/// <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 <see cref="TextFragment"/> objects.
/// Thanks to Jason Calabrese for help in redefining the interface.
/// </summary>
/// <exception cref="IOException">If there is a low-level I/O error</exception>
/// <exception cref="InvalidTokenOffsetsException">thrown if any token's EndOffset exceeds the provided text's length</exception>
public TextFragment[] GetBestTextFragments(
TokenStream tokenStream,
string text,
bool mergeContiguousFragments,
int maxNumFragments)
{
var docFrags = new JCG.List <TextFragment>();
var newText = new StringBuilder();
var termAtt = tokenStream.AddAttribute <ICharTermAttribute>();
var offsetAtt = tokenStream.AddAttribute <IOffsetAttribute>();
tokenStream.Reset();
var currentFrag = new TextFragment(newText, newText.Length, docFrags.Count);
if (_fragmentScorer is QueryScorer queryScorer)
{
queryScorer.SetMaxDocCharsToAnalyze(_maxDocCharsToAnalyze);
}
var newStream = _fragmentScorer.Init(tokenStream);
if (newStream != null)
{
tokenStream = newStream;
}
_fragmentScorer.StartFragment(currentFrag);
docFrags.Add(currentFrag);
var fragQueue = new FragmentQueue(maxNumFragments);
try
{
string tokenText;
int startOffset;
int endOffset;
int lastEndOffset = 0;
_textFragmenter.Start(text, tokenStream);
var tokenGroup = new TokenGroup(tokenStream);
for (bool next = tokenStream.IncrementToken();
next && (offsetAtt.StartOffset < _maxDocCharsToAnalyze);
next = tokenStream.IncrementToken())
{
if ((offsetAtt.EndOffset > text.Length)
||
(offsetAtt.StartOffset > text.Length)
)
{
throw new InvalidTokenOffsetsException("Token " + termAtt.ToString()
+ " exceeds length of provided text sized " + text.Length);
}
if ((tokenGroup.NumTokens > 0) && (tokenGroup.IsDistinct()))
{
//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);
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 = Math.Max(endOffset, lastEndOffset);
tokenGroup.Clear();
//check if current token marks the start of a new fragment
if (_textFragmenter.IsNewFragment())
{
currentFrag.Score = _fragmentScorer.FragmentScore;
//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(_fragmentScorer.GetTokenScore());
// if(lastEndOffset>maxDocBytesToAnalyze)
// {
// break;
// }
}
currentFrag.Score = _fragmentScorer.FragmentScore;
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);
var 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 = Math.Max(lastEndOffset, endOffset);
}
//Test what remains of the original text beyond the point where we stopped analyzing
if (
// if there is text beyond the last token considered..
(lastEndOffset < text.Length)
&&
// and that text is not too large...
(text.Length <= _maxDocCharsToAnalyze)
)
{
//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
foreach (var f in docFrags)
{
currentFrag = f;
//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.InsertWithOverflow(currentFrag);
}
//return the most relevant fragments
var frag = new TextFragment[fragQueue.Count];
for (int i = frag.Length - 1; i >= 0; i--)
{
frag[i] = fragQueue.Pop();
}
//merge any contiguous fragments to improve readability
if (mergeContiguousFragments)
{
MergeContiguousFragments(frag);
JCG.List <TextFragment> fragTexts = new JCG.List <TextFragment>();
for (int i = 0; i < frag.Length; i++)
{
if ((frag[i] != null) && (frag[i].Score > 0))
{
fragTexts.Add(frag[i]);
}
}
frag = new TextFragment[fragTexts.Count];
fragTexts.CopyTo(frag);
}
return(frag);
}
finally
{
if (tokenStream != null)
{
try
{
tokenStream.End();
tokenStream.Dispose();
}
catch (Exception e) when(e.IsException())
{
}
}
}
}