You are viewing a plain text version of this content. The canonical link for it is here.
Posted to solr-user@lucene.apache.org by Andreas Owen <ao...@conx.ch> on 2013/09/24 20:35:30 UTC

dih HTMLStripTransformer

why does stripHTML="false" have no effect in dih? the html is strippedin text and text_nohtml when i do display the index with select?q=*

i'm trying to get a field without html and one with it so i can also index the links on the page.

data-config.xml
<entity name="rec" processor="XPathEntityProcessor" url="file:///C:\ColdFusion10\cfusion\solr\solr\tkbintranet\docImportUrl.xml" forEach="/docs/doc" dataSource="main"> <!-- transformer="script:GenerateId"-->
		<field column="title" xpath="//title" />
		<field column="id" xpath="//id" />
		<field column="file" xpath="//file" />
		<field column="url" xpath="//url" />
		<field column="urlParse" xpath="//urlParse" />
		<field column="last_modified" xpath="//last_modified" />
		<field column="Author" xpath="//author" />
		
		<entity name="tika" processor="TikaEntityProcessor" url="${rec.urlParse}" dataSource="dataUrl" onError="skip" htmlMapper="identity" format="html" transformer="HTMLStripTransformer">
			<field column="text" name="text" stripHTML="false" />
			<field column="text" name="text_nohtml" stripHTML="true" />
			<!--  transformer="RegexTransformer"
			<field column="text_html_b" regex="(?s)^.*&lt;div.*id=.*&gt;(.*)&lt;/div&gt;.*$" replaceWith="$1" sourceColName="text"  />
			<field column="text_html_b" regex="(?s)^.*&lt;!-body-&gt;(.*)&lt;!-/body-&gt;.*$" replaceWith="$1" sourceColName="text"  /> -->
		</entity>
	</entity>