scrappy 0.1.15 → 0.1.16

data/History.txt

@@ -1,3 +1,8 @@
+=== 0.1.16 2011-02-09
+
+* Added support to RDF abbreviated output by loading kb's prefixes
+* Fixed bug in wikitext <pre> formatting
+
 === 0.1.15 2011-02-04
 
 * Added literal output formats such as HTML or Wikitext

data/bin/scrappy

@@ -143,10 +143,17 @@ Copyright
         open(cache_file) { |f| Marshal.load(f) }
       else
         # Load YARF files and cache kb
-        data = Dir["#{data_folder}/*"].inject(RDF::Graph.new) { |graph, file| extension = file.split('.').last.to_sym; graph.merge(extension==:ignore ? RDF::Graph.new : RDF::Parser.parse(extension, open(file).read)) }
+        data = Dir["#{data_folder}/*"].inject(RDF::Graph.new) do |kb, file|
+          extension = file.split('.').last.to_sym
+          graph = RDF::Parser.parse(extension, open(file).read)
+          kb.ns.merge! graph.ns
+          kb.merge!(extension==:ignore ? RDF::Graph.new : graph)
+          kb
+        end
         open(cache_file, "w") { |f| Marshal.dump(data, f) }
         data
       end
+      RDF::QURI.ns.merge! Agent::Options.kb.ns
     end
   end
 

data/lib/scrappy.rb

@@ -21,7 +21,7 @@ require 'scrappy/agent/agent'
 Namespace :sc, 'http://lab.gsi.dit.upm.es/scraping.rdf#'
 
 module Scrappy
-  VERSION = '0.1.15'
+  VERSION = '0.1.16'
 end
 
 # Require selectors

data/lib/scrappy/agent/formats.rb

@@ -11,9 +11,13 @@ module Scrappy
         doc.search("h4").each {|n| n.replace(Nokogiri::XML::Text.new("==== #{n.text.strip} ====", n.document)) }
         doc.search("h5").each {|n| n.replace(Nokogiri::XML::Text.new("===== #{n.text.strip} =====", n.document)) }
         doc.search("b").each  {|n| n.replace(Nokogiri::XML::Text.new("'''#{n.text.strip}'''", n.document)) }
+        doc.search("li li li li li").each {|n| n.replace(Nokogiri::XML::Text.new("***** #{n.text.strip}", n.document)) }
+        doc.search("li li li li").each {|n| n.replace(Nokogiri::XML::Text.new("**** #{n.text.strip}", n.document)) }
+        doc.search("li li li").each {|n| n.replace(Nokogiri::XML::Text.new("*** #{n.text.strip}", n.document)) }
+        doc.search("li li").each {|n| n.replace(Nokogiri::XML::Text.new("** #{n.text.strip}", n.document)) }
         doc.search("li").each {|n| n.replace(Nokogiri::XML::Text.new("* #{n.text.strip}", n.document)) }
         doc.search("ul").each {|n| n.replace(Nokogiri::XML::Text.new(n.text.strip, n.document)) }
-        doc.search("pre, code").each {|n| n.replace(Nokogiri::XML::Text.new("<pre>\n#{n.text.strip}\n</pre>", n.document)) }
+        doc.search("pre, code").each {|n| n.replace(Nokogiri::XML::Text.new("<pre>#{n.text}</pre>", n.document)) }
         doc.search("p").each {|n| n.replace(Nokogiri::XML::Text.new("#{n.text.strip}\n", n.document)) }
         doc.text.strip
       when Node('sc:Html') then

data/scrappy.gemspec

@@ -2,11 +2,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{scrappy}
-  s.version = "0.1.15"
+  s.version = "0.1.16"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
   s.authors = ["Jose Ignacio"]
-  s.date = %q{2011-02-04}
+  s.date = %q{2011-02-09}
   s.default_executable = %q{scrappy}
   s.description = %q{RDF web scraper}
   s.email = %q{joseignacio.fernandez@gmail.com}

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 1
-  - 15
-  version: 0.1.15
+  - 16
+  version: 0.1.16
 platform: ruby
 authors: 
 - Jose Ignacio
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-02-04 00:00:00 +01:00
+date: 2011-02-09 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency