textractor 0.0.1 → 0.0.2

data/README.md

@@ -1,21 +1,23 @@
 # textractor
 
-textractor is a ruby library that provides a simple wrapper for
-extracting text from PDF and Word documents.
+textractor is a ruby library that provides a simple wrapper around CLI
+tools for extracting text from PDF and Word documents.
 
 ## Setup
 
+    gem install textractor
+
 In order to use textractor you have to install a few command line
 tools.
 
 ### OS X
 
-    port install wv pdftohtml links
+    port install wv xpdf links
 
 I recommend using also passing +no_x11 to the install command, but
 this may not work on all systems due to dependency issues.
 
-    port install wv pdftohtml links +no_x11
+    port install wv xpdf links +no_x11
 
 ### Ubuntu 8.04
 

data/Rakefile

@@ -5,12 +5,12 @@ begin
   require 'jeweler'
   Jeweler::Tasks.new do |gem|
     gem.name = "textractor"
-    gem.summary = %Q{simple wrapper for extracting text from PDF and Word documents}
-    gem.description = %Q{simple wrapper for extracting text from PDF and Word documents}
+    gem.summary = %Q{simple wrapper around CLI tools for extracting text from PDF and Word documents}
+    gem.description = %Q{simple wrapper around CLI for extracting text from PDF and Word documents}
     gem.email = "mguterl@gmail.com"
     gem.homepage = "http://github.com/mguterl/textractor"
     gem.authors = ["Michael Guterl"]
-    gem.add_development_dependency "rspec", ">= 1.2.9"
+    gem.add_development_dependency "rspec", ">= 1.3.0"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end
   Jeweler::GemcutterTasks.new

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.2

data/lib/textractor/document.rb

@@ -7,6 +7,7 @@ module Textractor
       'application/x-pdf' => :pdf,
       'application/doc'   => :word,
       'application/x-doc' => :word,
+      'text/plain'        => :txt
     }
 
     attr_reader :filename
@@ -27,6 +28,8 @@ module Textractor
         :pdf
       when /doc/
         :word
+      when /txt/
+        :txt
       else
         nil
       end
@@ -46,6 +49,10 @@ module Textractor
       `wvWare -c utf-8 --nographics -x #{Textractor.wvText_path} #{filename} 2>/dev/null`.strip
     end
 
+    def extract_from_txt
+      File.read(filename)
+    end
+
   end
 
 end

data/spec/document_spec.rb

@@ -4,6 +4,7 @@ describe Textractor::Document do
 
   PDF_DOCUMENT_FIXTURE  = File.expand_path(File.dirname(__FILE__) + "/fixtures/document.pdf")
   WORD_DOCUMENT_FIXTURE = File.expand_path(File.dirname(__FILE__) + "/fixtures/document.doc")
+  TXT_DOCUMENT_FIXTURE  = File.expand_path(File.dirname(__FILE__) + "/fixtures/document.txt")
 
   it 'should require a filename to create' do
     expect { Textractor::Document.new }.to raise_error(ArgumentError)
@@ -30,6 +31,15 @@ describe Textractor::Document do
 
     end
 
+    describe "with txt document" do
+
+      it 'should extract the text from the document' do
+        @doc = Textractor::Document.new(TXT_DOCUMENT_FIXTURE)
+        @doc.text.should == "Ruby on rails developer"
+      end
+
+    end
+
   end
 
   describe "#type" do

data/spec/fixtures/document.txt

@@ -0,0 +1 @@
+Ruby on rails developer

data/textractor.gemspec

@@ -0,0 +1,62 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{textractor}
+  s.version = "0.0.2"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Michael Guterl"]
+  s.date = %q{2010-07-26}
+  s.description = %q{simple wrapper around CLI for extracting text from PDF and Word documents}
+  s.email = %q{mguterl@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.md"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.md",
+     "Rakefile",
+     "VERSION",
+     "lib/textractor.rb",
+     "lib/textractor/document.rb",
+     "spec/document_spec.rb",
+     "spec/fixtures/document.doc",
+     "spec/fixtures/document.pdf",
+     "spec/fixtures/document.txt",
+     "spec/spec.opts",
+     "spec/spec_helper.rb",
+     "spec/textractor_spec.rb",
+     "support/wvText.xml",
+     "textractor.gemspec"
+  ]
+  s.homepage = %q{http://github.com/mguterl/textractor}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{simple wrapper around CLI tools for extracting text from PDF and Word documents}
+  s.test_files = [
+    "spec/document_spec.rb",
+     "spec/spec_helper.rb",
+     "spec/textractor_spec.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_development_dependency(%q<rspec>, [">= 1.3.0"])
+    else
+      s.add_dependency(%q<rspec>, [">= 1.3.0"])
+    end
+  else
+    s.add_dependency(%q<rspec>, [">= 1.3.0"])
+  end
+end
+

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: textractor
 version: !ruby/object:Gem::Version 
+  hash: 27
   prerelease: false
   segments: 
   - 0
   - 0
-  - 1
-  version: 0.0.1
+  - 2
+  version: 0.0.2
 platform: ruby
 authors: 
 - Michael Guterl
@@ -14,24 +15,26 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-04-20 00:00:00 -04:00
+date: 2010-07-26 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: rspec
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 27
         segments: 
         - 1
-        - 2
-        - 9
-        version: 1.2.9
+        - 3
+        - 0
+        version: 1.3.0
   type: :development
   version_requirements: *id001
-description: simple wrapper for extracting text from PDF and Word documents
+description: simple wrapper around CLI for extracting text from PDF and Word documents
 email: mguterl@gmail.com
 executables: []
 
@@ -52,10 +55,12 @@ files:
 - spec/document_spec.rb
 - spec/fixtures/document.doc
 - spec/fixtures/document.pdf
+- spec/fixtures/document.txt
 - spec/spec.opts
 - spec/spec_helper.rb
 - spec/textractor_spec.rb
 - support/wvText.xml
+- textractor.gemspec
 has_rdoc: true
 homepage: http://github.com/mguterl/textractor
 licenses: []
@@ -66,26 +71,30 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: 
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
-summary: simple wrapper for extracting text from PDF and Word documents
+summary: simple wrapper around CLI tools for extracting text from PDF and Word documents
 test_files: 
 - spec/document_spec.rb
 - spec/spec_helper.rb