You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by jp...@apache.org on 2016/06/10 07:12:59 UTC
[1/3] lucene-solr:master: LUCENE-7286: Added support for highlighting
SynonymQuery.
Repository: lucene-solr
Updated Branches:
refs/heads/branch_6_1 e0c6762de -> 5e87c2b31
refs/heads/branch_6x 74d94ec26 -> ef707f05a
refs/heads/master 387143997 -> e418bd0eb
LUCENE-7286: Added support for highlighting SynonymQuery.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/e418bd0e
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/e418bd0e
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/e418bd0e
Branch: refs/heads/master
Commit: e418bd0eb33eb058c0403dfcdaef8733bd6f4fc1
Parents: 3871439
Author: Adrien Grand <jp...@gmail.com>
Authored: Fri Jun 10 09:11:15 2016 +0200
Committer: Adrien Grand <jp...@gmail.com>
Committed: Fri Jun 10 09:11:15 2016 +0200
----------------------------------------------------------------------
lucene/CHANGES.txt | 2 ++
.../highlight/WeightedSpanTermExtractor.java | 3 ++-
.../search/highlight/HighlighterTest.java | 21 +++++++++++++++++++-
3 files changed, 24 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e418bd0e/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 20df7b2..279fc4d 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -134,6 +134,8 @@ Bug Fixes
other ranges had more than one clause matching (Ahmet Arslan,
hossman, Mike McCandless)
+* LUCENE-7286: Added support for highlighting SynonymQuery. (Adrien Grand)
+
Other
* LUCENE-7295: TermAutomatonQuery.hashCode calculates Automaton.toDot().hash,
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e418bd0e/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
index 43f75cc..7507bdd 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
@@ -53,6 +53,7 @@ import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.join.ToChildBlockJoinQuery;
import org.apache.lucene.search.join.ToParentBlockJoinQuery;
@@ -138,7 +139,7 @@ public class WeightedSpanTermExtractor {
SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
- } else if (query instanceof TermQuery) {
+ } else if (query instanceof TermQuery || query instanceof SynonymQuery) {
extractWeightedTerms(terms, query, boost);
} else if (query instanceof SpanQuery) {
extractWeightedSpanTerms(terms, (SpanQuery) query, boost);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/e418bd0e/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
index 3c6f108..cf727d7 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
@@ -71,6 +71,7 @@ import org.apache.lucene.search.PhraseQuery.Builder;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
@@ -223,6 +224,24 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
assertEquals("This piece of text refers to Kennedy at the beginning then has a longer piece of text that is <B>very</B>", fragment);
}
+ public void testHighlightingSynonymQuery() throws Exception {
+ searcher = newSearcher(reader);
+ Query query = new SynonymQuery(new Term(FIELD_NAME, "jfk"), new Term(FIELD_NAME, "kennedy"));
+ QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
+ Highlighter highlighter = new Highlighter(scorer);
+ TokenStream stream = getAnyTokenStream(FIELD_NAME, 2);
+ Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
+ highlighter.setTextFragmenter(fragmenter);
+ String storedField = searcher.doc(2).get(FIELD_NAME);
+ String fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("<B>JFK</B> has been shot", fragment);
+
+ stream = getAnyTokenStream(FIELD_NAME, 3);
+ storedField = searcher.doc(3).get(FIELD_NAME);
+ fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("John <B>Kennedy</B> has been shot", fragment);
+ }
+
public void testHighlightUnknownQueryAfterRewrite() throws IOException, InvalidTokenOffsetsException {
Query query = new Query() {
@@ -2093,7 +2112,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, MockTokenFilter.ENGLISH_STOPSET);
ramDir = newDirectory();
fieldType = random().nextBoolean() ? FIELD_TYPE_TV : TextField.TYPE_STORED;
- IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer));
+ IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer).setMergePolicy(newLogMergePolicy()));
for (String text : texts) {
writer.addDocument(doc(FIELD_NAME, text));
[3/3] lucene-solr:branch_6_1: LUCENE-7286: Added support for
highlighting SynonymQuery.
Posted by jp...@apache.org.
LUCENE-7286: Added support for highlighting SynonymQuery.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/5e87c2b3
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/5e87c2b3
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/5e87c2b3
Branch: refs/heads/branch_6_1
Commit: 5e87c2b31fb0cd0d2c99986fdd79abe2544a04c2
Parents: e0c6762
Author: Adrien Grand <jp...@gmail.com>
Authored: Fri Jun 10 09:11:15 2016 +0200
Committer: Adrien Grand <jp...@gmail.com>
Committed: Fri Jun 10 09:12:22 2016 +0200
----------------------------------------------------------------------
lucene/CHANGES.txt | 2 ++
.../highlight/WeightedSpanTermExtractor.java | 3 ++-
.../search/highlight/HighlighterTest.java | 21 +++++++++++++++++++-
3 files changed, 24 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/5e87c2b3/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index c3b7cee..7b0f069 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -109,6 +109,8 @@ Bug Fixes
other ranges had more than one clause matching (Ahmet Arslan,
hossman, Mike McCandless)
+* LUCENE-7286: Added support for highlighting SynonymQuery. (Adrien Grand)
+
Other
* LUCENE-7295: TermAutomatonQuery.hashCode calculates Automaton.toDot().hash,
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/5e87c2b3/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
index 43f75cc..7507bdd 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
@@ -53,6 +53,7 @@ import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.join.ToChildBlockJoinQuery;
import org.apache.lucene.search.join.ToParentBlockJoinQuery;
@@ -138,7 +139,7 @@ public class WeightedSpanTermExtractor {
SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
- } else if (query instanceof TermQuery) {
+ } else if (query instanceof TermQuery || query instanceof SynonymQuery) {
extractWeightedTerms(terms, query, boost);
} else if (query instanceof SpanQuery) {
extractWeightedSpanTerms(terms, (SpanQuery) query, boost);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/5e87c2b3/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
index 3c6f108..cf727d7 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
@@ -71,6 +71,7 @@ import org.apache.lucene.search.PhraseQuery.Builder;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
@@ -223,6 +224,24 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
assertEquals("This piece of text refers to Kennedy at the beginning then has a longer piece of text that is <B>very</B>", fragment);
}
+ public void testHighlightingSynonymQuery() throws Exception {
+ searcher = newSearcher(reader);
+ Query query = new SynonymQuery(new Term(FIELD_NAME, "jfk"), new Term(FIELD_NAME, "kennedy"));
+ QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
+ Highlighter highlighter = new Highlighter(scorer);
+ TokenStream stream = getAnyTokenStream(FIELD_NAME, 2);
+ Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
+ highlighter.setTextFragmenter(fragmenter);
+ String storedField = searcher.doc(2).get(FIELD_NAME);
+ String fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("<B>JFK</B> has been shot", fragment);
+
+ stream = getAnyTokenStream(FIELD_NAME, 3);
+ storedField = searcher.doc(3).get(FIELD_NAME);
+ fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("John <B>Kennedy</B> has been shot", fragment);
+ }
+
public void testHighlightUnknownQueryAfterRewrite() throws IOException, InvalidTokenOffsetsException {
Query query = new Query() {
@@ -2093,7 +2112,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, MockTokenFilter.ENGLISH_STOPSET);
ramDir = newDirectory();
fieldType = random().nextBoolean() ? FIELD_TYPE_TV : TextField.TYPE_STORED;
- IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer));
+ IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer).setMergePolicy(newLogMergePolicy()));
for (String text : texts) {
writer.addDocument(doc(FIELD_NAME, text));
[2/3] lucene-solr:branch_6x: LUCENE-7286: Added support for
highlighting SynonymQuery.
Posted by jp...@apache.org.
LUCENE-7286: Added support for highlighting SynonymQuery.
Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/ef707f05
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/ef707f05
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/ef707f05
Branch: refs/heads/branch_6x
Commit: ef707f05ae590347e08bb6f92cc5d62854481a1b
Parents: 74d94ec
Author: Adrien Grand <jp...@gmail.com>
Authored: Fri Jun 10 09:11:15 2016 +0200
Committer: Adrien Grand <jp...@gmail.com>
Committed: Fri Jun 10 09:11:49 2016 +0200
----------------------------------------------------------------------
lucene/CHANGES.txt | 2 ++
.../highlight/WeightedSpanTermExtractor.java | 3 ++-
.../search/highlight/HighlighterTest.java | 21 +++++++++++++++++++-
3 files changed, 24 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ef707f05/lucene/CHANGES.txt
----------------------------------------------------------------------
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index f4fa8ba..e7e3e28 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -126,6 +126,8 @@ Bug Fixes
other ranges had more than one clause matching (Ahmet Arslan,
hossman, Mike McCandless)
+* LUCENE-7286: Added support for highlighting SynonymQuery. (Adrien Grand)
+
Other
* LUCENE-7295: TermAutomatonQuery.hashCode calculates Automaton.toDot().hash,
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ef707f05/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
index 43f75cc..7507bdd 100644
--- a/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
+++ b/lucene/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java
@@ -53,6 +53,7 @@ import org.apache.lucene.search.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.join.ToChildBlockJoinQuery;
import org.apache.lucene.search.join.ToParentBlockJoinQuery;
@@ -138,7 +139,7 @@ public class WeightedSpanTermExtractor {
SpanNearQuery sp = new SpanNearQuery(clauses, phraseQuery.getSlop() + positionGaps, inorder);
extractWeightedSpanTerms(terms, sp, boost);
}
- } else if (query instanceof TermQuery) {
+ } else if (query instanceof TermQuery || query instanceof SynonymQuery) {
extractWeightedTerms(terms, query, boost);
} else if (query instanceof SpanQuery) {
extractWeightedSpanTerms(terms, (SpanQuery) query, boost);
http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/ef707f05/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
----------------------------------------------------------------------
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
index 3c6f108..cf727d7 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
@@ -71,6 +71,7 @@ import org.apache.lucene.search.PhraseQuery.Builder;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
+import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
@@ -223,6 +224,24 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
assertEquals("This piece of text refers to Kennedy at the beginning then has a longer piece of text that is <B>very</B>", fragment);
}
+ public void testHighlightingSynonymQuery() throws Exception {
+ searcher = newSearcher(reader);
+ Query query = new SynonymQuery(new Term(FIELD_NAME, "jfk"), new Term(FIELD_NAME, "kennedy"));
+ QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
+ Highlighter highlighter = new Highlighter(scorer);
+ TokenStream stream = getAnyTokenStream(FIELD_NAME, 2);
+ Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
+ highlighter.setTextFragmenter(fragmenter);
+ String storedField = searcher.doc(2).get(FIELD_NAME);
+ String fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("<B>JFK</B> has been shot", fragment);
+
+ stream = getAnyTokenStream(FIELD_NAME, 3);
+ storedField = searcher.doc(3).get(FIELD_NAME);
+ fragment = highlighter.getBestFragment(stream, storedField);
+ assertEquals("John <B>Kennedy</B> has been shot", fragment);
+ }
+
public void testHighlightUnknownQueryAfterRewrite() throws IOException, InvalidTokenOffsetsException {
Query query = new Query() {
@@ -2093,7 +2112,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
analyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE, true, MockTokenFilter.ENGLISH_STOPSET);
ramDir = newDirectory();
fieldType = random().nextBoolean() ? FIELD_TYPE_TV : TextField.TYPE_STORED;
- IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer));
+ IndexWriter writer = new IndexWriter(ramDir, newIndexWriterConfig(analyzer).setMergePolicy(newLogMergePolicy()));
for (String text : texts) {
writer.addDocument(doc(FIELD_NAME, text));