Chore/solr9 upgrade

.github/workflows/lighthouse.yml

@@ -19,7 +19,7 @@ jobs:
         ports:
           - 5432:5432
       solr:
-        image: solr:8.6
+        image: solr:9.2
         ports:
           - 8983:8983
     steps:

.github/workflows/unit_tests.yml

@@ -30,7 +30,7 @@ jobs:
         ports:
           - 5432:5432
       solr:
-        image: solr:8.6
+        image: solr:9.2
         ports:
           - 8983:8983
     steps:
@@ -43,7 +43,7 @@ jobs:
           docker cp solr_conf ${{ job.services.solr.id }}:/opt/solr/server/solr/configsets/geniza
           docker exec --user root ${{ job.services.solr.id }} /bin/bash -c "chown -R solr:solr /opt/solr/server/solr/configsets/geniza"
 
-      - name: Copy solr configsets to solr home directory (Solr 8 specific)
+      - name: Copy solr configsets to solr home directory
         run: "docker exec -d ${{ job.services.solr.id }} cp -r /opt/solr/server/solr/configsets /var/solr/data"
 
       # Python version to use is stored in the .python-version file, which is the

.github/workflows/visual_tests.yml

@@ -53,7 +53,7 @@ jobs:
         ports:
           - 5432:5432
       solr:
-        image: solr:8.6
+        image: solr:9.2
         ports:
           - 8983:8983
     steps:

DEPLOYNOTES.md

@@ -1,5 +1,10 @@
 # Deploy Notes
 
+## 4.15
+
+-   The minimum required Solr version has been bumped to 9.2. Please upgrade to this version,
+    update Solr configset, and then reindex all content with `python manage.py index`.
+
 ## 4.14
 
 -   Seleucid calendar conversion is now implemented, so automatic conversion should be applied

README.rst

@@ -6,7 +6,7 @@ Princeton Geniza Project
 Python/Django web application for a version 4.x of the `Princeton Geniza Project
 <https://cdh.princeton.edu/projects/princeton-geniza-project/>`_.
 
-Python 3.9 / Django 3.2 / Node 16 / Postgresql / Solr 8.6
+Python 3.9 / Django 3.2 / Node 16 / Postgresql / Solr 9.2
 
 .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.7347726.svg
    :target: https://doi.org/10.5281/zenodo.7347726

requirements/prod.txt

@@ -13,7 +13,9 @@ django-modeltranslation==0.17.5
 django-admin-sortable2
 python-dateutil>=2.8
 django-tabular-export
-parasolr>=0.9
+# NOTE: Once parasolr 0.10 is released, stop pulling it from git
+git+https://github.com/Princeton-CDH/parasolr@develop
+# parasolr>=0.9
 django-gfklookupwidget
 django-adminlogentries
 django-autocomplete-light>=3.9.4

solr_conf/conf/managed-schema

@@ -107,7 +107,7 @@
       <tokenizer class="solr.StandardTokenizerFactory"/>
       <filter class="solr.ICUFoldingFilterFactory"/>
       <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
-      <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="20" luceneMatchVersion="4.3"/>
+      <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="20" />
       <filter class="solr.LowerCaseFilterFactory"/>
     </analyzer>
     <analyzer type="query">

solr_conf/conf/params.json

@@ -11,12 +11,6 @@
       "facet": "on",
       "facet.mincount": "1",
       "": { "v": 0 }
-    },
-    "velocity": {
-      "wt": "velocity",
-      "v.template": "browse",
-      "v.layout": "layout",
-      "": { "v": 0 }
     }
   }
 }

solr_conf/conf/solrconfig.xml

@@ -36,7 +36,7 @@
        affect both how text is indexed and queried.
   -->
   <!-- TODO: test this change.... -->
-  <luceneMatchVersion>7.0.0</luceneMatchVersion>
+  <luceneMatchVersion>9.2.0</luceneMatchVersion>
 
   <!-- <lib/> directives can be used to instruct Solr to load any Jars
        identified and use them to resolve any "plugins" specified in
@@ -73,20 +73,17 @@
        The examples below can be used to load some solr-contribs along
        with their external dependencies.
     -->
-  <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:../../../..}/modules/extraction/lib" regex=".*\.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:../../../..}/modules/clustering/lib/" regex=".*\.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:../../../..}/modules/langid/lib/" regex=".*\.jar" />
 
-  <lib dir="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
-  <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\d.*\.jar" />
-  <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-analysis-extras-\d.*\.jar" />
-  <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs/" regex="lucene-analyzers-icu-\d.*\.jar" />
-  <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib/" regex="icu4j-\d.*\.jar" />
+  <lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib/" regex="solr-analysis-extras-\d.*\.jar" />
+  <lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib/" regex="lucene-analysis-icu-\d.*\.jar" />
+  <lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib/" regex="icu4j-\d.*\.jar" />
+
+  <lib dir="${solr.install.dir:../../../..}/modules/scripting/lib" regex=".*\.jar" />
   <!-- an exact 'path' can be used instead of a 'dir' to specify a
        specific jar file.  This will cause a serious error to be logged
        if it can't be loaded.
@@ -387,31 +384,18 @@
     <maxBooleanClauses>1024</maxBooleanClauses>
 
 
-    <!-- Solr Internal Query Caches
-
-         There are two implementations of cache available for Solr,
-         LRUCache, based on a synchronized LinkedHashMap, and
-         FastLRUCache, based on a ConcurrentHashMap.
-
-         FastLRUCache has faster gets and slower puts in single
-         threaded operation and thus is generally faster than LRUCache
-         when the hit ratio of the cache is high (> 75%), and may be
-         faster under other scenarios on multi-cpu systems.
-    -->
+    <!-- Solr Internal Query Caches -->
 
     <!-- Filter Cache
 
          Cache used by SolrIndexSearcher for filters (DocSets),
          unordered sets of *all* documents that match a query.  When a
          new searcher is opened, its caches may be prepopulated or
          "autowarmed" using data from caches in the old searcher.
-         autowarmCount is the number of items to prepopulate.  For
-         LRUCache, the autowarmed items will be the most recently
-         accessed items.
+         autowarmCount is the number of items to prepopulate.
 
          Parameters:
-           class - the SolrCache implementation LRUCache or
-               (LRUCache or FastLRUCache)
+           class - the SolrCache implementation (CaffeineCache)
            size - the maximum number of entries in the cache
            initialSize - the initial capacity (number of entries) of
                the cache.  (see java.util.HashMap)
@@ -421,7 +405,7 @@
                       to occupy. Note that when this option is specified, the size
                       and initialSize parameters are ignored.
       -->
-    <filterCache class="solr.FastLRUCache"
+    <filterCache class="solr.CaffeineCache"
                  size="512"
                  initialSize="512"
                  autowarmCount="0"/>
@@ -430,11 +414,8 @@
 
          Caches results of searches - ordered lists of document ids
          (DocList) based on a query, a sort, and the range of documents requested.
-         Additional supported parameter by LRUCache:
-            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
-                       to occupy
       -->
-    <queryResultCache class="solr.LRUCache"
+    <queryResultCache class="solr.CaffeineCache"
                       size="512"
                       initialSize="512"
                       autowarmCount="0"/>
@@ -445,14 +426,14 @@
          document).  Since Lucene internal document ids are transient,
          this cache will not be autowarmed.
       -->
-    <documentCache class="solr.LRUCache"
+    <documentCache class="solr.CaffeineCache"
                    size="512"
                    initialSize="512"
                    autowarmCount="0"/>
 
     <!-- custom cache currently used by block join -->
     <cache name="perSegFilter"
-           class="solr.search.LRUCache"
+           class="solr.search.CaffeineCache"
            size="10"
            initialSize="0"
            autowarmCount="10"
@@ -482,7 +463,7 @@
       -->
     <!--
        <cache name="myUserCache"
-              class="solr.LRUCache"
+              class="solr.CaffeineCache"
               size="4096"
               initialSize="1024"
               autowarmCount="1024"
@@ -729,7 +710,7 @@
     <lst name="defaults">
       <str name="echoParams">explicit</str>
       <int name="rows">10</int>
-      <str name="defType">edismax</str>
+      <str name="defType">lucene</str>
       <!-- <str name="df">text</str> -->
 
       <!-- keyword search field for geniza prototype -->
@@ -893,7 +874,7 @@
        (SearchHandler) can be registered multiple times with different
        names (and different init parameters)
     -->
-  <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,velocity,browse">
+  <requestHandler name="/browse" class="solr.SearchHandler" useParams="query,facets,browse">
     <lst name="defaults">
       <str name="echoParams">explicit</str>
     </lst>
@@ -1414,17 +1395,12 @@
   <!--
      Custom response writers can be declared as needed...
     -->
-  <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>
 
   <!-- XSLT response writer transforms the XML output by any xslt file found
        in Solr's conf/xslt directory.  Changes to xslt files are checked for
        every xsltCacheLifetimeSeconds.
     -->
-  <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
+  <queryResponseWriter name="xslt" class="solr.scripting.xslt.XSLTResponseWriter">
     <int name="xsltCacheLifetimeSeconds">5</int>
   </queryResponseWriter>