doctor_ninja 0.0.1

data/lib/doctor_ninja/parsers/paragraph.rb

@@ -0,0 +1,38 @@
+require "doctor_ninja/parsers/base"
+
+class DoctorNinja::Parsers::Paragraph < DoctorNinja::Parsers::Base
+  @@style_map = {
+    /^T[í|i]?t(ulo|le)$/ => "h1",
+    /^Subt[í|i]?t(ulo|le)$/ => "h2",
+    // => "p"
+  }
+
+  def self.applicable_to?(node)
+    node.name == "p"
+  end
+
+  def parse
+    @context[:has_text] = false
+    content = parse_children
+    attrs = {}
+    style = {}
+    style["text-align"] = "center" unless @context[:has_text]
+
+    attrs["style"] = style.map{|k,v| "#{k}:#{v};"}.join(" ") if style.length > 0
+
+    attrs = attrs.map{|k,v| " #{k}=\"#{v}\""}.join("")
+    "<#{tag}#{attrs}>#{content}</#{tag}>"
+  end
+
+  def tag
+    style == nil ? "p" : @@style_map.select do |k,v|
+      k =~ style
+    end.first[1]
+  end
+
+  def style
+    @node.xpath("./w:pPr/w:pStyle").first.attributes["val"].value 
+  rescue
+    nil
+  end
+end

data/lib/doctor_ninja/parsers/run.rb

@@ -0,0 +1,24 @@
+require_relative "./base"
+
+class DoctorNinja::Parsers::Run < DoctorNinja::Parsers::Base
+  @@available_tags = ["b", "u", "i"]
+
+  def self.applicable_to?(node)
+    node.name == "r"
+  end
+
+  def parse
+    tag = nil
+    if @node.xpath(".//w:rPr/w:b").length > 0
+      tag = "b"
+    end
+
+    tags.inject(parse_children){|text,tag| "<#{tag}>#{text}</#{tag}>"}
+  end
+
+  def tags
+    @node.xpath("./w:rPr").children
+      .map{|n| n.name}
+      .select{|n| @@available_tags.include? n}
+  end
+end

data/lib/doctor_ninja/parsers/text.rb

@@ -0,0 +1,12 @@
+require_relative "./base"
+
+class DoctorNinja::Parsers::Text < DoctorNinja::Parsers::Base
+  def self.applicable_to?(node)
+    node.text?
+  end
+
+  def parse
+    @context[:has_text] = true
+    @node.text
+  end
+end

data/lib/doctor_ninja/relationships.rb

@@ -0,0 +1,20 @@
+module DoctorNinja
+  class Relationships
+    def initialize(doc)
+      @doc = doc
+      @rels = Nokogiri::XML @doc.read "word/_rels/document.xml.rels"
+    end
+
+    def read id
+      @doc.read "word/#{path id}"
+    end
+
+    alias_method :[], :read
+
+    def path id
+      @rels.xpath("//*[@Id=\"#{id}\"]").attribute("Target").value
+    rescue
+      nil
+    end
+  end
+end

data/lib/doctor_ninja/version.rb

@@ -0,0 +1,3 @@
+module DoctorNinja
+  VERSION = "0.0.1"
+end

data/test/document_test.rb

@@ -0,0 +1,15 @@
+require_relative "./minitest_helper"
+require "doctor_ninja/document"
+require "doctor_ninja/errors"
+
+class DocumentTest < MiniTest::Test
+  def test_valid_file
+    @doc = DoctorNinja::Document.new("test/fixtures/limites.docx")
+  end
+
+  def test_invalid_file
+    assert_raises(::DoctorNinja::InvalidDocumentError) do
+      ::DoctorNinja::Document.new("test/fixtures/invalid_file.docx")
+    end
+  end
+end

data/test/integration_test.rb

@@ -0,0 +1,33 @@
+# encoding: UTF-8
+require "minitest/autorun"
+require "doctor_ninja"
+
+class IntegrationTest < MiniTest::Test
+  def test_valid_file
+    @doc = DoctorNinja::Document.new("test/fixtures/limites.docx")
+    @parser = DoctorNinja::Parser.new(@doc)
+    @result = @parser.parse
+
+    assert_includes(@result, "<h1>Introdução aos Limites</h1>")
+    assert_includes(@result, "<h2>Introdução</h2>")
+    assert_includes(@result, "<b>O limite")
+    assert_includes(@result, "<u>Mas a verdade é")
+    
+    math = <<-MATH
+      <math xmlns="http://www.w3.org/1998/Math/MathML" display="block">
+        <mfrac>
+          <mrow>
+            <mn>1</mn>
+          </mrow>
+          <mrow>
+            <mn>0</mn>
+          </mrow>
+        </mfrac>
+        <mo>=</mo>
+        <mi>∞</mi>
+      </math>
+    MATH
+
+    assert_includes(@result.gsub(/[\n ]/,""), math.gsub(/[\n ]/,""))
+  end
+end

data/test/minitest_helper.rb

@@ -0,0 +1,3 @@
+require 'minitest/reporters'
+Minitest::Reporters.use!(Minitest::Reporters::SpecReporter.new)
+require 'minitest/autorun'

metadata

@@ -0,0 +1,186 @@
+--- !ruby/object:Gem::Specification
+name: doctor_ninja
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Bernardo Amorim
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-10-09 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.4'
+- !ruby/object:Gem::Dependency
+  name: minitest-reporters
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: rmagick
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.13'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.13'
+description: DoctorNinja is built by the Responde Aí Team (www.respondeai.com.br/time)
+  in an attempt to fill our needs to convert docx files into html that also converts
+  Word Forumlas into MathML.
+email:
+- contato@bamorim.com
+executables:
+- ninjadoc
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/ninjadoc
+- doctor_ninja.gemspec
+- lib/doctor_ninja.rb
+- lib/doctor_ninja/document.rb
+- lib/doctor_ninja/errors.rb
+- lib/doctor_ninja/parser.rb
+- lib/doctor_ninja/parsers/base.rb
+- lib/doctor_ninja/parsers/blip_fill.rb
+- lib/doctor_ninja/parsers/drawing.rb
+- lib/doctor_ninja/parsers/math.rb
+- lib/doctor_ninja/parsers/math_para.rb
+- lib/doctor_ninja/parsers/omml2mml.xsl
+- lib/doctor_ninja/parsers/paragraph.rb
+- lib/doctor_ninja/parsers/run.rb
+- lib/doctor_ninja/parsers/text.rb
+- lib/doctor_ninja/relationships.rb
+- lib/doctor_ninja/version.rb
+- test/document_test.rb
+- test/fixtures/img.docx
+- test/fixtures/img_crop.docx
+- test/fixtures/img_rot.docx
+- test/fixtures/img_rot_crop.docx
+- test/fixtures/invalid_file.docx
+- test/fixtures/limites.docx
+- test/integration_test.rb
+- test/minitest_helper.rb
+homepage: https://github.com/bamorim/doctor_ninja
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: DoctorNinja is a library to convert word documents into html files like a
+  ninja.
+test_files:
+- test/document_test.rb
+- test/fixtures/img.docx
+- test/fixtures/img_crop.docx
+- test/fixtures/img_rot.docx
+- test/fixtures/img_rot_crop.docx
+- test/fixtures/invalid_file.docx
+- test/fixtures/limites.docx
+- test/integration_test.rb
+- test/minitest_helper.rb