bagira 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +54 -0
- data/Rakefile +2 -0
- data/bagira.gemspec +28 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/bagira/version.rb +3 -0
- data/lib/bagira.rb +59 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: c89e0a11106f559851a61973771b5470c7311fd8
|
4
|
+
data.tar.gz: d24ecb98d615bd5dc485cd14120edb4553151f32
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 8b72a911a0d94c4618a4996f29e69d8bbc2910199b595fdfc5bc8bc216a7e3bd60c43835152a50319e92e903c7022769c9d616609f8fba409f2e6326cf96ec90
|
7
|
+
data.tar.gz: 6fe3df94d34f740e69b896785bdf1bc1cc33254ff2cee451f5523947a6a4b7f57f2f57d13f241038959c971b2f191f060b5a5adeab929323fadd7d325ff8b255
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 Juan Manuel Vallejo
|
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 +1,54 @@
|
|
1
|
+
# Bagira
|
2
|
+
|
3
|
+
This is a simple gem that executes Ghostscript and Tesseract OCR via command line in order to perform ocr on images and pdf documets. It currently supports JPG, PNG and PDF.
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Before using please make sure that you have installed both Ghostscript and Tesseract OCR
|
8
|
+
|
9
|
+
On Ubuntu:
|
10
|
+
```
|
11
|
+
sudo apt-get install libgs-dev
|
12
|
+
sudo apt-get install tesseract-ocr
|
13
|
+
```
|
14
|
+
|
15
|
+
On Mac (Homebrew):
|
16
|
+
```
|
17
|
+
brew install gs
|
18
|
+
brew install tesseract
|
19
|
+
```
|
20
|
+
|
21
|
+
Add this line to your application's Gemfile:
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
gem 'bagira'
|
25
|
+
```
|
26
|
+
|
27
|
+
And then execute:
|
28
|
+
|
29
|
+
$ bundle
|
30
|
+
|
31
|
+
Or install it yourself as:
|
32
|
+
|
33
|
+
$ gem install bagira
|
34
|
+
|
35
|
+
## Usage
|
36
|
+
|
37
|
+
```ruby
|
38
|
+
bagira = Bagira.new(path_to_your_file)
|
39
|
+
output = bagira.perform_ocr
|
40
|
+
```
|
41
|
+
|
42
|
+
## Development
|
43
|
+
|
44
|
+
rSpec is included with basic tests, you can check the spec/ folder for more details.
|
45
|
+
|
46
|
+
## Contributing
|
47
|
+
|
48
|
+
Bug reports and pull requests are welcome on GitHub at https://bitbucket.org/juanmvallejo/bagira/issues
|
49
|
+
|
50
|
+
|
51
|
+
## License
|
52
|
+
|
53
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
54
|
+
|
data/Rakefile
ADDED
data/bagira.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'bagira/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "bagira"
|
8
|
+
spec.version = Bagira::VERSION
|
9
|
+
spec.authors = ["Juan Manuel Vallejo"]
|
10
|
+
spec.email = ["jmvallejo@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{This gem uses Ghostscript and Tesseract to perform OCR on various file formats.}
|
13
|
+
spec.description = %q{This gem uses Ghostscript and Tesseract to perform OCR on various file formats.}
|
14
|
+
spec.homepage = "http://bitbucket.org/juanmvallejo/bagira/overview"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_development_dependency "rspec"
|
25
|
+
|
26
|
+
# Runtime dependencies
|
27
|
+
spec.add_dependency "pdf-reader", "~> 1.4"
|
28
|
+
end
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "bagira"
|
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
|
data/bin/setup
ADDED
data/lib/bagira.rb
ADDED
@@ -0,0 +1,59 @@
|
|
1
|
+
require "bagira/version"
|
2
|
+
require "pdf-reader"
|
3
|
+
|
4
|
+
class Bagira
|
5
|
+
|
6
|
+
FILE_TYPE = { :invalid => 'invalid', :not_found => 'not_found', :pdf => 'pdf', :jpg => 'jpg', :png => 'png' }
|
7
|
+
|
8
|
+
attr_reader :file_type
|
9
|
+
attr_reader :filepath
|
10
|
+
attr_reader :page_count
|
11
|
+
|
12
|
+
def initialize(filepath)
|
13
|
+
@file_type = FILE_TYPE[:invalid]
|
14
|
+
@file_type = FILE_TYPE[:pdf] unless filepath.match(/\.pdf$/).nil?
|
15
|
+
@file_type = FILE_TYPE[:png] unless filepath.match(/\.png$/).nil?
|
16
|
+
@file_type = FILE_TYPE[:jpg] unless filepath.match(/\.jpg$/).nil?
|
17
|
+
@file_type = FILE_TYPE[:not_found] unless File.exist?(filepath)
|
18
|
+
|
19
|
+
@filepath = filepath
|
20
|
+
|
21
|
+
@page_count = 0
|
22
|
+
@page_count = 1 if is_image?
|
23
|
+
if is_document?
|
24
|
+
reader = PDF::Reader.new(filepath)
|
25
|
+
@page_count = reader.page_count
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
def perform_ocr
|
30
|
+
return process_image(@filepath) if is_image?
|
31
|
+
return process_pdf(@filepath) if is_document?
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
def process_image(filepath)
|
36
|
+
result = %x(tesseract #{filepath} stdout)
|
37
|
+
return result.strip unless result.nil?
|
38
|
+
end
|
39
|
+
|
40
|
+
def process_pdf(filepath)
|
41
|
+
result_array = []
|
42
|
+
for i in 1..@page_count
|
43
|
+
page_result = %x(gs -q -dNOPAUSE -sDEVICE=pnggray -dTextAlphaBits=4 -r300 -sOutputFile=%stdout -dBATCH -dFirstPage=#{i} -dLastPage=#{i} #{filepath}|tesseract stdin stdout)
|
44
|
+
result_array << page_result.strip unless page_result.nil?
|
45
|
+
end
|
46
|
+
result_array.join("\n")
|
47
|
+
end
|
48
|
+
|
49
|
+
def is_image?
|
50
|
+
return true if (@file_type.eql?(FILE_TYPE[:jpg]) or @file_type.eql?(FILE_TYPE[:png]))
|
51
|
+
return false
|
52
|
+
end
|
53
|
+
|
54
|
+
def is_document?
|
55
|
+
return true if (@file_type.eql?(FILE_TYPE[:pdf]))
|
56
|
+
return false
|
57
|
+
end
|
58
|
+
|
59
|
+
end
|
metadata
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bagira
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Juan Manuel Vallejo
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-04-19 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: '1.11'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.11'
|
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: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: pdf-reader
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.4'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '1.4'
|
69
|
+
description: This gem uses Ghostscript and Tesseract to perform OCR on various file
|
70
|
+
formats.
|
71
|
+
email:
|
72
|
+
- jmvallejo@gmail.com
|
73
|
+
executables: []
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- .gitignore
|
78
|
+
- .rspec
|
79
|
+
- Gemfile
|
80
|
+
- LICENSE.txt
|
81
|
+
- README.md
|
82
|
+
- Rakefile
|
83
|
+
- bagira.gemspec
|
84
|
+
- bin/console
|
85
|
+
- bin/setup
|
86
|
+
- lib/bagira.rb
|
87
|
+
- lib/bagira/version.rb
|
88
|
+
homepage: http://bitbucket.org/juanmvallejo/bagira/overview
|
89
|
+
licenses:
|
90
|
+
- MIT
|
91
|
+
metadata: {}
|
92
|
+
post_install_message:
|
93
|
+
rdoc_options: []
|
94
|
+
require_paths:
|
95
|
+
- lib
|
96
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - '>='
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '0'
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - '>='
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
requirements: []
|
107
|
+
rubyforge_project:
|
108
|
+
rubygems_version: 2.4.8
|
109
|
+
signing_key:
|
110
|
+
specification_version: 4
|
111
|
+
summary: This gem uses Ghostscript and Tesseract to perform OCR on various file formats.
|
112
|
+
test_files: []
|