public override System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
if (tokenGroup.GetTotalScore() == 0)
return originalText;
float score = tokenGroup.GetTotalScore();
if (score == 0)
{
return originalText;
}
// try to size sb correctly
System.Text.StringBuilder sb = new System.Text.StringBuilder(originalText.Length + EXTRA);
sb.Append("<span style=\"");
if (highlightForeground)
{
sb.Append("color: ");
sb.Append(GetForegroundColorString(score));
sb.Append("; ");
}
if (highlightBackground)
{
sb.Append("background: ");
sb.Append(GetBackgroundColorString(score));
sb.Append("; ");
}
sb.Append("\">");
sb.Append(originalText);
sb.Append("</span>");
return sb.ToString();
}
public override System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
if (tokenGroup.GetTotalScore() == 0)
{
return(originalText);
}
float score = tokenGroup.GetTotalScore();
if (score == 0)
{
return(originalText);
}
// try to size sb correctly
System.Text.StringBuilder sb = new System.Text.StringBuilder(originalText.Length + EXTRA);
sb.Append("<span style=\"");
if (highlightForeground)
{
sb.Append("color: ");
sb.Append(GetForegroundColorString(score));
sb.Append("; ");
}
if (highlightBackground)
{
sb.Append("background: ");
sb.Append(GetBackgroundColorString(score));
sb.Append("; ");
}
sb.Append("\">");
sb.Append(originalText);
sb.Append("</span>");
return(sb.ToString());
}
public virtual System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
if (tokenGroup.GetTotalScore() == 0)
{
return(originalText);
}
float score = tokenGroup.GetTotalScore();
if (score == 0)
{
return(originalText);
}
System.Text.StringBuilder sb = new System.Text.StringBuilder();
sb.Append("<font ");
if (highlightForeground)
{
sb.Append("color=\"");
sb.Append(GetForegroundColorString(score));
sb.Append("\" ");
}
if (highlightBackground)
{
sb.Append("bgcolor=\"");
sb.Append(GetBackgroundColorString(score));
sb.Append("\" ");
}
sb.Append(">");
sb.Append(originalText);
sb.Append("</font>");
return(sb.ToString());
}
/* (non-Javadoc)
* @see Lucene.Net.Highlight.Formatter#highlightTerm(java.lang.String, Lucene.Net.Highlight.TokenGroup)
*/
public virtual System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
System.Text.StringBuilder returnBuffer;
if (tokenGroup.GetTotalScore() > 0)
{
returnBuffer = new System.Text.StringBuilder();
returnBuffer.Append(preTag);
returnBuffer.Append(originalText);
returnBuffer.Append(postTag);
return(returnBuffer.ToString());
}
return(originalText);
}
/* (non-Javadoc)
* @see Lucene.Net.Highlight.Formatter#highlightTerm(java.lang.String, Lucene.Net.Highlight.TokenGroup)
*/
public virtual System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
System.Text.StringBuilder returnBuffer;
if (tokenGroup.GetTotalScore() > 0)
{
returnBuffer = new System.Text.StringBuilder();
returnBuffer.Append(preTag);
returnBuffer.Append(originalText);
returnBuffer.Append(postTag);
return returnBuffer.ToString();
}
return originalText;
}
/// <summary> Low level api to get the most relevant (formatted) sections of the document.
/// This method has been made public to allow visibility of score information held in TextFragment objects.
/// Thanks to Jason Calabrese for help in redefining the interface.
/// </summary>
/// <param name="">tokenStream
/// </param>
/// <param name="">text
/// </param>
/// <param name="">maxNumFragments
/// </param>
/// <param name="">mergeContiguousFragments
/// </param>
/// <throws> IOException </throws>
public TextFragment[] GetBestTextFragments(TokenStream tokenStream, System.String text, bool mergeContiguousFragments, int maxNumFragments)
{
System.Collections.ArrayList docFrags = new System.Collections.ArrayList();
System.Text.StringBuilder newText = new System.Text.StringBuilder();
TextFragment currentFrag = new TextFragment(newText, newText.Length, docFrags.Count);
fragmentScorer.StartFragment(currentFrag);
docFrags.Add(currentFrag);
FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);
try
{
Lucene.Net.Analysis.Token token;
System.String tokenText;
int startOffset;
int endOffset;
int lastEndOffset = 0;
textFragmenter.Start(text);
TokenGroup tokenGroup = new TokenGroup();
token = tokenStream.Next();
while ((token != null) && (token.StartOffset() < maxDocBytesToAnalyze))
{
if ((tokenGroup.numTokens > 0) && (tokenGroup.IsDistinct(token)))
{
//the current token is distinct from previous tokens -
// markup the cached token group info
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;
tokenText = text.Substring(startOffset, (endOffset) - (startOffset));
System.String markedUpText = formatter.HighlightTerm(encoder.EncodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset, (startOffset) - (lastEndOffset))));
newText.Append(markedUpText);
lastEndOffset = System.Math.Max(endOffset, lastEndOffset);
tokenGroup.Clear();
//check if current token marks the start of a new fragment
if (textFragmenter.IsNewFragment(token))
{
currentFrag.SetScore(fragmentScorer.GetFragmentScore());
//record stats for a new fragment
currentFrag.textEndPos = newText.Length;
currentFrag = new TextFragment(newText, newText.Length, docFrags.Count);
fragmentScorer.StartFragment(currentFrag);
docFrags.Add(currentFrag);
}
}
tokenGroup.AddToken(token, fragmentScorer.GetTokenScore(token));
// if(lastEndOffset>maxDocBytesToAnalyze)
// {
// break;
// }
token = tokenStream.Next();
}
currentFrag.SetScore(fragmentScorer.GetFragmentScore());
if (tokenGroup.numTokens > 0)
{
//flush the accumulated text (same code as in above loop)
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;
tokenText = text.Substring(startOffset, (endOffset) - (startOffset));
System.String markedUpText = formatter.HighlightTerm(encoder.EncodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset, (startOffset) - (lastEndOffset))));
newText.Append(markedUpText);
lastEndOffset = System.Math.Max(lastEndOffset, endOffset);
}
//Test what remains of the original text beyond the point where we stopped analyzing
if ((lastEndOffset < text.Length) && (text.Length < maxDocBytesToAnalyze))
{
//append it to the last fragment
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset)));
}
currentFrag.textEndPos = newText.Length;
//sort the most relevant sections of the text
for (System.Collections.IEnumerator i = docFrags.GetEnumerator(); i.MoveNext(); )
{
currentFrag = (TextFragment) i.Current;
//If you are running with a version of Lucene before 11th Sept 03
// you do not have PriorityQueue.insert() - so uncomment the code below
/*
if (currentFrag.getScore() >= minScore)
{
fragQueue.put(currentFrag);
if (fragQueue.size() > maxNumFragments)
{ // if hit queue overfull
fragQueue.pop(); // remove lowest in hit queue
minScore = ((TextFragment) fragQueue.top()).getScore(); // reset minScore
}
}
*/
//The above code caused a problem as a result of Christoph Goller's 11th Sept 03
//fix to PriorityQueue. The correct method to use here is the new "insert" method
// USE ABOVE CODE IF THIS DOES NOT COMPILE!
fragQueue.Insert(currentFrag);
}
//return the most relevant fragments
TextFragment[] frag = new TextFragment[fragQueue.Size()];
for (int i = frag.Length - 1; i >= 0; i--)
{
frag[i] = (TextFragment) fragQueue.Pop();
}
//merge any contiguous fragments to improve readability
if (mergeContiguousFragments)
{
MergeContiguousFragments(frag);
System.Collections.ArrayList fragTexts = new System.Collections.ArrayList();
for (int i = 0; i < frag.Length; i++)
{
if ((frag[i] != null) && (frag[i].GetScore() > 0))
{
fragTexts.Add(frag[i]);
}
}
frag = (TextFragment[]) fragTexts.ToArray(typeof(TextFragment));
}
return frag;
}
finally
{
if (tokenStream != null)
{
try
{
tokenStream.Close();
}
catch (System.Exception e)
{
}
}
}
}
public virtual System.String HighlightTerm(System.String originalText, TokenGroup tokenGroup)
{
if (tokenGroup.GetTotalScore() == 0)
return originalText;
float score = tokenGroup.GetTotalScore();
if (score == 0)
{
return originalText;
}
System.Text.StringBuilder sb = new System.Text.StringBuilder();
sb.Append("<font ");
if (highlightForeground)
{
sb.Append("color=\"");
sb.Append(GetForegroundColorString(score));
sb.Append("\" ");
}
if (highlightBackground)
{
sb.Append("bgcolor=\"");
sb.Append(GetBackgroundColorString(score));
sb.Append("\" ");
}
sb.Append(">");
sb.Append(originalText);
sb.Append("</font>");
return sb.ToString();
}
/// <summary> Low level api to get the most relevant (formatted) sections of the document.
/// This method has been made public to allow visibility of score information held in TextFragment objects.
/// Thanks to Jason Calabrese for help in redefining the interface.
/// </summary>
/// <param name="">tokenStream
/// </param>
/// <param name="">text
/// </param>
/// <param name="">maxNumFragments
/// </param>
/// <param name="">mergeContiguousFragments
/// </param>
/// <throws> IOException </throws>
public TextFragment[] GetBestTextFragments(TokenStream tokenStream, System.String text, bool mergeContiguousFragments, int maxNumFragments)
{
System.Collections.ArrayList docFrags = new System.Collections.ArrayList();
System.Text.StringBuilder newText = new System.Text.StringBuilder();
TextFragment currentFrag = new TextFragment(newText, newText.Length, docFrags.Count);
fragmentScorer.StartFragment(currentFrag);
docFrags.Add(currentFrag);
FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);
try
{
Lucene.Net.Analysis.Token token;
System.String tokenText;
int startOffset;
int endOffset;
int lastEndOffset = 0;
textFragmenter.Start(text);
TokenGroup tokenGroup = new TokenGroup();
token = tokenStream.Next();
while ((token != null) && (token.StartOffset() < maxDocBytesToAnalyze))
{
if ((tokenGroup.numTokens > 0) && (tokenGroup.IsDistinct(token)))
{
//the current token is distinct from previous tokens -
// markup the cached token group info
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;
tokenText = text.Substring(startOffset, (endOffset) - (startOffset));
System.String markedUpText = formatter.HighlightTerm(encoder.EncodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
{
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset, (startOffset) - (lastEndOffset))));
}
newText.Append(markedUpText);
lastEndOffset = System.Math.Max(endOffset, lastEndOffset);
tokenGroup.Clear();
//check if current token marks the start of a new fragment
if (textFragmenter.IsNewFragment(token))
{
currentFrag.SetScore(fragmentScorer.GetFragmentScore());
//record stats for a new fragment
currentFrag.textEndPos = newText.Length;
currentFrag = new TextFragment(newText, newText.Length, docFrags.Count);
fragmentScorer.StartFragment(currentFrag);
docFrags.Add(currentFrag);
}
}
tokenGroup.AddToken(token, fragmentScorer.GetTokenScore(token));
// if(lastEndOffset>maxDocBytesToAnalyze)
// {
// break;
// }
token = tokenStream.Next();
}
currentFrag.SetScore(fragmentScorer.GetFragmentScore());
if (tokenGroup.numTokens > 0)
{
//flush the accumulated text (same code as in above loop)
startOffset = tokenGroup.matchStartOffset;
endOffset = tokenGroup.matchEndOffset;
tokenText = text.Substring(startOffset, (endOffset) - (startOffset));
System.String markedUpText = formatter.HighlightTerm(encoder.EncodeText(tokenText), tokenGroup);
//store any whitespace etc from between this and last group
if (startOffset > lastEndOffset)
{
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset, (startOffset) - (lastEndOffset))));
}
newText.Append(markedUpText);
lastEndOffset = System.Math.Max(lastEndOffset, endOffset);
}
//Test what remains of the original text beyond the point where we stopped analyzing
if ((lastEndOffset < text.Length) && (text.Length < maxDocBytesToAnalyze))
{
//append it to the last fragment
newText.Append(encoder.EncodeText(text.Substring(lastEndOffset)));
}
currentFrag.textEndPos = newText.Length;
//sort the most relevant sections of the text
for (System.Collections.IEnumerator i = docFrags.GetEnumerator(); i.MoveNext();)
{
currentFrag = (TextFragment)i.Current;
//If you are running with a version of Lucene before 11th Sept 03
// you do not have PriorityQueue.insert() - so uncomment the code below
/*
* if (currentFrag.getScore() >= minScore)
* {
* fragQueue.put(currentFrag);
* if (fragQueue.size() > maxNumFragments)
* { // if hit queue overfull
* fragQueue.pop(); // remove lowest in hit queue
* minScore = ((TextFragment) fragQueue.top()).getScore(); // reset minScore
* }
*
*
* }
*/
//The above code caused a problem as a result of Christoph Goller's 11th Sept 03
//fix to PriorityQueue. The correct method to use here is the new "insert" method
// USE ABOVE CODE IF THIS DOES NOT COMPILE!
fragQueue.Insert(currentFrag);
}
//return the most relevant fragments
TextFragment[] frag = new TextFragment[fragQueue.Size()];
for (int i = frag.Length - 1; i >= 0; i--)
{
frag[i] = (TextFragment)fragQueue.Pop();
}
//merge any contiguous fragments to improve readability
if (mergeContiguousFragments)
{
MergeContiguousFragments(frag);
System.Collections.ArrayList fragTexts = new System.Collections.ArrayList();
for (int i = 0; i < frag.Length; i++)
{
if ((frag[i] != null) && (frag[i].GetScore() > 0))
{
fragTexts.Add(frag[i]);
}
}
frag = (TextFragment[])fragTexts.ToArray(typeof(TextFragment));
}
return(frag);
}
finally
{
if (tokenStream != null)
{
try
{
tokenStream.Close();
}
catch (System.Exception e)
{
}
}
}
}
