grim 0.2.4 → 0.3.0

data/README.textile

@@ -48,6 +48,21 @@ h2. Usage
   end
 </pre></code>
 
+We also support using other processors (the default is whatever version of Imagemagick/Ghostscript is in your path).
+
+<pre><code>
+  # specifying one processor with specific ImageMagick and GhostScript paths
+  Grim.processor =  Grim::ImageMagickProcessor.new({:imagemagick_path => "/path/to/convert", :ghostscript_path => "/path/to/gs"})
+
+  # multiple processors with fallback if first fails, useful if you need multiple versions of convert/gs
+  Grim.processor = Grim::MultiProcessor.new([
+    Grim::ImageMagickProcessor.new({:imagemagick_path => "/path/to/6.7/convert", :ghostscript_path => "/path/to/9.04/gs"}),
+    Grim::ImageMagickProcessor.new({:imagemagick_path => "/path/to/6.6/convert", :ghostscript_path => "/path/to/9.02/gs"})
+  ])
+
+  pdf = Grim.reap('/path/to/pdf)
+</code></pre>
+
 h2. License
 
 See LICENSE for details.

data/grim.gemspec

@@ -12,7 +12,6 @@ Gem::Specification.new do |s|
   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.add_dependency 'safe_shell', '~> 1.0.0'
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/lib/grim.rb

@@ -1,7 +1,10 @@
 # encoding: UTF-8
-require 'safe_shell'
+require 'shellwords'
 
 module Grim
+  extend self
+  attr_accessor :processor
+
   # Default resize output width, any positive integer
   WIDTH = 1024
 
@@ -47,4 +50,8 @@ module Grim
 end
 
 require 'grim/pdf'
-require 'grim/page'
+require 'grim/page'
+require 'grim/image_magick_processor'
+require 'grim/multi_processor'
+
+Grim.processor = Grim::ImageMagickProcessor.new

data/lib/grim/image_magick_processor.rb

@@ -0,0 +1,37 @@
+module Grim
+  class ImageMagickProcessor
+
+    # ghostscript prints out a warning, this regex matches it
+    WarningRegex = /\*\*\*\*.*\n/
+
+    def initialize(options={})
+      @imagemagick_path = options[:imagemagick_path] || 'convert'
+      @ghostscript_path = options[:ghostscript_path]
+      @original_path        = ENV['PATH']
+    end
+
+    def count(path)
+      command = ["-dNODISPLAY", "-q",
+        "-sFile=#{Shellwords.shellescape(path)}",
+        File.expand_path('../../../lib/pdf_info.ps', __FILE__)]
+      @ghostscript_path ? command.unshift(@ghostscript_path) : command.unshift('gs')
+      result = `#{command.join(' ')}`
+      result.gsub(WarningRegex, '').to_i
+    end
+
+    def save(pdf, index, path, options)
+      width   = options.fetch(:width,   Grim::WIDTH)
+      density = options.fetch(:density, Grim::DENSITY)
+      quality = options.fetch(:quality, Grim::QUALITY)
+      command = [@imagemagick_path, "-resize", width.to_s, "-antialias", "-render",
+        "-quality", quality.to_s, "-colorspace", "RGB",
+        "-interlace", "none", "-density", density.to_s,
+        "#{Shellwords.shellescape(pdf.path)}[#{index}]", path]
+      command.unshift("PATH=#{File.dirname(@ghostscript_path)}:#{ENV['PATH']}") if @ghostscript_path
+
+      result = `#{command.join(' ')}`
+
+      $? == 0 || raise(UnprocessablePage, result)
+    end
+  end
+end

data/lib/grim/multi_processor.rb

@@ -0,0 +1,29 @@
+module Grim
+  class MultiProcessor
+    def initialize(processors)
+      @processors = processors
+    end
+
+    def count(path)
+      result = ""
+      @processors.each do |processor|
+        result = processor.count(path)
+        break if result != ""
+      end
+      result
+    end
+
+    def save(pdf, index, path, options)
+      result = true
+      @processors.each do |processor|
+        begin
+          result = processor.save(pdf, index, path, options)
+        rescue UnprocessablePage
+          next
+        end
+        break if result
+      end
+      raise UnprocessablePage unless result
+    end
+  end
+end

data/lib/grim/page.rb

@@ -32,16 +32,7 @@ module Grim
     def save(path, options={})
       raise PathMissing if path.nil? || path !~ /\S/
 
-      width   = options.fetch(:width,   Grim::WIDTH)
-      density = options.fetch(:density, Grim::DENSITY)
-      quality = options.fetch(:quality, Grim::QUALITY)
-
-      output = SafeShell.execute("convert", "-resize", width, "-antialias", "-render",
-                        "-quality", quality, "-colorspace", "RGB",
-                        "-interlace", "none", "-density", density,
-                        "#{@pdf.path}[#{@index}]", path)
-
-      $? == 0 || raise(UnprocessablePage, output)
+      Grim.processor.save(@pdf, @index, path, options)
     end
 
     # Extracts the text from the selected page.
@@ -54,7 +45,7 @@ module Grim
     # Returns a String.
     #
     def text
-      SafeShell.execute("pdftotext", "-enc", "UTF-8", "-f", @number, "-l", @number, @pdf.path, "-")
+      `#{["pdftotext", "-enc", "UTF-8", "-f", @number, "-l", @number, Shellwords.escape(@pdf.path), "-"].join(' ')}`
     end
   end
 end

data/lib/grim/pdf.rb

@@ -5,9 +5,6 @@ module Grim
 
     attr_reader :path
 
-    # ghostscript prints out a warning, this regex matches it
-    WarningRegex = /\*\*\*\*.*\n/
-
     # Raises an error if pdf not found and sets some instance
     # variables if pdf is found.
     #
@@ -30,8 +27,7 @@ module Grim
     #
     def count
       @count ||= begin
-        result = SafeShell.execute("gs", "-dNODISPLAY", "-q", "-sFile=#{@path}", File.expand_path('../../../lib/pdf_info.ps', __FILE__))
-        result.gsub(WarningRegex, '').to_i
+        Grim.processor.count(@path)
       end
     end
 

data/lib/grim/version.rb

@@ -1,4 +1,4 @@
 # encoding: UTF-8
 module Grim
-  VERSION = "0.2.4" unless defined?(::Grim::VERSION)
+  VERSION = "0.3.0" unless defined?(::Grim::VERSION)
 end

data/spec/lib/grim/image_magick_processor_spec.rb

@@ -0,0 +1,87 @@
+# encoding: UTF-8
+require 'spec_helper'
+
+describe Grim::ImageMagickProcessor do
+  before(:each) do
+    @reset_to  = ENV['PATH']
+  end
+
+  after(:each) do
+    ENV['PATH'] = @reset_to
+  end
+
+  describe "#count" do
+    before(:each) do
+      @processor = Grim::ImageMagickProcessor.new
+    end
+
+    it "should return page count" do
+      @processor.count(fixture_path("smoker.pdf")).should == 25
+    end
+  end
+
+  describe "#save" do
+    before(:all) do
+      @path = tmp_path("to_png_spec.png")
+      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
+
+      @processor = Grim::ImageMagickProcessor.new
+    end
+
+    it "should create the file" do
+      @processor.save(@pdf, 0, @path, {})
+      File.exist?(@path).should be_true
+    end
+
+    it "should use default width of 1024" do
+      @processor.save(@pdf, 0, @path, {})
+      width, height = dimensions_for_path(@path)
+      width.should == 1024
+    end
+  end
+
+  describe "#save with width option" do
+    before(:each) do
+      @path = tmp_path("to_png_spec.png")
+      pdf   = Grim::Pdf.new(fixture_path("smoker.pdf"))
+
+      Grim::ImageMagickProcessor.new.save(pdf, 0, @path, {:width => 20})
+    end
+
+    it "should set width" do
+      width, height = dimensions_for_path(@path)
+      width.should == 20
+    end
+  end
+
+  describe "#save with quality option" do
+    before(:each) do
+      @path = tmp_path("to_png_spec.jpg")
+      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
+    end
+
+    it "should use quality" do
+      Grim::ImageMagickProcessor.new.save(@pdf, 0, @path, {:quality => 20})
+      lower_size = File.size(@path)
+
+      Grim::ImageMagickProcessor.new.save(@pdf, 0, @path, {:quality => 90})
+      higher_size = File.size(@path)
+
+      (lower_size < higher_size).should be_true
+    end
+  end
+
+  describe "#save with density option" do
+    before(:each) do
+      @path = tmp_path("to_png_spec.jpg")
+      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
+    end
+
+    it "should use density" do
+      lower_time  = Benchmark.realtime { Grim::ImageMagickProcessor.new.save(@pdf, 0, @path, {:density => 72}) }
+      higher_time = Benchmark.realtime { Grim::ImageMagickProcessor.new.save(@pdf, 0, @path, {:density => 300}) }
+
+      (lower_time < higher_time).should be_true
+    end
+  end
+end

data/spec/lib/grim/multi_processor_spec.rb

@@ -0,0 +1,42 @@
+# encoding: UTF-8
+require 'spec_helper'
+
+describe Grim::MultiProcessor do
+  before(:each) do
+    @failure     = Grim::ImageMagickProcessor.new
+    @success     = Grim::ImageMagickProcessor.new
+    @extra       = Grim::ImageMagickProcessor.new
+    @processor  = Grim::MultiProcessor.new([@failure, @success, @extra])
+
+    @path = fixture_path("smoker.pdf")
+    @pdf  = Grim::Pdf.new(@path)
+  end
+
+  describe "#count" do
+    it "should try processors until it succeeds" do
+      @failure.stub(:count){""}
+      @success.should_receive(:count).and_return(30)
+      @extra.should_not_receive(:count)
+
+      @processor.count(@path)
+    end
+  end
+
+  describe "#save" do
+    it "should try processors until it succeeds" do
+      @failure.stub(:save){false}
+      @success.should_receive(:save).and_return(true)
+      @extra.should_not_receive(:save)
+
+      @processor.save(@pdf, 0, @path, {})
+    end
+
+    it "should raise error if all processors fail" do
+      @failure.should_receive(:save).and_return(false)
+      @success.should_receive(:save).and_return(false)
+      @extra.should_receive(:save).and_return(false)
+
+      lambda { @processor.save(@pdf, 0, @path, {}) }.should raise_error(Grim::UnprocessablePage)
+    end
+  end
+end

data/spec/lib/grim/page_spec.rb

@@ -14,18 +14,12 @@ describe Grim::Page do
   describe "#save" do
     before(:all) do
       @path = tmp_path("to_png_spec.png")
-      pdf   = Grim::Pdf.new(fixture_path("smoker.pdf"))
-
-      pdf[0].save(@path)
-    end
-
-    it "should create the file" do
-      File.exist?(@path).should be_true
+      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
     end
 
-    it "should use default width of 1024" do
-      width, height = dimensions_for_path(@path)
-      width.should == 1024
+    it "should call Grim.processor.save with pdf, index, path, and options" do
+      Grim.processor.should_receive(:save).with(@pdf, 0, @path, {})
+      @pdf[0].save(@path)
     end
   end
 
@@ -41,59 +35,14 @@ describe Grim::Page do
     end
   end
 
-  describe "#save with width option" do
-    before(:each) do
-      @path = tmp_path("to_png_spec.png")
-      pdf   = Grim::Pdf.new(fixture_path("smoker.pdf"))
-
-      pdf[0].save(@path, :width => 20)
-    end
-
-    it "should set width" do
-      width, height = dimensions_for_path(@path)
-      width.should == 20
-    end
-  end
-
-  describe "#save with quality option" do
-    before(:each) do
-      @path = tmp_path("to_png_spec.jpg")
-      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
-    end
-
-    it "should use quality" do
-      @pdf[0].save(@path, :quality => 20)
-      lower_size = File.size(@path)
-
-      @pdf[0].save(@path, :quality => 90)
-      higher_size = File.size(@path)
-
-      (lower_size < higher_size).should be_true
-    end
-  end
-
-  describe "#save with density option" do
-    before(:each) do
-      @path = tmp_path("to_png_spec.jpg")
-      @pdf  = Grim::Pdf.new(fixture_path("smoker.pdf"))
-    end
-
-    it "should use density" do
-      lower_time  = Benchmark.realtime { @pdf[0].save(@path, :density => 20) }
-      higher_time = Benchmark.realtime { @pdf[0].save(@path, :density => 300) }
-
-      (lower_time < higher_time).should be_true
-    end
-  end
-
-  describe "#save with an unprocessable PDF" do
-    let(:path) { tmp_path("unprocessable.jpg") }
-    let(:pdf)  { Grim::Pdf.new(fixture_path("unprocessable.pdf")) }
-
-    it "should raise an error" do
-      lambda { pdf[0].save(path) }.should raise_error(Grim::UnprocessablePage, /missing an image filename/)
-    end
-  end
+  # describe "#save with an unprocessable PDF" do
+  #   let(:path) { tmp_path("unprocessable.jpg") }
+  #   let(:pdf)  { Grim::Pdf.new(fixture_path("unprocessable.pdf")) }
+  #
+  #   it "should raise an error" do
+  #     lambda { pdf[0].save(path) }.should raise_error(Grim::UnprocessablePage, /missing an image filename/)
+  #   end
+  # end
 
   describe "#text" do
     it "should return the text from the selected page" do

data/spec/lib/grim/pdf_spec.rb

@@ -19,9 +19,10 @@ describe Grim::Pdf do
   end
 
   describe "#count" do
-    it "should return 25" do
+    it "should call Grim.processor.count with pdf path" do
+      Grim.processor.should_receive(:count).with(fixture_path("smoker.pdf"))
       pdf = Grim::Pdf.new(fixture_path("smoker.pdf"))
-      pdf.count.should == 25
+      pdf.count
     end
   end
 

data/spec/lib/grim_spec.rb

@@ -2,6 +2,10 @@
 require 'spec_helper'
 
 describe Grim do
+  it "should have a default processor" do
+    Grim.processor.class.should == Grim::ImageMagickProcessor
+  end
+
   it "should have a VERSION constant" do
     Grim.const_defined?('VERSION').should be_true
   end
@@ -18,7 +22,7 @@ describe Grim do
     Grim::DENSITY.should == 300
   end
 
-  describe "#new" do
+  describe "#reap" do
     it "should return an instance of Grim::Pdf" do
       Grim.reap(fixture_path("smoker.pdf")).class.should == Grim::Pdf
     end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: grim
 version: !ruby/object:Gem::Version 
-  hash: 31
+  hash: 19
   prerelease: 
   segments: 
   - 0
-  - 2
-  - 4
-  version: 0.2.4
+  - 3
+  - 0
+  version: 0.3.0
 platform: ruby
 authors: 
 - Jonathan Hoyt
@@ -15,24 +15,9 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-27 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
-  name: safe_shell
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
-    - - ~>
-      - !ruby/object:Gem::Version 
-        hash: 23
-        segments: 
-        - 1
-        - 0
-        - 0
-        version: 1.0.0
-  type: :runtime
-  version_requirements: *id001
+date: 2011-10-04 00:00:00 Z
+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
@@ -50,12 +35,16 @@ files:
 - Rakefile
 - grim.gemspec
 - lib/grim.rb
+- lib/grim/image_magick_processor.rb
+- lib/grim/multi_processor.rb
 - lib/grim/page.rb
 - lib/grim/pdf.rb
 - lib/grim/version.rb
 - lib/pdf_info.ps
 - spec/fixtures/smoker.pdf
 - spec/fixtures/unprocessable.pdf
+- spec/lib/grim/image_magick_processor_spec.rb
+- spec/lib/grim/multi_processor_spec.rb
 - spec/lib/grim/page_spec.rb
 - spec/lib/grim/pdf_spec.rb
 - spec/lib/grim_spec.rb
@@ -96,6 +85,8 @@ summary: Extract slides and text from a PDF.
 test_files: 
 - spec/fixtures/smoker.pdf
 - spec/fixtures/unprocessable.pdf
+- spec/lib/grim/image_magick_processor_spec.rb
+- spec/lib/grim/multi_processor_spec.rb
 - spec/lib/grim/page_spec.rb
 - spec/lib/grim/pdf_spec.rb
 - spec/lib/grim_spec.rb