From c47478502608ce66e9a6a99ebd1cd2285bc6b986 Mon Sep 17 00:00:00 2001
From: Brett <brett@kowh.ai>
Date: Fri, 29 Oct 2021 14:19:27 +0200
Subject: [PATCH] More solr changes

---
 solr/Dockerfile                               |  24 +-
 .../solrconfig-2.9.3.xml                      |   0
 solr/solrconfig.xml                           | 345 ------------------
 3 files changed, 13 insertions(+), 356 deletions(-)
 rename solrconfig-2.9.3.xml => solr/solrconfig-2.9.3.xml (100%)
 delete mode 100755 solr/solrconfig.xml

diff --git a/solr/Dockerfile b/solr/Dockerfile
index 8922342..1e0c650 100755
--- a/solr/Dockerfile
+++ b/solr/Dockerfile
@@ -2,9 +2,10 @@ FROM solr:6.6.6
 
 # Enviroment variables
 ENV SOLR_CORE ckan
-ENV SOLR_VERSION 6.6.6
-ENV CKAN_VERSION 2.9.1
-###TODO!!! CKAN_VERSION to be passed in as an ARG
+
+# Build Arguments
+ARG CKAN_VERSION
+ARG SOLR_VERSION
 
 # root user for initial config
 USER root
@@ -15,14 +16,14 @@ RUN mkdir -p /opt/solr/server/solr/${SOLR_CORE}/conf && \
     mkdir -p /opt/solr/server/solr/${SOLR_CORE}/data/index
 
 # Add files
-ADD solrconfig.xml \
-https://raw.githubusercontent.com/ckan/ckan/ckan-${CKAN_VERSION}/ckan/config/solr/schema.xml \
-https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/$SOLR_VERSION/solr/server/solr/configsets/basic_configs/conf/currency.xml \
-https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/$SOLR_VERSION/solr/server/solr/configsets/basic_configs/conf/synonyms.txt \
-https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/$SOLR_VERSION/solr/server/solr/configsets/basic_configs/conf/stopwords.txt \
-https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/$SOLR_VERSION/solr/server/solr/configsets/basic_configs/conf/protwords.txt \
-https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/$SOLR_VERSION/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml \
-/opt/solr/server/solr/$SOLR_CORE/conf/
+COPY ./solr/solrconfig-${CKAN_VERSION}.xml /opt/solr/server/solr/${SOLR_CORE}/conf/solrconfig.xml
+ADD https://raw.githubusercontent.com/ckan/ckan/ckan-${CKAN_VERSION}/ckan/config/solr/schema.xml \
+https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/${SOLR_VERSION}/solr/server/solr/configsets/basic_configs/conf/currency.xml \
+https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/${SOLR_VERSION}/solr/server/solr/configsets/basic_configs/conf/synonyms.txt \
+https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/${SOLR_VERSION}/solr/server/solr/configsets/basic_configs/conf/stopwords.txt \
+https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/${SOLR_VERSION}/solr/server/solr/configsets/basic_configs/conf/protwords.txt \
+https://raw.githubusercontent.com/apache/lucene-solr/releases/lucene-solr/${SOLR_VERSION}/solr/server/solr/configsets/data_driven_schema_configs/conf/elevate.xml \
+/opt/solr/server/solr/${SOLR_CORE}/conf/
 
 # Create core.properties
 RUN echo name=${SOLR_CORE} > /opt/solr/server/solr/${SOLR_CORE}/core.properties
@@ -32,3 +33,4 @@ RUN chown -R ${SOLR_USER}:${SOLR_USER} /opt/solr/server/solr/${SOLR_CORE}
 
 # non-root user for runtime
 USER ${SOLR_USER}:${SOLR_USER}
+
diff --git a/solrconfig-2.9.3.xml b/solr/solrconfig-2.9.3.xml
similarity index 100%
rename from solrconfig-2.9.3.xml
rename to solr/solrconfig-2.9.3.xml
diff --git a/solr/solrconfig.xml b/solr/solrconfig.xml
deleted file mode 100755
index 8a3eade..0000000
--- a/solr/solrconfig.xml
+++ /dev/null
@@ -1,345 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-
-<!--solrconfig.xml documentation [https://wiki.apache.org/solr/SolrConfigXml]-->
-<config>
- 
-	<luceneMatchVersion>6.0.0</luceneMatchVersion>
-	
-	<lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\d.*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
-	<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
-	
-	<dataDir>${solr.data.dir:}</dataDir>
-	
-	<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}" />
-	
-	<codecFactory class="solr.SchemaCodecFactory" />
-	
-	<indexConfig>
-		<lockType>${solr.lock.type:native}</lockType>
-	</indexConfig>
-	
-	<jmx />
-	
-	<updateHandler class="solr.DirectUpdateHandler2">
-	 
-		<updateLog>
-			<str name="dir">${solr.ulog.dir:}</str>
-			<int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
-		</updateLog>
-		
-		<autoCommit>
-			<maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
-			<openSearcher>false</openSearcher>
-		</autoCommit>
-		
-		<autoSoftCommit>
-			<maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
-		</autoSoftCommit>
-		
-	</updateHandler>
-	
-	<query>
-	 
-		<maxBooleanClauses>1024</maxBooleanClauses>
-		<filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0" />
-		<queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" />
-		<documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" />
-		<cache name="perSegFilter" class="solr.search.LRUCache" size="10" initialSize="0" autowarmCount="10" regenerator="solr.NoOpRegenerator" />
-		<enableLazyFieldLoading>true</enableLazyFieldLoading>
-		<queryResultWindowSize>20</queryResultWindowSize>
-		<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-		
-		<listener event="newSearcher" class="solr.QuerySenderListener">
-			<arr name="queries" />
-		</listener>
-		
-		<listener event="firstSearcher" class="solr.QuerySenderListener">
-			<arr name="queries" />
-		</listener>
-		
-		<useColdSearcher>false</useColdSearcher>
-		<maxWarmingSearchers>2</maxWarmingSearchers>
-		
-	</query>
-	
-	<requestDispatcher handleSelect="false">
-	 
-		<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000" formdataUploadLimitInKB="2048" addHttpRequestToContext="false" />
-		<httpCaching never304="true" />
-		
-	</requestDispatcher>
-	
-	<requestHandler name="/select" class="solr.SearchHandler">
-	 
-		<lst name="defaults">
-			<str name="echoParams">explicit</str>
-			<int name="rows">10</int>
-		</lst>
-		
-	</requestHandler>
-	
-	<requestHandler name="/query" class="solr.SearchHandler">
-	 
-		<lst name="defaults">
-			<str name="echoParams">explicit</str>
-			<str name="wt">json</str>
-			<str name="indent">true</str>
-		</lst>
-		
-	</requestHandler>
-	
-	<requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
-	 
-		<lst name="defaults">
-			<str name="echoParams">explicit</str>
-		</lst>
-		
-	</requestHandler>
-	
-	<initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
-	 
-		<lst name="defaults">
-			<str name="df">_text_</str>
-		</lst>
-		
-	</initParams>
-	
-	<initParams path="/update/**">
-	 
-		<lst name="defaults">
-			<str name="update.chain">add-unknown-fields-to-the-schema</str>
-		</lst>
-		
-	</initParams>
-	
-	<requestHandler name="/update/extract" startup="lazy" class="solr.extraction.ExtractingRequestHandler">
-	 
-		<lst name="defaults">
-			<str name="lowernames">true</str>
-			<str name="fmap.meta">ignored_</str>
-			<str name="fmap.content">_text_</str>
-		</lst>
-		
-	</requestHandler>
-	
-	<requestHandler name="/analysis/field" startup="lazy" class="solr.FieldAnalysisRequestHandler" />
-	<requestHandler name="/analysis/document" class="solr.DocumentAnalysisRequestHandler" startup="lazy" />
-	
-	<requestHandler name="/debug/dump" class="solr.DumpRequestHandler">
-	 
-		<lst name="defaults">
-			<str name="echoParams">explicit</str>
-			<str name="echoHandler">true</str>
-		</lst>
-		
-	</requestHandler>
-	
-	<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
-	 
-		<str name="queryAnalyzerFieldType">text_general</str>
-		
-		<lst name="spellchecker">
-			<str name="name">default</str>
-			<str name="field">_text_</str>
-			<str name="classname">solr.DirectSolrSpellChecker</str>
-			<str name="distanceMeasure">internal</str>
-			<float name="accuracy">0.5</float>
-			<int name="maxEdits">2</int>
-			<int name="minPrefix">1</int>
-			<int name="maxInspections">5</int>
-			<int name="minQueryLength">4</int>
-			<float name="maxQueryFrequency">0.01</float>
-		</lst>
-		
-	</searchComponent>
-	
-	<requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
-	 
-		<lst name="defaults">
-			<str name="spellcheck.dictionary">default</str>
-			<str name="spellcheck">on</str>
-			<str name="spellcheck.extendedResults">true</str>
-			<str name="spellcheck.count">10</str>
-			<str name="spellcheck.alternativeTermCount">5</str>
-			<str name="spellcheck.maxResultsForSuggest">5</str>
-			<str name="spellcheck.collate">true</str>
-			<str name="spellcheck.collateExtendedResults">true</str>
-			<str name="spellcheck.maxCollationTries">10</str>
-			<str name="spellcheck.maxCollations">5</str>
-		</lst>
-		
-		<arr name="last-components">
-			<str>spellcheck</str>
-		</arr>
-		
-	</requestHandler>
-	
-	<searchComponent name="tvComponent" class="solr.TermVectorComponent" />
-	
-	<requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
-	 
-		<lst name="defaults">
-			<bool name="tv">true</bool>
-		</lst>
-		<arr name="last-components">
-			<str>tvComponent</str>
-		</arr>
-		
-	</requestHandler>
-	
-	<searchComponent name="terms" class="solr.TermsComponent" />
-	
-	<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
-	 
-		<lst name="defaults">
-			<bool name="terms">true</bool>
-			<bool name="distrib">false</bool>
-		</lst>
-		
-		<arr name="components">
-			<str>terms</str>
-		</arr>
-		
-	</requestHandler>
-	
-	<searchComponent name="elevator" class="solr.QueryElevationComponent">
-	 
-		<str name="queryFieldType">string</str>
-		<str name="config-file">elevate.xml</str>
-		
-	</searchComponent>
-	
-	<requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
-	 
-		<lst name="defaults">
-			<str name="echoParams">explicit</str>
-		</lst>
-		<arr name="last-components">
-			<str>elevator</str>
-		</arr>
-		
-	</requestHandler>
-	
-	<searchComponent class="solr.HighlightComponent" name="highlight">
-	 
-		<highlighting>
-		 
-			<fragmenter name="gap" default="true" class="solr.highlight.GapFragmenter">
-				<lst name="defaults">
-					<int name="hl.fragsize">100</int>
-				</lst>
-			</fragmenter>
-			
-			<fragmenter name="regex" class="solr.highlight.RegexFragmenter">
-				<lst name="defaults">
-					<int name="hl.fragsize">70</int>
-					<float name="hl.regex.slop">0.5</float>
-					<str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
-				</lst>
-			</fragmenter>
-			
-			<formatter name="html" default="true" class="solr.highlight.HtmlFormatter">
-				<lst name="defaults">
-					<str name="hl.simple.pre"><![CDATA[<em>]]></str>
-					<str name="hl.simple.post"><![CDATA[</em>]]></str>
-				</lst>
-			</formatter>
-			
-			<encoder name="html" class="solr.highlight.HtmlEncoder" />
-			<fragListBuilder name="simple" class="solr.highlight.SimpleFragListBuilder" />
-			<fragListBuilder name="single" class="solr.highlight.SingleFragListBuilder" />
-			<fragListBuilder name="weighted" default="true" class="solr.highlight.WeightedFragListBuilder" />
-			<fragmentsBuilder name="default" default="true" class="solr.highlight.ScoreOrderFragmentsBuilder" />
-			<fragmentsBuilder name="colored" class="solr.highlight.ScoreOrderFragmentsBuilder">
-			 
-				<lst name="defaults">
-					<str name="hl.tag.pre"><![CDATA[<b style="background:yellow">,<b style="background:lawgreen">,
-               <b style="background:aquamarine">,<b style="background:magenta">,
-               <b style="background:palegreen">,<b style="background:coral">,
-               <b style="background:wheat">,<b style="background:khaki">,
-               <b style="background:lime">,<b style="background:deepskyblue">]]></str>
-					<str name="hl.tag.post"><![CDATA[</b>]]></str>
-				</lst>
-				
-			</fragmentsBuilder>
-			
-			<boundaryScanner name="default" default="true" class="solr.highlight.SimpleBoundaryScanner">
-				<lst name="defaults">
-					<str name="hl.bs.maxScan">10</str>
-					<str name="hl.bs.chars">.,!?</str>
-				</lst>
-			</boundaryScanner>
-			
-			<boundaryScanner name="breakIterator" class="solr.highlight.BreakIteratorBoundaryScanner">
-				<lst name="defaults">
-					<str name="hl.bs.type">WORD</str>
-					<str name="hl.bs.language">en</str>
-					<str name="hl.bs.country">US</str>
-				</lst>
-			</boundaryScanner>
-			
-		</highlighting>
-		
-	</searchComponent>
-	
-	<schemaFactory class="ManagedIndexSchemaFactory">
-		<bool name="mutable">true</bool>
-	</schemaFactory>
-	
-	<updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
-		<processor class="solr.UUIDUpdateProcessorFactory" />
-		<processor class="solr.LogUpdateProcessorFactory" />
-		<processor class="solr.DistributedUpdateProcessorFactory" />
-		<processor class="solr.RemoveBlankFieldUpdateProcessorFactory" />
-		<processor class="solr.FieldNameMutatingUpdateProcessorFactory">
-			<str name="pattern">[^\w-\.]</str>
-			<str name="replacement">_</str>
-		</processor>
-		<processor class="solr.ParseBooleanFieldUpdateProcessorFactory" />
-		<processor class="solr.ParseLongFieldUpdateProcessorFactory" />
-		<processor class="solr.ParseDoubleFieldUpdateProcessorFactory" />
-		<processor class="solr.ParseDateFieldUpdateProcessorFactory">
-			<arr name="format">
-				<str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
-				<str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
-				<str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
-				<str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
-				<str>yyyy-MM-dd'T'HH:mm:ssZ</str>
-				<str>yyyy-MM-dd'T'HH:mm:ss</str>
-				<str>yyyy-MM-dd'T'HH:mmZ</str>
-				<str>yyyy-MM-dd'T'HH:mm</str>
-				<str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
-				<str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
-				<str>yyyy-MM-dd HH:mm:ss.SSS</str>
-				<str>yyyy-MM-dd HH:mm:ss,SSS</str>
-				<str>yyyy-MM-dd HH:mm:ssZ</str>
-				<str>yyyy-MM-dd HH:mm:ss</str>
-				<str>yyyy-MM-dd HH:mmZ</str>
-				<str>yyyy-MM-dd HH:mm</str>
-				<str>yyyy-MM-dd</str>
-			</arr>
-		</processor>
-		<processor class="solr.RunUpdateProcessorFactory" />
-	</updateRequestProcessorChain>
-	
-	<queryResponseWriter name="json" class="solr.JSONResponseWriter">
-		<str name="content-type">text/plain; charset=UTF-8</str>
-	</queryResponseWriter>
-	
-	<queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
-		<str name="template.base.dir">${velocity.template.base.dir:}</str>
-		<str name="solr.resource.loader.enabled">${velocity.solr.resource.loader.enabled:true}</str>
-		<str name="params.resource.loader.enabled">${velocity.params.resource.loader.enabled:false}</str>
-	</queryResponseWriter>
-	
-	<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
-		<int name="xsltCacheLifetimeSeconds">5</int>
-	</queryResponseWriter>
-	
-</config>