arclight 0.1.4 → 0.3.3

data/lib/generators/arclight/templates/config/downloads.yml

@@ -3,6 +3,11 @@
 #                 provide the PDF and/or EAD (.xml) links. The
 #                 size value should be a String (shown as-is) or
 #                 the number of bytes in the download.
+#               - Pass a template key to use a formatted string
+#                 which interpolates document accessors into the
+#                 url using the %{accessor} syntax.
+#               - Pass a size_accessor key to pull the size of
+#                 the file from an accessor in the solr document
 #
 sample_unitid:
   pdf:
@@ -11,3 +16,10 @@ sample_unitid:
   ead:
     href: 'http://example.com/sample.xml'
     size: 123456
+    # size_accessor: 'level'
+default:
+  disabled: true
+  pdf:
+    template: 'http://example.com/%{unitid}.pdf'
+  ead:
+    template: 'http://example.com/%{unitid}.xml'

data/lib/generators/arclight/templates/config/repositories.yml

@@ -11,8 +11,10 @@ nlm:
   phone: ''
   contact_info: 'hmdref@nlm.nih.gov'
   thumbnail_url: "https://collections.nlm.nih.gov/pageturnerserver/ajaxp?theurl=http://localhost:8080/fedora/get/nlm:nlmuid-101421040-img/THUMB"
-  google_request_url: 'https://docs.google.com/a/stanford.edu/forms/d/e/1FAIpQLSeOamhY_IcFw4sPnz0ddwWWkrPaHbM5wp7JVbOLOL_mIusEyw/viewform'
-  google_request_mappings: "document_url=entry.1980510262&collection_name=entry.619150170&collection_creator=entry.14428541&eadid=entry.996397105&containers=entry.1125277048&title=entry.862815208"
+  request_types:
+    google_form:
+      request_url: 'https://docs.google.com/a/stanford.edu/forms/d/e/1FAIpQLSeOamhY_IcFw4sPnz0ddwWWkrPaHbM5wp7JVbOLOL_mIusEyw/viewform'
+      request_mappings: "document_url=entry.1980510262&collection_name=entry.619150170&collection_creator=entry.14428541&eadid=entry.996397105&containers=entry.1125277048&title=entry.862815208"
 sul-spec:
   name: 'Stanford University Libraries. Special Collections and University Archives'
   visit_note: 'Special Collections and University Archives materials are stored offsite and must be paged 36 hours in advance.'
@@ -27,6 +29,10 @@ sul-spec:
   phone: '(650) 725-1022'
   contact_info: 'specialcollections@stanford.edu'
   thumbnail_url: 'https://library.stanford.edu/sites/default/files/styles/150x150/public/collection/image/Collections-Super-Enlight.jpg'
+  request_types:
+    aeon_web_ead:
+      request_url: 'https://sample.request.com'
+      request_mappings: 'Action=10&Form=31&Value=ead_url'
 umich-bhl:
   name: 'University of Michigan. Bentley Historical Library'
   description: 'The Bentley Historical Library collects the materials for and promotes the study of the histories of two great, intertwined institutions, the State of Michigan and the University of Michigan. The Library is open without fee to the public, and we welcome researchers regardless of academic or professional affiliation.'
@@ -40,3 +46,15 @@ umich-bhl:
   phone: ''
   contact_info: 'bentley.ref@umich.edu'
   thumbnail_url: 'https://upload.wikimedia.org/wikipedia/commons/thumb/9/93/Bhlexterior.jpg/150px-Bhlexterior.jpg'
+  request_types:
+    aeon_external_request_endpoint:
+      request_url: https://example.com/aeon/aeon.dll
+      request_mappings:
+        url_params:
+          Action: 11
+          Type: 200
+        static:
+          SystemId: ArcLight
+          ItemInfo1: manuscript
+        accessor:
+          ItemTitle: collection_name

data/lib/generators/arclight/update_generator.rb

@@ -9,7 +9,7 @@ module Arclight
   # downstream application to choose if they want to take our changes or not and
   # can choose to see a diff of our changes to help them decide.
   class Update < Arclight::Install
-    source_root File.expand_path('../templates', __FILE__)
+    source_root File.expand_path('templates', __dir__)
 
     def create_blacklight_catalog
       copy_file 'catalog_controller.rb', 'app/controllers/catalog_controller.rb'

data/lib/tasks/index.rake

@@ -4,7 +4,7 @@ require 'arclight'
 require 'benchmark'
 
 ##
-# Environment variables for indexing:
+# Environment variables and information for indexing:
 #
 # REPOSITORY_ID for the repository id/slug to load repository data from
 # your configuration (default: none).
@@ -12,22 +12,31 @@ require 'benchmark'
 # REPOSITORY_FILE for the YAML file of your repository configuration
 # (default: config/repositories.yml).
 #
-# SOLR_URL for the location of your Solr instance
+# Blacklight default connection for the location of your Solr instance, SOLR_URL
+# as a backup
 # (default: http://127.0.0.1:8983/solr/blacklight-core)
 #
 namespace :arclight do
   desc 'Index an EAD document, use FILE=<path/to/ead.xml> and REPOSITORY_ID=<myid>'
   task :index do
     raise 'Please specify your EAD document, ex. FILE=<path/to/ead.xml>' unless ENV['FILE']
-    indexer = load_indexer
+
     print "Loading #{ENV['FILE']} into index...\n"
-    elapsed_time = Benchmark.realtime { indexer.update(ENV['FILE']) }
+    solr_url = begin
+                 Blacklight.default_index.connection.base_uri
+               rescue StandardError
+                 ENV['SOLR_URL'] || 'http://127.0.0.1:8983/solr/blacklight-core'
+               end
+    elapsed_time = Benchmark.realtime {
+      `bundle exec traject -u #{solr_url} -i xml -c #{Arclight::Engine.root}/lib/arclight/traject/ead2_config.rb #{ENV['FILE']}`
+    }
     print "Indexed #{ENV['FILE']} (in #{elapsed_time.round(3)} secs).\n"
   end
 
   desc 'Index a directory of EADs, use DIR=<path/to/directory> and REPOSITORY_ID=<myid>'
   task :index_dir do
     raise 'Please specify your directory, ex. DIR=<path/to/directory>' unless ENV['DIR']
+
     Dir.glob(File.join(ENV['DIR'], '*.xml')).each do |file|
       system("rake arclight:index FILE=#{file}")
     end
@@ -36,6 +45,7 @@ namespace :arclight do
   desc 'Index an EAD document, use URL=<http[s]://domain/path/to/ead.xml> and REPOSITORY_ID=<myid>'
   task :index_url do
     raise 'Please specify your EAD document, ex. URL=<http[s]://domain/path/to/ead.xml>' unless ENV['URL']
+
     ead = Nokogiri::XML(open(ENV['URL']))
     tmp = Tempfile.new(["#{Time.now.to_i}-", '.xml'], encoding: 'utf-8')
     begin
@@ -53,9 +63,11 @@ namespace :arclight do
   desc 'Index EADs from a file of URLs, use BATCH=<path/to/urls.txt> and REPOSITORY_ID=<myid>'
   task :index_url_batch do
     raise 'Please specify your URLs file, ex. BATCH=<path/to/urls.txt>' unless ENV['BATCH']
+
     File.open(ENV['BATCH']).each_line do |l|
       ENV['URL'] = l.chomp
       next if ENV['URL'].empty?
+
       unless ENV['URL'] =~ /\A#{URI.regexp(%w[http https])}\z/
         puts "Skipping invalid looking url #{ENV['URL']}"
         next
@@ -67,21 +79,9 @@ namespace :arclight do
   end
 
   desc 'Destroy all documents in the index'
-  task :destroy_index_docs do
+  task destroy_index_docs: :environment do
     puts 'Deleting all documents from index...'
-    indexer = load_indexer
-    indexer.delete_all
+    Blacklight.default_index.connection.delete_by_query('*:*')
+    Blacklight.default_index.connection.commit
   end
 end
-
-def load_indexer
-  # hardcoded since we don't have access to Blacklight.connection_config[:url] here
-  ENV['SOLR_URL'] ||= 'http://127.0.0.1:8983/solr/blacklight-core'
-
-  options = {
-    document: Arclight::CustomDocument,
-    component: Arclight::CustomComponent
-  }
-
-  Arclight::Indexer.new(options)
-end

data/package.json

@@ -2,13 +2,20 @@
   "name": "arclight",
   "description": "",
   "main": "index.js",
-  "dependencies": {},
+  "dependencies": {
+    "@babel/core": "^7.5.5",
+    "@babel/plugin-external-helpers": "^7.2.0",
+    "@babel/plugin-transform-modules-umd": "^7.2.0",
+    "@babel/preset-env": "^7.5.5"
+  },
   "devDependencies": {
     "eslint": "^3.19.0",
     "eslint-config-airbnb-base": "^11.1.3",
     "eslint-plugin-import": "^2.2.0"
   },
   "scripts": {
+    "lint": "eslint './app/assets/javascripts/**/*.{js,es6}'",
+    "lint:fix": "eslint --fix './app/assets/javascripts/**/*.{js,es6}'",
     "test": "echo \"Error: no test specified\" && exit 1"
   },
   "repository": {

data/solr/conf/schema.xml

@@ -67,7 +67,7 @@
     -->
 
     <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
-    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true" docValues="true"/>
 
     <!-- boolean type: "true" or "false" -->
     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
@@ -89,29 +89,14 @@
          then default lucene sorting will be used which places docs without the
          field first in an ascending sort and last in a descending sort.
     -->
-
-    <!--
-      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-    -->
-    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
-
     <!--
-     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.
+      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="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
+    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
+    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
+    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
+    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
 
     <!-- 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
@@ -135,10 +120,8 @@
 
          Note: For faster range queries, consider the tdate type
       -->
-    <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
-
-    <!-- A Trie based date field for faster date range queries and date faceting. -->
-    <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
+    <!-- KD-tree versions of date fields -->
+    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
 
     <!-- The "RandomSortField" is not used to store or search any
          data.  You can declare fields of this type it in your schema
@@ -153,154 +136,61 @@
      -->
     <fieldType name="random" class="solr.RandomSortField" indexed="true" />
 
-    <!-- solr.TextField allows the specification of custom text analyzers
-         specified as a tokenizer and a list of token filters. Different
-         analyzers may be specified for indexing and querying.
-
-         The optional positionIncrementGap puts space between multiple fields of
-         this type on the same document, with the purpose of preventing false phrase
-         matching across fields.
-
-         For more info on customizing your analyzer chain, please see
-         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-     -->
-     <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
-       <analyzer>
-         <tokenizer class="solr.StandardTokenizerFactory"/>
-         <filter class="solr.ICUFoldingFilterFactory" />
-         <filter class="solr.SnowballPorterFilterFactory" language="English" />
-       </analyzer>
-     </fieldType>
-
-    <!-- One can also specify an existing Analyzer class that has a
-         default constructor via the class attribute on the analyzer element
-    <fieldType name="text_greek" class="solr.TextField">
-      <analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
-    </fieldType>
-    -->
-
-    <!-- A text field that only splits on whitespace for exact matching of words -->
-    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
-        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      </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"
-	 (empty by default), and down cases.  At query time only, it
-	 also applies synonyms. -->
-    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
-      <analyzer type="index">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <!-- in this example, we will only use synonyms at query time
-        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-        -->
-        <filter class="solr.LowerCaseFilterFactory"/>
-      </analyzer>
-      <analyzer type="query">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
+        <tokenizer class="solr.ICUTokenizerFactory" />
+        <filter class="solr.KeywordRepeatFilterFactory" />
+        <filter class="solr.ICUFoldingFilterFactory" />
+        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldType>
 
-    <!-- A text field with defaults appropriate for English: it
-         tokenizes with StandardTokenizer, removes English stop words
-         (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. -->
     <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <!-- in this example, we will only use synonyms at query time
-        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-        -->
-        <filter class="solr.LowerCaseFilterFactory"/>
-	<filter class="solr.EnglishPossessiveFilterFactory"/>
+        <tokenizer class="solr.WhitespaceTokenizerFactory" />
+        <filter class="solr.KeywordRepeatFilterFactory" />
+        <filter class="solr.WordDelimiterGraphFilterFactory"/>
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory" />
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
-        <filter class="solr.EnglishMinimalStemFilterFactory"/>
-	-->
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.FlattenGraphFilterFactory"/> <!-- required on index analyzers after graph filters -->
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
       <analyzer type="query">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <tokenizer class="solr.WhitespaceTokenizerFactory" />
+        <filter class="solr.KeywordRepeatFilterFactory" />
+        <filter class="solr.WordDelimiterGraphFilterFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-	<filter class="solr.EnglishPossessiveFilterFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory" />
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
         <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-	<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
-        <filter class="solr.EnglishMinimalStemFilterFactory"/>
-	-->
         <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
       </analyzer>
     </fieldType>
 
-    <!-- A text field with defaults appropriate for English, plus
-	 aggressive word-splitting and autophrase features enabled.
-	 This field is just like text_en, except it adds
-	 WordDelimiterFilter to enable splitting and matching of
-	 words on case-change, alpha numeric boundaries, and
-	 non-alphanumeric chars.  This means certain compound word
-	 cases will work, for example query "wi fi" will match
-	 document "WiFi" or "wi-fi".  However, other cases will still
-	 not match, for example if the query is "wifi" and the
-	 document is "wi fi" or if the query is "wi-fi" and the
-	 document is "wifi".
-        -->
-    <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+    <fieldType name="identifier_match" class="solr.TextField" positionIncrementGap="100">
       <analyzer type="index">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <!-- in this example, we will only use synonyms at query time
-        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-        -->
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-        <filter class="solr.PorterStemFilterFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+          catenateWords="1"
+          catenateNumbers="1"
+          catenateAll="1"
+          />
+        <filter class="solr.ICUFoldingFilterFactory" />
+        <filter class="solr.FlattenGraphFilterFactory"/> <!-- required on index analyzers after graph filters -->
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-        <filter class="solr.PorterStemFilterFactory"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- Less flexible matching, but less false matches.  Probably not ideal for product names,
-         but may be good for SKUs.  Can insert dashes in the wrong place and still match. -->
-    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
-      <analyzer>
-        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
-        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
-        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
-        <filter class="solr.EnglishMinimalStemFilterFactory"/>
-        <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
-             possible with WordDelimiterFilter in conjuncton with stemming. -->
-        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-      </analyzer>
-    </fieldType>
-
-    <!-- Just like text_general except it reverses the characters of
-	 each token, to enable more efficient leading wildcard queries. -->
-    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
-      <analyzer type="index">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
-           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
-      </analyzer>
-      <analyzer type="query">
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
+        <filter class="solr.WordDelimiterGraphFilterFactory"
+          catenateWords="1"
+          catenateNumbers="1"
+          catenateAll="1"
+          />
+        <filter class="solr.ICUFoldingFilterFactory" />
+        <filter class="solr.WordDelimiterGraphFilterFactory"/>
       </analyzer>
     </fieldType>
 
@@ -308,31 +198,19 @@
       <analyzer>
         <tokenizer class="solr.StandardTokenizerFactory"/>
         <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
-        <filter class="solr.StandardFilterFactory"/>
         <filter class="solr.LowerCaseFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldType>
 
-    <fieldType class="solr.TextField" name="textSuggest" positionIncrementGap="100">
+    <fieldType name="textSuggest" class="solr.TextField" positionIncrementGap="100">
        <analyzer>
           <tokenizer class="solr.KeywordTokenizerFactory"/>
-          <filter class="solr.StandardFilterFactory"/>
           <filter class="solr.LowerCaseFilterFactory"/>
           <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
        </analyzer>
     </fieldType>
 
-    <!-- charFilter + WhitespaceTokenizer  -->
-    <!--
-    <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
-      <analyzer>
-        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
-        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      </analyzer>
-    </fieldType>
-    -->
-
     <!-- This is an example of using the KeywordTokenizer along
          With various TokenFilterFactories to produce a sortable field
          that does not include some properties of the source text
@@ -366,70 +244,11 @@
       </analyzer>
     </fieldType>
 
-    <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
-      <analyzer>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
-      </analyzer>
-    </fieldtype>
-
-    <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
-      <analyzer>
-        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-        <!--
-        The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
-        a token of "foo|1.4"  would be indexed as "foo" with a payload of 1.4f
-        Attributes of the DelimitedPayloadTokenFilterFactory :
-         "delimiter" - a one character delimiter. Default is | (pipe)
-	 "encoder" - how to encode the following value into a playload
-	    float -> org.apache.lucene.analysis.payloads.FloatEncoder,
-	    integer -> o.a.l.a.p.IntegerEncoder
-	    identity -> o.a.l.a.p.IdentityEncoder
-            Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-         -->
-        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
-      </analyzer>
-    </fieldtype>
-
-    <!-- lowercases the entire field value, keeping it as a single token.  -->
-    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
-      <analyzer>
-        <tokenizer class="solr.KeywordTokenizerFactory"/>
-        <filter class="solr.LowerCaseFilterFactory" />
-      </analyzer>
-    </fieldType>
-
-    <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
-      <analyzer>
-        <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
-      </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" 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
-      subFieldSuffix is defined, that is used to create the subFields.
-      Example: if subFieldType="double", then the coordinates would be
-        indexed in fields myloc_0___double,myloc_1___double.
-      Example: if subFieldSuffix="_d" then the coordinates would be indexed
-        in fields myloc_0_d,myloc_1_d
-      The subFields are an implementation detail of the fieldType, and end
-      users normally should not need to know about them.
-     -->
-    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
-
     <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
     <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
 
-   <!--
-    A Geohash is a compact representation of a latitude longitude pair in a single field.
-    See http://wiki.apache.org/solr/SpatialSearch
-   -->
-    <fieldtype name="geohash" class="solr.GeoHashField"/>
+    <fieldType name="_nest_path_" class="solr.NestPathField" />
+
  </types>
 
 
@@ -459,10 +278,15 @@
 
    <!-- NOTE: this is not a full list of fields in the index; dynamic fields are also used -->
    <field name="id" type="string" indexed="true" stored="true" required="true" />
-   <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
-   <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+   <field name="_version_" type="plong" indexed="true" stored="true" multiValued="false" />
+   <field name="timestamp" type="pdate" indexed="true" stored="true" default="NOW" multiValued="false"/>
    <!-- default, catch all search field -->
    <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>
+   <field name="unitid_identifier_match" type="identifier_match" indexed="true" multiValued="true" />
+
+   <field name="_root_" type="string" indexed="true" stored="true" docValues="false" />
+   <field name="_nest_parent_" type="string" indexed="true" stored="true"/>
+   <field name="_nest_path_" type="_nest_path_" indexed="true" stored="true"/>
 
    <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
         will be used if the name matches any of the patterns.
@@ -471,37 +295,9 @@
         EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
         Longer patterns will be matched first.  if equal size patterns
         both match, the first appearing in the schema will be used.  -->
-   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
-   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
-   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
-   <dynamicField name="*_t"  type="text"    indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_txt" type="text_general"    indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
-   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
-   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
-
-   <!-- Type used to index the lat and lon components for the "location" FieldType -->
-   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false"/>
-
-   <dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
-   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
-
-   <!-- some trie-coded dynamic fields for faster range queries -->
-   <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
-   <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
-   <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
-   <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
-   <dynamicField name="*_tdt" type="tdate"  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" />
 
-   <dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
-   <dynamicField name="*_facet" type="string" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*_sort" type="alphaNumericSort" indexed="true" stored="false" multiValued="false" />
-   <dynamicField name="*_unstem_search" type="text_general" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />
 
@@ -518,12 +314,8 @@
    <dynamicField name="*_ssm"   type="string"    stored="true"  indexed="false" multiValued="true"  />
    <dynamicField name="*_ssi"   type="string"    stored="true"  indexed="true"  multiValued="false" />
    <dynamicField name="*_ssim"  type="string"    stored="true"  indexed="true"  multiValued="true"  />
-   <dynamicField name="*_dtsi"  type="date"      stored="true"  indexed="true"  multiValued="false" />
-   <dynamicField name="*_dtsim" type="date"      stored="true"  indexed="true"  multiValued="true"  />
-   <dynamicField name="*_bsi"   type="boolean"   stored="true"  indexed="true"  multiValued="false" />
-   <dynamicField name="*_isim"  type="int"       stored="true"  indexed="true"  multiValued="true"  />
-   <dynamicField name="*_ii"    type="int"       stored="false" indexed="true"  multiValued="false" />
-
+   <dynamicField name="*_isim"  type="pint"      stored="true"  indexed="true"  multiValued="true"  />
+   <dynamicField name="*_ii"    type="pint"      stored="false" indexed="true"  multiValued="false" />
  </fields>
 
  <!-- Field to use to determine and enforce document uniqueness.
@@ -576,9 +368,7 @@
    <copyField source="userestrict_teim" dest="text" />
    <!-- grab structured data that's important -->
    <copyField source="unitid_ssm" dest="text" />
-
-   <!-- unstemmed fields -->
-   <!-- <copyField source="title_t" dest="title_unstem_search"/> -->
+   <copyField source="unitid_ssm" dest="unitid_identifier_match" />
 
    <!-- sort fields -->
    <copyField source="normalized_title_ssm" dest="title_sort"/> <!-- TODO: assumes single values -->
@@ -597,30 +387,4 @@
    <copyField source="places_ssim" dest="suggest"/>
    <copyField source="access_subjects_ssim" dest="suggest"/>
 
-   <!-- Above, multiple source fields are copied to the [text] field.
-	  Another way to map multiple source fields to the same
-	  destination field is to use the dynamic field syntax.
-	  copyField also supports a maxChars to copy setting.  -->
-
-   <!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
-
-   <!-- copy name to alphaNameSort, a field designed for sorting by name -->
-   <!-- <copyField source="name" dest="alphaNameSort"/> -->
-
-
- <!-- Similarity is the scoring routine for each document vs. a query.
-      A custom similarity may be specified here, but the default is fine
-      for most applications.  -->
- <!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
- <!-- ... OR ...
-      Specify a SimilarityFactory class name implementation
-      allowing parameters to be used.
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
-   <str name="paramkey">param value</str>
- </similarity>
- -->
-
-
 </schema>