textractor 0.1.6 → 0.2.0

data/Gemfile.lock

@@ -1,12 +1,14 @@
 PATH
   remote: .
   specs:
-    textractor (0.1.4)
+    textractor (0.1.6)
+      escape (>= 0.0.4)
 
 GEM
   remote: http://rubygems.org/
   specs:
     diff-lcs (1.1.2)
+    escape (0.0.4)
     rspec (2.1.0)
       rspec-core (~> 2.1.0)
       rspec-expectations (~> 2.1.0)

data/Rakefile

@@ -15,7 +15,7 @@ end
 
 task :default => :spec
 
-require 'rake/rdoctask'
+require 'rdoc/task'
 Rake::RDocTask.new do |rdoc|
   version = File.exist?('VERSION') ? File.read('VERSION') : ""
 

data/lib/textractor.rb

@@ -64,3 +64,4 @@ module Textractor
 end
 
 require 'textractor/content_type_detector'
+require 'escape'

data/lib/textractor/extractors/doc_extractor.rb

@@ -13,7 +13,7 @@ module Textractor::Extractors
     end
 
     def text_from_path(path)
-      command = "wvWare -c utf-8 --nographics -x #{wvText_path} '#{path}'"
+      command = "wvWare -c utf-8 --nographics -x #{wvText_path} #{Escape.shell_single_word(path)}"
       puts command if $DEBUG
       `#{command}`.strip
     end

data/lib/textractor/extractors/docx_extractor.rb

@@ -14,7 +14,7 @@ module Textractor::Extractors
 
 
     def text_from_path(path)
-      `#{docx2txt_path} '#{path}' -`.strip
+      `#{docx2txt_path} #{Escape.shell_single_word(path)} -`.strip
     end
 
     private

data/lib/textractor/extractors/pdf_extractor.rb

@@ -3,7 +3,7 @@ module Textractor::Extractors
   class PDFExtractor
 
     def text_from_path(path)
-      `pdftotext '#{path}' - 2>/dev/null`.strip
+      `pdftotext #{Escape.shell_single_word(path)} - 2>/dev/null`.strip
     end
 
   end

data/lib/textractor/version.rb

@@ -1,3 +1,3 @@
 module Textractor
-  VERSION = '0.1.6'
+  VERSION = '0.2.0'
 end

data/textractor.gemspec

@@ -16,7 +16,9 @@ Gem::Specification.new do |s|
   s.add_development_dependency "bundler", ">= 1.0.0"
   s.add_development_dependency "rspec",   "~> 2.1.0"
 
-  s.files        = `git ls-files`.split("\n")
+  s.add_runtime_dependency "escape", ">=0.0.4"
+
+  s.files        = `git ls-files`.split("\n").reject{|f| f.gsub(/"/, "") =~ /^spec/}
   s.executables  = `git ls-files`.split("\n").map{|f| f =~ /^bin\/(.*)/ ? $1 : nil}.compact
   s.require_path = 'lib'
   s.extra_rdoc_files = ["LICENSE", "README.md"]

metadata

@@ -5,9 +5,9 @@ version: !ruby/object:Gem::Version
   prerelease: 
   segments: 
   - 0
-  - 1
-  - 6
-  version: 0.1.6
+  - 2
+  - 0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Michael Guterl
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-07-22 00:00:00 -04:00
+date: 2011-07-29 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -50,6 +50,22 @@ dependencies:
         version: 2.1.0
   type: :development
   version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: escape
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 23
+        segments: 
+        - 0
+        - 0
+        - 4
+        version: 0.0.4
+  type: :runtime
+  version_requirements: *id003
 description: simple wrapper around CLI for extracting text from PDF and Word documents
 email: 
 - michael@diminishing.org
@@ -81,19 +97,6 @@ files:
 - lib/textractor/extractors/pdf_extractor.rb
 - lib/textractor/extractors/text_extractor.rb
 - lib/textractor/version.rb
-- spec/content_type_detector/simple_spec.rb
-- spec/fixtures/document .doc
-- spec/fixtures/document .docx
-- spec/fixtures/document .pdf
-- spec/fixtures/document .txt
-- spec/fixtures/document.doc
-- spec/fixtures/document.docx
-- spec/fixtures/document.pdf
-- spec/fixtures/document.txt
-- spec/fixtures/no_extension
-- spec/integration/textractor_spec.rb
-- spec/spec_helper.rb
-- spec/textractor_spec.rb
 - support/wvText.xml
 - textractor.gemspec
 - vendor/docx2txt/AUTHORS

data/spec/content_type_detector/simple_spec.rb

@@ -1,30 +0,0 @@
-require 'spec_helper'
-
-describe Textractor::ContentTypeDetector::Simple do
-
-  FILENAMES = [
-    [
-      "foo.pdf", "application/pdf",
-      "foo.doc", "application/msword",
-      "foo.docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-      "foo.txt", "text/plain",
-    ]
-  ]
-
-  describe '.content_type_for_path' do
-    FILENAMES.each do |(filename, content_type)|
-      context "given #{filename}" do
-        it "returns #{content_type}" do
-          Textractor::ContentTypeDetector::Simple.content_type_for_path(filename).should == content_type
-        end
-      end
-
-      context "given #{filename}" do
-        it "returns #{content_type}" do
-          Textractor::ContentTypeDetector::Simple.content_type_for_path(filename.upcase).should == content_type
-        end
-      end
-    end
-  end
-
-end

data/spec/fixtures/document .txt

@@ -1 +0,0 @@
-text

data/spec/fixtures/document.txt

@@ -1 +0,0 @@
-text

data/spec/integration/textractor_spec.rb

@@ -1,74 +0,0 @@
-require 'spec_helper'
-
-describe Textractor do
-
-  before do
-    Textractor.clear_registry
-    Textractor.register_basic_types
-  end
-
-  it 'returns the contents of word (.doc) documents' do
-    Textractor.text_from_path(fixture_path("document.doc")).should == 'text'
-  end
-
-  it 'returns the contents of word (.docx) documents' do
-    Textractor.text_from_path(fixture_path("document.docx")).should == 'text'
-  end
-
-  it 'returns the contents of pdf documents' do
-    Textractor.text_from_path(fixture_path("document.pdf")).should == 'text'
-  end
-
-  it 'returns the contents of text documents' do
-    Textractor.text_from_path(fixture_path("document.txt")).should == 'text'
-  end
-
-  it 'allows the user to specify content type to avoid internal resolution' do
-    Textractor.text_from_path(fixture_path("no_extension"), :content_type => "application/pdf").should == 'text'
-  end
-
-  it 'raises an exception when the content type is unable to be determined' do
-    expect {
-      Textractor.text_from_path(fixture_path("no_extension"))
-    }.to raise_error(Textractor::UnknownContentType)
-  end
-
-  it 'raises an exception when the path specified does not exist' do
-    expect {
-      Textractor.text_from_path('non-existant')
-    }.to raise_error(Textractor::FileNotFound)
-  end
-
-  it 'raises an exception when there is no extractor defined for the content type' do
-    Textractor.clear_registry
-
-    expect {
-      Textractor.text_from_path(fixture_path('document.pdf'))
-    }.to raise_error(Textractor::ContentTypeNotRegistered)
-  end
-
-  it 'allows content type extractors to be removed' do
-    Textractor.remove_content_type("application/pdf")
-
-    expect {
-      Textractor.text_from_path(fixture_path('document.pdf'))
-    }.to raise_error(Textractor::ContentTypeNotRegistered)
-  end
-
-  it 'returns the contents of doc files with a space in the path' do
-    Textractor.text_from_path(fixture_path("document .doc")).should == 'text'
-  end
-
-  it 'returns the contents of docx files with a space in the path' do
-    Textractor.text_from_path(fixture_path("document .docx")).should == 'text'
-  end
-
-  it 'returns the contents of pdf files with a space in the path' do
-    Textractor.text_from_path(fixture_path("document .pdf")).should == 'text'
-  end
-
-  it 'returns the contents of txt files with a space in the path' do
-    Textractor.text_from_path(fixture_path("document .txt")).should == 'text'
-  end
-
-end

data/spec/spec_helper.rb

@@ -1,14 +0,0 @@
-$LOAD_PATH.unshift(File.dirname(__FILE__))
-
-require 'rubygems'
-require 'bundler/setup'
-require 'rspec'
-require 'textractor'
-
-def fixture_path(path)
-  File.expand_path(File.join(File.dirname(__FILE__), 'fixtures', path))
-end
-
-RSpec.configure do |config|
-
-end

data/spec/textractor_spec.rb

@@ -1,104 +0,0 @@
-require 'spec_helper'
-
-class TestExtractor
-
-  def text_from_path(path)
-    path
-  end
-
-end
-
-describe Textractor do
-
-  before do
-    Textractor.clear_registry
-  end
-
-  describe ".text_from_path" do
-    before do
-      File.stub(:exists?).and_return(true)
-      Textractor.stub(:content_type_for_path).and_return('test')
-      Textractor.stub(:extractor_for_content_type).and_return(TestExtractor)
-    end
-
-    it 'extracts the text from a given path' do
-      Textractor.text_from_path('document').should == 'document'
-    end
-
-    it 'uses content_type_for_path to determine the content type' do
-      Textractor.should_receive(:content_type_for_path).with('document')
-      Textractor.text_from_path('document')
-    end
-
-    it 'uses extractor_for_content_type to look up the correct extractor' do
-      Textractor.should_receive(:extractor_for_content_type).with('test')
-      Textractor.text_from_path('document')
-    end
-
-  end
-
-  describe ".register_content_type" do
-
-    it 'raises an exception if an extractor is already defined for that content type' do
-      Textractor.register_content_type("text/plain", TestExtractor)
-
-      expect {
-        Textractor.register_content_type("text/plain", TestExtractor)
-      }.to raise_error(Textractor::ContentTypeAlreadyRegistered)
-    end
-
-    it 'takes a block for simple cases' do
-      File.stub(:exists?).and_return(true)
-      Textractor.stub(:content_type_for_path).and_return('test')
-      Textractor.register_content_type('test') do |path|
-        path
-      end
-
-      Textractor.text_from_path('document').should == 'document'
-    end
-
-  end
-
-  describe ".extractor_for_content_type" do
-    before do
-      Textractor.register_content_type("text/plain", TestExtractor)
-    end
-
-    it 'returns the extractor for the content type' do
-      Textractor.extractor_for_content_type("text/plain").should == TestExtractor
-    end
-
-    it 'raises an exception when no extractor is defined for that content type' do
-      expect {
-        Textractor.extractor_for_content_type("unknown")
-      }.to raise_error(Textractor::ContentTypeNotRegistered)
-    end
-  end
-
-  describe ".content_type_for_path" do
-
-    it 'returns the content type based on the file extension' do
-      Textractor.content_type_for_path("document.pdf").should == "application/pdf"
-    end
-
-    it 'raises an exception if it cannot determine the content type' do
-      expect {
-        Textractor.content_type_for_path('unknown')
-      }.to raise_error(Textractor::UnknownContentType)
-    end
-
-  end
-
-  describe ".clear_registry" do
-    before do
-      Textractor.register_content_type("text/plain", TestExtractor)
-    end
-
-    it 'clears the registered content types and their respective extractors' do
-      Textractor.clear_registry
-      Textractor.extractors.should be_empty
-    end
-
-  end
-
-end