standard-procedure-consolidate 0.3.0 → 0.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1bd2015cc0f88bc4b16bae7d8ecd335fb7b28c2bc940f81b1479e4a58ecce647
-  data.tar.gz: 44905254b9536f40f839d64d0448c4fb40b1a3720fb4d9ba3e2251468175eb9b
+  metadata.gz: e7a086625fa1f07169c2f9eba544538df266fbd83702efeedd13998d1a9e83b3
+  data.tar.gz: f80f0c11aa839c9dba9c4dc41758471ccfc31d7d38159e902e11d48cc8016c82
 SHA512:
-  metadata.gz: 36dee64a5f21766e06e7b5eb213e5a5b4dee9ca04da8bde4b429c4d93c5bd49275226975c7e9887214ea5a3b5975c4f955b245ab45e0103656b928ab59854789
-  data.tar.gz: 687bba668eb1f137b67c82819561ec2e8c2c3bc9a54f03aa4b6ac76958ae3a15988af8db5f78e7e95adb59968b5764b32c37e71d257b7885d1eb0e10d6e3f56a
+  metadata.gz: 72b26cbc5f54cc481ad49cbb604338591e27f1a503330372ab41920a05f3cbde4b1d6b6aa4b607b1189fbd8fd5ed30102d9741b8b6cf762c0cb39c900ac19327
+  data.tar.gz: 33ab5fbe36794cf24ca73ce70ec6da8f91cfe5430a438d5794da54bd668e72dd956331401ac983f5d15b7f77d60ef8ac6a3d438e4a0fb6279736c6dd79342931

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## [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.  

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

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

data/lib/consolidate/docx/merge.rb

@@ -30,8 +30,8 @@ module Consolidate
       # Read all documents within the docx and extract any merge fields
       def field_names
         tag_nodes.collect do |tag_node|
-          field_name_from tag_node
-        end.compact.uniq
+          field_names_from tag_node
+        end.flatten.compact.uniq
       end
 
       # List the documents stored within this docx
@@ -45,7 +45,7 @@ module Consolidate
 
         if verbose
           puts "...substitutions..."
-          fields.each do |key, value|
+          mapping.each do |key, value|
             puts "      #{key} => #{value}"
           end
         end
@@ -76,6 +76,7 @@ module Consolidate
       attr_reader :xml
       attr_reader :documents
       attr_accessor :output
+      TAG = /\{\{\s*(\S+)\s*\}\}/
 
       def load_documents
         @zip.entries.each_with_object({}) do |entry, documents|
@@ -100,40 +101,52 @@ module Consolidate
       # 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:t").collect do |node|
-          (node.children.any? { |child| child.content.include? "{{" }) ? enclosing_node_for_start_tag(node) : nil
-        end.compact
+        (document / "//w:p").select do |paragraph|
+          paragraph.content.match(TAG)
+        end
       end
 
       # Extract the merge field name from the node
-      def field_name_from(tag_node)
-        return nil unless (matches = tag_node.content.match(/{{\s*(\S+)\s*}}/))
-        field_name = matches[1].strip
-        puts "...field #{field_name} found in #{name}" if verbose
-        field_name.to_s
+      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_name = field_name_from tag_node
-          next unless mapping.has_key? field_name
-          field_value = mapping[field_name]
-          puts "...substituting #{field_name} with #{field_value} in #{document_name}" if verbose
-          tag_node.content = tag_node.content.gsub(field_name, field_value).gsub(/{{\s*/, "").gsub(/\s*}}/, "")
+          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 = 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
-
-      # Find the ancestor node that contains both the start {{ text and the end }} text enclosing the merge field
-      def enclosing_node_for_start_tag(node)
-        return node if node.content.include? "}}"
-        node.parent.nil? ? nil : enclosing_node_for_start_tag(node.parent)
-      end
     end
   end
 end

data/lib/consolidate/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Consolidate
-  VERSION = "0.3.0"
+  VERSION = "0.3.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: standard-procedure-consolidate
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors:
 - Rahoul Baruah
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-11-21 00:00:00.000000000 Z
+date: 2024-11-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -62,6 +62,7 @@ files:
 - 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