[prev in list] [next in list] [prev in thread] [next in thread]
List: lucene-dev
Subject: svn commit: r154083 - in
From: dnaber () apache ! org
Date: 2005-02-16 20:38:01
Message-ID: 20050216203801.22568.qmail () minotaur ! apache ! org
[Download RAW message or body]
Author: dnaber
Date: Wed Feb 16 12:37:57 2005
New Revision: 154083
URL: http://svn.apache.org/viewcvs?view=rev&rev=154083
Log:
remove empty "@return" tags so javadoc stops complaining; small whitespace cleanup
Modified:
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Formatter.java
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Fragmenter.java
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Highlighter.java
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenGroup.java
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java \
Wed Feb 16 12:37:57 2005 @@ -25,7 +25,6 @@
{
/**
* @param originalText The section of text being output
- * @return
*/
String encodeText(String originalText);
}
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Formatter.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Formatter.java?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Formatter.java \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Formatter.java \
Wed Feb 16 12:37:57 2005 @@ -27,7 +27,6 @@
* @param originalText The section of text being considered for markup
* @param tokenGroup contains one or several overlapping Tokens along with
* their scores and positions.
- * @return
*/
String highlightTerm(String originalText, TokenGroup tokenGroup);
}
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Fragmenter.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Fragmenter.java?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Fragmenter.java \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Fragmenter.java \
Wed Feb 16 12:37:57 2005 @@ -34,7 +34,6 @@
/**
* Test to see if this token from the stream should be held in a new TextFragment
* @param nextToken
- * @return
*/
public boolean isNewFragment(Token nextToken);
}
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Highlighter.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Highlighter.java?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Highlighter.java \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Highlighter.java \
Wed Feb 16 12:37:57 2005 @@ -127,7 +127,6 @@
* @param text
* @param maxNumFragments
* @param mergeContiguousFragments
- * @return
* @throws IOException
*/
public final TextFragment[] getBestTextFragments(
@@ -411,7 +410,6 @@
}
/**
- * @return
*/
public Fragmenter getTextFragmenter()
{
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenGroup.java
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenGroup.java?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenGroup.java \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/TokenGroup.java \
Wed Feb 16 12:37:57 2005 @@ -105,7 +105,7 @@
}
/**
- * @return
+ * @return all tokens' scores summed up
*/
public float getTotalScore()
{
Modified: lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html
URL: http://svn.apache.org/viewcvs/lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html?view=diff&r1=154082&r2=154083
==============================================================================
--- lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html \
(original)
+++ lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/package.html \
Wed Feb 16 12:37:57 2005 @@ -1,51 +1,57 @@
<html>
<body>
+
The highlight package contains classes to provide "keyword in context" features
-typically used to highlight search terms in the text of results pages. <br>
+typically used to highlight search terms in the text of results pages.
The Highlighter class is the central component and can be used to extract the
most interesting sections of a piece of text and highlight them, with the help of
Fragmenter, FragmentScorer, Formatter classes.
+
<h2>Example Usage</h2>
<pre>
- IndexSearcher searcher = new IndexSearcher(ramDir);
- Query query = QueryParser.parse("Kenne*", FIELD_NAME, analyzer);
- query=query.rewrite(reader); //required to expand search terms
- Hits hits = searcher.search(query);
-
- Highlighter highlighter =new Highlighter(this,new QueryScorer(query));
- for (int i = 0; i < hits.length(); i++)
- {
- String text = hits.doc(i).get(FIELD_NAME);
- TokenStream tokenStream=analyzer.tokenStream(FIELD_NAME,new StringReader(text));
- // Get 3 best fragments and seperate with a "..."
- String result = highlighter.getBestFragments(tokenStream,text,3,"...");
- System.out.println(result);
- }
+ IndexSearcher searcher = new IndexSearcher(ramDir);
+ Query query = QueryParser.parse("Kenne*", FIELD_NAME, analyzer);
+ query = query.rewrite(reader); //required to expand search terms
+ Hits hits = searcher.search(query);
+
+ Highlighter highlighter = new Highlighter(this, new QueryScorer(query));
+ for (int i = 0; i < hits.length(); i++)
+ {
+ String text = hits.doc(i).get(FIELD_NAME);
+ TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new \
StringReader(text)); + // Get 3 best fragments and seperate with a "..."
+ String result = highlighter.getBestFragments(tokenStream, text, 3, "...");
+ System.out.println(result);
+ }
</pre>
+
<h2>New features 06/02/2005</h2>
+
This release adds options for encoding (thanks to Nicko Cadell).
An "Encoder" implementation such as the new SimpleHTMLEncoder class can be passed to \
the highlighter to encode all those non-xhtml standard characters such as & into \
legal values. This simple class may not suffice for some languages - Commons Lang \
has an implementation that could be used: escapeHtml(String) in \
http://svn.apache.org/viewcvs.cgi/jakarta/commons/proper/lang/trunk/src/java/org/apache/commons/lang/StringEscapeUtils.java?rev=137958&view=markup
-
-
<h2>New features 22/12/2004</h2>
+
This release adds some new capabilities:
<ol>
<li>Faster highlighting using Term vector support</li>
<li>New formatting options to use color intensity to show informational value</li>
<li>Options for better summarization by using term IDF scores to influence fragment \
selection</li> </ol>
+
<p>
The highlighter takes a TokenStream as input. Until now these streams have typically \
been produced using an Analyzer but the new class TokenSources provides helper \
methods for obtaining TokenStreams from the new TermVector position support (see \
latest CVS version).</p> +
<p>The new class GradientFormatter can use a scale of colors to highlight terms \
according to their score. A subtle use of color can help emphasise the reasons for \
matching (useful when doing "MoreLikeThis" queries and
-you want to see what the basis of the similarities are)</p>
+you want to see what the basis of the similarities are).</p>
+
<p>The QueryScorer class has a new constructor which can use an IndexReader to \
derive the IDF (inverse document frequency) for each term in order to influcence the \
score. This is useful for helping to extracting the most significant sections of a \
document and in supplying scores used by the new GradientFormatter to color \
significant words more strongly.
---------------------------------------------------------------------
To unsubscribe, e-mail: lucene-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: lucene-dev-help@jakarta.apache.org
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic