Merge branch 'master' of https://github.com/chrahunt/docx

Author: chrahunt

README.md

@@ -1,16 +1,16 @@
 # docx
 
-a ruby library/gem for interacting with `.docx` files. currently capabilities include reading paragraphs/bookmarks, inserting text at bookmarks, reading tables/rows/columns/cells and saving the document.
+A ruby library/gem for interacting with `.docx` files. currently capabilities include reading paragraphs/bookmarks, inserting text at bookmarks, reading tables/rows/columns/cells and saving the document.
 
-## usage
+## Usage
 
-### install
+### Install
 
-requires ruby (only tested with 1.9.3 so far)
+Requires ruby (tested with 2.1.1)
 
-    gem install docx
+    gem 'docx', '~> 0.2.07', :require => ["docx"]
 
-### reading
+### Reading
 
 ``` ruby
 require 'docx'
@@ -29,7 +29,18 @@ doc.bookmarks.each_pair do |bookmark_name, bookmark_object|
 end
 ```
 
-### reading tables
+### Rendering html
+``` ruby
+require 'docx'
+
+# Retrieve and display paragraphs as html
+doc = Docx::Document.open('example.docx')
+doc.paragraphs.each do |p|
+  puts p.to_html
+end
+```
+
+### Reading tables
 
 ``` ruby
 require 'docx'
@@ -59,7 +70,7 @@ doc.tables.each do |table|
 end
 ```
 
-### writing
+### Writing
 
 ``` ruby
 require 'docx'
@@ -77,7 +88,7 @@ doc.bookmarks['example_bookmark_2'].insert_multiple_lines_after(['Hello', 'World
 doc.save('example-edited.docx')
 ```
 
-### advanced
+### Advanced
 
 ``` ruby
 require 'docx'
@@ -99,7 +110,6 @@ p_child = p_element.at_xpath("//child::*") # selects first child
 
 ### todo
 
-* Add better formatting identification for specific nodes and other formatting indicators (text size, paragraph spacing)
 * Calculate element formatting based on values present in element properties as well as properties inherited from parents
 * Default formatting of inserted elements to inherited values
 * Implement formattable elements.

docx.gemspec

@@ -6,13 +6,13 @@ Gem::Specification.new do |s|
   s.version     = Docx::VERSION
   s.summary     = 'a ruby library/gem for interacting with .docx files'
   s.description = s.summary
-  s.authors     = ['Christopher Hunt', 'Marcus Ortiz']
+  s.authors     = ['Christopher Hunt', 'Marcus Ortiz', 'Higgins Dragon', 'Toms Mikoss', 'Sebastian Wittenkamp']
   s.email       = ['chrahunt@gmail.com']
   s.homepage    = 'https://github.com/chrahunt/docx'
   s.files       = Dir["README.md", "LICENSE.md", "lib/**/*.rb"]
 
   s.add_dependency 'nokogiri', '~> 1.5'
-  s.add_dependency 'rubyzip',  '~> 1.0'
+  s.add_dependency 'rubyzip',  '~> 1.1.6'
 
   s.add_development_dependency 'rspec'
 end

lib/docx/containers/paragraph.rb

@@ -15,9 +15,11 @@ def self.tag
 
         # Child elements: pPr, r, fldSimple, hlink, subDoc
         # http://msdn.microsoft.com/en-us/library/office/ee364458(v=office.11).aspx
-        def initialize(node)
+        def initialize(node, document_properties = {})
           @node = node
           @properties_tag = 'pPr'
+          @document_properties = document_properties
+          @font_size = @document_properties[:font_size]
         end
 
         # Set text of paragraph
@@ -39,17 +41,55 @@ def to_s
           text_runs.map(&:text).join('')
         end
 
+        # Return paragraph as a <p></p> HTML fragment with formatting based on properties.
+        def to_html
+          html = ''
+          text_runs.each do |text_run|
+            html << text_run.to_html
+          end
+          styles = { 'font-size' => "#{font_size}pt" }
+          styles['text-align'] = alignment if alignment
+          html_tag(:p, content: html, styles: styles)
+        end
+
+
         # Array of text runs contained within paragraph
         def text_runs
-          @node.xpath('w:r|w:hyperlink/w:r').map {|r_node| Containers::TextRun.new(r_node) }
+          @node.xpath('w:r|w:hyperlink/w:r').map { |r_node| Containers::TextRun.new(r_node, @document_properties) }
         end
 
         # Iterate over each text run within a paragraph
         def each_text_run
           text_runs.each { |tr| yield(tr) }
         end
+
+        def aligned_left?
+          ['left', nil].include?(alignment)
+        end
+
+        def aligned_right?
+          alignment == 'right'
+        end
+
+        def aligned_center?
+          alignment == 'center'
+        end
+
+        def font_size
+          size_tag = @node.xpath('w:pPr//w:sz').first
+          size_tag ? size_tag.attributes['val'].value.to_i / 2 : @font_size
+        end
 
         alias_method :text, :to_s
+
+        private
+
+        # Returns the alignment if any, or nil if left
+        def alignment
+          alignment_tag = @node.xpath('.//w:jc').first
+          alignment_tag ? alignment_tag.attributes['val'].value : nil
+        end
+
       end
     end
   end

lib/docx/containers/text_run.rb

@@ -20,12 +20,14 @@ def self.tag
         attr_reader :text
         attr_reader :formatting
 
-        def initialize(node)
+        def initialize(node, document_properties = {})
           @node = node
           @text_nodes = @node.xpath('w:t').map {|t_node| Elements::Text.new(t_node) }
           @properties_tag = 'rPr'
           @text       = parse_text || ''
           @formatting = parse_formatting || DEFAULT_FORMATTING
+          @document_properties = document_properties
+          @font_size = @document_properties[:font_size]
         end
 
         # Set text of text run
@@ -54,7 +56,20 @@ def parse_formatting
         def to_s
           @text
         end
-        
+
+        # Return text as a HTML fragment with formatting based on properties.
+        def to_html
+          html = @text
+          html = html_tag(:em, content: html) if italicized?
+          html = html_tag(:strong, content: html) if bolded?
+          styles = {}
+          styles['text-decoration'] = 'underline' if underlined?
+          # No need to be granular with font size down to the span level if it doesn't vary.
+          styles['font-size'] = "#{font_size}pt" if font_size != @font_size 
+          html = html_tag(:span, content: html, styles: styles) unless styles.empty?
+          return html
+        end
+
         def italicized?
           @formatting[:italic]
         end
@@ -66,6 +81,11 @@ def bolded?
         def underlined?
           @formatting[:underline]
         end
+
+        def font_size
+          size_tag = @node.xpath('w:rPr//w:sz').first
+          size_tag ? size_tag.attributes['val'].value.to_i / 2 : @font_size
+        end
       end
     end
   end