officedoc 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 433f8b39a4a7ce8011fe06a166effeb910d6947f
-  data.tar.gz: 5823ce66d151beb15391e2a88a5aab8ca47fed35
+  metadata.gz: 34b7c7a92fb76a9d7393592087ba378fd022f018
+  data.tar.gz: ca9f2361b0e48c95e29667e26dfb126bc2888d66
 SHA512:
-  metadata.gz: 48541c809c57543bd7d07042656861ebbba1fab06b5a2675bd1b33961dc59f14684b6c9040e550f9668bf9144551f49e4dee7756dac8adbcfa8ab1891cbd6b2a
-  data.tar.gz: 1e972f0acbe8eefa166810443a2d4e684a8bb933abda97b1832677f3f2995ee360895a294cefdea112c7c4be87de8b214dcfe78e1c462b757d3f4bd960dce7fc
+  metadata.gz: 910f8dbfd5118d44fe66365cd3b17fc1c05d4db582ac573b36efd02ae9cb49c7781aef961e407b707f596637b339b359701cec21d357010e470dcf4c26992b64
+  data.tar.gz: a40568de299d516f11f2f176d32e26d1c07ab07ee21ee8cc68023049c3ab7c209556425f2a6a4d8d0e83b60639e6314fa0a75f8c575bc94a4b5a9a1610203533

data/.gitattributes

@@ -0,0 +1,10 @@
+*.docx binary
+*.doc binary
+*.xlsx binary
+*.xls binary
+*.pptx binary
+*.ppt binary
+*.odt binary
+*.odp binary
+*.ods binary
+*.odg binary

data/.gitignore

@@ -20,3 +20,4 @@ tmp
 *.o
 *.a
 mkmf.log
+**/.DS_Store

data/.rspec

@@ -0,0 +1 @@
+--color

data/.travis.yml

@@ -1,3 +1,6 @@
+branches:
+  only:
+    - master
 language: ruby
 rvm:
   - 2.1.0
@@ -5,3 +8,4 @@ rvm:
 env:
   global:
     secure: DzmZmBdrv+tIRNXyqAE1Z7/ksQOmBUThgpeKH2in2vzTZ8q5YAzeQat8YLTW+Z2UcIT7hQMUb+W11rUfPmDCBfcJFn5NaXNowoyHz+CeqJ5XjZtA05o96/8zu6wdh/3d8xfON703SgE7vFGOj3klIqVoBl2ABbk/p2A3sbS7mHs=
+script: bundle exec rspec

data/README.md

@@ -1,12 +1,16 @@
 # Officedoc
 
+[![Gem Version](https://badge.fury.io/rb/officedoc.svg)](http://badge.fury.io/rb/officedoc)
 [![GitHub version](https://badge.fury.io/gh/moonfly%2Fofficedoc.svg)](http://badge.fury.io/gh/moonfly%2Fofficedoc)
 [![Build Status](https://travis-ci.org/moonfly/officedoc.svg?branch=master)](https://travis-ci.org/moonfly/officedoc)
 [![Code Climate](https://codeclimate.com/github/moonfly/officedoc.png)](https://codeclimate.com/github/moonfly/officedoc)
+[![Code Coverage](https://codeclimate.com/github/moonfly/officedoc/coverage.png)](https://codeclimate.com/github/moonfly/officedoc)
 [![Dependency Status](https://gemnasium.com/moonfly/officedoc.svg)](https://gemnasium.com/moonfly/officedoc)
 
 Parsing and constructing documents using XML-based Office formats: ODF and OOXML.
 
+NOT FOR PUBLIC USE YET. ACTIVE INITIAL DEVELOPMENT IN PROGRESS.
+
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -49,11 +53,13 @@ Semantic versioning (http://semver.org/spec/v2.0.0.html) is used.
 For a version number MAJOR.MINOR.PATCH, unless MAJOR is 0:
 
 1. MAJOR version is incremented when incompatible API changes are made,
-2. MINOR version is incremented when functionality is added in a backwards-compatible manner, and
+2. MINOR version is incremented when functionality is added in a backwards-compatible manner, 
 3. PATCH version is incremented when backwards-compatible bug fixes are made.
 
-Major version zero (0.y.z) is for initial development. Anything may change at any time. 
-The public API should not be considered stable.
+Major version "zero" (0.y.z) is for initial development. Anything may change at any time. 
+The public API should not be considered stable. 
+Furthermore, version "double-zero" (0.0.x) is not intended for public use, 
+as even minimal functionality is not guaranteed to be implemented yet.
 
 ## Dependencies
 

data/lib/officedoc.rb

@@ -1,5 +1,9 @@
 require "officedoc/version"
+require "officedoc/null_object"
+require "officedoc/package"
 
 module Officedoc
-  # Your code goes here...
+  def self.open(*args)
+    Officedoc::Package.new(*args)
+  end
 end

data/lib/officedoc/null_object.rb

@@ -0,0 +1,12 @@
+require "naught"
+
+module Officedoc
+  private 
+    NullObject = Naught.build do |config|
+      config.black_hole
+      config.traceable
+    end
+    def self.null
+      NullObject.get
+    end
+end

data/lib/officedoc/package.rb

@@ -0,0 +1,20 @@
+require "officedoc/package/raw"
+
+module Officedoc
+  class Package
+
+    include NullObject::Conversions
+
+    attr_accessor :filename
+    attr_reader :raw
+
+    def initialize( filename: Officedoc.null, stream: Officedoc.null )
+      @filename = filename
+      unless Actual(stream)
+        stream = open( filename, "rb" ) if Actual(filename)
+      end
+      @raw = Raw.new( stream )
+    end
+
+  end
+end

data/lib/officedoc/package/raw.rb

@@ -0,0 +1,37 @@
+require "officedoc/package/raw/ruby_zip_engine"
+require "officedoc/package/raw/parts"
+
+module Officedoc
+  class Package
+    class Raw
+      attr_reader :zip_engine
+      attr_reader :stream
+      
+      def initialize( stream, zip_engine: ::Officedoc::Package::Raw::RubyZipEngine )
+        @zip_engine = zip_engine
+        @stream = stream
+      end
+      private def zip_file
+        @zip_file ||= zip_engine.new(stream)
+      end
+
+      def file_names
+        zip_file.entries.map(&:name)
+      end
+      def parts
+        @parts ||= PartList.new zip_file
+      end
+      def document_type
+        @document_type ||= get_document_type
+      end
+      private def get_document_type
+        # Example: "application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"
+        main_doc_parts = parts.of_type "document.main+xml", partial: true
+        return "" if main_doc_parts.size != 1
+      
+        match = /.*\.(.*)\.document\.main\+xml/.match(main_doc_parts[0].type)
+        match ? match[1] : ""
+      end
+    end
+  end
+end

data/lib/officedoc/package/raw/parts.rb

@@ -0,0 +1,65 @@
+require "nokogiri"
+require "officedoc/package/raw/ruby_zip_engine"
+
+module Officedoc
+  class Package
+    class Raw
+      class Part
+        attr_reader :name
+        attr_reader :type
+        
+        def initialize(zip_file,xml_node)
+          @name = xml_node["PartName"]
+          @type = xml_node["ContentType"]
+          @zip_file = zip_file
+        end
+        private def file_name
+          name[1..-1]
+        end
+        
+        def read_stream(&block)
+          @zip_file.entry_read_stream(file_name,&block)
+        end
+      end
+    end
+  end
+end
+
+module Officedoc
+  class Package
+    class Raw
+      class PartList < SimpleDelegator
+        EntryName = '[Content_Types].xml'
+        
+        def initialize(zip_file)
+          __setobj__([])
+          @zip_file = zip_file
+          read_from zip_file if zip_file
+          yield self if block_given?
+        end
+        
+        def read_from(zip_file)
+          zip_file.entry_read_stream( EntryName ) do |stream| 
+            doc = Nokogiri::XML(stream)
+            doc.css("Override[@PartName]").each do |node|
+              push Officedoc::Package::Raw::Part.new @zip_file, node
+            end
+          end
+        end
+        
+        def of_type( type, regexp: false, partial: false )
+          select do |part| 
+            if regexp 
+              part.type.match(type)
+            elsif partial
+              part.type.include?(type)
+            else
+              part.type == type
+            end
+          end
+        end
+
+      end
+    end
+  end
+end

data/lib/officedoc/package/raw/ruby_zip_engine.rb

@@ -0,0 +1,36 @@
+# Engine for RubyZip gem
+require "zip"
+
+module Officedoc
+  class Package
+    class Raw
+      class RubyZipEngine
+        def initialize(stream)
+          @f = ::Zip::File.new(stream, true, true)
+          @f.read_from_stream(stream)
+        end
+        
+        def entries
+          @entries ||= get_entries
+        end
+        def entry(name)
+          @entries_by_name ||= {}
+          @entries_by_name.fetch(name) { get_entry(name) }
+        end
+        def entry_read_stream(name,&block)
+          entry(name).get_input_stream(&block)
+        end
+
+        private def get_entries
+          entries = []
+          @f.each { |entry| entries << entry }
+          entries
+        end
+        private def get_entry(name)
+          entries.find { |entry| entry.name == name } || Officedoc.null
+        end
+      end
+    end
+  end
+end
+

data/lib/officedoc/version.rb

@@ -1,3 +1,3 @@
 module Officedoc
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/officedoc.gemspec

@@ -5,22 +5,27 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'officedoc/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "officedoc"
-  spec.version       = Officedoc::VERSION
-  spec.authors       = ["Andrey Pronin"]
-  spec.email         = ["moonfly.msk@gmail.com"]
-  spec.summary       = %q{Parsing and constructing ODF and OOXML documents}
-  spec.description   = %q{Parsing and constructing documents using XML-based Office formats: ODF and OOXML.}
-  spec.homepage      = "https://github.com/moonfly/officedoc"
-  spec.license       = "GPL-3"
+  spec.name                   = "officedoc"
+  spec.version                = Officedoc::VERSION
+  spec.required_ruby_version  = '>= 2.1.0'
+  spec.authors                = ["Andrey Pronin"]
+  spec.email                  = ["moonfly.msk@gmail.com"]
+  spec.summary                = %q{Parsing and constructing ODF and OOXML documents}
+  spec.description            = %q{Parsing and constructing documents using XML-based Office formats: ODF and OOXML.}
+  spec.homepage               = "https://github.com/moonfly/officedoc"
+  spec.license                = "GPL-3"
 
-  spec.files         = `git ls-files -z`.split("\x0")
-  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
-  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
-  spec.require_paths = ["lib"]
-
-  spec.add_development_dependency "bundler", "~> 1.6"
-  spec.add_development_dependency "rake"
+  spec.files                  = `git ls-files -z`.split("\x0")
+  spec.executables            = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files             = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths          = ["lib"]
+  
+  spec.add_runtime_dependency     "naught", "~> 1.0"
+  spec.add_runtime_dependency     "rubyzip", "~> 1.1"
+  spec.add_runtime_dependency     "nokogiri", "~> 1.6"
+  
+  spec.add_development_dependency "bundler", ">= 1.5"
+  spec.add_development_dependency "rake", "~> 10.2"
   spec.add_development_dependency "rspec", "~> 3.0.0.beta2"
-  spec.add_development_dependency "codeclimate-test-reporter"
+  spec.add_development_dependency "codeclimate-test-reporter", "~> 0.3.0"
 end

data/spec/classes/package/raw/part_spec.rb

@@ -0,0 +1,4 @@
+require 'spec_helper'
+
+describe "Officedoc::Package::Raw::Part" do
+end

data/spec/classes/package/raw_spec.rb

@@ -0,0 +1,40 @@
+require "spec_helper"
+
+describe "Officedoc::Package::Raw" do
+  def new_raw_for_file(name)
+    Officedoc::Package::Raw.new( file_stream(name) )
+  end
+  
+  let(:raw_docx_sample_filename) { "samples/sample1.docx" }
+  let(:raw_docx_sample) { new_raw_for_file raw_docx_sample_filename }
+
+  it "should correctly count the number of files in package" do
+    expect(raw_docx_sample.file_names.count).to eq(count_files_in_zip raw_docx_sample_filename)
+  end
+  it "should correctly list the files in package" do
+    expect(raw_docx_sample.file_names).to match_array(list_files_in_zip raw_docx_sample_filename)
+  end
+  
+  it "should list the parts" do
+    expect(raw_docx_sample.parts.count).to be > 0
+
+    expect(raw_docx_sample.parts.map(&:name)).to include "/word/document.xml"
+    expect(raw_docx_sample.parts.map(&:name)).to include "/docProps/core.xml"
+    
+    expect(raw_docx_sample.parts.map(&:type)).to include "application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"
+    expect(raw_docx_sample.parts.map(&:type)).to include "application/vnd.openxmlformats-package.core-properties+xml"
+  end
+  it "should find the part by full type" do
+    parts = raw_docx_sample.parts.of_type "application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"
+    expect(parts.size).to eq 1
+    expect(parts[0].name).to eq "/word/document.xml"
+  end
+  it "should find the part by partial type" do
+    parts = raw_docx_sample.parts.of_type "wordprocessingml.document.main", partial: true
+    expect(parts.size).to eq 1
+    expect(parts[0].name).to eq "/word/document.xml"
+  end
+  it "should detect the document type" do
+    expect(raw_docx_sample.document_type).to eq "wordprocessingml"
+  end
+end

data/spec/features/package_spec.rb

@@ -0,0 +1,20 @@
+require "spec_helper"
+
+describe "Officedoc" do
+  it "should open OOXML package by filename" do
+    fn = rspec_file "samples/sample1.docx"
+    od = Officedoc.open( filename: fn )
+    expect(od).not_to be_nil
+    expect(od.filename).to eq(fn)
+    f = open(fn,"rb")
+    expect_identical_file_streams f, od.raw.stream 
+  end
+  it "should open OOXML package from stream" do
+    fn = rspec_file "samples/sample1.docx"
+    f = open(fn,"rb")
+    od = Officedoc.open( stream: f )
+    expect(od).not_to be_nil
+    expect(od.raw.stream).not_to be_nil
+    expect(od.raw.stream).to eq(f)
+  end
+end

data/spec/spec_helper.rb

@@ -3,3 +3,25 @@ CodeClimate::TestReporter.start
 
 require 'officedoc'
 
+Rspec_Root = Pathname(__FILE__).dirname
+def rspec_file(tail)
+  Rspec_Root.join(tail)
+end
+
+Dir[rspec_file("support/**/*.rb")].each { |f| require f }
+Dir[rspec_file("**/*_handlers.rb")].each { |f| require f }
+
+RSpec.configure do |config|
+  config.order = "random"
+  config.filter_run focus: true
+  config.run_all_when_everything_filtered = true  
+  
+  config.include Support::FileHandlers  
+end
+
+
+
+
+
+
+

data/spec/support/file_handlers.rb

@@ -0,0 +1,25 @@
+module Support
+  module FileHandlers
+    def expect_identical_file_streams(f1,f2)
+      f1.rewind
+      f2.rewind
+      expect(f1.read).to eq(f2.read)
+    end
+    def file_stream(name)
+      open( rspec_file(name), "rb" )
+    end
+    def count_files_in_zip(name)
+      `zipinfo -t #{rspec_file(name)} | sed -e "/ files.*/s///"`.to_i
+    end
+    def list_files_in_zip(name)
+      `zipinfo -1 #{rspec_file(name)}`.split
+    end
+    def output_file_from_zip(name,fname)
+      # unzip treats [ ] specially, so requires escaping for '[' and ']' in filenames like '[Content_Types].xml'
+      unzip_fname = fname
+        .gsub('[', '\\\\\[')
+        .gsub(']', '\\\\\]')
+      `unzip -p #{rspec_file(name)} #{unzip_fname}`
+    end
+  end
+end

metadata

@@ -1,23 +1,51 @@
 --- !ruby/object:Gem::Specification
 name: officedoc
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Andrey Pronin
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-04-10 00:00:00.000000000 Z
+date: 2014-04-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: naught
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.6'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -25,19 +53,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.6'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.5'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.2'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -56,16 +98,16 @@ dependencies:
   name: codeclimate-test-reporter
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.3.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.3.0
 description: 'Parsing and constructing documents using XML-based Office formats: ODF
   and OOXML.'
 email:
@@ -74,16 +116,29 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".gitattributes"
 - ".gitignore"
+- ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - LICENSE.txt
 - README.md
 - Rakefile
 - lib/officedoc.rb
+- lib/officedoc/null_object.rb
+- lib/officedoc/package.rb
+- lib/officedoc/package/raw.rb
+- lib/officedoc/package/raw/parts.rb
+- lib/officedoc/package/raw/ruby_zip_engine.rb
 - lib/officedoc/version.rb
 - officedoc.gemspec
+- spec/classes/package/raw/part_spec.rb
+- spec/classes/package/raw_spec.rb
+- spec/features/package_spec.rb
+- spec/samples/sample1.docx
 - spec/spec_helper.rb
+- spec/support/file_handlers.rb
 - tasks/rspec.rake
 homepage: https://github.com/moonfly/officedoc
 licenses:
@@ -97,7 +152,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
@@ -110,4 +165,9 @@ signing_key:
 specification_version: 4
 summary: Parsing and constructing ODF and OOXML documents
 test_files:
+- spec/classes/package/raw/part_spec.rb
+- spec/classes/package/raw_spec.rb
+- spec/features/package_spec.rb
+- spec/samples/sample1.docx
 - spec/spec_helper.rb
+- spec/support/file_handlers.rb