public void UnorderedListWithMultipleItemsWithoutFormattingIsTransformedIntoGroupWithManyUnits()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<unit id=""u1"" name=""original"">
<segment>
<source><![CDATA[<ul><li>Hello Word1!</li><li>Hello Word2!</li><li>Hello Word3!</li></ul>]]></source>
</segment>
</unit>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter();
var newDocument = splitter.ExecuteExtraction(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var group = newDocument.Files[0].Containers[0] as Group;
Assert.IsNotNull(group);
Assert.AreEqual("u1-g", group.Id);
Assert.AreEqual("original", group.Name);
Assert.AreEqual(1, group.Containers.Count);
var ulGroup = group.Containers[0] as Group;
Assert.AreEqual("ul", ulGroup.Name);
Assert.AreEqual(3, ulGroup.Containers.Count);
var unit1 = ulGroup.Containers[0] as Unit;
var textUnit1 = unit1.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("li", unit1.Name);
Assert.AreEqual("Hello Word1!", textUnit1);
var unit2 = ulGroup.Containers[1] as Unit;
var textUnit2 = unit2.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("li", unit2.Name);
Assert.AreEqual("Hello Word2!", textUnit2);
var unit3 = ulGroup.Containers[2] as Unit;
var textUnit3 = unit3.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("li", unit3.Name);
Assert.AreEqual("Hello Word3!", textUnit3);
}
public void OrderedListAsChildWithTwoItemIsWrappedInUL()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" trgLang=""it-IT"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<group id=""u1-g"" name=""original"">
<unit id=""u1-1"" name=""p"" >
<segment>
<source>whatever</source>
<target>whatever</target>
</segment>
</unit>
<group id=""u1-2-g"" name=""ul"" >
<unit id= ""u1-2-1"" name=""li"">
<segment>
<source>Item 1</source>
<target>Item 1</target>
</segment>
</unit>
<unit id= ""u1-2-2"" name=""li"" >
<segment>
<source>Item 1</source>
<target>Item 1</target>
</segment>
</unit>
</group>
</group>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter();
var newDocument = splitter.ExecuteMerge(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var unit = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit);
Assert.AreEqual("u1", unit.Id);
Assert.AreEqual("original", unit.Name);
Assert.AreEqual(1, unit.Resources[0].Target.Text.Count);
var text = unit.Resources[0].Target.Text[0] as CDataTag;
Assert.IsNotNull(text);
Assert.AreEqual("<p>whatever</p><ul><li>Item 1</li><li>Item 1</li></ul>", text.Text);
}
public void MultipleParagraphsUnitIsTransformedIntoGroupWithManyUnits()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<unit id=""u1"">
<segment>
<source><![CDATA[<p>Hello Word1!</p><p>Hello Word2!</p><p>Hello <b>Word3</b>!</p>]]></source>
</segment>
</unit>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter(_htmlParser);
var newDocument = splitter.ExecuteExtraction(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var group = newDocument.Files[0].Containers[0] as Group;
Assert.IsNotNull(group);
Assert.AreEqual("u1-g", group.Id);
Assert.AreEqual(3, group.Containers.Count);
var unit1 = group.Containers[0] as Unit;
var textUnit1 = unit1.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("html:p", unit1.Type);
Assert.AreEqual("Hello Word1!", textUnit1);
var unit2 = group.Containers[1] as Unit;
var textUnit2 = unit2.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("html:p", unit2.Type);
Assert.AreEqual("Hello Word2!", textUnit2);
var unit3 = group.Containers[2] as Unit;
var textUnit3 = unit3.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("html:p", unit3.Type);
Assert.AreEqual("<![CDATA[Hello <b>Word3</b>!]]>", textUnit3);
}
public void OneGroupWithMultipleParagraphWithNotFormattingCDataAreMergedBackIntoOneUnit()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" trgLang=""it-IT"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<group id=""u1-g"" name=""original"">
<unit id=""u1-1"" name=""p"">
<segment>
<source>Hello Word1!</source>
<target>Hello Word1!</target>
</segment>
</unit>
<unit id=""u1-2"" name=""p"">
<segment>
<source>Hello Word2!</source>
<target>Hello Word2!</target>
</segment>
</unit>
<unit id=""u1-3"" name=""p"">
<segment>
<source>Hello Word3!</source>
<target>Hello Word3!</target>
</segment>
</unit>
</group>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter();
var newDocument = splitter.ExecuteMerge(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var unit = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit);
Assert.AreEqual("u1", unit.Id);
Assert.AreEqual("original", unit.Name);
Assert.AreEqual(1, unit.Resources[0].Target.Text.Count);
var cdata = unit.Resources[0].Target.Text[0] as CDataTag;
Assert.IsNotNull(cdata);
Assert.AreEqual("<p>Hello Word1!</p><p>Hello Word2!</p><p>Hello Word3!</p>", cdata.Text);
}
public void OneGroupMultipleParagraphPlainTextAreMergedBackIntoOneUnit()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" trgLang=""it-IT"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<group id=""u1-g"" name=""original"">
<unit id=""u1-1"">
<segment>
<source>Hello Word1!</source>
<target>Hello Word1!</target>
</segment>
</unit>
<unit id=""u1-2"">
<segment>
<source>Hello Word2!</source>
<target>Hello Word2!</target>
</segment>
</unit>
<unit id=""u1-3"">
<segment>
<source>Hello Word3!</source>
<target>Hello Word3!</target>
</segment>
</unit>
</group>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter(_htmlParser);
var newDocument = splitter.ExecuteMerge(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var unit = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit);
Assert.AreEqual("u1", unit.Id);
Assert.AreEqual("original", unit.Name);
Assert.AreEqual(1, unit.Resources[0].Target.Text.Count);
var text = unit.Resources[0].Target.Text[0] as PlainText;
Assert.IsNotNull(text);
Assert.AreEqual("Hello Word1!" + Environment.NewLine + "Hello Word2!" + Environment.NewLine + "Hello Word3!", text.Text);
}
public void MulipleParagraphPlainTextUnitIsSplit()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<unit id=""u1"" name=""originaParagraph"">
<segment>
<source>Hello Word1!
Hello Word2!
Hello Word3!</source>
</segment>
</unit>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter(_htmlParser);
var newDocument = splitter.ExecuteExtraction(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var group = newDocument.Files[0].Containers[0] as Group;
Assert.IsNotNull(group);
Assert.AreEqual("u1-g", group.Id);
Assert.AreEqual("originaParagraph", group.Name);
Assert.AreEqual(3, group.Containers.Count);
var unit1 = group.Containers[0] as Unit;
var textUnit1 = unit1.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("Hello Word1!", textUnit1);
var unit2 = group.Containers[1] as Unit;
var textUnit2 = unit2.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("Hello Word2!", textUnit2);
var unit3 = group.Containers[2] as Unit;
var textUnit3 = unit3.Resources[0].Source.Text[0].ToString();
Assert.AreEqual("Hello Word3!", textUnit3);
}
public void ClassAttributeInsideNestedHtmlElementIsReadFromXliff()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff xmlns:mda=""urn:oasis:names:tc:xliff:metadata:2.0"" srcLang=""en-GB"" trgLang=""it-IT"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<group id=""u1-g"" name=""original"">
<group id=""u1-1-g"" type=""html:ul"">
<unit id=""u1-1-1"" type=""html:li"">
<mda:metadata>
<mda:metaGroup id=""originalAttributes"">
<mda:meta type=""class"">even</mda:meta>
</mda:metaGroup>
</mda:metadata>
<segment>
<source>Hello Word1!</source>
<target>Hello Word1!</target>
</segment>
</unit>
</group>
</group>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter(_htmlParser);
var newDocument = splitter.ExecuteMerge(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var unit = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit);
Assert.AreEqual("u1", unit.Id);
Assert.AreEqual("original", unit.Name);
Assert.AreEqual(1, unit.Resources[0].Target.Text.Count);
var text = unit.Resources[0].Target.Text[0] as CDataTag;
Assert.IsNotNull(text);
Assert.AreEqual("<ul><li class=\"even\">Hello Word1!</li></ul>", text.Text);
}
public void SingleParagraphPlainTextUnitIsNotSplit()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<unit id=""u1"">
<segment>
<source>Hello Word!</source>
</segment>
</unit>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter(_htmlParser);
var newDocument = splitter.ExecuteExtraction(document);
Assert.AreEqual(1, newDocument.Files[0].Containers.Count);
var unit = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit);
}
public void TwoGroupsWithMultipleParagraphCDataAreMergedBackIntoOneUnit()
{
var xliff = @"<?xml version=""1.0"" encoding=""utf-8""?>
<xliff srcLang=""en-GB"" trgLang=""it-IT"" version=""2.0"" xmlns=""urn:oasis:names:tc:xliff:document:2.0"">
<file id=""f1"">
<group id=""u1-g"" name=""original1"">
<unit id=""u1-1"" name=""p"">
<segment>
<source>Hello Word1!</source>
<target>Hello Word1!</target>
</segment>
</unit>
<unit id=""u1-2"" name=""p"">
<segment>
<source>Hello Word2!</source>
<target>Hello Word2!</target>
</segment>
</unit>
<unit id=""u1-3"" name=""p"">
<segment>
<source><![CDATA[Hello <b>Word3</b>!]]></source>
<target><![CDATA[Hello <b>Word3</b>!]]></target>
</segment>
</unit>
</group>
<group id=""u2-g"" name=""original2"">
<unit id=""u2-1"" name=""p"">
<segment>
<source>Hello2 Word1!</source>
<target>Hello2 Word1!</target>
</segment>
</unit>
<unit id=""u2-2"" name=""p"">
<segment>
<source>Hello2 Word2!</source>
<target>Hello2 Word2!</target>
</segment>
</unit>
<unit id=""u2-3"" name=""p"">
<segment>
<source><![CDATA[Hello2 <b>Word3</b>!]]></source>
<target><![CDATA[Hello2 <b>Word3</b>!]]></target>
</segment>
</unit>
</group>
</file>
</xliff>";
XliffDocument document = LoadXliff(xliff);
var splitter = new ParagraphSplitter();
var newDocument = splitter.ExecuteMerge(document);
Assert.AreEqual(2, newDocument.Files[0].Containers.Count);
var unit1 = newDocument.Files[0].Containers[0] as Unit;
Assert.IsNotNull(unit1);
Assert.AreEqual("u1", unit1.Id);
Assert.AreEqual("original1", unit1.Name);
var unit2 = newDocument.Files[0].Containers[1] as Unit;
Assert.IsNotNull(unit2);
Assert.AreEqual("u2", unit2.Id);
Assert.AreEqual("original2", unit2.Name);
var cdata1 = unit1.Resources[0].Target.Text[0] as CDataTag;
Assert.IsNotNull(cdata1);
Assert.AreEqual("<p>Hello Word1!</p><p>Hello Word2!</p><p>Hello <b>Word3</b>!</p>", cdata1.Text);
var cdata2 = unit2.Resources[0].Target.Text[0] as CDataTag;
Assert.IsNotNull(cdata2);
Assert.AreEqual("<p>Hello2 Word1!</p><p>Hello2 Word2!</p><p>Hello2 <b>Word3</b>!</p>", cdata2.Text);
}
private static void ProcessParserModelParagraphs(SimpleParserViewModel parse)
{
Dialect dialect = BindDialect(parse);
ParagraphSplitter ps = new ParagraphSplitter(dialect);
StringBuilder normalizedSb = new StringBuilder();
StringBuilder spitBackSb = new StringBuilder();
StringBuilder bracketSb = new StringBuilder();
StringBuilder posSb = new StringBuilder();
StringBuilder glossSb = new StringBuilder();
StringBuilder errors = new StringBuilder();
StringBuilder colorized = new StringBuilder();
HtmlFormatter hf = new HtmlFormatter();
Prose prose;
try
{
prose = ps.ParseProse(parse.SourceText);
}
catch (Exception ex)
{
//We CAN'T.
ProcessParserModelSentences(parse);
return;
}
foreach (Paragraph paragraph in prose.Paragraphs)
{
//////// TP
try
{
spitBackSb.AppendLine(paragraph.ToString("g", dialect).ToHtml() + "<br/>");
}
catch (Exception ex)
{
string error = "[[CANNOT REPEAT BACK: " + ex.Message + "]]";
spitBackSb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
//spitBackSb.AppendLine(hf.BoldTheWords(paragraph.ToHtml()) + "<br/>");
//UpdateErrors(errors, error, sentence);
}
try
{
//string result = parsedSentence.ToString("html", dialect);
//if (result.Replace("<span", "").Contains("<"))
//{
// throw new InvalidOperationException("No HTML allowed in input");
//}
colorized.AppendLine(paragraph.ToString("html", dialect) + "<br/>");
}
catch (Exception ex)
{
string error = "[[CANNOT COLORIZE: " + ex.Message + "]]";
spitBackSb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
//spitBackSb.AppendLine(hf.BoldTheWords(sentence.ToHtml()) + "<br/>");
//
//UpdateErrors(errors, error, sentence);
}
//////// TP
try
{
bracketSb.AppendLine(hf.BoldTheWords(paragraph.ToString("b", dialect).ToHtml()) + "<br/>");
}
catch (Exception ex)
{
string error = "[[CANNOT BRACKET: " + ex.Message + "]]";
bracketSb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
//bracketSb.AppendLine(hf.BoldTheWords(sentence.ToHtml()) + "<br/>");
//UpdateErrors(errors, error, sentence);
}
//////// ENGLISH
try
{
dialect.TargetGloss = "en";
GlossMaker gm = new GlossMaker();
string glossed = gm.GlossParagraph(paragraph, dialect);
glossSb.AppendLine(glossed.ToHtml() + "<br/>");
glossed = gm.GlossParagraph(paragraph, dialect, true);
posSb.AppendLine(glossed.ToHtml() + "<br/>"); //bs doesn't do anything.
}
catch (Exception ex)
{
string error = "[[CANNOT GLOSS: " + ex.Message.ToHtml() + "]]";
glossSb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
//glossSb.AppendLine(hf.BoldTheWords(sentence.ToHtml()) + "<br/>");
posSb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
//posSb.AppendLine(hf.BoldTheWords(sentence.ToHtml()) + "<br/>");
//UpdateErrors(errors, error, sentence);
}
//}
//catch (Exception ex)
//{
// string error = "[[CANNOT Parse: " + ex.Message.ToHtml() + "]]";
// foreach (StringBuilder sb in new StringBuilder[] { //normalizedSb,
// spitBackSb, bracketSb, posSb, glossSb, colorized })
// {
// sb.AppendLine(hf.BoldTheWords(error.ToHtml()) + "<br/>");
// sb.Append(sentence.ToHtml() + "<br/>");
// }
// UpdateErrors(errors, error, sentence);
//}
//finally
//{
// dialect.TargetGloss = "tp";
//}
}
parse.Normalized = normalizedSb.ToString();
parse.Recovered = spitBackSb.ToString();
parse.Formatted = bracketSb.ToString();
parse.FormattedPos = hf.SubThePartsOfSpeech(posSb.ToString());
parse.Glossed = glossSb.ToString();
parse.Colorized = colorized.ToString();
parse.Errors = errors.ToString();
}
