static CSLNameComponents SplitToWordsCommas(List<WordToken> tokens, int[] commaIndexes)
{
var result = new CSLNameComponents();
var familyNameTokens = new List<WordToken>();
var givenNameTokens = new List<WordToken>();
var droppingParticleNameTokens = new List<WordToken>();
// Find the last comma
var commaIndex = commaIndexes[commaIndexes.Length - 1];
// Everything after the (last) comma goes to given name
tokens.RemoveAt(commaIndex);
givenNameTokens.AddRange(ExtractTokenRange(tokens, commaIndex));
// Check if multiple commas are present
if (commaIndex != commaIndexes[0])
{
// Remove the first comma
commaIndex = commaIndexes[0];
tokens.RemoveAt(commaIndex);
// Extract following tokens (removing any extra commas)
var tokensBetweenCommas = ExtractTokenRange(tokens, commaIndex);
tokensBetweenCommas.RemoveAll(token => token.IsComma);
// Add to the dropping-particle
droppingParticleNameTokens.AddRange(tokensBetweenCommas);
}
if (tokens.Count > 0)
{
// The last word before the (first) comma goes to family name
familyNameTokens.Add(ExtractToken(tokens, tokens.Count - 1));
int firstLowerCaseIndex;
int lowerCaseSequenceCount;
FindLowerCaseTokenRange(tokens, out firstLowerCaseIndex, out lowerCaseSequenceCount);
// Did we find any?
if (lowerCaseSequenceCount > 0)
{
// Yes, so extract everything from the start (not the first lower-case token!)
// to the last lower-case as dropping particles
droppingParticleNameTokens.InsertRange(0, ExtractTokenRange(tokens, 0, firstLowerCaseIndex + lowerCaseSequenceCount));
}
// Anything else goes into family
if (tokens.Count > 0)
{
familyNameTokens.InsertRange(0, tokens);
}
}
if (familyNameTokens.Count > 0) result.Family = JoinTokens(familyNameTokens);
if (givenNameTokens.Count > 0) result.Given = JoinTokens(givenNameTokens);
if (droppingParticleNameTokens.Count > 0) result.DroppingParticle = JoinTokens(droppingParticleNameTokens);
return result;
}
static CSLNameComponents SplitToWordsNoCommas(List <WordToken> tokens)
{
var result = new CSLNameComponents();
var familyNameTokens = new List <WordToken>();
var givenNameTokens = new List <WordToken>();
var droppingParticleNameTokens = new List <WordToken>();
// Always at least a family name
familyNameTokens.Add(ExtractToken(tokens, tokens.Count - 1));
// Do we have any remaining tokens?
if (tokens.Count != 0)
{
// Yes, so find the range of the tokens which are lower-cased
int firstLowerCaseIndex;
int lowerCaseSequenceCount;
FindLowerCaseTokenRange(tokens, out firstLowerCaseIndex, out lowerCaseSequenceCount);
// Did we find any?
if (lowerCaseSequenceCount > 0)
{
// Yes, so extract them as dropping particles
droppingParticleNameTokens.AddRange(ExtractTokenRange(tokens, firstLowerCaseIndex, lowerCaseSequenceCount));
// Were there any word tokens after this section?
if (tokens.Count - firstLowerCaseIndex > 0)
{
// Yes, so they are inserted before the family name
familyNameTokens.InsertRange(0, ExtractTokenRange(tokens, firstLowerCaseIndex, tokens.Count - firstLowerCaseIndex));
}
}
// Given is anything left
result.Given = JoinTokens(tokens);
}
if (familyNameTokens.Count > 0)
{
result.Family = JoinTokens(familyNameTokens);
}
if (givenNameTokens.Count > 0)
{
result.Given = JoinTokens(givenNameTokens);
}
if (droppingParticleNameTokens.Count > 0)
{
result.DroppingParticle = JoinTokens(droppingParticleNameTokens);
}
return(result);
}
static void Check(CSLNameComponents nameComponents,
string expectedFamily = null,
string expectedGiven = null,
string expectedDroppingParticle = null,
string expectedNonDroppingParticle = null,
string expectedSuffix = null,
bool? expectedCommaSuffix = null,
bool? expectedStaticOrdering = null )
{
if (expectedFamily != null)
{
Assert.AreEqual(expectedFamily, nameComponents.Family, "Family");
}
if (expectedGiven != null)
{
Assert.AreEqual(expectedGiven, nameComponents.Given, "Given");
}
if (expectedDroppingParticle != null)
{
Assert.AreEqual(expectedDroppingParticle, nameComponents.DroppingParticle, "Dropping Particle");
}
if (expectedNonDroppingParticle != null)
{
Assert.AreEqual(expectedNonDroppingParticle, nameComponents.NonDroppingParticle, "Non-Dropping Particle");
}
if (expectedSuffix != null)
{
Assert.AreEqual(expectedSuffix, nameComponents.Suffix, "Suffix");
}
if (expectedCommaSuffix != null)
{
Assert.AreEqual(expectedCommaSuffix, nameComponents.CommaSuffix, "Comma-Suffix");
}
if (expectedStaticOrdering != null)
{
Assert.AreEqual(expectedStaticOrdering, nameComponents.StaticOrdering, "Static-Ordering");
}
}
static CSLNameComponents SplitToWordsNoCommas(List<WordToken> tokens)
{
var result = new CSLNameComponents();
var familyNameTokens = new List<WordToken>();
var givenNameTokens = new List<WordToken>();
var droppingParticleNameTokens = new List<WordToken>();
// Always at least a family name
familyNameTokens.Add(ExtractToken(tokens, tokens.Count - 1));
// Do we have any remaining tokens?
if (tokens.Count != 0)
{
// Yes, so find the range of the tokens which are lower-cased
int firstLowerCaseIndex;
int lowerCaseSequenceCount;
FindLowerCaseTokenRange(tokens, out firstLowerCaseIndex, out lowerCaseSequenceCount);
// Did we find any?
if (lowerCaseSequenceCount > 0)
{
// Yes, so extract them as dropping particles
droppingParticleNameTokens.AddRange(ExtractTokenRange(tokens, firstLowerCaseIndex, lowerCaseSequenceCount));
// Were there any word tokens after this section?
if (tokens.Count - firstLowerCaseIndex > 0)
{
// Yes, so they are inserted before the family name
familyNameTokens.InsertRange(0, ExtractTokenRange(tokens, firstLowerCaseIndex, tokens.Count - firstLowerCaseIndex));
}
}
// Given is anything left
result.Given = JoinTokens(tokens);
}
if (familyNameTokens.Count > 0) result.Family = JoinTokens(familyNameTokens);
if (givenNameTokens.Count > 0) result.Given = JoinTokens(givenNameTokens);
if (droppingParticleNameTokens.Count > 0) result.DroppingParticle = JoinTokens(droppingParticleNameTokens);
return result;
}
static CSLNameComponents SplitToWordsCommas(List <WordToken> tokens, int[] commaIndexes)
{
var result = new CSLNameComponents();
var familyNameTokens = new List <WordToken>();
var givenNameTokens = new List <WordToken>();
var droppingParticleNameTokens = new List <WordToken>();
// Find the last comma
var commaIndex = commaIndexes[commaIndexes.Length - 1];
// Everything after the (last) comma goes to given name
tokens.RemoveAt(commaIndex);
givenNameTokens.AddRange(ExtractTokenRange(tokens, commaIndex));
// Check if multiple commas are present
if (commaIndex != commaIndexes[0])
{
// Remove the first comma
commaIndex = commaIndexes[0];
tokens.RemoveAt(commaIndex);
// Extract following tokens (removing any extra commas)
var tokensBetweenCommas = ExtractTokenRange(tokens, commaIndex);
tokensBetweenCommas.RemoveAll(token => token.IsComma);
// Add to the dropping-particle
droppingParticleNameTokens.AddRange(tokensBetweenCommas);
}
if (tokens.Count > 0)
{
// The last word before the (first) comma goes to family name
familyNameTokens.Add(ExtractToken(tokens, tokens.Count - 1));
int firstLowerCaseIndex;
int lowerCaseSequenceCount;
FindLowerCaseTokenRange(tokens, out firstLowerCaseIndex, out lowerCaseSequenceCount);
// Did we find any?
if (lowerCaseSequenceCount > 0)
{
// Yes, so extract everything from the start (not the first lower-case token!)
// to the last lower-case as dropping particles
droppingParticleNameTokens.InsertRange(0, ExtractTokenRange(tokens, 0, firstLowerCaseIndex + lowerCaseSequenceCount));
}
// Anything else goes into family
if (tokens.Count > 0)
{
familyNameTokens.InsertRange(0, tokens);
}
}
if (familyNameTokens.Count > 0)
{
result.Family = JoinTokens(familyNameTokens);
}
if (givenNameTokens.Count > 0)
{
result.Given = JoinTokens(givenNameTokens);
}
if (droppingParticleNameTokens.Count > 0)
{
result.DroppingParticle = JoinTokens(droppingParticleNameTokens);
}
return(result);
}
