SOLR-10344: Update Solr default/example and test configs to use WordDelimiterGraphFilterFactory

solr/CHANGES.txt

@@ -157,6 +157,8 @@ Other Changes
 
 * SOLR-10352: bin/solr script now prints warning when available system entropy is lower than 300 (Esther Quansah via
   Ishan Chattopadhyaya)
+  
+* SOLR-10344: Update Solr default/example and test configs to use WordDelimiterGraphFilterFactory. (Steve Rowe)
 
 ==================  6.5.0 ==================
 

solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/schema.xml

@@ -155,7 +155,7 @@
     </analyzer>
   </fieldType>
 
-  <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+  <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
       words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
       so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
       Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -174,18 +174,19 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -198,11 +199,23 @@
   <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
        but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
   <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+      <filter class="solr.EnglishMinimalStemFilterFactory"/>
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/contrib/clustering/src/test-files/clustering/solr/collection1/conf/synonyms.txt

@@ -23,7 +23,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/contrib/dataimporthandler-extras/src/test-files/dihextras/solr/collection1/conf/dataimport-schema-no-unique-key.xml

@@ -158,7 +158,7 @@
     </analyzer>
   </fieldType>
 
-  <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+  <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
       words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
       so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
       Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -172,18 +172,19 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>-->
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-schema.xml

@@ -10,23 +10,32 @@
   <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
     </analyzer>
   </fieldType>
   <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>

solr/contrib/dataimporthandler/src/test-files/dih/solr/collection1/conf/dataimport-solr_id-schema.xml

@@ -156,7 +156,7 @@
     </analyzer>
   </fieldType>
 
-  <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+  <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
       words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
       so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
       Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -170,18 +170,19 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>-->
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>-->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -194,11 +195,23 @@
   <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
        but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
   <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+      <filter class="solr.EnglishMinimalStemFilterFactory"/>-->
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <!--<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>-->
+      <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <!--<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/contrib/extraction/src/test-files/extraction/solr/collection1/conf/schema.xml

@@ -55,26 +55,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -233,15 +248,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -253,13 +269,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -269,13 +286,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/contrib/ltr/src/test-files/solr/collection1/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/contrib/uima/src/test-files/uima/solr/collection1/conf/schema.xml

@@ -191,7 +191,7 @@
     </fieldType>
 
     <!--
-      A text field that uses WordDelimiterFilter to enable splitting and
+      A text field that uses WordDelimiterGraphFilter to enable splitting and
       matching of words on case-change, alpha numeric boundaries, and
       non-alphanumeric chars, so that a query of "wifi" or "wi fi" could
       match a document containing "Wi-Fi". Synonyms and stopwords are
@@ -212,11 +212,11 @@
         -->
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="1"
           catenateNumbers="1" catenateAll="0" splitOnCaseChange="1" />
         <filter class="solr.LowerCaseFilterFactory" />
-        
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory" />
@@ -224,7 +224,7 @@
           ignoreCase="true" expand="true" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="0"
           catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" />
         <filter class="solr.LowerCaseFilterFactory" />
@@ -240,23 +240,36 @@
     -->
     <fieldType name="textTight" class="solr.TextField"
       positionIncrementGap="100">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory" />
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
           ignoreCase="true" expand="false" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="0" generateNumberParts="0" catenateWords="1"
           catenateNumbers="1" catenateAll="0" />
         <filter class="solr.LowerCaseFilterFactory" />
         
         <!--
           this filter can remove any duplicate tokens that appear at the
-          same position - sometimes possible with WordDelimiterFilter in
+          same position - sometimes possible with WordDelimiterGraphFilter in
           conjuncton with stemming.
         -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.MockTokenizerFactory" />
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt"
+                ignoreCase="true" expand="false" />
+        <filter class="solr.StopFilterFactory" ignoreCase="true"
+                words="stopwords.txt" />
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0" generateNumberParts="0" catenateWords="1"
+                catenateNumbers="1" catenateAll="0" />
+        <filter class="solr.LowerCaseFilterFactory" />
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldType>
 
@@ -271,10 +284,11 @@
         <tokenizer class="solr.MockTokenizerFactory" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="1"
           catenateNumbers="1" catenateAll="0" splitOnCaseChange="0" />
         <filter class="solr.LowerCaseFilterFactory" />
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory" />
@@ -282,7 +296,7 @@
           ignoreCase="true" expand="true" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="0"
           catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
         <filter class="solr.LowerCaseFilterFactory" />
@@ -301,13 +315,14 @@
         <tokenizer class="solr.MockTokenizerFactory" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="1"
           catenateNumbers="1" catenateAll="0" splitOnCaseChange="0" />
         <filter class="solr.LowerCaseFilterFactory" />
         <filter class="solr.ReversedWildcardFilterFactory"
           withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2"
           maxFractionAsterisk="0.33" />
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory" />
@@ -315,7 +330,7 @@
           ignoreCase="true" expand="true" />
         <filter class="solr.StopFilterFactory" ignoreCase="true"
           words="stopwords.txt" />
-        <filter class="solr.WordDelimiterFilterFactory"
+        <filter class="solr.WordDelimiterGraphFilterFactory"
           generateWordParts="1" generateNumberParts="1" catenateWords="0"
           catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
         <filter class="solr.LowerCaseFilterFactory" />

solr/contrib/uima/src/test-files/uima/solr/collection1/conf/synonyms.txt

@@ -23,7 +23,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/contrib/uima/src/test-files/uima/uima-tokenizers-schema.xml

@@ -191,7 +191,7 @@
   </fieldType>
 
   <!--
-    A text field that uses WordDelimiterFilter to enable splitting and
+    A text field that uses WordDelimiterGraphFilter to enable splitting and
     matching of words on case-change, alpha numeric boundaries, and
     non-alphanumeric chars, so that a query of "wifi" or "wi fi" could
     match a document containing "Wi-Fi". Synonyms and stopwords are
@@ -210,16 +210,18 @@
       <!--
         Case insensitive stop word removal. add
       -->
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
 
+      <filter class="solr.FlattenGraphFilterFactory"/>
+
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
 
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
@@ -235,19 +237,29 @@
   -->
   <fieldType name="textTight" class="solr.TextField"
              positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
 
       <!--
         this filter can remove any duplicate tokens that appear at the
-        same position - sometimes possible with WordDelimiterFilter in
+        same position - sometimes possible with WordDelimiterGraphFilter in
         conjuncton with stemming.
       -->
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+
+      <filter class="solr.FlattenGraphFilterFactory" />
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory"
+              generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
     </analyzer>
   </fieldType>
 
@@ -277,14 +289,15 @@
              positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
@@ -301,17 +314,18 @@
              positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.ReversedWildcardFilterFactory"
               withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2"
               maxFractionAsterisk="0.33"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory"
+      <filter class="solr.WordDelimiterGraphFilterFactory"
               generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema-HighlighterMaxOffsetTest.xml

@@ -67,16 +67,17 @@ Test for HighlighterMaxOffsetTest which requires the use of ReversedWildcardFilt
   <fieldType name="text_stx" class="solr.TextField" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
               maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema-copyfield-test.xml

@@ -60,17 +60,25 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -229,15 +237,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -249,13 +258,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -265,13 +275,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema-docValuesJoin.xml

@@ -42,11 +42,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -55,7 +56,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/core/src/test-files/solr/collection1/conf/schema-folding.xml

@@ -47,7 +47,7 @@
     </analyzer>
     <analyzer type="multiterm">        <!-- Intentionally different to test that these are kept  distinct -->
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.ASCIIFoldingFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema-hash.xml

@@ -72,26 +72,41 @@
   <fieldtype name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldtype name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <fieldtype name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -191,9 +206,16 @@
     </analyzer>
   </fieldtype>
   <fieldtype name="lowerpunctfilt" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+              catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -265,15 +287,16 @@
   <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -285,15 +308,16 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -304,8 +328,9 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -318,13 +343,14 @@
   <fieldtype name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -334,13 +360,14 @@
   <fieldtype name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema-psuedo-fields.xml

@@ -50,11 +50,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -63,7 +64,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/core/src/test-files/solr/collection1/conf/schema-required-fields.xml

@@ -60,9 +60,10 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
@@ -219,15 +220,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -239,13 +241,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -255,13 +258,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema-rest.xml

@@ -45,26 +45,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -90,11 +105,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -103,7 +119,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -153,11 +169,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -166,7 +183,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -300,15 +317,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -320,16 +338,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -341,9 +360,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -356,13 +376,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -372,13 +393,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -401,16 +423,17 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema-single-dynamic-copy-field.xml

@@ -45,26 +45,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -90,11 +105,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -103,7 +119,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -153,11 +169,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -166,7 +183,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -300,15 +317,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -320,16 +338,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -341,9 +360,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -356,13 +376,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -372,13 +393,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -401,16 +423,17 @@
               <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
               -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema-sql.xml

@@ -72,26 +72,41 @@
   <fieldtype name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldtype name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <fieldtype name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -191,9 +206,16 @@
     </analyzer>
   </fieldtype>
   <fieldtype name="lowerpunctfilt" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+              catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -265,15 +287,16 @@
   <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -285,15 +308,16 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -304,8 +328,9 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -318,13 +343,14 @@
   <fieldtype name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -334,13 +360,14 @@
   <fieldtype name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema-trie.xml

@@ -151,7 +151,7 @@
     </analyzer>
   </fieldType>
 
-  <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+  <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
       words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
       so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
       Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -165,18 +165,19 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -189,11 +190,23 @@
   <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
        but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
   <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+      <filter class="solr.EnglishMinimalStemFilterFactory"/>
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>

solr/core/src/test-files/solr/collection1/conf/schema.xml

@@ -55,26 +55,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -196,7 +211,15 @@
     </analyzer>
   </fieldType>
   <fieldType name="lowerpunctfilt" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" expand="true"/>
+      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+              catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" expand="true"/>
       <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
@@ -274,15 +297,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -294,16 +318,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -315,9 +340,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -330,13 +356,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -346,13 +373,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/core/src/test-files/solr/collection1/conf/schema11.xml

@@ -147,7 +147,7 @@
       </analyzer>
     </fieldType>
 
-    <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
+    <!-- A text field that uses WordDelimiterGraphFilter to enable splitting and matching of
         words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
         so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
         Synonyms and stopwords are customized by external files, and stemming is enabled.
@@ -161,17 +161,18 @@
         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
         -->
         <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -183,11 +184,22 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" >
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.MockTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
@@ -417,17 +429,18 @@ valued. -->
             <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
        -->
        <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+       <filter class="solr.FlattenGraphFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.MockTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema12.xml

@@ -54,26 +54,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -99,11 +114,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -112,7 +128,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -129,11 +145,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -142,7 +159,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -270,15 +287,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -290,16 +308,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -311,9 +330,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -326,13 +346,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -342,13 +363,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -371,16 +393,17 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema15.xml

@@ -46,26 +46,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -91,11 +106,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -104,7 +120,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -121,11 +137,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -134,7 +151,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -268,15 +285,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -288,16 +306,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -309,9 +328,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -324,13 +344,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -340,13 +361,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -369,16 +391,17 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/schema_latest.xml

@@ -541,7 +541,7 @@
   <!-- A text field with defaults appropriate for English, plus
  aggressive word-splitting and autophrase features enabled.
  This field is just like text_en, except it adds
- WordDelimiterFilter to enable splitting and matching of
+ WordDelimiterGraphFilter to enable splitting and matching of
  words on case-change, alpha numeric boundaries, and
  non-alphanumeric chars.  This means certain compound word
  cases will work, for example query "wi fi" will match
@@ -560,11 +560,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -573,7 +574,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -585,17 +586,31 @@
        but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
   <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100"
              autoGeneratePhraseQueries="true">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.EnglishMinimalStemFilterFactory"/>
       <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-           possible with WordDelimiterFilter in conjuncton with stemming. -->
+           possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+      <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+              catenateNumbers="1" catenateAll="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+      <filter class="solr.EnglishMinimalStemFilterFactory"/>
+      <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+           possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
       <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
     </analyzer>
   </fieldType>

solr/core/src/test-files/solr/collection1/conf/schemasurround.xml

@@ -47,26 +47,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -92,11 +107,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -105,7 +121,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -122,11 +138,12 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -135,7 +152,7 @@
               ignoreCase="true"
               words="stopwords.txt"
       />
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
@@ -263,15 +280,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -283,16 +301,17 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1"
               catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
@@ -304,9 +323,10 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords.txt" splitOnNumerics="0"
               splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0"
               catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -319,13 +339,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -335,13 +356,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -364,16 +386,17 @@
       <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
       -->
       <!--<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>-->
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
       <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -384,15 +407,16 @@
   <fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.EnglishMinimalStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.EnglishMinimalStemFilterFactory"/>

solr/core/src/test-files/solr/collection1/conf/synonyms.txt

@@ -23,7 +23,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/core/src/test-files/solr/collection1/conf/wdftypes.txt

@@ -13,7 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-# A customized type mapping for WordDelimiterFilterFactory
+# A customized type mapping for WordDelimiterGraphFilterFactory
 # the allowable types are: LOWER, UPPER, ALPHA, DIGIT, ALPHANUM, SUBWORD_DELIM
 # 
 # the default for any character without a mapping is always computed from 

solr/core/src/test-files/solr/configsets/cloud-dynamic/conf/schema.xml

@@ -45,26 +45,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -86,14 +101,15 @@
   <fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -111,14 +127,15 @@
   <fieldType name="text_np" class="solr.TextField" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test-files/solr/configsets/doc-expiry/conf/schema.xml

@@ -45,26 +45,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -86,14 +101,15 @@
   <fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -111,14 +127,15 @@
   <fieldType name="text_np" class="solr.TextField" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>

solr/core/src/test/org/apache/solr/ConvertedLegacyTest.java

@@ -872,7 +872,7 @@ public class ConvertedLegacyTest extends SolrTestCaseJ4 {
             );
 
 
-    // intra-word delimiter testing (WordDelimiterFilter)
+    // intra-word delimiter testing (WordDelimiterGraphFilter)
 
     assertU("<add><doc><field name=\"id\">42</field><field name=\"subword\">foo bar</field></doc></add>");
     assertU("<commit/>");

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

@@ -382,7 +382,7 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
   }
 
   @Test
-  public void testPositionHistoryWithWDF() throws Exception {
+  public void testPositionHistoryWithWDGF() throws Exception {
 
     FieldAnalysisRequest request = new FieldAnalysisRequest();
     request.addFieldType("skutype1");
@@ -407,12 +407,12 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
     assertToken(tokenList.get(1), new TokenInfo("3456-12", null, "word", 4, 11, 2, new int[]{2}, null, false));
     assertToken(tokenList.get(2), new TokenInfo("a", null, "word", 12, 13, 3, new int[]{3}, null, false));
     assertToken(tokenList.get(3), new TokenInfo("Test", null, "word", 14, 18, 4, new int[]{4}, null, false));
-    tokenList = indexPart.get("org.apache.lucene.analysis.miscellaneous.WordDelimiterFilter");
-    assertNotNull("Expcting WordDelimiterFilter analysis breakdown", tokenList);
+    tokenList = indexPart.get("org.apache.lucene.analysis.miscellaneous.WordDelimiterGraphFilter");
+    assertNotNull("Expcting WordDelimiterGraphFilter analysis breakdown", tokenList);
     assertEquals(6, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, new int[]{1,1}, null, false));
-    assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2}, null, false));
-    assertToken(tokenList.get(2), new TokenInfo("345612", null, "word", 4, 11, 2, new int[]{2,2}, null, false));
+    assertToken(tokenList.get(1), new TokenInfo("345612", null, "word", 4, 11, 2, new int[]{2,2}, null, false));
+    assertToken(tokenList.get(2), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2}, null, false));
     assertToken(tokenList.get(3), new TokenInfo("12", null, "word", 9, 11, 3, new int[]{2,3}, null, false));
     assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, new int[]{3,4}, null, false));
     assertToken(tokenList.get(5), new TokenInfo("Test", null, "word", 14, 18, 5, new int[]{4,5}, null, false));
@@ -420,8 +420,8 @@ public class FieldAnalysisRequestHandlerTest extends AnalysisRequestHandlerTestB
     assertNotNull("Expcting LowerCaseFilter analysis breakdown", tokenList);
     assertEquals(6, tokenList.size());
     assertToken(tokenList.get(0), new TokenInfo("hi", null, "word", 0, 2, 1, new int[]{1,1,1}, null, false));
-    assertToken(tokenList.get(1), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2,2}, null, false));
-    assertToken(tokenList.get(2), new TokenInfo("345612", null, "word", 4, 11, 2, new int[]{2,2,2}, null, false));
+    assertToken(tokenList.get(1), new TokenInfo("345612", null, "word", 4, 11, 2, new int[]{2,2,2}, null, false));
+    assertToken(tokenList.get(2), new TokenInfo("3456", null, "word", 4, 8, 2, new int[]{2,2,2}, null, false));
     assertToken(tokenList.get(3), new TokenInfo("12", null, "word", 9, 11, 3, new int[]{2,3,3}, null, false));
     assertToken(tokenList.get(4), new TokenInfo("a", null, "word", 12, 13, 4, new int[]{3,4,4}, null, false));
     assertToken(tokenList.get(5), new TokenInfo("test", null, "word", 14, 18, 5, new int[]{4,5,5}, null, false));

solr/core/src/test/org/apache/solr/rest/schema/TestBulkSchemaAPI.java

@@ -396,7 +396,7 @@ public class TestBulkSchemaAPI extends RestTestBase {
         "                       'name' : 'myNewTxtField',\n" +
         "                       'class':'solr.TextField',\n" +
         "                       'positionIncrementGap':'100',\n" +
-        "                       'analyzer' : {\n" +
+        "                       'indexAnalyzer' : {\n" +
         "                               'charFilters':[\n" +
         "                                          {\n" +
         "                                           'class':'solr.PatternReplaceCharFilterFactory',\n" +
@@ -407,7 +407,32 @@ public class TestBulkSchemaAPI extends RestTestBase {
         "                               'tokenizer':{'class':'solr.WhitespaceTokenizerFactory'},\n" +
         "                               'filters':[\n" +
         "                                          {\n" +
-        "                                           'class':'solr.WordDelimiterFilterFactory',\n" +
+        "                                           'class':'solr.WordDelimiterGraphFilterFactory',\n" +
+        "                                           'preserveOriginal':'0'\n" +
+        "                                          },\n" +
+        "                                          {\n" +
+        "                                           'class':'solr.StopFilterFactory',\n" +
+        "                                           'words':'stopwords.txt',\n" +
+        "                                           'ignoreCase':'true'\n" +
+        "                                          },\n" +
+        "                                          {'class':'solr.LowerCaseFilterFactory'},\n" +
+        "                                          {'class':'solr.ASCIIFoldingFilterFactory'},\n" +
+        "                                          {'class':'solr.KStemFilterFactory'},\n" +
+        "                                          {'class':'solr.FlattenGraphFilterFactory'}\n" +
+        "                                         ]\n" +
+        "                               },\n" +
+        "                       'queryAnalyzer' : {\n" +
+        "                               'charFilters':[\n" +
+        "                                          {\n" +
+        "                                           'class':'solr.PatternReplaceCharFilterFactory',\n" +
+        "                                           'replacement':'$1$1',\n" +
+        "                                           'pattern':'([a-zA-Z])\\\\\\\\1+'\n" +
+        "                                          }\n" +
+        "                                         ],\n" +
+        "                               'tokenizer':{'class':'solr.WhitespaceTokenizerFactory'},\n" +
+        "                               'filters':[\n" +
+        "                                          {\n" +
+        "                                           'class':'solr.WordDelimiterGraphFilterFactory',\n" +
         "                                           'preserveOriginal':'0'\n" +
         "                                          },\n" +
         "                                          {\n" +

solr/example/example-DIH/solr/db/conf/managed-schema

@@ -500,7 +500,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -518,10 +518,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -530,7 +531,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -540,16 +541,29 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/db/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/example/example-DIH/solr/mail/conf/managed-schema

@@ -419,7 +419,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -437,10 +437,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -449,7 +450,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -459,16 +460,29 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/mail/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/example/example-DIH/solr/rss/conf/managed-schema

@@ -242,18 +242,19 @@
         <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
         -->
         <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <charFilter class="solr.HTMLStripCharFilterFactory"/>
         <tokenizer class="solr.StandardTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -450,7 +451,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -468,10 +469,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -480,7 +482,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -490,16 +492,29 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/rss/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/example/example-DIH/solr/solr/conf/managed-schema

@@ -500,7 +500,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -518,10 +518,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -530,7 +531,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -540,16 +541,29 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/example-DIH/solr/solr/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/example/example-DIH/solr/tika/conf/managed-schema

@@ -353,7 +353,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -362,13 +362,14 @@
     <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
       <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
@@ -377,13 +378,23 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/example/files/conf/managed-schema

@@ -145,27 +145,39 @@
     <analyzer type="index">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
-      <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
       <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
-      <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.PorterStemFilterFactory"/>
     </analyzer>
   </fieldType>
   <fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.WhitespaceTokenizerFactory"/>
       <filter class="solr.SynonymFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
       <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
-      <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+      <filter class="solr.EnglishMinimalStemFilterFactory"/>
+      <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory" />
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+      <filter class="solr.SynonymFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
+      <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
       <filter class="solr.EnglishMinimalStemFilterFactory"/>

solr/example/files/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/server/solr/configsets/basic_configs/conf/managed-schema

@@ -436,7 +436,7 @@
     <!-- A text field with defaults appropriate for English, plus
          aggressive word-splitting and autophrase features enabled.
          This field is just like text_en, except it adds
-         WordDelimiterFilter to enable splitting and matching of
+         WordDelimiterGraphFilter to enable splitting and matching of
          words on case-change, alpha numeric boundaries, and
          non-alphanumeric chars.  This means certain compound word
          cases will work, for example query "wi fi" will match
@@ -455,10 +455,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
         />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -467,7 +468,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
         />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -478,16 +479,29 @@
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/server/solr/configsets/basic_configs/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/server/solr/configsets/data_driven_schema_configs/conf/managed-schema

@@ -435,7 +435,7 @@
     <!-- A text field with defaults appropriate for English, plus
          aggressive word-splitting and autophrase features enabled.
          This field is just like text_en, except it adds
-         WordDelimiterFilter to enable splitting and matching of
+         WordDelimiterGraphFilter to enable splitting and matching of
          words on case-change, alpha numeric boundaries, and
          non-alphanumeric chars.  This means certain compound word
          cases will work, for example query "wi fi" will match
@@ -454,10 +454,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
         />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -466,7 +467,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
         />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -477,16 +478,29 @@
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight"  indexed="true"  stored="true"/>
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/server/solr/configsets/data_driven_schema_configs/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/server/solr/configsets/sample_techproducts_configs/conf/managed-schema

@@ -544,7 +544,7 @@
     <!-- A text field with defaults appropriate for English, plus
    aggressive word-splitting and autophrase features enabled.
    This field is just like text_en, except it adds
-   WordDelimiterFilter to enable splitting and matching of
+   WordDelimiterGraphFilter to enable splitting and matching of
    words on case-change, alpha numeric boundaries, and
    non-alphanumeric chars.  This means certain compound word
    cases will work, for example query "wi fi" will match
@@ -562,10 +562,11 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -574,7 +575,7 @@
                 ignoreCase="true"
                 words="lang/stopwords_en.txt"
                 />
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -584,16 +585,29 @@
     <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
          but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
     <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
         <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.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
         <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+             possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>

solr/server/solr/configsets/sample_techproducts_configs/conf/synonyms.txt

@@ -21,7 +21,7 @@ fooaaa,baraaa,bazaaa
 GB,gib,gigabyte,gigabytes
 MB,mib,megabyte,megabytes
 Television, Televisions, TV, TVs
-#notice we use "gib" instead of "GiB" so any WordDelimiterFilter coming
+#notice we use "gib" instead of "GiB" so any WordDelimiterGraphFilter coming
 #after us won't split it into two words.
 
 # Synonym mappings can be used for spelling correction too

solr/solrj/src/test-files/solrj/solr/collection1/conf/schema-sql.xml

@@ -72,26 +72,41 @@
   <fieldtype name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldtype name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldtype>
 
   <fieldtype name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -191,9 +206,16 @@
     </analyzer>
   </fieldtype>
   <fieldtype name="lowerpunctfilt" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+              catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -265,15 +287,16 @@
   <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -285,15 +308,16 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -304,8 +328,9 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -318,13 +343,14 @@
   <fieldtype name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -334,13 +360,14 @@
   <fieldtype name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/solrj/src/test-files/solrj/solr/collection1/conf/schema.xml

@@ -47,26 +47,41 @@
   <fieldType name="failtype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <!-- Demonstrating ignoreCaseChange -->
   <fieldType name="wdf_nocase" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
   </fieldType>
 
   <fieldType name="wdf_preserve" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
+              catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -166,9 +181,16 @@
     </analyzer>
   </fieldType>
   <fieldType name="lowerpunctfilt" class="solr.TextField">
-    <analyzer>
+    <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+              catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+      <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
+    </analyzer>
+    <analyzer type="query">
+      <tokenizer class="solr.MockTokenizerFactory"/>
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -240,15 +262,16 @@
   <fieldType name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0"
               catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
       <filter class="solr.StopFilterFactory"/>
@@ -260,15 +283,16 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.StopFilterFactory"/>
       <filter class="solr.PorterStemFilterFactory"/>
@@ -279,8 +303,9 @@
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1"
               generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
@@ -293,13 +318,14 @@
   <fieldType name="skutype1" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
@@ -309,13 +335,14 @@
   <fieldType name="skutype2" class="solr.TextField">
     <analyzer type="index">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
+      <filter class="solr.FlattenGraphFilterFactory"/>
     </analyzer>
     <analyzer type="query">
       <tokenizer class="solr.MockTokenizerFactory"/>
-      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
+      <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1"
               catenateNumbers="1" catenateAll="0"/>
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>

solr/solrj/src/test-files/solrj/solr/configsets/streaming/conf/schema.xml

@@ -73,24 +73,37 @@
     <fieldtype name="failtype1" class="solr.TextField">
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
     </fieldtype>
 
     <!-- Demonstrating ignoreCaseChange -->
     <fieldtype name="wdf_nocase" class="solr.TextField">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.MockTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>
 
     <fieldtype name="wdf_preserve" class="solr.TextField">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.MockTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>
@@ -179,9 +192,15 @@
       </analyzer>
     </fieldtype>
     <fieldtype name="lowerpunctfilt" class="solr.TextField">
-      <analyzer>
+      <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.MockTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>
@@ -252,14 +271,15 @@
     <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.StopFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
@@ -270,14 +290,15 @@
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
         <filter class="solr.StopFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.StopFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
@@ -287,7 +308,8 @@
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory"  splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"  splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
@@ -300,12 +322,13 @@
     <fieldtype name="skutype1" class="solr.TextField">
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>
@@ -314,12 +337,13 @@
     <fieldtype name="skutype2" class="solr.TextField">
       <analyzer type="index">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.MockTokenizerFactory"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
       </analyzer>
     </fieldtype>

solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java

@@ -529,7 +529,7 @@ public class SchemaTest extends RestTestBase {
     tokenizerAttributes.put("class", "solr.WhitespaceTokenizerFactory");
     analyzerDefinition.setTokenizer(tokenizerAttributes);
     Map<String, Object> filterAttributes = new LinkedHashMap<>();
-    filterAttributes.put("class", "solr.WordDelimiterFilterFactory");
+    filterAttributes.put("class", "solr.WordDelimiterGraphFilterFactory");
     filterAttributes.put("preserveOriginal", "0");
     analyzerDefinition.setFilters(Collections.singletonList(filterAttributes));
     fieldTypeDefinition.setAnalyzer(analyzerDefinition);