standard-procedure-consolidate 0.2.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f61fdd9cdf73d8609574952bca3a57839983f74f100aea6f8b54a4248b526efa
-  data.tar.gz: 0a64110c54d435f10c1465b96dd61e150c2ff56ae887788b5880d7bf489e93d5
+  metadata.gz: e7a086625fa1f07169c2f9eba544538df266fbd83702efeedd13998d1a9e83b3
+  data.tar.gz: f80f0c11aa839c9dba9c4dc41758471ccfc31d7d38159e902e11d48cc8016c82
 SHA512:
-  metadata.gz: ac0a18d02265eb79b2c9ffda09b2a13825e520a08faef45c1a0f3fd29877b11abf46776554a7c7e2e4157e560f0269889a95f3a9dc3dc4f49b66bda51848e37c
-  data.tar.gz: 1fce15f81e519792c058dc731cd298db46dc4163d7c0c6cd753c87c2ec7a672aa4b9e350d526d8a641ebdb13bd3dd98b1a9ebd8bb854cd6d0e2342899103b883
+  metadata.gz: 72b26cbc5f54cc481ad49cbb604338591e27f1a503330372ab41920a05f3cbde4b1d6b6aa4b607b1189fbd8fd5ed30102d9741b8b6cf762c0cb39c900ac19327
+  data.tar.gz: 33ab5fbe36794cf24ca73ce70ec6da8f91cfe5430a438d5794da54bd668e72dd956331401ac983f5d15b7f77d60ef8ac6a3d438e4a0fb6279736c6dd79342931

data/.devcontainer/devcontainer.json

@@ -1,7 +1,23 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
 // README at: https://github.com/devcontainers/templates/tree/main/src/ruby
 {
-	"name": "Ruby",
-	"image": "mcr.microsoft.com/devcontainers/ruby:1-3.2-bullseye",
-	"postCreateCommand": "bundle install"
-}
+  "name": "Ruby",
+  "image": "mcr.microsoft.com/devcontainers/ruby:1-3.2-bullseye",
+  "postCreateCommand": "bundle install",
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "Shopify.ruby-extensions-pack",
+        "testdouble.vscode-standard-ruby",
+        "manuelpuyol.erb-linter",
+        "Shopify.ruby-lsp",
+        "aki77.rails-db-schema",
+        "miguel-savignano.ruby-symbols",
+        "sibiraj-s.vscode-scss-formatter",
+        "Thadeu.vscode-run-rspec-file",
+        "Cronos87.yaml-symbols",
+        "aliariff.vscode-erb-beautify"
+      ]
+    }
+  }
+}

data/.ruby-version

@@ -1 +1 @@
-3.2.2
+3.2.5

data/.standard.yml

@@ -1,3 +1,3 @@
 # For available configuration options, see:
 #   https://github.com/testdouble/standard
-ruby_version: 2.6
+ruby_version: 3.2.5

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## [0.3.1] - 2024-11-22
+
+Ensure that the substituted nodes are reinserted correctly into the output document, attempting to restore formatting at the paragraph level (although it does lose formatting at lower levels than this - so-called "run" nodes which represent arbitrary spans of characters within the paragraph).
+
+
+## [0.3.0] - 2024-11-21
+
+Updated the code that examines the docx file for merge fields to deal with Word formatting tags being inserted in the middle of the merge fields.  
+
 ## [0.2.0] - 2023-09-13
 
 Thrown away the mail-merge implementation and replaced it with a simple search/replace.  

data/README.md

@@ -78,7 +78,7 @@ Consolidate looks for word/document.xml files, plus any files that match word/he
 
 ## Development
 
-The repo contains a .devcontainer folder - this contains instructions for a development container that has everything needed to build the project.  Once the container has started, you can use `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+The repo contains a .devcontainer folder - this contains instructions for a development container that has everything needed to build the project.  Once the container has started, you can use `bin/setup` to install dependencies. Then, run `bundle exec rake` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
 
 `bundle exec rake install` will install the gem on your local machine (obviously not from within the devcontainer though). To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to [rubygems.org](https://rubygems.org).
 

data/Rakefile

@@ -7,4 +7,4 @@ RSpec::Core::RakeTask.new(:spec)
 
 require "standard/rake"
 
-task default: %i[spec standard]
+task default: %i[standard:fix spec]

data/checksums/standard-procedure-consolidate-0.3.0.gem.sha512

@@ -0,0 +1 @@
+098078b13e3bb4e3370cbc6bdb0195300489dfb33a5c27a201a4c5f1f0184bba73557264e674f49da41dbc62ad991e8ae99bef1debf417a5b1a363b1d56829f1

data/checksums/standard-procedure-consolidate-0.3.1.gem.sha512

@@ -0,0 +1 @@
+ac1393002b538b8f000c1e4f1f7f4514f689434dad0889a77a0470bd839c58cb49d6218daafd4a8ca48675e220ab9c42147de78a40ec0fd59d5a19371b699eb0

data/lib/consolidate/docx/merge.rb

@@ -11,6 +11,15 @@ module Consolidate
         path
       end
 
+      def initialize(path, verbose: false, &block)
+        @verbose = verbose
+        @output = {}
+        @zip = Zip::File.open(path)
+        @documents = load_documents
+        block&.call self
+      end
+
+      # Helper method to display the contents of the document and the merge fields from the CLI
       def examine
         documents = document_names.join(", ")
         fields = field_names.join(", ")
@@ -18,39 +27,37 @@ module Consolidate
         puts "Merge fields: #{fields}"
       end
 
+      # Read all documents within the docx and extract any merge fields
       def field_names
-        documents.collect do |name, document|
-          (document / "//w:t").collect do |text_node|
-            next unless (matches = text_node.content.match(/{{\s*(\S+)\s*}}/))
-            field_name = matches[1].strip
-            puts "...field #{field_name} found in #{name}" if verbose
-            field_name
-          end.compact
-        end.flatten
+        tag_nodes.collect do |tag_node|
+          field_names_from tag_node
+        end.flatten.compact.uniq
       end
 
+      # List the documents stored within this docx
       def document_names
         @zip.entries.collect { |entry| entry.name }
       end
 
-      def data fields = {}
-        fields = fields.transform_keys(&:to_s)
+      # Substitute the data from the merge fields with the values provided
+      def data mapping = {}
+        mapping = mapping.transform_keys(&:to_s)
 
         if verbose
           puts "...substitutions..."
-          fields.each do |key, value|
+          mapping.each do |key, value|
             puts "      #{key} => #{value}"
           end
         end
 
         @documents.each do |name, document|
-          result = document.dup
-          result = substitute result, fields, name
+          output_document = substitute document.dup, mapping: mapping, document_name: name
 
-          @output[name] = result.serialize save_with: 0
+          @output[name] = output_document.serialize save_with: 0
         end
       end
 
+      # Write the new document to the given path
       def write_to path
         puts "...writing to #{path}" if verbose
         Zip::File.open(path, Zip::File::CREATE) do |out|
@@ -62,51 +69,84 @@ module Consolidate
         end
       end
 
-      protected
+      private
 
       attr_reader :verbose
       attr_reader :zip
       attr_reader :xml
       attr_reader :documents
       attr_accessor :output
+      TAG = /\{\{\s*(\S+)\s*\}\}/
 
-      def initialize(path, verbose: false, &block)
-        raise "No block given" unless block
-        @verbose = verbose
-        @output = {}
-        @documents = {}
-        begin
-          @zip = Zip::File.open(path)
-          @zip.entries.each do |entry|
-            next unless entry.name.match?(/word\/(document|header|footer|footnotes|endnotes).?\.xml/)
-            puts "...reading #{entry.name}" if verbose
-            xml = @zip.get_input_stream entry
-            @documents[entry.name] = Nokogiri::XML(xml) { |x| x.noent }
-          end
-          yield self
-        ensure
-          @zip.close
+      def load_documents
+        @zip.entries.each_with_object({}) do |entry, documents|
+          next unless entry.name.match?(/word\/(document|header|footer|footnotes|endnotes).?\.xml/)
+          puts "...reading #{entry.name}" if verbose
+          xml = @zip.get_input_stream entry
+          documents[entry.name] = Nokogiri::XML(xml) { |x| x.noent }
         end
+      ensure
+        @zip.close
       end
 
-      def substitute document, fields, document_name
-        (document / "//w:t").each do |text_node|
-          next unless (matches = text_node.content.match(/{{\s*(\S+)\s*}}/))
-          field_name = matches[1].strip
-          if fields.has_key? field_name
-            field_value = fields[field_name]
+      # Collect all the nodes that contain merge fields
+      def tag_nodes
+        documents.collect do |name, document|
+          tag_nodes_for document
+        end.flatten
+      end
+
+      # go through all w:t (Word Text???) nodes of the document
+      # find any nodes that contain "{{"
+      # then find the ancestor node that also includes the ending "}}"
+      # This collection of nodes contains all the merge fields for this document
+      def tag_nodes_for document
+        (document / "//w:p").select do |paragraph|
+          paragraph.content.match(TAG)
+        end
+      end
+
+      # Extract the merge field name from the node
+      def field_names_from(tag_node)
+        matches = tag_node.content.scan(TAG)
+        matches.empty? ? nil : matches.flatten.map(&:strip)
+      end
+
+      # Go through the given document, replacing any merge fields with the values provided
+      # and storing the results in a new document
+      def substitute document, document_name:, mapping: {}
+        tag_nodes_for(document).each do |tag_node|
+          field_names = field_names_from tag_node
+          puts "Original Node for #{field_names} is #{tag_node}" if verbose
+
+          # Extract the paragraph properties node if it exists
+          paragraph_properties = tag_node.search ".//w:pPr"
+          run_properties = tag_node.at_xpath ".//w:rPr"
+
+          text = tag_node.content
+          field_names.each do |field_name|
+            field_value = mapping[field_name].to_s
             puts "...substituting #{field_name} with #{field_value} in #{document_name}" if verbose
-            text_node.content = text_node.content.gsub(matches[1], field_value).gsub("{{", "").gsub("}}", "")
-          elsif verbose
-            puts "...found #{field_name} but no replacement value"
+            text = text.gsub(/{{\s*#{field_name}\s*}}/, field_value)
           end
+
+          # Create a new text node with the substituted text
+          text_node = Nokogiri::XML::Node.new("w:t", tag_node.document)
+          text_node.content = text
+
+          # Create a new run node to hold the substituted text and the paragraph properties
+          run_node = Nokogiri::XML::Node.new("w:r", tag_node.document)
+          run_node << run_properties if run_properties
+          run_node << text_node
+          tag_node.children = Nokogiri::XML::NodeSet.new(document, paragraph_properties.to_a + [run_node])
+
+          puts "TAG NODE FOR #{field_names} IS #{tag_node}" if verbose
+        rescue => ex
+          # Have to mangle the exception message otherwise it outputs the entire document
+          puts ex.message.to_s[0..255]
         end
         document
       end
-
-      def close
-        zip.close
-      end
     end
   end
 end

data/lib/consolidate/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Consolidate
-  VERSION = "0.2.0"
+  VERSION = "0.3.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: standard-procedure-consolidate
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Rahoul Baruah
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-09-13 00:00:00.000000000 Z
+date: 2024-11-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -48,7 +48,6 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".devcontainer/devcontainer.json"
-- ".nova/Configuration.json"
 - ".rspec"
 - ".ruby-version"
 - ".standard.yml"
@@ -62,6 +61,8 @@ files:
 - checksums/standard-procedure-consolidate-0.1.3.gem.sha512
 - checksums/standard-procedure-consolidate-0.1.4.gem.sha512
 - checksums/standard-procedure-consolidate-0.2.0.gem.sha512
+- checksums/standard-procedure-consolidate-0.3.0.gem.sha512
+- checksums/standard-procedure-consolidate-0.3.1.gem.sha512
 - exe/consolidate
 - exe/examine
 - lib/consolidate.rb
@@ -77,7 +78,7 @@ metadata:
   homepage_uri: https://github.com/standard-procedure/standard-procedure-consolidate
   source_code_uri: https://github.com/standard-procedure/standard-procedure-consolidate
   changelog_uri: https://github.com/standard-procedure/standard-procedure-consolidate/blob/main/CHANGELOG.md
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -92,8 +93,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.10
-signing_key:
+rubygems_version: 3.4.19
+signing_key: 
 specification_version: 4
 summary: Simple ruby mailmerge for Microsoft Word .docx files.
 test_files: []

data/.nova/Configuration.json

@@ -1,3 +0,0 @@
-{
-
-}