ruby-fedora 0.9.0 → 1.0.0

data/solr/config/schema.xml

@@ -1,229 +0,0 @@
-<?xml version="1.0" ?>
-<!--
- Licensed to the Apache Software Foundation (ASF) under one or more
- contributor license agreements.  See the NOTICE file distributed with
- this work for additional information regarding copyright ownership.
- The ASF licenses this file to You under the Apache License, Version 2.0
- (the "License"); you may not use this file except in compliance with
- the License.  You may obtain a copy of the License at
-
-     http://www.apache.org/licenses/LICENSE-2.0
-
- Unless required by applicable law or agreed to in writing, software
- distributed under the License is distributed on an "AS IS" BASIS,
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- See the License for the specific language governing permissions and
- limitations under the License.
--->
-
-<!-- This is the Solr schema file. This file should be named "schema.xml" and
- should be in the conf directory under the solr home
- (i.e. ./solr/conf/schema.xml by default) 
- or located where the classloader for the Solr webapp can find it.
-
- For more information, on how to customize this file, please see
- http://wiki.apache.org/solr/SchemaXml
--->
-
-<schema name="active_fedora" version="0.1">
-  <!-- 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
-       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 -->
-
-  <types>
-    <!-- field type definitions. The "name" attribute is
-       just a label to be used by field definitions.  The "class"
-       attribute and any other attributes determine the real
-       behavior of the fieldtype.
-         Class names starting with "solr" refer to java classes in the
-       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).
-    -->
-    <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"/>
-
-    <!-- The optional sortMissingLast and sortMissingFirst attributes are
-         currently supported on types that are sorted internally as strings.
-       - 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).
-       - If sortMissingFirst="true", then a sort on this field will cause documents
-         without the field to come before documents with the field,
-         regardless of the requested sort order.
-       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
-         then default lucene sorting will be used which places docs without the
-         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"/>
-
-
-    <!-- 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
-         http://www.w3.org/TR/xmlschema-2/#dateTime    
-         The trailing "Z" designates UTC time and is mandatory.
-         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
-         All other components are mandatory.
-
-         Expressions can also be used to denote calculations that should be
-         performed relative to "NOW" to determine the value, ie...
-
-               NOW/HOUR
-                  ... Round to the start of the current hour
-               NOW-1DAY
-                  ... Exactly 1 day prior to now
-               NOW/DAY+6MONTHS+3DAYS
-                  ... 6 months and 3 days in the future from the start of
-                      the current day
-                      
-         Consult the DateField javadocs for more information.
-      -->
-    <fieldtype name="date" class="solr.DateField" sortMissingLast="true" omitNorms="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
-     -->
-
-    <!-- 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">
-      <analyzer>
-        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
-      </analyzer>
-    </fieldtype>
-
-    <fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
-      <analyzer>
-        <tokenizer class="solr.StandardTokenizerFactory"/>
-        <filter class="solr.StandardFilterFactory"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-      </analyzer>
-    </fieldtype>
-
-    <fieldtype name="text_zh" class="solr.TextField">
-      <analyzer class="org.apache.lucene.analysis.cn.ChineseAnalyzer"/>
-    </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" >
-      <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.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
-        <filter class="solr.LowerCaseFilterFactory"/>
-        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
-        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
-      </analyzer>
-    </fieldtype>
-
- </types>
-
-
- <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
-     compressed: [false] if this field should be stored using gzip compression
-       (this will only apply if the field type is compressable; among
-       the standard field types, only TextField and StrField are)
-     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.
-   -->
-
-   <field name="id" type="string" indexed="true" stored="true"/>
-
-   <!-- catchall field, containing all other searchable text fields (implemented
-        via copyField further on in this schema  -->
-   <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
-   <!-- catchall field, containing all other searchable text fields (implemented
-        via copyField further on in this schema  -->
-   <field name="date" type="date" indexed="true" stored="false" multiValued="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="*_date"  type="date"  indexed="true"  stored="true" multiValued="true"/>
-	<dynamicField name="*_name"  type="date"  indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_field"  type="text"  indexed="true"  stored="true" multiValued="true"/>
-
-   <dynamicField name="*_facet"  type="string"  indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_zh_text"   type="text_zh"    indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_text"   type="text"    indexed="true"  stored="true" multiValued="true"/>
-   <dynamicField name="*_display"   type="text"    indexed="false"  stored="true" multiValued="true"/>   
- </fields>
-
- <!-- field to use to determine and enforce document uniqueness. -->
- <uniqueKey>id</uniqueKey>
-
- <!-- field for the QueryParser to use when an explicit fieldname is absent -->
- <defaultSearchField>text</defaultSearchField>
-
- <!-- 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.  -->
- <copyField source="*_date" dest="date"/>
- <copyField source="*_text" dest="text"/>
- <copyField source="*_facet" dest="text"/>
-
- <!-- 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"/> -->
-
-</schema>

data/test/test_helper.rb

@@ -1,6 +0,0 @@
-require 'rubygems'
-require 'test/unit'
-
-require File.dirname(__FILE__) + '/../lib/ruby-fedora'
-
-FEDORA_URL = 'http://localhost:8080/fedora' unless defined? FEDORA_URL