hydra-core 5.0.0.pre14 → 5.0.0.pre15

data/lib/generators/hydra/templates/solr_conf/conf/schema.xml

@@ -27,15 +27,35 @@
 
  For more information, on how to customize this file, please see
  http://wiki.apache.org/solr/SchemaXml
+
+ PERFORMANCE NOTE: this schema includes many optional features and should not
+ be used for benchmarking.  To improve performance one could
+  - set stored="false" for all fields possible (esp large fields) when you
+    only need to search on the field but don't need to return the original
+    value.
+  - set indexed="false" if you don't need to search on the field, but only
+    return the field as a result of searching on other indexed fields.
+  - remove all unneeded copyField statements
+  - 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 StreamingUpdateSolrServer
+    java client.
+  - Remember to run the JVM in server mode, and use a higher logging level
+    that avoids logging every request
 -->
 
-<schema name="salt" version="1.1">
+<schema name="Hydra" version="1.4">
   <!-- attribute "name" is the name of this schema and is only used for display purposes.
        Applications should change this to reflect the nature of the search collection.
-       version="1.1" is Solr's version number for the schema syntax and semantics.  It should
+       version="1.4" is Solr's version number for the schema syntax and semantics.  It should
        not normally be changed by applications.
        1.0: multiValued attribute did not exist, all fields are multiValued by nature
-       1.1: multiValued attribute introduced, false by default -->
+       1.1: multiValued attribute introduced, false by default 
+       1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
+       1.3: removed optional field compress feature
+       1.4: default auto-phrase (QueryParser feature) to off
+     -->
 
   <types>
     <!-- field type definitions. The "name" attribute is
@@ -46,18 +66,19 @@
        org.apache.solr.analysis package.
     -->
 
-    <!-- The StrField type is not analyzed, but indexed/stored verbatim.  
-       - StrField and TextField support an optional compressThreshold which
-       limits compression (if enabled in the derived fields) to values which
-       exceed a certain size (in characters).
-    -->
+    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
     <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
 
     <!-- boolean type: "true" or "false" -->
     <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
+    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+    <fieldtype name="binary" class="solr.BinaryField"/>
 
     <!-- The optional sortMissingLast and sortMissingFirst attributes are
-         currently supported on types that are sorted internally as strings.
+         currently supported on types that are sorted internally as strings
+         and on numeric types.
+	       This includes "string","boolean", and, as of 3.5 (and 4.x),
+	       int, float, long, date, double, including the "Trie" variants.
        - 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).
@@ -69,25 +90,28 @@
          field first in an ascending sort and last in a descending sort.
     -->    
 
-
-    <!-- numeric field types that store and index the text
-         value verbatim (and hence don't support range queries, since the
-         lexicographic ordering isn't equal to the numeric ordering) -->
-    <fieldType name="integer" class="solr.IntField" omitNorms="true"/>
-    <fieldType name="long" class="solr.LongField" omitNorms="true"/>
-    <fieldType name="float" class="solr.FloatField" omitNorms="true"/>
-    <fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
-
-
-    <!-- Numeric field types that manipulate the value into
-         a string value that isn't human-readable in its internal form,
-         but with a lexicographic ordering the same as the numeric ordering,
-         so that range queries work correctly. -->
-    <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
-    <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
-    <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
-    <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
-
+    <!--
+      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.
+    -->
+    <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"/>
 
     <!-- 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
@@ -108,18 +132,55 @@
                       the current day
                       
          Consult the DateField javadocs for more information.
+
+         Note: For faster range queries, consider the tdate type
       -->
-    <fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
+    <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"/>
+
+
+    <!--
+      Note:
+      These should only be used for compatibility with existing indexes (created with older Solr versions)
+      or if "sortMissingFirst" or "sortMissingLast" functionality is needed. Use Trie based fields instead.
+
+      Plain numeric field types that store and index the text
+      value verbatim (and hence don't support range queries, since the
+      lexicographic ordering isn't equal to the numeric ordering)
+    -->
+    <fieldType name="pint" class="solr.IntField" omitNorms="true"/>
+    <fieldType name="plong" class="solr.LongField" omitNorms="true"/>
+    <fieldType name="pfloat" class="solr.FloatField" omitNorms="true"/>
+    <fieldType name="pdouble" class="solr.DoubleField" omitNorms="true"/>
+    <fieldType name="pdate" class="solr.DateField" sortMissingLast="true" omitNorms="true"/>
+
+
+    <!--
+      Note:
+      These should only be used for compatibility with existing indexes (created with older Solr versions).
+      Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
+
+      Numeric field types that manipulate the value into
+      a string value that isn't human-readable in its internal form,
+      but with a lexicographic ordering the same as the numeric ordering,
+      so that range queries work correctly.
+    -->
+    <fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
+    <fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="true"/>
 
 
     <!-- The "RandomSortField" is not used to store or search any
          data.  You can declare fields of this type it in your schema
-         to generate psuedo-random orderings of your docs for sorting 
+         to generate pseudo-random orderings of your docs for sorting 
          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 differend psuedo-random orderings of documents,
+         If you want different psuedo-random orderings of documents,
          for the same version of the index, use a dynamicField and
          change the name
      -->
@@ -136,6 +197,14 @@
          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.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+         <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
@@ -151,59 +220,176 @@
       </analyzer>
     </fieldType>
 
-    <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
-        words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
-        so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
-        Synonyms and stopwords are customized by external files, and stemming is enabled.
-        Duplicate tokens at the same position (which may result from Stemmed Synonyms or
-        WordDelim parts) are removed.
+    <!-- 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"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <!-- 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.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.SynonymFilterFactory" 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
+         (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"/>
+        -->
+        <!-- Case insensitive stop word removal.
+          add enablePositionIncrements=true in both the index and query
+          analyzers to leave a 'gap' for more accurate phrase queries.
         -->
-    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+	<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"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
+        <filter class="solr.LowerCaseFilterFactory"/>
+	<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"/>
+      </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">
       <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"/>
         -->
         <!-- Case insensitive stop word removal.
-             enablePositionIncrements=true ensures that a 'gap' is left to
-             allow for accurate phrase queries.
+          add enablePositionIncrements=true in both the index and query
+          analyzers to leave a 'gap' for more accurate phrase queries.
         -->
         <filter class="solr.StopFilterFactory"
                 ignoreCase="true"
-                words="stopwords.txt"
+                words="stopwords_en.txt"
                 enablePositionIncrements="true"
                 />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English"/>
-        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+        <filter class="solr.PorterStemFilterFactory"/>
       </analyzer>
       <analyzer type="query">
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
-        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
+        <filter class="solr.StopFilterFactory"
+                ignoreCase="true"
+                words="stopwords_en.txt"
+                enablePositionIncrements="true"
+                />
         <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
         <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.SnowballPorterFilterFactory" language="English"/>
-        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+        <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="textTight" class="solr.TextField" positionIncrementGap="100" >
+    <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.txt"/>
+        <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.SnowballPorterFilterFactory" language="English"/>
+        <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.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <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.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
+    <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100" >
+      <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>
 
+    <!-- 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
@@ -223,11 +409,11 @@
         <!-- The PatternReplaceFilter gives you the flexibility to use
              Java Regular expression to replace any sequence of characters
              matching a pattern with an arbitrary replacement string, 
-             which may include back refrences to portions of the orriginal
+             which may include back references to portions of the original
              string matched by the pattern.
              
              See the Java Regular Expression documentation for more
-             infomation on pattern and replacement string syntax.
+             information on pattern and replacement string syntax.
              
              http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
           -->
@@ -236,48 +422,271 @@
         />
       </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>
 
-    <!-- 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" class="solr.StrField" /> 
+    <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"/>
  </types>
 
- <fields>
 
+ <fields>
+   <!-- Valid attributes for fields:
+     name: mandatory - the name for the field
+     type: mandatory - the name of a previously defined type from the 
+       <types> section
+     indexed: true if this field should be indexed (searchable or sortable)
+     stored: true if this field should be retrievable
+     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
+       boosting for the field, and saves some memory).  Only full-text
+       fields or fields that need an index-time boost need norms.
+     termVectors: [false] set to true to store the term vector for a
+       given field.
+       When using MoreLikeThis, fields used for similarity should be
+       stored for best performance.
+     termPositions: Store position information with the term vector.  
+       This will increase storage costs.
+     termOffsets: Store offset information with the term vector. This 
+       will increase storage costs.
+     default: a value that should be used if no value is specified
+       when adding a document.
+   -->
+
+   <!-- 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="text" type="text" indexed="true" stored="true" multiValued="true"/>
    <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
-
-   <!-- These pub_date fields are just for testing hydra and can be removed -->
+   <!-- default, catch all search field -->
+   <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
+   
+   <!-- these display fields are NOT multi-valued -->
+   <field name="marc_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="title_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="title_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="subtitle_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="subtitle_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="author_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   <field name="author_vern_display" type="string" indexed="false" stored="true" multiValued="false"/>
+   
+   <!-- these fields are also used for display, so they must be stored -->
+   <field name="isbn_t" type="text" indexed="true" stored="true" multiValued="true"/>
+   <field name="language_facet" type="string" indexed="true" stored="true" multiValued="true" />
+   <field name="subject_topic_facet" type="string" indexed="true" stored="true" multiValued="true" />
+   <field name="subject_era_facet" type="string" indexed="true" stored="true" multiValued="true" />
+   <field name="subject_geo_facet" type="string" indexed="true" stored="true" multiValued="true" />
+   <!-- pub_date is used for facet and display so it must be indexed and stored -->
    <field name="pub_date" type="string" indexed="true" stored="true" multiValued="true"/>
-   <field name="pub_date_sort" type="sint" indexed="true" stored="true" multiValued="false"/>
-
+   <!-- pub_date sort uses new trie-based int fields, which are recommended for any int and are displayable, sortable, and range-quer
+   we use 'tint' for faster range-queries. -->
+   <field name="pub_date_sort" type="tint" indexed="true" stored="true" multiValued="false"/>
+     
    <!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
    <field name="format" type="string" indexed="true" stored="true"/>
+
    
-   <dynamicField name="*_i"  type="sint"    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.
+        RESTRICTION: the glob-like pattern in the name attribute must have
+        a "*" only at the start or the end.
+        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" multiValued="true"/>
-   <dynamicField name="*_l"  type="slong"   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="sfloat"  indexed="true"  stored="true"/>
-   <dynamicField name="*_d"  type="sdouble" 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="*_pi"  type="pint"    indexed="true"  stored="true"/>
 
-   <dynamicField name="random*" type="random" />
+   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
+   <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
 
-   <dynamicField name="*_sort" type="string" indexed="true" stored="false" multiValued="false" />
-   <dynamicField name="*_facet" type="string" indexed="true" stored="true" multiValued="true" />
-   <dynamicField name="*_display" type="string" indexed="false" 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="true" multiValued="true" />
+   <dynamicField name="*_sort" type="string" 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" />
+
+   <!-- 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 --> 
+   <!--dynamicField name="*" type="ignored" multiValued="true" /-->
+   
  </fields>
 
+ <!-- Field to use to determine and enforce document uniqueness. 
+      Unless this field is marked with required="false", it will be a required field
+   -->
  <uniqueKey>id</uniqueKey>
+
+ <!-- field for the QueryParser to use when an explicit fieldname is absent -->
  <defaultSearchField>text</defaultSearchField>
- <solrQueryParser defaultOperator="AND" />
- <copyField source="*_facet" dest="text" />
- <copyField source="pub_date" dest="pub_date_sort"/>
+
+ <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
+ <solrQueryParser defaultOperator="AND"/>
+
+  <!-- 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.  -->
+   <!-- Copy Fields -->
+        
+   <!-- unstemmed fields -->
+   <copyField source="title_t" dest="title_unstem_search"/>
+   <copyField source="subtitle_t" dest="subtitle_unstem_search"/>
+   <copyField source="title_addl_t" dest="title_addl_unstem_search"/>
+   <copyField source="title_added_entry_t" dest="title_added_entry_unstem_search"/>
+   <copyField source="title_series_t" dest="title_series_unstem_search"/>
+   <copyField source="author_t" dest="author_unstem_search"/>
+   <copyField source="author_addl_t" dest="author_addl_unstem_search"/>
+   <copyField source="subject_t" dest="subject_unstem_search"/>
+   <copyField source="subject_addl_t" dest="subject_addl_unstem_search"/>
+   <copyField source="subject_topic_facet" dest="subject_topic_unstem_search"/>
+   
+   <!-- sort fields -->
+   <copyField source="pub_date" dest="pub_date_sort"/>
+   
+        
+   <!-- spellcheck fields -->
+   <!-- default spell check;  should match fields for default request handler -->
+   <!-- it won't work with a copy of a copy field -->
+   <copyField source="*_t" dest="spell"/>
+   <copyField source="*_facet" dest="spell"/>
+   <!-- title spell check;  should match fields for title request handler -->
+   <copyField source="title_t" dest="title_spell"/>
+   <copyField source="subtitle_t" dest="title_spell"/>
+   <copyField source="addl_titles_t" dest="title_spell"/>
+   <copyField source="title_added_entry_t" dest="title_spell"/>
+   <copyField source="title_series_t" dest="title_spell"/>
+   <!-- author spell check; should match fields for author request handler -->
+   <copyField source="author_t" dest="author_spell"/>
+   <copyField source="author_addl_t" dest="author_spell"/>
+   <!-- subject spell check; should match fields for subject request handler -->
+   <copyField source="subject_topic_facet" dest="subject_spell"/>
+   <copyField source="subject_t" dest="subject_spell"/>
+   <copyField source="subject_addl_t" dest="subject_spell"/>  
+   
+   <!-- OpenSearch query field should match request handler search fields -->
+   <copyField source="title_t" dest="opensearch_display"/>
+   <copyField source="subtitle_t" dest="opensearch_display"/>
+   <copyField source="addl_titles_t" dest="opensearch_display"/>
+   <copyField source="title_added_entry_t" dest="opensearch_display"/>
+   <copyField source="title_series_t" dest="opensearch_display"/>
+   <copyField source="author_t" dest="opensearch_display"/>
+   <copyField source="author_addl_t" dest="opensearch_display"/>
+   <copyField source="subject_topic_facet" dest="opensearch_display"/>
+   <copyField source="subject_t" dest="opensearch_display"/>
+   <copyField source="subject_addl_t" dest="opensearch_display"/>  
+
+
+   <!-- 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"/> -->
+   <copyField source="*_s" dest="text"/>
+   <copyField source="*_t" dest="text"/>
+   <copyField source="*_facet" dest="text"/>
+
+   <!-- 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>