>();
m_text0 = textFactory.Create();
//Cache.LangProject.TextsOC.Add(m_text0);
m_stText0 = stTextFactory.Create();
m_text0.ContentsOA = m_stText0;
m_para0_0 = m_stText0.AddNewTextPara(null);
m_para0_0.Contents = TsStringUtils.MakeTss("Xxxhope xxxthis xxxwill xxxdo. xxxI xxxhope.", wsXkal.Handle);
InterlinMaster.LoadParagraphAnnotationsAndGenerateEntryGuessesIfNeeded(m_stText0, false);
// paragraph 0_0 simply has wordforms as analyses
foreach (var occurence in SegmentServices.GetAnalysisOccurrences(m_para0_0))
if (occurence.HasWordform)
m_analysis_para0_0.Add(new AnalysisTree(occurence.Analysis));
}
public void TestSpacesBetweenWords()
{
string xml = "<document><interlinear-text>" +
"<item type=\"title\" lang=\"en\">wordspace</item>" +
"<item type=\"title-abbreviation\" lang=\"en\">ws</item>" +
"<paragraphs><paragraph><phrases><phrase>" +
"<item type=\"reference-number\" lang=\"en\">1 Musical</item>" +
"<item type=\"note\" lang=\"pt\">origem: mary poppins</item>" +
"<words><word><item type=\"txt\" lang=\"en\">a</item></word>" +
"<word><item type=\"txt\" lang=\"en\">space</item></word>" +
"<word><item type=\"txt\" lang=\"en\">space</item></word>" +
"</words></phrase></phrases></paragraph></paragraphs></interlinear-text></document>";
LinguaLinksImport li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using (var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text);
using (var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
var para = imported.ContentsOA[0];
var spaceOne = para.Contents.Text.Substring(1, 1); //should be: " "
var wordAfter = para.Contents.Text.Substring(2, 5); //should be: "space"
var spaceTwo = para.Contents.Text.Substring(7, 1); //should be: " "
//test to make sure no space was inserted before the first word.
Assert.IsFalse(" ".Equals(para.Contents.GetSubstring(0, 1)));
//test to make sure spaces were inserted between "a" and "space", and between "space" and "space"
//any extra spaces would result in the "space" word looking like " spac"
Assert.IsTrue(spaceOne.Equals(spaceTwo));
Assert.IsTrue(wordAfter.Equals("space"));
}
}
}
/// <summary>
/// Do the conversion. The signature of this method is required for use with ProgressDialogWithTask.RunTask,
/// but the parameters and return result are not actually used.
/// </summary>
private object DoConversion(IThreadedProgress dlg, object[] parameters)
{
m_firstNewText = null;
foreach (var path1 in InputFiles)
{
var path = path1.Trim();
if (!File.Exists(path))
continue; // report?
var input = new ByteReader(path);
var converterStage1 = GetSfmConverter();
var stage1 = converterStage1.Convert(input, m_mappings, m_cache.WritingSystemFactory);
// Skip actual import if SHIFT was held down.
if (secretShiftText.Visible == true)
continue;
DoStage2Conversion(stage1, dlg);
}
return null;
}
/// <summary>
/// This method will create a new Text document from the given BIRD format Interlineartext.
/// </summary>
/// <param name="newText">The text to populate, could be set to null.</param>
/// <param name="textParams"></param>
private static bool PopulateTextFromBIRDDoc(ref FDO.IText newText, TextCreationParams textParams)
{
s_importOptions = textParams.ImportOptions;
Interlineartext interlinText = textParams.InterlinText;
FdoCache cache = textParams.Cache;
IThreadedProgress progress = textParams.Progress;
if (s_importOptions.CheckAndAddLanguages == null)
{
s_importOptions.CheckAndAddLanguages = CheckAndAddLanguagesInternal;
}
ILgWritingSystemFactory wsFactory = cache.WritingSystemFactory;
char space = ' ';
//handle the languages(writing systems) section alerting the user if new writing systems are encountered
if (!s_importOptions.CheckAndAddLanguages(cache, interlinText, wsFactory, progress))
{
return(false);
}
//handle the header(info or meta) information
SetTextMetaAndMedia(cache, interlinText, wsFactory, newText);
//create all the paragraphs
foreach (var paragraph in interlinText.paragraphs)
{
if (newText.ContentsOA == null)
{
newText.ContentsOA = cache.ServiceLocator.GetInstance <IStTextFactory>().Create();
}
IStTxtPara newTextPara = newText.ContentsOA.AddNewTextPara("");
int offset = 0;
if (paragraph.phrases == null)
{
continue;
}
foreach (var phrase in paragraph.phrases)
{
ICmObject oldSegment = null;
//Try and locate a segment with this Guid.
if (!String.IsNullOrEmpty(phrase.guid))
{
if (cache.ServiceLocator.ObjectRepository.TryGetObject(new Guid(phrase.guid), out oldSegment))
{
//We aren't merging, but we have this guid in our system, ignore the file Guid
oldSegment = cache.ServiceLocator.GetInstance <ISegmentFactory>().Create(newTextPara, offset);
}
else
{
//The segment is identified by a Guid, but apparently we don't have it in our current document, so make one with the guid
oldSegment = cache.ServiceLocator.GetInstance <ISegmentFactory>().Create(newTextPara, offset, cache,
new Guid(phrase.guid));
}
}
//set newSegment to the old, or create a brand new one.
ISegment newSegment = oldSegment as ISegment ?? cache.ServiceLocator.GetInstance <ISegmentFactory>().Create(newTextPara, offset);
var tsStrFactory = cache.ServiceLocator.GetInstance <ITsStrFactory>();
//Fill in the ELAN time information if it is present.
AddELANInfoToSegment(cache, phrase, newSegment);
ITsString phraseText = null;
bool textInFile = false;
//Add all of the data from <item> elements into the segment.
AddSegmentItemData(cache, wsFactory, phrase, newSegment, tsStrFactory, ref textInFile, ref phraseText);
bool lastWasWord = false;
if (phrase.WordsContent != null && phrase.WordsContent.Words != null)
{
if (textParams.Version == 0 && PhraseHasExactlyOneTxtItemNotAKnownWordform(newSegment.Cache, phrase))
{
// It might be a SayMore text that makes the whole segment a single txt item.
// We want to add the text anyway (unless a higher level did so), but we will skip making
// a wordform. Eventual parsing of the text will do so.
if (!textInFile)
{
UpdatePhraseTextForWordItems(wsFactory, tsStrFactory, ref phraseText, phrase.WordsContent.Words[0], ref lastWasWord, space);
}
}
else
{
foreach (var word in phrase.WordsContent.Words)
{
//If the text of the phrase was not given in the document build it from the words.
if (!textInFile)
{
UpdatePhraseTextForWordItems(wsFactory, tsStrFactory, ref phraseText, word, ref lastWasWord, space);
}
AddWordToSegment(newSegment, word, tsStrFactory);
}
}
}
UpdateParagraphTextForPhrase(newTextPara, ref offset, phraseText);
}
}
return(true);
}
private static void SetTextMetaAndMedia(FdoCache cache, Interlineartext interlinText, ILgWritingSystemFactory wsFactory, FDO.IText newText)
{
if (interlinText.Items != null) // apparently it is null if there are no items.
{
foreach (var item in interlinText.Items)
{
switch (item.type)
{
case "title":
newText.Name.set_String(GetWsEngine(wsFactory, item.lang).Handle, item.Value);
break;
case "title-abbreviation":
newText.Abbreviation.set_String(GetWsEngine(wsFactory, item.lang).Handle, item.Value);
break;
case "source":
newText.Source.set_String(GetWsEngine(wsFactory, item.lang).Handle, item.Value);
break;
case "comment":
newText.Description.set_String(GetWsEngine(wsFactory, item.lang).Handle, item.Value);
break;
}
}
}
//handle media files section (ELAN initiated) needs to be processed before the paragraphs as segmenets could reference
//these parts.
if (interlinText.mediafiles != null)
{
var mediaFiles = newText.MediaFilesOA = cache.ServiceLocator.GetInstance <ICmMediaContainerFactory>().Create();
mediaFiles.OffsetType = interlinText.mediafiles.offsetType;
foreach (var mediaFile in interlinText.mediafiles.media)
{
var media = cache.ServiceLocator.GetInstance <ICmMediaURIFactory>().Create(cache, new Guid(mediaFile.guid));
mediaFiles.MediaURIsOC.Add(media);
media.MediaURI = mediaFile.location;
}
}
}
public override void Initialize()
{
CheckDisposed();
base.Initialize();
SetupOldWordformingOverrides();
m_text1 = LoadTestText(@"LexText\Interlinear\ITextDllTests\ParagraphParserTestTexts.xml", 1, m_textsDefn);
}
private static bool MergeTextWithBIRDDoc(ref FDO.IText newText, TextCreationParams textParams)
{
s_importOptions = textParams.ImportOptions;
Interlineartext interlinText = textParams.InterlinText;
FdoCache cache = textParams.Cache;
IThreadedProgress progress = textParams.Progress;
if (s_importOptions.CheckAndAddLanguages == null)
{
s_importOptions.CheckAndAddLanguages = CheckAndAddLanguagesInternal;
}
ILgWritingSystemFactory wsFactory = cache.WritingSystemFactory;
char space = ' ';
//handle the languages(writing systems) section alerting the user if new writing systems are encountered
if (!s_importOptions.CheckAndAddLanguages(cache, interlinText, wsFactory, progress))
{
return(false);
}
//handle the header(info or meta) information as well as any media-files sections
SetTextMetaAndMedia(cache, interlinText, wsFactory, newText);
IStText oldContents = newText.ContentsOA;
IStText newContents = null;
//create all the paragraphs NOTE: Currently the paragraph guids are being ignored, this might be wrong.
foreach (var paragraph in interlinText.paragraphs)
{
if (newContents == null)
{
newContents = cache.ServiceLocator.GetInstance <IStTextFactory>().Create();
newText.ContentsOA = newContents;
}
IStTxtPara newTextPara = newContents.AddNewTextPara("");
int offset = 0;
if (paragraph.phrases == null)
{
continue;
}
foreach (var phrase in paragraph.phrases)
{
ICmObject oldSegment = null;
//Try and locate a segment with this Guid.
if (!String.IsNullOrEmpty(phrase.guid))
{
if (cache.ServiceLocator.ObjectRepository.TryGetObject(new Guid(phrase.guid), out oldSegment))
{
if (oldSegment as ISegment != null) //The segment matches, add it into our paragraph.
{
newTextPara.SegmentsOS.Add(oldSegment as ISegment);
}
else if (oldSegment == null) //The segment is identified by a Guid, but apparently we don't have it in our current document, so make one
{
oldSegment = cache.ServiceLocator.GetInstance <ISegmentFactory>().Create(newTextPara, offset, cache, new Guid(phrase.guid));
}
else //The Guid is in use, but not by a segment. This is bad.
{
return(false);
}
}
}
//set newSegment to the old, or create a brand new one.
ISegment newSegment = oldSegment as ISegment ?? cache.ServiceLocator.GetInstance <ISegmentFactory>().Create(newTextPara, offset);
var tsStrFactory = cache.ServiceLocator.GetInstance <ITsStrFactory>();
//Fill in the ELAN time information if it is present.
AddELANInfoToSegment(cache, phrase, newSegment);
ITsString phraseText = null;
bool textInFile = false;
//Add all of the data from <item> elements into the segment.
AddSegmentItemData(cache, wsFactory, phrase, newSegment, tsStrFactory, ref textInFile, ref phraseText);
bool lastWasWord = false;
if (phrase.WordsContent != null && phrase.WordsContent.Words != null)
{
foreach (var word in phrase.WordsContent.Words)
{
//If the text of the phrase was not found in a "txt" item for this segment then build it from the words.
if (!textInFile)
{
UpdatePhraseTextForWordItems(wsFactory, tsStrFactory, ref phraseText, word, ref lastWasWord, space);
}
MergeWordToSegment(newSegment, word, tsStrFactory);
}
}
UpdateParagraphTextForPhrase(newTextPara, ref offset, phraseText);
}
}
return(true);
}
public override void Exit()
{
CheckDisposed();
// UndoEverything before we clear our wordform table, so we can make sure
// the real wordform list is what we want to start with the next time.
base.Exit();
// clear the wordform table.
m_text1.Cache.LangProject.WordformInventoryOA.ResetAllWordformOccurrences();
m_text1 = null;
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
// setup default vernacular ws.
m_wsXkal = Cache.ServiceLocator.WritingSystemManager.Set("qaa-x-kal");
m_wsXkal.DefaultFontName = "Times New Roman";
Cache.ServiceLocator.WritingSystems.VernacularWritingSystems.Add(m_wsXkal);
Cache.ServiceLocator.WritingSystems.CurrentVernacularWritingSystems.Insert(0, m_wsXkal);
m_textsDefn = new XmlDocument();
m_tagRepo = Cache.ServiceLocator.GetInstance<ITextTagRepository>();
ConfigurationFilePath("Language Explorer/Configuration/Words/AreaConfiguration.xml");
m_text1 = LoadTestText("FDO/FDOTests/TestData/ParagraphParserTestTexts.xml", 1, m_textsDefn);
m_para1 = m_text1.ContentsOA.ParagraphsOS[0] as IStTxtPara;
ParseTestText();
m_tagChild = new TestTaggingChild(Cache);
m_tagChild.SetText(m_text1.ContentsOA);
// This could change, but at least it gives a reasonably stable list to test from.
m_textMarkupTags = Cache.LangProject.GetDefaultTextTagList();
LoadTagListPossibilities();
}
public override void Initialize()
{
CheckDisposed();
base.Initialize();
m_text1 = Cache.LangProject.TextsOC.Add(new Text());
m_text1.ContentsOA = new StText();
m_text1.ContentsOA.ParagraphsOS.Append(new StTxtPara());
(m_text1.ContentsOA.ParagraphsOS[0] as StTxtPara).Contents.UnderlyingTsString =
StringUtils.MakeTss("xxxa xxxb xxxc xxxd xxxe, xxxa xxxb.", Cache.DefaultVernWs);
bool fDidParse;
ParagraphParser.ParseText(m_text1.ContentsOA, new NullProgressState(), out fDidParse);
InterlinLineChoices lineChoices = InterlinLineChoices.DefaultChoices(0, Cache.DefaultAnalWs, Cache.LangProject,
InterlinLineChoices.InterlinMode.GlossAddWordsToLexicon);
m_sandbox = new SandboxForTests(Cache, lineChoices);
}
internal TextBuilder(TextBuilder tbToClone)
: this(tbToClone.m_cache)
{
m_text = tbToClone.m_text;
this.SelectedNode = ParagraphBuilder.Snapshot(tbToClone.SelectedNode);
}
public override void Exit()
{
CheckDisposed();
m_text1 = null;
m_choices = null;
base.Exit();
}
/// ------------------------------------------------------------------------------------
/// <summary>
/// Executes in two distinct scenarios.
///
/// 1. If disposing is true, the method has been called directly
/// or indirectly by a user's code via the Dispose method.
/// Both managed and unmanaged resources can be disposed.
///
/// 2. If disposing is false, the method has been called by the
/// runtime from inside the finalizer and you should not reference (access)
/// other managed objects, as they already have been garbage collected.
/// Only unmanaged resources can be disposed.
/// </summary>
/// <param name="disposing"></param>
/// <remarks>
/// If any exceptions are thrown, that is fine.
/// If the method is being done in a finalizer, it will be ignored.
/// If it is thrown by client code calling Dispose,
/// it needs to be handled by fixing the bug.
///
/// If subclasses override this method, they should call the base implementation.
/// </remarks>
/// ------------------------------------------------------------------------------------
protected override void Dispose(bool disposing)
{
//Debug.WriteLineIf(!disposing, "****************** " + GetType().Name + " 'disposing' is false. ******************");
// Must not be run more than once.
if (IsDisposed)
return;
if (disposing)
{
// Dispose managed resources here.
if (m_vc != null)
m_vc.Dispose();
if (m_writer != null)
m_writer.Close();
if (m_stream != null)
m_stream.Close();
}
// Dispose unmanaged resources here, whether disposing is true or false.
m_vc = null;
m_textsDefn = null;
m_text1 = null;
m_exportedXml = null;
m_writer = null;
m_exporter = null;
m_choices = null;
m_stream = null;
base.Dispose(disposing);
}
public override void Initialize()
{
CheckDisposed();
base.Initialize();
m_text1 = SetupDataForText1();
m_choices = new InterlinLineChoices(0, Cache.DefaultAnalWs, Cache.LangProject);
}
public override void FixtureTeardown()
{
m_textsDefn = null;
m_text1 = null;
base.FixtureTeardown();
}
/// <summary>
/// non-undoable task
/// </summary>
private void DoSetupFixture()
{
// Setup default analysis ws
m_wsEn = Cache.ServiceLocator.WritingSystemManager.Get("en");
// setup default vernacular ws.
m_wsXkal = Cache.ServiceLocator.WritingSystemManager.Set("qaa-x-kal");
m_wsXkal.DefaultFontName = "Times New Roman";
Cache.ServiceLocator.WritingSystems.DefaultVernacularWritingSystem = m_wsXkal;
m_text1 = LoadTestText(
Path.Combine("FDO",
Path.Combine("FDOTests",
Path.Combine("TestData", "ParagraphParserTestTexts.xml"))),
1, m_textsDefn);
// capture text defn state.
m_testFixtureTextsDefn = m_textsDefn;
}
/// <summary>
/// Creates the text to be used by this TextBuilder
/// </summary>
/// <param name="fCreateContents"></param>
/// <returns></returns>
public FDO.IText CreateText(bool fCreateContents)
{
Debug.Assert(m_text == null);
m_text = CreateText();
if (fCreateContents)
CreateContents(m_text);
return m_text;
}
internal FDO.IText BuildText(XmlNode textDefn)
{
if (textDefn.Name != "Text")
return null;
m_textDefn = textDefn;
// 1. Create the new text and give it an owner.
m_text = this.CreateText();
textDefn.Attributes["id"].Value = m_text.Hvo.ToString();
XmlNode name = textDefn.SelectSingleNode("Name5/AUni");
// 2. If we have a name, set it.
if (name != null && name.InnerText.Length > 0)
{
string wsAbbr = XmlUtils.GetOptionalAttributeValue(name, "ws");
int ws = 0;
if (wsAbbr != null)
ws = m_cache.ServiceLocator.WritingSystemManager.GetWsFromStr(wsAbbr);
if (ws == 0)
ws = m_cache.DefaultVernWs;
this.SetName(name.InnerText, ws);
}
// 3. Create a body for the text;
XmlNode contents = textDefn.SelectSingleNode("Contents5054/StText");
if (contents == null)
return m_text;
IStText body = this.CreateContents(m_text);
// 4. Create each paragraph for the text.
XmlNodeList paragraphs = contents.SelectNodes("Paragraphs14/StTxtPara");
if (paragraphs != null)
{
foreach (XmlNode paraDef in paragraphs)
{
ParagraphBuilder pb = new ParagraphBuilder(m_cache, m_text.ContentsOA.ParagraphsOS);
IStTxtPara realPara = pb.BuildParagraphContent(paraDef);
}
}
return m_text;
}
void SetupTexts()
{
// First make a regular text.
using (new UndoRedoTaskHelper(Cache, "ConcordanceControlTests - SetupTexts()", "ConcordanceControlTests - SetupTexts()"))
{
m_text1 = Cache.LangProject.TextsOC.Add(new Text());
m_text1.ContentsOA = new StText();
StTxtPara para0 = new StTxtPara();
StTxtPara para1 = new StTxtPara();
m_text1.ContentsOA.ParagraphsOS.Append(para0);
m_text1.ContentsOA.ParagraphsOS.Append(para1);
ITsStrFactory tsf = TsStrFactoryClass.Create();
// 1 2 3 4 5 6
// 0123456789012345678901234567890123456789012345678901234567890123456789
// XXXXsecrecyZZZ; XXXsentenceZZZ!!
// XXXlocoZZZ, XXXsegmentZZZ?? ZZZamazingXXX wonderfulXXXzzzcounselor!!
para0.Contents.UnderlyingTsString = tsf.MakeString("XXXXsecrecyZZZ; XXXsentenceZZZ!!", Cache.DefaultVernWs);
para1.Contents.UnderlyingTsString = tsf.MakeString("XXXlocoZZZ, XXXsegmentZZZ?? ZZZamazingXXX wonderfulXXXzzzcounselor!!", Cache.DefaultVernWs);
// add scripture
m_newBook1 = new ScrBook();
Cache.LangProject.TranslatedScriptureOA.ScriptureBooksOS.Append(m_newBook1);
m_newBook1.TitleOA = new StText();
m_newBook1.TitleOA.ParagraphsOS.Append(new StTxtPara());
(m_newBook1.TitleOA.ParagraphsOS[0] as StTxtPara).Contents.UnderlyingTsString = tsf.MakeString("XXXnewBook1zzz.Title", Cache.DefaultVernWs);
IScrSection newSection1_0 = m_newBook1.SectionsOS.Append(new ScrSection());
newSection1_0.ContentOA = new StText();
StTxtPara paraSection1_0 = new StTxtPara();
(newSection1_0.ContentOA as StText).ParagraphsOS.Append(paraSection1_0);
paraSection1_0.Contents.UnderlyingTsString = tsf.MakeString("ZZZnewBook1.Section0.Introduction1XXX", Cache.DefaultVernWs);
IScrSection newSection1_1 = m_newBook1.SectionsOS.Append(new ScrSection());
newSection1_1.ContentOA = new StText();
StTxtPara paraSection1_1 = new StTxtPara();
(newSection1_1.ContentOA as StText).ParagraphsOS.Append(paraSection1_1);
paraSection1_1.Contents.UnderlyingTsString = tsf.MakeString("XXXnewBook1.Section1.1:1-1:20ZZZ", Cache.DefaultVernWs);
// section.VerseRefEnd = book.CanonicalNum * 1000000 + 1 * 1000 + (introSection ? 0 : 1);
newSection1_1.VerseRefEnd = 70 * 1000000 + 1 * 1000 + 1;
// setup some basic analyses for the texts.
string formLexEntry = "XXXlexEntry1";
ITsString tssLexEntryForm = StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs);
int clsidForm;
StringUtils.ReassignTss(ref tssLexEntryForm, StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs));
ILexEntry lexEntry1_Entry = LexEntry.CreateEntry(Cache,
MoMorphType.FindMorphType(Cache, new MoMorphTypeCollection(Cache), ref formLexEntry, out clsidForm), tssLexEntryForm,
"XXXlexEntry1.sense1", null);
ILexSense lexEntry1_Sense1 = lexEntry1_Entry.SensesOS[0];
ILexSense lexEntry1_Sense2 = LexSense.CreateSense(lexEntry1_Entry, null, "XXXlexEntry1.sense2");
ParagraphAnnotator tapara0 = new ParagraphAnnotator(para0);
ParagraphAnnotator tapara1 = new ParagraphAnnotator(para1);
ParagraphAnnotator taSection1_0 = new ParagraphAnnotator(paraSection1_0);
ParagraphAnnotator taSection1_1 = new ParagraphAnnotator(paraSection1_1);
// currently setup mono-morphemic search
ArrayList morphForms = new ArrayList();
formLexEntry = "XXXXsecrecyZZZ";
StringUtils.ReassignTss(ref tssLexEntryForm, StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs));
ILexEntry lexEntry2_Entry = LexEntry.CreateEntry(Cache,
MoMorphType.FindMorphType(Cache, new MoMorphTypeCollection(Cache), ref formLexEntry, out clsidForm), tssLexEntryForm,
"XXXlexEntry2.sense1", null);
morphForms.Add(lexEntry2_Entry.LexemeFormOA);
IWfiAnalysis wfiAnalysis = tapara0.BreakIntoMorphs(0, 0, morphForms);
m_wfXXXXsecrecyZZZ = (wfiAnalysis as WfiAnalysis).Owner as IWfiWordform;
ILexSense lexEntry2_Sense1 = lexEntry2_Entry.SensesOS[0];
tapara0.SetMorphSense(0, 0, 0, lexEntry2_Sense1);
formLexEntry = "XXXsegmentZZZ";
StringUtils.ReassignTss(ref tssLexEntryForm, StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs));
ILexEntry lexEntry3_Entry = LexEntry.CreateEntry(Cache,
MoMorphType.FindMorphType(Cache, new MoMorphTypeCollection(Cache), ref formLexEntry, out clsidForm), tssLexEntryForm,
"XXXlexEntry3.sense1", null);
morphForms[0] = lexEntry3_Entry.LexemeFormOA;
tapara1.BreakIntoMorphs(0, 2, morphForms);
ILexSense lexEntry3_Sense1 = lexEntry3_Entry.SensesOS[0];
tapara1.SetMorphSense(0, 2, 0, lexEntry3_Sense1);
formLexEntry = "ZZZamazingXXX";
StringUtils.ReassignTss(ref tssLexEntryForm, StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs));
ILexEntry lexEntry4_Entry = LexEntry.CreateEntry(Cache,
MoMorphType.FindMorphType(Cache, new MoMorphTypeCollection(Cache), ref formLexEntry, out clsidForm), tssLexEntryForm,
"XXXlexEntry4.sense1", null);
morphForms[0] = lexEntry4_Entry.LexemeFormOA;
tapara1.BreakIntoMorphs(1, 0, morphForms);
ILexSense lexEntry4_Sense1 = lexEntry4_Entry.SensesOS[0];
tapara1.SetMorphSense(1, 0, 0, lexEntry4_Sense1);
//XXXlocoZZZ
morphForms[0] = "XXXlocoZZZ";
tapara1.BreakIntoMorphs(0, 0, morphForms);
tapara1.SetMorphSense(0, 0, 0, lexEntry1_Sense2);
formLexEntry = paraSection1_0.Contents.Text;
StringUtils.ReassignTss(ref tssLexEntryForm, StringUtils.MakeTss(formLexEntry, Cache.DefaultVernWs));
ILexEntry lexEntry5_Entry = LexEntry.CreateEntry(Cache,
MoMorphType.FindMorphType(Cache, new MoMorphTypeCollection(Cache), ref formLexEntry, out clsidForm), tssLexEntryForm,
"XXXlexEntry5.sense1", null);
morphForms[0] = lexEntry5_Entry.LexemeFormOA;
taSection1_0.BreakIntoMorphs(0, 0, morphForms);
ILexSense lexEntry5_Sense1 = lexEntry5_Entry.SensesOS[0];
taSection1_0.SetMorphSense(0, 0, 0, lexEntry5_Sense1);
morphForms[0] = paraSection1_1.Contents.Text;
taSection1_1.BreakIntoMorphs(0, 0, morphForms); // won't match on LexEntry
taSection1_1.SetMorphSense(0, 0, 0, lexEntry1_Sense2); // will match on LexGloss
string gloss;
tapara0.SetDefaultWordGloss(0, 0, out gloss);
tapara1.SetDefaultWordGloss(0, 2, out gloss);
tapara1.SetDefaultWordGloss(1, 0, out gloss);
taSection1_1.SetDefaultWordGloss(0, 0, out gloss);
StTxtPara.TwficInfo infoCba0_0_0 = new StTxtPara.TwficInfo(Cache, tapara0.GetSegmentForm(0, 0));
StTxtPara.TwficInfo infoCba1_0_2 = new StTxtPara.TwficInfo(Cache, tapara1.GetSegmentForm(0, 2));
StTxtPara.TwficInfo infoCbaScr_0_0 = new StTxtPara.TwficInfo(Cache, taSection1_1.GetSegmentForm(0, 0));
int segDefn_literalTranslation = Cache.GetIdFromGuid(LangProject.kguidAnnLiteralTranslation);
int segDefn_freeTranslation = Cache.GetIdFromGuid(LangProject.kguidAnnFreeTranslation);
int segDefn_note = Cache.GetIdFromGuid(LangProject.kguidAnnNote);
BaseFreeformAdder ffAdder = new BaseFreeformAdder(Cache);
ICmIndirectAnnotation freeTrans0 = ffAdder.AddFreeformAnnotation(infoCba0_0_0.SegmentHvo, segDefn_freeTranslation);
freeTrans0.Comment.SetAlternative("Para0.Segment0: XXXFreeform translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation literalTrans0 = ffAdder.AddFreeformAnnotation(infoCba0_0_0.SegmentHvo, segDefn_literalTranslation);
literalTrans0.Comment.SetAlternative("Para0.Segment0: XXXLiteral translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation note0 = ffAdder.AddFreeformAnnotation(infoCba0_0_0.SegmentHvo, segDefn_note);
note0.Comment.SetAlternative("Para0.Segment0: XXXNote.", Cache.DefaultAnalWs);
ICmIndirectAnnotation freeTrans1 = ffAdder.AddFreeformAnnotation(infoCba1_0_2.SegmentHvo, segDefn_freeTranslation);
freeTrans1.Comment.SetAlternative("Para1.Segment0: XXXFreeform translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation literalTrans1 = ffAdder.AddFreeformAnnotation(infoCba1_0_2.SegmentHvo, segDefn_literalTranslation);
literalTrans1.Comment.SetAlternative("Para1.Segment0: XXXLiteral translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation note1 = ffAdder.AddFreeformAnnotation(infoCba1_0_2.SegmentHvo, segDefn_note);
note1.Comment.SetAlternative("Para1.Segment0: XXXNote.", Cache.DefaultAnalWs);
// Scripture
ICmIndirectAnnotation freeTransScr1 = ffAdder.AddFreeformAnnotation(infoCbaScr_0_0.SegmentHvo, segDefn_freeTranslation);
freeTransScr1.Comment.SetAlternative("Scr1.Para0.Segment0: XXXFreeform translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation literalTransScr1 = ffAdder.AddFreeformAnnotation(infoCbaScr_0_0.SegmentHvo, segDefn_literalTranslation);
literalTransScr1.Comment.SetAlternative("Scr1.Para0.Segment0: XXXLiteral translation.", Cache.DefaultAnalWs);
ICmIndirectAnnotation noteScr1 = ffAdder.AddFreeformAnnotation(infoCbaScr_0_0.SegmentHvo, segDefn_note);
noteScr1.Comment.SetAlternative("Scr1.Para0.Segment0: XXXNote.", Cache.DefaultAnalWs);
}
}
/// <summary>
/// Import a file which looks like a FieldWorks interlinear XML export.
/// </summary>
/// <param name="dlg"></param>
/// <param name="parameters"></param>
/// <returns></returns>
public object ImportInterlinear(IThreadedProgress dlg, object[] parameters)
{
bool retValue = false;
Debug.Assert(parameters.Length == 1);
using (var stream = new FileStream((string) parameters[0], FileMode.Open, FileAccess.Read))
{
FDO.IText firstNewText = null;
retValue = ImportInterlinear(dlg, stream, 100, ref firstNewText);
FirstNewText = firstNewText;
}
return retValue;
}
