pdftoimage 0.1.1

Sign up to get free protection for your applications and to get access to all the features.
data/.bundle/config ADDED
@@ -0,0 +1,2 @@
1
+ ---
2
+ BUNDLE_DISABLE_SHARED_GEMS: "1"
data/.document ADDED
@@ -0,0 +1,3 @@
1
+ -
2
+ ChangeLog.*
3
+ LICENSE.txt
data/.rspec ADDED
@@ -0,0 +1 @@
1
+ --colour --format documentation
data/.yardopts ADDED
@@ -0,0 +1 @@
1
+ --markup rdoc --title "pdftoimage Documentation" --protected
data/ChangeLog.rdoc ADDED
@@ -0,0 +1,4 @@
1
+ === 0.1.0 / 2010-11-08
2
+
3
+ * Initial release:
4
+
data/Gemfile ADDED
@@ -0,0 +1,10 @@
1
+ source :rubygems
2
+
3
+ gemspec
4
+
5
+ group :development do
6
+ gem 'rake', '~> 0.8.7'
7
+ gem 'ore-core', '~> 0.1.0'
8
+ gem 'rspec', '~> 2.0.0'
9
+ gem 'yard', '~> 0.6.0'
10
+ end
data/Gemfile.lock ADDED
@@ -0,0 +1,33 @@
1
+ PATH
2
+ remote: .
3
+ specs:
4
+ pdftoimage (0.1.1)
5
+
6
+ GEM
7
+ remote: http://rubygems.org/
8
+ specs:
9
+ diff-lcs (1.1.2)
10
+ ore-core (0.1.0)
11
+ rake (0.8.7)
12
+ rspec (2.0.1)
13
+ rspec-core (~> 2.0.1)
14
+ rspec-expectations (~> 2.0.1)
15
+ rspec-mocks (~> 2.0.1)
16
+ rspec-core (2.0.1)
17
+ rspec-expectations (2.0.1)
18
+ diff-lcs (>= 1.1.2)
19
+ rspec-mocks (2.0.1)
20
+ rspec-core (~> 2.0.1)
21
+ rspec-expectations (~> 2.0.1)
22
+ yard (0.6.1)
23
+
24
+ PLATFORMS
25
+ ruby
26
+
27
+ DEPENDENCIES
28
+ bundler (~> 1.0.0)
29
+ ore-core (~> 0.1.0)
30
+ pdftoimage!
31
+ rake (~> 0.8.7)
32
+ rspec (~> 2.0.0)
33
+ yard (~> 0.6.0)
data/LICENSE.txt ADDED
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2010 Rob Flynn
2
+
3
+ Permission is hereby granted, free of charge, to any person obtaining
4
+ a copy of this software and associated documentation files (the
5
+ "Software"), to deal in the Software without restriction, including
6
+ without limitation the rights to use, copy, modify, merge, publish,
7
+ distribute, sublicense, and/or sell copies of the Software, and to
8
+ permit persons to whom the Software is furnished to do so, subject to
9
+ the following conditions:
10
+
11
+ The above copyright notice and this permission notice shall be
12
+ included in all copies or substantial portions of the Software.
13
+
14
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
15
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
16
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
17
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
18
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
19
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
20
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
data/README.rdoc ADDED
@@ -0,0 +1,38 @@
1
+ = pdftoimage
2
+
3
+ * {Homepage}[http://rubygems.org/gems/pdftoimage]
4
+
5
+ == Description
6
+
7
+ PDFToImage is a ruby gem which allows for conversion of a PDF document into
8
+ images. It uses poppler_utils to first convert the document to PNG and then
9
+ allows usage of ImageMagick to convert the image into other formats.
10
+
11
+ The reasoning behind using poppler_utils is due to the fact that ghostscript
12
+ occasionally has trouble with certain PDF documents which poppler_utils seems
13
+ to be able to parse without error.
14
+
15
+ == Examples
16
+
17
+ require 'pdftoimage'
18
+ images = PDFToImage.open('somefile.pdf')
19
+ images.each do |img|
20
+ img.resize('50%').save("output/page-#{img.page}.jpg")
21
+ end
22
+
23
+ == Requirements
24
+
25
+ poppler_utils
26
+
27
+ ImageMagick
28
+
29
+
30
+ == Install
31
+
32
+ $ gem install pdftoimage
33
+
34
+ == Copyright
35
+
36
+ Copyright (c) 2010 Rob Flynn
37
+
38
+ See LICENSE.txt for details.
data/Rakefile ADDED
@@ -0,0 +1,26 @@
1
+ require 'rubygems'
2
+
3
+ begin
4
+ require 'bundler'
5
+ rescue LoadError => e
6
+ STDERR.puts e.message
7
+ STDERR.puts "Run `gem install bundler` to install Bundler."
8
+ exit e.status_code
9
+ end
10
+
11
+ begin
12
+ Bundler.setup(:development)
13
+ rescue Bundler::BundlerError => e
14
+ STDERR.puts e.message
15
+ STDERR.puts "Run `bundle install` to install missing gems."
16
+ exit e.status_code
17
+ end
18
+
19
+ require 'rake'
20
+
21
+ require 'rspec/core/rake_task'
22
+ RSpec::Core::RakeTask.new
23
+ task :default => :spec
24
+
25
+ require 'yard'
26
+ YARD::Rake::YardocTask.new
data/gemspec.yml ADDED
@@ -0,0 +1,12 @@
1
+ name: pdftoimage
2
+ summary: "A ruby gem for converting PDF documents into a series of images."
3
+ description: "A ruby gem for converting PDF documents into a series of images. This module is based off poppler_utils and ImageMagick."
4
+ license: MIT
5
+ authors: Rob Flynn
6
+ homepage: http://rubygems.org/gems/pdftoimage
7
+ email: rob@thingerly.com
8
+ has_yard: true
9
+
10
+ development_dependencies:
11
+ bundler: ~> 1.0.0
12
+ yard: ~> 0.6.0
data/lib/pdftoimage.rb ADDED
@@ -0,0 +1,74 @@
1
+ require 'tmpdir'
2
+ require 'pdftoimage/version'
3
+ require 'pdftoimage/image'
4
+
5
+ module PDFToImage
6
+ class PDFError < RuntimeError; end
7
+ end
8
+
9
+ module PDFToImage
10
+ # A class variable for storing the location of our temp folder
11
+ @@pdf_temp_dir = File.join(Dir.tmpdir())
12
+
13
+ begin
14
+ tmp = `pdftoppm -v 2>&1`
15
+ raise(PDFToImage::PDFError, "poppler_utils not installed") unless tmp.index('Poppler')
16
+ rescue Errno::ENOENT
17
+ raise PDFToImage::PDFError, "poppler_utils not installed"
18
+ end
19
+
20
+ begin
21
+ tmp = `identify -version 2>&1`
22
+ raise(PDFToImage::PDFError, "ImageMagick not installed") unless tmp.index('ImageMagick')
23
+ rescue Errno::ENOENT
24
+ raise PDFToImage::PDFError, "ImageMagick not installed"
25
+ end
26
+
27
+ class << self
28
+
29
+ # Opens a PDF document and prepares it for splitting into images.
30
+ #
31
+ # @param [filename] The filename of the PDF to open
32
+ # @return [Array] An array of images
33
+ def open(filename)
34
+ target_path = random_filename
35
+
36
+ if not File.exists?(filename)
37
+ raise PDFError, "File '#{filename}' not found."
38
+ end
39
+
40
+ cmd = "pdftoppm -png #{filename} #{target_path}"
41
+
42
+ `#{cmd}`
43
+ if $? != 0
44
+ raise PDFError, "Error reading PDF."
45
+ end
46
+
47
+ pngs = Dir.glob("#{target_path}*.png")
48
+
49
+ images = []
50
+
51
+ pngs.each do |png|
52
+ image = Image.new(png)
53
+ images << image
54
+ end
55
+
56
+ return images.sort!
57
+ end
58
+
59
+ private
60
+
61
+ # Generate a random file name in the system's tmp folder
62
+ def random_filename
63
+ File.join(@@pdf_temp_dir, random_name)
64
+ end
65
+
66
+ # Generate a random name of {#length} characters.
67
+ def random_name(length = 15)
68
+ @@chars ||= ("a".."z").to_a + ("A".."Z").to_a + ("1".."9").to_a
69
+ return 'pdftoimage-' + Array.new(length, '').collect{@@chars[rand(@@chars.size)]}.join
70
+ end
71
+
72
+ end
73
+
74
+ end
@@ -0,0 +1,97 @@
1
+ module PDFToImage
2
+
3
+ class Image
4
+ attr_reader :filename
5
+ attr_reader :width
6
+ attr_reader :height
7
+ attr_reader :format
8
+ attr_reader :page
9
+ attr_reader :args
10
+
11
+ # We currently only support resizing, as that's all I need at the moment
12
+ # selfish, but I need to return to the main project
13
+ CUSTOM_IMAGE_METHODS = [
14
+ "resize"
15
+ ]
16
+
17
+ CUSTOM_IMAGE_METHODS.each do |method|
18
+ define_method(method.to_sym) do |*args|
19
+ @args << "-#{method} #{args.join(' ')}"
20
+
21
+ self
22
+ end
23
+ end
24
+
25
+ # Image constructor
26
+ #
27
+ # @param [filename] The name of the image file to open
28
+ def initialize(filename)
29
+ @args = []
30
+
31
+ @filename = filename
32
+
33
+ info = identify()
34
+
35
+ @width = info[:width]
36
+ @height = info[:height]
37
+ @format = info[:format]
38
+
39
+ tmp_base = File.basename(filename, File.extname(filename))
40
+ pieces = tmp_base.split('-')
41
+ @page = pieces[-1].to_i
42
+ end
43
+
44
+ # Saves the converted image to the specified location
45
+ #
46
+ # @param [outname] The output filename of the image
47
+ #
48
+ def save(outname)
49
+ cmd = "convert "
50
+
51
+ if not @args.empty?
52
+ cmd += "#{@args.join(' ')} "
53
+ end
54
+
55
+ cmd += "#{@filename} #{outname}"
56
+
57
+ `#{cmd}`
58
+ if $? != 0
59
+ raise PDFError, "Error converting file: #{cmd}"
60
+ end
61
+
62
+ return true
63
+ end
64
+
65
+ def <=>(img)
66
+ if @page == img.page
67
+ return 0
68
+ elsif @page < img.page
69
+ return -1
70
+ else
71
+ return 1
72
+ end
73
+ end
74
+
75
+ private
76
+
77
+ def identify
78
+ cmd = "identify #{@filename}"
79
+
80
+ result = `#{cmd}`
81
+ unless $?.success?
82
+ raise PDFToImage::PDFError, "Error executing #{cmd}"
83
+ end
84
+
85
+ info = result.strip.split(' ')
86
+ dimensions = info[2].split('x')
87
+
88
+ return {
89
+ :format => info[1],
90
+ :width => dimensions[0],
91
+ :height => dimensions[1]
92
+ }
93
+ end
94
+
95
+ end
96
+
97
+ end
@@ -0,0 +1,4 @@
1
+ module PDFToImage
2
+ # pdftoimage version
3
+ VERSION = "0.1.1"
4
+ end
@@ -0,0 +1,10 @@
1
+ # -*- encoding: utf-8 -*-
2
+
3
+ begin
4
+ Ore::Specification.new do |gemspec|
5
+ # custom logic here
6
+ end
7
+ rescue NameError
8
+ STDERR.puts "The 'pdftoimage.gemspec' file requires Ore."
9
+ STDERR.puts "Run `gem install ore-core` to install Ore."
10
+ end
data/spec/3pages.pdf ADDED
Binary file
@@ -0,0 +1,31 @@
1
+ require 'spec_helper'
2
+ require 'pdftoimage'
3
+
4
+ describe PDFToImage do
5
+ it "should have a VERSION constant" do
6
+ PDFToImage.const_get('VERSION').should_not be_empty
7
+ end
8
+
9
+ describe "3pages.pdf" do
10
+ it "should have three pages" do
11
+ @pages = PDFToImage.open('spec/3pages.pdf')
12
+ @pages.size.should equal 3
13
+ end
14
+
15
+ it "should allow saving" do
16
+ @pages = PDFToImage.open('spec/3pages.pdf')
17
+ @pages[0].save('spec/tmp.jpg')
18
+ File.exists?('spec/tmp.jpg').should equal true
19
+ File.unlink('spec/tmp.jpg')
20
+ end
21
+
22
+ it "should allow resizing" do
23
+ @pages = PDFToImage.open('spec/3pages.pdf')
24
+ @pages[0].resize('50%').save('spec/tmp2.jpg')
25
+ File.exists?('spec/tmp2.jpg').should equal true
26
+ File.unlink('spec/tmp2.jpg')
27
+ end
28
+
29
+
30
+ end
31
+ end
@@ -0,0 +1,4 @@
1
+ require 'rspec'
2
+ require 'pdftoimage/version'
3
+
4
+ include PDFToImage
metadata ADDED
@@ -0,0 +1,119 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: pdftoimage
3
+ version: !ruby/object:Gem::Version
4
+ hash: 25
5
+ prerelease: false
6
+ segments:
7
+ - 0
8
+ - 1
9
+ - 1
10
+ version: 0.1.1
11
+ platform: ruby
12
+ authors:
13
+ - Rob Flynn
14
+ autorequire:
15
+ bindir: bin
16
+ cert_chain: []
17
+
18
+ date: 2010-11-10 00:00:00 +00:00
19
+ default_executable:
20
+ dependencies:
21
+ - !ruby/object:Gem::Dependency
22
+ name: yard
23
+ prerelease: false
24
+ requirement: &id001 !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ~>
28
+ - !ruby/object:Gem::Version
29
+ hash: 7
30
+ segments:
31
+ - 0
32
+ - 6
33
+ - 0
34
+ version: 0.6.0
35
+ type: :development
36
+ version_requirements: *id001
37
+ - !ruby/object:Gem::Dependency
38
+ name: bundler
39
+ prerelease: false
40
+ requirement: &id002 !ruby/object:Gem::Requirement
41
+ none: false
42
+ requirements:
43
+ - - ~>
44
+ - !ruby/object:Gem::Version
45
+ hash: 23
46
+ segments:
47
+ - 1
48
+ - 0
49
+ - 0
50
+ version: 1.0.0
51
+ type: :development
52
+ version_requirements: *id002
53
+ description: A ruby gem for converting PDF documents into a series of images. This module is based off poppler_utils and ImageMagick.
54
+ email: rob@thingerly.com
55
+ executables: []
56
+
57
+ extensions: []
58
+
59
+ extra_rdoc_files:
60
+ - README.rdoc
61
+ - LICENSE.txt
62
+ - ChangeLog.rdoc
63
+ files:
64
+ - spec/spec_helper.rb
65
+ - spec/3pages.pdf
66
+ - lib/pdftoimage/version.rb
67
+ - gemspec.yml
68
+ - ChangeLog.rdoc
69
+ - .rspec
70
+ - pdftoimage.gemspec
71
+ - .yardopts
72
+ - .bundle/config
73
+ - lib/pdftoimage/image.rb
74
+ - Gemfile
75
+ - Rakefile
76
+ - LICENSE.txt
77
+ - lib/pdftoimage.rb
78
+ - README.rdoc
79
+ - Gemfile.lock
80
+ - spec/pdftoimage_spec.rb
81
+ - .document
82
+ has_rdoc: yard
83
+ homepage: http://rubygems.org/gems/pdftoimage
84
+ licenses:
85
+ - MIT
86
+ post_install_message:
87
+ rdoc_options: []
88
+
89
+ require_paths:
90
+ - lib
91
+ required_ruby_version: !ruby/object:Gem::Requirement
92
+ none: false
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ hash: 3
97
+ segments:
98
+ - 0
99
+ version: "0"
100
+ required_rubygems_version: !ruby/object:Gem::Requirement
101
+ none: false
102
+ requirements:
103
+ - - ">="
104
+ - !ruby/object:Gem::Version
105
+ hash: 23
106
+ segments:
107
+ - 1
108
+ - 3
109
+ - 6
110
+ version: 1.3.6
111
+ requirements: []
112
+
113
+ rubyforge_project: pdftoimage
114
+ rubygems_version: 1.3.7
115
+ signing_key:
116
+ specification_version: 3
117
+ summary: A ruby gem for converting PDF documents into a series of images.
118
+ test_files:
119
+ - spec/pdftoimage_spec.rb