philologic-client 0.0.11 → 0.0.13

data/HISTORY.rdoc

@@ -1,5 +1,13 @@
 = Philologic::Client History
 
+== 2012-03-30 v0.0.13
+
+* Supports all of the Philologic v4 specification except collocation tables
+
+== 2012-02-13 v0.0.12
+
+* Revert to parsing with +Nokogiri::HTML+, not +Nokogiri::XML+
+
 == 2012-02-09 v0.0.11
 
 * Added +Philologic::Link#text()+

data/PhiloLogicResponseDocumentation.txt

@@ -0,0 +1,86 @@
+---Concordance Report: returned by fulltext searches---
+
+<div class='philologic_response'>
+ <ol class='philologic_concordance'>
+  <li class='philologic_occurrence'>
+    <span class='hit_n'> {hit_number} </span>
+    <a href =’{link_to_cited_object}' class='philologic_cite'>
+        <span class='philologic_property' title="{key}">{value}</span>
+        {more properties}
+    </a>
+    {possibly multiple links with their own properties--page images, etc.}
+    <div class='philologic_context'>{left context} 
+     <span class='hilite'>{search term}<span>
+     …{possibly multiple separate hilt terms}…{right context}
+    </div>
+  </li>
+  {probably many occurrences}
+ </ol>
+</div>
+
+
+---Bibliography Report: returned by metadata-only---
+
+<div class='philologic_response'>
+ <ol class='philologic_cite_list'>
+  <li class='philologic_occurrence'>
+    <span class='hit_n'> {hit_number} </span>
+    <div class='philologic_cite'>
+      <a href='{link_to_cited_object}'>
+        <span class='philologic_property' title="{key}">{value}</span>
+        {more properties}
+      </a>
+      {possibly multiple links with their own properties--page images, etc.}
+    </div>
+  </li>
+  {probably many occurrences}
+ </ol>
+</div>
+
+
+---Frequency Table: returned by frequency and collocation reports---
+<div class='philologic_response'>
+ <table class='philologic_table'>
+  <tr class='freq_header_row'>
+    <th class='freq_checkbox_header'></th>
+    <th class='freq_label_header'> {facet_widget} </th>
+    <th class='freq_value_header'> {count} </th>
+  </tr>
+  <tr class='freq_row'>
+    <td class='freq_checkbox'><input type='checkbox'></input></td>
+    <td class='freq_label'> <a href='{link to concordance}'> {label} </a></td>
+    <td class='freq_value'> {count} </td>
+  </tr>
+  {probably many rows}
+ </table>
+</div>
+
+
+---Object Viewer: returned by div and paragraph object access---
+
+<div class='philologic_response'>
+  <div class=’philologic_cite’> 
+   <span class='philologic_property' title="{key}">{value}</span>
+   {more properties}
+  </div>
+  <div class=’philologic_object’>
+   {various content}
+   <span class='hilite'>{hilit word}</span>
+   {possibly multiple hilit words}
+  </div>
+</div>
+
+
+---Object Navigation: returned by document objects, links to children---
+
+<div class='philologic_response'>
+  <div class=’philologic_cite’> 
+   <span class='philologic_property' title="{key}">{value}</span>
+   {more properties}
+  </div>
+  <div class=’philologic_navigation’>
+   <a href=”zzz”>[link to child object]</a>
+   [links to all child objects]
+  </div>
+</div>
+

data/README.rdoc

@@ -6,50 +6,74 @@
 
  Philologic::Client.new(endpoint) do |client|
 
-   # Get children of root
-   client.children.each { |child| puts child }
+   # Get/Set encoding
+   encoding        = client.encoding 
+   client.encoding = 'utf-8' # Default
 
-   # Get document
-   first = client.children.first
-   doc   = first.document
-   html  = doc.html
-   txt   = doc.text
+   # Get/Set endpoint
+   endpoint        = client.endpoint
+   client.endpoint = 'http://philologic.example.org'
 
+   # Get bibliography
+   # +biblio+ is a Philologic::Client::Bibliography object
+   biblio = client.bibliography
+   
+   # Get reference to first title
+   # +first+ is a Philologic::Client::Occurrence object
+   first  = biblio.titles.first
 
-   # Simple (concordance) search
-   client.search('sartre').each { |result| puts result }
+   # Get first title
+   # +doc+ will be a Philologic::Client::Document object
+   doc = client.document( first['href'] )
 
-   # Search by arbitrary key-value pairs
-   client.search( :query => 'sartre', :foo => 1 ).each { |result| puts result }
+   # Get text if present
+   if doc.text?
+     txt  = doc.text # Document text
+     html = doc.html # Document HTML
+   end
 
+   # Get links if present
+   if doc.links?
+     doc.links.each do |link|
+      # +link+ is Philologic::Client::Link object
+      link.url  # Link URL
+      link.text # Link text
+     end
+   end
 
-   # Simple collocation table search.
-   client.collocation('sartre').each { |result| puts result }
+   # Get +Array+ of document property keys.
+   doc.keys
 
-   # Collocation table search by arbitrary key-value pairs
-   client.collocation( :query => 'sartre', :foo => 1 ).each { |result| puts result }
+   # Get document properties
+   doc.each { |p| puts "%s\t%s" % [ p, doc[p] ] }
 
-   # Links for first result in collocation table search
-   client.collocation('sartre').first.links.each { |link| puts link }
 
+   # Concordance search
+   # Returns Philologic::Client::Concordance object
+   q = client.concordance('lion')
 
-   # Simple frequency table search.
-   client.frequency('sartre').each { |result| puts result }
+   # Get results if present.
+   if q.results?
+     q.results.each do |result|
+       # +result+ is a Philologic::Client::Occurrence object
+     end 
+   end
 
-   # Frequency table search by arbitrary key-value pairs
-   client.frequency( :query => 'sartre', :foo => 1 ).each { |result| puts result }
 
-   # Links for first result in frequency table search
-   client.frequency('sartre').first.links.each { |link| puts link }
+   # Frequency search
+   # Returns Philologic::Client::Frequency object
+   q = client.frequency('lion')
 
+   # Get results if present
+   if q.results?
+     q.results.each do |result|
+       # +result+ is a Philologic::Client::FrequencyRow object
+     end
+   end
 
-   # Get/Set encoding
-   encoding        = client.encoding 
-   client.encoding = 'utf-8' # Default
 
-   # Get/Set endpoint
-   endpoint        = client.endpoint
-   client.endpoint = 'http://philologic.example.org'
+   # Collocation search
+   # TODO - Pending implementation update
 
  end
 
@@ -68,8 +92,6 @@ https://github.com/blairc/philologic-client/
 
 == To Do
 
-* Add +children+ to Philologic::Document
-* Add +parent+ to Philologic::Document
-* Unify (as much as possible) Philologic::Document, Philologic::Link, Philologic::TableRow
+* Collocation searches
 * Cache results?
 

data/Rakefile

@@ -22,3 +22,29 @@ RDoc::Task.new do |rdoc|
   rdoc.rdoc_files.include('README.rdoc', 'lib/**/*.rb', 'doc/*.txt')
 end
 
+desc 'Update test data files'
+task :update_test_data do
+  require 'net/http'
+  require 'uri'
+
+  endpoint      = 'http://pantagruel.ci.uchicago.edu/philo4/shakespeare/dispatcher.py'
+  test_data_dir = File.join( File.dirname(__FILE__), 'test', 'data' )
+  test_data_ext = '.html'
+  {
+    '?title='                                   =>  'bibliography',
+    '?q=lion&report=frequency&field=collocates' =>  'collocation',
+    '?q=lion'                                   =>  'concordance',
+    '?q=lion&report=frequency'                  =>  'frequency',
+    '1'                                         =>  'navigation',
+    '1/1'                                       =>  'object'
+  }.each_pair do |request, file|
+    fn  = "#{test_data_dir}/#{file}#{test_data_ext}"
+    uri = URI.parse( "#{endpoint}/#{request}" )
+    puts "updating #{fn} from #{uri} ..."
+
+    http    = Net::HTTP.new(uri.host, uri.port)
+    request = http.get(uri.request_uri)
+    File.open(fn, 'w') { |fh| fh.puts request.body }
+  end
+end
+

data/lib/philologic-client/bibliography.rb

@@ -0,0 +1,60 @@
+
+module Philologic # :nodoc:
+  class Client    # :nodoc:
+
+    #
+    # Bibliography response returned by bibliography report.
+    #
+    # Extends Philologic::Client::Response
+    #
+    # = Usage
+    # 
+    #   # <div class='philologic_response'>
+    #   #   <p class='description'>Bibliography Report: 42 results.</p>
+    #   #   <ol class='philologic_cite_list'>
+    #   #     <li class='philologic_occurrence'>
+    #   #       <a href="./1/0/0/0/0" class='philologic_cite'>
+    #   #         <span class='philologic_property' title='author'>William Shakespeare</span>,
+    #   #         <i>
+    #   #           <span class='philologic_cite' title='title'>
+    #   #             The First Part of King Henry the Fourth
+    #   #           </span>
+    #   #         </i>
+    #   #         :
+    #   #         <span class='philologic_property' title='who'></span>
+    #   #       </a>
+    #   #    </li>
+    #   #    ...
+    #   #   </ol>
+    #   # </div>
+    #   biblio = Philologic::Client::Bibliography.new(html)
+    #   biblio.titles.each do |title|
+    #     ... Philologic::Client::Occurrence object ...
+    #   end
+    #
+    class Bibliography < ::Philologic::Client::Response
+
+      #
+      # Get +Array+ of Philologic::Client::Occurrence objects
+      #
+      attr_reader :titles
+
+      #
+      # Initialize Philologic::Client::Bibliography object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      # +client+:: (optional) Philologic::Client object or +nil+
+      #
+      def initialize(document, client = nil)
+        super
+
+        @properties = {} # TODO Sigh...
+        @titles     = @doc.css('li.philologic_occurrence').collect { |o| Philologic::Client::Occurrence.new(o, client) }
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/collocation.rb

@@ -0,0 +1,61 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic collocation table.
+    #
+    # Extends Philologic::Client::Response
+    #
+    class Collocation < ::Philologic::Client::Response
+
+      #
+      # Get +Array+ of Philologic::Client::CollocationRow objects
+      #
+      attr_reader :results
+
+      #
+      # Initialize Philologic::Client::Collocation object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      # +client+:: (optional) Philologic::Client object or +nil+
+      #
+      def initialize(document, client = nil)
+        super
+
+        #@results = []
+        #table = @doc.css('table.philologic_table').first
+        #unless table.nil?
+        #  #@results = table.css('tr').select { |tr| tr.css('tr > td') }.collect { |tr| tr }
+        #  @results = table.css('tr').collect { |tr| tr }
+        #end
+        @results = @doc.css('tr').collect { |tr| tr } # XXX
+#  <tr>
+#     <td>
+#           <tr><td width="25%">bear (8)</td><td width="25%">bear (5)</td><td width="25%">prey
+#           (5)</td></tr>
+#
+#              </td>
+#                </tr> 
+#        header = @doc.css('table.philologic_table > tr.freq_header_row').first
+#        unless header.nil?
+#          @label_header = header.css('th.freq_label_header').first.text
+#          @value_header = header.css('th.freq_value_header').first.text
+#        end
+#
+#        @results = @doc.css('tr.freq_row').collect { |tr| Philologic::Client::CollocationRow.new(tr) }
+      end
+
+      # 
+      # Does this collocation table contain results?
+      #
+      def results?
+        @results.size > 0 ? true : false
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/concordance.rb

@@ -0,0 +1,39 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic concordance search results.
+    #
+    class Concordance < ::Philologic::Client::Response
+
+      #
+      # Get +Array+ of Philologic::Client::Occurrence objects
+      #
+      attr_reader :results
+
+      #
+      # Initialize Philologic::Client::Concordance object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      # +client+:: (optional) Philologic::Client object or +nil+
+      #
+      def initialize(document, client = nil)
+        super
+
+        @results = @doc.css('li.philologic_occurrence').collect { |o| Philologic::Client::Occurrence.new(o, client) }
+      end
+
+      #
+      # Were any results found?
+      #
+      def results?
+        @results.size > 0 ? true : false
+      end
+      
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/document.rb

@@ -0,0 +1,65 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic document.
+    #
+    class Document < ::Philologic::Client::Response
+
+      #
+      # Get document HTML or +nil+
+      #
+      attr_reader :html
+
+      #
+      # Get +Array+ of Philologic::Client::Link objects
+      #
+      attr_reader :links
+
+      #
+      # Get document text or +nil+
+      #
+      attr_reader :text
+
+      #
+      # Initialize Philologic::Client::Document object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      # +client+:: (optional) Philologic::Client object or +nil+
+      #
+      def initialize(document, client = nil)
+        super
+
+        @html = @text = nil
+        unless @doc.css('div.philologic_object').first.nil?
+          @text = @doc.css('div.philologic_object').children.text
+          @html = @doc.css('div.philologic_object').children.to_html
+        end
+
+        @links  = []
+        @doc.css('div.philologic_navigation > a').each do |a|
+          @links << ::Philologic::Client::Link.new( a.attributes['href'].value, a.text.strip )
+        end
+      end
+
+      # 
+      # Does this document contain navigation links?
+      #
+      def links?
+        @links.size > 0 ? true : false
+      end
+
+      # 
+      # Does this document contain text?
+      #
+      def text?
+        @text ? true : false
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/frequency.rb

@@ -0,0 +1,57 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic frequency table.
+    #
+    # Extends Philologic::Client::Response
+    #
+    class Frequency < ::Philologic::Client::Response
+
+      #
+      # Get label header or +nil+
+      #
+      attr_reader :label_header
+
+      #
+      # Get +Array+ of Philologic::Client::FrequencyRow objects
+      #
+      attr_reader :results
+
+      #
+      # Get value header or +nil+
+      #
+      attr_reader :value_header
+
+      #
+      # Initialize Philologic::Client::Frequency object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      # +client+:: (optional) Philologic::Client object or +nil+
+      #
+      def initialize(document, client = nil)
+        super
+
+        header = @doc.css('table.philologic_table > tr.freq_header_row').first
+        unless header.nil?
+          @label_header = header.css('th.freq_label_header').first.text
+          @value_header = header.css('th.freq_value_header').first.text
+        end
+
+        @results = @doc.css('tr.freq_row').collect { |tr| Philologic::Client::FrequencyRow.new(tr) }
+      end
+
+      # 
+      # Does this frequency table contain results?
+      #
+      def results?
+        @results.size > 0 ? true : false
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/frequency_row.rb

@@ -0,0 +1,67 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic frequency table row.
+    #
+    # = Usage
+    #
+    #  # <tr class='freq_row'>
+    #  #   <td class='freq_label'>
+    #  #     <a href='./?q=lion&title=A+Midsummer+Night%27s+Dream'>
+    #  #       A Midsummer Night's Dream
+    #  #     </a>
+    #  #   </td>
+    #  #   <td class='freq_value'>
+    #  #     30
+    #  #   </td>
+    #  # </tr>
+    #  
+    #  r = Philologic::Client::FrequencyRow.new(html)
+    #  r.label # "A Midsummer Night's Dream"
+    #  r.link  # './?q=lion&title=A+Midsummer+Night%27s+Dream'
+    #  r.value # "0"
+    #
+    class FrequencyRow
+
+      #
+      # Get label or +nil+
+      #
+      attr_reader :label
+
+      #
+      # Get link or +nil+
+      #
+      attr_reader :link
+
+      #
+      # Get value or +nil+
+      #
+      attr_reader :value
+
+      #
+      # Initialize Philologic::Client::FrequencyRow object.
+      #
+      # Params:
+      # +document+:: Nokogiri document
+      #
+      def initialize(document)
+        @label = @link = @value = nil
+
+        unless document.css('td.freq_label').first.nil?
+          @label = document.css('td.freq_label').first.text
+        end
+        unless document.css('a').first.nil?
+          @link = document.css('a').first.attributes['href'].value
+        end
+        unless document.css('td.freq_value').first.nil?
+          @value = document.css('td.freq_value').first.text
+        end
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+

data/lib/philologic-client/link.rb

@@ -0,0 +1,37 @@
+
+module Philologic # :nodoc: 
+  class Client    # :nodoc:
+
+    #
+    # Philologic link.
+    #
+    class Link
+
+      #
+      # Get link text or nil.
+      #
+      attr_reader :text
+
+      #
+      # Get link URL.
+      #
+      attr_reader :url
+
+      #
+      # Initialize Philologic::Client::Link object.
+      #
+      # Params:
+      # +url+:: URL
+      # +text+:: (optional) Text or +nil+
+      #
+      def initialize(url, text = nil)
+        raise('nil link') if url.nil?
+        @text = text
+        @url  = url
+      end
+
+    end
+
+  end # class Client
+end # module Philologic
+