-
Notifications
You must be signed in to change notification settings - Fork 40
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
fvh adaptor to highlight the top phrase once only.
- Loading branch information
Showing
10 changed files
with
2,086 additions
and
1,835 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -26,7 +26,7 @@ java { | |
| } | ||
|
|
||
| allprojects { | ||
| version = '0.40.0' | ||
| version = '0.40.1' | ||
| group = 'com.yelp.nrtsearch' | ||
| } | ||
|
|
||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
90 changes: 90 additions & 0 deletions
90
...m/yelp/nrtsearch/server/luceneserver/highlights/TopPhraseOnceFragmentsBuilderAdaptor.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,90 @@ | ||
| /* | ||
| * Copyright 2024 Yelp Inc. | ||
| * | ||
| * Licensed under the Apache License, Version 2.0 (the "License"); | ||
| * you may not use this file except in compliance with the License. | ||
| * You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
| package com.yelp.nrtsearch.server.luceneserver.highlights; | ||
|
|
||
| import org.apache.lucene.document.Field; | ||
| import org.apache.lucene.search.highlight.Encoder; | ||
| import org.apache.lucene.search.vectorhighlight.BaseFragmentsBuilder; | ||
| import org.apache.lucene.search.vectorhighlight.BoundaryScanner; | ||
| import org.apache.lucene.search.vectorhighlight.FieldFragList.WeightedFragInfo; | ||
| import org.apache.lucene.search.vectorhighlight.FieldFragList.WeightedFragInfo.SubInfo; | ||
| import org.apache.lucene.search.vectorhighlight.FieldPhraseList.WeightedPhraseInfo.Toffs; | ||
|
|
||
| import java.util.Comparator; | ||
| import java.util.List; | ||
|
|
||
| public class TopPhraseOnceFragmentsBuilderAdaptor extends BaseFragmentsBuilder { | ||
| private final BaseFragmentsBuilder innerBaseFragmentsBuilder; | ||
| private final boolean topPhraseOnce; | ||
|
|
||
| /** a constructor. */ | ||
| public TopPhraseOnceFragmentsBuilderAdaptor( | ||
| BaseFragmentsBuilder baseFragmentsBuilder, | ||
| BoundaryScanner boundaryScanner, | ||
| boolean topPhraseOnce) { | ||
| super(boundaryScanner); | ||
| this.innerBaseFragmentsBuilder = baseFragmentsBuilder; | ||
| this.topPhraseOnce = topPhraseOnce; | ||
| } | ||
|
|
||
| @Override | ||
| public List<WeightedFragInfo> getWeightedFragInfoList(List<WeightedFragInfo> src) { | ||
| return innerBaseFragmentsBuilder.getWeightedFragInfoList(src); | ||
| } | ||
|
|
||
| @Override | ||
| protected String makeFragment( | ||
| StringBuilder buffer, | ||
| int[] index, | ||
| Field[] values, | ||
| WeightedFragInfo fragInfo, | ||
| String[] preTags, | ||
| String[] postTags, | ||
| Encoder encoder) { | ||
| if (!topPhraseOnce) { | ||
| return super.makeFragment(buffer, index, values, fragInfo, preTags, postTags, encoder); | ||
| } | ||
| StringBuilder fragment = new StringBuilder(); | ||
| final int s = fragInfo.getStartOffset(); | ||
| int[] modifiedStartOffset = {s}; | ||
| String src = | ||
| getFragmentSourceMSO( | ||
| buffer, index, values, s, fragInfo.getEndOffset(), modifiedStartOffset); | ||
| int srcIndex = 0; | ||
| // get a list of the first highest boosted phrase only | ||
| List<SubInfo> subInfos = | ||
| fragInfo.getSubInfos().stream().max(Comparator.comparingDouble(SubInfo::getBoost)).stream() | ||
| .toList(); | ||
| for (SubInfo subInfo : subInfos) { | ||
| for (Toffs to : subInfo.getTermsOffsets()) { | ||
| fragment | ||
| .append( | ||
| encoder.encodeText( | ||
| src.substring(srcIndex, to.getStartOffset() - modifiedStartOffset[0]))) | ||
| .append(getPreTag(preTags, subInfo.getSeqnum())) | ||
| .append( | ||
| encoder.encodeText( | ||
| src.substring( | ||
| to.getStartOffset() - modifiedStartOffset[0], | ||
| to.getEndOffset() - modifiedStartOffset[0]))) | ||
| .append(getPostTag(postTags, subInfo.getSeqnum())); | ||
| srcIndex = to.getEndOffset() - modifiedStartOffset[0]; | ||
| } | ||
| } | ||
| fragment.append(encoder.encodeText(src.substring(srcIndex))); | ||
| return fragment.toString(); | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters