From 18ea585150e338267601a937546f6e4df1551093 Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 14 Nov 2023 12:47:01 -0800
Subject: [PATCH 1/2] update schema to be compatible with solr 8

resolves #121
BioPortal configuration is groupped into one section to make future
upgrades easier.
---
 config/solr/property_search/schema.xml | 528 ++++++++++++------------
 config/solr/term_search/schema.xml     | 534 ++++++++++++-------------
 2 files changed, 517 insertions(+), 545 deletions(-)

diff --git a/config/solr/property_search/schema.xml b/config/solr/property_search/schema.xml
index 20824ea6..64083d19 100644
--- a/config/solr/property_search/schema.xml
+++ b/config/solr/property_search/schema.xml
@@ -17,16 +17,13 @@
 -->
 
 <!--
- 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.
 
  This example schema is the recommended starting point for users.
  It should be kept correct and concise, usable out-of-the-box.
 
+
  For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
+ http://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
 
  PERFORMANCE NOTE: this schema includes many optional features and should not
  be used for benchmarking.  To improve performance one could
@@ -39,13 +36,9 @@
   - for best index size and searching performance, set "index" to false
     for all general text fields, use copyField to copy them to the
     catchall "text" field, and use that for searching.
-  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
-    java client.
-  - Remember to run the JVM in server mode, and use a higher logging level
-    that avoids logging every request
 -->
 
-<schema name="ncbo_property" version="1.7">
+<schema name="ncbo_property" version="1.6">
     <!-- attribute "name" is the name of this schema and is only used for display purposes.
        version="x.y" is Solr's version number for the schema syntax and
        semantics.  It should not normally be changed by applications.
@@ -65,20 +58,20 @@
     -->
 
     <!-- Valid attributes for fields:
-     name: mandat ory - the name for the field
+     name: mandatory - the name for the field
      type: mandatory - the name of a field type from the
        fieldTypes section
      indexed: true if this field should be indexed (searchable or sortable)
      stored: true if this field should be retrievable
-     docValues: true if this field should have doc values. Doc values are
-       useful (required, if you are using *Point fields) for faceting,
-       grouping, sorting and function queries. Doc values will make the index
+     docValues: true if this field should have doc values. Doc Values is
+       recommended (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc Values will make the index
        faster to load, more NRT-friendly and more memory-efficient.
-       They however come with some limitations: they are currently only
-       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
-       and depending on the field type, they might require the field to be
-       single-valued, be required or have a default value (check the
-       documentation of the field type you're interested in for more information)
+       They are currently only supported by StrField, UUIDField, all
+       *PointFields, and depending on the field type, they might require
+       the field to be single-valued, be required or have a default value
+       (check the documentation of the field type you're interested in for
+       more information)
      multiValued: true if this field may contain multiple values per document
      omitNorms: (expert) set to true to omit the norms associated with
        this field (this disables length normalization and index-time
@@ -106,10 +99,9 @@
       trailing underscores (e.g. _version_) are reserved.
     -->
 
-    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
-         id, _version_, and _text_.  All other fields will be type guessed and added via the
-         "add-unknown-fields-to-the-schema" update request processor chain declared
-         in solrconfig.xml.
+    <!-- In this _default configset, only four fields are pre-declared:
+         id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
 
          Note that many dynamic fields are also defined - you can use them to specify a
          field's type via field naming conventions - see below.
@@ -117,14 +109,24 @@
          WARNING: The _text_ catch-all field will significantly increase your index size.
          If you don't need it, consider removing it and the corresponding copyField directive.
     -->
+
     <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
-    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
-    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <!-- docValues are enabled by default for long type so we don't need to index the version field  -->
+    <field name="_version_" type="plong" indexed="false" stored="false"/>
+
+    <!-- If you don't use child/nested documents, then you should remove the next two fields:  -->
+    <!-- for nested documents (minimal; points to root document) -->
     <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <!-- for nested documents (relationship tracking) -->
+    <field name="_nest_path_" type="_nest_path_" /><fieldType name="_nest_path_" class="solr.NestPathField" />
+
     <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
 
+    <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+         because it's very expensive to index everything twice. -->
+    <!-- <copyField source="*" dest="_text_"/> -->
 
-    <!-- NCBO specific fields -->
+ <!-- NCBO specific fields -->
     <field name="resource_id"                type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
 
     <!-- searchable fields -->
@@ -146,78 +148,155 @@
     <field name="ontologyType"               type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
     <field name="propertyType"               type="propertyType"       indexed="true"  stored="true"  multiValued="false" />
     <field name="ontologyId"                 type="string"             indexed="true"  stored="true"  multiValued="false" />
-    <field name="submissionId"               type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"               type="pint"               indexed="true"  stored="true"  multiValued="false" />
     <!-- END: NCBO specific fields -->
 
+    <copyField source="label" dest="_text_"/>
+    <copyField source="label" dest="labelExact"/>
+    <copyField source="label" dest="labelSuggest" />
+    <copyField source="label" dest="labelSuggestEdge" />
+    <copyField source="label" dest="labelSuggestNgram" />
+
+    <copyField source="labelGenerated" dest="_text_"/>
+    <copyField source="labelGenerated" dest="labelGeneratedExact"/>
+    <copyField source="labelGenerated" dest="labelGeneratedSuggest" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestEdge" />
+    <copyField source="labelGenerated" dest="labelGeneratedSuggestNgram" />
+
+    <fieldType name="ontologyType" class="solr.EnumFieldType" enumsConfig="enumsconfig.xml" docValues="true" enumName="ontologyType"/>
+    <fieldType name="propertyType" class="solr.EnumFieldType" enumsConfig="enumsconfig.xml" docValues="true" enumName="propertyType"/>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+           be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+           wild card phrases bypass the query analyzer and will not be lowercased before matching
+           against the index. This means that the characters in wildcard phrases must be lowercase in
+           order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+       <analyzer type="query">
+           <tokenizer class="solr.KeywordTokenizerFactory"/>
+           <filter class="solr.LowerCaseFilterFactory"/>
+       </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+    <!-- END: NCBO customization -->
+
     <!-- Dynamic field definitions allow using convention over configuration
        for fields via the specification of patterns to match field names.
        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
-       RESTRICTION: the glob-like pattern in the name attribute must have
-       a "*" only at the start or the end.  -->
+       RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end.  -->
 
-    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
-    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_i"  type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="pints"    indexed="true"  stored="true"/>
     <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
     <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
-    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
-    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_l"  type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
     <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
     <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
     <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
-    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
-    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
-    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
-
-    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
-    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_f"  type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="random_*" type="random"/>
+    <dynamicField name="ignored_*" type="ignored"/>
+
+    <!-- Type used for data-driven schema, to add a string copy for each text field -->
+    <dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
+
+    <dynamicField name="*_dt"  type="pdate"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="pdate"    indexed="true"  stored="true" multiValued="true"/>
     <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
     <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
 
-    <!-- KD-tree (point) numerics -->
-    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
-    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
-    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
-    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
-    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
-    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
-
-    <!-- some trie-coded dynamic fields -->
-    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
-    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
-    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
-    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
-    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
-    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
-    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
-    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
-
     <!-- payloaded dynamic fields -->
     <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
     <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
     <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
 
-    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
     <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
 
-    <dynamicField name="random_*" type="random" />
-
-    <!-- uncomment the following to ignore any fields that don't already match an existing
-        field name or dynamic field, rather than reporting them as an error.
-        alternately, change the type="ignored" to some other type e.g. "text" if you want
-        unknown fields indexed and/or stored by default
-
-        NB: use of "*" dynamic fields will disable field type guessing and adding
-        unknown fields to the schema. -->
-    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
     <!-- Field to use to determine and enforce document uniqueness.
       Unless this field is marked with required="false", it will be a required field
     -->
@@ -225,19 +304,10 @@
 
     <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
-       or to add multiple fields to the same field for easier/faster searching. -->
+       or to add multiple fields to the same field for easier/faster searching.
 
-    <copyField source="label" dest="_text_"/>
-    <copyField source="label" dest="labelExact"/>
-    <copyField source="label" dest="labelSuggest" />
-    <copyField source="label" dest="labelSuggestEdge" />
-    <copyField source="label" dest="labelSuggestNgram" />
-
-    <copyField source="labelGenerated" dest="_text_"/>
-    <copyField source="labelGenerated" dest="labelGeneratedExact"/>
-    <copyField source="labelGenerated" dest="labelGeneratedSuggest" />
-    <copyField source="labelGenerated" dest="labelGeneratedSuggestEdge" />
-    <copyField source="labelGenerated" dest="labelGeneratedSuggestNgram" />
+    <copyField source="sourceFieldName" dest="destinationFieldName"/>
+    -->
 
     <!-- field type definitions. The "name" attribute is
        just a label to be used by field definitions.  The "class"
@@ -247,26 +317,10 @@
        standard package such as org.apache.solr.analysis
     -->
 
-    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
-    <fieldType name="propertyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="propertyType"/>
-
-    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
-       It supports doc values but in that case the field needs to be
-       single-valued and either required or have a default value.
-      -->
-    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
-    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
-
-    <!-- boolean type: "true" or "false" -->
-    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
-    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
-
     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
          currently supported on types that are sorted internally as strings
          and on numeric types.
-	     This includes "string","boolean", "int", "float", "long", "date", "double",
-	     including the "Trie" and "Point" variants.
+       This includes "string", "boolean", "pint", "pfloat", "plong", "pdate", "pdouble".
        - If sortMissingLast="true", then a sort on this field will cause documents
          without the field to come after documents with the field,
          regardless of the requested sort order (asc or desc).
@@ -278,9 +332,16 @@
          field first in an ascending sort and last in a descending sort.
     -->
 
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
     <!--
-      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
-      search time and at index time, but some features are still not supported.
+      Numeric field types that index values using KD-trees.
       Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
     -->
     <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
@@ -292,42 +353,11 @@
     <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
     <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
     <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
 
-    <!--
-      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
-      tint/tfloat/tlong/tdouble types.
-    -->
-    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-
-    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
-    <!--
-     Numeric field types that index each value at various levels of precision
-     to accelerate range queries when the number of values between the range
-     endpoints is large. See the javadoc for NumericRangeQuery for internal
-     implementation details.
-
-     Smaller precisionStep values (specified in bits) will lead to more tokens
-     indexed per value, slightly larger index size, and faster range queries.
-     A precisionStep of 0 disables indexing at different precision levels.
-
-     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
-    -->
-    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-
-    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <!-- since fields of this type are by default not stored or indexed,
+       any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
 
     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
          is a more restricted form of the canonical representation of dateTime
@@ -347,33 +377,20 @@
                   ... 6 months and 3 days in the future from the start of
                       the current day
 
-         Consult the TrieDateField javadocs for more information.
       -->
     <!-- KD-tree versions of date fields -->
     <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
     <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
 
-    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
-    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
     <fieldType name="binary" class="solr.BinaryField"/>
 
-    <!-- The "RandomSortField" is not used to store or search any
-         data.  You can declare fields of this type it in your schema
-         to generate pseudo-random orderings of your docs for sorting
-         or function purposes.  The ordering is generated based on the field
-         name and the version of the index. As long as the index version
-         remains unchanged, and the same field name is reused,
-         the ordering of the docs will be consistent.
-         If you want different psuedo-random orderings of documents,
-         for the same version of the index, use a dynamicField and
-         change the field name in the request.
-     -->
-    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+    <!--
+    RankFields can be used to store scoring factors to improve document ranking. They should be used
+    in combination with RankQParserPlugin.
+    (experimental)
+    -->
+    <fieldType name="rank" class="solr.RankField"/>
 
     <!-- solr.TextField allows the specification of custom text analyzers
          specified as a tokenizer and a list of token filters. Different
@@ -384,7 +401,7 @@
          matching across fields.
 
          For more info on customizing your analyzer chain, please see
-         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+         http://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
      -->
 
     <!-- One can also specify an existing Analyzer class that has a
@@ -403,19 +420,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- With this field type case is preserved for stored values, but a case insensitive field will
-        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
-        wild card phrases bypass the query analyzer and will not be lowercased before matching
-        against the index. This means that the characters in wildcard phrases must be lowercase in
-        order to match.
-    -->
-    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
-      <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-      </analyzer>
-    </fieldType>
-
     <!-- A general text field that has reasonable, generic
          cross-language defaults: it tokenizes with StandardTokenizer,
 	       removes stop words from case-insensitive "stopwords.txt"
@@ -440,11 +444,34 @@
       </analyzer>
     </fieldType>
 
-    <!-- A text field with defaults appropriate for English: it
-         tokenizes with StandardTokenizer, removes English stop words
-         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
-         finally applies Porter's stemming.  The query time analyzer
-         also applies synonyms from synonyms.txt. -->
+
+    <!-- SortableTextField generaly functions exactly like TextField,
+         except that it supports, and by default uses, docValues for sorting (or faceting)
+         on the first 1024 characters of the original field values (which is configurable).
+
+         This makes it a bit more useful then TextField in many situations, but the trade-off
+         is that it takes up more space on disk; which is why it's not used in place of TextField
+         for every fieldType in this _default schema.
+	  -->
+    <dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
+    <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
+         removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer also applies synonyms from synonyms.txt. -->
     <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
@@ -577,86 +604,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- text_suggest : Matches whole terms in the suggest text -->
-    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory"
-                generateWordParts="1"
-                generateNumberParts="1"
-                catenateWords="1"
-                catenateNumbers="1"
-                catenateAll="1"
-                splitOnCaseChange="1"
-                splitOnNumerics="1"
-                preserveOriginal="1"
-                />
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory"
-                generateWordParts="0"
-                generateNumberParts="0"
-                catenateWords="0"
-                catenateNumbers="0"
-                catenateAll="0"
-                splitOnCaseChange="0"
-                splitOnNumerics="0"
-                />
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
-     is "A brown fox" and the query is "A bro", it will match, but not "brown"
-    -->
-    <fieldType name="text_suggest_edge" class="solr.TextField">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
-        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
-     This means that the field "A brown fox" will be matched by query "bro".
-     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
-    -->
-    <fieldType name="text_suggest_ngram" class="solr.TextField">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
-      </analyzer>
-    </fieldType>
-
     <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
     <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
       <analyzer>
@@ -702,10 +649,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- since fields of this type are by default not stored or indexed,
-         any data added to them will be ignored outright.  -->
-    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
-
     <!-- This point type indexes the coordinates as separate fields (subFields)
       If subFieldType is defined, it references a type, and a dynamic field
       definition is created matching *___<typename>.  Alternately, if
@@ -723,9 +666,9 @@
     <!-- A specialized field for geospatial search filters and distance sorting. -->
     <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
 
-    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
-      For more information about this and other Spatial fields new to Solr 4, see:
-      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    <!-- A geospatial field type that supports multiValued and polygon shapes.
+      For more information about this and other spatial fields see:
+      http://lucene.apache.org/solr/guide/spatial-search.html
     -->
     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
                geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
@@ -863,6 +806,17 @@
       </analyzer>
     </fieldType>
 
+    <!-- Estonian -->
+    <dynamicField name="*_txt_et" type="text_et"  indexed="true"  stored="true"/>
+    <fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
+      </analyzer>
+    </fieldType>
+
     <!-- Basque -->
     <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
     <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
@@ -1039,8 +993,6 @@
            See lang/userdict_ja.txt for a sample user dictionary file.
 
            Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
-
-           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
         -->
         <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
         <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
@@ -1059,6 +1011,40 @@
       </analyzer>
     </fieldType>
 
+    <!-- Korean morphological analysis -->
+    <dynamicField name="*_txt_ko" type="text_ko"  indexed="true"  stored="true"/>
+    <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
+          The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
+          It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
+
+          This dictionary was built with MeCab, it defines a format for the features adapted
+          for the Korean language.
+
+          Nori also has a convenient user dictionary feature that allows overriding the statistical
+          model with your own entries for segmentation, part-of-speech tags and readings without a need
+          to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+          The tokenizer supports multiple schema attributes:
+            * userDictionary: User dictionary path.
+            * userDictionaryEncoding: User dictionary encoding.
+            * decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
+            * outputUnknownUnigrams: If true outputs unigrams for unknown words.
+        -->
+        <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
+        <!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
+          listing the tags to remove. By default it removes:
+          E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
+          This is basically an equivalent to stemming.
+        -->
+        <filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
+        <!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
+        <filter class="solr.KoreanReadingFormFilterFactory" />
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
     <!-- Latvian -->
     <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
     <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
@@ -1168,7 +1154,7 @@
     <!-- Similarity is the scoring routine for each document vs. a query.
        A custom Similarity or SimilarityFactory may be specified here, but
        the default is fine for most applications.
-       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+       For more info: http://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
     -->
     <!--
      <similarity class="com.example.solr.CustomSimilarityFactory">
diff --git a/config/solr/term_search/schema.xml b/config/solr/term_search/schema.xml
index 6b18a2a1..a6aa39ab 100644
--- a/config/solr/term_search/schema.xml
+++ b/config/solr/term_search/schema.xml
@@ -17,16 +17,13 @@
 -->
 
 <!--
- 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.
 
  This example schema is the recommended starting point for users.
  It should be kept correct and concise, usable out-of-the-box.
 
+
  For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
+ http://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
 
  PERFORMANCE NOTE: this schema includes many optional features and should not
  be used for benchmarking.  To improve performance one could
@@ -39,13 +36,9 @@
   - for best index size and searching performance, set "index" to false
     for all general text fields, use copyField to copy them to the
     catchall "text" field, and use that for searching.
-  - For maximum indexing performance, use the ConcurrentUpdateSolrServer
-    java client.
-  - Remember to run the JVM in server mode, and use a higher logging level
-    that avoids logging every request
 -->
 
-<schema name="ncbo_class" version="1.7">
+<schema name="ncbo_class" version="1.6">
     <!-- attribute "name" is the name of this schema and is only used for display purposes.
        version="x.y" is Solr's version number for the schema syntax and
        semantics.  It should not normally be changed by applications.
@@ -65,20 +58,20 @@
     -->
 
     <!-- Valid attributes for fields:
-     name: mandat ory - the name for the field
+     name: mandatory - the name for the field
      type: mandatory - the name of a field type from the
        fieldTypes section
      indexed: true if this field should be indexed (searchable or sortable)
      stored: true if this field should be retrievable
-     docValues: true if this field should have doc values. Doc values are
-       useful (required, if you are using *Point fields) for faceting,
-       grouping, sorting and function queries. Doc values will make the index
+     docValues: true if this field should have doc values. Doc Values is
+       recommended (required, if you are using *Point fields) for faceting,
+       grouping, sorting and function queries. Doc Values will make the index
        faster to load, more NRT-friendly and more memory-efficient.
-       They however come with some limitations: they are currently only
-       supported by StrField, UUIDField, all Trie*Fields and *PointFields,
-       and depending on the field type, they might require the field to be
-       single-valued, be required or have a default value (check the
-       documentation of the field type you're interested in for more information)
+       They are currently only supported by StrField, UUIDField, all
+       *PointFields, and depending on the field type, they might require
+       the field to be single-valued, be required or have a default value
+       (check the documentation of the field type you're interested in for
+       more information)
      multiValued: true if this field may contain multiple values per document
      omitNorms: (expert) set to true to omit the norms associated with
        this field (this disables length normalization and index-time
@@ -106,10 +99,9 @@
       trailing underscores (e.g. _version_) are reserved.
     -->
 
-    <!-- In this data_driven_schema_configs configset, only three fields are pre-declared:
-         id, _version_, and _text_.  All other fields will be type guessed and added via the
-         "add-unknown-fields-to-the-schema" update request processor chain declared
-         in solrconfig.xml.
+    <!-- In this _default configset, only four fields are pre-declared:
+         id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
+         "add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
 
          Note that many dynamic fields are also defined - you can use them to specify a
          field's type via field naming conventions - see below.
@@ -117,14 +109,24 @@
          WARNING: The _text_ catch-all field will significantly increase your index size.
          If you don't need it, consider removing it and the corresponding copyField directive.
     -->
+
     <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
-    <!-- doc values are enabled by default for primitive types such as long so we don't index the version field  -->
-    <field name="_version_" type="long" indexed="false" stored="false"/>
+    <!-- docValues are enabled by default for long type so we don't need to index the version field  -->
+    <field name="_version_" type="plong" indexed="false" stored="false"/>
+
+    <!-- If you don't use child/nested documents, then you should remove the next two fields:  -->
+    <!-- for nested documents (minimal; points to root document) -->
     <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
+    <!-- for nested documents (relationship tracking) -->
+    <field name="_nest_path_" type="_nest_path_" /><fieldType name="_nest_path_" class="solr.NestPathField" />
+
     <field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
 
+    <!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
+         because it's very expensive to index everything twice. -->
+    <!-- <copyField source="*" dest="_text_"/> -->
 
-    <!-- NCBO specific fields -->
+   <!-- NCBO specific fields -->
     <field name="resource_id"           type="string"             indexed="true"  stored="true"  multiValued="false" required="true" />
 
     <!-- searchable fields -->
@@ -147,8 +149,8 @@
     <field name="parents"               type="string"             indexed="true"  stored="true"  multiValued="true" />
     <field name="ontologyType"          type="ontologyType"       indexed="true"  stored="true"  multiValued="false" />
     <field name="ontologyId"            type="string"             indexed="true"  stored="true"  multiValued="false" />
-    <field name="submissionId"          type="int"                indexed="true"  stored="true"  multiValued="false" />
-    <field name="childCount"            type="int"                indexed="true"  stored="true"  multiValued="false" />
+    <field name="submissionId"          type="pint"                indexed="true"  stored="true"  multiValued="false" />
+    <field name="childCount"            type="pint"                indexed="true"  stored="true"  multiValued="false" />
 
     <!-- Added cui and tui (semanticType) - NCBO-695 -->
     <field name="cui"                   type="text_general"       indexed="true"  stored="true"  multiValued="true" />
@@ -161,75 +163,154 @@
     <field name="provisional"           type="boolean"            indexed="true"  stored="true"  multiValued="false" default="false"/>
     <!-- END: NCBO specific fields -->
 
+    <copyField source="prefLabel" dest="_text_"/>
+    <copyField source="prefLabel" dest="prefLabelExact"/>
+    <copyField source="prefLabel" dest="prefLabelSuggest" />
+    <copyField source="prefLabel" dest="prefLabelSuggestEdge" />
+    <copyField source="prefLabel" dest="prefLabelSuggestNgram" />
+
+    <copyField source="synonym" dest="_text_"/>
+    <copyField source="synonym" dest="synonymExact"/>
+    <copyField source="synonym" dest="synonymSuggest" />
+    <copyField source="synonym" dest="synonymSuggestEdge" />
+    <copyField source="synonym" dest="synonymSuggestNgram" />
+
+    <copyField source="notation" dest="_text_"/>
+
+    <fieldType name="ontologyType" class="solr.EnumFieldType" enumsConfig="enumsconfig.xml" docValues="true" enumName="ontologyType"/>
+
+    <!-- With this field type case is preserved for stored values, but a case insensitive field will
+        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
+        wild card phrases bypass the query analyzer and will not be lowercased before matching
+        against the index. This means that the characters in wildcard phrases must be lowercase in
+        order to match.
+    -->
+    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest : Matches whole terms in the suggest text -->
+    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="1"
+                generateNumberParts="1"
+                catenateWords="1"
+                catenateNumbers="1"
+                catenateAll="1"
+                splitOnCaseChange="1"
+                splitOnNumerics="1"
+                preserveOriginal="1"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+                generateWordParts="0"
+                generateNumberParts="0"
+                catenateWords="0"
+                catenateNumbers="0"
+                catenateAll="0"
+                splitOnCaseChange="0"
+                splitOnNumerics="0"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
+     is "A brown fox" and the query is "A bro", it will match, but not "brown"
+    -->
+    <fieldType name="text_suggest_edge" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
+     This means that the field "A brown fox" will be matched by query "bro".
+     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
+    -->
+    <fieldType name="text_suggest_ngram" class="solr.TextField">
+      <analyzer type="index">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+      </analyzer>
+      <analyzer type="query">
+        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
+        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- NCBO END -->
+
     <!-- Dynamic field definitions allow using convention over configuration
        for fields via the specification of patterns to match field names.
        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
-       RESTRICTION: the glob-like pattern in the name attribute must have
-       a "*" only at the start or the end.  -->
+       RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end.  -->
 
-    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
-    <dynamicField name="*_is" type="ints"    indexed="true"  stored="true"/>
+    <dynamicField name="*_i"  type="pint"    indexed="true"  stored="true"/>
+    <dynamicField name="*_is" type="pints"    indexed="true"  stored="true"/>
     <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
     <dynamicField name="*_ss" type="strings"  indexed="true"  stored="true"/>
-    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
-    <dynamicField name="*_ls" type="longs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_t"   type="text_general" indexed="true" stored="true"/>
+    <dynamicField name="*_l"  type="plong"   indexed="true"  stored="true"/>
+    <dynamicField name="*_ls" type="plongs"   indexed="true"  stored="true"/>
+    <dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
     <dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
     <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
     <dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
-    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
-    <dynamicField name="*_fs" type="floats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
-    <dynamicField name="*_ds" type="doubles" indexed="true"  stored="true"/>
-
-    <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
-    <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
+    <dynamicField name="*_f"  type="pfloat"  indexed="true"  stored="true"/>
+    <dynamicField name="*_fs" type="pfloats"  indexed="true"  stored="true"/>
+    <dynamicField name="*_d"  type="pdouble" indexed="true"  stored="true"/>
+    <dynamicField name="*_ds" type="pdoubles" indexed="true"  stored="true"/>
+    <dynamicField name="random_*" type="random"/>
+    <dynamicField name="ignored_*" type="ignored"/>
+
+    <!-- Type used for data-driven schema, to add a string copy for each text field -->
+    <dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
+
+    <dynamicField name="*_dt"  type="pdate"    indexed="true"  stored="true"/>
+    <dynamicField name="*_dts" type="pdate"    indexed="true"  stored="true" multiValued="true"/>
     <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
     <dynamicField name="*_srpt"  type="location_rpt" indexed="true" stored="true"/>
 
-    <!-- KD-tree (point) numerics -->
-    <dynamicField name="*_pi" type="pint"    indexed="true"  stored="true"/>
-    <dynamicField name="*_pis" type="pints"    indexed="true"  stored="true"/>
-    <dynamicField name="*_pl" type="plong"   indexed="true"  stored="true"/>
-    <dynamicField name="*_pls" type="plongs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_pf" type="pfloat"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pfs" type="pfloats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pd" type="pdouble" indexed="true"  stored="true"/>
-    <dynamicField name="*_pds" type="pdoubles" indexed="true"  stored="true"/>
-    <dynamicField name="*_pdt" type="pdate"  indexed="true"  stored="true"/>
-    <dynamicField name="*_pdts" type="pdates"  indexed="true"  stored="true"/>
-
-    <!-- some trie-coded dynamic fields -->
-    <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
-    <dynamicField name="*_tis" type="tints"    indexed="true"  stored="true"/>
-    <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
-    <dynamicField name="*_tls" type="tlongs"   indexed="true"  stored="true"/>
-    <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
-    <dynamicField name="*_tfs" type="tfloats"  indexed="true"  stored="true"/>
-    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
-    <dynamicField name="*_tds" type="tdoubles" indexed="true"  stored="true"/>
-    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
-    <dynamicField name="*_tdts" type="tdates"  indexed="true"  stored="true"/>
-
     <!-- payloaded dynamic fields -->
     <dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true"  stored="true"/>
     <dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true"  stored="true"/>
     <dynamicField name="*_dps" type="delimited_payloads_string" indexed="true"  stored="true"/>
 
-    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
     <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
 
-    <dynamicField name="random_*" type="random" />
-
-    <!-- uncomment the following to ignore any fields that don't already match an existing
-        field name or dynamic field, rather than reporting them as an error.
-        alternately, change the type="ignored" to some other type e.g. "text" if you want
-        unknown fields indexed and/or stored by default
-
-        NB: use of "*" dynamic fields will disable field type guessing and adding
-        unknown fields to the schema. -->
-    <!--dynamicField name="*" type="ignored" multiValued="true" /-->
-
     <!-- Field to use to determine and enforce document uniqueness.
       Unless this field is marked with required="false", it will be a required field
     -->
@@ -237,22 +318,10 @@
 
     <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
-       or to add multiple fields to the same field for easier/faster searching. -->
-
-    <copyField source="prefLabel" dest="_text_"/>
-    <copyField source="prefLabel" dest="prefLabelExact"/>
-    <copyField source="prefLabel" dest="prefLabelSuggest" />
-    <copyField source="prefLabel" dest="prefLabelSuggestEdge" />
-    <copyField source="prefLabel" dest="prefLabelSuggestNgram" />
-
-    <copyField source="synonym" dest="_text_"/>
-    <copyField source="synonym" dest="synonymExact"/>
-    <copyField source="synonym" dest="synonymSuggest" />
-    <copyField source="synonym" dest="synonymSuggestEdge" />
-    <copyField source="synonym" dest="synonymSuggestNgram" />
-
-    <copyField source="notation" dest="_text_"/>
+       or to add multiple fields to the same field for easier/faster searching.
 
+    <copyField source="sourceFieldName" dest="destinationFieldName"/>
+    -->
 
     <!-- field type definitions. The "name" attribute is
        just a label to be used by field definitions.  The "class"
@@ -262,25 +331,10 @@
        standard package such as org.apache.solr.analysis
     -->
 
-    <fieldType name="ontologyType" class="solr.EnumField" enumsConfig="enumsconfig.xml" enumName="ontologyType"/>
-
-    <!-- The StrField type is not analyzed, but indexed/stored verbatim.
-       It supports doc values but in that case the field needs to be
-       single-valued and either required or have a default value.
-      -->
-    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
-    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
-
-    <!-- boolean type: "true" or "false" -->
-    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
-
-    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
-
     <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
          currently supported on types that are sorted internally as strings
          and on numeric types.
-	     This includes "string","boolean", "int", "float", "long", "date", "double",
-	     including the "Trie" and "Point" variants.
+       This includes "string", "boolean", "pint", "pfloat", "plong", "pdate", "pdouble".
        - If sortMissingLast="true", then a sort on this field will cause documents
          without the field to come after documents with the field,
          regardless of the requested sort order (asc or desc).
@@ -292,9 +346,16 @@
          field first in an ascending sort and last in a descending sort.
     -->
 
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
+    <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
+
+    <!-- boolean type: "true" or "false" -->
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
+    <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
+
     <!--
-      Numeric field types that index values using KD-trees. *Point fields are faster and more efficient than Trie* fields both, at
-      search time and at index time, but some features are still not supported.
+      Numeric field types that index values using KD-trees.
       Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
     -->
     <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
@@ -306,42 +367,11 @@
     <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
     <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
     <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
+    <fieldType name="random" class="solr.RandomSortField" indexed="true"/>
 
-    <!--
-      Default numeric field types. For faster range queries, consider *PointFields (pint/pfloat/plong/pdouble), or the
-      tint/tfloat/tlong/tdouble types.
-    -->
-    <fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-
-    <fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-
-    <!--
-     Numeric field types that index each value at various levels of precision
-     to accelerate range queries when the number of values between the range
-     endpoints is large. See the javadoc for NumericRangeQuery for internal
-     implementation details.
-
-     Smaller precisionStep values (specified in bits) will lead to more tokens
-     indexed per value, slightly larger index size, and faster range queries.
-     A precisionStep of 0 disables indexing at different precision levels.
-
-     Consider using pint/pfloat/plong/pdouble instead of Trie* fields if possible
-    -->
-    <fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-    <fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
-
-    <fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
+    <!-- since fields of this type are by default not stored or indexed,
+       any data added to them will be ignored outright.  -->
+    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
 
     <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
          is a more restricted form of the canonical representation of dateTime
@@ -361,33 +391,20 @@
                   ... 6 months and 3 days in the future from the start of
                       the current day
 
-         Consult the TrieDateField javadocs for more information.
       -->
     <!-- KD-tree versions of date fields -->
     <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
     <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
 
-    <fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
-    <fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
-    <fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
-    <fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
-
-
     <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
     <fieldType name="binary" class="solr.BinaryField"/>
 
-    <!-- The "RandomSortField" is not used to store or search any
-         data.  You can declare fields of this type it in your schema
-         to generate pseudo-random orderings of your docs for sorting
-         or function purposes.  The ordering is generated based on the field
-         name and the version of the index. As long as the index version
-         remains unchanged, and the same field name is reused,
-         the ordering of the docs will be consistent.
-         If you want different psuedo-random orderings of documents,
-         for the same version of the index, use a dynamicField and
-         change the field name in the request.
-     -->
-    <fieldType name="random" class="solr.RandomSortField" indexed="true" />
+    <!--
+    RankFields can be used to store scoring factors to improve document ranking. They should be used
+    in combination with RankQParserPlugin.
+    (experimental)
+    -->
+    <fieldType name="rank" class="solr.RankField"/>
 
     <!-- solr.TextField allows the specification of custom text analyzers
          specified as a tokenizer and a list of token filters. Different
@@ -398,7 +415,7 @@
          matching across fields.
 
          For more info on customizing your analyzer chain, please see
-         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
+         http://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
      -->
 
     <!-- One can also specify an existing Analyzer class that has a
@@ -417,19 +434,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- With this field type case is preserved for stored values, but a case insensitive field will
-        be provided to search on. Caveat: case insensitive wildcard search cannot be done since
-        wild card phrases bypass the query analyzer and will not be lowercased before matching
-        against the index. This means that the characters in wildcard phrases must be lowercase in
-        order to match.
-    -->
-    <fieldType name="string_ci" class="solr.TextField" sortMissingLast="true" omitNorms="true">
-      <analyzer type="query">
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-      </analyzer>
-    </fieldType>
-
     <!-- A general text field that has reasonable, generic
          cross-language defaults: it tokenizes with StandardTokenizer,
 	       removes stop words from case-insensitive "stopwords.txt"
@@ -454,11 +458,34 @@
       </analyzer>
     </fieldType>
 
-    <!-- A text field with defaults appropriate for English: it
-         tokenizes with StandardTokenizer, removes English stop words
-         (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
-         finally applies Porter's stemming.  The query time analyzer
-         also applies synonyms from synonyms.txt. -->
+
+    <!-- SortableTextField generaly functions exactly like TextField,
+         except that it supports, and by default uses, docValues for sorting (or faceting)
+         on the first 1024 characters of the original field values (which is configurable).
+
+         This makes it a bit more useful then TextField in many situations, but the trade-off
+         is that it takes up more space on disk; which is why it's not used in place of TextField
+         for every fieldType in this _default schema.
+	  -->
+    <dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
+    <dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
+    <fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
+      <analyzer type="index">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer,
+         removes English stop words (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+         finally applies Porter's stemming.  The query time analyzer also applies synonyms from synonyms.txt. -->
     <dynamicField name="*_txt_en" type="text_en"  indexed="true"  stored="true"/>
     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
@@ -591,86 +618,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- text_suggest : Matches whole terms in the suggest text -->
-    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory"
-                generateWordParts="1"
-                generateNumberParts="1"
-                catenateWords="1"
-                catenateNumbers="1"
-                catenateAll="1"
-                splitOnCaseChange="1"
-                splitOnNumerics="1"
-                preserveOriginal="1"
-                />
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory"
-                generateWordParts="0"
-                generateNumberParts="0"
-                catenateWords="0"
-                catenateNumbers="0"
-                catenateAll="0"
-                splitOnCaseChange="0"
-                splitOnNumerics="0"
-                />
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement=" " replace="all"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- text_suggest_edge : Will match from the left of the field, e.g. if the document field
-     is "A brown fox" and the query is "A bro", it will match, but not "brown"
-    -->
-    <fieldType name="text_suggest_edge" class="solr.TextField">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
-        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{30})(.*)?" replacement="$1" replace="all"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- text_suggest_ngram : Matches any word in the input field, with implicit right truncation.
-     This means that the field "A brown fox" will be matched by query "bro".
-     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored
-    -->
-    <fieldType name="text_suggest_ngram" class="solr.TextField">
-      <analyzer type="index">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="1"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-      </analyzer>
-      <analyzer type="query">
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
-        <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/>
-      </analyzer>
-    </fieldType>
-
     <dynamicField name="*_phon_en" type="phonetic_en"  indexed="true"  stored="true"/>
     <fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
       <analyzer>
@@ -716,10 +663,6 @@
       </analyzer>
     </fieldType>
 
-    <!-- since fields of this type are by default not stored or indexed,
-         any data added to them will be ignored outright.  -->
-    <fieldType name="ignored" stored="false" indexed="false" docValues="false" multiValued="true" class="solr.StrField" />
-
     <!-- This point type indexes the coordinates as separate fields (subFields)
       If subFieldType is defined, it references a type, and a dynamic field
       definition is created matching *___<typename>.  Alternately, if
@@ -737,9 +680,9 @@
     <!-- A specialized field for geospatial search filters and distance sorting. -->
     <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
 
-    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
-      For more information about this and other Spatial fields new to Solr 4, see:
-      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
+    <!-- A geospatial field type that supports multiValued and polygon shapes.
+      For more information about this and other spatial fields see:
+      http://lucene.apache.org/solr/guide/spatial-search.html
     -->
     <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
                geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
@@ -877,6 +820,17 @@
       </analyzer>
     </fieldType>
 
+    <!-- Estonian -->
+    <dynamicField name="*_txt_et" type="text_et"  indexed="true"  stored="true"/>
+    <fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
+        <filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
+      </analyzer>
+    </fieldType>
+
     <!-- Basque -->
     <dynamicField name="*_txt_eu" type="text_eu"  indexed="true"  stored="true"/>
     <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
@@ -1053,8 +1007,6 @@
            See lang/userdict_ja.txt for a sample user dictionary file.
 
            Punctuation characters are discarded by default.  Use discardPunctuation="false" to keep them.
-
-           See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
         -->
         <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
         <!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
@@ -1073,6 +1025,40 @@
       </analyzer>
     </fieldType>
 
+    <!-- Korean morphological analysis -->
+    <dynamicField name="*_txt_ko" type="text_ko"  indexed="true"  stored="true"/>
+    <fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
+          The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
+          It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
+
+          This dictionary was built with MeCab, it defines a format for the features adapted
+          for the Korean language.
+
+          Nori also has a convenient user dictionary feature that allows overriding the statistical
+          model with your own entries for segmentation, part-of-speech tags and readings without a need
+          to specify weights. Notice that user dictionaries have not been subject to extensive testing.
+
+          The tokenizer supports multiple schema attributes:
+            * userDictionary: User dictionary path.
+            * userDictionaryEncoding: User dictionary encoding.
+            * decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
+            * outputUnknownUnigrams: If true outputs unigrams for unknown words.
+        -->
+        <tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
+        <!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
+          listing the tags to remove. By default it removes:
+          E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
+          This is basically an equivalent to stemming.
+        -->
+        <filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
+        <!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
+        <filter class="solr.KoreanReadingFormFilterFactory" />
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>
+    </fieldType>
+
     <!-- Latvian -->
     <dynamicField name="*_txt_lv" type="text_lv"  indexed="true"  stored="true"/>
     <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
@@ -1182,7 +1168,7 @@
     <!-- Similarity is the scoring routine for each document vs. a query.
        A custom Similarity or SimilarityFactory may be specified here, but
        the default is fine for most applications.
-       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
+       For more info: http://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
     -->
     <!--
      <similarity class="com.example.solr.CustomSimilarityFactory">

From fa7f11e612a88ee72847a20f369cc35b6a963fff Mon Sep 17 00:00:00 2001
From: Alex Skrenchuk <alexskr@stanford.edu>
Date: Tue, 14 Nov 2023 13:16:12 -0800
Subject: [PATCH 2/2] set luceneMatchVersion to 8.11.2

---
 config/solr/property_search/solrconfig.xml        | 2 +-
 config/solr/term_search/solrconfig.xml            | 2 +-
 test/solr/configsets/_default/conf/solrconfig.xml | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/config/solr/property_search/solrconfig.xml b/config/solr/property_search/solrconfig.xml
index 771a0f32..1f9fde0d 100644
--- a/config/solr/property_search/solrconfig.xml
+++ b/config/solr/property_search/solrconfig.xml
@@ -35,7 +35,7 @@
        that you fully re-index after changing this setting as it can
        affect both how text is indexed and queried.
   -->
-  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+  <luceneMatchVersion>8.11.2</luceneMatchVersion>
 
   <!-- <lib/> directives can be used to instruct Solr to load any Jars
        identified and use them to resolve any "plugins" specified in
diff --git a/config/solr/term_search/solrconfig.xml b/config/solr/term_search/solrconfig.xml
index 771a0f32..1f9fde0d 100644
--- a/config/solr/term_search/solrconfig.xml
+++ b/config/solr/term_search/solrconfig.xml
@@ -35,7 +35,7 @@
        that you fully re-index after changing this setting as it can
        affect both how text is indexed and queried.
   -->
-  <luceneMatchVersion>8.8.2</luceneMatchVersion>
+  <luceneMatchVersion>8.11.2</luceneMatchVersion>
 
   <!-- <lib/> directives can be used to instruct Solr to load any Jars
        identified and use them to resolve any "plugins" specified in
diff --git a/test/solr/configsets/_default/conf/solrconfig.xml b/test/solr/configsets/_default/conf/solrconfig.xml
index 165544a2..26097d1d 100644
--- a/test/solr/configsets/_default/conf/solrconfig.xml
+++ b/test/solr/configsets/_default/conf/solrconfig.xml
@@ -35,7 +35,7 @@
        that you fully re-index after changing this setting as it can
        affect both how text is indexed and queried.
   -->
-  <luceneMatchVersion>8.10.1</luceneMatchVersion>
+  <luceneMatchVersion>8.11.2</luceneMatchVersion>
 
   <!-- <lib/> directives can be used to instruct Solr to load any Jars
        identified and use them to resolve any "plugins" specified in