docx_manipulator 0.0.4 → 0.0.5

data/docx_manipulator.gemspec

@@ -22,4 +22,5 @@ Gem::Specification.new do |s|
   s.add_development_dependency "rspec"
   s.add_dependency "rubyzip"
   s.add_dependency "nokogiri"
+  s.add_dependency 'i18n'
 end

data/lib/docx_manipulator/content.rb

@@ -0,0 +1,27 @@
+require 'nokogiri'
+
+class DocxManipulator
+  class Content
+    def set(new_content, options = {})
+      @new_content = if new_content.kind_of?(File)
+                       new_content.read
+                     else
+                       new_content
+                     end
+      if options.include?(:xslt)
+        xslt = Nokogiri::XSLT.parse(options[:xslt])
+        data = Nokogiri::XML.parse(@new_content)
+        @new_content = xslt.transform(data).to_s
+      end
+    end
+
+    def writes_to_files
+      ['word/document.xml']
+    end
+
+    def process(output)
+      output.put_next_entry 'word/document.xml'
+      output.write @new_content
+    end
+  end
+end

data/lib/docx_manipulator/relationships.rb

@@ -0,0 +1,62 @@
+require 'i18n'
+require 'nokogiri'
+
+class DocxManipulator
+  class Relationships
+    def initialize(source)
+      @relationships = read_relationships(source)
+      @images = []
+      @binary_images = {}
+    end
+
+    def read_relationships(path)
+      content = ''
+      Zip::ZipFile.open(path) do |file|
+        content = file.read('word/_rels/document.xml.rels')
+      end
+      Nokogiri::XML.parse(content)
+    end
+    private :read_relationships
+
+    def add_image(id, path)
+      @images << path
+      add_node(id, I18n.transliterate(File.basename(path)))
+    end
+
+    def add_binary_image(id, name, data)
+      name = I18n.transliterate(name)
+      @binary_images[name] = data
+      add_node(id, name)
+    end
+
+    def add_node(id, name)
+      image_node = Nokogiri::XML::Node.new('Relationship', @relationships)
+      image_node['Id'] = id
+      image_node['Type'] = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image'
+      image_node['Target'] = "media/#{name}"
+      @relationships.root << image_node
+    end
+    private :add_node
+
+    def writes_to_files
+      ['word/_rels/document.xml.rels']
+    end
+
+    def process(output)
+      output.put_next_entry 'word/_rels/document.xml.rels'
+      output.write @relationships.to_s
+
+      @images.each do |path|
+        output.put_next_entry "word/media/#{I18n.transliterate(File.basename(path))}"
+        File.open(path) do |file|
+          IO.copy_stream file, output
+        end
+      end
+
+      @binary_images.each do |name, data|
+        output.put_next_entry "word/media/#{I18n.transliterate(name)}"
+        output.write data
+      end
+    end
+  end
+end

data/lib/docx_manipulator/version.rb

@@ -1,3 +1,3 @@
 class DocxManipulator
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

data/lib/docx_manipulator.rb

@@ -1,91 +1,46 @@
 require 'docx_manipulator/version'
-require 'nokogiri'
+require 'docx_manipulator/content'
+require 'docx_manipulator/relationships'
+
 require 'zip/zip'
 
 class DocxManipulator
 
-  attr_reader :source, :target, :new_content, :new_relationships
+  attr_reader :source, :target
 
   def initialize(source, target)
     @source = source
     @target = target
-    @new_relationships = source_relationships
-    @images = {}
-    @binary_images = {}
-  end
-
-  def source_content
-    content = ''
-    Zip::ZipFile.open(source) do |file|
-      content = file.read('word/document.xml')
-    end
-    content
-  end
 
-  def source_relationships
-    content = ''
-    Zip::ZipFile.open(source) do |file|
-      content = file.read('word/_rels/document.xml.rels')
-    end
-    Nokogiri::XML.parse(content)
+    @content = Content.new
+    @relationships = Relationships.new(source)
   end
 
   def content(new_content, options = {})
-    new_content_string = case new_content
-                         when File then new_content.read
-                         else new_content
-                         end
-    if options.include?(:xslt)
-      xslt = Nokogiri::XSLT.parse(options[:xslt])
-      data = Nokogiri::XML.parse(new_content_string)
-      @new_content = xslt.transform(data).to_s
-    else
-      @new_content = new_content_string
-    end
+    @content.set(new_content, options)
   end
 
   def add_image(id, path)
-    @images[id] = path
-    image_node = Nokogiri::XML::Node.new('Relationship', new_relationships)
-    image_node['Id'] = id
-    image_node['Type'] = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image'
-    image_node['Target'] = "media/#{File.basename(path)}"
-    new_relationships.root << image_node
+    @relationships.add_image(id, path)
   end
 
   def add_binary_image(id, name, data)
-    @binary_images[name] = data
-    image_node = Nokogiri::XML::Node.new('Relationship', new_relationships)
-    image_node['Id'] = id
-    image_node['Type'] = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships/image'
-    image_node['Target'] = "media/#{name}"
-    new_relationships.root << image_node
+    @relationships.add_binary_image(id, name, data)
   end
 
   def process
+    files_to_be_written = @content.writes_to_files + @relationships.writes_to_files
+
     Zip::ZipOutputStream.open(target) do |os|
       Zip::ZipFile.foreach(source) do |entry|
-        os.put_next_entry entry.name
-        if entry.name == 'word/document.xml'
-          os.write @new_content
-        elsif entry.name == 'word/_rels/document.xml.rels'
-          os.write new_relationships.to_s
-        elsif entry.file?
+        unless files_to_be_written.include?(entry.name)
+          os.put_next_entry entry.name
           os.write entry.get_input_stream.read
         end
       end
 
-      @images.each do |id, path|
-        os.put_next_entry "word/media/#{File.basename(path)}"
-        File.open(path) do |file|
-          IO.copy_stream file, os
-        end
-      end
-
-      @binary_images.each do |name, data|
-        os.put_next_entry "word/media/#{name}"
-        os.write data
-      end
+      @content.process(os)
+      @relationships.process(os)
     end
   end
 

data/spec/docx_manipulator_spec.rb

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 require 'docx_manipulator'
 require 'zip/zip'
 
@@ -5,13 +6,24 @@ describe DocxManipulator do
 
   subject { DocxManipulator.new('spec/files/movies.docx', 'spec/files/result.docx') }
 
-  describe "#source_content" do
-    it "returns the content of document.xml" do
-      subject.source_content.should =~ /w:document/
-    end
+  after :each do
+    File.delete('spec/files/result.docx') if File.exist?('spec/files/result.docx')
+  end
+
+  it "generates the resulting document" do
+    subject.process
+    File.should exist('spec/files/result.docx')
   end
 
-  describe "#content" do
+  context 'content' do
+    it "accepts a string" do
+      subject.content 'bla'
+      subject.process
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        file.get_input_stream('word/document.xml').read.should == 'bla'
+      end
+    end
+
     let(:xml_string) { <<-EOF
 <?xml version="1.0" encoding="UTF-8"?>
 <Movies>
@@ -31,82 +43,75 @@ EOF
 
     it "transforms the data file with an xslt file" do
       subject.content File.new('spec/files/data.xml'), :xslt => File.new('spec/files/document.xslt')
-      subject.new_content.should =~ /<w:t>The Departed<\/w:t>/
-      subject.new_content.should =~ /<w:t>The Pursuit of Happyness<\/w:t>/
+      subject.process
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        data = file.get_input_stream('word/document.xml').read
+        data.should =~ /<w:t>The Departed<\/w:t>/
+        data.should =~ /<w:t>The Pursuit of Happyness<\/w:t>/
+      end
     end
 
     it "transforms a string with an xslt file" do
       subject.content xml_string, :xslt => File.new('spec/files/document.xslt')
-      subject.new_content.should =~ /<w:t>The Departed<\/w:t>/
-      subject.new_content.should =~ /<w:t>The Pursuit of Happyness<\/w:t>/
+      subject.process
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        data = file.get_input_stream('word/document.xml').read
+        data.should =~ /<w:t>The Departed<\/w:t>/
+        data.should =~ /<w:t>The Pursuit of Happyness<\/w:t>/
+      end
     end
 
     it "accepts a string" do
       subject.content 'the new content'
-      subject.new_content.should == 'the new content'
+      subject.process
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        data = file.get_input_stream('word/document.xml').read
+        data.should == 'the new content'
+      end
     end
 
     it "accepts a file as input" do
       subject.content File.new('spec/files/content.txt')
-      subject.new_content.should == 'this is the new content of the document'
-    end
-  end
-
-  describe '#add_image' do
-    it 'adds an image to the relations file' do
-      subject.add_image 'rId9', 'path/to/image.jpg'
-      subject.new_relationships.to_s.should =~ /<Relationship Id="rId9" Type="http:\/\/schemas.openxmlformats.org\/officeDocument\/2006\/relationships\/image" Target="media\/image.jpg"\/>/
-    end
-  end
-
-  describe '#add_binary_image' do
-    let(:image) { File.new(File.join(File.dirname(__FILE__), 'files', 'duck.jpeg'), 'rb') }
-    it 'adds an image in binary format to the docx' do
-      data = image.read
-      subject.add_binary_image 'rId18', 'duck.jpeg', data
-      subject.new_relationships.to_s.should =~ /<Relationship Id="rId18" Type="http:\/\/schemas.openxmlformats.org\/officeDocument\/2006\/relationships\/image" Target="media\/duck.jpeg"\/>/
       subject.process
-
       Zip::ZipFile.open('spec/files/result.docx') do |file|
-        file.read('word/media/duck.jpeg').should == data
+        data = file.get_input_stream('word/document.xml').read
+        data.should == 'this is the new content of the document'
       end
     end
   end
 
-  describe "#process" do
-    after :each do
-      File.delete 'spec/files/result.docx'
-    end
-
-    it "generates the resulting document" do
+  context 'with an image' do
+    it 'adds an image' do
+      subject.add_image 'rId19', 'spec/files/duck.jpeg'
       subject.process
-      File.should exist('spec/files/result.docx')
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        content = Nokogiri::XML.parse(file.get_input_stream('word/_rels/document.xml.rels').read)
+        content.xpath('//r:Relationship[@Id="rId19"]', 'r' => 'http://schemas.openxmlformats.org/package/2006/relationships').first['Target'].should == 'media/duck.jpeg'
+        file.find_entry('word/media/duck.jpeg').should_not be_nil
+      end
     end
 
-    it "replaces the content of the document" do
-      subject.content 'bla'
+    it 'adds an image as binary data' do
+      file = File.new(File.join(File.dirname(__FILE__), 'files', 'duck.jpeg'), 'rb')
+      data = file.read
+      subject.add_binary_image 'rId19', 'duck.jpeg', data
       subject.process
       Zip::ZipFile.open('spec/files/result.docx') do |file|
-        file.get_input_stream('word/document.xml').read.should == 'bla'
+        content = Nokogiri::XML.parse(file.get_input_stream('word/_rels/document.xml.rels').read)
+        content.xpath('//r:Relationship[@Id="rId19"]', 'r' => 'http://schemas.openxmlformats.org/package/2006/relationships').first['Target'].should == 'media/duck.jpeg'
+        file.read('word/media/duck.jpeg').should == data
       end
     end
 
-    context 'with an image' do
-      it 'replaces the relations file' do
-        subject.add_image 'rId19', 'spec/files/duck.jpeg'
-        subject.process
-        Zip::ZipFile.open('spec/files/result.docx') do |file|
-          content = Nokogiri::XML.parse(file.get_input_stream('word/_rels/document.xml.rels').read)
-          content.xpath('//r:Relationship[@Id="rId19"]', 'r' => 'http://schemas.openxmlformats.org/package/2006/relationships').first['Target'].should == 'media/duck.jpeg'
-        end
-      end
-
-      it 'adds the image to the resulting file' do
-        subject.add_image 'rId19', 'spec/files/duck.jpeg'
-        subject.process
-        Zip::ZipFile.open('spec/files/result.docx') do |file|
-          file.find_entry('word/media/duck.jpeg').should_not be_nil
-        end
+    it 'transliterates the image name' do
+      file = File.new(File.join(File.dirname(__FILE__), 'files', 'duck.jpeg'), 'rb')
+      data = file.read
+      subject.add_binary_image 'rId19', 'dück.jpeg', data
+      subject.process
+      Zip::ZipFile.open('spec/files/result.docx') do |file|
+        content = Nokogiri::XML.parse(file.get_input_stream('word/_rels/document.xml.rels').read)
+        content.xpath('//r:Relationship[@Id="rId19"]', 'r' => 'http://schemas.openxmlformats.org/package/2006/relationships').first['Target'].should == 'media/duck.jpeg'
+        file.find_entry('word/media/duck.jpeg').should_not be_nil
       end
     end
   end

metadata

@@ -2,7 +2,7 @@
 name: docx_manipulator
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.0.4
+  version: 0.0.5
 platform: ruby
 authors: 
 - "Michael St\xC3\xA4mpfli"
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2012-04-03 00:00:00 Z
+date: 2012-04-19 00:00:00 Z
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: rspec
@@ -45,6 +45,17 @@ dependencies:
         version: "0"
   type: :runtime
   version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: i18n
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+  type: :runtime
+  version_requirements: *id004
 description: This Gem enables you to modify the contents of docx files.
 email: 
 - michael.staempfli@gmail.com
@@ -62,6 +73,8 @@ files:
 - Rakefile
 - docx_manipulator.gemspec
 - lib/docx_manipulator.rb
+- lib/docx_manipulator/content.rb
+- lib/docx_manipulator/relationships.rb
 - lib/docx_manipulator/version.rb
 - spec/docx_manipulator_spec.rb
 - spec/files/content.txt