/// <summary>
/// Reads the data. (allows faster custom serialization for better performance in TraceLab)
/// </summary>
/// <param name="reader">The reader.</param>
public void ReadData(System.IO.BinaryReader reader)
{
int dataversion = reader.ReadInt32();
if (dataversion != version)
{
throw new InvalidOperationException("Binary reader did not correct version data. Data corrupted. Potentially IRawSerializable not implemented correctly");
}
else
{
int termsCount = reader.ReadInt32();
//create new collections
m_terms = new Dictionary <string, TLTermEntry>();
m_termEntries = new TermEntryCollection();
for (int i = 0; i < termsCount; ++i)
{
TLTermEntry termEntry = new TLTermEntry();
termEntry.ReadData(reader);
AddTermEntry(termEntry);
}
int vectorLenghtsOfArtifactsCount = reader.ReadInt32();
m_vectorLengthsOfArtifacts = new Dictionary <string, double>();
for (int i = 0; i < vectorLenghtsOfArtifactsCount; ++i)
{
string artifactId = reader.ReadString();
double weight = reader.ReadDouble();
m_vectorLengthsOfArtifacts.Add(artifactId, weight);
}
}
}
/// <summary>
/// Generates an object from its XML representation.
/// </summary>
/// <param name="reader">The XmlReader stream from which the object is deserialized. </param>
public void ReadXml(System.Xml.XmlReader reader)
{
bool wasEmpty = reader.IsEmptyElement;
if (wasEmpty)
{
return;
}
version = int.Parse(reader.GetAttribute("Version"));
reader.Read();
reader.Read();
while (reader.NodeType != System.Xml.XmlNodeType.EndElement)
{
TLTermEntry termEntry = new TLTermEntry();
termEntry.ReadXml(reader);
AddTermEntry(termEntry);
}
reader.Read();
reader.Read();
while (reader.NodeType != System.Xml.XmlNodeType.EndElement)
{
string artifactId = reader.GetAttribute("artifactId");
double vectorLength = double.Parse(reader.GetAttribute("vectorLength"));
SetDocumentVectorWeight(artifactId, vectorLength);
reader.Read();
}
}
/// <summary>
/// Allows to add a new term entry to the dictionary index.
/// </summary>
/// <param name="termEntry">term entry to be added</param>
private void AddTermEntry(TLTermEntry termEntry)
{
if (Terms.ContainsKey(termEntry.Term))
{
throw new ArgumentException("The dictionary already contains that term");
}
Terms.Add(termEntry.Term, termEntry);
m_termEntries.Add(termEntry);
}
/// <summary>
/// Allows to add the new term entry to the dictionary index.
/// </summary>
/// <param name="term">term word</param>
/// <param name="numberOfArtifactsContainingTerm">number of all artifacts of each text contain given term</param>
/// <param name="totalFrequencyAcrossAllArtifacts">total frequency across all artifacts</param>
/// <param name="weight">weight for the given term</param>
/// <returns>just created term entry</returns>
public TLTermEntry AddTermEntry(string term, int numberOfArtifactsContainingTerm, int totalFrequencyAcrossAllArtifacts, double weight)
{
// Integrity checks
if (Terms.ContainsKey(term))
{
throw new ArgumentException("The dictionary already contains that term");
}
TLTermEntry termEntry = new TLTermEntry(term, numberOfArtifactsContainingTerm, totalFrequencyAcrossAllArtifacts, weight);
Terms.Add(term, termEntry);
m_termEntries.Add(termEntry);
return(termEntry);
}
/// <summary>
/// Reads the data. (allows faster custom serialization for better performance in TraceLab)
/// </summary>
/// <param name="reader">The reader.</param>
public void ReadData(System.IO.BinaryReader reader)
{
int dataversion = reader.ReadInt32();
if (dataversion != version)
{
throw new InvalidOperationException("Binary reader did not correct version data. Data corrupted. Potentially IRawSerializable not implemented correctly");
}
else
{
int termsCount = reader.ReadInt32();
//create new collections
m_terms = new Dictionary<string, TLTermEntry>();
m_termEntries = new TermEntryCollection();
for (int i = 0; i < termsCount; ++i)
{
TLTermEntry termEntry = new TLTermEntry();
termEntry.ReadData(reader);
AddTermEntry(termEntry);
}
int vectorLenghtsOfArtifactsCount = reader.ReadInt32();
m_vectorLengthsOfArtifacts = new Dictionary<string, double>();
for (int i = 0; i < vectorLenghtsOfArtifactsCount; ++i)
{
string artifactId = reader.ReadString();
double weight = reader.ReadDouble();
m_vectorLengthsOfArtifacts.Add(artifactId, weight);
}
}
}
/// <summary>
/// Generates an object from its XML representation.
/// </summary>
/// <param name="reader">The XmlReader stream from which the object is deserialized. </param>
public void ReadXml(System.Xml.XmlReader reader)
{
bool wasEmpty = reader.IsEmptyElement;
if (wasEmpty)
return;
version = int.Parse(reader.GetAttribute("Version"));
reader.Read();
reader.Read();
while (reader.NodeType != System.Xml.XmlNodeType.EndElement)
{
TLTermEntry termEntry = new TLTermEntry();
termEntry.ReadXml(reader);
AddTermEntry(termEntry);
}
reader.Read();
reader.Read();
while (reader.NodeType != System.Xml.XmlNodeType.EndElement)
{
string artifactId = reader.GetAttribute("artifactId");
double vectorLength = double.Parse(reader.GetAttribute("vectorLength"));
SetDocumentVectorWeight(artifactId, vectorLength);
reader.Read();
}
}
/// <summary>
/// Allows to add a new term entry to the dictionary index.
/// </summary>
/// <param name="termEntry">term entry to be added</param>
private void AddTermEntry(TLTermEntry termEntry)
{
if (Terms.ContainsKey(termEntry.Term))
throw new ArgumentException("The dictionary already contains that term");
Terms.Add(termEntry.Term, termEntry);
m_termEntries.Add(termEntry);
}
/// <summary>
/// Allows to add the new term entry to the dictionary index.
/// </summary>
/// <param name="term">term word</param>
/// <param name="numberOfArtifactsContainingTerm">number of all artifacts of each text contain given term</param>
/// <param name="totalFrequencyAcrossAllArtifacts">total frequency across all artifacts</param>
/// <param name="weight">weight for the given term</param>
/// <returns>just created term entry</returns>
public TLTermEntry AddTermEntry(string term, int numberOfArtifactsContainingTerm, int totalFrequencyAcrossAllArtifacts, double weight)
{
// Integrity checks
if (Terms.ContainsKey(term))
throw new ArgumentException("The dictionary already contains that term");
TLTermEntry termEntry = new TLTermEntry(term, numberOfArtifactsContainingTerm, totalFrequencyAcrossAllArtifacts, weight);
Terms.Add(term, termEntry);
m_termEntries.Add(termEntry);
return termEntry;
}
/// <summary>
/// Compares two specified TLTermEntry objects and returns an integer that indicates their relative position in the sort order.
/// </summary>
/// <param name="x">The first TLTermEntry to compare. </param>
/// <param name="y">The second TLTermEntry to compare. </param>
/// <returns>A 32-bit signed integer that indicates the lexical relationship between the two comparands.</returns>
public int Compare(TLTermEntry x, TLTermEntry y)
{
return ((new CaseInsensitiveComparer()).Compare(x.Term, y.Term));
}
/// <summary>
/// Compares two specified TLTermEntry objects and returns an integer that indicates their relative position in the sort order.
/// </summary>
/// <param name="x">The first TLTermEntry to compare. </param>
/// <param name="y">The second TLTermEntry to compare. </param>
/// <returns>A 32-bit signed integer that indicates the lexical relationship between the two comparands.</returns>
public int Compare(TLTermEntry x, TLTermEntry y)
{
return((new CaseInsensitiveComparer()).Compare(x.Term, y.Term));
}