/// <summary> Split up a string containing options into an array of strings,
/// one for each option.
///
/// </summary>
/// <param name="optionString">the string containing the options
/// </param>
/// <returns> the array of options
/// </returns>
public static System.String[] splitOptions(System.String quotedOptionString)
{
FastVector optionsVec = new FastVector();
System.String str = new System.Text.StringBuilder(quotedOptionString).ToString();
int i;
while (true)
{
//trimLeft
i = 0;
while ((i < str.Length) && (System.Char.IsWhiteSpace(str[i])))
i++;
str = str.Substring(i);
//stop when str is empty
if (str.Length == 0)
break;
//if str start with a double quote
if (str[0] == '"')
{
//find the first not anti-slached double quote
i = 1;
while (i < str.Length)
{
if (str[i] == str[0])
break;
if (str[i] == '\\')
{
i += 1;
if (i >= str.Length)
throw new System.Exception("String should not finish with \\");
if (str[i] != '\\' && str[i] != '"')
throw new System.Exception("Unknow character \\" + str[i]);
}
i += 1;
}
if (i >= str.Length)
throw new System.Exception("Quote parse error.");
//add the founded string to the option vector (without quotes)
System.String optStr = str.Substring(1, (i) - (1));
optStr = unbackQuoteChars(optStr);
optionsVec.addElement(optStr);
str = str.Substring(i + 1);
}
else
{
//find first whiteSpace
i = 0;
while ((i < str.Length) && (!System.Char.IsWhiteSpace(str[i])))
i++;
//add the founded string to the option vector
System.String optStr = str.Substring(0, (i) - (0));
optionsVec.addElement(optStr);
str = str.Substring(i);
}
}
//convert optionsVec to an array of String
System.String[] options = new System.String[optionsVec.size()];
for (i = 0; i < optionsVec.size(); i++)
{
options[i] = ((System.String) optionsVec.elementAt(i));
}
return options;
}
/// <summary> Constructor for nominal attributes and string attributes, where
/// metadata is supplied. If a null vector of attribute values is passed
/// to the method, the attribute is assumed to be a string.
///
/// </summary>
/// <param name="attributeName">the name for the attribute
/// </param>
/// <param name="attributeValues">a vector of strings denoting the
/// attribute values. Null if the attribute is a string attribute.
/// </param>
/// <param name="metadata">the attribute's properties
/// </param>
//@ requires attributeName != null;
//@ requires metadata != null;
/*@ ensures m_Name == attributeName;
ensures m_Index == -1;
ensures attributeValues == null && m_Type == STRING
|| attributeValues != null && m_Type == NOMINAL
&& m_Values.size() == attributeValues.size();
signals (IllegalArgumentException ex)
(* if duplicate strings in attributeValues *);
*/
public Attribute(System.String attributeName, FastVector attributeValues, ProtectedProperties metadata)
{
m_Name = attributeName;
m_Index = - 1;
if (attributeValues == null)
{
m_Values = new FastVector();
m_Hashtable = System.Collections.Hashtable.Synchronized(new System.Collections.Hashtable());
m_Type = STRING;
}
else
{
m_Values = new FastVector(attributeValues.size());
//m_Hashtable = System.Collections.Hashtable.Synchronized(new System.Collections.Hashtable(attributeValues.size()));
m_Hashtable = new System.Collections.Hashtable(attributeValues.size());
for (int i = 0; i < attributeValues.size(); i++)
{
// No serialization
System.Object store = attributeValues.elementAt(i);
//if (((System.String) store).Length > STRING_COMPRESS_THRESHOLD)
//{
// try
// {
// store = new SerializedObject(attributeValues.elementAt(i), true);
// }
// catch (System.Exception ex)
// {
// System.Console.Error.WriteLine("Couldn't compress nominal attribute value -" + " storing uncompressed.");
// }
//}
if (m_Hashtable.ContainsKey(store))
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Object.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
throw new System.ArgumentException("A nominal attribute (" + attributeName + ") cannot" + " have duplicate labels (" + store + ").");
}
m_Values.addElement(store);
m_Hashtable.Add(store, (System.Int32) i);
}
m_Type = NOMINAL;
}
setMetadata(metadata);
}
private Instance createSingleWhyInstance(FastVector fvWhy, Token candidate)
{
//first word-n attribute number
int wordsBeforeFirstAttributeNumber = 7;
//first pos-n attribute number
int posBeforeFirstAttributeNumber = wordsBeforeFirstAttributeNumber + whyWordsBefore + whyWordsAfter;
//word+1 attribute number
int wordsAfterFirstAttributeNumber = wordsBeforeFirstAttributeNumber + whyWordsBefore;
//pos+1 attribute number
int posAfterFirstAttributeNumber = posBeforeFirstAttributeNumber + whyWordsBefore;
int totalAttributeCount = wordsBeforeFirstAttributeNumber + whyWordsBefore * 2 + whyWordsAfter * 2 + 1;
Instance whyCandidate = new DenseInstance(totalAttributeCount);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(0), candidate.Value);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(1), candidate.Value.Split(' ').Count());
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(2), candidate.Sentence);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(3), candidate.Score);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(4), candidate.NumWho);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(5), candidate.NumWhen);
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(6), candidate.NumWhere);
for (int i = whyWordsBefore; i > 0; i--)
{
if (candidate.Position - i - 1 >= 0)
{
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(whyWordsBefore - i + wordsBeforeFirstAttributeNumber), articleCurrent[candidate.Position - i - 1].Value);
if (articleCurrent[candidate.Position - i - 1].PartOfSpeech != null)
{
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(whyWordsBefore - i + posBeforeFirstAttributeNumber), articleCurrent[candidate.Position - i - 1].PartOfSpeech);
}
}
}
for (int i = 0; i < whyWordsAfter; i++)
{
if (candidate.Position + i < articleCurrent.Count)
{
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(wordsAfterFirstAttributeNumber + i), articleCurrent[candidate.Position + i].Value);
if (articleCurrent[candidate.Position + i].PartOfSpeech != null)
{
whyCandidate.setValue((weka.core.Attribute)fvWhy.elementAt(posAfterFirstAttributeNumber + i), articleCurrent[candidate.Position + i].PartOfSpeech);
}
}
}
return whyCandidate;
}
/// <summary> Sets a value of a nominal attribute or string attribute.
/// Creates a fresh list of attribute values before it is set.
///
/// </summary>
/// <param name="index">the value's index
/// </param>
/// <param name="string">the value
/// </param>
/// <exception cref="IllegalArgumentException">if the attribute is not nominal or
/// string.
/// </exception>
//@ requires string != null;
//@ requires isNominal() || isString();
//@ requires 0 <= index && index < m_Values.size();
internal void setValue(int index, System.String string_Renamed)
{
switch (m_Type)
{
case NOMINAL:
case STRING:
m_Values = (FastVector) m_Values.copy();
m_Hashtable = (System.Collections.Hashtable) m_Hashtable.Clone();
System.Object store = string_Renamed;
if (string_Renamed.Length > STRING_COMPRESS_THRESHOLD)
{
try
{
store = string_Renamed;
}
catch (System.Exception ex)
{
System.Console.Error.WriteLine("Couldn't compress string attribute value -" + " storing uncompressed." + " " + ex.ToString());
}
}
m_Hashtable.Remove(m_Values.elementAt(index));
m_Values.setXmlElementAt(store, index);
m_Hashtable.Add(store, (System.Int32) index);
break;
default:
throw new System.ArgumentException("Can only set values for nominal" + " or string attributes!");
}
}
private Instance createSingleWhoInstance(FastVector fvWho, Token candidate)
{
//first word-n attribute number
int wordsBeforeFirstAttributeNumber = 6;
//first pos-n attribute number
int posBeforeFirstAttributeNumber = wordsBeforeFirstAttributeNumber + whoWordsBefore + whoWordsAfter;
//word+1 attribute number
int wordsAfterFirstAttributeNumber = wordsBeforeFirstAttributeNumber + whoWordsBefore;
//pos+1 attribute number
int posAfterFirstAttributeNumber = posBeforeFirstAttributeNumber + whoWordsBefore;
int totalAttributeCount = wordsBeforeFirstAttributeNumber + whoWordsBefore * 2 + whoWordsAfter * 2 + 1;
Instance whoCandidate = new DenseInstance(totalAttributeCount);
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(0), candidate.Value);
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(1), candidate.Value.Split(' ').Count());
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(2), candidate.Sentence);
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(3), candidate.Position);
double sentenceStartProximity = -1;
foreach (List<Token> tokenList in segregatedArticleCurrent)
{
if (tokenList.Count > 0 && tokenList[0].Sentence == candidate.Sentence)
{
sentenceStartProximity = (double)(candidate.Position - tokenList[0].Position) / (double)tokenList.Count;
break;
}
}
if (sentenceStartProximity > -1)
{
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(4), sentenceStartProximity);
}
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(5), candidate.Frequency);
for (int i = whoWordsBefore; i > 0; i--)
{
if (candidate.Position - i - 1 >= 0)
{
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(whoWordsBefore - i + wordsBeforeFirstAttributeNumber), articleCurrent[candidate.Position - i - 1].Value);
if (articleCurrent[candidate.Position - i - 1].PartOfSpeech != null)
{
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(whoWordsBefore - i + posBeforeFirstAttributeNumber), articleCurrent[candidate.Position - i - 1].PartOfSpeech);
}
}
}
for (int i = 0; i < whoWordsAfter; i++)
{
if (candidate.Position + i < articleCurrent.Count)
{
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(wordsAfterFirstAttributeNumber + i), articleCurrent[candidate.Position + i].Value);
if (articleCurrent[candidate.Position + i].PartOfSpeech != null)
{
whoCandidate.setValue((weka.core.Attribute)fvWho.elementAt(posAfterFirstAttributeNumber + i), articleCurrent[candidate.Position + i].PartOfSpeech);
}
}
}
return whoCandidate;
}
