|
@@ -22,7 +22,7 @@
|
|
|
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
|
|
then default lucene sorting will be used which places docs without the
|
|
|
field first in an ascending sort and last in a descending sort.
|
|
|
- -->
|
|
|
+ -->
|
|
|
|
|
|
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
|
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
@@ -86,7 +86,7 @@
|
|
|
|
|
|
<!-- A text field with defaults appropriate for English: it
|
|
|
tokenizes with StandardTokenizer, removes English stop words
|
|
|
- (stopwords_en.txt), down cases, protects words from protwords.txt, and
|
|
|
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
|
|
|
finally applies Porter's stemming. The query time analyzer
|
|
|
also applies synonyms from synonyms.txt. -->
|
|
|
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
@@ -101,7 +101,7 @@
|
|
|
-->
|
|
|
<filter class="solr.StopFilterFactory"
|
|
|
ignoreCase="true"
|
|
|
- words="stopwords_en.txt"
|
|
|
+ words="lang/stopwords_en.txt"
|
|
|
enablePositionIncrements="true"
|
|
|
/>
|
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
@@ -117,7 +117,7 @@
|
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
|
<filter class="solr.StopFilterFactory"
|
|
|
ignoreCase="true"
|
|
|
- words="stopwords_en.txt"
|
|
|
+ words="lang/stopwords_en.txt"
|
|
|
enablePositionIncrements="true"
|
|
|
/>
|
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
@@ -154,7 +154,7 @@
|
|
|
-->
|
|
|
<filter class="solr.StopFilterFactory"
|
|
|
ignoreCase="true"
|
|
|
- words="stopwords_en.txt"
|
|
|
+ words="lang/stopwords_en.txt"
|
|
|
enablePositionIncrements="true"
|
|
|
/>
|
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
|
|
@@ -167,7 +167,7 @@
|
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
|
<filter class="solr.StopFilterFactory"
|
|
|
ignoreCase="true"
|
|
|
- words="stopwords_en.txt"
|
|
|
+ words="lang/stopwords_en.txt"
|
|
|
enablePositionIncrements="true"
|
|
|
/>
|
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
@@ -183,7 +183,7 @@
|
|
|
<analyzer>
|
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
|
|
|
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
@@ -202,14 +202,14 @@
|
|
|
</fieldtype>
|
|
|
|
|
|
<!-- since fields of this type are by default not stored or indexed,
|
|
|
- any data added to them will be ignored outright. -->
|
|
|
+ any data added to them will be ignored outright. -->
|
|
|
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
|
|
</types>
|
|
|
|
|
|
<fields>
|
|
|
<!-- Valid attributes for fields:
|
|
|
name: mandatory - the name for the field
|
|
|
- type: mandatory - the name of a previously defined type from the
|
|
|
+ type: mandatory - the name of a previously defined type from the
|
|
|
<types> section
|
|
|
indexed: true if this field should be indexed (searchable or sortable)
|
|
|
stored: true if this field should be retrievable
|
|
@@ -222,23 +222,23 @@
|
|
|
given field.
|
|
|
When using MoreLikeThis, fields used for similarity should be
|
|
|
stored for best performance.
|
|
|
- termPositions: Store position information with the term vector.
|
|
|
+ termPositions: Store position information with the term vector.
|
|
|
This will increase storage costs.
|
|
|
- termOffsets: Store offset information with the term vector. This
|
|
|
+ termOffsets: Store offset information with the term vector. This
|
|
|
will increase storage costs.
|
|
|
default: a value that should be used if no value is specified
|
|
|
when adding a document.
|
|
|
-->
|
|
|
|
|
|
- <field name="id" type="string" indexed="true" stored="true" required="true" />
|
|
|
+ <field name="id" type="string" indexed="true" stored="true" required="true" />
|
|
|
<field name="name" type="text_general_rev" indexed="true" stored="true"/>
|
|
|
<field name="description" type="text_general_rev" indexed="true" stored="true"/>
|
|
|
<field name="tags" type="text_general_rev" indexed="true" stored="true" multiValued="true"/>
|
|
|
-
|
|
|
+
|
|
|
<!-- catchall field, containing all other searchable text fields (implemented
|
|
|
via copyField further on in this schema -->
|
|
|
<field name="text" type="text_en" indexed="true" stored="false" multiValued="true"/>
|
|
|
-
|
|
|
+
|
|
|
<!-- extra name field allowing dashes to be omitted/misplaced -->
|
|
|
<field name="name_split" type="text_en_splitting_tight" indexed="true" stored="false" />
|
|
|
|
|
@@ -246,7 +246,7 @@
|
|
|
<field name="text_ngram" type="text_edgengram" indexed="true" stored="false" multiValued="true" />
|
|
|
</fields>
|
|
|
|
|
|
- <!-- Field to use to determine and enforce document uniqueness.
|
|
|
+ <!-- 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>
|