lbp 0.0.2 → 0.1.0

data/lib/lbp/file_part.rb

@@ -0,0 +1,120 @@
+require 'nokogiri'
+#require 'rugged'
+#require 'lbp/functions'
+require 'lbp'
+
+module Lbp
+	class FilePart
+		attr_reader :partid, :element
+		def initialize(filepath, transcription_type, confighash, partid)
+			
+			@confighash = confighash
+			
+			@partid = partid
+			@filepath = filepath
+			@transcription_type = transcription_type
+			@element = self.element_name
+			
+	  end
+
+	  def element_name
+	  	transcr = File.new(@filepath, @transcription_type, @confighash)
+	  	xmlobject = transcr.nokogiri
+	  	element_name = xmlobject.xpath("name(//node()[@xml:id='#{@partid}'])", 'tei' => 'http://www.tei-c.org/ns/1.0')
+	  end
+
+	  # def number
+	  # 	transcr = File.new(@filepath, @transcription_type, @confighash)
+	  # 	totalparts = transcr.number_of_body_paragraphs
+	  # 	xmlobject = transcr.nokogiri
+	  # 	parts_following = xmlobject.xpath("//tei:body//tei:#{@element}[preceding::tei:#{@element}[@xml:id='#{@partid}']]", 'tei' => 'http://www.tei-c.org/ns/1.0').count
+	  # 	part_number = totalparts - parts_following
+
+	  	
+			# return part_number
+	  # end
+	  def next
+	  	xmlobject = File.new(@filepath, @transcription_type, @confighash).nokogiri
+	  	nextpartid = xmlobject.xpath("//tei:#{@element}[@xml:id='#{@partid}']/following::tei:#{@element}[1]/@xml:id", 'tei' => 'http://www.tei-c.org/ns/1.0')
+			if nextpartid.text == nil
+        return nil
+      else
+				return FilePart.new(@filepath, @transcription_type, @confighash, nextpartid.text)
+      end	
+	  end
+	  def previous
+	  	xmlobject = File.new(@filepath, @transcription_type, @confighash).nokogiri
+	  	previouspartid = xmlobject.xpath("//tei:#{@element}[@xml:id='#{@partid}']/preceding::tei:#{@element}[1]/@xml:id", 'tei' => 'http://www.tei-c.org/ns/1.0')
+	  	if previouspartid.empty?
+        return nil
+      else
+				return FilePart.new(@filepath, @transcription_type, @confighash, previouspartid.text)
+      end
+	  end
+		def number_of_zones
+			xmlobject = File.new(@filepath, @transcription_type, @confighash).nokogiri
+			partid_with_hash = "#" + @partid
+			result = xmlobject.xpath("/tei:TEI/tei:facsimile//tei:surface/tei:zone[@start='#{partid_with_hash}']", 'tei' => 'http://www.tei-c.org/ns/1.0')
+			return result.count
+		end
+
+	  def xml
+	  	result = File.new(@filepath, @transcription_type, @confighash).nokogiri
+	  	p = result.xpath("//tei:#{@element}[@xml:id='#{@partid}']", 'tei' => 'http://www.tei-c.org/ns/1.0')
+	  end
+
+	  def transform(xsltfile, xslt_param_array=[])
+	  	result = File.new(@filepath, @transcription_type, @confighash).transform(xsltfile, xslt_param_array)
+			p = result.xpath("//#{@element}[@id='#{@partid}']")
+			return p
+		end
+		# TODO
+		# not working because result of transformation is no longer valid xml document
+		# might be easier to pass the part if to the xslt_param_array and then return the result
+		#def transform_main_view(xslt_param_array=[])
+		#	result = File.new(@filepath, @transcription_type, @confighash).transform_main_view(xslt_param_array)
+		#	#p = result.xpath("//#{@element}[@id='#{@partid}']")
+		#	#hard coding for the moment so it will only really work for paragraphs
+		#	p = result.xpath("//div[@id='pwrap_#{@partid}']")
+		#	return p
+		#end
+		def transform_plain_text(xslt_param_array=[])
+			# not that it could be slightly confusing that paragraph plain text uses the transform clean,
+			# because we still the basic paragraph elements in order to select the desired paragraph
+			result = File.new(@filepath, @transcription_type, @confighash).transform_clean_nokogiri(xslt_param_array)
+			
+			p = result.xpath("//#{@element}[@id='#{@partid}']")
+			return p
+		end
+
+		def word_count
+    	plaintext = self.transform_plain_text
+    	size = plaintext.text.split.size
+    end
+    def word_array
+    	plaintext = self.transform_plain_text
+    	word_array = plaintext.text.split
+    	word_array.map!{ |word| word.downcase}
+    end
+    def word_frequency(sort='frequency', order='descending')
+    	word_array = self.word_array
+    	wf = Hash.new(0)
+			word_array.each { |word| wf[word] += 1 }
+			
+			if sort == "frequency" 
+				if order == "descending" # high to low
+					wf = wf.sort_by{|k,v| v}.reverse
+				elsif order == "ascending" # low to high
+					wf = wf.sort_by{|k,v| v}
+				end
+			elsif sort == "word"
+				if order == "descending" # z - a
+						wf = wf.sort_by{|k,v| k}.reverse
+				elsif order == "ascending" #a - z
+						wf = wf.sort_by{|k,v| k}
+				end
+			end
+			return wf.to_h
+		end
+	end
+end

data/lib/lbp/functions.rb

@@ -2,11 +2,20 @@
 require 'nokogiri'
 require 'open-uri'
 
-def xslt_transform(xmlfile, xsltfile, xslt_param_array)
-	xml  = Nokogiri::XML(open(xmlfile))
+def xslt_transform(xml_open_uri_file, xsltfile, xslt_param_array)
+	xml  = xml_open_uri_file
 	xslt = Nokogiri::XSLT(open(xsltfile))
 	result_doc = xslt.transform(xml, xslt_param_array)
 	return result_doc
 end
 
+def xslt_apply_to(xml_open_uri_file, xsltfile, xslt_param_array)
+	xml  = xml_open_uri_file
+	xslt = Nokogiri::XSLT(open(xsltfile))
+	result_doc = xslt.apply_to(xml, xslt_param_array)
+	return result_doc
+end
+
+
+
 				

data/lib/lbp/manifestation.rb

@@ -0,0 +1,36 @@
+require 'openssl'
+require 'rdf'
+require 'rdf/rdfxml'
+require 'rdf/ntriples'
+require 'rdf/vocab'
+require 'lbp'
+
+
+module Lbp
+	class Manifestation < Resource 
+		
+		#inherits initialization from Resource
+		
+		def transcriptionUrls
+			results = self.results.dup.filter(:p => RDF::URI("http://scta.info/property/hasTranscription"))
+			transcriptions = results.map {|m| m[:o].to_s}
+			return transcriptions
+		end
+		def canonicalTranscriptionUrl
+			# TODO this check against an empty array should
+			# occur everywhere the filter is used
+			# maybe we need a helper function that does this once
+			unless self.results.count == 0 
+				transcriptionUrl = self.results.dup.filter(:p => RDF::URI("http://scta.info/property/hasCanonicalTranscription")).first[:o].to_s
+				return transcriptionUrl
+			end
+		end
+		def canonicalTranscription
+			url = self.canonicalTranscriptionUrl
+			transcriptionObj = Transcription.new(url)
+			return transcriptionObj
+		end
+	end
+end
+
+		

data/lib/lbp/paragraph_image.rb

@@ -0,0 +1,39 @@
+require 'nokogiri'
+require 'lbp/functions'
+
+module Lbp
+	class ParagraphImage
+		attr_reader :pid 
+		
+		#def initialize(confighash, filehash, pid, position=1)
+		def initialize(paragraphurl, position=1)
+			@query = Query.new();
+			@results = @query.zone_info("<" + paragraphurl + ">")
+			@zone_index = position - 1
+		end
+		def ulx
+			return @results[@zone_index][:ulx].to_s.to_i
+		end
+		def uly
+			return @results[@zone_index][:uly].to_s.to_i
+		end
+		def lrx
+			return @results[@zone_index][:lrx].to_s.to_i
+		end
+		def lry
+			return @results[@zone_index][:lry].to_s.to_i
+		end
+		def width
+			return @results[@zone_index][:width].to_s.to_i
+		end
+		def height
+			return @results[@zone_index][:height].to_s.to_i
+		end
+		def url
+			return @results[@zone_index][:canvasurl].to_s.split("/").last + ".jpg"
+		end
+		def canvas
+			return @results[@zone_index][:canvasurl].to_s.split("/").last
+		end
+	end
+end

data/lib/lbp/query.rb

@@ -0,0 +1,181 @@
+require 'sparql'
+
+module Lbp
+	class Query
+		
+		def initialize
+		
+			@prefixes = "
+	      PREFIX owl: <http://www.w3.org/2002/07/owl#>
+	      PREFIX dbpedia: <http://dbpedia.org/ontology/>
+	      PREFIX dcterms: <http://purl.org/dc/terms/>
+	      PREFIX dc: <http://purl.org/dc/elements/1.1/>
+	      PREFIX sctap: <http://scta.info/property/>
+	      PREFIX sctar: <http://scta.info/resource/>
+	      PREFIX sctat: <http://scta.info/text/>
+	      PREFIX role: <http://www.loc.gov/loc.terms/relators/>
+	      PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+	      PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+	      PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+	      "
+    end
+		def query(query)
+			if ENV['SPARQL'] == "local"
+		  	sparqlendpoint = "http://localhost:3030/ds/query"
+		  elsif ENV['SPARQL'] == "staging"
+		  	sparqlendpoint = "http://sparql-staging.scta.info/ds/query"
+		  elsif ENV['RACK_ENV'] == "production" || ENV['SPARQL'] == "production"
+		    sparqlendpoint = "http://sparql.scta.info/ds/query"
+		  else
+		    sparqlendpoint = "http://sparql.scta.info/ds/query"
+		  end
+			
+			sparql = SPARQL::Client.new(sparqlendpoint)
+		  result = sparql.query(query)
+
+		  return result
+		end
+		def subject(url)
+			query = "#{@prefixes}
+
+          SELECT ?p ?o ?ptype
+          {
+          #{url} ?p ?o .
+          OPTIONAL {
+              ?p rdfs:subPropertyOf ?ptype .
+              }
+
+          }
+          ORDER BY ?p
+          "
+      result = self.query(query)
+		end 
+		def subject_with_short_id(shortid)
+			query = "#{@prefixes}
+
+          SELECT ?p ?o ?ptype
+          {
+          ?resource <http://scta.info/property/shortId> '#{shortid}' .
+          ?resource ?p ?o .
+          OPTIONAL {
+              ?p rdfs:subPropertyOf ?ptype .
+              }
+
+          }
+          ORDER BY ?p
+          "
+      result = self.query(query)
+		end 
+
+		def zone_info(paragraphurl)
+			query = "#{@prefixes}
+				SELECT DISTINCT ?zone ?ulx ?uly ?lry ?lrx ?position ?height ?width ?canvasurl
+	      {
+	        #{paragraphurl} <http://scta.info/property/hasZone> ?zone .
+	         ?zone <http://scta.info/property/ulx> ?ulx .
+	         ?zone <http://scta.info/property/uly> ?uly .
+	         ?zone <http://scta.info/property/lry> ?lry .
+	         ?zone <http://scta.info/property/lrx> ?lrx .
+	         ?zone <http://scta.info/property/position> ?position .
+	         ?zone <http://scta.info/property/height> ?height .
+	         ?zone <http://scta.info/property/width> ?width .
+	         ?zone <http://scta.info/property/isZoneOn> ?canvasurl .
+	      }
+	      ORDER BY ?position"
+			result = self.query(query)
+		end
+
+
+		def collection_query(collection_url)
+			query = "#{@prefixes}
+			
+				SELECT ?collectiontitle ?title ?item ?questiontitle ?order ?status ?gitRepository
+	      {
+	        #{collection_url} <http://scta.info/property/hasStructureItem> ?item .
+	        #{collection_url} <http://purl.org/dc/elements/1.1/title> ?collectiontitle .
+	        ?item <http://purl.org/dc/elements/1.1/title> ?title  .
+	        ?item <http://scta.info/property/totalOrderNumber> ?order .
+	        ?item <http://scta.info/property/status> ?status .
+	        ?item <http://scta.info/property/gitRepository> ?gitRepository .
+
+	        
+	        OPTIONAL
+	      	{
+	      	?item <http://scta.info/property/questionTitle> ?questiontitle  .
+	      	}
+	      }
+	      ORDER BY ?order"
+		  
+		  result = self.query(query)
+		end
+
+		def item_query(expression_url)
+			query = "#{@prefixes}
+
+	      SELECT ?item_title ?transcript ?transcript_title ?transcript_status ?transcript_type ?manifestation
+	      {
+	      	#{expression_url} <http://purl.org/dc/elements/1.1/title> ?item_title .
+	      	?manifestation <http://scta.info/property/isManifestationOf> #{expression_url} . 
+
+	      	?transcript <http://scta.info/property/isTranscriptionOf> ?manifestation .
+					?transcript <http://purl.org/dc/elements/1.1/title> ?transcript_title  .
+	        ?transcript <http://scta.info/property/status> ?transcript_status .
+	        ?transcript <http://scta.info/property/transcriptionType> ?transcript_type .
+	      }"
+			
+			result = self.query(query)	        
+			
+		end
+		def expressionElementQuery(expression_url, type)
+		# currently assumes expression_url is for a structureType="structureCollection"
+		expression_url = "<#{expression_url}>"
+		elementTypeUrl = "<#{type}>"
+			query = "#{@prefixes}
+			
+				SELECT ?expression ?structureBlock ?resource ?resourceTitle 
+	      {
+
+	        #{expression_url} <http://scta.info/property/hasStructureItem> ?structureItem .
+	        ?structureItem <http://scta.info/property/hasStructureBlock> ?structureBlock .
+	        ?structureBlock <http://scta.info/property/hasStructureElement> ?element .
+	        ?element <http://scta.info/property/structureElementType> #{elementTypeUrl} .
+	        ?element <http://scta.info/property/isPartOfStructureBlock> ?structureBlock .
+	        ?element <http://scta.info/property/isInstanceOf> ?resource .
+	        ?resource <http://purl.org/dc/elements/1.1/title> ?resourceTitle  .
+	      }
+	       	ORDER BY ?resourceTitle
+	       
+	       "
+	    result = self.query(query)
+		end
+		def names(item_url)
+		item_url = "<#{item_url}>"
+			query = "#{@prefixes}
+			
+				SELECT ?item ?name ?nameTitle ?mentioningItem
+	      {
+	        #{item_url} <http://scta.info/property/mentions> ?name .
+	        ?name <http://purl.org/dc/elements/1.1/title> ?nameTitle  .
+	      }
+	       	ORDER BY ?nameTitle
+	       
+	       "
+	    result = self.query(query)
+		end
+
+		def quotes(item_url)
+			item_url = "<#{item_url}>"
+				query = "#{@prefixes}
+				
+					SELECT ?item ?quote ?quoteText ?quoteCitation
+		      {
+		        #{item_url} <http://scta.info/property/quotes> ?quote .
+		        ?quote <http://scta.info/property/quotation> ?quoteText .
+		        ?quote <http://scta.info/property/citation> ?quoteCitation .
+		       }
+		       ORDER BY ?quoteText
+		       "
+		    result = self.query(query)
+		end
+	end
+end

data/lib/lbp/resource.rb

@@ -0,0 +1,72 @@
+require 'openssl'
+require 'rdf'
+require 'rdf/rdfxml'
+require 'rdf/ntriples'
+require 'rdf/vocab'
+require 'lbp'
+
+
+module Lbp
+	class Resource 
+		attr_reader :resource_shortId, :resource_url, :results
+		def initialize(resource_id)
+			# fist conditions check to see if search results 
+			# are being passed
+			if resource_id.class != String
+				@results = resource_id
+				# resource should should be returned instead of "unsure"
+				@resource_shortId = @results.first[:s].to_s.split("resource/").last
+				@resource_url = @results.first[:s].to_s
+				# if resource id is a string rather than results 
+			# it looks ot see if this is a URL to query for results	
+			elsif resource_id.include? "http"
+				@query = Query.new();
+				@results = @query.subject("<" + resource_id + ">")
+				@resource_url = resource_id
+				@resource_shortId = resource_id.split("resource/").last
+			# finally, it looks for results using the shortId
+			else
+				@query = Query.new();
+				@results = @query.subject_with_short_id(resource_id)
+				@resource_url = "http://scta.info/resource/" + resource_id
+				@resource_shortId = resource_id
+			end
+		end
+		def convert
+			#this conditional should be replaced 
+			# by a function that converts the string
+			# into a class name
+			if self.type_shortId == 'workGroup'
+				return WorkGroup.new(@results)
+			elsif self.type_shortId == 'work'
+				return Work.new(@results)
+			elsif self.type_shortId == 'expression'
+				return Expression.new(@results)
+			elsif self.type_shortId == "manifestation"
+				return Manifestation.new(@results)
+			elsif self.type_shortId == "transcription"
+				return Transcription.new(@results)
+			else
+				puts "no subclass to conver to"
+				return self
+			end
+		end
+		def type_shortId
+			type = @results.dup.filter(:p => RDF::URI("http://www.w3.org/1999/02/22-rdf-syntax-ns#type")).first[:o].to_s.split("/").last
+		end
+		def type
+			type = @results.dup.filter(:p => RDF::URI("http://www.w3.org/1999/02/22-rdf-syntax-ns#type")).first[:o].to_s
+		end
+		def title
+			type = @results.dup.filter(:p => RDF::URI(RDF::Vocab::DC11.title)).first[:o].to_s
+		end
+		## structure type should be moved to expression and other classes because it's not generic enough
+		## some resources like quotes or name will not have structure type
+		def structureType_shortId
+			type = @results.dup.filter(:p => RDF::URI("http://scta.info/property/structureType")).first[:o].to_s.split("/").last
+		end
+		def structureType
+			type = @results.dup.filter(:p => RDF::URI("http://scta.info/property/structureType")).first[:o].to_s
+		end
+	end
+end