docstache 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 09dcc56ee2a672c326f0dfeca2286abff6020861
+  data.tar.gz: f557ff91695d6cbdd27adb2901c6a8b5bb564e7a
+SHA512:
+  metadata.gz: abdc024d14d88019410b688cf5ce50de62154e97bace385d330eb5f79f43934abb2cb71c7dd1cb19024ee95edab4bb86c833abe9b9c81debeda17d2d5193bb19
+  data.tar.gz: 24723da702b5a4e15dd8434ce8d7ff7ffc02f6586f1a170480e4313b44256c39132de7ae7585569a70692e77bc9849ac0323029a3e805f2637842ffa633e8d6b

data/.gitignore

@@ -0,0 +1,5 @@
+.DS_Store
+spec/example_input/tmp
+.idea/
+*.gem
+Gemfile.lock

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

data/LICENSE.txt

@@ -0,0 +1,176 @@
+                              Apache License
+                        Version 2.0, January 2004
+                     http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding those notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

data/README.rdoc

@@ -0,0 +1,24 @@
+= Turns a docx file template and a data set into a fully formed docx document
+Inspired from [https://github.com/jawspeak/ruby-docx-templater] and [https://github.com/michaelfranzl/docx_converter], this takes a .docx file and uses it as a template to create a new docx, with your data
+
+== Features
+
+* All manipulation in memory (great if you have sensitive data)
+* Global key/value substitutions by entering a `$KEY$` anywhere in the word document, with whatever formatting you want.
+* Multi-row loops inside tables, also with whatever your formatting you wish. `#BEGIN_ROW:XYZ#`... `#END_ROW:XYZ#` see tests/example
+* Allows for embedded loops through fully recursive parsing of the document
+
+== Usage
+* Create your docx "template" in Word
+* Install rvm and bundler
+* Run `bundle install`.
+* Render new docx files from the template, ex: `ruby render_docx_template.rb`. Look for a rendered_*.docx file.
+* Sample output with tests: `rake spec` (unit tests) `rake integration` (opens word)
+
+__MS WORD is painful__ You will probably need to modify your docx document in word until such a time as all flags to replace are set properly within a single XML element. You can’t have Word’s split a string of characters across multiple xml elements in your template document.
+Test the template and keep fixing it until the fields are all set properly.
+
+I frequently use this workflow:
+ - Cut string to replace out to notepad
+ - Paste string back into MS Word
+ - Save Word Document

data/Rakefile

@@ -0,0 +1,7 @@
+require 'rspec/core/rake_task'
+require 'rubocop/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+RuboCop::RakeTask.new
+
+task default: [:spec, :rubocop]

data/docstache.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "docstache/version"
+
+Gem::Specification.new do |s|
+  s.name        = "docstache"
+  s.version     = Docstache::VERSION
+  s.authors     = ["Will Cosgrove"]
+  s.email       = ["will@willcosgrove.com"]
+  s.homepage    = "https://github.com/willcosgrove/docstache"
+  s.summary     = %q{Merges Hash of Data into Word docx template files using mustache syntax}
+  s.description = %q{Integrates data into MS Word docx template files. Processing supports loops and replacement of strings of data both outside and within loops.}
+  s.license     = 'MIT'
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.require_paths = ["lib"]
+
+  # specify any dependencies here; for example:
+  s.add_runtime_dependency 'nokogiri', '~> 1.6'
+  s.add_runtime_dependency 'rubyzip', '~> 1.1'
+end

data/lib/docstache/document.rb

@@ -0,0 +1,102 @@
+module Docstache
+  class Document
+    def initialize(*paths)
+      raise ArgumentError if paths.empty?
+      @path = paths.shift
+      @zip_file = Zip::File.open(@path)
+      @document = Nokogiri::XML(unzip_read(@zip_file, "word/document.xml"))
+      zip_files = paths.map{|p| Zip::File.open(p)}
+      documents = zip_files.map{|f| Nokogiri::XML(unzip_read(f, "word/document.xml"))}
+      documents.each do |doc|
+        @document.at_css('w|p:last').add_next_sibling(page_break)
+        @document.at_css('w|p:last').add_next_sibling(doc.at_css('w|body').children)
+      end
+    end
+
+    def tags
+      @document.text.gsub(/\s+/, '').scan(/\{\{[\w\.\/\#]+\}\}/)
+    end
+
+    def usable_tags
+      @document.css('w|t').select { |tag| tag.text =~ /\{\{[\w\.\/\#]+\}\}/ }.map(&:text)
+    end
+
+    def fix_errors
+      missing_tags = tags - usable_tags
+      problem_paragraphs = missing_tags.map { |tag|
+        @document.css('w|p').select {|t| t.text =~ /#{tag}/}.first
+      }
+
+      problem_paragraphs.each do |p|
+        flatten_paragraph(p) if p
+      end
+    end
+
+    def errors?
+      tags.length != usable_tags.length
+    end
+
+    def save
+      buffer = zip_buffer(@document)
+      File.open(@path, "w") {|f| f.write buffer.string}
+    end
+
+    def render_file(output, data={})
+      rendered = Docstache::Renderer.new(@document, data).render
+      buffer = zip_buffer(rendered)
+      File.open(output, "w") {|f| f.write buffer.string}
+    end
+
+    def render_stream(data={})
+      rendered = Docstache::Renderer.new(@document, data).render
+      buffer = zip_buffer(rendered)
+      buffer.rewind
+      return buffer.sysread
+    end
+
+    private
+
+    def flatten_paragraph(p)
+      runs = p.css('w|r')
+      host_run = runs.shift
+      runs.each do |run|
+        host_run.at_css('w|t').content += run.text
+        run.unlink
+      end
+    end
+
+    def unzip_read(zip, zip_path)
+      file = zip.find_entry(zip_path)
+      contents = ""
+      file.get_input_stream do |f|
+        contents = f.read
+      end
+      return contents
+    end
+
+    def zip_buffer(document)
+      buffer = Zip::OutputStream.write_buffer do |out|
+        @zip_file.entries.each do |e|
+          unless ["word/document.xml"].include?(e.name)
+            out.put_next_entry(e.name)
+            out.write(e.get_input_stream.read)
+          end
+        end
+        out.put_next_entry("word/document.xml")
+        out.write(@document.to_xml(indent: 0).gsub("\n", ""))
+      end
+      return buffer
+    end
+
+    def page_break
+      p = Nokogiri::XML::Node.new("p", @document)
+      p.namespace = @document.at_css('w|p:last').namespace
+      r = Nokogiri::XML::Node.new("r", @document)
+      p.add_child(r)
+      br = Nokogiri::XML::Node.new("br", @document)
+      r.add_child(br)
+      br['w:type'] = "page"
+      return p
+    end
+  end
+end

data/lib/docstache/renderer.rb

@@ -0,0 +1,152 @@
+module Docstache
+  class Renderer
+    def initialize(xml, data)
+      @content = xml
+      @data = data
+    end
+
+    def render
+      process_content
+      return @content
+    end
+
+    private
+
+    def process_content
+      parse_content(@content.elements)
+
+      content_tr = @content.xpath('//w:tr')
+
+      cleanup_loop(content_tr)
+    end
+
+    def extract_end_row(nd, key)
+      if !nd.nil?
+        case nd.text.to_s
+        when /\{\{\/#{key.to_s}\}\}/
+          puts "Found End Row for #{key.to_s}"
+          return nd
+        else
+          return extract_end_row(nd.next, key)
+        end
+      else
+        return nil
+      end
+    end
+
+    def expand_loop(nd, end_nd, key, element)
+      out = []
+      case nd.text.to_s
+      when /\{\{\##{key.to_s}\}\}/
+        out = expand_loop(nd.next, end_nd, key, element)
+      when end_nd.text.to_s
+        out = []
+      when /\{\{\#([a-zA-Z0-9_\.]+)\}\}/
+        new_key = $1.to_sym
+        out += process_loop(nd, new_key, element)
+      else
+        new_node = nd.dup
+        puts "Adding Row #{nd.text} to list"
+        parse_content(new_node.elements, element)
+        out << new_node
+        puts "Next Node is: #{nd.next.text.to_s}"
+        out += expand_loop(nd.next, end_nd, key, element)
+      end
+      return out
+    end
+
+
+    def remove_loop(nd, key)
+      if nd
+        case nd.text.to_s
+        when /\{\{\/#{key.upcase.to_s}\}\}/
+          nd.unlink
+        else
+          remove_loop(nd.next, key)
+          nd.unlink
+        end
+      end
+    end
+
+
+    def process_loop(nd, key, data)
+      out = []
+      puts "Found Loop #{key.to_s}"
+      end_row = extract_end_row(nd, key)
+
+      if !data.has_key?(key)
+        nil # Error in the data model
+        return []
+      elsif data[key].empty?
+        remove_loop(nd, key) # No data to put in
+        return []
+      else # Actual loop to process
+        data_set = data[key]
+        puts "Expanding Rows for loop #{key.to_s}"
+        puts "Data count is #{data_set.count}"
+        puts "Data is #{data_set}"
+
+        data_set.each do |element|
+          out += expand_loop(nd, end_row, key, element)
+        end
+        return out
+      end
+    end
+
+    def parse_content(elements, data=@data)
+      elements.each do |nd|
+        case nd.name
+        when "tr"
+          case nd.text.to_s
+          when /\{\{\#([a-zA-Z0-9_\.]+)\}\}/
+            key = $1.to_sym
+            # Get elements to add
+            elements = process_loop(nd, key, data)
+            # Add elements
+            elements.reverse.each do |e|
+              puts "Adding Row to file: #{e.text.to_s}"
+              nd.add_next_sibling(e)
+            end
+          else # it's a normal table row
+            parse_content(nd.elements, data)
+          end
+        when "t" # It's a leaf that contains data to replace
+          subst_content(nd, data)
+	else # it's neither a leaf or a loop so let's process it
+          parse_content(nd.elements, data)
+        end
+      end
+    end
+
+    def cleanup_loop(nodeset) # Acts in w/tr only as loops are based on these
+      nodeset.each do |nd|
+        case nd.text.to_s
+        when /\{\{\#([a-zA-Z0-9_\.]+)\}\}/
+          nd.unlink
+        when /\{\{\/([a-zA-Z0-9_\.]+)\}\}/
+          nd.unlink
+        when /\{\{[a-zA-Z0-9_\.]+\}\}/
+          nd.unlink
+        end
+      end
+    end
+
+    def subst_content(nd, data)
+      inner = nd.inner_html
+      keys = nd.text.scan(/\{\{([a-zA-Z0-9_\.]+)\}\}/).map(&:first).map(&:to_sym)
+      keys.each do |key|
+        value = data[key]
+        puts "Substituting {{#{key.to_s}}} with #{value}"
+        inner.gsub!("{{#{key.to_s}}}", safe(value))
+      end
+      if !keys.empty?
+        nd.inner_html = inner
+      end
+    end
+
+    def safe(text)
+      text.to_s
+    end
+
+  end
+end

data/lib/docstache/version.rb

@@ -0,0 +1,3 @@
+module Docstache
+  VERSION = "0.0.1"
+end

data/lib/docstache.rb

@@ -0,0 +1,9 @@
+require 'nokogiri'
+require 'zip'
+
+require "docstache/renderer"
+require "docstache/document"
+
+module Docstache
+  #noop
+end