SOLR-1859: speed up indexing for example schema

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@930050 13f79535-47bb-0310-9956-ffa450edef68

solr/client/ruby/solr-ruby/solr/conf/schema.xml

@@ -155,7 +155,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>

solr/client/ruby/solr-ruby/test/conf/schema.xml

@@ -149,7 +149,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -158,7 +159,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>
@@ -173,7 +175,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>

solr/contrib/clustering/src/test/resources/solr/conf/schema.xml

@@ -175,7 +175,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -184,7 +185,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -199,7 +201,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/contrib/dataimporthandler/src/extras/test/resources/solr/conf/dataimport-schema-no-unique-key.xml

@@ -167,7 +167,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/contrib/dataimporthandler/src/test/resources/solr/conf/dataimport-schema.xml

@@ -167,7 +167,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -191,7 +193,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/contrib/dataimporthandler/src/test/resources/solr/conf/dataimport-solr_id-schema.xml

@@ -167,7 +167,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -191,7 +193,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/contrib/extraction/src/test/resources/solr/conf/schema.xml

@@ -121,10 +121,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <!-- lucene PorterStemFilterFactory deprecated
+        <filter class="solr.PorterStemFilterFactory"/>
-          <filter class="solr.PorterStemFilterFactory"/>
-        -->
-        <filter class="solr.EnglishPorterFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -247,14 +244,14 @@
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -302,7 +299,7 @@
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.SynonymFilterFactory"
                   synonyms="synonyms.txt" expand="true" />
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
           <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldtype>

solr/contrib/velocity/src/main/solr/conf/schema.xml

@@ -220,7 +220,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -232,7 +233,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldType>
 
@@ -246,7 +248,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
              possible with WordDelimiterFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>

solr/example/example-DIH/solr/db/conf/schema.xml

@@ -167,7 +167,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -191,7 +193,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/mail/conf/schema.xml

@@ -212,7 +212,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -225,7 +226,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -240,7 +242,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/rss/conf/schema.xml

@@ -167,7 +167,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -191,7 +193,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -243,7 +246,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -252,7 +256,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>

solr/example/example-DIH/solr/tika/conf/schema.xml

@@ -167,7 +167,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <!--<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>-->
+        <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>-->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/solr/conf/schema.xml

@@ -231,7 +231,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -243,7 +244,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldType>
 
@@ -257,7 +259,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
              possible with WordDelimiterFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>

solr/src/test/org/apache/solr/handler/DocumentAnalysisRequestHandlerTest.java

@@ -190,8 +190,8 @@ public class DocumentAnalysisRequestHandlerTest extends AnalysisRequestHandlerTe
     assertNotNull("Expecting the 'StopFilter' to be applied on the query for the 'text' field", tokenList);
     assertEquals("Query has only one token", 1, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("jumping", null, "<ALPHANUM>", 0, 7, 1, null, false));
-    tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.snowball.SnowballFilter");
+    tokenList = (List<NamedList>) queryResult.get("org.apache.lucene.analysis.PorterStemFilter");
-    assertNotNull("Expecting the 'SnowballFilter' to be applied on the query for the 'text' field", tokenList);
+    assertNotNull("Expecting the 'PorterStemFilter' to be applied on the query for the 'text' field", tokenList);
     assertEquals("Query has only one token", 1, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("jump", null, "<ALPHANUM>", 0, 7, 1, null, false));
     indexResult = textResult.get("index");
@@ -231,8 +231,8 @@ public class DocumentAnalysisRequestHandlerTest extends AnalysisRequestHandlerTe
     assertToken(tokenList.get(1), new TokenInfo("jumped", null, "<ALPHANUM>", 8, 14, 2, null, false));
     assertToken(tokenList.get(2), new TokenInfo("over", null, "<ALPHANUM>", 15, 19, 3, null, false));
     assertToken(tokenList.get(3), new TokenInfo("dogs", null, "<ALPHANUM>", 24, 28, 4, null, false));
-    tokenList = valueResult.get("org.apache.lucene.analysis.snowball.SnowballFilter");
+    tokenList = valueResult.get("org.apache.lucene.analysis.PorterStemFilter");
-    assertNotNull("Expecting the 'SnowballFilter' to be applied on the index for the 'text' field", tokenList);
+    assertNotNull("Expecting the 'PorterStemFilter' to be applied on the index for the 'text' field", tokenList);
     assertEquals("Expecting 4 tokens", 4, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 4, 7, 1, null, false));
     assertToken(tokenList.get(1), new TokenInfo("jump", null, "<ALPHANUM>", 8, 14, 2, null, true));

solr/src/test/org/apache/solr/handler/FieldAnalysisRequestHandlerTest.java

@@ -173,8 +173,8 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
     assertToken(tokenList.get(5), new TokenInfo("lazy", null, "<ALPHANUM>", 34, 38, 6, null, false));
     assertToken(tokenList.get(6), new TokenInfo("brown", null, "<ALPHANUM>", 39, 44, 7, null, true));
     assertToken(tokenList.get(7), new TokenInfo("dogs", null, "<ALPHANUM>", 45, 49, 8, null, false));
-    tokenList = indexPart.get("org.apache.lucene.analysis.snowball.SnowballFilter");
+    tokenList = indexPart.get("org.apache.lucene.analysis.PorterStemFilter");
-    assertNotNull("Expcting SnowballFilter analysis breakdown", tokenList);
+    assertNotNull("Expcting PorterStemFilter analysis breakdown", tokenList);
     assertEquals(tokenList.size(), 8);
     assertToken(tokenList.get(0), new TokenInfo("quick", null, "<ALPHANUM>", 4, 9, 1, null, false));
     assertToken(tokenList.get(1), new TokenInfo("red", null, "<ALPHANUM>", 10, 13, 2, null, false));
@@ -208,8 +208,8 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
     assertEquals(2, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, null, false));
     assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, null, false));
-    tokenList = queryPart.get("org.apache.lucene.analysis.snowball.SnowballFilter");
+    tokenList = queryPart.get("org.apache.lucene.analysis.PorterStemFilter");
-    assertNotNull("Expcting SnowballFilter analysis breakdown", tokenList);
+    assertNotNull("Expcting PorterStemFilter analysis breakdown", tokenList);
     assertEquals(2, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("fox", null, "<ALPHANUM>", 0, 3, 1, null, false));
     assertToken(tokenList.get(1), new TokenInfo("brown", null, "<ALPHANUM>", 4, 9, 2, null, false));

solr/src/test/test-files/solr/conf/schema-copyfield-test.xml

@@ -113,10 +113,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <!-- lucene PorterStemFilterFactory deprecated
+        <filter class="solr.PorterStemFilterFactory"/>
-          <filter class="solr.PorterStemFilterFactory"/>
-        -->
-        <filter class="solr.EnglishPorterFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -239,14 +236,14 @@
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -294,7 +291,7 @@
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.SynonymFilterFactory"
                   synonyms="synonyms.txt" expand="true" />
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
           <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldtype>

solr/src/test/test-files/solr/conf/schema-luceneMatchVersion.xml

@@ -23,7 +23,7 @@
       <filter class="solr.StandardFilterFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory" luceneMatchVersion="2.4"/>
-      <filter class="solr.EnglishPorterFilterFactory"/>
+      <filter class="solr.PorterStemFilterFactory"/>
     </analyzer>
   </fieldtype>
   <fieldtype name="textDefault" class="solr.TextField">
@@ -32,7 +32,7 @@
       <filter class="solr.StandardFilterFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
-      <filter class="solr.EnglishPorterFilterFactory"/>
+      <filter class="solr.PorterStemFilterFactory"/>
     </analyzer>
   </fieldtype>
   <fieldtype name="textStandardAnalyzer20" class="solr.TextField">

solr/src/test/test-files/solr/conf/schema-required-fields.xml

@@ -104,10 +104,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <!-- lucene PorterStemFilterFactory deprecated
+        <filter class="solr.PorterStemFilterFactory"/>
-          <filter class="solr.PorterStemFilterFactory"/>
-        -->
-        <filter class="solr.EnglishPorterFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -230,14 +227,14 @@
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -285,7 +282,7 @@
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.SynonymFilterFactory"
                   synonyms="synonyms.txt" expand="true" />
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
           <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldtype>

solr/src/test/test-files/solr/conf/schema-spellchecker.xml

@@ -42,7 +42,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 

solr/src/test/test-files/solr/conf/schema-trie.xml

@@ -176,7 +176,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -185,7 +186,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -200,7 +202,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/src/test/test-files/solr/conf/schema.xml

@@ -134,10 +134,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <!-- lucene PorterStemFilterFactory deprecated
+        <filter class="solr.PorterStemFilterFactory"/>
-          <filter class="solr.PorterStemFilterFactory"/>
-        -->
-        <filter class="solr.EnglishPorterFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -272,14 +269,14 @@
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -289,14 +286,14 @@
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
           <filter class="solr.StopFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -357,7 +354,7 @@
           <tokenizer class="solr.WhitespaceTokenizerFactory"/>
           <filter class="solr.SynonymFilterFactory"
                   synonyms="old_synonyms.txt" expand="true" />
-          <filter class="solr.EnglishPorterFilterFactory"/>
+          <filter class="solr.PorterStemFilterFactory"/>
           <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldtype>

solr/src/test/test-files/solr/conf/schema11.xml

@@ -167,7 +167,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
@@ -176,7 +177,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
@@ -191,7 +193,8 @@
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/src/test/test-files/solr/conf/schema12.xml

@@ -126,7 +126,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -138,7 +139,8 @@
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldType>
 

solr/src/test/test-files/solr/crazy-path-to-schema.xml

@@ -32,7 +32,7 @@
         <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
     </fieldtype>
  </types>