open_xml 0.0.2 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ece1bea9f9256c7d83cdb1394600d707c9d90231
-  data.tar.gz: d4114902905037b7bb784e628edfcd4fc09e01f6
+  metadata.gz: b75c6c22557762c26b167295be1afa1e6598abc1
+  data.tar.gz: e149a88a547038884e322ddb66f5dea018591027
 SHA512:
-  metadata.gz: 482b6c85019fd035aab63bc487281fdc0b750b076abe758fa4a9cd4f34aa90d7de1b8d8e88c0a2b453ea84cc433c65c5a271a4a897e4ea34a7f1efee76724109
-  data.tar.gz: b3ac90b31711f61e0a83ed819a3d9fceab806a914a6481bfaf938acf4326daefd24cf1f4d91517d1b5bd779a0fad0bb47e9120fdb03c3e82c52245fa3eb8fcdd
+  metadata.gz: 071829499a303aeeb9d536e1ee07d8f1f9537b207fd17352a5a350cae341a8c97d715a8d5b88e39542f2cb04f65386804f7803c91f1e0696ee2257a181a86ed6
+  data.tar.gz: f76afcba14892b117bbcf1ff0d2d03da1ff029e046bd3a1952c690432aa4a423c774719ae92fa3e5df2256cffcb7ef7e72095e948175bec3e4d733c7257873cf

data/.gitignore

@@ -15,3 +15,4 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+.DS_Store

data/CHANGELOG.md

@@ -1,3 +1,8 @@
-## v0.0.1
+## v0.1.0
+* API Change!!! the template document is now created once and the data
+is passed in through the process call. This allows you to loop over
+lots of data and generate documents without having to instatiate a new
+template document object.
 
+## v0.0.1
 * initial release

data/README.md

@@ -1,7 +1,7 @@
 OpenXml
 ========
 
-Library for reading and writing to open xml documents (*but at the moment you can generate word docs from a template*)
+A ruby library for generating word documents that can handle basic html and images too.
 
 ## Installation
 
@@ -17,27 +17,41 @@ Or install it yourself as:
 
     $ gem install open_xml
 
-   
+
 ## Usage
 Provide a path to a docx with the text **[SUPERPOWER]** placed anywhere.
 
 ```ruby
 require 'open_xml'
 
-doc = OpenXml::TemplateDocument.new(path: "[path to template]", data: {"[SUPERPOWER]" => "Bug Fixing!!!!"})
-doc.process
-  
+doc = OpenXml::TemplateDocument.new(path: "[path to template]")
+doc.process({"[SUPERPOWER]" => {text: "Bug Fixing!!!!"}})
+
 IO.write "./powers.docx", doc.to_zip_buffer.string
 ```
 
+HTML content
+
+```ruby
+doc = OpenXml::TemplateDocument.new(path: "[path to template]")
+doc.process({"[SUPERPOWER]" => {text: "<h1>Bug Fixing!!!!</h1>", html: true}})
+```
+
+HTML with images
+
+```ruby
+doc = OpenXml::TemplateDocument.new(path: "[path to template]")
+doc.process({"[SUPERPOWER]" => {text: "<img src='/powers.png' />", html: true, images: {'/powers.png' => "[Base64 encoded image]"}}})
+```
+
 ## Todo
   * ~~Implement reading and writing the word zip files~~
   * ~~Create a template word document with formatted key words (bold, 14pt).~~
   * ~~Replace the key words with the supplied plain text content but maintain all the formatting.~~
   * ~~Handle replacing a key with multiple content~~
   * ~~Extract these features into a gem~~
-  * Format html content for wordprocessingML e.x. bold, italic,
-    underline
+  * ~~Format html content for wordprocessingML e.x. bold, italic,
+    underline and handle images~~
 
 ## Contributing
 

data/lib/open_xml/template_document.rb

@@ -2,49 +2,149 @@ require 'zip'
 require 'nokogiri'
 
 module OpenXml
-
-
   class TemplateDocument
-    attr_reader :template_path, :parts, :data
+    attr_reader :template_path, :parts
 
     def initialize(options)
-      @template_path = options[:path]
+      @template_path = options.fetch(:path)
       @parts = {}
-      @data = options[:data]
-      split_parts
+
+      read_files
     end
 
     def to_zip_buffer
       Zip::OutputStream.write_buffer do |w|
-        parts.each do |k, v|
-          w.put_next_entry k
-          w.write v
+        parts.each do |key, value|
+          w.put_next_entry key
+          w.write value
         end
       end
     end
 
-    def process
-      doc = Nokogiri::XML(parts["word/document.xml"])
-      doc.xpath("//w:t").each do |node|
-        data.each do |k, v|
-          node.content = node.content.gsub(k, Array(v).join("\n")) if node.content[/#{k}/]
+    def process(data)
+      @parts = @parts_cache.clone
+      register_type 'message/rfc822', 'mht'
+
+      doc = Nokogiri::XML(parts['word/document.xml'])
+      doc.xpath('//w:t').each do |node|
+        data.each do |key, value|
+
+          if node.content[/#{key}/]
+            process_plain_text(node, key, value, doc) unless value[:html]
+            process_html(node, key, value, doc) if value[:html]
+          end
+
         end
       end
 
-      parts["word/document.xml"] = doc.to_xml
+      parts['word/document.xml'] = flatten_xml doc
     end
 
     private
 
-    def split_parts
+    def process_plain_text(node, key, value, doc)
+      values = Array(value[:text])
+
+      if values.size > 1
+        values.each do |v|
+          br = Nokogiri::XML::Node.new 'w:br', doc
+          n = Nokogiri::XML::Node.new 'w:t', doc
+
+          n.content = v.to_s
+
+          node.parent << n
+          node.parent << br
+        end
+
+        node.remove
+      else
+        node.content = node.content.gsub(key, values.first.to_s) if values.first
+      end
+    end
+
+    def process_html(node, key, value, doc)
+      new_node = create_chunk_file(key, value, doc)
+      node.parent.parent.add_next_sibling new_node
+      node.remove
+    end
+
+    def create_chunk_file(key, content, doc)
+      id = key
+
+      parts["word/#{id}.mht"] = build_mht(content)
+      add_relation id
+
+      chunk = Nokogiri::XML::Node.new 'w:altChunk', doc
+      chunk['r:id'] = id
+      chunk
+    end
+
+    def add_relation(id)
+      relationships = Nokogiri::XML(parts['word/_rels/document.xml.rels'])
+      rel = Nokogiri::XML::Node.new 'Relationship', relationships
+      rel['Id'] = id
+      rel['Type'] = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk'
+      rel['Target'] = "/word/#{id}.mht"
+
+      relationships.at_xpath('//xmlns:Relationships') << rel
+      parts['word/_rels/document.xml.rels'] = flatten_xml relationships
+    end
+
+    def register_type(type, extension)
+      content = Nokogiri::XML(parts['[Content_Types].xml'])
+      node = Nokogiri::XML::Node.new 'Default', content
+      node['ContentType'] = type
+      node['Extension'] = extension
+
+      content.at_xpath('//xmlns:Default').add_next_sibling node
+      parts['[Content_Types].xml'] = flatten_xml content
+    end
+
+    def flatten_xml(doc)
+      doc.to_xml(indent: 0).gsub("\n","")
+    end
+
+    def read_files
       Zip::File.new(template_path).each do |f|
         parts[f.name] = f.get_input_stream.read
       end
 
-      parts
+      @parts_cache = parts.clone
     end
 
+    def build_mht(content)
+      message =<<MESSAGE
+MIME-Version: 1.0
+Content-Type: multipart/related; boundary=MY-SEPARATOR
+
+--MY-SEPARATOR
+Content-Type: text/html; charset=utf-8
+Content-Transfer-Encoding: 8bit
+
+#{content[:text]}
+
+MESSAGE
 
-  end
 
+      content.fetch(:images){{}}.each do |key, value|
+        message << img_template(key, value)
+      end
+
+      message << "\n--MY-SEPARATOR--"
+      message
+    end
+
+    def img_template(key, value)
+      <<IMG
+
+--MY-SEPARATOR
+Content-Location: #{key}
+Content-Transfer-Encoding: Base64
+
+#{value}
+
+IMG
+    end
+
+  end
 end

data/lib/open_xml/version.rb

@@ -1,3 +1,3 @@
 module OpenXml
-  VERSION = "0.0.2"
+  VERSION = '0.1.0'
 end

data/lib/open_xml.rb

@@ -1,2 +1,2 @@
-require 'open_xml/version'
 require_relative 'open_xml/template_document'
+require_relative 'open_xml/version'

data/open_xml.gemspec

@@ -8,8 +8,8 @@ Gem::Specification.new do |spec|
   spec.version       = OpenXml::VERSION
   spec.authors       = ["Carlos Espejo"]
   spec.email         = ["carlosespejo@gmail.com"]
-  spec.description   = %q{Currently you can only generate word documents from a template word document.}
-  spec.summary       = %q{Library for reading and writing to open xml documents (*but at the moment you can generate word docs from a template*)}
+  spec.description   = %q{Generate Word documents from a template, also handle html and images too.}
+  spec.summary       = %q{A ruby library for generating word documents that can handle basic html and images too.}
   spec.homepage      = "https://github.com/CarlosEspejo/open_xml"
   spec.license       = "MIT"
 

data/spec/alternate_chunk_spec.rb

@@ -0,0 +1,43 @@
+require 'spec_helper'
+require 'base64'
+
+describe "Adding HTML and Images through the alternate chunk feature" do
+
+  let(:report_path){"#{File.expand_path('samples', __dir__)}/report.docx"}
+  let(:encoded_img){Base64.encode64(File.read("#{File.expand_path('samples', __dir__)}/caterpillar.jpg"))}
+
+  let(:t){TemplateDocument.new(path: report_path)}
+
+  it "should register MIME html type" do
+    t.process 'my_content' => {text: 'empty', html: true}
+    doc = Nokogiri::XML(t.parts['[Content_Types].xml'])
+    doc.xpath('//xmlns:Default/@ContentType').map(&:value).must_include 'message/rfc822'
+  end
+
+  it "should add the chunk id to the rels file" do
+    t.process 'my_content' => {text: 'empty', html: true}
+    doc = Nokogiri::XML(t.parts['word/_rels/document.xml.rels'])
+    doc.xpath('//xmlns:Relationship/@Id').map(&:value).must_include 'my_content'
+  end
+
+  it "should generate MIME html file" do
+    t.process 'my_content' => {text: '<u>This is underlined</u>', html: true}
+    t.parts['word/my_content.mht'].must_match(/#{'<u>This is underlined</u>'}/)
+  end
+
+  it "should generate MIME html file with a image" do
+    content = '<h1>Look at the image</h1><img src="./image.jpg" />'
+
+    t.process 'my_content' => {text: content, html: true, images: {"./image.jpg" => encoded_img}}
+    t.parts['word/my_content.mht'].must_match(/#{'Content-Location: ./image.jpg'}/)
+  end
+
+  it "should geneate MIME html file with multiple images" do
+    content = '<h1>Look at the images</h1>'
+    content << '<img src="/image.jpg" /><br/><br/><img src="/image2.jpg" />'
+    t.process 'my_content' => {text: content, html: true, images: {"/image.jpg" => encoded_img, '/image2.jpg' => encoded_img}}
+    t.parts['word/my_content.mht'].must_match(/#{'Content-Location: /image.jpg'}/)
+    t.parts['word/my_content.mht'].must_match(/#{'Content-Location: /image2.jpg'}/)
+  end
+
+end

data/spec/spec_helper.rb

@@ -1,6 +1,6 @@
 require 'minitest/autorun'
 require 'minitest/pride'
-require 'open_xml'
+require_relative '../lib/open_xml'
 require 'pry'
 
 include OpenXml

data/spec/template_document_spec.rb

@@ -1,17 +1,20 @@
 require 'spec_helper'
 require 'tempfile'
 require 'nokogiri'
+require 'pry'
 
 describe TemplateDocument do
 
-  it "should read the template file and split it into parts" do
-    t = TemplateDocument.new(path: template_path)
-    t.parts.keys.must_equal template_parts.keys
+  let(:template_path){"#{File.expand_path('samples', File.dirname(__FILE__))}/template_sample.docx"}
+  let(:report_path){"#{File.expand_path('samples', File.dirname(__FILE__))}/report.docx"}
 
+  it 'should read the template file and split it into parts' do
+    t = TemplateDocument.new(path: template_path)
+    t.parts.keys.must_include 'word/document.xml'
   end
 
-  it "should create a new file from the template parts" do
-    t = Tempfile.new(['output','.docx'])
+  it 'should create a new file from the template parts' do
+    t = Tempfile.new(['output', '.docx'])
 
     temp_doc = TemplateDocument.new(path: template_path)
 
@@ -23,56 +26,48 @@ describe TemplateDocument do
 
   end
 
-  it "should replace key words in the document xml" do
-    temp = Tempfile.new(['output','.docx'])
-
-    t = TemplateDocument.new(path: template_path, data: {"[NAME]" => "<b>Carlos</b>", "[AGE]" => 30 })
-    t.process
-    IO.write temp.path, t.to_zip_buffer.string
-
-    processed = TemplateDocument.new(path: temp.path)
-    doc = Nokogiri::XML(processed.parts["word/document.xml"])
+  it 'should replace key words in the document xml' do
+    t = TemplateDocument.new(path: template_path)
+    t.process({ 'person_name' => {text: '<b>Carlos</b>'}, 'person_age' => {text: 30} })
+    doc = Nokogiri::XML(t.parts['word/document.xml'])
 
-    doc.xpath('//w:t').text[/\[NAME\]/].must_be_nil
-    doc.xpath('//w:t').text[/\[AGE\]/].must_be_nil
+    text = doc.xpath('//w:t').text
+    text[/Carlos/].wont_be_nil
+    text[/30/].wont_be_nil
   end
 
-  it "should replace one key word with many items" do
+  it 'should replace one key word with many items' do
     data = {
-      "[LIST]" => [
-                    "list 1",
-                    "list 2",
-                    "list 3",
-                    "list 4",
-                    "list 5"
-                  ]
+      'my_list' => {text: [
+                    'list 1',
+                    'list 2',
+                    'list 3',
+                    'list 4',
+                    'list 5'
+                  ]}
     }
 
-    t = TemplateDocument.new(path: template_path, data: data)
-    t.process
-    doc = Nokogiri::XML(t.parts["word/document.xml"])
+    t = TemplateDocument.new(path: template_path)
+    t.process(data)
+
+    doc = Nokogiri::XML(t.parts['word/document.xml'])
 
     text = doc.xpath('//w:t').text
 
-    text[/list 1\nlist 2/].wont_be_nil
+    text[/list 2/].wont_be_nil
   end
 
-  let(:template_path){"#{File.expand_path('samples', File.dirname(__FILE__))}/template_sample.docx"}
+  it "should cache the template document" do
+    t = TemplateDocument.new(path: template_path)
+    t.process({'person_name' => {text: 'steve'}})
+    doc = Nokogiri::XML(t.parts['word/document.xml'])
 
-  let(:template_parts) do
-    {
-      "_rels/.rels" => '',
-      "docProps/core.xml" => '',
-      "docProps/app.xml" => '',
-      "word/document.xml" => '',
-      "word/styles.xml" => '',
-      "word/fontTable.xml" => '',
-      "word/header.xml" => '',
-      "word/footer.xml" => '',
-      "word/settings.xml" => '',
-      "word/_rels/document.xml.rels" => '',
-      "[Content_Types].xml" => ''
-    }
+    doc.text[/steve/].wont_be_nil
+
+    t.process({'person_name' => {text: 'carlos'}})
+    doc = Nokogiri::XML(t.parts['word/document.xml'])
+
+    doc.text[/carlos/].wont_be_nil
   end
 
 end

metadata

@@ -1,107 +1,108 @@
 --- !ruby/object:Gem::Specification
 name: open_xml
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors:
 - Carlos Espejo
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-04 00:00:00.000000000 Z
+date: 2014-06-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.1'
-description: Currently you can only generate word documents from a template word document.
+description: Generate Word documents from a template, also handle html and images
+  too.
 email:
 - carlosespejo@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - CHANGELOG.md
 - Gemfile
 - LICENSE
@@ -111,6 +112,10 @@ files:
 - lib/open_xml/template_document.rb
 - lib/open_xml/version.rb
 - open_xml.gemspec
+- spec/.DS_Store
+- spec/alternate_chunk_spec.rb
+- spec/samples/caterpillar.jpg
+- spec/samples/report.docx
 - spec/samples/template_sample.docx
 - spec/spec_helper.rb
 - spec/template_document_spec.rb
@@ -124,22 +129,26 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.1.11
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
-summary: Library for reading and writing to open xml documents (*but at the moment
-  you can generate word docs from a template*)
+summary: A ruby library for generating word documents that can handle basic html and
+  images too.
 test_files:
+- spec/.DS_Store
+- spec/alternate_chunk_spec.rb
+- spec/samples/caterpillar.jpg
+- spec/samples/report.docx
 - spec/samples/template_sample.docx
 - spec/spec_helper.rb
 - spec/template_document_spec.rb