grim 0.1.0

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

@@ -0,0 +1,4 @@
+source :rubygems
+gemspec
+gem 'rspec'
+gem 'ruby-debug'

data/README.textile

@@ -0,0 +1,17 @@
+h1. Grim
+
+Grim is a simple gem for extracting a page from a pdf and converting it to an image as well as extract the text from the page as a string. It basically gives you an easy to use api to ghostscript, imagemagick, and pdftotext specific to this use case.
+
+h2. Prerequisites
+
+You will need ghostscript, imagemagick, and xpdf installed. On the Mac (OSX) I highly recommend using "Homebrew":http://mxcl.github.com/homebrew/ to get them installed, its as simple as "brew install ghostscript", "brew install imagemagick", and "brew install xpdf".
+
+h2. Usage
+
+<pre><code>
+  instance    = Grim.new("/path/to/pdf")
+  page_count  = instance.page_count                            # returns the number of pages in the pdf
+  png  = instance.page(1).to_image("/path/to/save/image.png")  # saves png to path and returns File instance
+  jpeg = instance.page(2).to_image("/path/to/save/image.jpeg") # saves jpeg to path and returns File instance
+  text = instance.page(3).text                                 # returns text as a string
+</pre></code>

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/grim.gemspec

@@ -0,0 +1,20 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "grim"
+
+Gem::Specification.new do |s|
+  s.name        = "grim"
+  s.version     = Grim::VERSION
+  s.authors     = ["Jonathan Hoyt"]
+  s.email       = ["jonmagic@gmail.com"]
+  s.homepage    = ""
+  s.summary     = %q{Extract slides and text from a PDF.}
+  s.description = %q{Grim is a simple gem for extracting a page from a pdf and converting it to an image as well as extract the text from the page as a string. It basically gives you an easy to use api to ghostscript, imagemagick, and pdftotext specific to this use case.}
+
+  s.rubyforge_project = "grim"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+end

data/lib/grim.rb

@@ -0,0 +1,104 @@
+# Grim is a class with instance methods for getting number of pages in a pdf,
+# extracting a page as an image, and extracting the text from a page.
+#
+# For example:
+#
+#    instance    = Grim.new("/path/to/pdf")
+#    page_count  = instance.page_count
+#    png         = instance.page(1).to_png("/path/to/save/png")
+#    jpeg        = instance.page(2).to_jpeg("/path/to/save/jpeg")
+#    text        = instance.page(3).text
+#
+class Grim
+  # VERSION
+  VERSION = "0.1.0"
+
+  # Default resize output width, any positive integer
+  WIDTH = 1024
+
+  # Default image quality, 1 to 100
+  QUALITY = 90
+
+  # Default density, any positive integer
+  DENSITY = 300
+
+  # Default exception class for Grim.
+  class Exception < ::StandardError
+  end
+
+  # Exception that is raised if pdf is not found.
+  class PdfNotFound < Grim::Exception
+  end
+
+  # be able to store what page instance should focus on
+  attr_accessor :page_number
+
+  # initialize is called when a new instance is created and accepts path.
+  def initialize(path)
+    raise Grim::PdfNotFound unless File.exists?(path)
+    @page_number = 1
+    @path = path
+  end
+
+  # page_count uses the memoized path and shells out to ghostscript
+  # to read the pdf with the pdf_info.ps script as a filter,
+  # returning the number of pages in the pdf as an integer.
+  #
+  # For example:
+  #
+  #    instance.page_count
+  # => 4
+  #
+  # Returns an integer.
+  def page_count
+    @page_count ||= begin
+      `gs -dNODISPLAY -q -sFile=#{@path} ./lib/pdf_info.ps`.to_i
+    end
+  end
+
+  # page just sets the page attribute on the instance.
+  #
+  # For example:
+  #
+  #    instance.page(1)
+  # => instance
+  #
+  # Returns self.
+  def page(number)
+    @page_number = number
+    self
+  end
+
+  # Returns page_number minus 1
+  def index
+    @page_number - 1
+  end
+
+  # to_image extracts the selected page and turns it into an image.
+  # Tested on png and jpeg.
+  #
+  # For example:
+  #
+  #    instance.page(2).to_image(/path/to/save/image)
+  # => File
+  #
+  # Returns an instance of File
+  def to_image(path)
+    `convert -resize #{Grim::WIDTH} -antialias -render -quality #{Grim::QUALITY} -colorspace RGB -interlace none -density #{Grim::DENSITY} #{@path}[#{index}] #{path}`
+    file = File.open(path)
+    file.rewind
+    file
+  end
+
+  # text is an instance method that extracts the text from the selected page.
+  #
+  # For example:
+  #
+  #    instance.page(2).text
+  # => "This is text from slide 2.\n\nAnd even more text from slide 2."
+  #
+  # Returns a string
+  def text
+    `pdftotext -enc UTF-8 -f #{@page_number} -l #{@page_number} #{@path} -`
+  end
+end

data/lib/pdf_info.ps

@@ -0,0 +1,21 @@
+% usage: gs -dNODISPLAY -q -sFile=____.pdf pdf_info.ps
+
+/File where not {
+  (\n   *** Missing input file name \(use -sFile=____.pdf\)\n) =
+  (    usage: gs -dNODISPLAY -q -sFile=____.pdf [ options ] toolbin/pdf_info.ps\n) =
+  () =
+  flush
+  quit
+} if
+pop      % discard the dict from where
+
+/QUIET true def    % in case they forgot
+
+() =
+File dup (r) file runpdfbegin
+/PDFPageCount pdfpagecount def
+ PDFPageCount =print () =
+flush
+() =
+
+quit

data/spec/lib/grim_spec.rb

@@ -0,0 +1,95 @@
+require 'fileutils'
+require 'spec_helper'
+
+describe Grim do
+  after(:all) do
+    FileUtils.rm_rf(tmp_dir)
+  end
+
+  it "should have a VERSION constant" do
+    Grim.const_defined?('VERSION').should be_true
+  end
+
+  describe "Pdf" do
+    describe "#initialize" do
+      it "should raise an error if pdf does not exist" do
+        lambda { Grim.new(fixture_path("booboo.pdf")) }.should raise_error(Grim::PdfNotFound)
+      end
+    end
+
+    describe "#page_count" do
+      it "should return an integer" do
+        instance = Grim.new(fixture_path("smoker.pdf"))
+        instance.page_count.should == 25
+      end
+    end
+
+    describe "#page" do
+      it "should be set to 1 by default" do
+        instance = Grim.new(fixture_path("smoker.pdf"))
+        instance.page_number.should == 1
+      end
+
+      it "should set page attribute and return instance" do
+        instance = Grim.new(fixture_path("smoker.pdf"))
+        instance.page(2).should == instance
+        instance.page_number.should == 2
+      end
+    end
+
+    describe "#index" do
+      it "should return page minus 1" do
+        instance = Grim.new(fixture_path("smoker.pdf"))
+        instance.page(2)
+        instance.index.should == 1
+      end
+    end
+
+    describe "#to_image" do
+      describe "output png" do
+        before(:all) do
+          instance = Grim.new(fixture_path("smoker.pdf"))
+          @png = instance.to_image(tmp_path("to_png_spec.png"))
+        end
+
+        it "should create the file" do
+          File.exist?(tmp_path("to_png_spec.png")).should be_true
+        end
+
+        it "should return an instance of File" do
+          @png.class.should == File
+        end
+
+        it "should have the right file size" do
+          @png.stat.size.should == 188515
+        end
+      end
+
+      describe "output jpeg" do
+        before(:all) do
+          instance = Grim.new(fixture_path("smoker.pdf"))
+          @jpeg = instance.to_image(tmp_path("to_jpeg_spec.jpeg"))
+        end
+
+        it "should create the file" do
+          File.exist?(tmp_path("to_jpeg_spec.jpeg")).should be_true
+        end
+
+        it "should return an instance of File" do
+          @jpeg.class.should == File
+        end
+
+        it "should have the right file size" do
+          @jpeg.stat.size.should == 53980
+        end
+      end
+    end
+
+    describe "#text" do
+      it "should return the text from the selected page" do
+        instance = Grim.new(fixture_path("smoker.pdf"))
+        instance.page(2).text.should == "Step 1: get someone to print this curve for you to scale, 72\342\200\235 wide\n\nStep 2: Get a couple 55 gallon drums\n\n\f"
+      end
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,21 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'grim'
+
+RSpec.configure do |config|
+  def fixture_path(name)
+    path = File.expand_path("./spec/fixtures/")
+    File.join(path, name)
+  end
+
+  def tmp_dir
+    path = File.expand_path("./tmp")
+    Dir.mkdir(path) unless File.directory?(path)
+    path
+  end
+
+  def tmp_path(name)
+    File.join(tmp_dir, name)
+  end
+end

metadata

@@ -0,0 +1,79 @@
+--- !ruby/object:Gem::Specification 
+name: grim
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Jonathan Hoyt
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-09-05 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: Grim is a simple gem for extracting a page from a pdf and converting it to an image as well as extract the text from the page as a string. It basically gives you an easy to use api to ghostscript, imagemagick, and pdftotext specific to this use case.
+email: 
+- jonmagic@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- .gitignore
+- Gemfile
+- README.textile
+- Rakefile
+- grim.gemspec
+- lib/grim.rb
+- lib/pdf_info.ps
+- spec/fixtures/smoker.pdf
+- spec/lib/grim_spec.rb
+- spec/spec_helper.rb
+has_rdoc: true
+homepage: ""
+licenses: []
+
+post_install_message: 
+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: grim
+rubygems_version: 1.6.2
+signing_key: 
+specification_version: 3
+summary: Extract slides and text from a PDF.
+test_files: 
+- spec/fixtures/smoker.pdf
+- spec/lib/grim_spec.rb
+- spec/spec_helper.rb