word_mail_merge.rb is a simple way to do mail merge in ruby

word_mail_merge.rb

#!/usr/bin/env ruby

require 'zip/zip' # rubyzip gem
require 'nokogiri'

class WordMailMerge
  def self.open(path, &block)
    self.new(path, &block)
  end
  
  def initialize(path, &block)
    @replace = {}
    if block_given?
      @zip = Zip::ZipFile.open(path)
      yield(self)
      @zip.close
    else
      @zip = Zip::ZipFile.open(path)
    end
  end
  
  def force_settings
    @replace["word/settings.xml"] = %{<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:settings xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:sl="http://schemas.openxmlformats.org/schemaLibrary/2006/main"><w:zoom w:percent="100"/></w:settings>}
  end
  
  def merge(rec)
    xml = @zip.read("word/document.xml")
    doc = Nokogiri::XML(xml) {|x| x.noent}
    # Word's first way of doing things
    (doc/"//w:fldSimple").each do |field|
      if field.attributes['instr'].value =~ /MERGEFIELD (\S+)/
        text_node = (field/".//w:t").first
        puts "#{$1} existing text: #{text_node.inner_html}, Set to #{rec[$1]}"
        p text_node
        if text_node
          puts "Replace node for #{$1}"
          text_node.inner_html = rec[$1].to_s
        else
          puts "No text node for #{$1}"
        end
      end
    end
    
    # Word's second way of doing things (why???)
    (doc/"//w:instrText").each do |instr|
      if instr.inner_text =~ /MERGEFIELD (\S+)/
        #rsid = instr.parent.attributes['rsidR']
        text_node = instr.parent.next_sibling.next_sibling.xpath(".//w:t").first
        text_node ||= instr.parent.next_sibling.next_sibling.next_sibling.xpath(".//w:t").first
        if text_node
        #if text_node = instr.parent.parent.xpath(".//w:t").first
        
        #if text_node = (doc/"//w:r[@w:rsidR='#{rsid}']//w:t").first
          text_node.inner_html = rec[$1].to_s
        end
      end
    end
    @replace["word/document.xml"] = doc.serialize :save_with => 0
        
  end
  
  def save(path)
    Zip::ZipFile.open(path, Zip::ZipFile::CREATE) do |out|
      @zip.each do |entry|
        out.get_output_stream(entry.name) do |o|
          if @replace[entry.name]
            o.write(@replace[entry.name])
          else
            o.write(@zip.read(entry.name))
          end
        end
      end
    end
  end
  
  def close
    @zip.close
  end
end

if __FILE__ == $0
  file = ARGV[0]
  out_file = ARGV[1] || file.sub(/\.docx/, ' Merged.docx')
  w = WordMailMerge.open(file) 
  w.force_settings
  w.merge('First_Name' => 'Eric', 'Last_Name' => 'Mason')
  w.save(out_file)
end