ooxml_parser 0.1.1

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/docx_paragraph.rb

@@ -0,0 +1,324 @@
+# noinspection RubyTooManyInstanceVariablesInspection
+require_relative 'docx_paragraph/docx_paragraph_run'
+require_relative 'docx_paragraph/indents'
+require_relative 'docx_paragraph/frame_properties'
+require_relative 'docx_paragraph/docx_formula'
+require_relative 'docx_paragraph/paragraph_style'
+module OoxmlParser
+  class DocxParagraph < OOXMLDocumentObject
+    attr_accessor :number, :bookmark_start, :bookmark_end, :align, :spacing, :background_color, :ind, :numbering,
+                  :character_style_array, :horizontal_line, :page_break, :kinoku, :borders, :keep_lines,
+                  :contextual_spacing, :sector_properties, :page_numbering, :section_break, :style, :keep_next,
+                  :orphan_control, :tabs, :frame_properties
+
+    def initialize
+      @number = 0
+      @bookmark_start = []
+      @bookmark_end = []
+      @align = 'left'
+      @spacing = Spacing.new
+      @background_color = nil
+      @ind = Indents.new
+      @kinoku = false
+      @numbering = nil
+      @character_style_array = []
+      @horizontal_line = false
+      @page_break = false
+      @borders = Borders.new
+      @keep_lines = false
+      @contextual_spacing = false
+      @sector_properties = nil
+      @page_numbering = false
+      @section_break = nil
+      @style = nil
+      @keep_next = false
+      @orphan_control = true
+      @tabs = []
+      @frame_properties = nil
+    end
+
+    def copy
+      paragraph = DocxParagraph.new
+      paragraph.number = number
+      paragraph.bookmark_start = @bookmark_start.dup
+      paragraph.bookmark_end = @bookmark_end.dup
+      paragraph.align = @align
+      paragraph.spacing = @spacing.copy
+      paragraph.background_color = @background_color
+      paragraph.ind = @ind.copy
+      paragraph.numbering = @numbering
+      paragraph.character_style_array = @character_style_array
+      paragraph.horizontal_line = @horizontal_line
+      paragraph.page_break = @page_break
+      paragraph.kinoku = @kinoku
+      paragraph.borders = @borders
+      paragraph.keep_lines = @keep_lines
+      paragraph.contextual_spacing = @contextual_spacing
+      paragraph.sector_properties = @sector_properties
+      paragraph.page_numbering = @page_numbering
+      paragraph.section_break = @section_break
+      paragraph.style = @style
+      paragraph.keep_next = @keep_next
+      paragraph.orphan_control = @orphan_control
+      paragraph.tabs = @tabs.dup
+      paragraph.frame_properties = @frame_properties
+      paragraph
+    end
+
+    def nonempty_runs
+      @character_style_array.select do |cur_run|
+        if cur_run.is_a?(DocxParagraphRun)
+          (!cur_run.text.empty? || !cur_run.alternate_content.nil? || !cur_run.drawing.nil?)
+        elsif cur_run.is_a?(DocxFormula)
+          true
+        end
+      end
+    end
+
+    def remove_empty_runs
+      nonempty = nonempty_runs
+      @character_style_array.each do |cur_run|
+        @character_style_array.delete(cur_run) unless nonempty.include?(cur_run)
+      end
+    end
+
+    def ==(other)
+      character_style_array.each do |current_run|
+        character_style_array.delete(current_run) if current_run.text.empty?
+      end
+      other.character_style_array.each do |current_run|
+        other.character_style_array.delete(current_run) if current_run.text.empty?
+      end
+      ignored_attributes = [:@number]
+      all_instance_variables = instance_variables
+      significan_attribues = all_instance_variables - ignored_attributes
+      significan_attribues.each do |current_attributes|
+        unless instance_variable_get(current_attributes) == other.instance_variable_get(current_attributes)
+          return false
+        end
+      end
+      true
+    end
+
+    def self.parse(p_tag, par_number = 0, default_paragraph = DocxParagraph.new, default_character = DocxParagraphRun.new)
+      paragraph_style = default_paragraph.copy
+      default_character_style = default_character.copy
+      character_styles_array = []
+      custom_character_style = DocxParagraphRun.new
+      char_number = 0
+      comments = []
+      p_tag.xpath('w:bookmarkStart').each do |bookmark_start|
+        paragraph_style.bookmark_start << Bookmark.new(bookmark_start.attribute('id').value, bookmark_start.attribute('name').value)
+      end
+      p_tag.xpath('w:bookmarkEnd').each do |bookmark_end|
+        paragraph_style.bookmark_end << Bookmark.new(bookmark_end.attribute('id').value)
+      end
+      p_tag.xpath('*').each do |p_element|
+        if p_element.name == 'pPr'
+          p_props = p_tag.xpath('w:pPr')
+          DocxParagraph.parse_paragraph_style(p_props, paragraph_style, custom_character_style)
+          p_tag.xpath('w:pict').each do |pict|
+            pict.xpath('v:rect').each do
+              paragraph_style.horizontal_line = true
+            end
+          end
+        elsif p_element.name == 'commentRangeStart'
+          comments << p_element.attribute('id').value
+        elsif p_element.name == 'fldSimple'
+          instruction = p_element.attribute('instr').to_s
+          paragraph_style.page_numbering = true if instruction.include?('PAGE')
+          p_element.xpath('w:r').each do |r_tag|
+            character_style = DocxParagraphRun.parse_character(r_tag, default_character_style.copy, char_number)
+            character_style.page_number = paragraph_style.page_numbering
+            character_style.instruction = instruction
+            character_styles_array << character_style.copy
+            char_number += 1
+          end
+        elsif p_element.name == 'r'
+          character_style = custom_character_style.copy
+          p_element.xpath('w:instrText').each do |insrt_text|
+            if insrt_text.text.include?('PAGE')
+              paragraph_style.page_numbering = true
+            end
+          end
+          character_style = DocxParagraphRun.parse_character(p_element, character_style, char_number)
+          character_style.comments = comments.dup
+          character_styles_array << character_style.copy
+          unless character_style.shape.nil?
+            character_styles_array.last.shape = character_style.shape
+          end
+          char_number += 1
+        elsif p_element.name == 'hyperlink'
+          character_style = default_character_style.copy
+          if !p_element.attribute('id').nil?
+            character_style.link = Hyperlink.parse(p_element)
+          else
+            unless p_element.attribute('anchor').nil?
+              character_style.link = p_element.attribute('anchor').value
+            end
+          end
+          p_element.xpath('w:r').each do |r_tag|
+            character_style = DocxParagraphRun.parse_character(r_tag, character_style, char_number)
+            character_styles_array << character_style.copy
+            char_number += 1
+          end
+          p_element.xpath('w:fldSimple').each do |simple_field|
+            instruction = simple_field.attribute('instr').to_s
+            paragraph_style.page_numbering = true if instruction.include?('PAGE')
+            simple_field.xpath('w:r').each do |r_tag|
+              character_style = DocxParagraphRun.parse_character(r_tag, character_style.copy, char_number)
+              character_style.page_number = paragraph_style.page_numbering
+              character_style.instruction = instruction
+              character_styles_array << character_style.copy
+              char_number += 1
+            end
+          end
+        elsif p_element.name == 'oMathPara'
+          p_element.xpath('m:oMath').each do |o_math|
+            character_styles_array << DocxFormula.parse(o_math)
+          end
+        elsif p_element.name == 'commentRangeEnd'
+          comments.each_with_index do |comment, index|
+            if comment == p_element.attribute('id').value
+              comments.delete_at(index)
+              break
+            end
+          end
+        end
+      end
+      paragraph_style.number = par_number
+      if character_styles_array.last.class == DocxParagraphRun
+        character_styles_array.last.text = character_styles_array.last.text.rstrip
+      end
+      paragraph_style.character_style_array = character_styles_array
+      paragraph_style
+    end
+
+    def self.parse_paragraph_style(paragraph_pr_tag, paragraph_style = DocxParagraph.new, default_char_style = DocxParagraphRun.new)
+      paragraph_pr_tag.xpath('w:tabs').each do |tabs_node|
+        tabs_node.xpath('w:tab').each { |tab_node| paragraph_style.tabs << ParagraphTab.new(tab_node.attribute('val').value.to_sym, (tab_node.attribute('pos').value.to_f / 566.9).round(2)) }
+      end
+      paragraph_pr_tag.xpath('w:pageBreakBefore').each do |page_break_before|
+        if page_break_before.attribute('val').nil? || page_break_before.attribute('val').value != 'false'
+          paragraph_style.page_break = true
+        end
+      end
+      paragraph_pr_tag.xpath('w:pBdr').each do |paragraph_br|
+        paragraph_style.borders = Borders.new
+        paragraph_br.xpath('w:bottom').each do |bottom|
+          paragraph_style.borders.bottom = BordersProperties.parse(bottom)
+        end
+        paragraph_br.xpath('w:left').each do |left|
+          paragraph_style.borders.left = BordersProperties.parse(left)
+        end
+        paragraph_br.xpath('w:top').each do |top|
+          paragraph_style.borders.top = BordersProperties.parse(top)
+        end
+        paragraph_br.xpath('w:right').each do |right|
+          paragraph_style.borders.right = BordersProperties.parse(right)
+        end
+        paragraph_br.xpath('w:between').each do |between|
+          paragraph_style.borders.between = BordersProperties.parse(between)
+        end
+        paragraph_br.xpath('w:bar').each do |bar|
+          paragraph_style.borders.bar = BordersProperties.parse(bar)
+        end
+      end
+      paragraph_pr_tag.xpath('w:keepLines').each do |keep_lines|
+        if keep_lines.attribute('val').nil?
+          paragraph_style.keep_lines = true
+        else
+          unless keep_lines.attribute('val').value == 'false'
+            paragraph_style.keep_lines = true
+          end
+        end
+      end
+      paragraph_pr_tag.xpath('w:widowControl').each do |widow_control_node|
+        paragraph_style.orphan_control = OOXMLDocumentObject.option_enabled?(widow_control_node)
+      end
+      paragraph_pr_tag.xpath('w:keepNext').each do |_|
+        paragraph_style.keep_next = true
+      end
+      paragraph_style.contextual_spacing = true unless paragraph_pr_tag.xpath('w:contextualSpacing').empty?
+      paragraph_pr_tag.xpath('w:shd').each do |shd|
+        background_color_string = shd.attribute('fill').value
+        paragraph_style.background_color = Color.from_int16(background_color_string)
+        unless shd.attribute('val').nil?
+          paragraph_style.background_color.set_style(shd.attribute('val').value)
+        end
+      end
+      paragraph_pr_tag.xpath('w:pStyle').each do |p_style|
+        parse_paragraph_style_xml(p_style.attribute('val').value, paragraph_style, default_char_style)
+      end
+      paragraph_pr_tag.xpath('w:ind').each do |ind|
+        paragraph_style.ind = Indents.parse(ind)
+      end
+      paragraph_pr_tag.xpath('w:kinoku').each do
+        paragraph_style.kinoku = true
+      end
+      paragraph_pr_tag.xpath('w:framePr').each do |frame_pr_node|
+        paragraph_style.frame_properties = FrameProperties.parse(frame_pr_node)
+      end
+      paragraph_pr_tag.xpath('w:numPr').each do |num_pr|
+        numbering = Numbering.new
+        num_pr.xpath('w:ilvl').each do |ilvl|
+          numbering.ilvl = ilvl.attribute('val').value
+        end
+        num_pr.xpath('w:numId').each do |num_id|
+          numbering.numbering_properties = NumberingProperties.parse(num_id.attribute('val').value) if File.exist?(OOXMLDocumentObject.path_to_folder + 'word/numbering.xml')
+        end
+        paragraph_style.numbering = numbering
+      end
+      paragraph_pr_tag.xpath('w:jc').each do |jc|
+        paragraph_style.align = jc.attribute('val').value.to_sym unless jc.attribute('val').nil?
+        paragraph_style.align = :justify if jc.attribute('val').value == 'both'
+      end
+      paragraph_pr_tag.xpath('w:framePr').each do |frame_pr_node|
+        paragraph_style.frame_properties = FrameProperties.parse(frame_pr_node)
+      end
+      paragraph_pr_tag.xpath('w:spacing').each do |spacing|
+        unless spacing.attribute('before').nil?
+          paragraph_style.spacing.before = (spacing.attribute('before').value.to_f / 566.9).round(2)
+        end
+        unless spacing.attribute('after').nil?
+          paragraph_style.spacing.after = (spacing.attribute('after').value.to_f / 566.9).round(2)
+        end
+        unless spacing.attribute('lineRule').nil?
+          paragraph_style.spacing.line_rule = spacing.attribute('lineRule').value.sub('atLeast', 'at_least').to_sym
+        end
+        unless spacing.attribute('line').nil?
+          paragraph_style.spacing.line = (paragraph_style.spacing.line_rule == :auto ? (spacing.attribute('line').value.to_f / 240.0).round(2) : (spacing.attribute('line').value.to_f / 566.9).round(2))
+        end
+      end
+      paragraph_pr_tag.xpath('w:sectPr').each do |sect_pr|
+        paragraph_style.sector_properties = PageProperties.parse(sect_pr, paragraph_style, default_char_style)
+        paragraph_style.section_break = case paragraph_style.sector_properties.type
+                                        when 'oddPage'
+                                          'Odd page'
+                                        when 'evenPage'
+                                          'Even page'
+                                        when 'continuous'
+                                          'Current Page'
+                                        else
+                                          'Next Page'
+                                        end
+      end
+      paragraph_style
+    end
+
+    def self.parse_paragraph_style_xml(id, paragraph_style, character_style)
+      doc = Nokogiri::XML(File.open(OOXMLDocumentObject.path_to_folder + 'word/styles.xml'))
+      doc.search('//w:style').each do |style|
+        next unless style.attribute('styleId').value == id
+        style.xpath('w:pPr').each do |p_pr|
+          parse_paragraph_style(p_pr, paragraph_style, character_style)
+          paragraph_style.style = StyleParametres.parse(style)
+        end
+        style.xpath('w:rPr').each do |r_pr|
+          DocxParagraphRun.parse(r_pr, character_style, @default_character)
+        end
+        break
+      end
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/header_footer.rb

@@ -0,0 +1,37 @@
+module OoxmlParser
+  class HeaderFooter < OOXMLDocumentObject
+    attr_accessor :id, :description, :type
+
+    def initialize(type = :header)
+      @type = type
+    end
+
+    def parse(type, id, default_paragraph, default_character)
+      if type == :header
+        doc = Nokogiri::XML(File.open(OOXMLDocumentObject.path_to_folder + 'word/footnotes.xml'))
+        doc.search('//w:footnote').each do |footnote|
+          next unless footnote.attribute('id').value == id
+          description = []
+          paragraph_number = 0
+          footnote.xpath('w:p').each do |paragraph|
+            description << DocxParagraph.parse(paragraph, paragraph_number, default_paragraph, default_character)
+            paragraph_number += 1
+          end
+          return description
+        end
+      elsif type == :header
+        doc = Nokogiri::XML(File.open(OOXMLDocumentObject.path_to_folder + 'word/endnotes.xml'))
+        doc.search('//w:endnote').each do |footnote|
+          next unless footnote.attribute('id').value == id
+          description = []
+          paragraph_number = 0
+          footnote.xpath('w:p').each do |paragraph|
+            description << DocxParagraph.parse(paragraph, paragraph_number, default_paragraph, default_character)
+            paragraph_number += 1
+          end
+          return description
+        end
+      end
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/image.rb

@@ -0,0 +1,15 @@
+# Image Data
+module OoxmlParser
+  class Image
+    attr_accessor :path, :start_x, :start_y, :end_x, :end_y, :wrap_text
+
+    def initialize
+      @path = nil
+      @start_x = 0
+      @start_y = 0
+      @end_x = nil
+      @end_y = nil
+      @wrap_text = 'In text'
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/columns/column.rb

@@ -0,0 +1,10 @@
+module OoxmlParser
+  class Column
+    attr_accessor :width, :space, :separator
+
+    def initialize(width = nil, space = nil)
+      @width = width
+      @space = space
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/columns.rb

@@ -0,0 +1,37 @@
+require_relative 'columns/column'
+module OoxmlParser
+  class Columns < OOXMLDocumentObject
+    attr_accessor :separator
+    attr_accessor :count
+    attr_accessor :equal_width
+    alias equal_width? equal_width
+    attr_accessor :column_array
+
+    def initialize(columns_count)
+      @count = columns_count
+      @column_array = []
+    end
+
+    # @return [Array, Column] accessor
+    def [](key)
+      @column_array[key]
+    end
+
+    # Parse Columns data
+    # @param [Nokogiri::XML:Element] node with Columns data
+    # @return [DocumentGrid] value of Columns data
+    def self.parse(columns_grid)
+      columns_count = 1
+      columns_count = columns_grid.attribute('num').value.to_i unless columns_grid.attribute('num').nil?
+      columns = Columns.new(columns_count)
+      columns.separator = columns_grid.attribute('sep').value unless columns_grid.attribute('sep').nil?
+      columns.equal_width = option_enabled?(columns_grid, 'equalWidth') unless columns_grid.attribute('equalWidth').nil?
+      columns_grid.xpath('w:col').each do |col|
+        width = (col.attribute('w').value.to_f / OoxmlParser.configuration.units_delimiter).round(2)
+        space = (col.attribute('space').value.to_f / OoxmlParser.configuration.units_delimiter).round(2) unless col.attribute('space').nil?
+        columns.column_array << Column.new(width, space)
+      end
+      columns
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/document_grid.rb

@@ -0,0 +1,29 @@
+module OoxmlParser
+  class DocumentGrid
+    attr_accessor :type, :line_pitch, :char_space
+
+    def initialize(type = nil, line_pitch = nil, char_space = nil)
+      @type = type
+      @line_pitch = line_pitch
+      @char_space = char_space
+    end
+
+    # Parse DocumentGrid
+    # @param [Nokogiri::XML:Element] node with DocumentGrid
+    # @return [DocumentGrid] value of DocumentGrid
+    def self.parse(node)
+      document_grid = DocumentGrid.new
+      node.attributes.each do |key, value|
+        case key
+        when 'charSpace'
+          document_grid.char_space = value.value
+        when 'linePitch'
+          document_grid.line_pitch = value.value.to_i
+        when 'type'
+          document_grid.type = value.value
+        end
+      end
+      document_grid
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/note.rb

@@ -0,0 +1,49 @@
+module OoxmlParser
+  class Note < OOXMLDocumentObject
+    attr_accessor :type, :elements, :assigned_to
+
+    def initialize(type = nil, elements = [], assigned_to = nil)
+      @type = type
+      @elements = elements
+      @assigned_to = assigned_to
+    end
+
+    def self.parse(default_paragraph, default_character, target, assigned_to, type)
+      note = Note.new
+      note.type = type
+      note.assigned_to = assigned_to
+      doc = Nokogiri::XML(File.open(OOXMLDocumentObject.path_to_folder + "word/#{target}"))
+      if type.include?('footer')
+        xpath_note = '//w:ftr'
+      elsif type.include?('header')
+        xpath_note = '//w:hdr'
+      else
+        raise "Cannot parse unknown Note type: #{type}"
+      end
+      doc.search(xpath_note).each do |ftr|
+        number = 0
+        ftr.xpath('*').each do |sub_element|
+          if sub_element.name == 'p'
+            note.elements << DocxParagraph.parse(sub_element, number, default_paragraph, default_character)
+            number += 1
+          elsif sub_element.name == 'tbl'
+            note.elements << Table.parse(sub_element, number)
+            number += 1
+          elsif sub_element.name == 'std'
+            sub_element.xpath('w:p').each do |p|
+              note.elements << DocxParagraph.parse(p, number, default_paragraph, default_character)
+              number += 1
+            end
+            sub_element.xpath('w:sdtContent').each do |sdt_content|
+              sdt_content.xpath('w:p').each do |p|
+                note.elements << DocxParagraph.parse(p, number, default_paragraph, default_character)
+                number += 1
+              end
+            end
+          end
+        end
+      end
+      note
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/page_margins.rb

@@ -0,0 +1,42 @@
+module OoxmlParser
+  class PageMargins
+    attr_accessor :top, :bottom, :left, :right, :footer, :gutter, :header
+
+    def initialize(top: nil, bottom: nil, left: nil, right: nil, header: nil, footer: nil, gutter: nil)
+      @top = top
+      @bottom = bottom
+      @left = left
+      @right = right
+      @header = header
+      @footer = footer
+      @gutter = gutter
+    end
+
+    def ==(other)
+      other.class == PageMargins &&
+        @top == other.top &&
+        @bottom == other.bottom &&
+        @left == other.left &&
+        @right == other.right &&
+        @footer == other.footer &&
+        @header == other.header &&
+        @gutter == other.gutter
+    end
+
+    # Parse BordersProperties
+    # @param [Nokogiri::XML:Element] node with PageMargins
+    # @return [PageMargins] value of PageMargins
+    def self.parse(node)
+      margins = PageMargins.new
+      # TODO: implement and understand, why 566.929, but not `unit_delimiter`
+      margins.top = (node.attribute('top').value.to_f / 566.929).round(2)
+      margins.left = (node.attribute('left').value.to_f / 566.929).round(2)
+      margins.right = (node.attribute('right').value.to_f / 566.929).round(2)
+      margins.bottom = (node.attribute('bottom').value.to_f / 566.929).round(2)
+      margins.header = (node.attribute('header').value.to_f / 566.929).round(2) unless node.attribute('header').nil?
+      margins.footer = (node.attribute('footer').value.to_f / 566.929).round(2) unless node.attribute('footer').nil?
+      margins.gutter = (node.attribute('gutter').value.to_f / 566.929).round(2)
+      margins
+    end
+  end
+end

data/lib/ooxml_parser/docx_parser/docx_data/document_structure/page_properties/page_properties.rb

@@ -0,0 +1,88 @@
+require_relative 'document_grid'
+require_relative 'size'
+require_relative 'page_margins'
+require_relative 'columns'
+require_relative 'note'
+module OoxmlParser
+  class PageProperties < OOXMLDocumentObject
+    attr_accessor :type, :size, :margins, :document_grid, :num_type, :form_prot, :text_direction, :page_borders, :columns,
+                  :notes
+
+    def initialize
+      @type = nil
+      @size = nil
+      @margins = nil
+      @document_grid = nil
+      @num_type = nil
+      @form_prot = nil
+      @text_direction = nil
+      @columns = nil
+      @notes = []
+    end
+
+    def self.parse(sect_pr, default_paragraph, default_character)
+      page_properties = PageProperties.new
+      sect_pr.xpath('w:pgSz').each do |pg_sz|
+        page_properties.size = Size.parse(pg_sz)
+      end
+      sect_pr.xpath('w:pgBorders').each do |pg_borders|
+        page_borders = Borders.new
+        unless pg_borders.attribute('display').nil?
+          page_borders.display = pg_borders.attribute('display').value
+        end
+        unless pg_borders.attribute('offsetFrom').nil?
+          page_borders.offset_from = pg_borders.attribute('offsetFrom').value
+        end
+        pg_borders.xpath('w:bottom').each do |bottom|
+          page_borders.bottom = BordersProperties.parse(bottom)
+        end
+        pg_borders.xpath('w:left').each do |left|
+          page_borders.bottom = BordersProperties.parse(left)
+        end
+        pg_borders.xpath('w:top').each do |top|
+          page_borders.bottom = BordersProperties.parse(top)
+        end
+        pg_borders.xpath('w:right').each do |right|
+          page_borders.bottom = BordersProperties.parse(right)
+        end
+        page_properties.page_border = page_borders
+      end
+      sect_pr.xpath('w:type').each do |type|
+        page_properties.type = type.attribute('val').value
+      end
+      sect_pr.xpath('w:pgMar').each do |pg_mar|
+        page_properties.margins = PageMargins.parse(pg_mar)
+      end
+      sect_pr.xpath('w:pgNumType').each do |pg_num_type|
+        page_properties.num_type = pg_num_type.attribute('fmt').value unless pg_num_type.attribute('fmt').nil?
+      end
+      sect_pr.xpath('w:formProt').each do |form_prot|
+        page_properties.form_prot = form_prot.attribute('val').value
+      end
+      sect_pr.xpath('w:textDirection').each do |text_direction|
+        page_properties.text_direction = text_direction.attribute('val').value
+      end
+      sect_pr.xpath('w:docGrid').each do |doc_grid|
+        page_properties.document_grid = DocumentGrid.parse(doc_grid)
+      end
+      sect_pr.xpath('w:cols').each do |columns_grid|
+        page_properties.columns = Columns.parse(columns_grid)
+      end
+      sect_pr.xpath('w:headerReference').each do |header_reference|
+        target = OOXMLDocumentObject.get_link_from_rels(header_reference.attribute('id').value)
+        OOXMLDocumentObject.add_to_xmls_stack("word/#{target}")
+        note = Note.parse(default_paragraph, default_character, target, header_reference.attribute('type').value, File.basename(target).sub('.xml', ''))
+        page_properties.notes << note
+        OOXMLDocumentObject.xmls_stack.pop
+      end
+      sect_pr.xpath('w:footerReference').each do |footer_reference|
+        target = OOXMLDocumentObject.get_link_from_rels(footer_reference.attribute('id').value)
+        OOXMLDocumentObject.add_to_xmls_stack("word/#{target}")
+        note = Note.parse(default_paragraph, default_character, target, footer_reference.attribute('type').value, File.basename(target).sub('.xml', ''))
+        page_properties.notes << note
+        OOXMLDocumentObject.xmls_stack.pop
+      end
+      page_properties
+    end
+  end
+end