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

LUCENE-2003: Highlighter doesn't respect position increments other than 1 with PhraseQuerys 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@829129 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Mark Robert Miller 2009-10-23 17:08:50 +00:00
parent 0f76b3139d
commit 9609a2cb4d
2 changed files with 69 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
View File

@ -95,13 +95,32 @@ public class WeightedSpanTermExtractor {
} }
} }
} else if (query instanceof PhraseQuery) { } else if (query instanceof PhraseQuery) {
Term[] phraseQueryTerms = ((PhraseQuery) query).getTerms(); PhraseQuery phraseQuery = ((PhraseQuery) query);
Term[] phraseQueryTerms = phraseQuery.getTerms();
SpanQuery[] clauses = new SpanQuery[phraseQueryTerms.length]; SpanQuery[] clauses = new SpanQuery[phraseQueryTerms.length];
for (int i = 0; i < phraseQueryTerms.length; i++) { for (int i = 0; i < phraseQueryTerms.length; i++) {
clauses[i] = new SpanTermQuery(phraseQueryTerms[i]); clauses[i] = new SpanTermQuery(phraseQueryTerms[i]);
} }
int slop = phraseQuery.getSlop();
int[] positions = phraseQuery.getPositions();
// add largest position increment to slop
if (positions.length > 0) {
int lastPos = positions[0];
int largestInc = 0;
int sz = positions.length;
for (int i = 1; i < sz; i++) {
int pos = positions[i];
int inc = pos - lastPos;
if (inc > largestInc) {
largestInc = inc;
}
lastPos = pos;
}
if(largestInc > 1) {
slop += largestInc;
}
}
int slop = ((PhraseQuery) query).getSlop();
boolean inorder = false; boolean inorder = false;
if (slop == 0) { if (slop == 0) {

50
contrib/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
View File

@ -84,7 +84,7 @@ import org.w3c.dom.NodeList;
*/ */
public class HighlighterTest extends BaseTokenStreamTestCase implements Formatter { public class HighlighterTest extends BaseTokenStreamTestCase implements Formatter {
// TODO: change to CURRENT, does not work because posIncr: // TODO: change to CURRENT, does not work because posIncr:
static final Version TEST_VERSION = Version.LUCENE_24; static final Version TEST_VERSION = Version.LUCENE_29;
private IndexReader reader; private IndexReader reader;
static final String FIELD_NAME = "contents"; static final String FIELD_NAME = "contents";
@ -100,7 +100,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
"This piece of text refers to Kennedy at the beginning then has a longer piece of text that is very long in the middle and finally ends with another reference to Kennedy", "This piece of text refers to Kennedy at the beginning then has a longer piece of text that is very long in the middle and finally ends with another reference to Kennedy",
"JFK has been shot", "John Kennedy has been shot", "JFK has been shot", "John Kennedy has been shot",
"This text has a typo in referring to Keneddy", "This text has a typo in referring to Keneddy",
"wordx wordy wordz wordx wordy wordx worda wordb wordy wordc", "y z x y z a b" }; "wordx wordy wordz wordx wordy wordx worda wordb wordy wordc", "y z x y z a b", "lets is a the lets is a the lets is a the lets" };
/** /**
* Constructor for HighlightExtractorTest. * Constructor for HighlightExtractorTest.
@ -256,6 +256,51 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
assertTrue("Failed to find correct number of highlights " + numHighlights + " found", assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
numHighlights == 3); numHighlights == 3);
numHighlights = 0;
doSearching("\"This piece of text refers to Kennedy\"");
maxNumFragmentsRequired = 2;
scorer = new QueryScorer(query, FIELD_NAME);
highlighter = new Highlighter(this, scorer);
for (int i = 0; i < hits.totalHits; i++) {
String text = searcher.doc(hits.scoreDocs[i].doc).get(FIELD_NAME);
TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
highlighter.setTextFragmenter(new SimpleFragmenter(40));
String result = highlighter.getBestFragments(tokenStream, text, maxNumFragmentsRequired,
"...");
System.out.println("\t" + result);
}
assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
numHighlights == 4);
numHighlights = 0;
doSearching("\"lets is a the lets is a the lets is a the lets\"");
maxNumFragmentsRequired = 2;
scorer = new QueryScorer(query, FIELD_NAME);
highlighter = new Highlighter(this, scorer);
for (int i = 0; i < hits.totalHits; i++) {
String text = searcher.doc(hits.scoreDocs[i].doc).get(FIELD_NAME);
TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
highlighter.setTextFragmenter(new SimpleFragmenter(40));
String result = highlighter.getBestFragments(tokenStream, text, maxNumFragmentsRequired,
"...");
System.out.println("\t" + result);
}
assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
numHighlights == 4);
} }
public void testSimpleQueryScorerPhraseHighlighting2() throws Exception { public void testSimpleQueryScorerPhraseHighlighting2() throws Exception {
@ -1531,6 +1576,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
public void doSearching(String queryString) throws Exception { public void doSearching(String queryString) throws Exception {
QueryParser parser = new QueryParser(FIELD_NAME, analyzer); QueryParser parser = new QueryParser(FIELD_NAME, analyzer);
parser.setEnablePositionIncrements(true);
parser.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE); parser.setMultiTermRewriteMethod(MultiTermQuery.SCORING_BOOLEAN_QUERY_REWRITE);
query = parser.parse(queryString); query = parser.parse(queryString);
doSearching(query); doSearching(query);