From 94c5c8332065ba28c9c90ec762acac3743d6475e Mon Sep 17 00:00:00 2001
From: Yonik Seeley <yonik@apache.org>
Date: Thu, 30 Nov 2006 19:00:07 +0000
Subject: [PATCH] little schema cleanups

git-svn-id: https://svn.apache.org/repos/asf/incubator/solr/trunk@481036 13f79535-47bb-0310-9956-ffa450edef68
---
 example/solr/conf/schema.xml | 77 +++++++++++++++---------------------
 1 file changed, 32 insertions(+), 45 deletions(-)

diff --git a/example/solr/conf/schema.xml b/example/solr/conf/schema.xml
index 560179d67b4..ee67026a9c0 100755
--- a/example/solr/conf/schema.xml
+++ b/example/solr/conf/schema.xml
@@ -16,12 +16,12 @@
  limitations under the License.
 -->
 
-<!-- The Solr schema file. This file should be named "schema.xml" and
+<!-- This is the Solr schema file. This file should be named "schema.xml" and
  should be in the conf directory under the solr home
  (i.e. ./solr/conf/schema.xml by default) 
  or located where the classloader for the Solr webapp can find it.
 
- For more information, on how to customize this file, please see...
+ For more information, on how to customize this file, please see
  http://wiki.apache.org/solr/SchemaXml
 -->
 
@@ -35,9 +35,12 @@
 
   <types>
     <!-- field type definitions. The "name" attribute is
-         just a label to be used by field definitions.  The "class"
-         attribute and any other attributes determine the real
-         behavior of the fieldtype.  -->
+       just a label to be used by field definitions.  The "class"
+       attribute and any other attributes determine the real
+       behavior of the fieldtype.
+         Class names starting with "solr" refer to java classes in the
+       org.apache.solr.analysis package.
+    -->
 
     <!-- The StrField type is not analyzed, but indexed/stored verbatim.  
        - StrField and TextField support an optional compressThreshold which
@@ -112,32 +115,18 @@
          this type on the same document, with the purpose of preventing false phrase
          matching across fields.
 
-         For more info on customizing your analyzer chain, please see...
-	  http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-	 
+         For more info on customizing your analyzer chain, please see
+         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
      -->
 
-     <!-- Standard analyzer commonly used by Lucene developers
-     -->
-    <!-- Standard analyzer commonly used by Lucene developers -->
-    <fieldtype name="text_lu" class="solr.TextField" positionIncrementGap="100">
-      <analyzer>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.StandardFilterFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.StopFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory"/>
-        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-      </analyzer>
-    </fieldtype>
-    <!-- One could also specify an existing Analyzer class that has a
+    <!-- One can also specify an existing Analyzer class that has a
          default constructor via the class attribute on the analyzer element
-    <fieldtype name="text_lu" class="solr.TextField">
+    <fieldtype name="text_greek" class="solr.TextField">
       <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
     </fieldType>
     -->
-    
-    <!-- A text field that only splits on whitespace for more exact matching -->
+
+    <!-- A text field that only splits on whitespace for exact matching of words -->
     <fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
@@ -153,24 +142,24 @@
         -->
     <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
-          <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-          <!-- in this example, we will only use synonyms at query time
-          <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-          -->
-          <filter class="solr.StopFilterFactory" ignoreCase="true"/>
-          <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
-          <filter class="solr.LowerCaseFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
-          <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <!-- in this example, we will only use synonyms at query time
+        <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"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
       <analyzer type="query">
-          <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-          <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-          <filter class="solr.StopFilterFactory" ignoreCase="true"/>
-          <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
-          <filter class="solr.LowerCaseFilterFactory"/>
-          <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
-          <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <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"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -181,7 +170,7 @@
       <analyzer>
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
-        <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
@@ -252,9 +241,7 @@
  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
  <defaultSearchField>text</defaultSearchField>
 
- <!-- SolrQueryParser configuration:
-        defaultOperator="AND|OR"
- -->
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
  <solrQueryParser defaultOperator="OR"/>
 
   <!-- copyField commands copy one field to another at the time a document