public void ParseCharacterSequences_Diacritics()
{
// Arabic letter alef with madda above
// Arabic letter yeh with hamza above and immediately followed by a character without
// diacritics (Arabic letter zain)
string charsWithDiacritics = "\u0627\u0653 \u064A\u0654\u0632";
// set up for this test.
m_dataSource.m_tokens.Add(new DummyTextToken(charsWithDiacritics,
TextType.Verse, true, false, "Paragraph"));
m_check = new CharactersCheck(m_dataSource);
ReflectionHelper.SetField(m_check, "m_categorizer", m_dataSource.CharacterCategorizer);
// Get the parsed character sequences.
List <string> parsedChars = new List <string>();
foreach (string character in ((CharactersCheck)m_check).ParseCharacterSequences(charsWithDiacritics))
{
parsedChars.Add(character);
}
// Confirm that we have four characters with the expected contents.
Assert.AreEqual(4, parsedChars.Count, "We expected four characters");
Assert.AreEqual("\u0627\u0653", parsedChars[0]);
Assert.AreEqual(" ", parsedChars[1]);
Assert.AreEqual("\u064A\u0654", parsedChars[2]);
Assert.AreEqual("\u0632", parsedChars[3]);
}
void Test(string[] result, string text, string desiredKey)
{
m_UsfmDataSource.Text = text;
CharactersCheck check = new CharactersCheck(m_UsfmDataSource);
List <TextTokenSubstring> tts =
check.GetReferences(m_UsfmDataSource.TextTokens(), desiredKey);
Assert.AreEqual(result.GetUpperBound(0) + 1, tts.Count,
"A different number of results was returned than what was expected.");
for (int i = 0; i <= result.GetUpperBound(0); ++i)
{
Assert.AreEqual(result[i], tts[i].InventoryText, "Result number: " + i.ToString());
}
}
public override void TestSetup()
{
base.TestSetup();
m_dataSource = new TestChecksDataSource();
m_check = new CharactersCheck(m_dataSource);
}
public override void TestSetup()
{
base.TestSetup();
m_dataSource = new TestChecksDataSource();
m_check = new CharactersCheck(m_dataSource);
}
void Test(string[] result, string text, string desiredKey)
{
m_UsfmDataSource.Text = text;
CharactersCheck check = new CharactersCheck(m_UsfmDataSource);
List<TextTokenSubstring> tts =
check.GetReferences(m_UsfmDataSource.TextTokens(), desiredKey);
Assert.AreEqual(result.GetUpperBound(0)+1, tts.Count,
"A different number of results was returned than what was expected." );
for (int i = 0; i <= result.GetUpperBound(0); ++i)
Assert.AreEqual(result[i], tts[i].InventoryText, "Result number: " + i.ToString());
}
public void ParseCharacterSequences_Diacritics()
{
// Arabic letter alef with madda above
// Arabic letter yeh with hamza above and immediately followed by a character without
// diacritics (Arabic letter zain)
string charsWithDiacritics = "\u0627\u0653 \u064A\u0654\u0632";
// set up for this test.
m_dataSource.m_tokens.Add(new DummyTextToken(charsWithDiacritics,
TextType.Verse, true, false, "Paragraph"));
m_check = new CharactersCheck(m_dataSource);
ReflectionHelper.SetField(m_check, "m_categorizer", m_dataSource.CharacterCategorizer);
// Get the parsed character sequences.
List<string> parsedChars = new List<string>();
foreach (string character in ((CharactersCheck)m_check).ParseCharacterSequences(charsWithDiacritics))
parsedChars.Add(character);
// Confirm that we have four characters with the expected contents.
Assert.AreEqual(4, parsedChars.Count, "We expected four characters");
Assert.AreEqual("\u0627\u0653", parsedChars[0]);
Assert.AreEqual(" ", parsedChars[1]);
Assert.AreEqual("\u064A\u0654", parsedChars[2]);
Assert.AreEqual("\u0632", parsedChars[3]);
}
