Merge pull request #3 from ruby-docx/master

Merge latest from upstream

Author: danblaker

.github/workflows/release.yml

@@ -8,14 +8,34 @@ on:
 jobs:
   build:
     name: Build a package
-
     runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 3.4
+          bundler-cache: true
+      - run: bundle exec rake build
 
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      id-token: write
+    if: startsWith(github.ref, 'refs/tags/') # Run only when tagged like v1.0.1
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: 3.4
+          bundler-cache: true
+      - id: package_name
+        run: |
+          echo "package_name=$(basename pkg/*.gem | tail -n1)" >> $GITHUB_OUTPUT
 
-      - uses: softprops/action-gh-release@v1
-        if: startsWith(github.ref, 'refs/tags/') # Run only when tagged like v1.0.1
+      - uses: softprops/action-gh-release@v2
         with:
-          files: packages/${{steps.package_name.outputs.package_name}}.zip
+          files: pkg/${{steps.package_name.outputs.package_name}}
           generate_release_notes: true
+      - uses: rubygems/release-gem@v1

.github/workflows/ruby.yml

@@ -17,7 +17,12 @@ jobs:
 
     strategy:
       matrix:
-        ruby: [2.7, "3.0", 3.1, 3.2]
+        ruby:
+          - 3.1
+          - 3.2
+          - 3.3
+          - 3.4
+          - head
 
     steps:
     - uses: actions/checkout@v2

README.md

@@ -52,7 +52,7 @@ doc.bookmarks.each_pair do |bookmark_name, bookmark_object|
 end
 ```
 
-Don't have a local file but a buffer? Docx handles those to:
+Don't have a local file but a buffer? Docx handles those too:
 
 ```ruby
 require 'docx'
@@ -130,6 +130,14 @@ doc.paragraphs.each do |p|
   end
 end
 
+# Substitute text with access to captures, note block arg is a MatchData, a bit
+# different than String.gsub. https://ruby-doc.org/3.3.7/MatchData.html
+doc.paragraphs.each do |p|
+  p.each_text_run do |tr|
+    tr.substitute_with_block(/total: (\d+)/) { |match_data| "total: #{match_data[1].to_i * 10}" }
+  end
+end
+
 # Save document to specified path
 doc.save('example-edited.docx')
 ```
@@ -145,7 +153,7 @@ doc = Docx::Document.open('tables.docx')
 # Iterate over each table
 doc.tables.each do |table|
   last_row = table.rows.last
-  
+
   # Copy last row and insert a new one before last row
   new_row = last_row.copy
   new_row.insert_before(last_row)
@@ -261,3 +269,4 @@ The following is a list of attributes and what they control within the style.
 * Default formatting of inserted elements to inherited values
 * Implement formattable elements.
 * Easier multi-line text insertion at a single bookmark (inserting paragraph nodes after the one containing the bookmark)
+

docx.gemspec

@@ -14,7 +14,7 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '>= 2.7.0'
 
   s.add_dependency 'nokogiri', '~> 1.13', '>= 1.13.0'
-  s.add_dependency 'rubyzip',  '~> 2.0'
+  s.add_dependency 'rubyzip',  '>= 2.0', "< 4"
 
   s.add_development_dependency 'coveralls_reborn', '~> 0.21'
   s.add_development_dependency 'rake', '~> 13.0'

lib/docx/containers/text_run.rb

@@ -57,6 +57,19 @@ def substitute(match, replacement)
           reset_text
         end
 
+        # Weird things with how $1/$2 in regex blocks are handled means we can't just delegate
+        # block to gsub to get block, we have to do it this way, with a block that gets a MatchData,
+        # from which captures and other match data can be retrieved.
+        # https://ruby-doc.org/3.3.7/MatchData.html
+        def substitute_with_block(match, &block)
+          @text_nodes.each do |text_node|
+            text_node.content = text_node.content.gsub(match) { |_unused_matched_string|
+              block.call(Regexp.last_match)
+            }
+          end
+          reset_text
+        end
+
         def parse_formatting
           {
             italic:    !@node.xpath('.//w:i').empty?,

lib/docx/document.rb

@@ -30,7 +30,6 @@ def initialize(path_or_io, options = {})
 
       # if path-or_io is string && does not contain a null byte
       if (path_or_io.instance_of?(String) && !/\u0000/.match?(path_or_io))
-        raise Errno::EIO.new('Invalid file format') if !File.extname(path_or_io).eql?('.docx')
         @zip = Zip::File.open(path_or_io)
       else
         @zip = Zip::File.open_buffer(path_or_io)

lib/docx/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Docx #:nodoc:
-  VERSION = '0.8.0'
+  VERSION = '0.10.0'
 end

spec/docx/document_spec.rb

@@ -20,12 +20,6 @@
     end
 
     context 'When reading a un-supported file' do
-      it 'should throw file not supported error' do
-        expect do
-          Docx::Document.open(@fixtures_path + '/invalid_format.pdf')
-        end.to raise_error(Errno::EIO, 'Input/output error - Invalid file format')
-      end
-
       it 'should throw file not found error' do
         invalid_path = @fixtures_path + '/invalid_file_path.docx'
         expect do
@@ -206,6 +200,19 @@
 
       expect(@doc.paragraphs[1].text).to eq('Multi-line paragraph line 1same paragraph line 2yet the same paragraph line3 ')
     end
+
+    it "should replace placeholder in any line of paragraph using substitute_with_block" do
+      expect(@doc.paragraphs[0].text).to eq('Page title')
+      expect(@doc.paragraphs[1].text).to eq('Multi-line paragraph line 1_placeholder2_ line 2_placeholder3_ line3 ')
+
+      @doc.paragraphs[1].each_text_run do |text_run|
+        text_run.substitute_with_block(/_placeholder(\d)_/) { |match_data|
+          "_replacement_#{match_data[1]}"
+        }
+      end
+
+      expect(@doc.paragraphs[1].text).to eq('Multi-line paragraph line 1_replacement_2 line 2_replacement_3 line3 ')
+    end
   end
 
   describe 'read formatting' do