Fix display of ellipsis in search fragments (#1896)

Display ellipsis as an indicator that there is more content before or behind a search result fragment only if there really is more content.
This commit is contained in:
Matthias Thieroff
2021-12-15 15:07:46 +01:00
committed by GitHub
parent 1118ddd146
commit 11673e6d07
11 changed files with 135 additions and 50 deletions

View File

@@ -0,0 +1,44 @@
/*
* MIT License
*
* Copyright (c) 2020-present Cloudogu GmbH and Contributors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
package sonia.scm.search;
import lombok.Getter;
@Getter
public class ContentFragment {
private final String fragment;
private final boolean matchesContentStart;
private final boolean matchesContentEnd;
ContentFragment(String fragment) {
this(fragment, false, false);
}
ContentFragment(String fragment, boolean matchesContentStart, boolean matchesContentEnd) {
this.fragment = fragment;
this.matchesContentStart = matchesContentStart;
this.matchesContentEnd = matchesContentEnd;
}
}

View File

@@ -70,25 +70,32 @@ public final class LuceneHighlighter {
return field.isHighlighted() && queriedFields.contains(field.getName());
}
public String[] highlight(String fieldName, Indexed.Analyzer fieldAnalyzer, String value) throws InvalidTokenOffsetsException, IOException {
public ContentFragment[] highlight(String fieldName, Indexed.Analyzer fieldAnalyzer, String value) throws InvalidTokenOffsetsException, IOException {
String[] fragments = highlighter.getBestFragments(analyzer, fieldName, value, MAX_NUM_FRAGMENTS);
if (fieldAnalyzer == Indexed.Analyzer.CODE) {
fragments = keepWholeLine(value, fragments);
return keepWholeLine(value, fragments);
}
return Arrays.stream(fragments)
.toArray(String[]::new);
return Arrays.stream(fragments).map(ContentFragment::new)
.toArray(ContentFragment[]::new);
}
private String[] keepWholeLine(String content, String[] fragments) {
private ContentFragment[] keepWholeLine(String content, String[] fragments) {
return Arrays.stream(fragments)
.map(fragment -> keepWholeLine(content, fragment))
.toArray(String[]::new);
.toArray(ContentFragment[]::new);
}
private String keepWholeLine(String content, String fragment) {
private ContentFragment keepWholeLine(String content, String fragment) {
boolean matchesContentStart = false;
boolean matchesContentEnd = false;
String raw = fragment.replace(PRE_TAG, "").replace(POST_TAG, "");
int index = content.indexOf(raw);
if (index == 0) {
matchesContentStart = true;
}
int start = content.lastIndexOf('\n', index);
String snippet;
@@ -109,9 +116,10 @@ public final class LuceneHighlighter {
int end = content.indexOf('\n', index + raw.length());
if (end < 0) {
end = content.length();
matchesContentEnd = true;
}
return snippet + content.substring(index + raw.length(), end) + "\n";
return new ContentFragment(snippet + content.substring(index + raw.length(), end) + (matchesContentEnd ? "" : "\n"), matchesContentStart, matchesContentEnd);
}
}

View File

@@ -34,6 +34,7 @@ import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
@@ -75,9 +76,11 @@ public class QueryResultFactory {
Object value = field.value(document);
if (value != null) {
if (highlighter.isHighlightable(field)) {
String[] fragments = createFragments(field, value.toString());
ContentFragment[] fragments = createFragments(field, value.toString());
if (fragments.length > 0) {
return of(new Hit.HighlightedField(fragments));
boolean firstFragmentMatchesContentStart = fragments[0].isMatchesContentStart();
boolean lastFragmentMatchesContentEnd = fragments[fragments.length - 1].isMatchesContentEnd();
return of(new Hit.HighlightedField(Arrays.stream(fragments).map(ContentFragment::getFragment).toArray(String[]::new), firstFragmentMatchesContentStart, lastFragmentMatchesContentEnd));
}
}
return of(new Hit.ValueField(value));
@@ -85,7 +88,7 @@ public class QueryResultFactory {
return empty();
}
private String[] createFragments(LuceneSearchableField field, String value) throws InvalidTokenOffsetsException, IOException {
private ContentFragment[] createFragments(LuceneSearchableField field, String value) throws InvalidTokenOffsetsException, IOException {
return highlighter.highlight(field.getName(), field.getAnalyzer(), value);
}