spotlight-dor-resources 0.0.1

data/app/models/spotlight/resources/purl.rb

@@ -0,0 +1,14 @@
+module Spotlight::Resources
+  class Purl < Spotlight::Resources::DorResource
+    self.weight = -1000
+
+    def self.can_provide? res
+      !!(res.url =~ /^https?:\/\/purl.stanford.edu/)
+    end
+
+    def doc_id
+      url.match(/^https?:\/\/purl.stanford.edu\/([^#\/\.]+)/)[1]
+    end
+
+  end
+end

data/app/models/spotlight/resources/searchworks.rb

@@ -0,0 +1,15 @@
+module Spotlight::Resources
+  class Searchworks < Spotlight::Resources::DorResource
+
+    self.weight = -1000
+
+    def self.can_provide? res
+      !!(res.url =~ /^https?:\/\/searchworks[^\.]*.stanford.edu/)
+    end
+
+    def doc_id
+      url.match(/^https?:\/\/searchworks[^\.]*.stanford.edu\/.*view\/([^\/\.#]+)/)[1]
+    end
+
+  end
+end

data/lib/spotlight/dor/indexer.rb

@@ -0,0 +1,160 @@
+# external gems
+require 'gdor/indexer'
+require 'solrizer'
+# Base class to harvest from DOR via harvestdor gem
+module Spotlight::Dor
+  class Indexer < GDor::Indexer
+    # add contentMetadata fields
+    before_index do |sdb, solr_doc|
+      Solrizer.insert_field(solr_doc, 'content_metadata_type', sdb.public_xml.xpath("/publicObject/contentMetadata/@type").text, :symbol, :displayable)
+
+      sdb.public_xml.xpath("/publicObject/contentMetadata").xpath('resource/file[@mimetype="image/jp2"]').each do |node|
+        file_id = node.attr('id').gsub(".jp2", '')
+
+        if node.attr('id') =~ /jp2$/ and !solr_doc[Solrizer.solr_name('content_metadata_first_image_file_name', :displayable)]
+          Solrizer.insert_field(solr_doc, 'content_metadata_first_image_file_name', file_id, :displayable)
+          Solrizer.insert_field(solr_doc, 'content_metadata_first_image_width', node.xpath('./imageData/@width').text, :displayable)
+          Solrizer.insert_field(solr_doc, 'content_metadata_first_image_height', node.xpath('./imageData/@height').text, :displayable)
+        end
+
+        Solrizer.insert_field(solr_doc, 'content_metadata_image_iiif_info', "https://stacks.stanford.edu/image/iiif/#{solr_doc[:id]}%2F#{file_id}/info.json", :displayable)
+        Solrizer.insert_field(solr_doc, 'thumbnail_square_url', "https://stacks.stanford.edu/image/#{solr_doc[:id]}/#{file_id}_square", :displayable)
+        Solrizer.insert_field(solr_doc, 'thumbnail_url', "https://stacks.stanford.edu/image/#{solr_doc[:id]}/#{file_id}_thumb", :displayable)
+        Solrizer.insert_field(solr_doc, 'large_image_url', "https://stacks.stanford.edu/image/#{solr_doc[:id]}/#{file_id}_large", :displayable)
+        Solrizer.insert_field(solr_doc, 'full_image_url', "https://stacks.stanford.edu/image/#{solr_doc[:id]}/#{file_id}_full", :displayable)
+      end
+    end
+
+    # tweak author_sort field from stanford-mods
+    before_index do |_sdb, solr_doc|
+      solr_doc[:author_sort] &&= solr_doc[:author_sort].gsub("\uFFFF", "\uFFFD")
+    end
+
+    # add fields from raw mods
+    # see comment with add_donor_tags about Feigenbaum specific donor tags data
+    before_index :add_box
+    before_index :add_donor_tags
+    before_index :add_genre
+    before_index :add_folder
+    before_index :add_series
+    before_index :mods_cartographics_indexing
+
+    def solr_client
+      @solr_client
+    end
+
+    def solr_document resource
+      doc_hash = super
+      run_hook :before_index, resource, doc_hash
+      doc_hash
+    end
+
+    def resource druid
+      Harvestdor::Indexer::Resource.new harvestdor, druid
+    end
+
+    private
+
+    # add the box number to solr_doc as box_ssi field (note: single valued!)
+    #   data in location/physicalLocation or in relatedItem/location/physicalLocation
+    # TODO:  push this up to stanford-mods gem?  or should it be hierarchical series/box/folder?
+    def add_box(sdb, solr_doc)
+      # see spec for data from actual collections
+      #   _location.physicalLocation should find top level and relatedItem
+      box_num = sdb.smods_rec._location.physicalLocation.map do |node|
+        val = node.text
+        # note that this will also find Flatbox or Flat-box
+        match_data = val.match(/Box ?:? ?([^,|(Folder)]+)/i)
+        match_data[1].strip if match_data.present?
+      end
+      solr_doc['box_ssi'] = box_num.first if box_num.present?
+    end
+
+    # This new donor_tags_sim field was added in October 2015 specifically for the Feigenbaum exhibit.  It is very likely
+    #  it will go ununsed by other projects, but should be benign (since this field will not be created if this specific MODs note is not found.)
+    #  Later refactoring could include project specific fields.   Peter Mangiafico
+    def add_donor_tags sdb, solr_doc
+      donor_tags = sdb.smods_rec.note.select { |n| n.displayLabel == 'Donor tags' }.map(&:content)
+      insert_field solr_doc, 'donor_tags', donor_tags, :symbol # this is a _ssim field
+    end
+
+    # add the folder number to solr_doc as folder_ssi field (note: single valued!)
+    #   data in location/physicalLocation or in relatedItem/location/physicalLocation
+    # TODO:  push this up to stanford-mods gem?  or should it be hierarchical series/box/folder?
+    def add_folder(sdb, solr_doc)
+      # see spec for data from actual collections
+      #   _location.physicalLocation should find top level and relatedItem
+      folder_num = sdb.smods_rec._location.physicalLocation.map do |node|
+        val = node.text
+        # folder may be text with commas
+        match_data = val.match(/Folder:? ?(.+)/i)
+        next if match_data.blank?
+        result = match_data[1].strip
+        # Menuez collection may have folder followed by Sleeve then Frame
+        match2_data = result.match(/(.*),? ?Sleeve/i)
+        if match2_data
+          match2_data[1].strip.sub(/,$/, '')
+        else
+          result
+        end
+      end
+      solr_doc['folder_ssi'] = folder_num.first if folder_num.present?
+    end
+
+    # add plain MODS <genre> element data, not the SearchWorks genre values
+    def add_genre sdb, solr_doc
+      insert_field solr_doc, 'genre', sdb.smods_rec.genre.content, :symbol # this is a _ssim field
+    end
+
+    # add the series/accession 'number' to solr_doc as series_ssi field (note: single valued!)
+    #   data in location/physicalLocation or in relatedItem/location/physicalLocation
+    # TODO:  push this up to stanford-mods gem?  or should it be hierarchical series/box/folder?
+    def add_series(sdb, solr_doc)
+      # see spec for data from actual collections
+      #   _location.physicalLocation should find top level and relatedItem
+      series_num = sdb.smods_rec._location.physicalLocation.map do |node|
+        val = node.text
+        # feigenbaum uses 'Accession'
+        match_data = val.match(/(?:(?:Series)|(?:Accession)):? ([^,|]+)/i)
+        match_data[1].strip if match_data.present?
+      end
+      solr_doc['series_ssi'] = series_num.first if series_num.present?
+    end
+
+    def mods_cartographics_indexing sdb, solr_doc
+      insert_field(solr_doc, "coordinates", Array(sdb.smods_rec.subject.cartographics.coordinates).map { |n| n.text }, :stored_searchable)
+
+      Array(sdb.smods_rec.subject.cartographics.coordinates).map do |n|
+        next unless n.text =~ /^\(/ and n.text =~ /\)$/
+
+        bbox = n.text.gsub(/[\(\)]/, '')
+
+        lng, lat = bbox.split('/')
+
+        minX,maxX = lng.split('--').map { |x| coord_to_decimal(x) }
+        maxY,minY = lat.split('--').map { |x| coord_to_decimal(x) }
+
+        solr_doc["point_bbox"] ||= []
+        solr_doc["point_bbox"] << "#{minX} #{minY} #{maxX} #{maxY}"
+      end
+    end
+
+    def coord_to_decimal point
+      regex = /(?<dir>[NESW])\s*(?<deg>\d+)°(?:(?<sec>\d+)ʹ)?/
+      match = regex.match(point)
+      dec = 0
+
+      dec += match['deg'].to_i
+      dec += match['sec'].to_f / 60
+      dec = -1 * dec if match['dir'] == "W" or match['dir'] == "S"
+
+      dec
+    end
+
+    def insert_field solr_doc, field, values, *args
+      Array(values).each do |v|
+        Solrizer.insert_field solr_doc, field, v, *args
+      end
+    end
+  end
+end

data/lib/spotlight/dor/resources.rb

@@ -0,0 +1,16 @@
+require "harvestdor-indexer"
+require "spotlight/dor/resources/version"
+
+module Spotlight
+  module Dor
+    module Resources
+
+      require "spotlight/dor/indexer"
+      require "spotlight/dor/resources/engine"
+      
+      def self.indexer
+        @indexer ||= Spotlight::Dor::Indexer.new File.join(Rails.root, "config", "gdor.yml"), solr: Blacklight.solr_config
+      end
+    end
+  end
+end

data/lib/spotlight/dor/resources/engine.rb

@@ -0,0 +1,13 @@
+require 'spotlight/engine'
+require 'spotlight/dor/resources'
+
+module Spotlight::Dor::Resources
+  class Engine < ::Rails::Engine
+
+    initializer "spotlight.dor.initialize" do
+      Spotlight::Engine.config.resource_providers << Spotlight::Resources::Searchworks
+      Spotlight::Engine.config.resource_providers << Spotlight::Resources::Purl
+      Spotlight::Dor::Resources::Engine.config.parallel_options = { in_threads: 1 }
+    end
+  end
+end

data/lib/spotlight/dor/resources/version.rb

@@ -0,0 +1,7 @@
+module Spotlight
+  module Dor
+    module Resources
+      VERSION = "0.0.1"
+    end
+  end
+end

data/solr_conf/conf/schema.xml

@@ -0,0 +1,346 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<schema name="Hydra" version="1.5">
+  <!-- NOTE: various comments and unused configuration possibilities have been purged
+     from this file.  Please refer to http://wiki.apache.org/solr/SchemaXml,
+     as well as the default schema file included with Solr -->
+  
+  <uniqueKey>id</uniqueKey>
+  
+  <fields>
+    <field name="id" type="string" stored="true" indexed="true" multiValued="false" required="true"/>
+    <field name="_version_" type="long"     indexed="true"  stored="true"/>
+    <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
+    
+    <field name="lat" type="tdouble" stored="true" indexed="true" multiValued="false"/>
+    <field name="lng" type="tdouble" stored="true" indexed="true" multiValued="false"/>
+    <field name="original_pid_tesim" type="pid_text" stored="true" indexed="true" multiValued="true"/>
+
+    <field name="full_title_ng" type="text_en_ng" stored="false" indexed="true" multiValued="true"/>
+    <field name="id_ng"         type="text_en_ng" stored="false" indexed="true" multiValued="false"/>
+
+    <!-- NOTE:  not all possible Solr field types are represented in the dynamic fields -->
+
+    <!-- text (_t...) -->
+<!--
+    <dynamicField name="*_ti" type="text" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_tim" type="text" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_ts" type="text" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_tsm" type="text" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_tsi" type="text" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_tsim" type="text" stored="true" indexed="true" multiValued="true"/>
+<!--
+    <dynamicField name="*_tiv" type="text" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
+    <dynamicField name="*_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
+-->
+    <dynamicField name="*_tsiv" type="text" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
+    <dynamicField name="*_tsimv" type="text" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
+    
+    <!-- English text (_te...) -->
+<!--
+    <dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_tes" type="text_en" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_tesm" type="text_en" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_tesi" type="text_en" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_tesim" type="text_en" stored="true" indexed="true" multiValued="true"/>
+<!--
+    <dynamicField name="*_teiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
+    <dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
+-->
+    <dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
+    <dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
+    
+    <!-- string (_s...) -->
+<!--
+    <dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_ss" type="string" stored="true" indexed="false" multiValued="false"/>
+    <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="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false"/>
+-->
+    
+    <!-- integer (_i...) -->
+<!--
+    <dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_is" type="int" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- trie integer (_it...) (for faster range queries) -->
+<!--
+    <dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_its" type="tint" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- date (_dt...) -->
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->
+<!--
+    <dynamicField name="*_dti" type="date" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dtim" type="date" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_dts" type="date" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- trie date (_dtt...) (for faster range queries) -->
+<!--
+    <dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_dtts" type="tdate" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- long (_l...) -->
+<!--
+    <dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_ls" type="long" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- trie long (_lt...) (for faster range queries) -->
+<!--
+    <dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_lts" type="tlong" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- double (_db...) -->
+<!--
+    <dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_dbs" type="double" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- trie double (_dbt...) (for faster range queries) -->
+<!--
+    <dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_dbts" type="tdouble" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- float (_f...) -->
+<!--
+    <dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_fs" type="float" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- trie float (_ft...) (for faster range queries) -->
+<!--
+    <dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_fts" type="tfloat" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true"/>
+    
+    <!-- boolean (_b...) -->
+<!--
+    <dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false"/>
+-->
+    <dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false"/>
+    
+    <!-- Type used to index the lat and lon components for the "location" FieldType -->
+<!--
+    <dynamicField name="*_coordinate" type="tdouble" indexed="true"  stored="false" />
+-->
+
+    <!-- location (_ll...) -->
+<!--
+    <dynamicField name="*_lli" type="location" stored="false" indexed="true" multiValued="false"/>
+    <dynamicField name="*_llim" type="location" stored="false" indexed="true" multiValued="true"/>
+-->
+    <dynamicField name="*_lls" type="location" stored="true" indexed="false" multiValued="false"/>
+    <dynamicField name="*_llsm" type="location" stored="true" indexed="false" multiValued="true"/>
+    <dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false"/>
+    <dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true"/>
+
+    <!-- you must define copyField source and dest fields explicity or schemaBrowser doesn't work -->
+    <field name="all_text_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
+
+
+  </fields>
+
+
+  <!-- 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="id" dest="id_ng" maxChars="3000"/>
+  <copyField source="full_title_tesim" dest="full_title_ng" maxChars="3000"/>
+  <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/>
+
+  <types>
+    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>    
+    <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>
+    
+    <!-- Default numeric field types.  -->
+    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
+    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
+    
+    <!-- trie numeric field types for faster range queries -->
+    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
+    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
+    
+    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
+         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
+      -->
+    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
+    <!-- A Trie based date field for faster date range queries and date faceting. -->
+    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
+    
+    
+    <!-- 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"/>
+    
+    <!-- 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
+    -->
+    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
+      geo="true" distErrPct="0.025" maxDistErr="0.000009" units="degrees" />
+    
+    <fieldType name="text" class="solr.TextField" omitNorms="false">
+      <analyzer>
+        <tokenizer class="solr.ICUTokenizerFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
+        <filter class="solr.TrimFilterFactory"/>
+      </analyzer>
+    </fieldType>
+    
+    <!-- A text field that only splits on whitespace for exact matching of words -->
+    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.TrimFilterFactory"/>
+      </analyzer>
+    </fieldType>
+        
+    <!-- single token analyzed text, for sorting.  Punctuation is significant. -->
+    <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+        <filter class="solr.ICUFoldingFilterFactory"/>
+        <filter class="solr.TrimFilterFactory" />
+      </analyzer>
+    </fieldtype>
+    
+    <!-- A text field with defaults appropriate for English -->
+    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.ICUTokenizerFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <!--
+        <filter class="solr.PorterStemFilterFactory"/>
+        -->
+        <filter class="solr.TrimFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <!-- A text field with defaults appropriate for English an NGrams -->
+    <fieldType name="text_en_ng" class="solr.TextField" positionIncrementGap="100">
+      <analyzer type="index">
+        <tokenizer class="solr.ICUTokenizerFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <filter class="solr.TrimFilterFactory"/>
+        <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15" side="front"/>:
+      </analyzer>
+
+      <analyzer type="index">
+        <tokenizer class="solr.ICUTokenizerFactory"/>
+        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
+        <filter class="solr.EnglishPossessiveFilterFactory"/>
+        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
+        <filter class="solr.EnglishMinimalStemFilterFactory"/>
+        <filter class="solr.TrimFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <fieldType name="pid_text" class="solr.TextField" positionIncrementGap="100">
+      <analyzer>
+        <tokenizer class="solr.KeywordTokenizerFactory"/>
+      </analyzer>
+    </fieldType>
+        
+    <!-- queries for paths match documents at that path, or in descendent paths -->
+    <fieldType name="descendent_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+    </fieldType>
+    
+    <!-- queries for paths match documents at that path, or in ancestor paths -->
+    <fieldType name="ancestor_path" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory" />
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
+      </analyzer>
+    </fieldType>
+    
+  </types>
+  
+</schema>