ruby-fedora 0.1.2 → 0.9.0

data/lib/fedora/datastream.rb

@@ -12,11 +12,20 @@ class Fedora::Datastream < Fedora::BaseObject
   end
   
   def dsid
-    attributes[:dsID]
+    if attributes.has_key?(:dsid) 
+      attributes[:dsid]
+    else
+      attributes[:dsID]
+    end
   end
   
   # See http://www.fedora.info/definitions/identifiers/
   def uri
     "fedora:info/#{pid}/datastreams/#{dsid}"
   end
+  
+  # @returns the url of the datastream in Fedora, without the repository userinfo
+  def url
+    return "#{Fedora::Repository.instance.base_url}/objects/#{pid}/datastreams/#{dsid}"
+  end
 end

data/lib/fedora/fedora_object.rb

@@ -33,19 +33,25 @@ class Fedora::FedoraObject < Fedora::BaseObject
   # TODO: Mix In DC attribute finders/accessors
   # TODO: Make sure that fedora_object_type and contentModel are juggled properly. 
   def retrieve_attr_from_fedora
-    self.attributes.merge!(objectProfile)
+    self.attributes.merge!(profile)
+    object_rexml = REXML::Document.new(object_xml)
     self.attributes.merge!({
-         :state => objectXML.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#state']"].attributes["value"]
+         :state => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#state']"].attributes["value"],
+         :create_date => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#createdDate']"].attributes["value"],
+         :modified_date => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#lastModifiedDate']"].attributes["value"],
+         :label => object_rexml.root.elements["objectProperties/property[@NAME='info:fedora/fedora-system:def/model#label']"].attributes["value"]
     })
   
   end
 
   def create_date
-    objectProfile[:create_date]
+    profile[:create_date]
+    #self.attributes[:cDate]
   end
 
   def modified_date
-    objectProfile[:modified_date]
+    profile[:create_date]
+    #self.attributes[:mDate]
   end
 
 
@@ -77,14 +83,6 @@ class Fedora::FedoraObject < Fedora::BaseObject
     self.attributes[:label] = new_label
   end
 
-  def content_model
-    self.attributes[:contentModel]
-  end
-
-  def content_model=(new_content_model)
-    self.attributes[:contentModel] = new_content_model
-  end
-
   #  Get the object and read its @ownerId from the profile
   def owner_id
     self.attributes[:ownerID]
@@ -96,24 +94,30 @@ class Fedora::FedoraObject < Fedora::BaseObject
   
   def profile
     # Use xmlsimple to slurp the attributes
-    objectProfile = XmlSimple.xml_in(@fedora.call_resource(:retrieve, :objects_profile, {:pid => @pid}))
-    # TODO: Find out if xmlsimple automatically expands camelCased element names...
-    profile_as_array = {
-      :owner_id => objectProfile[objOwnerId],
-      :content_model => objectProfile[objContentModel],
-      :label => objectProfile[objLabel],
-      :date_created => objectProfile[objCreateDate],
-      :date_modified => objectProfile[objLastModDate]
-    }
+    retrieved_profile = XmlSimple.xml_in(Fedora::Repository.instance.fetch_custom(self.pid, :profile))
+    profile_hash = Hash[:owner_id => retrieved_profile["objOwnerId"],
+                          :label => retrieved_profile["objLabel"],
+                          :create_date =>  retrieved_profile["objCreateDate"],
+                          :modified_date => retrieved_profile["objLastModDate"]
+                        ]                           
   end
 
-  def objectXML
-    # Use REXML to slurp the attributes (can't use xmlsimple because the XML is too complex.  Need XPath-like queries.
-    @objectXML ||= REXML::Document.new(@fedora.call_resource(:retrieve, :objects_objectXml, {:pid => @pid}))
+  def object_xml
+    Fedora::Repository.instance.fetch_custom(pid, :objectXML)
+  end
+  
+  def self.object_xml(pid=pid)
+    Fedora::Repository.instance.fetch_custom(pid, :objectXML)
   end
   
   # See http://www.fedora.info/definitions/identifiers
   def uri
     "fedora:info/#{pid}"
   end
+  
+  # @returns the url of the object in Fedora, without the repository userinfo
+  def url
+    repo_url = Fedora::Repository.instance.fedora_url
+    return "#{repo_url.scheme}://#{repo_url.host}:#{repo_url.port}#{repo_url.path}/objects/#{pid}"
+  end
 end  

data/lib/fedora/generic_search.rb

@@ -0,0 +1,71 @@
+# 
+#  @Creator Matt Zumwalt, MediaShelf LLC
+#  @Copyright Matt Zumwalt, 2007.  All Rights Reserved.
+#
+ 
+module Fedora
+  class GenericSearch
+  
+    def initialize(uri, service_name)
+      @uri = "#{uri}/#{service_name}"
+      @client = HTTPClient.new(@uri)
+      @extheader = {'User-Agent'=>"RubyFedora"}
+    end
+  
+    def call_resource
+    
+    end
+  
+    # TODO: Handle ruby-tyle params, camel-casing them before passing to call_resource...
+    def update_index(params)
+      query = {:action=>action,:value=>value,:repositoryName=>repository_name,:indexName=>indexname,:restXslt=>"copyXML"}.merge(params)
+      query.merge {:operation> "updateIndex"}
+    
+      @client.get(@uri, query, @extheader)
+      return "update_index Not Implemented."
+    end
+  
+  
+    def browse_index(params)
+      # Sample: /fedoragsearch/rest?operation=browseIndex&startTerm=&fieldName=PID&termPageSize=20&indexName=FedoraIndex&restXslt=copyXml&resultPageXslt=browseIndexToResultPage
+      query = {:startTerm=>URLEncoder.encode(start_term, "UTF-8"),:fieldName=>"",:indexName=>"",:termPageSize=>"", :restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
+      query.merge {:operation> "browseIndex"}
+      @client.get(@uri, query, @extheader)
+      return "browse_index Not Implemented."
+    end
+  
+    def gfind_objects(params)
+      # Sample: /fedoragsearch/rest?operation=gfindObjects&query=test&hitPageSize=10&restXslt=copyXml
+      # fieldMaxLength limits the number of characters returned from the value of each object field.
+      # Snippets will highlight matched words within the search results.  To keep the xml as simple as possible, set snippetsMax to 0.
+      query = {:query=>URLEncoder.encode(query, "UTF-8"),:value=>value,:indexName=>indexname,:hitPageStart=>"",:hitPageSize=>"",:snippetsMax=>"0",:fieldMaxLength=>"",:restXslt=>"copyXML",:resultPageXslt=>""}.merge(params)
+      query.merge {:operation> "gfindObjects"}
+      @client.get(@uri, query, @extheader)
+      return "gfind_objects Not Implemented."
+    end
+  
+    def get_index_info(params)
+      # Sample: /fedoragsearch/rest?operation=getIndexInfo&restXslt=copyXml
+      query = {:indexName=>"",:restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
+      query.merge {:operation> "getIndexInfo"}
+      @client.get(@uri, query, @extheader)
+      return "get_index_info Not Implemented."
+    end
+  
+    def get_repository_info(params)
+      # Sample: /fedoragsearch/rest?operation=getRepositoryInfo&restXslt=copyXml
+      query = {:repositoryName=>"",:restXslt=>"copyXml", :resultPageXslt=>""}.merge(params)
+      query.merge {:operation> "getRepositoryInfo"}
+      @client.get(@uri, query, @extheader)
+      return "get_repository_info Not Implemented."
+    end
+  
+    def configure(params)
+      query = {:configName=>""}.merge(params)
+      query.merge {:operation> "configure"}
+      @client.get(@uri, query, @extheader)
+      return "configure Not Implemented."
+    end
+  
+  end
+end

data/lib/fedora/repository.rb

@@ -15,6 +15,30 @@ module Fedora
   ]
   
   class Repository
+    
+    attr_accessor :repository_name, :base_url, :fedora_version, :pid_namespace, :pid_delimiter
+    
+    def self.flush
+      Thread.current[:repo]=nil
+    end
+    def self.register(url, surrogate=nil)
+      Thread.current[:repo]= Fedora::Repository.new(url, surrogate)
+      begin
+        repo = Thread.current[:repo]
+        attributes = repo.describe_repository
+        repo.repository_name = attributes["repositoryName"].first
+        repo.base_url = attributes["repositoryBaseURL"].first
+        repo.fedora_version = attributes["repositoryVersion"].first
+        repo.pid_namespace = attributes["repositoryPID"].first["PID-namespaceIdentifier"].first
+        repo.pid_delimiter = attributes["repositoryPID"].first["PID-delimiter"].first
+      rescue
+      end
+      Thread.current[:repo]
+    end
+    def self.instance
+      raise "did you register a repo?" unless Thread.current[:repo]
+      Thread.current[:repo]
+    end
     class StringResponse < String
       attr_reader :content_type
       
@@ -26,8 +50,9 @@ module Fedora
     
     attr_accessor :fedora_url
 
-    def initialize(fedora_url = "http://localhost:8080/fedora") 
+    def initialize(fedora_url, surrogate=nil)
       @fedora_url = fedora_url.is_a?(URI) ? fedora_url : URI.parse(fedora_url)
+      @surrogate = surrogate
       @connection = nil
     end
     
@@ -37,6 +62,8 @@ module Fedora
       StringResponse.new(response.body, response.content_type)
     end
     
+
+    
     # Find fedora objects with http://www.fedora.info/wiki/index.php/API-A-Lite_findObjects
     #
     # == Parameters
@@ -69,6 +96,11 @@ module Fedora
       
       convert_xml(connection.get("#{fedora_url.path}/objects?#{params.to_query}#{includes}"))
     end
+    def find_model(pid, klazz)
+      obj = self.find_objects("pid=#{pid}").first
+      doc = REXML::Document.new(obj.object_xml, :ignore_whitespace_nodes=>:all)
+      klazz.deserialize(doc)
+    end
     
     # Create the given object if it's new (not obtained from a find method).  Otherwise update the object.
     #
@@ -78,6 +110,12 @@ module Fedora
     def save(object)
       object.new_object? ? create(object) : update(object)
     end
+
+    def nextid
+      d = REXML::Document.new(connection.post(fedora_url.path+"/management/getNextPID?xml=true").body)
+      d.elements['//pid'].text
+    end
+
   
     def create(object)
       case object
@@ -139,7 +177,7 @@ module Fedora
     def delete(object)
       raise ArgumentError, "Object must not be nil" if object.nil?
       response = connection.delete("#{url_for(object)}")
-      response.code == '200'
+      response.code == '200' or response.code == '204'  # Temporary hack around error in Fedora 3.0 Final's REST API
     end
 
     # Fetch the given object using custom method.  This is used to fetch other aspects of a fedora object,
@@ -162,6 +200,11 @@ module Fedora
       connection.raw_get("#{url_for(object)}#{path}?#{extra_params.to_query}").body
     end
     
+    def describe_repository
+      result_body = connection.raw_get("#{fedora_url.path}/describe?xml=true").body
+      XmlSimple.xml_in(result_body)
+    end
+    
   private
     def convert_xml(response)
       results = FedoraObjects.new
@@ -175,6 +218,7 @@ module Fedora
         when Hash
           results << FedoraObject.new(objectFields.symbolize_keys!)
       end
+      results.each {|result| result.new_object = false}
       results
     end
     
@@ -189,7 +233,7 @@ module Fedora
     # or not (defaults to +false+).
     def connection(refresh = false)
       if refresh || @connection.nil?
-        @connection = RubyFedora::Connection.new(@fedora_url, Fedora::XmlFormat)
+        @connection = Fedora::Connection.new(@fedora_url, Fedora::XmlFormat, @surrogate)
       end
       @connection
     end

data/lib/ruby-fedora.rb

@@ -1,17 +1,18 @@
 $LOAD_PATH.unshift File.dirname(__FILE__) unless
-  $LOAD_PATH.include?(File.dirname(__FILE__)) ||
-  $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
+$LOAD_PATH.include?(File.dirname(__FILE__)) || $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
 
-module RubyFedora #:nodoc:
+module Fedora #:nodoc:
   module VERSION #:nodoc:
-    MAJOR = 0
-    MINOR = 1
-    TINY  = 2
+    unless defined? MAJOR
+      MAJOR = 0
+      MINOR = 9
+      TINY  = 0
 
-    STRING = [MAJOR, MINOR, TINY].join('.')
+      STRING = [MAJOR, MINOR, TINY].join('.')
+    end
   end
 end
 
 module Fedora; end
 
-require 'fedora/repository'
+require 'fedora/repository'

data/lib/util/class_level_inheritable_attributes.rb

@@ -0,0 +1,23 @@
+module MediaShelfClassLevelInheritableAttributes
+  def self.included(base)
+    base.extend(MSClassMethods)
+  end
+  module MSClassMethods
+    def ms_inheritable_attributes(*args)
+      @ms_inheritable_attributes ||=[:ms_inheritable_attributes]
+      @ms_inheritable_attributes+=args
+      args.each do |arg|
+        class_eval %(
+          class <<self;attr_accessor :#{arg} end
+        )
+      end
+      @ms_inheritable_attributes
+    end
+    def inherited(subclass)
+      @ms_inheritable_attributes.each do |attrib|
+        instance_var = "@#{attrib}"
+        subclass.instance_variable_set(instance_var, instance_variable_get(instance_var))
+      end
+    end
+  end
+end

data/solr/config/schema.xml

@@ -0,0 +1,229 @@
+<?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>