grim 1.0.0 → 1.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d9b3ea24639d459434c20b2f23e417e13b811a6a
+  data.tar.gz: d25c76a9a4ead4f3a3067eb40a364ff532460911
+SHA512:
+  metadata.gz: cb6007819bb63ba6b07c253e978bcad0b792adcfac87f96ff1ea3b11fa4e94621384bb182e8413abc08efa37f984a70f6d3f1643a2d922e7f9147b42ae98a487
+  data.tar.gz: 64c20dc98e97cf1a341ef904d7c038feffe54acdd00e21c4d2f1dded2d5a756861e8e665d7910f9b94d0f457dd8734a0951110095c0b6f1b3116ea35d7866224

data/lib/grim/page.rb

@@ -8,11 +8,16 @@ module Grim
     #
     # 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 @@ module Grim
     # 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

data/lib/grim/pdf.rb

@@ -9,10 +9,15 @@ module Grim
     # 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 @@ module Grim
     #
     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

data/lib/grim/version.rb

@@ -1,4 +1,4 @@
 # encoding: UTF-8
 module Grim
-  VERSION = "1.0.0" unless defined?(::Grim::VERSION)
+  VERSION = "1.1.0" unless defined?(::Grim::VERSION)
 end

data/spec/lib/grim/page_spec.rb

@@ -47,7 +47,13 @@ describe Grim::Page do
   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

metadata

@@ -1,15 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: grim
 version: !ruby/object:Gem::Version
-  version: 1.0.0
-  prerelease: 
+  version: 1.1.0
 platform: ruby
 authors:
 - Jonathan Hoyt
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-12 00:00:00.000000000 Z
+date: 2014-11-25 00:00:00.000000000 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
@@ -21,7 +20,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - LICENSE
 - README.textile
@@ -44,27 +43,26 @@ files:
 - spec/spec_helper.rb
 homepage: http://github.com/jonmagic/grim
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: grim
-rubygems_version: 1.8.23
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Extract slides and text from a PDF.
 test_files:
 - spec/fixtures/smoker.pdf