ruby_powerpoint 1.1 → 1.2

checksums.yaml

@@ -1,7 +1,15 @@
 ---
-SHA1:
-  metadata.gz: bbe73641d400cad7d34d38df587d69d9e1b9b88a
-  data.tar.gz: aecce478e9035955dfa28b1eb29ae2820ee3ab2f
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    MDQwYjA2MjA0Yjg5N2EwZjA3YzY3ZTBkMjMwZjBjYjYyNGIyMzEzYw==
+  data.tar.gz: !binary |-
+    NjY3OTA1NDc2ZDc3NjY3ZDZkZjM3NzAzZmM2ZDk2NDU2MTQxMDM4Zg==
 SHA512:
-  metadata.gz: 25226cceb297a612a2de56afbf1052496053a83e4be02a8e2c94aefc2fa9afc474c39b2dbce7764ef4f9c497d3bf5dc86fa636ac71bccacdc2b2b09911a5abfd
-  data.tar.gz: 2fe1972c306d877792503a21c8385ed7f79da2bf50e669ba82ecd3c825d4dd38b3c04609d8ccf6cb4f28e23b492ac873720c5fbe62ac82afea999a4bd270c0ed
+  metadata.gz: !binary |-
+    NGU5OWY5MTgzODE2ZGRlMDQ3NzE3MzE5NjM3MDI5NmE5YTZkNWQxZjEwY2Y0
+    M2M5MTBmMGEzOTMwNzY2Y2UyMWYwMTBlMDc5NTQ4MzU4NjM2ZWNjMWVhODMz
+    MjY3YzdhMzgwMDBkYzE1YTIwM2I5NDM0MTNhMWQwOTczYTcwOTI=
+  data.tar.gz: !binary |-
+    NTAxNWNlZGU3ODAyNDE3ZmIwMWZjYzgzYmYyNDAxMjYwMTM5NzFlNzFkYjc1
+    ZmY0ZGZiNmU5NjE5MDFjYjJkNTM5MzQ5MmE5N2Q4OWI1NWY3NDcxZmQzMDI1
+    NWZlYjg3NmVlZjc3ZmQ5MWZkYzc1NmRiZmY3MTc3NzlhYTA4Y2E=

data/lib/ruby_powerpoint/presentation.rb

@@ -14,9 +14,9 @@ module RubyPowerpoint
 
     def slides
       slides = Array.new
-      @files.sort{|a,b| a.name <=> b.name}.each_with_index do |doc, i|
-        if doc.name.include? 'ppt/slides/slide'
-          slides.push RubyPowerpoint::Slide.new(self, doc.name, i)
+      @files.sort{|a,b| a.name <=> b.name}.each do |f|
+        if f.name.include? 'ppt/slides/slide'
+          slides.push RubyPowerpoint::Slide.new(self, f.name)
         end
       end
       slides

data/lib/ruby_powerpoint/slide.rb

@@ -5,47 +5,81 @@ module RubyPowerpoint
   class RubyPowerpoint::Slide
 
     attr_reader :presentation,
-                :path,
-                :index
+                :slide_number,
+                :slide_number,
+                :slide_file_name
 
-    def initialize presentation, path, index
+    def initialize presentation, slide_xml_path
       @presentation = presentation
-      @path = path
-      @index = index
+      @slide_xml_path = slide_xml_path
+      @slide_number = extract_slide_number_from_path slide_xml_path
+      @slide_file_name = extract_slide_file_name_from_path slide_xml_path
+      parse_slide
+      parse_relation
     end
 
-    def content
-      content = Array.new
-      doc = @presentation.files.file.open @path
-      xml = Nokogiri::XML::Document.parse doc
-      xml.xpath('//a:t').each do |node|
-        content.push node.text
+    def parse_slide 
+      slide_doc = @presentation.files.file.open @slide_xml_path
+      @slide_xml = Nokogiri::XML::Document.parse slide_doc
+    end
+
+    def parse_relation
+      @relation_xml_path = "ppt/slides/_rels/#{@slide_file_name}.rels"
+      if @presentation.files.file.exist? @relation_xml_path
+        relation_doc = @presentation.files.file.open @relation_xml_path
+        @relation_xml = Nokogiri::XML::Document.parse relation_doc
       end
-      content
+    end
+
+    def content
+      content_elements @slide_xml
     end
     
     def title
-      #extracts just the title from the slide. Useful information on how to find just the title shape using C# is found here: http://msdn.microsoft.com/en-us/library/office/cc850843.aspx but you'll obviously need to dig into the XML structure if you aren't using C#, so see http://msdn.microsoft.com/en-us/library/office/gg278332(v=office.15).aspx
-      # should return nil if there is no title
-      title_elements = Array.new
-      doc = @presentation.files.file.open @path
-      xml = Nokogiri::XML::Document.parse doc
-      title_elements(xml).join(" ") if title_elements(xml).length > 0
+      title_elements = title_elements(@slide_xml)
+      title_elements.join(" ") if title_elements.length > 0
+    end
+
+    def images
+      image_elements(@relation_xml)
+        .map.each do |node|
+          @presentation.files.file.open(
+            node['Target'].gsub('..', 'ppt'))
+        end
     end
     
-    protected
-    
+    private
+
+    def extract_slide_number_from_path path
+      path.gsub('ppt/slides/slide', '').gsub('.xml', '').to_i
+    end
+
+    def extract_slide_file_name_from_path path
+      path.gsub('ppt/slides/', '')
+    end
+
     def title_elements(xml)
       shape_elements(xml).select{|shape| element_is_title(shape)}
     end
-  
+    
+    def content_elements(xml)
+      xml.xpath('//a:t').collect{ |node| node.text }
+    end
+
+    def image_elements(xml)
+      xml.css('Relationship').select{ |node| element_is_image(node)}
+    end    
+
     def shape_elements(xml)
       xml.xpath('//p:sp')
-    end
+    end    
   
     def element_is_title(shape)
       shape.xpath('.//p:nvSpPr/p:nvPr/p:ph').select{|prop| prop['type'] == 'title' || prop['type'] == 'ctrTitle'}.length > 0
     end
-    
+
+    def element_is_image(node)
+      node['Type'].include? 'image' 
+    end
   end
 end

data/lib/ruby_powerpoint/version.rb

@@ -1,3 +1,3 @@
 module RubyPowerpoint
-  VERSION = "1.1"
+  VERSION = "1.2"
 end

data/spec/test_spec.rb

@@ -18,13 +18,15 @@ describe 'RubyPowerpoint parsing a sample PPTX file' do
   it 'open a PPTX file successfully.' do
     @deck.should_not be_nil
     @deck.slides.should_not eql []
-    @deck.slides.first.content.should eql ["Some header here", "Some content here."]
-    @deck.slides.last.content.should eql ["WTF?", "What the hell s gong on?", "1234", "asdf", "34", "6"]
+    @deck.slides.first.content.should eql ["Some test ", "Powerpoint"]
+    @deck.slides.first.content.should eql  ["Some test ", "Powerpoint"]
+    @deck.slides.first.images.first.should_not eql nil #"ppt/media/image1.jpeg"
+    @deck.slides.last.title.should eql "Some title here" 
+    @deck.slides.last.content.should eql ["Some title here", "Some txt here", "Some ", "more text here."]
   end
 end
 
 describe 'open rime.pptx file' do
-  # I couldn't get the sample.pptx file to open on either Powerpoint 2007 on Windows 7 or in Powerpoint 2008 on Mac OS X 10.9, so I created my own file to test
   before(:all) do
     @deck = RubyPowerpoint::Presentation.new 'spec/fixtures/rime.pptx'
   end

metadata

@@ -1,83 +1,83 @@
 --- !ruby/object:Gem::Specification
 name: ruby_powerpoint
 version: !ruby/object:Gem::Version
-  version: '1.1'
+  version: '1.2'
 platform: ruby
 authors:
 - pythonicrubyist
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-02 00:00:00.000000000 Z
+date: 2014-03-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.13.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.13.0
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 1.6.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 1.6.0
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 0.9.9
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 0.9.9
 description: A Ruby gem that can extract text from PowerPoint(pptx) files.
@@ -87,7 +87,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
+- .gitignore
 - Gemfile
 - LICENSE.txt
 - README.rdoc
@@ -97,7 +97,6 @@ files:
 - lib/ruby_powerpoint/slide.rb
 - lib/ruby_powerpoint/version.rb
 - ruby_powerpoint.gemspec
-- spec/fixtures/.~lock.sample.pptx#
 - spec/fixtures/invalid.xls
 - spec/fixtures/rime.pptx
 - spec/fixtures/sample.pptx
@@ -112,22 +111,21 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: 1.9.2
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0.rc.1
+rubygems_version: 2.2.0
 signing_key: 
 specification_version: 4
 summary: A Ruby gem for Parsng text from PowerPoint(pptx) files.
 test_files:
-- spec/fixtures/.~lock.sample.pptx#
 - spec/fixtures/invalid.xls
 - spec/fixtures/rime.pptx
 - spec/fixtures/sample.pptx

data/spec/fixtures/.~lock.sample.pptx#

@@ -1 +0,0 @@
-,ramtin,ramtin-VirtualBox,26.06.2013 14:02,file:///home/ramtin/.config/libreoffice/3;