jruby_streaming_update_solr_server 0.3.1 → 0.4.1

data/README.rdoc

@@ -25,7 +25,6 @@ See the class files for more information, documentation, and examples.
     #
     #   doc = SolrInputDocument.new
     #   doc.add 'title', 'This is the title'
-    #   doc.add :title, 'Another title' # symbols are automatically cast to strings for field name
     #   doc << ['title', "This is yet another title, added with '<<'"]
     #   doc.add 'id', 1
     #   doc.add 'author', ['Mike', 'Bill', 'Molly'] # adds multiple values at once
@@ -38,8 +37,7 @@ See the class files for more information, documentation, and examples.
     #   suss = StreamingUpdateSolrServer.new(url,queuesize,threads)
     #   hash = {}
     #   hash['title'] = This is the title'
-    #   hash[:id] = 1 # Can also take symbols instead of strings if you like
-    #   hash[:author] = ['Bill', 'Mike'] # Note that we can add multiple values at once 
+    #   hash['author'] = ['Bill', 'Mike'] # Note that we can add multiple values at once 
     #   suss << hash
     #   # repeat as desired
     #   suss.commit
@@ -56,20 +54,24 @@ construct Solr documents and send them to Solr all from within the comfort of th
 
 Note that you can use threach to multi-thread it all.
 
-== WARNING: Program hangs on for 60 seconds!
-
-*WARNING*: After your program ends, the StreamingUpdateSolrServer object hangs on for a full minute, presumably
-the timeout of the underlying http client object. I haven't figure out how to change this yet.
 
 == ToDo
 
 * Figure out why the http client hangs on for so long
-* Modify SolrInputDocument.add to take a relevancy weight. 
 * More complete examples
 
 
 === CHANGES
 
+0.4.1 (2010.09.07)
+* Updated documentation
+* Added access to document-level boost via #boost and #boost=
+* Added access to field-level boost via #fieldBoost and #setFieldBoost
+* Added third parameter to `#add` for field-level boost
+* Added #values
+* Release new gem
+
+
 2010.07.09 Added #useJavabin!
 
 == Copyright

data/Rakefile

@@ -10,7 +10,7 @@ begin
     gem.email = "bill@dueber.com"
     gem.homepage = "http://github.com/billdueber/jruby_streaming_update_solr_server"
     gem.authors = ["Bill Dueber"]
-    gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
+    gem.add_development_dependency 'bacon', ">=0"
     gem.add_development_dependency "yard", ">= 0"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end
@@ -20,18 +20,18 @@ rescue LoadError
 end
 
 require 'rake/testtask'
-Rake::TestTask.new(:test) do |test|
-  test.libs << 'lib' << 'test'
-  test.pattern = 'test/**/test_*.rb'
-  test.verbose = true
+Rake::TestTask.new(:spec) do |spec|
+  spec.libs << 'lib' << 'spec'
+  spec.pattern = 'spec/**/*_spec.rb'
+  spec.verbose = true
 end
 
 begin
   require 'rcov/rcovtask'
-  Rcov::RcovTask.new do |test|
-    test.libs << 'test'
-    test.pattern = 'test/**/test_*.rb'
-    test.verbose = true
+  Rcov::RcovTask.new do |spec|
+    spec.libs << 'spec'
+    spec.pattern = 'spec/**/*_spec.rb'
+    spec.verbose = true
   end
 rescue LoadError
   task :rcov do
@@ -41,7 +41,7 @@ end
 
 task :test => :check_dependencies
 
-task :default => :test
+task :default => :spec
 
 begin
   require 'yard'

data/VERSION

@@ -1 +1 @@
-0.3.1
+0.4.1

data/lib/jruby_streaming_update_solr_server.rb

@@ -67,7 +67,7 @@ class  StreamingUpdateSolrServer
   # Add a document to the SUSS 
   # @param [SolrInputDocument, #each_pair] doc The SolrInputDocument or hash (or hash-like object
   # that responds to #each_pair) to add. The latter must be of the form solrfield => value or
-  # solrfield => [list, of, values]. They keys can be either symbols or strings.
+  # solrfield => [list, of, values]. They keys must be strings.
   #
   # @example Create and add a SolrInputDocument
   #   url = 'http://solrmachine:port/solr' # URL to solr
@@ -88,8 +88,7 @@ class  StreamingUpdateSolrServer
   #   suss = StreamingUpdateSolrServer.new(url,queuesize,threads)
   #   doc = {}
   #   doc['title'] = This is the title'
-  #   doc[:id] = 1 # Can also take symbols instead of strings if you like
-  #   doc[:author] = ['Bill', 'Mike']
+  #   doc['author'] = ['Bill', 'Mike']
   #   suss << doc
   #   # repeat as desired
   #   suss.commit
@@ -116,18 +115,62 @@ end
 #
 # @author Bill Dueber
 
+# SolrInputDocument is a wrapper around the {http://lucene.apache.org/solr/api/org/apache/solr/common/SolrInputDocument.html Java SolrInputDocument}. 
+# In addition to the methods below, you can call the java methods directly. Common ones are:
+# * `#clear` to empty the document
+# * `#size` to get the number of k-v pairs
+# * `#boost` and `#boost=` to get and set the document-level boost
+
 class SolrInputDocument
+  
+  
+  # Get the document boost for this document
+  # @return [Float] the current document boost
+  alias_method :boost, :getDocumentBoost
+  
+  # Set the document boost
+  # @param [Float] boost The boost for the document
+  # @return [Float] the new boost
+  
+  alias_method :boost=, :setDocumentBoost
+  
+  
+  # Boost a field. Does nothing if the field does not exist
+  # @param [String] field The name of the field
+  # @param [Float] boost The new boost
+  # @return [Float] the new boost
+  
+  def setFieldBoost field, boost
+    f = self.get(field)
+    if f
+      f.setBoost(boost)
+      return boost
+    else
+      return nil
+    end
+  end
+  
+  # get the field boost
+  # @param [String] field The field whose boost you want
+  # @return [Float] The boost
+  
+  def fieldBoost field
+    f = self.get(field)
+    if f
+      return f.getBoost
+    else
+      return nil
+    end
+  end
     
   # Add a value to a field. Will add all elements of an array in turn
-  # @param [Symbol, String] field The field to add a value or values to
+  # @param [String] field The field to add a value or values to
   # @param [String, Numeric, #each] val The value or array-like of values to add.
+  # @param [Float] boost The boost for this field
   # @return [Array<String,Numeric>] An array of the field's values after this addition
   
-  def add(field, val)
+  def add(field, val, boost=nil)
     return if val == nil
-    if field.is_a?(Symbol)
-      field = field.to_s
-    end
     if val.is_a? String or val.is_a? Numeric
       self.addField(field, val)
     else
@@ -137,13 +180,14 @@ class SolrInputDocument
         raise NoMethodError, "SolrInputDocument values must be a string, numeric, or an array-like (responds to #each) of same, not #{val.inspect}"
       end
     end
-    self[field]
+    self.boost = boost if boost
+    return self[field]
   end  
   
   
-  # An alternate syntax for #add, which will usuall be preferred.
+  # An alternate syntax for #add.
   #
-  # @param [Array<Symbol, String>] fv A two-element array of the form [field, value] or [field, [value1, value2, ...]]
+  # @param [Array<String>] fv A two-element array of Strings of the form [field, value] or [field, [value1, value2, ...]]
   # @return [Array<String>] the list of current values for the field in fv[0]
   #
   # @example Add some fields
@@ -162,13 +206,10 @@ class SolrInputDocument
   #
   # Note that this will always return either nil (not found) or an array, even of one element
   #
-  # @param [String, Symbol] field The field whose values you want (as String or Symbol)
+  # @param [String] field The field whose values you want (as String)
   # @return [Array<String>] An array of values (or nil on not found)
   #
   def [] field
-    if field.is_a?(Symbol)
-      field = field.to_s
-    end
     f = self.get(field)
     return nil if (f == nil)
     return f.values.to_a
@@ -178,23 +219,20 @@ class SolrInputDocument
   #
   # Note that this is destructive; see #<< to add multiple values to a field
   #
-  # @param [String, Symbol] field The solr field you're setting the value of
+  # @param [String] field The solr field you're setting the value of
   # @param [String, Array<String>] value The value or array of values to set
   # @return [Array<String>] The list of values (i.e., either +value+ or +[value]+)
   #
   # @example
   #  doc = SolrInputDocument.new
-  #  doc[:id] = 1 #=> [1]
-  #  doc[:author] = 'Mike' #=> ['Mike']
-  #  doc[:author] = 'Bill' #=> ['Bill']
-  #  doc[:author] #=> ['Bill']
+  #  doc['id'] = 1 #=> [1]
+  #  doc['author'] = 'Mike' #=> ['Mike']
+  #  doc['author'] = 'Bill' #=> ['Bill']
+  #  doc['author'] #=> ['Bill']
   
   def []= field, value
-    if field.is_a?(Symbol)
-      field = field.to_s
-    end
     self.removeField(field)
-    self.add(field, value)
+    self.add(field, value) unless value.nil?
   end
   
   
@@ -206,15 +244,15 @@ class SolrInputDocument
   #
   # @example Merge a hash into an existing document
   #   doc = SolrInputDocument.new
-  #   doc << [:author, 'Bill']
+  #   doc << ['author', 'Bill']
   #   h = {}
   #   h['author'] = 'Mike'
   #   h['id'] = 1
-  #   h[:copies] = ['Grad reference', 'Long-term storage']
+  #   h['copies'] = ['Grad reference', 'Long-term storage']
   #   doc.merge! h
-  #   doc[:id] #=> 1
-  #   doc[:author] #=> ['Bill', 'Mike']
-  #   doc[:copies] #=> ['Grad reference', 'Long-term storage']
+  #   doc['id'] #=> 1
+  #   doc['author'] #=> ['Bill', 'Mike']
+  #   doc['copies'] #=> ['Grad reference', 'Long-term storage']
   
   def merge! h
     unless h.respond_to? :each_pair
@@ -241,17 +279,45 @@ class SolrInputDocument
     return self.keySet.to_a
   end
 
+  # Get the values as an array
+  # @return [Array<String] An array of all the values in all the keys (flattened out)
+  #
+  alias_method :oldvalues, :values
+  def values
+    rv = self.keys.map {|k| self[k]}
+    rv.uniq!
+    rv.flatten!
+    return rv
+  end
+
   # Does this doc contain the given key?
-  # @param [Symbol, String] field The field whose presence you want to check
+  # @param [String] field The field whose presence you want to check
   # @return [Boolean] True if the key is present
   
   def has_key? field
-    if field.is_a?(Symbol)
-      field = field.to_s
-    end
     return self.containsKey(field)
   end
 
+  # Does this doc have the given value?
+  # @param [String] value to look for
+  # @return [Boolean]
+  
+  def has_value? val
+    self.keys.each do |k|
+      return true if self[k].include? val
+    end
+    return false
+  end
+  
+  # Delete a key/value pair
+  # @param [String] key The key
+  # @return [Array<String>] The removed values (or nil)
+  
+  def delete key
+    rv = self[key]
+    self.removeField key
+    return rv
+  end
   
 end
 

data/spec/basics_spec.rb

@@ -0,0 +1,82 @@
+require 'spec_helper'
+
+describe "SolrDocument" do
+  
+  before do
+    @doc = SolrInputDocument.new
+  end
+  
+  it "starts out empty" do
+    @doc.empty?.should.equal true
+    @doc.size.should.equal 0
+    @doc.values.should.equal []
+    @doc.keys.should.equal []
+  end
+  
+  it "reports nil for an unset field" do
+    @doc['notinhere'].should.equal nil
+  end
+  
+  it "sets using =" do
+    @doc['t'] = 1
+    @doc['t'].should.equal [1]
+    @doc['t'] = 2
+    @doc['t'].should.equal [2]
+  end
+  
+  it "adds using <<" do
+    @doc << ['t', 1]
+    @doc['t'].should.equal [1]
+    @doc << ['t', 2]
+    @doc['t'].should.equal [1,2]
+  end
+
+  it "adds items in hash via merge!" do
+    @doc << ['id', '1']
+    h = {'id' => '2', 'name' => 'Bill'}
+    @doc.merge! h
+    @doc['id'].should.equal ['1', '2']
+    @doc['name'].should.equal ['Bill']
+    @doc.values.sort.should.equal ['1', '2','Bill'].sort
+  end
+
+  it "aliases additive_merge! as well" do
+    @doc << ['id', 1]
+    h = {'id' => 2, 'name' => 'Bill'}
+    @doc.additive_merge! h
+    @doc['id'].should.equal [1,2]
+    @doc['name'].should.equal ['Bill']    
+  end  
+  
+  it "correctly finds keys and values" do
+    @doc << ['id', '1']
+    @doc << ['name', 'Bill']
+    @doc.has_key?('name').should.equal true
+    @doc.has_key?('id').should.equal true
+    @doc.has_key?('junk').should.equal false
+    @doc.has_value?('1').should.equal true
+    @doc.has_value?('Bill').should.equal true
+    @doc.has_value?('junk').should.equal false
+  end
+  
+  it "can add multiple items at once" do
+    @doc.add('name', ['Bill', 'Mike', 'Molly'])
+    @doc['name'].sort.should.equal ['Bill', 'Mike', 'Molly'].sort
+  end
+  
+  it "boosts the doc" do
+    @doc.boost = 100
+    @doc.boost.should.equal 100
+  end
+  
+  it "boosts a field" do
+    @doc.add('id', '1')
+    @doc.fieldBoost('id').should.equal 1.0
+    @doc.setFieldBoost('id', 100.0)
+    @doc.fieldBoost('id').should.equal 100.0
+    @doc.setFieldBoost('junk', 100.0).should.equal nil
+    @doc.fieldBoost('junk').should.equal nil
+    
+  end
+  
+end

data/{test/helper.rb → spec/spec_helper.rb}

@@ -1,10 +1,14 @@
 require 'rubygems'
-require 'test/unit'
-require 'shoulda'
+require 'bacon'
+begin
+  require 'greeneggs'
+rescue LoadError
+end
 
-$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 require 'jruby_streaming_update_solr_server'
 
-class Test::Unit::TestCase
-end
+DIR = File.dirname(__FILE__)
+
+Bacon.summary_on_exit

metadata

@@ -1,46 +1,51 @@
 --- !ruby/object:Gem::Specification 
 name: jruby_streaming_update_solr_server
 version: !ruby/object:Gem::Version 
+  hash: 13
   prerelease: false
   segments: 
-    - 0
-    - 3
-    - 1
-  version: 0.3.1
+  - 0
+  - 4
+  - 1
+  version: 0.4.1
 platform: ruby
 authors: 
-  - Bill Dueber
+- Bill Dueber
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2010-08-16 00:00:00 -04:00
+date: 2010-09-07 00:00:00 -04:00
 default_executable: 
 dependencies: 
-  - !ruby/object:Gem::Dependency 
-    name: thoughtbot-shoulda
-    prerelease: false
-    requirement: &id001 !ruby/object:Gem::Requirement 
-      requirements: 
-        - - ">="
-          - !ruby/object:Gem::Version 
-            segments: 
-              - 0
-            version: "0"
-    type: :development
-    version_requirements: *id001
-  - !ruby/object:Gem::Dependency 
-    name: yard
-    prerelease: false
-    requirement: &id002 !ruby/object:Gem::Requirement 
-      requirements: 
-        - - ">="
-          - !ruby/object:Gem::Version 
-            segments: 
-              - 0
-            version: "0"
-    type: :development
-    version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: bacon
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: yard
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :development
+  version_requirements: *id002
 description: Some sugar on top of StreamingUpdateSolrServer for use within JRuby
 email: bill@dueber.com
 executables: []
@@ -48,52 +53,56 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
-  - LICENSE
-  - README.rdoc
+- LICENSE
+- README.rdoc
 files: 
-  - LICENSE
-  - README.rdoc
-  - Rakefile
-  - VERSION
-  - jars/apache-solr-solrj-1.5-dev.jar
-  - jars/commons-codec-1.3.jar
-  - jars/commons-httpclient-3.1.jar
-  - jars/commons-logging-1.1.1.jar
-  - jars/slf4j-api-1.5.5.jar
-  - jars/slf4j-jdk14-1.5.5 2.jar
-  - lib/jruby_streaming_update_solr_server.rb
-  - test/helper.rb
-  - test/test_jruby_streaming_update_solr_server.rb
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- jars/apache-solr-solrj-1.5-dev.jar
+- jars/commons-codec-1.3.jar
+- jars/commons-httpclient-3.1.jar
+- jars/commons-logging-1.1.1.jar
+- jars/slf4j-api-1.5.5.jar
+- jars/slf4j-jdk14-1.5.5 2.jar
+- lib/jruby_streaming_update_solr_server.rb
+- spec/basics_spec.rb
+- spec/spec_helper.rb
 has_rdoc: true
 homepage: http://github.com/billdueber/jruby_streaming_update_solr_server
 licenses: []
 
 post_install_message: 
 rdoc_options: 
-  - --charset=UTF-8
+- --charset=UTF-8
 require_paths: 
-  - lib
+- lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-          - 0
-        version: "0"
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-          - 0
-        version: "0"
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: Simple jruby interface into StreamingUpdateSolrServer
 test_files: 
-  - test/helper.rb
-  - test/test_jruby_streaming_update_solr_server.rb
+- spec/basics_spec.rb
+- spec/spec_helper.rb

data/test/test_jruby_streaming_update_solr_server.rb

@@ -1,49 +0,0 @@
-require 'helper'
-
-class TestJrubyStreamingUpdateSolrServer < Test::Unit::TestCase
-  should "Write some tests, but don't know how to mock up a solr server" do
-    assert_equal 1, 1
-  end
-
-  should "Report nil for a document that doesn't include a field" do 
-    doc = SolrInputDocument.new
-    assert_equal nil, doc[:notinthere]
-  end
-  
-  should "Return single and multiple values in arrays" do
-    doc = SolrInputDocument.new
-    doc << [:id, 1]
-    assert_equal [1], doc[:id]
-    doc << [:id, 2]
-    assert_equal [1,2], doc[:id]
-  end
-  
-  should "Add items in hash via merge!" do
-    doc = SolrInputDocument.new
-    doc << [:id, 1]
-    h = {:id => 2, :name => 'Bill'}
-    doc.merge! h
-    assert_equal [1,2], doc[:id]
-    assert_equal ['Bill'], doc[:name]
-  end
-  
-  should "Allow additive_merge! as well" do
-    doc = SolrInputDocument.new
-    doc << [:id, 1]
-    h = {:id => 2, :name => 'Bill'}
-    doc.additive_merge! h
-    assert_equal [1,2], doc[:id]
-    assert_equal ['Bill'], doc[:name]
-    
-  end
-  
-  should "Destroy existing items via []=" do
-    doc = SolrInputDocument.new
-    doc[:id] = 1
-    assert_equal [1], doc[:id]
-    doc[:id] = 2
-    assert_equal [2], doc[:id]
-  end    
-    
-
-end