pdftoimage 0.1.1 → 0.1.2

data/ChangeLog.rdoc

@@ -1,4 +1,9 @@
-=== 0.1.0 / 2010-11-08
+=== 0.1.2 / 2010-11-11
+* Added support for blocks upon opening a PDF
+* Image objects now support the "quality" method for JPEG/MIFF/PNG compression levels.
+* PDF conversion is now deferred until saving. This greatly speeds up the conversion process in cases where you only want a few pages out of a large document converted.
+
+=== 0.1.1 / 2010-11-10
 
 * Initial release:
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    pdftoimage (0.1.1)
+    pdftoimage (0.1.2)
 
 GEM
   remote: http://rubygems.org/

data/gemspec.yml

@@ -3,10 +3,11 @@ summary: "A ruby gem for converting PDF documents into a series of images."
 description: "A ruby gem for converting PDF documents into a series of images. This module is based off poppler_utils and ImageMagick."
 license: MIT
 authors: Rob Flynn
-homepage: http://rubygems.org/gems/pdftoimage
+homepage: https://github.com/robflynn/pdftoimage
 email: rob@thingerly.com
 has_yard: true
 
 development_dependencies:
   bundler: ~> 1.0.0
   yard: ~> 0.6.0
+

data/lib/pdftoimage.rb

@@ -30,33 +30,75 @@ module PDFToImage
     #
     # @param [filename] The filename of the PDF to open
     # @return [Array] An array of images
-    def open(filename)
-      target_path = random_filename
-
+    def open(filename, &block)
       if not File.exists?(filename)
         raise PDFError, "File '#{filename}' not found."
       end
 
-      cmd = "pdftoppm -png #{filename} #{target_path}"
+      pages = page_count(filename)
+
+      # Array of images
+      images = []
+
+      1.upto(pages) { |n|
+        dimensions = page_size(filename, n)
+        image = Image.new(filename, random_filename, n, dimensions)
+        images << image
+      }
+
+      images.each(&block) if block_given?
+
+      return images
 
-      `#{cmd}`
+    end
+
+    # Executes the specified command, returning the output.
+    #
+    # @param [cmd] The command to run
+    # @return [String] The output of the command
+    def exec(cmd, error = nil)
+      output = `#{cmd}`
       if $? != 0
-        raise PDFError, "Error reading PDF."
+        if error == nil
+          raise PDFError, "Error executing command: #{cmd}"
+        else
+          raise PDFError, error
+        end
       end
 
-      pngs = Dir.glob("#{target_path}*.png")
+      return output
+    end
 
-      images = []
+    private
 
-      pngs.each do |png|
-        image = Image.new(png)
-        images << image
+    def page_size(filename, page)
+      cmd = "pdfinfo -f #{page} -l #{page} #{filename}"
+      output = exec(cmd)
+
+      matches = /^Page.*?size:.*?(\d+).*?(\d+)/.match(output)
+      if matches.nil?
+        raise PDFError, "Unable to determine page size."
       end
 
-      return images.sort!
+      scale = 2.08333333333333333
+      dimension = {
+        :width => (matches[1].to_i * scale).to_i,
+        :height => (matches[2].to_i * scale).to_i
+      }
+
+      dimension
     end
 
-    private
+    def page_count(filename)
+      cmd = "pdfinfo #{filename}"
+      output = exec(cmd)
+      matches = /^Pages:.*?(\d+)$/.match(output)
+      if matches.nil?
+        raise PDFError, "Error determining page count."
+      end
+
+      return matches[1].to_i
+    end
 
     # Generate a random file name in the system's tmp folder
     def random_filename

data/lib/pdftoimage/image.rb

@@ -1,17 +1,20 @@
 module PDFToImage
 
+  # A class which is instantiated by PDFToImage when a PDF document
+  # is opened.
   class Image
+    attr_reader :pdf_name
     attr_reader :filename
     attr_reader :width
     attr_reader :height
-    attr_reader :format
     attr_reader :page
     attr_reader :args
+    attr_reader :opened
 
-    # We currently only support resizing, as that's all I need at the moment
-    # selfish, but I need to return to the main project
+    # ImageMagick methods that we currently support.
     CUSTOM_IMAGE_METHODS = [
-      "resize"
+      "resize",
+      "quality"
     ]
 
     CUSTOM_IMAGE_METHODS.each do |method|
@@ -25,20 +28,16 @@ module PDFToImage
     # Image constructor
     #
     # @param [filename] The name of the image file to open
-    def initialize(filename)
+    def initialize(pdf_name, filename, page, page_size)
       @args = []
 
+      @pdf_name = pdf_name
       @filename = filename
+      @opened = false
+      @width = page_size[:width]
+      @height = page_size[:height]
 
-      info = identify()
-
-      @width = info[:width]
-      @height = info[:height]
-      @format = info[:format]
-
-      tmp_base = File.basename(filename, File.extname(filename))
-      pieces = tmp_base.split('-')
-      @page = pieces[-1].to_i
+      @page = page
     end
 
     # Saves the converted image to the specified location
@@ -46,6 +45,9 @@ module PDFToImage
     # @param [outname] The output filename of the image
     #
     def save(outname)
+
+      generate_temp_file
+
       cmd = "convert "
 
       if not @args.empty?
@@ -54,10 +56,7 @@ module PDFToImage
       
       cmd += "#{@filename} #{outname}"
 
-      `#{cmd}`
-      if $? != 0
-        raise PDFError, "Error converting file: #{cmd}"
-      end
+      PDFToImage::exec(cmd)
 
       return true
     end
@@ -74,22 +73,15 @@ module PDFToImage
 
     private 
 
-    def identify
-      cmd = "identify #{@filename}"
-
-      result = `#{cmd}`
-      unless $?.success?
-        raise PDFToImage::PDFError, "Error executing #{cmd}"
+    def generate_temp_file
+      if @opened == false
+        cmd = "pdftoppm -png -f #{@page} -l #{@page} #{@pdf_name} #{@filename}"
+        PDFToImage::exec(cmd)
+        @filename = "#{@filename}-#{@page}.png"
+        @opened = true
       end
 
-      info = result.strip.split(' ')
-      dimensions = info[2].split('x')
-
-      return {
-        :format => info[1],
-        :width => dimensions[0],
-        :height => dimensions[1]
-      }
+      return true
     end
 
   end

data/lib/pdftoimage/version.rb

@@ -1,4 +1,4 @@
 module PDFToImage
   # pdftoimage version
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/spec/pdftoimage_spec.rb

@@ -19,13 +19,21 @@ describe PDFToImage do
       File.unlink('spec/tmp.jpg')
     end
 
-    it "should allow resizing" do
+    it "should allow resizing and quality control" do
       @pages = PDFToImage.open('spec/3pages.pdf')
-      @pages[0].resize('50%').save('spec/tmp2.jpg')
+      @pages[0].resize('50%').quality('80%').save('spec/tmp2.jpg')
       File.exists?('spec/tmp2.jpg').should equal true
       File.unlink('spec/tmp2.jpg')
     end
 
+    it "should work with blocks" do
+      counter = 0
+      PDFToImage.open("spec/3pages.pdf") do |page|
+        counter = counter + 1
+      end
+      counter.should equal 3
+    end
+
 
   end
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: pdftoimage
 version: !ruby/object:Gem::Version 
-  hash: 25
+  hash: 31
   prerelease: false
   segments: 
   - 0
   - 1
-  - 1
-  version: 0.1.1
+  - 2
+  version: 0.1.2
 platform: ruby
 authors: 
 - Rob Flynn
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-11-10 00:00:00 +00:00
+date: 2010-11-11 00:00:00 +00:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -80,7 +80,7 @@ files:
 - spec/pdftoimage_spec.rb
 - .document
 has_rdoc: yard
-homepage: http://rubygems.org/gems/pdftoimage
+homepage: https://github.com/robflynn/pdftoimage
 licenses: 
 - MIT
 post_install_message: