Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-1295: Made method public and added retrieveInterestingTerms variation 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@662413 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Grant Ingersoll 2008-06-02 12:29:02 +00:00
parent e33f551cba
commit 1979d75605
2 changed files with 21 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGES.txt
View File

@ -175,6 +175,8 @@ New features
and DocIdSetIterator-based filters. Backwards-compatibility with old
BitSet-based filters is ensured. (Paul Elschot via Michael Busch)
15. LUCENE-1295: Added new method to MoreLikeThis for retrieving interesting terms and made retrieveTerms(int) public. (Grant Ingersoll)
Optimizations
1. LUCENE-705: When building a compound file, use

21
contrib/queries/src/java/org/apache/lucene/search/similar/MoreLikeThis.java
View File

@ -731,7 +731,7 @@ public final class MoreLikeThis {
*
* @param docNum the id of the lucene document from which to find terms
*/
private PriorityQueue retrieveTerms(int docNum) throws IOException {
public PriorityQueue retrieveTerms(int docNum) throws IOException {
Map termFreqMap = new HashMap();
for (int i = 0; i < fieldNames.length; i++) {
String fieldName = fieldNames[i];
@ -871,7 +871,24 @@ public final class MoreLikeThis {
return createQueue(words);
}
/**
/**
* @see #retrieveInterestingTerms(java.io.Reader)
*/
public String [] retrieveInterestingTerms(int docNum) throws IOException{
ArrayList al = new ArrayList( maxQueryTerms);
PriorityQueue pq = retrieveTerms(docNum);
Object cur;
int lim = maxQueryTerms; // have to be careful, retrieveTerms returns all words but that's probably not useful to our caller...
// we just want to return the top words
while (((cur = pq.pop()) != null) && lim-- > 0) {
Object[] ar = (Object[]) cur;
al.add( ar[ 0]); // the 1st entry is the interesting word
}
String[] res = new String[ al.size()];
return (String[]) al.toArray( res);
}
/**
* Convenience routine to make it easy to return the most interesting words in a document.
* More advanced users will call {@link #retrieveTerms(java.io.Reader) retrieveTerms()} directly.
* @param r the source document