Merge pull request #20 from jonmagic/pdftotext-path

Allow passing full path to pdftotext

Author: jonmagic

lib/grim/page.rb

@@ -8,11 +8,16 @@ class Page
     #
     # pdf - the pdf this page belongs to
     # index - the index of the page in the array of pages
+    # options - A Hash of options.
+    #           :pdftotext_path - The String path of where to find the pdftotext
+    #                             binary to use when extracting text
+    #                             (default: "pdftotext").
     #
-    def initialize(pdf, index)
+    def initialize(pdf, index, options = {})
       @pdf    = pdf
       @index  = index
       @number   = index + 1
+      @pdftotext_path = options[:pdftotext_path] || 'pdftotext'
     end
 
     # Extracts the selected page and turns it into an image.
@@ -45,7 +50,7 @@ def save(path, options={})
     # Returns a String.
     #
     def text
-      `#{["pdftotext", "-enc", "UTF-8", "-f", @number, "-l", @number, Shellwords.escape(@pdf.path), "-"].join(' ')}`
+      `#{[@pdftotext_path, "-enc", "UTF-8", "-f", @number, "-l", @number, Shellwords.escape(@pdf.path), "-"].join(' ')}`
     end
   end
-end
+end

lib/grim/pdf.rb

@@ -9,10 +9,15 @@ class Pdf
     # variables if pdf is found.
     #
     # path - A String or Path to the pdf
+    # options - A Hash of options.
+    #           :pdftotext_path - The String path of where to find the pdftotext
+    #                             binary to use when extracting text
+    #                             (default: "pdftotext").
     #
-    def initialize(path)
+    def initialize(path, options = {})
       raise Grim::PdfNotFound unless File.exists?(path)
       @path = path
+      @pdftotext_path = options[:pdftotext_path] || 'pdftotext'
     end
 
     # Shells out to ghostscript to read the pdf with the pdf_info.ps script
@@ -43,14 +48,14 @@ def count
     #
     def [](index)
       raise Grim::PageNotFound unless index >= 0 && index < count
-      Grim::Page.new(self, index)
+      Grim::Page.new(self, index, pdftotext_path: @pdftotext_path)
     end
 
     def each
       (0..(count-1)).each do |index|
-        yield Grim::Page.new(self, index)
+        yield Grim::Page.new(self, index, pdftotext_path: @pdftotext_path)
       end
     end
 
   end
-end
+end

spec/lib/grim/page_spec.rb

@@ -47,7 +47,13 @@
   describe "#text" do
     it "should return the text from the selected page" do
       pdf = Grim::Pdf.new(fixture_path("smoker.pdf"))
-      pdf[1].text.should == "Step 1: get someone to print this curve for you to scale, 72” wide\n\nStep 2: Get a couple 55 gallon drums\n\n\f"
+      pdf[1].text.should == "Step 1: get someone to print this curve for you to scale, 72” wide\nStep 2: Get a couple 55 gallon drums\n\n\f"
+    end
+
+    it "works with full path to pdftotext" do
+      pdftotext_path = `which pdftotext`.chomp
+      pdf = Grim::Pdf.new(fixture_path("smoker.pdf"), pdftotext_path: pdftotext_path)
+      pdf[1].text.should == "Step 1: get someone to print this curve for you to scale, 72” wide\nStep 2: Get a couple 55 gallon drums\n\n\f"
     end
   end
 end