hey...

i work with tika and Solr, at the Moment, i can index Dokument information
but nur content..

to the details:

part of my config:

<requestHandler name="/update/extract"
class="org.apache.solr.handler.extraction.ExtractingRequestHandler"
startup="lazy">
<lst name="defaults">
<str name="ext.map.Last-Modified">last_modified</str>
<bool name="ext.ignore.und.fl">true</bool>
<str name="fmap.content">text</str>
<str name="lowernames">true</str>
<str name="uprefix">ignored_</str>
<str name="captureAttr">true</str>
<str name="fmap.a">links</str>
<str name="fmap.div">ignored_</str>
</lst>
</requestHandler>

Part of my Schema:

<field name="id" type="string" indexed="true" stored="true"
required="true"/>
<field name="sku" type="textTight" indexed="true" stored="true"
omitNorms="true"/>
<field name="name" type="textgen" indexed="true" stored="true"/>
<field name="alphaNameSort" type="alphaOnlySort" indexed="true"
stored="false"/>
<field name="manu" type="textgen" indexed="true" stored="true"
omitNorms="true"/>
<field name="cat" type="text_ws" indexed="true" stored="true"
multiValued="true" omitNorms="true"/>
<field name="features" type="text" indexed="true" stored="true"
multiValued="true"/>
<field name="includes" type="text" indexed="true" stored="true"
termVectors="true" termPositions="true" termOffsets="true"/>
<field name="weight" type="float" indexed="true" stored="true"/>
<field name="price" type="float" indexed="true" stored="true"/>
<field name="popularity" type="int" indexed="true" stored="true"/>
<field name="inStock" type="boolean" indexed="true" stored="true"/>
<field name="title" type="text" indexed="true" stored="true"
multiValued="true"/>
<field name="subject" type="text" indexed="true" stored="true"/>
<field name="description" type="text" indexed="true" stored="true"/>
<field name="comments" type="text" indexed="true" stored="true"/>
<field name="author" type="textgen" indexed="true" stored="true"/>
<field name="keywords" type="textgen" indexed="true" stored="true"/>
<field name="category" type="textgen" indexed="true" stored="true"/>
<field name="content_type" type="string" indexed="true" stored="true"
multiValued="true"/>
<field name="last_modified" type="date" indexed="true" stored="true"/>
<field name="links" type="string" indexed="true" stored="true"
multiValued="true"/>
<field name="text" type="text" indexed="true" stored="false"
multiValued="true"/>

curl command:

curl "
http://192.168.105.66:8983/solr/update/extract?literal.id=1234&uprefix=attr_commit=true";
-F "myfile=@Word-Text.doc"

result in Solr:

<doc>
-
<arr name="attr_commit=trueapplication_name">
<str>TX_WORD 10.1.210.500</str>
</arr>
-
<arr name="attr_commit=truestream_content_type">
<str>application/octet-stream</str>
</arr>
-
<arr name="attr_commit=truestream_name">
<str>Word-Text.doc</str>
</arr>
-
<arr name="attr_commit=truestream_size">
<str>43592</str>
</arr>
-
<arr name="attr_commit=truestream_source_info">
<str>myfile</str>
</arr>
-
<arr name="content_type">
<str>application/msword</str>
</arr>
<str name="id">1234</str>
</doc>

_________________________________________________________
_________________________________________________________
_________________________________________________________

But i need the Content to.. what i make wrong?

Thanks for Halt

King

Reply via email to