pdftoimage 0.1.6 → 0.1.7
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/{LICENSE.txt → LICENSE} +0 -0
- data/lib/pdftoimage.rb +87 -89
- data/lib/pdftoimage/image.rb +113 -112
- data/lib/pdftoimage/version.rb +2 -2
- metadata +42 -75
- data/.bundle/config +0 -2
- data/.document +0 -3
- data/.rspec +0 -1
- data/.yardopts +0 -1
- data/Gemfile +0 -12
- data/Gemfile.lock +0 -35
- data/Rakefile +0 -26
- data/gemspec.yml +0 -13
- data/pdftoimage.gemspec +0 -15
- data/spec/10pages.pdf +0 -0
- data/spec/11pages.pdf +0 -0
- data/spec/3pages.pdf +0 -0
- data/spec/pdftoimage_spec.rb +0 -83
- data/spec/spec_helper.rb +0 -13
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: eebf9a790b95c556d3b47ba87bd69998ccd15529
|
4
|
+
data.tar.gz: bc3a5653ae433aee369c98325f0358c1fec53d47
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 7d13c5805d512c7bceba7f9da7bab1f74fcc9e5fbbca9f1c951abc08614818ce97835b44b8f5cf33eddb903fc1b7ee042d453cc7cbb9742943425616504bc634
|
7
|
+
data.tar.gz: b4c38f9539b6050e52c4b5cca7971bfb78f5357dae0b17807be779832e3706f062b7a6bf65dd740648c1ac9b7e951b516ef6f6da1d7985409685792a17a0f157
|
data/{LICENSE.txt → LICENSE}
RENAMED
File without changes
|
data/lib/pdftoimage.rb
CHANGED
@@ -1,117 +1,115 @@
|
|
1
|
-
require 'tmpdir'
|
2
1
|
require 'pdftoimage/version'
|
3
2
|
require 'pdftoimage/image'
|
3
|
+
|
4
|
+
require 'tmpdir'
|
4
5
|
require 'iconv'
|
5
6
|
|
6
7
|
module PDFToImage
|
7
|
-
|
8
|
+
class PDFError < RuntimeError; end
|
8
9
|
end
|
9
10
|
|
10
11
|
module PDFToImage
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
begin
|
22
|
-
tmp = `identify -version 2>&1`
|
23
|
-
raise(PDFToImage::PDFError, "ImageMagick not installed") unless tmp.index('ImageMagick')
|
24
|
-
rescue Errno::ENOENT
|
25
|
-
raise PDFToImage::PDFError, "ImageMagick not installed"
|
26
|
-
end
|
27
|
-
|
28
|
-
class << self
|
12
|
+
# A class variable for storing the location of our temp folder
|
13
|
+
@@pdf_temp_dir = File.join(Dir.tmpdir())
|
14
|
+
|
15
|
+
begin
|
16
|
+
tmp = `pdftoppm -v 2>&1`
|
17
|
+
raise(PDFToImage::PDFError, "poppler_utils not installed") unless tmp.index('Poppler')
|
18
|
+
rescue Errno::ENOENT
|
19
|
+
raise PDFToImage::PDFError, "poppler_utils not installed"
|
20
|
+
end
|
29
21
|
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
raise PDFError, "File '#{filename}' not found."
|
37
|
-
end
|
22
|
+
begin
|
23
|
+
tmp = `identify -version 2>&1`
|
24
|
+
raise(PDFToImage::PDFError, "ImageMagick not installed") unless tmp.index('ImageMagick')
|
25
|
+
rescue Errno::ENOENT
|
26
|
+
raise PDFToImage::PDFError, "ImageMagick not installed"
|
27
|
+
end
|
38
28
|
|
39
|
-
|
29
|
+
class << self
|
30
|
+
# Opens a PDF document and prepares it for splitting into images.
|
31
|
+
#
|
32
|
+
# @param filename [String] The filename of the PDF to open
|
33
|
+
#
|
34
|
+
# @return [Array] An array of images
|
35
|
+
def open(filename, &block)
|
36
|
+
if not File.exists?(filename)
|
37
|
+
raise PDFError, "File '#{filename}' not found."
|
38
|
+
end
|
40
39
|
|
41
|
-
|
42
|
-
images = []
|
40
|
+
pages = page_count(filename)
|
43
41
|
|
44
|
-
|
45
|
-
|
46
|
-
image = Image.new(filename, random_filename, n, dimensions, pages)
|
47
|
-
images << image
|
48
|
-
}
|
42
|
+
# Array of images
|
43
|
+
images = []
|
49
44
|
|
50
|
-
|
45
|
+
1.upto(pages) { |n|
|
46
|
+
dimensions = page_size(filename, n)
|
47
|
+
image = Image.new(filename, random_filename, n, dimensions, pages)
|
48
|
+
images << image
|
49
|
+
}
|
51
50
|
|
52
|
-
|
51
|
+
images.each(&block) if block_given?
|
53
52
|
|
54
|
-
|
55
|
-
|
56
|
-
# Executes the specified command, returning the output.
|
57
|
-
#
|
58
|
-
# @param [cmd] The command to run
|
59
|
-
# @return [String] The output of the command
|
60
|
-
def exec(cmd, error = nil)
|
61
|
-
output = `#{cmd}`
|
62
|
-
if $? != 0
|
63
|
-
if error == nil
|
64
|
-
raise PDFError, "Error executing command: #{cmd}"
|
65
|
-
else
|
66
|
-
raise PDFError, error
|
53
|
+
return images
|
67
54
|
end
|
68
|
-
end
|
69
55
|
|
70
|
-
|
71
|
-
|
56
|
+
# Executes the specified command, returning the output.
|
57
|
+
#
|
58
|
+
# @param cmd [String] The command to run
|
59
|
+
# @return [String] The output of the command
|
60
|
+
def exec(cmd, error = nil)
|
61
|
+
output = `#{cmd}`
|
62
|
+
if $? != 0
|
63
|
+
if error == nil
|
64
|
+
raise PDFError, "Error executing command: #{cmd}"
|
65
|
+
else
|
66
|
+
raise PDFError, error
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
return output
|
71
|
+
end
|
72
72
|
|
73
|
-
|
73
|
+
private
|
74
74
|
|
75
|
-
|
76
|
-
|
77
|
-
|
75
|
+
def page_size(filename, page)
|
76
|
+
cmd = "pdfinfo -f #{page} -l #{page} #{filename} | grep Page"
|
77
|
+
output = exec(cmd)
|
78
78
|
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
79
|
+
matches = /^Page.*?size:.*?(\d+).*?(\d+)/.match(output)
|
80
|
+
if matches.nil?
|
81
|
+
raise PDFError, "Unable to determine page size."
|
82
|
+
end
|
83
83
|
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
84
|
+
scale = 2.08333333333333333
|
85
|
+
dimension = {
|
86
|
+
width: (matches[1].to_i * scale).to_i,
|
87
|
+
height: (matches[2].to_i * scale).to_i
|
88
|
+
}
|
89
89
|
|
90
|
-
|
91
|
-
|
90
|
+
dimension
|
91
|
+
end
|
92
92
|
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
93
|
+
def page_count(filename)
|
94
|
+
cmd = "pdfinfo #{filename} | grep Pages"
|
95
|
+
output = exec(cmd)
|
96
|
+
matches = /^Pages:.*?(\d+)$/.match(output)
|
97
|
+
if matches.nil?
|
98
|
+
raise PDFError, "Error determining page count."
|
99
|
+
end
|
100
100
|
|
101
|
-
|
102
|
-
|
101
|
+
return matches[1].to_i
|
102
|
+
end
|
103
103
|
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
104
|
+
# Generate a random file name in the system's tmp folder
|
105
|
+
def random_filename
|
106
|
+
File.join(@@pdf_temp_dir, random_name)
|
107
|
+
end
|
108
108
|
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
109
|
+
# Generate a random name of {#length} characters.
|
110
|
+
def random_name(length = 15)
|
111
|
+
@@chars ||= ("a".."z").to_a + ("A".."Z").to_a + ("1".."9").to_a
|
112
|
+
return 'pdftoimage-' + Array.new(length, '').collect { @@chars[rand(@@chars.size)] }.join
|
113
|
+
end
|
113
114
|
end
|
114
|
-
|
115
|
-
end
|
116
|
-
|
117
115
|
end
|
data/lib/pdftoimage/image.rb
CHANGED
@@ -1,115 +1,116 @@
|
|
1
1
|
module PDFToImage
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
2
|
+
# A class which is instantiated by PDFToImage when a PDF document
|
3
|
+
# is opened.
|
4
|
+
class Image
|
5
|
+
attr_reader :pdf_name
|
6
|
+
attr_reader :filename
|
7
|
+
attr_reader :width
|
8
|
+
attr_reader :height
|
9
|
+
attr_reader :page
|
10
|
+
attr_reader :args
|
11
|
+
attr_reader :opened
|
12
|
+
|
13
|
+
# ImageMagick methods that we currently support.
|
14
|
+
CUSTOM_IMAGE_METHODS = [
|
15
|
+
"resize",
|
16
|
+
"quality"
|
17
|
+
]
|
18
|
+
|
19
|
+
CUSTOM_IMAGE_METHODS.each do |method|
|
20
|
+
define_method(method.to_sym) do |*args|
|
21
|
+
@args << "-#{method} #{args.join(' ')}"
|
22
|
+
|
23
|
+
self
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
# Image constructor
|
28
|
+
#
|
29
|
+
# @param pdf_name [String] The name of the PDF
|
30
|
+
# @param filename [String] The name of the image for the specified page
|
31
|
+
# @param page [Integer] The page number of the PDF
|
32
|
+
# @param page_size [Hash] Hash containing width and height dimensions of the page
|
33
|
+
# @param page_count [integer] The number of pages in the PDF
|
34
|
+
#
|
35
|
+
def initialize(pdf_name, filename, page, page_size, page_count)
|
36
|
+
@args = []
|
37
|
+
|
38
|
+
@pdf_name = pdf_name
|
39
|
+
@filename = filename
|
40
|
+
@opened = false
|
41
|
+
@width = page_size[:width]
|
42
|
+
@height = page_size[:height]
|
43
|
+
@page_count = page_count
|
44
|
+
|
45
|
+
@page = page
|
46
|
+
end
|
47
|
+
|
48
|
+
# Saves the converted image to the specified location
|
49
|
+
#
|
50
|
+
# @param outname [String] The output filename of the image
|
51
|
+
#
|
52
|
+
def save(outname)
|
53
|
+
generate_temp_file
|
54
|
+
|
55
|
+
cmd = "convert "
|
56
|
+
|
57
|
+
if not @args.empty?
|
58
|
+
cmd += "#{@args.join(' ')} "
|
59
|
+
end
|
60
|
+
|
61
|
+
cmd += "#{@filename} #{outname}"
|
62
|
+
|
63
|
+
PDFToImage.exec(cmd)
|
64
|
+
|
65
|
+
return true
|
66
|
+
end
|
67
|
+
|
68
|
+
def <=>(img)
|
69
|
+
if @page == img.page
|
70
|
+
return 0
|
71
|
+
elsif @page < img.page
|
72
|
+
return -1
|
73
|
+
else
|
74
|
+
return 1
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
private
|
79
|
+
|
80
|
+
def generate_temp_file
|
81
|
+
if @opened == false
|
82
|
+
cmd = "pdftoppm -png -f #{@page} -l #{@page} #{@pdf_name} #{@filename}"
|
83
|
+
PDFToImage.exec(cmd)
|
84
|
+
@filename = "#{@filename}-#{page_suffix}.png"
|
85
|
+
@opened = true
|
86
|
+
end
|
87
|
+
|
88
|
+
return true
|
89
|
+
end
|
90
|
+
|
91
|
+
def page_suffix
|
92
|
+
cur_page_len = @page.to_s.length
|
93
|
+
total_page_len = @page_count.to_s.length
|
94
|
+
|
95
|
+
num_zeroes = total_page_len - cur_page_len
|
96
|
+
|
97
|
+
# This is really weird. Basically, poppler_utils does not
|
98
|
+
# prepend a '0' to the page count when the total number of
|
99
|
+
# pages is 10, 100, 1000, 10000, etc. I hate putting this here,
|
100
|
+
# but whatever...
|
101
|
+
|
102
|
+
# TODO: Keep an eye on this. This suddenly started causing problems.
|
103
|
+
# Did poppler_utils change?
|
104
|
+
# if @page_count.to_s.reverse.to_i == 1 && num_zeroes > 0
|
105
|
+
# num_zeroes = num_zeroes - 1
|
106
|
+
# end
|
107
|
+
|
108
|
+
if cur_page_len == total_page_len
|
109
|
+
@page
|
110
|
+
end
|
111
|
+
|
112
|
+
padded = '0' * num_zeroes + @page.to_s
|
113
|
+
padded
|
114
|
+
end
|
73
115
|
end
|
74
|
-
|
75
|
-
private
|
76
|
-
|
77
|
-
def generate_temp_file
|
78
|
-
if @opened == false
|
79
|
-
cmd = "pdftoppm -png -f #{@page} -l #{@page} #{@pdf_name} #{@filename}"
|
80
|
-
PDFToImage::exec(cmd)
|
81
|
-
@filename = "#{@filename}-#{page_suffix}.png"
|
82
|
-
@opened = true
|
83
|
-
end
|
84
|
-
|
85
|
-
return true
|
86
|
-
end
|
87
|
-
|
88
|
-
def page_suffix
|
89
|
-
cur_page_len = @page.to_s.length
|
90
|
-
total_page_len = @page_count.to_s.length
|
91
|
-
|
92
|
-
num_zeroes = total_page_len - cur_page_len
|
93
|
-
|
94
|
-
# This is really weird. Basically, poppler_utils does not
|
95
|
-
# prepend a '0' to the page count when the total number of
|
96
|
-
# pages is 10, 100, 1000, 10000, etc. I hate putting this here,
|
97
|
-
# but whatever...
|
98
|
-
|
99
|
-
# TODO: Keep an eye on this. This suddenly started causing problems.
|
100
|
-
# Did poppler_utils change?
|
101
|
-
# if @page_count.to_s.reverse.to_i == 1 && num_zeroes > 0
|
102
|
-
# num_zeroes = num_zeroes - 1
|
103
|
-
# end
|
104
|
-
|
105
|
-
if cur_page_len == total_page_len
|
106
|
-
@page
|
107
|
-
end
|
108
|
-
|
109
|
-
padded = '0' * num_zeroes + @page.to_s
|
110
|
-
padded
|
111
|
-
end
|
112
|
-
|
113
|
-
end
|
114
|
-
|
115
116
|
end
|
data/lib/pdftoimage/version.rb
CHANGED
metadata
CHANGED
@@ -1,99 +1,66 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: pdftoimage
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
5
|
-
version: 0.1.6
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.7
|
6
5
|
platform: ruby
|
7
|
-
authors:
|
6
|
+
authors:
|
8
7
|
- Rob Flynn
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
11
|
+
date: 2018-05-01 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: iconv
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
type: :runtime
|
18
21
|
prerelease: false
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: yard
|
29
|
-
prerelease: false
|
30
|
-
requirement: &id002 !ruby/object:Gem::Requirement
|
31
|
-
none: false
|
32
|
-
requirements:
|
33
|
-
- - ~>
|
34
|
-
- !ruby/object:Gem::Version
|
35
|
-
version: 0.6.0
|
36
|
-
type: :development
|
37
|
-
version_requirements: *id002
|
38
|
-
description: A ruby gem for converting PDF documents into a series of images. This module is based off poppler_utils and ImageMagick.
|
39
|
-
email:
|
40
|
-
- rob@thingerly.com
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
description: A ruby gem for converting PDF documents into a series of images. This
|
28
|
+
module is based off poppler_utils and ImageMagick.
|
29
|
+
email: rob@thingerly.com
|
41
30
|
executables: []
|
42
|
-
|
43
31
|
extensions: []
|
44
|
-
|
45
|
-
|
46
|
-
- README.rdoc
|
47
|
-
- ChangeLog.rdoc
|
48
|
-
- LICENSE.txt
|
49
|
-
files:
|
50
|
-
- .bundle/config
|
51
|
-
- .document
|
52
|
-
- .rspec
|
53
|
-
- .yardopts
|
32
|
+
extra_rdoc_files: []
|
33
|
+
files:
|
54
34
|
- ChangeLog.rdoc
|
55
|
-
-
|
56
|
-
- Gemfile.lock
|
57
|
-
- LICENSE.txt
|
35
|
+
- LICENSE
|
58
36
|
- README.rdoc
|
59
|
-
- Rakefile
|
60
|
-
- gemspec.yml
|
61
37
|
- lib/pdftoimage.rb
|
62
38
|
- lib/pdftoimage/image.rb
|
63
39
|
- lib/pdftoimage/version.rb
|
64
|
-
- pdftoimage.gemspec
|
65
|
-
- spec/10pages.pdf
|
66
|
-
- spec/11pages.pdf
|
67
|
-
- spec/3pages.pdf
|
68
|
-
- spec/pdftoimage_spec.rb
|
69
|
-
- spec/spec_helper.rb
|
70
|
-
has_rdoc: yard
|
71
40
|
homepage: https://github.com/robflynn/pdftoimage
|
72
|
-
licenses:
|
41
|
+
licenses:
|
73
42
|
- MIT
|
43
|
+
metadata:
|
44
|
+
changelog_uri: https://github.com/robflynn/pdftoimage/blob/master/ChangeLog.rdoc
|
45
|
+
source_code_uri: https://github.com/robflynn/pdftoimage/
|
74
46
|
post_install_message:
|
75
47
|
rdoc_options: []
|
76
|
-
|
77
|
-
require_paths:
|
48
|
+
require_paths:
|
78
49
|
- lib
|
79
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
80
|
-
|
81
|
-
requirements:
|
50
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
82
52
|
- - ">="
|
83
|
-
- !ruby/object:Gem::Version
|
84
|
-
version:
|
85
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
-
|
87
|
-
requirements:
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
56
|
+
requirements:
|
88
57
|
- - ">="
|
89
|
-
- !ruby/object:Gem::Version
|
90
|
-
version:
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
version: '0'
|
91
60
|
requirements: []
|
92
|
-
|
93
|
-
|
94
|
-
rubygems_version: 1.6.2
|
61
|
+
rubyforge_project:
|
62
|
+
rubygems_version: 2.6.14.1
|
95
63
|
signing_key:
|
96
|
-
specification_version:
|
64
|
+
specification_version: 4
|
97
65
|
summary: A ruby gem for converting PDF documents into a series of images.
|
98
|
-
test_files:
|
99
|
-
- spec/pdftoimage_spec.rb
|
66
|
+
test_files: []
|
data/.bundle/config
DELETED
data/.document
DELETED
data/.rspec
DELETED
@@ -1 +0,0 @@
|
|
1
|
-
--colour --format documentation
|
data/.yardopts
DELETED
@@ -1 +0,0 @@
|
|
1
|
-
--markup rdoc --title "pdftoimage Documentation" --protected
|
data/Gemfile
DELETED
data/Gemfile.lock
DELETED
@@ -1,35 +0,0 @@
|
|
1
|
-
PATH
|
2
|
-
remote: .
|
3
|
-
specs:
|
4
|
-
pdftoimage (0.1.6)
|
5
|
-
|
6
|
-
GEM
|
7
|
-
remote: http://rubygems.org/
|
8
|
-
specs:
|
9
|
-
autotest (4.4.4)
|
10
|
-
diff-lcs (1.1.2)
|
11
|
-
ore-core (0.1.5)
|
12
|
-
rake (0.8.7)
|
13
|
-
rspec (2.1.0)
|
14
|
-
rspec-core (~> 2.1.0)
|
15
|
-
rspec-expectations (~> 2.1.0)
|
16
|
-
rspec-mocks (~> 2.1.0)
|
17
|
-
rspec-core (2.1.0)
|
18
|
-
rspec-expectations (2.1.0)
|
19
|
-
diff-lcs (~> 1.1.2)
|
20
|
-
rspec-mocks (2.1.0)
|
21
|
-
spork (0.8.4)
|
22
|
-
yard (0.6.2)
|
23
|
-
|
24
|
-
PLATFORMS
|
25
|
-
ruby
|
26
|
-
|
27
|
-
DEPENDENCIES
|
28
|
-
autotest
|
29
|
-
bundler (~> 1.0.0)
|
30
|
-
ore-core (~> 0.1.0)
|
31
|
-
pdftoimage!
|
32
|
-
rake (~> 0.8.7)
|
33
|
-
rspec (>= 2.1.0)
|
34
|
-
spork
|
35
|
-
yard (~> 0.6.0)
|
data/Rakefile
DELETED
@@ -1,26 +0,0 @@
|
|
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
DELETED
@@ -1,13 +0,0 @@
|
|
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: https://github.com/robflynn/pdftoimage
|
7
|
-
email: rob@thingerly.com
|
8
|
-
has_yard: true
|
9
|
-
|
10
|
-
development_dependencies:
|
11
|
-
bundler: ~> 1.0.0
|
12
|
-
yard: ~> 0.6.0
|
13
|
-
|
data/pdftoimage.gemspec
DELETED
@@ -1,15 +0,0 @@
|
|
1
|
-
# -*- encoding: utf-8 -*-
|
2
|
-
|
3
|
-
begin
|
4
|
-
Ore::Specification.new do |gemspec|
|
5
|
-
# custom logic here
|
6
|
-
end
|
7
|
-
rescue NameError
|
8
|
-
begin
|
9
|
-
require 'ore/specification'
|
10
|
-
retry
|
11
|
-
rescue LoadError
|
12
|
-
STDERR.puts "The 'my-project.gemspec' file requires Ore."
|
13
|
-
STDERR.puts "Run `gem install ore-core` to install Ore."
|
14
|
-
end
|
15
|
-
end
|
data/spec/10pages.pdf
DELETED
Binary file
|
data/spec/11pages.pdf
DELETED
Binary file
|
data/spec/3pages.pdf
DELETED
Binary file
|
data/spec/pdftoimage_spec.rb
DELETED
@@ -1,83 +0,0 @@
|
|
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
|
-
# I will find a better solution for having this commented out. I do not
|
10
|
-
# have permission to release the document that I used for this test case.
|
11
|
-
# I will generate a sufficiently buggy version. Basically, buggy PDF software
|
12
|
-
# sometimes corrupts CreationDate and/or ModDate such as discussed here: http://www.linuxquestions.org/questions/solaris-opensolaris-20/converting-utf-16-files-to-another-encoding-such-as-utf-8-a-630588/
|
13
|
-
# I also need to come upw ith a better solution
|
14
|
-
|
15
|
-
# describe "edge cases" do
|
16
|
-
# it "should handle invalid utf-8 in headers without crashing" do
|
17
|
-
# @pages = PDFToImage.open('spec/weird_utf8.pdf')
|
18
|
-
# @pages.size.should equal 1
|
19
|
-
# @pages[0].resize('50%').save('spec/tmp1.jpg')
|
20
|
-
# File.exists?('spec/tmp1.jpg').should equal true
|
21
|
-
# File.unlink('spec/tmp1.jpg')
|
22
|
-
# end
|
23
|
-
# end
|
24
|
-
|
25
|
-
describe "3pages.pdf" do
|
26
|
-
it "should have three pages" do
|
27
|
-
@pages = PDFToImage.open('spec/3pages.pdf')
|
28
|
-
@pages.size.should equal 3
|
29
|
-
end
|
30
|
-
|
31
|
-
it "should allow saving" do
|
32
|
-
@pages = PDFToImage.open('spec/3pages.pdf')
|
33
|
-
@pages.each do |page|
|
34
|
-
page.save('spec/tmp.jpg')
|
35
|
-
File.exists?('spec/tmp.jpg').should equal true
|
36
|
-
File.unlink('spec/tmp.jpg')
|
37
|
-
end
|
38
|
-
end
|
39
|
-
|
40
|
-
it "should allow resizing and quality control" do
|
41
|
-
@pages = PDFToImage.open('spec/3pages.pdf')
|
42
|
-
@pages[0].resize('50%').quality('80%').save('spec/tmp2.jpg')
|
43
|
-
File.exists?('spec/tmp2.jpg').should equal true
|
44
|
-
File.unlink('spec/tmp2.jpg')
|
45
|
-
end
|
46
|
-
|
47
|
-
it "should work with blocks" do
|
48
|
-
counter = 0
|
49
|
-
PDFToImage.open("spec/3pages.pdf") do |page|
|
50
|
-
counter = counter + 1
|
51
|
-
end
|
52
|
-
counter.should equal 3
|
53
|
-
end
|
54
|
-
end
|
55
|
-
|
56
|
-
describe "multi page documents" do
|
57
|
-
it "should parse 10 page documents properly" do
|
58
|
-
counter = 0
|
59
|
-
PDFToImage.open('spec/10pages.pdf') do |page|
|
60
|
-
result = page.save("spec/10pg-#{page.page}.jpg")
|
61
|
-
File.exists?("spec/10pg-#{page.page}.jpg").should equal true
|
62
|
-
File.unlink("spec/10pg-#{page.page}.jpg")
|
63
|
-
counter = counter + 1
|
64
|
-
end
|
65
|
-
|
66
|
-
counter.should equal 10
|
67
|
-
end
|
68
|
-
|
69
|
-
it "should parse 11 page counts" do
|
70
|
-
counter = 0
|
71
|
-
PDFToImage.open('spec/11pages.pdf') do |page|
|
72
|
-
result = page.save("spec/11pg-#{page.page}.jpg")
|
73
|
-
File.exists?("spec/11pg-#{page.page}.jpg").should equal true
|
74
|
-
File.unlink("spec/11pg-#{page.page}.jpg")
|
75
|
-
counter = counter + 1
|
76
|
-
end
|
77
|
-
|
78
|
-
counter.should equal 11
|
79
|
-
end
|
80
|
-
|
81
|
-
|
82
|
-
end
|
83
|
-
end
|