libera 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +24 -0
- data/.rspec +3 -0
- data/.travis.yml +5 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +89 -0
- data/LICENSE.txt +21 -0
- data/README.md +52 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/libera +81 -0
- data/bin/setup +8 -0
- data/lib/libera.rb +90 -0
- data/lib/libera/tei.rb +85 -0
- data/lib/libera/version.rb +3 -0
- data/libera.gemspec +38 -0
- metadata +200 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: cc099d4ec4b7e794ee9fcd8dbd057a1ccd04467c
|
4
|
+
data.tar.gz: 42e414654cab1579bdaad82e5fe6d70f97b0fd7a
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 5e4e80f572b7e2bc9ac1febedd14693a956d818aa0ec999d486e11f74813df1029a2eaeed846c36d4fb7951d57c2c0981e50b6a9393c1daaa86b3114a504dd3f
|
7
|
+
data.tar.gz: d7bb316456adfd50f29e19c28eee08051c6bc2439ac41b98a6f550ee37031528ad89724225e20f6b5a424ea12c208dd9f0f9ada4ec035aff6e4999dc13c986c4
|
data/.gitignore
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
/.bundle/
|
2
|
+
/.yardoc
|
3
|
+
/_yardoc/
|
4
|
+
/coverage/
|
5
|
+
/doc/
|
6
|
+
/pkg/
|
7
|
+
/spec/reports/
|
8
|
+
/tmp/
|
9
|
+
|
10
|
+
# rspec failure tracking
|
11
|
+
.rspec_status
|
12
|
+
|
13
|
+
# Ignore all logfiles and tempfiles.
|
14
|
+
/log/*
|
15
|
+
/tmp/*
|
16
|
+
!/log/.keep
|
17
|
+
!/tmp/.keep
|
18
|
+
|
19
|
+
.vagrant
|
20
|
+
Vagrantfile
|
21
|
+
|
22
|
+
# .nfs files are created when an open file is removed but is still being accessed
|
23
|
+
.nfs*
|
24
|
+
.DS_Store
|
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,89 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
libera (1.0.0)
|
5
|
+
fileutils (~> 1.0.2)
|
6
|
+
nokogiri (~> 1.8.2)
|
7
|
+
om (~> 3.1.1)
|
8
|
+
pdf-reader (~> 2.1.0)
|
9
|
+
rmagick (~> 2.16.0)
|
10
|
+
rtesseract (~> 2.2.0)
|
11
|
+
ruby-progressbar (~> 1.9.0)
|
12
|
+
|
13
|
+
GEM
|
14
|
+
remote: https://rubygems.org/
|
15
|
+
specs:
|
16
|
+
Ascii85 (1.0.3)
|
17
|
+
activemodel (5.2.0)
|
18
|
+
activesupport (= 5.2.0)
|
19
|
+
activesupport (5.2.0)
|
20
|
+
concurrent-ruby (~> 1.0, >= 1.0.2)
|
21
|
+
i18n (>= 0.7, < 2)
|
22
|
+
minitest (~> 5.1)
|
23
|
+
tzinfo (~> 1.1)
|
24
|
+
afm (0.2.2)
|
25
|
+
concurrent-ruby (1.0.5)
|
26
|
+
daemons (1.2.6)
|
27
|
+
diff-lcs (1.3)
|
28
|
+
fileutils (1.0.2)
|
29
|
+
hashery (2.1.2)
|
30
|
+
i18n (1.0.1)
|
31
|
+
concurrent-ruby (~> 1.0)
|
32
|
+
mini_portile2 (2.3.0)
|
33
|
+
minitest (5.11.3)
|
34
|
+
nokogiri (1.8.2)
|
35
|
+
mini_portile2 (~> 2.3.0)
|
36
|
+
om (3.1.1)
|
37
|
+
activemodel
|
38
|
+
activesupport
|
39
|
+
nokogiri (>= 1.4.2)
|
40
|
+
solrizer (~> 3.3)
|
41
|
+
pdf-reader (2.1.0)
|
42
|
+
Ascii85 (~> 1.0.0)
|
43
|
+
afm (~> 0.2.1)
|
44
|
+
hashery (~> 2.0)
|
45
|
+
ruby-rc4
|
46
|
+
ttfunk
|
47
|
+
rake (10.5.0)
|
48
|
+
rmagick (2.16.0)
|
49
|
+
rspec (3.7.0)
|
50
|
+
rspec-core (~> 3.7.0)
|
51
|
+
rspec-expectations (~> 3.7.0)
|
52
|
+
rspec-mocks (~> 3.7.0)
|
53
|
+
rspec-core (3.7.1)
|
54
|
+
rspec-support (~> 3.7.0)
|
55
|
+
rspec-expectations (3.7.0)
|
56
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
57
|
+
rspec-support (~> 3.7.0)
|
58
|
+
rspec-mocks (3.7.0)
|
59
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
60
|
+
rspec-support (~> 3.7.0)
|
61
|
+
rspec-support (3.7.1)
|
62
|
+
rtesseract (2.2.0)
|
63
|
+
nokogiri
|
64
|
+
ruby-progressbar (1.9.0)
|
65
|
+
ruby-rc4 (0.1.5)
|
66
|
+
solrizer (3.4.1)
|
67
|
+
activesupport
|
68
|
+
daemons
|
69
|
+
nokogiri
|
70
|
+
stomp
|
71
|
+
xml-simple
|
72
|
+
stomp (1.4.4)
|
73
|
+
thread_safe (0.3.6)
|
74
|
+
ttfunk (1.5.1)
|
75
|
+
tzinfo (1.2.5)
|
76
|
+
thread_safe (~> 0.1)
|
77
|
+
xml-simple (1.1.5)
|
78
|
+
|
79
|
+
PLATFORMS
|
80
|
+
ruby
|
81
|
+
|
82
|
+
DEPENDENCIES
|
83
|
+
bundler (~> 1.16)
|
84
|
+
libera!
|
85
|
+
rake (~> 10.0)
|
86
|
+
rspec (~> 3.0)
|
87
|
+
|
88
|
+
BUNDLED WITH
|
89
|
+
1.16.1
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2018 TODO: Write your name
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
# Libera
|
2
|
+
|
3
|
+
Libera is a gem built for Charon - https://github.com/NEU-Libraries/charon - a digital humanities focused Samvera head.
|
4
|
+
|
5
|
+
It's purpose is to take PDF files as input, and split them apart into individual page images for OCR and TEI generation.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'libera'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install libera
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
To use this gem at the command-line:
|
26
|
+
|
27
|
+
```
|
28
|
+
libera -p ./input.pdf
|
29
|
+
```
|
30
|
+
|
31
|
+
There are several adjustable parameters;
|
32
|
+
|
33
|
+
* -p | --pdf_location (no default)
|
34
|
+
* -w | --working_directory (default is a unique directory made in the directory you run libera)
|
35
|
+
* -d | --density (default is 300)
|
36
|
+
* -q | --quality (default is 100)
|
37
|
+
* -f | --format_type (default is PNG)
|
38
|
+
* -h | --help
|
39
|
+
|
40
|
+
## Development
|
41
|
+
|
42
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
43
|
+
|
44
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
45
|
+
|
46
|
+
## Contributing
|
47
|
+
|
48
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/NEU-Libraries/libera.
|
49
|
+
|
50
|
+
## License
|
51
|
+
|
52
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "libera"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/libera
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
require 'libera'
|
3
|
+
require 'optparse'
|
4
|
+
require 'ruby-progressbar'
|
5
|
+
|
6
|
+
opt_parser = OptionParser.new do |opt|
|
7
|
+
opt.banner = "Usage: libera COMMAND [OPTIONS]"
|
8
|
+
opt.separator ""
|
9
|
+
opt.separator "Commands"
|
10
|
+
opt.separator " pdf_location: pdf_location ./input.pdf"
|
11
|
+
opt.separator " working_dir: /tmp"
|
12
|
+
opt.separator " density: 300"
|
13
|
+
opt.separator " quality: 100"
|
14
|
+
opt.separator " format_type: png"
|
15
|
+
opt.separator ""
|
16
|
+
opt.separator "Options"
|
17
|
+
|
18
|
+
opt.on("-p","--pdf_location PATH","What is the path to the PDF input file?") do |pdf_location|
|
19
|
+
Libera.configuration.pdf_location = pdf_location
|
20
|
+
end
|
21
|
+
|
22
|
+
opt.on("-w","--working_directory PATH","Where will Libera produce output?") do |working_dir|
|
23
|
+
Libera.configuration.working_dir = working_dir
|
24
|
+
end
|
25
|
+
|
26
|
+
opt.on("-d","--density INTEGER","What density should Libera convert to?") do |density|
|
27
|
+
Libera.configuration.density = density
|
28
|
+
end
|
29
|
+
|
30
|
+
opt.on("-q","--quality INTEGER","What image quality should Libera convert to?") do |quality|
|
31
|
+
Libera.configuration.quality = quality
|
32
|
+
end
|
33
|
+
|
34
|
+
opt.on("-f","--format_type EXTENSION","What image type should Libera convert to?") do |format_type|
|
35
|
+
Libera.configuration.format_type = format_type
|
36
|
+
end
|
37
|
+
|
38
|
+
opt.on("-h","--help","Help") do
|
39
|
+
puts opt_parser
|
40
|
+
exit
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
opt_parser.parse!
|
45
|
+
|
46
|
+
parser = Libera::Parser.new
|
47
|
+
|
48
|
+
parser.mk_working_dir
|
49
|
+
|
50
|
+
file_list = []
|
51
|
+
|
52
|
+
reader = PDF::Reader.new(Libera.configuration.pdf_location)
|
53
|
+
page_count = reader.page_count - 1
|
54
|
+
|
55
|
+
progressbar = ProgressBar.create(:title => "Pages", :starting_at => 0, :total => page_count + 1)
|
56
|
+
|
57
|
+
page_list = Hash.new
|
58
|
+
|
59
|
+
for i in 0..page_count
|
60
|
+
begin
|
61
|
+
pdf = Magick::ImageList.new(Libera.configuration.pdf_location + "[#{i}]") {self.density = Libera.configuration.density; self.quality = Libera.configuration.quality}
|
62
|
+
page_img = pdf.first
|
63
|
+
|
64
|
+
page_img.border!(0, 0, 'white')
|
65
|
+
page_img.alpha(Magick::DeactivateAlphaChannel)
|
66
|
+
|
67
|
+
file_name = "pdf-page-#{i}.#{Libera.configuration.format_type}"
|
68
|
+
file_path = "#{Libera.configuration.working_dir}/#{file_name}"
|
69
|
+
|
70
|
+
file_list << file_path
|
71
|
+
page_img.write(file_path) {self.depth = 8}
|
72
|
+
|
73
|
+
txt = parser.parse_image(file_path, i)
|
74
|
+
page_list[file_name] = txt
|
75
|
+
ensure
|
76
|
+
pdf.destroy! && page_img.destroy!
|
77
|
+
progressbar.increment
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
parser.generate_tei(page_list)
|
data/bin/setup
ADDED
data/lib/libera.rb
ADDED
@@ -0,0 +1,90 @@
|
|
1
|
+
require 'libera/version'
|
2
|
+
require 'libera/tei'
|
3
|
+
|
4
|
+
require 'rmagick'
|
5
|
+
require 'rtesseract'
|
6
|
+
require 'pdf-reader'
|
7
|
+
require 'tmpdir'
|
8
|
+
require 'fileutils'
|
9
|
+
|
10
|
+
include Magick
|
11
|
+
|
12
|
+
module Libera
|
13
|
+
|
14
|
+
class << self
|
15
|
+
# Simple attribute for configuration
|
16
|
+
attr_accessor :configuration
|
17
|
+
end
|
18
|
+
|
19
|
+
# Allows for configuration by block
|
20
|
+
#
|
21
|
+
# Example:
|
22
|
+
# MegaLotto.configure do |config|
|
23
|
+
# config.drawing_count = 10
|
24
|
+
# end
|
25
|
+
|
26
|
+
def self.configure
|
27
|
+
yield(configuration) if block_given?
|
28
|
+
end
|
29
|
+
|
30
|
+
def self.configuration
|
31
|
+
@configuration ||= Configuration.new
|
32
|
+
end
|
33
|
+
|
34
|
+
# Undoes any configuration - this method was built for testing purposes
|
35
|
+
#
|
36
|
+
# Example:
|
37
|
+
# Kataba.reset
|
38
|
+
|
39
|
+
def self.reset
|
40
|
+
@configuration = Configuration.new
|
41
|
+
end
|
42
|
+
|
43
|
+
class Configuration
|
44
|
+
# Example:
|
45
|
+
# Libera.configuration.example = "..."
|
46
|
+
# attr_accessor :example_value
|
47
|
+
|
48
|
+
attr_accessor :pdf_location
|
49
|
+
attr_accessor :working_dir
|
50
|
+
attr_accessor :density
|
51
|
+
attr_accessor :quality
|
52
|
+
attr_accessor :format_type
|
53
|
+
|
54
|
+
# Default configuration values
|
55
|
+
def initialize
|
56
|
+
@working_dir = "libera-#{Time.now.to_f.to_s.gsub!('.','')}" # Default value
|
57
|
+
@density = 300 # Default value
|
58
|
+
@quality = 100 # Default value
|
59
|
+
@format_type = "png" # Default value
|
60
|
+
end
|
61
|
+
end
|
62
|
+
|
63
|
+
class Parser
|
64
|
+
|
65
|
+
def parse_image(image_path, i)
|
66
|
+
file_path = "#{Libera.configuration.working_dir}/pdf-page-#{i}"
|
67
|
+
`tesseract #{image_path} #{file_path} >> /dev/null 2>&1`
|
68
|
+
return File.read(file_path + ".txt")
|
69
|
+
end
|
70
|
+
|
71
|
+
def generate_tei(page_list)
|
72
|
+
tei_path = "#{Libera.configuration.working_dir}/tei.xml"
|
73
|
+
tei_xml = Libera::Tei.new
|
74
|
+
|
75
|
+
page_list.each do |k, v|
|
76
|
+
tei_xml.add_page_break(k)
|
77
|
+
tei_xml.add_anon_block(v)
|
78
|
+
end
|
79
|
+
|
80
|
+
# write out xml to file
|
81
|
+
IO.write(tei_path, tei_xml.to_xml)
|
82
|
+
end
|
83
|
+
|
84
|
+
def mk_working_dir
|
85
|
+
# Check if working dir exists - If not, make it
|
86
|
+
FileUtils.mkdir("#{Libera.configuration.working_dir}") unless File.exists? "#{Libera.configuration.working_dir}"
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
end
|
data/lib/libera/tei.rb
ADDED
@@ -0,0 +1,85 @@
|
|
1
|
+
require 'om'
|
2
|
+
|
3
|
+
module Libera
|
4
|
+
class Tei
|
5
|
+
include OM::XML::Document
|
6
|
+
|
7
|
+
set_terminology do |t|
|
8
|
+
t.root(:path => 'tei', :xmlns => 'http://www.tei-c.org/ns/1.0', :namespace_prefix => nil)
|
9
|
+
t.text(path: 'text'){
|
10
|
+
t.body(path: 'body'){
|
11
|
+
t.page_break(path: 'pb')
|
12
|
+
t.anon_block(path: 'ab')
|
13
|
+
}
|
14
|
+
}
|
15
|
+
end
|
16
|
+
|
17
|
+
define_template :page_break do |xml, img_src|
|
18
|
+
xml.pb(:facs => img_src)
|
19
|
+
end
|
20
|
+
|
21
|
+
define_template :anon_block do |xml, ab_text|
|
22
|
+
xml.ab do
|
23
|
+
xml.text(ab_text)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.xml_template
|
28
|
+
builder = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') do |xml|
|
29
|
+
xml.TEI("xmlns"=>"http://www.tei-c.org/ns/1.0") {
|
30
|
+
xml.teiHeader{
|
31
|
+
xml.fileDesc{
|
32
|
+
xml.titleStmt{
|
33
|
+
xml.title
|
34
|
+
}
|
35
|
+
xml.publicationStmt{
|
36
|
+
xml.p_
|
37
|
+
}
|
38
|
+
xml.sourceDesc{
|
39
|
+
xml.p_
|
40
|
+
}
|
41
|
+
}
|
42
|
+
}
|
43
|
+
xml.text_{
|
44
|
+
xml.body{
|
45
|
+
xml.ab
|
46
|
+
}
|
47
|
+
}
|
48
|
+
}
|
49
|
+
end
|
50
|
+
|
51
|
+
return builder.doc
|
52
|
+
end
|
53
|
+
|
54
|
+
def add_page_break(page_img)
|
55
|
+
# any anon breaks?
|
56
|
+
ab_count = self.find_by_terms(:text, :body, :anon_block).count
|
57
|
+
|
58
|
+
if ab_count == 1 && self.find_by_terms(:text, :body, :anon_block).first.text.blank?
|
59
|
+
self.find_by_terms(:text, :body, :anon_block).first.remove
|
60
|
+
ab_count = 0
|
61
|
+
end
|
62
|
+
|
63
|
+
if !(ab_count > 0)
|
64
|
+
# if not add to child of body
|
65
|
+
self.template_registry.add_child(self.find_by_terms(:text, :body => 0), :page_break, page_img)
|
66
|
+
else
|
67
|
+
# else add as sibling
|
68
|
+
self.template_registry.add_next_sibling(self.find_by_terms(:text, :body, :anon_block).last, :page_break, page_img)
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
def add_anon_block(text)
|
73
|
+
if self.find_by_terms(:text, :body, :page_break).blank?
|
74
|
+
# Raise error, page break required
|
75
|
+
raise "Page Break not found, unable to add anon block"
|
76
|
+
end
|
77
|
+
|
78
|
+
if self.find_by_terms(:text, :body, :page_break).count == 1
|
79
|
+
self.template_registry.add_next_sibling(self.find_by_terms(:text, :body, :page_break => 0).first, :anon_block, text)
|
80
|
+
else
|
81
|
+
self.template_registry.add_next_sibling(self.find_by_terms(:text, :body, :page_break).last, :anon_block, text)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
data/libera.gemspec
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
lib = File.expand_path("../lib", __FILE__)
|
2
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
3
|
+
|
4
|
+
require "libera/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "libera"
|
8
|
+
spec.version = Libera::VERSION
|
9
|
+
spec.authors = ["David Cliff"]
|
10
|
+
spec.email = ["dgcliff@northeastern.edu"]
|
11
|
+
|
12
|
+
spec.summary = %q{A utility gem for processing PDFs for OCR and TEI}
|
13
|
+
# spec.description = %q{TODO: Write a longer description or delete this line.}
|
14
|
+
spec.homepage = "https://github.com/NEU-Libraries/libera"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
18
|
+
f.match(%r{^(test|spec|features)/})
|
19
|
+
end
|
20
|
+
|
21
|
+
# spec.bindir = "exe"
|
22
|
+
# spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
23
|
+
|
24
|
+
spec.executables = ["libera"]
|
25
|
+
spec.require_paths = ["lib"]
|
26
|
+
|
27
|
+
spec.add_development_dependency "bundler", "~> 1.16"
|
28
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
29
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
30
|
+
|
31
|
+
spec.add_dependency "rtesseract", "~> 2.2.0"
|
32
|
+
spec.add_dependency "rmagick", "~> 2.16.0"
|
33
|
+
spec.add_dependency "nokogiri", "~> 1.8.2"
|
34
|
+
spec.add_dependency "pdf-reader", "~> 2.1.0"
|
35
|
+
spec.add_dependency "om", "~> 3.1.1"
|
36
|
+
spec.add_dependency "fileutils", "~> 1.0.2"
|
37
|
+
spec.add_dependency "ruby-progressbar", "~> 1.9.0"
|
38
|
+
end
|
metadata
ADDED
@@ -0,0 +1,200 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: libera
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 1.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- David Cliff
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2018-06-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.16'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.16'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rtesseract
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 2.2.0
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 2.2.0
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rmagick
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 2.16.0
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 2.16.0
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: nokogiri
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 1.8.2
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 1.8.2
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: pdf-reader
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: 2.1.0
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: 2.1.0
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: om
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 3.1.1
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 3.1.1
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: fileutils
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: 1.0.2
|
132
|
+
type: :runtime
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: 1.0.2
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: ruby-progressbar
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: 1.9.0
|
146
|
+
type: :runtime
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: 1.9.0
|
153
|
+
description:
|
154
|
+
email:
|
155
|
+
- dgcliff@northeastern.edu
|
156
|
+
executables:
|
157
|
+
- libera
|
158
|
+
extensions: []
|
159
|
+
extra_rdoc_files: []
|
160
|
+
files:
|
161
|
+
- ".gitignore"
|
162
|
+
- ".rspec"
|
163
|
+
- ".travis.yml"
|
164
|
+
- Gemfile
|
165
|
+
- Gemfile.lock
|
166
|
+
- LICENSE.txt
|
167
|
+
- README.md
|
168
|
+
- Rakefile
|
169
|
+
- bin/console
|
170
|
+
- bin/libera
|
171
|
+
- bin/setup
|
172
|
+
- lib/libera.rb
|
173
|
+
- lib/libera/tei.rb
|
174
|
+
- lib/libera/version.rb
|
175
|
+
- libera.gemspec
|
176
|
+
homepage: https://github.com/NEU-Libraries/libera
|
177
|
+
licenses:
|
178
|
+
- MIT
|
179
|
+
metadata: {}
|
180
|
+
post_install_message:
|
181
|
+
rdoc_options: []
|
182
|
+
require_paths:
|
183
|
+
- lib
|
184
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
185
|
+
requirements:
|
186
|
+
- - ">="
|
187
|
+
- !ruby/object:Gem::Version
|
188
|
+
version: '0'
|
189
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
190
|
+
requirements:
|
191
|
+
- - ">="
|
192
|
+
- !ruby/object:Gem::Version
|
193
|
+
version: '0'
|
194
|
+
requirements: []
|
195
|
+
rubyforge_project:
|
196
|
+
rubygems_version: 2.6.12
|
197
|
+
signing_key:
|
198
|
+
specification_version: 4
|
199
|
+
summary: A utility gem for processing PDFs for OCR and TEI
|
200
|
+
test_files: []
|