From fc3f8b36d9cda22e7771fe0786b909548927a285 Mon Sep 17 00:00:00 2001
From: Joe Wicentowski <joewiz@gmail.com>
Date: Tue, 25 Jul 2017 14:45:33 -0400
Subject: [PATCH] Experiment with dropping stopwords from Lucene
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

to enable searches like @awmarrs’ “not found attached” - since “not” is currently dropped both from source data and from query strings
---
 volumes.xconf | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/volumes.xconf b/volumes.xconf
index 196dc9854..f1923a8c2 100644
--- a/volumes.xconf
+++ b/volumes.xconf
@@ -6,7 +6,12 @@
 
         <!-- Lucene index configuration -->
         <lucene>
-            <analyzer class="org.apache.lucene.analysis.standard.StandardAnalyzer"/>
+            <analyzer class="org.apache.lucene.analysis.standard.StandardAnalyzer">
+                <!-- Specify stop words - or remove them entirely -->
+                <param name="stopwords" type="org.apache.lucene.analysis.util.CharArraySet">
+                    <!--<value>the</value>-->
+                </param>
+            </analyzer>
             <text qname="tei:div"/>
         </lucene>