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 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));
}
}
}
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 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 });
}
}
}
protected virtual void DoStage2Conversion(byte[] stage1, IThreadedProgress dlg)
{
using (var stage2Input = new MemoryStream(stage1))
{
var stage2Converter = new LinguaLinksImport(m_cache, null, null);
// Until we have a better idea, assume we're half done with the import when we've produced the intermediate.
// Allocate 5 progress units to the ImportInterlinear, in case it can do better resolution.
// Enhance JohnT: we could divide the progress up based on the lengths of the files,
// and possibly converter.Convert could move the bar along based on how far through the file it is.
// ImportInterlinear could do something similar. However, procesing a single file is so quick
// that this very crude approximation is good enough.
dlg.Position += 50;
stage2Converter.ImportInterlinear(dlg, stage2Input, 50, ref m_firstNewText);
}
}
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.");
}
}
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.");
}
}
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?");
}
}
}
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"));
}
}
}
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.");
}
}
public void TestImportFullELANData()
{
const 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.AreEqual(new Guid("BBBBBBBB-BBBB-BBBB-BBBB-BBBBBBBBBBBB"), para.SegmentsOS[0].Guid, "Segment guid not maintained on import.");
VerifyMediaLink(imported);
}
}
}
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?");
}
}
}
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 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"));
}
}
}
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 });
}
}
}
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));
}
}
}
public void UglyEmptyDataShouldNotCrash()
{
const string textGuid = "eb0770f4-23aa-4f7b-b45d-fe745a3790a2";
//an interliner text example xml string
const string xml = "<document><interlinear-text guid='" + textGuid + "'>" +
"<paragraphs><paragraph guid='819742f3-3840-479e-9300-51755880680b'/></paragraphs><languages/>" +
"</interlinear-text></document>";
var li = new LinguaLinksImport(Cache, null, null);
FDO.IText text = null;
using(var stream = new MemoryStream(Encoding.ASCII.GetBytes(xml.ToCharArray())))
{
Assert.DoesNotThrow(()=> li.ImportInterlinear(new DummyProgressDlg(), stream, 0, ref text));
using(var firstEntry = Cache.LanguageProject.Texts.GetEnumerator())
{
firstEntry.MoveNext();
var imported = firstEntry.Current;
//The empty ugly text imported as its empty ugly self
Assert.AreEqual(imported.Guid.ToString(), textGuid);
}
}
}
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.");
}
}
protected virtual void DoStage2Conversion(byte[] stage1, IThreadedProgress dlg)
{
using (var stage2Input = new MemoryStream(stage1))
{
var stage2Converter = new LinguaLinksImport(m_cache, null, null);
// Until we have a better idea, assume we're half done with the import when we've produced the intermediate.
// Allocate 5 progress units to the ImportInterlinear, in case it can do better resolution.
// Enhance JohnT: we could divide the progress up based on the lengths of the files,
// and possibly converter.Convert could move the bar along based on how far through the file it is.
// ImportInterlinear could do something similar. However, procesing a single file is so quick
// that this very crude approximation is good enough.
dlg.Position += 50;
stage2Converter.ImportInterlinear(dlg, stage2Input, 50, ref m_firstNewText);
}
}
public void ImportParatextExportBasic()
{
string path = Path.Combine(FwDirectoryFinder.SourceDirectory, @"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.");
}
}