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

LUCENE-2603: FastVectorHighlighter: add a method to set an arbitrary char that is used when concatenating multiValued data 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@986173 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Koji Sekiguchi 2010-08-17 02:39:40 +00:00
parent c2df8e8a0c
commit db4b2af8af
3 changed files with 30 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lucene/contrib/CHANGES.txt
View File

@ -112,6 +112,10 @@ API Changes
such as stopword lists and any language-specific processing in addition to
stemming. Add Turkish and Romanian stopwords lists to support this.
(Robert Muir, Uwe Schindler, Simon Willnauer)
* LUCENE-2603: Add setMultiValuedSeparator(char) method to set an arbitrary
char that is used when concatenating multiValued data. Default is a space
(' '). It is applied on ANALYZED field only. (Koji Sekiguchi)
New features

13
lucene/contrib/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragmentsBuilder.java
View File

@ -44,6 +44,7 @@ public abstract class BaseFragmentsBuilder implements FragmentsBuilder {
"<b style=\"background:turquoise\">", "<b style=\"background:powderblue\">"
};
public static final String[] COLORED_POST_TAGS = { "</b>" };
private char multiValuedSeparator = ' ';
protected BaseFragmentsBuilder(){
this( new String[]{ "<b>" }, new String[]{ "</b>" } );
@ -155,7 +156,7 @@ public abstract class BaseFragmentsBuilder implements FragmentsBuilder {
int startOffset, int endOffset ){
while( buffer.length() < endOffset && index[0] < values.length ){
if( index[0] > 0 && values[index[0]].length() > 0 )
buffer.append( ' ' );
buffer.append( multiValuedSeparator );
buffer.append( values[index[0]++] );
}
int eo = buffer.length() < endOffset ? buffer.length() : endOffset;
@ -166,12 +167,20 @@ public abstract class BaseFragmentsBuilder implements FragmentsBuilder {
int startOffset, int endOffset ){
while( buffer.length() < endOffset && index[0] < values.length ){
if( index[0] > 0 && values[index[0]].isTokenized() && values[index[0]].stringValue().length() > 0 )
buffer.append( ' ' );
buffer.append( multiValuedSeparator );
buffer.append( values[index[0]++].stringValue() );
}
int eo = buffer.length() < endOffset ? buffer.length() : endOffset;
return buffer.substring( startOffset, eo );
}
public void setMultiValuedSeparator( char separator ){
multiValuedSeparator = separator;
}
public char getMultiValuedSeparator(){
return multiValuedSeparator;
}
protected String getPreTag( int num ){
return getPreTag( preTags, num );

15
lucene/contrib/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java
View File

@ -148,6 +148,21 @@ public class SimpleFragmentsBuilderTest extends AbstractTestCase {
SimpleFragListBuilder sflb = new SimpleFragListBuilder();
FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
SimpleFragmentsBuilder sfb = new SimpleFragmentsBuilder();
// '/' separator doesn't effect the snippet because of NOT_ANALYZED field
sfb.setMultiValuedSeparator( '/' );
assertEquals( "abc<b>defg</b>hijkl", sfb.createFragment( reader, 0, F, ffl ) );
}
public void testMVSeparator() throws Exception {
makeIndexShortMV();
FieldQuery fq = new FieldQuery( tq( "d" ), true, true );
FieldTermStack stack = new FieldTermStack( reader, 0, F, fq );
FieldPhraseList fpl = new FieldPhraseList( stack, fq );
SimpleFragListBuilder sflb = new SimpleFragListBuilder();
FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
SimpleFragmentsBuilder sfb = new SimpleFragmentsBuilder();
sfb.setMultiValuedSeparator( '/' );
assertEquals( "a b c/<b>d</b> e", sfb.createFragment( reader, 0, F, ffl ) );
}
}