docx 0.4.0 → 0.6.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9b2cc086dcc2bb5043cc9f20b311f1e4b02f7c9730f459c8b91e48097d8bacb5
-  data.tar.gz: 8536619dd3cebe92112b7328cf64cdca40be898411d974037d5e9ffc02af1a08
+  metadata.gz: 2a33dcd9e31c60144261a15670cd1c01b37877044aaf33f7091b46cc85ab3412
+  data.tar.gz: 1911db027b3e2fbf8eb9363eaa99b95231f875afe8de2a0c060b38fee86c7238
 SHA512:
-  metadata.gz: 77a0ee6f32422ad64e916b98d52d685958867e574582252d4ce424fac721cee4f73b400f8960ad88c762608024bfa7a5d966bea0cd65e1daecdb4d58967da307
-  data.tar.gz: e87937fb28f2c6f7d7777b63df9b483fde5670e98261253b91ed55fee4d737f72cc2596542ced45a80ba525a18b9ca7a1760f76440ad71ed30facdfe17fd0cc1
+  metadata.gz: 0a823fedf1b0bfc542c88533c787aefa5e9cee12ae4422a01f106985a2f03e8b636aa70820a179f5501ba8f996672f8f75e24356282cd7d81505cbb1984fa967
+  data.tar.gz: c06b4078536bd8b12b5c5e4f61fe0ef5f2f9e03e9cbc7c4017f2d01d3e8a0bc9200fa7457fac54c0b110a57ddc4bff8ad74c28d3e873512900266ac00137c6e6

data/README.md

@@ -1,12 +1,17 @@
 # docx
 
+[![Gem Version](https://badge.fury.io/rb/docx.svg)](https://badge.fury.io/rb/docx)
+[![Ruby](https://github.com/ruby-docx/docx/workflows/Ruby/badge.svg)](https://github.com/ruby-docx/docx/actions?query=workflow%3ARuby)
+[![Coverage Status](https://coveralls.io/repos/github/ruby-docx/docx/badge.svg?branch=master)](https://coveralls.io/github/ruby-docx/docx?branch=master)
+[![Gitter](https://badges.gitter.im/ruby-docx/community.svg)](https://gitter.im/ruby-docx/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)
+
 A ruby library/gem for interacting with `.docx` files. currently capabilities include reading paragraphs/bookmarks, inserting text at bookmarks, reading tables/rows/columns/cells and saving the document.
 
 ## Usage
 
 ### Prerequisites
 
-- Ruby 2.4 or later
+- Ruby 2.5 or later
 
 ### Install
 
@@ -47,6 +52,17 @@ doc.bookmarks.each_pair do |bookmark_name, bookmark_object|
 end
 ```
 
+Don't have a local file but a buffer? Docx handles those to:
+
+```ruby
+require 'docx'
+
+# Create a Docx::Document object from a remote file
+doc = Docx::Document.open(buffer)
+
+# Everything about reading is the same as shown above
+```
+
 ### Rendering html
 ``` ruby
 require 'docx'
@@ -118,6 +134,35 @@ end
 doc.save('example-edited.docx')
 ```
 
+### Writing to tables
+
+``` ruby
+require 'docx'
+
+# Create a Docx::Document object for our existing docx file
+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)
+
+  # Substitute text in each cell of this new row
+  new_row.cells.each do |cell|
+    cell.paragraphs.each do |paragraph|
+      paragraph.each_text_run do |text|
+        text.substitute('_placeholder_', 'replacement value')
+      end
+    end
+  end
+end
+
+doc.save('tables-edited.docx')
+```
+
 ### Advanced
 
 ``` ruby

data/lib/docx/containers/paragraph.rb

@@ -55,7 +55,7 @@ module Docx
 
         # Array of text runs contained within paragraph
         def text_runs
-          @node.xpath('w:r|w:hyperlink/w:r').map { |r_node| Containers::TextRun.new(r_node, @document_properties) }
+          @node.xpath('w:r|w:hyperlink').map { |r_node| Containers::TextRun.new(r_node, @document_properties) }
         end
 
         # Iterate over each text run within a paragraph

data/lib/docx/containers/text_run.rb

@@ -23,6 +23,8 @@ module Docx
         def initialize(node, document_properties = {})
           @node = node
           @text_nodes = @node.xpath('w:t').map {|t_node| Elements::Text.new(t_node) }
+          @text_nodes = @node.xpath('w:t|w:r/w:t').map {|t_node| Elements::Text.new(t_node) }
+
           @properties_tag = 'rPr'
           @text       = parse_text || ''
           @formatting = parse_formatting || DEFAULT_FORMATTING
@@ -74,6 +76,7 @@ module Docx
           # No need to be granular with font size down to the span level if it doesn't vary.
           styles['font-size'] = "#{font_size}pt" if font_size != @font_size 
           html = html_tag(:span, content: html, styles: styles) unless styles.empty?
+          html = html_tag(:a, content: html, attributes: {href: href, target: "_blank"}) if hyperlink?
           return html
         end
 
@@ -89,6 +92,18 @@ module Docx
           @formatting[:underline]
         end
 
+        def hyperlink?
+          @node.name == 'hyperlink'
+        end
+
+        def href
+          @document_properties[:hyperlinks][hyperlink_id]
+        end
+
+        def hyperlink_id
+          @node.attributes['id'].value
+        end        
+
         def font_size
           size_tag = @node.xpath('w:rPr//w:sz').first
           size_tag ? size_tag.attributes['val'].value.to_i / 2 : @font_size

data/lib/docx/document.rb

@@ -20,34 +20,41 @@ module Docx
   class Document
     attr_reader :xml, :doc, :zip, :styles
 
-    def initialize(path, &block)
+    def initialize(path_or_io, options = {})
       @replace = {}
-      @zip = Zip::File.open(path)
-      @document_xml = @zip.read('word/document.xml')
-      @doc = Nokogiri::XML(@document_xml)
-      @styles_xml = @zip.read('word/styles.xml')
-      @styles = Nokogiri::XML(@styles_xml)
-      if block_given?
-        yield self
-        @zip.close
+
+      # if path-or_io is string && does not contain a null byte
+      if (path_or_io.instance_of?(String) && !/\u0000/.match?(path_or_io))
+        @zip = Zip::File.open(path_or_io)
+      else
+        @zip = Zip::File.open_buffer(path_or_io)
       end
-    end
 
+      document = @zip.glob('word/document*.xml').first
+      raise Errno::ENOENT if document.nil?
+
+      @document_xml = document.get_input_stream.read
+      @doc = Nokogiri::XML(@document_xml)
+      load_styles
+      yield(self) if block_given?
+    ensure
+      @zip.close
+    end
 
     # This stores the current global document properties, for now
     def document_properties
       {
-        font_size: font_size
+        font_size: font_size,
+        hyperlinks: hyperlinks
       }
     end
 
-
     # With no associated block, Docx::Document.open is a synonym for Docx::Document.new. If the optional code block is given, it will be passed the opened +docx+ file as an argument and the Docx::Document oject will automatically be closed when the block terminates. The values of the block will be returned from Docx::Document.open.
     # call-seq:
     #   open(filepath) => file
     #   open(filepath) {|file| block } => obj
     def self.open(path, &block)
-      self.new(path, &block)
+      new(path, &block)
     end
 
     def paragraphs
@@ -55,11 +62,11 @@ module Docx
     end
 
     def bookmarks
-      bkmrks_hsh = Hash.new
+      bkmrks_hsh = {}
       bkmrks_ary = @doc.xpath('//w:bookmarkStart').map { |b_node| parse_bookmark_from b_node }
       # auto-generated by office 2010
-      bkmrks_ary.reject! {|b| b.name == "_GoBack" }
-      bkmrks_ary.each {|b| bkmrks_hsh[b.name] = b }
+      bkmrks_ary.reject! { |b| b.name == '_GoBack' }
+      bkmrks_ary.each { |b| bkmrks_hsh[b.name] = b }
       bkmrks_hsh
     end
 
@@ -70,10 +77,23 @@ module Docx
     # Some documents have this set, others don't.
     # Values are returned as half-points, so to get points, that's why it's divided by 2.
     def font_size
+      return nil unless @styles
+
       size_tag = @styles.xpath('//w:docDefaults//w:rPrDefault//w:rPr//w:sz').first
       size_tag ? size_tag.attributes['val'].value.to_i / 2 : nil
     end
 
+    # Hyperlink targets are extracted from the document.xml.rels file
+    def hyperlinks
+      hyperlink_relationships.each_with_object({}) do |rel, hash|
+        hash[rel.attributes['Id'].value] = rel.attributes['Target'].value
+      end
+    end
+
+    def hyperlink_relationships
+      @rels.xpath("//xmlns:Relationship[contains(@Type,'hyperlink')]")
+    end
+
     ##
     # *Deprecated*
     #
@@ -92,7 +112,7 @@ module Docx
 
     # Output entire document as a String HTML fragment
     def to_html
-      paragraphs.map(&:to_html).join('\n')
+      paragraphs.map(&:to_html).join("\n")
     end
 
     # Save document to provided path
@@ -103,6 +123,7 @@ module Docx
       Zip::OutputStream.open(path) do |out|
         zip.each do |entry|
           next unless entry.file?
+
           out.put_next_entry(entry.name)
 
           if @replace[entry.name]
@@ -115,7 +136,28 @@ module Docx
       zip.close
     end
 
-    alias_method :text, :to_s
+    # Output entire document as a StringIO object
+    def stream
+      update
+      stream = Zip::OutputStream.write_buffer do |out|
+        zip.each do |entry|
+          next unless entry.file?
+
+          out.put_next_entry(entry.name)
+
+          if @replace[entry.name]
+            out.write(@replace[entry.name])
+          else
+            out.write(zip.read(entry.name))
+          end
+        end
+      end
+
+      stream.rewind
+      stream
+    end
+
+    alias text to_s
 
     def replace_entry(entry_path, file_contents)
       @replace[entry_path] = file_contents
@@ -123,13 +165,30 @@ module Docx
 
     private
 
+    def load_styles
+      @styles_xml = @zip.read('word/styles.xml')
+      @styles = Nokogiri::XML(@styles_xml)
+      load_rels
+    rescue Errno::ENOENT => e
+      warn e.message
+      nil
+    end
+
+    def load_rels
+      rels_entry = @zip.glob('word/_rels/document*.xml.rels').first
+      raise Errno::ENOENT unless rels_entry
+
+      @rels_xml = rels_entry.get_input_stream.read
+      @rels = Nokogiri::XML(@rels_xml)
+    end
+
     #--
     # TODO: Flesh this out to be compatible with other files
     # TODO: Method to set flag on files that have been edited, probably by inserting something at the
     # end of methods that make edits?
     #++
     def update
-      replace_entry "word/document.xml", doc.serialize(:save_with => 0)
+      replace_entry 'word/document.xml', doc.serialize(save_with: 0)
     end
 
     # generate Elements::Containers::Paragraph from paragraph XML node

data/lib/docx/elements/bookmark.rb

@@ -5,7 +5,7 @@ module Docx
     class Bookmark
       include Element
       attr_accessor :name
-      
+
       def self.tag
         'bookmarkStart'
       end
@@ -17,14 +17,14 @@ module Docx
 
       # Insert text before bookmarkStart node
       def insert_text_before(text)
-        text_run = get_run_after
-        text_run.text = "#{text}#{text_run.text}"
+        text_run = get_run_before
+        text_run.text = "#{text_run.text}#{text}"
       end
 
       # Insert text after bookmarkStart node
       def insert_text_after(text)
-        text_run = get_run_before
-        text_run.text = "#{text_run.text}#{text}"
+        text_run = get_run_after
+        text_run.text = "#{text}#{text_run.text}"
       end
 
       # insert multiple lines starting with paragraph containing bookmark node.
@@ -51,7 +51,7 @@ module Docx
 
       # Get text run immediately prior to bookmark node
       def get_run_before
-        # at_xpath returns the first match found and preceding-sibling returns siblings in the 
+        # at_xpath returns the first match found and preceding-sibling returns siblings in the
         # order they appear in the document not the order as they appear when moving out from
         # the starting node
         if not (r_nodes = @node.xpath("./preceding-sibling::w:r")).empty?

data/lib/docx/elements/element.rb

@@ -65,8 +65,10 @@ module Docx
       def html_tag(name, options = {})
         content = options[:content]
         styles = options[:styles]
+        attributes = options[:attributes]
 
         html = "<#{name.to_s}"
+        
         unless styles.nil? || styles.empty?
           styles_array = []
           styles.each do |property, value|
@@ -74,6 +76,13 @@ module Docx
           end
           html << " style=\"#{styles_array.join('')}\""
         end
+        
+        unless attributes.nil? || attributes.empty?
+          attributes.each do |attr_name, attr_value|
+            html << " #{attr_name}=\"#{attr_value}\""
+          end
+        end
+        
         html << ">"
         html << content if content
         html << "</#{name.to_s}>"

data/lib/docx/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Docx #:nodoc:
-  VERSION = '0.4.0'
+  VERSION = '0.6.2'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: docx
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.6.2
 platform: ruby
 authors:
 - Christopher Hunt
@@ -9,10 +9,10 @@ authors:
 - Higgins Dragon
 - Toms Mikoss
 - Sebastian Wittenkamp
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-02-09 00:00:00.000000000 Z
+date: 2021-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -49,19 +49,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.0'
 - !ruby/object:Gem::Dependency
-  name: rspec
+  name: coveralls_reborn
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.7'
+        version: '0.21'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.7'
+        version: '0.21'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -76,6 +76,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.7'
 description: thin wrapper around rubyzip and nokogiri as a way to get started with
   docx files
 email:
@@ -106,7 +120,7 @@ homepage: https://github.com/chrahunt/docx
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -114,15 +128,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.4.0
+      version: 2.5.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.2
-signing_key: 
+rubygems_version: 3.1.6
+signing_key:
 specification_version: 4
 summary: a ruby library/gem for interacting with .docx files
 test_files: []