litvinovg/vitro
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Adding solr indexing prototype

Browse source
This commit is contained in:
briancaruso 2011-04-11 17:21:38 +00:00
parent 9bfa6acbd5
commit 543c1cd945
9 changed files with 442 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

90
solr/exampleSolr/conf/schema.xml
View file

@ -46,14 +46,6 @@
-->
<schema name="example" version="1.2">
<!-- attribute "name" is the name of this schema and is only used for display purposes.
Applications should change this to reflect the nature of the search collection.
version="1.2" is Solr's version number for the schema syntax and semantics. It should
not normally be changed by applications.
1.0: multiValued attribute did not exist, all fields are multiValued by nature
1.1: multiValued attribute introduced, false by default
1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
-->
<types>
<!-- field type definitions. The "name" attribute is
@ -426,36 +418,37 @@
when adding a document.
-->
<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" />
<!-- Common metadata fields, named specifically to match up with
SolrCell metadata when parsing rich documents such as Word, PDF.
Some fields are multiValued only because Tika currently may return
multiple values for them.
-->
<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"/>
<!-- **************************** Vitro Fields *************************** -->
<field name="DocId" type="string" indexed="true" stored="true" required="true" />
<field name="type" type="string" indexed="true" stored="true" omitNorms="ture" multiValued="true"/>
<field name="classLocalName" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="classLocalNameLowerCase" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="classgroup" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="PROHIBITED_FROM_TEXT_RESULTS" type="string" indexed="true" stored="false" multiValued="false"/>
<field name="URI" type="string" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
<field name="name" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="nameunstemmed" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="nameunanalyzed" type="string" indexed="true" stored="false" multiValued="true"/>
<field name="nameraw" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="indexedTime" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="ALLTEXT" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="ALLTEXTUNSTEMMED" type="textgen" indexed="true" stored="false" multiValued="true"/>
<field name="THUMBNAIL" type="string" indexed="true" stored="true"/>
<field name="moniker" type="ignored" />
<field name="modType" type="ignored"/>
<field name="JCLASS" type="ignored"/>
<!-- catchall field, containing all other searchable text fields (implemented
@ -466,19 +459,7 @@
leading wildcard queries. -->
<field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
<!-- non-tokenized version of manufacturer to make it easier to sort or group
results by manufacturer. copied from "manu" via copyField -->
<field name="manu_exact" type="string" indexed="true" stored="false"/>
<field name="payloads" type="payloads" indexed="true" stored="true"/>
<!-- Uncommenting the following will create a "timestamp" field using
a default value of "NOW" to indicate when each document was indexed.
-->
<!--
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-->
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
@ -521,10 +502,10 @@
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<uniqueKey>DocId</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<defaultSearchField>ALLTEXT</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
@ -533,12 +514,7 @@
is added to the index. It's used either to index the same field differently,
or to add multiple fields to the same field for easier/faster searching. -->
<copyField source="cat" dest="text"/>
<copyField source="name" dest="text"/>
<copyField source="manu" dest="text"/>
<copyField source="features" dest="text"/>
<copyField source="includes" dest="text"/>
<copyField source="manu" dest="manu_exact"/>
<!-- <copyField source="name" dest="text"/> -->
<!-- Above, multiple source fields are copied to the [text] field.
Another way to map multiple source fields to the same

2
solr/exampleSolr/conf/solrconfig.xml
View file

@ -68,7 +68,7 @@
<!-- Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home.
If replication is in use, this should match the replication configuration. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<!-- <dataDir>${solr.data.dir:./solr/data}</dataDir> -->
<!-- WARNING: this <indexDefaults> section only provides defaults for index writers