Issue #16, customizable graphicsmagick --density when extracting images.

Author: jashkenas

index.html

@@ -177,13 +177,15 @@ <h2 id="usage">Usage</h2>
     </p>
 
     <p>
-      <b class="header">images</b><code>--size --format --pages </code>
+      <b class="header">images</b><code>--size --format --pages --density</code>
       <span class="alias">Ruby: <b>extract_images</b></span>
       <br />
       Generates an image for each page in the document at the specified resolution
       and format. Pass <tt>--pages</tt> or <tt>-p</tt> to choose the specific pages to
       image. Passing<br /> <tt>--size</tt> or <tt>-s</tt> will specify the desired
-      image resolution, and <tt>--format</tt> or <tt>-f</tt> will select the format of the final images.
+      image resolution, <tt>--density</tt> or <tt>-d</tt> will specify the DPI to rasterize the images
+      at during conversion by GraphicsMagick, and <tt>--format</tt> or <tt>-f</tt> 
+      will select the format of the final images.
     </p>
 <pre>
 docsplit images example.pdf

lib/docsplit/command_line.rb

@@ -85,6 +85,9 @@ def parse_options
         opts.on('-f', '--format [FORMAT]', 'set image format (pdf, jpg, gif...)') do |t|
           @options[:format] = t.split(',')
         end
+        opts.on('-d', '--density [NUM]', 'set image density (DPI) when rasterizing') do |d|
+          @options[:density] = d
+        end
         opts.on('--[no-]ocr', 'force OCR to be used, or disable OCR') do |o|
           @options[:ocr] = o
         end

lib/docsplit/image_extractor.rb

@@ -4,9 +4,9 @@ module Docsplit
   # nicely sized images.
   class ImageExtractor
 
-    DENSITY_ARG     = "-density 150"
     MEMORY_ARGS     = "-limit memory 256MiB -limit map 512MiB"
     DEFAULT_FORMAT  = :png
+    DEFAULT_DENSITY = '150'
 
     # Extract a list of PDFs as rasterized page images, according to the
     # configuration in options.
@@ -34,7 +34,7 @@ def convert(pdf, size, format, previous=nil)
       pages     = @pages || '1-' + Docsplit.extract_length(pdf).to_s
       escaped_pdf = ESCAPE[pdf]
       FileUtils.mkdir_p(directory) unless File.exists?(directory)
-      common    = "#{MEMORY_ARGS} #{DENSITY_ARG} #{resize_arg(size)} #{quality_arg(format)}"
+      common    = "#{MEMORY_ARGS} -density #{@density} #{resize_arg(size)} #{quality_arg(format)}"
       if previous
         FileUtils.cp(Dir[directory_for(previous) + '/*'], directory)
         result = `MAGICK_TMPDIR=#{tempdir} OMP_NUM_THREADS=2 gm mogrify #{common} -unsharp 0x0.5+0.75 \"#{directory}/*.#{format}\" 2>&1`.chomp
@@ -58,6 +58,7 @@ def convert(pdf, size, format, previous=nil)
     def extract_options(options)
       @output  = options[:output]  || '.'
       @pages   = options[:pages]
+      @density = options[:density] || DEFAULT_DENSITY
       @formats = [options[:format] || DEFAULT_FORMAT].flatten
       @sizes   = [options[:size]].flatten.compact
       @sizes   = [nil] if @sizes.empty?