ruby_powerpoint 1.4.2 → 1.4.3

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    OTM1YmNmYzg5ZTE3YzAwY2NkNWI1NmU4ZmQwZTVmNjVlZDI5ODliNQ==
+    ZDQ5OTcyMTU2OTg4M2JjN2JkYzI4MjZjZGM0NGFhMzk0MTMzOGRkNA==
   data.tar.gz: !binary |-
-    N2Q1YTIyNDQ2NTViMDk3OGNiNWFjMGMwYjRkMzM2YWJjNDkxZjdlZQ==
+    M2I2ZDgxZGM3OWRhNDBkYmZjYTgyNWQwNTA0MTI5ZmUwMzQ5YTE3Nw==
 SHA512:
   metadata.gz: !binary |-
-    YTA2ZmE3YWMwZjY2MjU2MGJjMDgxYTE2MjAyZjc2ZTM3YzJjYTEzYTAzMzEw
-    Y2U3ZmI4NTBkNjE2NjVjNTUxMDhjYTM4NzFhODM0OTViNGIxNjI4OGIzNzgw
-    MDU2MzcyZmUxNGIxNDI5Y2IzNGU0ZTRiNGQ0NzMwYTBiMjZjM2M=
+    M2I4ZWZlOWFhMDRjN2E0ZDEzYjExMDY0ZTc4NjM1NzYyNGFiMWY3MmNlN2Ix
+    MDJlMDZjYmRhNDNiYWNkYTcxNmM4NDM3ZDU0OTExMzBjOWE1NDQ2YmRhNDU4
+    NGUxNWYxOWQ4MDQ5MDI1NWY1MjM4YTM3M2JkZTg0MWVkNzBiNTE=
   data.tar.gz: !binary |-
-    OWJiYzIzYjVmZDI1NDg4OTRkMDhiNTRkMzkyNjcwNTc3M2JlYWVmZDc1NGNk
-    ZjZkMjgyYmY4MWZkODQyYWQ1YTZmNGUwYjA2NmZmZDMzNDI4YjgwMTg5OGNl
-    Zjc1ZGQzYTBiYjkxYTM5ZDczYjdlMTMwZjRiNWFhMjUxMDRjNGI=
+    ZWI2ZjA1YTIyZTllODBjYmQ2MGRmZTMzMjJjMDgxOTJiODQ2MGNiOTgzMWQz
+    YzgwODk1NzgyMWI3NmYxN2RjYTZkOTdkMTIwYmRhOGNkODY1ODlmYWIxZTAw
+    Mjk4ZGNmYmM2NmJiZDJjNTQ0ZjI5YzE1ZmIzNzMxOTY2ZGIzN2Q=

data/lib/ruby_powerpoint.rb

@@ -1,6 +1,7 @@
 require "ruby_powerpoint/version"
 require 'ruby_powerpoint/presentation'
 require 'ruby_powerpoint/slide'
+require 'ruby_powerpoint/paragraph'
 
 module RubyPowerpoint
   # Your code goes here...

data/lib/ruby_powerpoint/paragraph.rb

@@ -0,0 +1,19 @@
+module RubyPowerpoint
+  class RubyPowerpoint::Paragraph
+    def initialize slide, paragraph_xml
+      @slide = slide
+      @presentation = slide.presentation
+      @paragraph_xml = paragraph_xml
+    end
+
+    def content
+      content_element @paragraph_xml
+    end
+
+    private
+
+    def content_element(xml)
+      xml.xpath('.//a:t').collect{ |node| node.text }
+    end
+  end
+end

data/lib/ruby_powerpoint/slide.rb

@@ -13,16 +13,24 @@ module RubyPowerpoint
       @presentation = presentation
       @slide_xml_path = slide_xml_path
       @slide_number = extract_slide_number_from_path slide_xml_path
+      @slide_notes_xml_path = "ppt/notesSlides/notesSlide#{@slide_number}.xml"
       @slide_file_name = extract_slide_file_name_from_path slide_xml_path
+
       parse_slide
+      parse_slide_notes
       parse_relation
     end
 
-    def parse_slide 
+    def parse_slide
       slide_doc = @presentation.files.file.open @slide_xml_path
       @slide_xml = Nokogiri::XML::Document.parse slide_doc
     end
 
+    def parse_slide_notes
+      slide_notes_doc = @presentation.files.file.open @slide_notes_xml_path rescue nil
+      @slide_notes_xml = Nokogiri::XML::Document.parse(slide_notes_doc) if slide_notes_doc
+    end
+
     def parse_relation
       @relation_xml_path = "ppt/slides/_rels/#{@slide_file_name}.rels"
       if @presentation.files.file.exist? @relation_xml_path
@@ -34,7 +42,11 @@ module RubyPowerpoint
     def content
       content_elements @slide_xml
     end
-    
+
+    def notes_content
+      content_elements @slide_notes_xml
+    end
+
     def title
       title_elements = title_elements(@slide_xml)
       title_elements.join(" ") if title_elements.length > 0
@@ -47,11 +59,15 @@ module RubyPowerpoint
             node['Target'].gsub('..', 'ppt'))
         end
     end
-   
+
     def slide_num
       @slide_xml_path.match(/slide([0-9]*)\.xml$/)[1].to_i
     end
- 
+
+    def paragraphs
+      paragraph_element @slide_xml
+    end
+
     private
 
     def extract_slide_number_from_path path
@@ -65,25 +81,29 @@ module RubyPowerpoint
     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    
+    end
 
     def shape_elements(xml)
       xml.xpath('//p:sp')
-    end    
-  
+    end
+
+    def paragraph_element(xml)
+      xml.xpath('//a:p').collect{ |node| RubyPowerpoint::Paragraph.new(self, node) }
+    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' 
+      node['Type'].include? 'image'
     end
   end
 end

data/lib/ruby_powerpoint/version.rb

@@ -1,3 +1,3 @@
 module RubyPowerpoint
-  VERSION = "1.4.2"
+  VERSION = "1.4.3"
 end

data/spec/test_spec.rb

@@ -24,11 +24,17 @@ describe 'RubyPowerpoint parsing a sample PPTX file' do
     File.open('temp_1.jpg', 'w'){|f| f.puts image_byte_stream_1}
 
     @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.title.should eql "Some title here"
     @deck.slides.last.content.should eql ["Some title here", "Some txt here", "Some ", "more text here."]
     image_byte_stream_2 = @deck.slides.last.images.first.read
     File.open('temp_2.jpg', 'w'){|f| f.puts image_byte_stream_2}
   end
+
+  it "it parses Slide Notes of a PPTX  slides" do
+    notes_content = @deck.slides[0].notes_content
+    notes_content.should eql ["Testing", " Multiline Notes.", "To be extracted here.", "Multiline notes extracted.", "1"]
+  end
+
 end
 
 describe 'open rime.pptx file' do
@@ -39,20 +45,20 @@ describe 'open rime.pptx file' do
   after(:all) do
     @deck.close
   end
-  
+
   it 'opened rime.pptx successfully' do
     @deck.should_not be_nil
     @deck.slides.should_not eql []
   end
-  
+
   it 'should have the right number of slides' do
     @deck.slides.length.should eql 12
   end
-  
+
   it 'the old content method should work the same way' do
     @deck.slides[0].content.should eql ["The Rime of the Ancient Mariner", "(text of 1834)", "http://rpo.library.utoronto.ca/poems/rime-ancient-mariner-text-1834"]
   end
-  
+
   context 'the titles should be right' do
     it 'should be able to get a main slide (usually centered)' do
       @deck.slides[0].title.should eql "The Rime of the Ancient Mariner"
@@ -68,9 +74,23 @@ describe 'open rime.pptx file' do
       @deck.slides[5].title.should be_nil
       @deck.slides[6].title.should be_nil
     end
-    
+
     it 'should only get one title even if there are two things that visually look like titles' do
       @deck.slides[7].title.should eql "What if we have two"
     end
+
+    context 'when slide contains paragraph' do
+      before(:all) do
+        @slide = @deck.slides[1]
+      end
+
+      it 'should return the list of paragraphs' do
+        @slide.paragraphs.count.should eql 2
+      end
+
+      it 'should return the content of the paragraph' do
+        @slide.paragraphs[0].content.should eq ['Argument']
+      end
+    end
   end
-end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby_powerpoint
 version: !ruby/object:Gem::Version
-  version: 1.4.2
+  version: 1.4.3
 platform: ruby
 authors:
 - pythonicrubyist
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-23 00:00:00.000000000 Z
+date: 2016-10-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -93,6 +93,7 @@ files:
 - README.rdoc
 - Rakefile
 - lib/ruby_powerpoint.rb
+- lib/ruby_powerpoint/paragraph.rb
 - lib/ruby_powerpoint/presentation.rb
 - lib/ruby_powerpoint/slide.rb
 - lib/ruby_powerpoint/version.rb
@@ -121,7 +122,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.4.3
 signing_key: 
 specification_version: 4
 summary: ruby_powerpoint is a Ruby gem that can extract title, content and images