Pyoungmeister has submitted this change and it was merged.

Change subject: Update TTMServer Solr schema
......................................................................


Update TTMServer Solr schema

Bug: 46840
Change-Id: Ic8d552207f75f456210b94cda45ab1d24915887e
---
M modules/solr/files/schema-ttmserver.xml
1 file changed, 8 insertions(+), 16 deletions(-)

Approvals:
  Pyoungmeister: Looks good to me, approved
  jenkins-bot: Verified



diff --git a/modules/solr/files/schema-ttmserver.xml 
b/modules/solr/files/schema-ttmserver.xml
index 2799f76..0ed2f04 100644
--- a/modules/solr/files/schema-ttmserver.xml
+++ b/modules/solr/files/schema-ttmserver.xml
@@ -5,23 +5,15 @@
                <fieldType name="long" class="solr.TrieLongField" 
precisionStep="0" positionIncrementGap="0"/>
                <fieldType name="string" class="solr.StrField" 
sortMissingLast="true" />
                <fieldType name="tint" class="solr.TrieIntField" 
precisionStep="50" positionIncrementGap="0"/>
-               <fieldType name="text_en" class="solr.TextField" 
positionIncrementGap="100">
-                       <analyzer type="index">
-                               <tokenizer 
class="solr.StandardTokenizerFactory"/>
-                               <filter class="solr.LowerCaseFilterFactory"/>
-                               <filter 
class="solr.EnglishPossessiveFilterFactory"/>
-                               <filter class="solr.PorterStemFilterFactory"/>
-                       </analyzer>
-                       <analyzer type="query">
-                               <tokenizer 
class="solr.StandardTokenizerFactory"/>
-                               <filter class="solr.LowerCaseFilterFactory"/>
-                               <filter class="solr.KeywordMarkerFilterFactory" 
protected="protwords.txt"/>
-                               <filter class="solr.PorterStemFilterFactory"/>
-                       </analyzer>
-               </fieldType>
+               <!-- Our input can basically be in any language, so we use 
either
+                    language agnostic processing or something that can adapt to
+                    the language in question. -->
                <fieldType name="text_ws" class="solr.TextField" 
positionIncrementGap="100">
                        <analyzer>
-                               <tokenizer 
class="solr.WhitespaceTokenizerFactory"/>
+                               <!-- Consider using solr.ICUTokenizerFactory -->
+                               <tokenizer 
class="solr.StandardTokenizerFactory"/>
+                               <!-- Consider using 
solr.ICUNormalizer2FilterFactory -->
+                               <filter class="solr.LowerCaseFilterFactory"/>
                        </analyzer>
                </fieldType>
        </types>
@@ -45,7 +37,7 @@
 
                <field name="content" type="string" indexed="true" 
stored="true" required="true" />
 
-               <field name="text" type="text_ws" indexed="true" stored="false" 
/>
+               <field name="text" type="text_ws" indexed="true" stored="true" 
termVectors="true" termPositions="true" termOffsets="true" />
                <copyField source="content" dest="text"/>
        </fields>
        <defaultSearchField>text</defaultSearchField>

-- 
To view, visit https://gerrit.wikimedia.org/r/57498
To unsubscribe, visit https://gerrit.wikimedia.org/r/settings

Gerrit-MessageType: merged
Gerrit-Change-Id: Ic8d552207f75f456210b94cda45ab1d24915887e
Gerrit-PatchSet: 6
Gerrit-Project: operations/puppet
Gerrit-Branch: production
Gerrit-Owner: Nikerabbit <[email protected]>
Gerrit-Reviewer: MaxSem <[email protected]>
Gerrit-Reviewer: Nikerabbit <[email protected]>
Gerrit-Reviewer: Pyoungmeister <[email protected]>
Gerrit-Reviewer: Siebrand <[email protected]>
Gerrit-Reviewer: jenkins-bot

_______________________________________________
MediaWiki-commits mailing list
[email protected]
https://lists.wikimedia.org/mailman/listinfo/mediawiki-commits

Reply via email to