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

SOLR-5202: cleaned up comments surrounding clustering component. Left all the algorithms in there, but added a pointer to integration-strategies which includes more exhaustive configuration examples. 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1521804 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Dawid Weiss 2013-09-11 11:24:19 +00:00
parent 3cf82592c1
commit 49a7ccee8c
1 changed files with 24 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
solr/example/solr/collection1/conf/solrconfig.xml
View File

@ -1381,6 +1381,7 @@
<!-- Clustering Component <!-- Clustering Component
http://wiki.apache.org/solr/ClusteringComponent http://wiki.apache.org/solr/ClusteringComponent
http://carrot2.github.io/solr-integration-strategies/
--> -->
<searchComponent name="clustering" <searchComponent name="clustering"
enable="${solr.clustering.enabled:true}" enable="${solr.clustering.enabled:true}"
@ -1391,8 +1392,7 @@
<lst name="engine"> <lst name="engine">
<str name="name">default</str> <str name="name">default</str>
<!-- Class name of a clustering algorithm compatible with the Carrot2 <!-- Class name of a clustering algorithm compatible with the Carrot2 framework.
framework.
Currently available open source algorithms are: Currently available open source algorithms are:
* org.carrot2.clustering.lingo.LingoClusteringAlgorithm * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
@ -1411,18 +1411,14 @@
A directory from which to load algorithm-specific stop words, A directory from which to load algorithm-specific stop words,
stop labels and attribute definition XMLs. stop labels and attribute definition XMLs.
Absolute or relative to Solr config directory.
If a specific resource (e.g. stopwords.en) is present in the
specified dir, it will completely override the corresponding
default one that typically ships with each algorithm.
For an overview of Carrot2 lexical resources, see: For an overview of Carrot2 lexical resources, see:
http://download.carrot2.org/head/manual/#chapter.lexical-resources http://download.carrot2.org/head/manual/#chapter.lexical-resources
For an overview of Lingo3G lexical resources, see: For an overview of Lingo3G lexical resources, see:
http://download.carrotsearch.com/lingo3g/manual/#chapter.lexical-resources http://download.carrotsearch.com/lingo3g/manual/#chapter.lexical-resources
--> -->
<!-- <str name="carrot.resourcesDir">clustering/carrot2</str> --> <str name="carrot.resourcesDir">clustering/carrot2</str>
</lst> </lst>
<!-- An example definition for the STC clustering algorithm. --> <!-- An example definition for the STC clustering algorithm. -->
@ -1453,26 +1449,28 @@
<bool name="clustering">true</bool> <bool name="clustering">true</bool>
<str name="clustering.engine">default</str> <str name="clustering.engine">default</str>
<bool name="clustering.results">true</bool> <bool name="clustering.results">true</bool>
<!-- The title field --> <!-- Field name with the logical "title" of a each document (optional) -->
<str name="carrot.title">name</str> <str name="carrot.title">name</str>
<!-- Field name with the logical "URL" of a each document (optional) -->
<str name="carrot.url">id</str> <str name="carrot.url">id</str>
<!-- The field to cluster on --> <!-- Field name with the logical "content" of a each document (optional) -->
<str name="carrot.snippet">features</str> <str name="carrot.snippet">features</str>
<!-- produce summaries --> <!-- Apply highlighter to the title/ content and use this for clustering. -->
<bool name="carrot.produceSummary">true</bool> <bool name="carrot.produceSummary">true</bool>
<!-- the maximum number of labels per cluster --> <!-- the maximum number of labels per cluster -->
<!--<int name="carrot.numDescriptions">5</int>--> <!--<int name="carrot.numDescriptions">5</int>-->
<!-- produce sub clusters --> <!-- produce sub clusters -->
<bool name="carrot.outputSubClusters">false</bool> <bool name="carrot.outputSubClusters">false</bool>
<str name="defType">edismax</str> <!-- Configure the remaining request handler parameters. -->
<str name="qf"> <str name="defType">edismax</str>
text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4 <str name="qf">
</str> text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
<str name="q.alt">*:*</str> </str>
<str name="rows">10</str> <str name="q.alt">*:*</str>
<str name="fl">*,score</str> <str name="rows">10</str>
</lst> <str name="fl">*,score</str>
</lst>
<arr name="last-components"> <arr name="last-components">
<str>clustering</str> <str>clustering</str>
</arr> </arr>