rtesseract 0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,5 @@
1
+ README.rdoc
2
+ lib/**/*.rb
3
+ bin/*
4
+ features/**/*.feature
5
+ LICENSE
@@ -0,0 +1,21 @@
1
+ ## MAC OS
2
+ .DS_Store
3
+
4
+ ## TEXTMATE
5
+ *.tmproj
6
+ tmtags
7
+
8
+ ## EMACS
9
+ *~
10
+ \#*
11
+ .\#*
12
+
13
+ ## VIM
14
+ *.swp
15
+
16
+ ## PROJECT::GENERAL
17
+ coverage
18
+ rdoc
19
+ pkg
20
+
21
+ ## PROJECT::SPECIFIC
data/LICENSE ADDED
@@ -0,0 +1,20 @@
1
+ Copyright (c) 2010 Danilo Jeremias da Silva
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.
@@ -0,0 +1,24 @@
1
+ = rtesseract
2
+
3
+ Ruby library for working with the Tesseract OCR.
4
+
5
+ == REQUIREMENTS:
6
+
7
+ To work properly rtesseract are needed:
8
+ * Tesseract - Program
9
+ * ImageMagic - Program
10
+ * RMagick - Gem
11
+
12
+ == Note on Patches/Pull Requests
13
+
14
+ * Fork the project.
15
+ * Make your feature addition or bug fix.
16
+ * Add tests for it. This is important so I don't break it in a
17
+ future version unintentionally.
18
+ * Commit, do not mess with rakefile, version, or history.
19
+ (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
20
+ * Send me a pull request. Bonus points for topic branches.
21
+
22
+ == Copyright
23
+
24
+ Copyright (c) 2010 Danilo Jeremias da Silva. See LICENSE for details.
@@ -0,0 +1,54 @@
1
+ require 'rubygems'
2
+ require 'rake'
3
+
4
+ begin
5
+ require 'jeweler'
6
+ Jeweler::Tasks.new do |gem|
7
+ gem.name = "rtesseract"
8
+ gem.version = '0.0.1'
9
+ gem.summary = "Ruby library for working with the Tesseract OCR."
10
+ gem.description = "Ruby library for working with the Tesseract OCR."
11
+ gem.email = "dannnylo@gmail.com"
12
+ gem.homepage = "http://github.com/dannnylo/rtesseract"
13
+ gem.authors = ["Danilo Jeremias da Silva"]
14
+ gem.add_development_dependency "thoughtbot-shoulda", ">= 0"
15
+ gem.add_development_dependency "rmagick", '>= 2.13.1'
16
+ end
17
+ Jeweler::GemcutterTasks.new
18
+ rescue LoadError
19
+ puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
20
+ end
21
+
22
+ require 'rake/testtask'
23
+ Rake::TestTask.new(:test) do |test|
24
+ test.libs << 'lib' << 'test'
25
+ test.pattern = 'test/**/test_*.rb'
26
+ test.verbose = true
27
+ end
28
+
29
+ begin
30
+ require 'rcov/rcovtask'
31
+ Rcov::RcovTask.new do |test|
32
+ test.libs << 'test'
33
+ test.pattern = 'test/**/test_*.rb'
34
+ test.verbose = true
35
+ end
36
+ rescue LoadError
37
+ task :rcov do
38
+ abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
39
+ end
40
+ end
41
+
42
+ task :test => :check_dependencies
43
+
44
+ task :default => :test
45
+
46
+ require 'rake/rdoctask'
47
+ Rake::RDocTask.new do |rdoc|
48
+ version = File.exist?('VERSION') ? File.read('VERSION') : ""
49
+
50
+ rdoc.rdoc_dir = 'rdoc'
51
+ rdoc.title = "rtesseract #{version}"
52
+ rdoc.rdoc_files.include('README*')
53
+ rdoc.rdoc_files.include('lib/**/*.rb')
54
+ end
@@ -0,0 +1,73 @@
1
+ require "RMagick"
2
+ require "pathname"
3
+ require "tempfile"
4
+
5
+ class RTesseract
6
+ VERSION = '0.0.1'
7
+
8
+ def initialize(src="", options={})
9
+ @source = Pathname.new src
10
+ @command = options[:command] || "tesseract"
11
+ @options = options
12
+ @value = ""
13
+ end
14
+
15
+ def source= src
16
+ @source = Pathname.new src
17
+ @value = ""
18
+ end
19
+
20
+ def image_name
21
+ @source.basename
22
+ end
23
+
24
+ #Convert image to tiff
25
+ def image_to_tiff
26
+ tmp_file = Pathname.new(Dir::tmpdir).join("#{@source.basename}.tif").to_s
27
+ cat = Magick::ImageList.new @source.to_s
28
+ cat.write tmp_file.to_s
29
+ return tmp_file
30
+ end
31
+
32
+ #Remove files
33
+ def remove_file(files)
34
+ files.each do |file|
35
+ begin
36
+ File.unlink(file) if File.exist?(file)
37
+ rescue
38
+ system "rm -f #{file}"
39
+ end
40
+ end
41
+ true
42
+ rescue
43
+ raise "Error on remove file."
44
+ end
45
+
46
+ #Convert image to string
47
+ def convert
48
+ tmp_file = Pathname.new(Dir::tmpdir).join("#{@source.basename}")
49
+ tmp_image = image_to_tiff
50
+ `#{@command} #{tmp_image} #{tmp_file.to_s}`
51
+ @value = File.read("#{tmp_file.to_s}.txt").to_s
52
+ remove_file([tmp_image,"#{tmp_file.to_s}.txt"])
53
+ rescue
54
+ raise "Error on conversion."
55
+ end
56
+
57
+ #Output value
58
+ def to_s
59
+ return @value if @value != ""
60
+ if @source.file?
61
+ convert
62
+ @value
63
+ else
64
+ raise "Select a image file."
65
+ end
66
+ end
67
+
68
+ #Remove spaces and break-lines
69
+ def to_s_without_spaces
70
+ to_s.gsub(" ","").gsub("\n","").gsub("\r","")
71
+ end
72
+ end
73
+
@@ -0,0 +1,56 @@
1
+ # Generated by jeweler
2
+ # DO NOT EDIT THIS FILE DIRECTLY
3
+ # Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
4
+ # -*- encoding: utf-8 -*-
5
+
6
+ Gem::Specification.new do |s|
7
+ s.name = %q{rtesseract}
8
+ s.version = "0.0.1"
9
+
10
+ s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
11
+ s.authors = ["Danilo Jeremias da Silva"]
12
+ s.date = %q{2010-08-25}
13
+ s.description = %q{Ruby library for working with the Tesseract OCR.}
14
+ s.email = %q{dannnylo@gmail.com}
15
+ s.extra_rdoc_files = [
16
+ "LICENSE",
17
+ "README.rdoc"
18
+ ]
19
+ s.files = [
20
+ ".document",
21
+ ".gitignore",
22
+ "LICENSE",
23
+ "README.rdoc",
24
+ "Rakefile",
25
+ "lib/rtesseract.rb",
26
+ "rtesseract.gemspec",
27
+ "test/helper.rb",
28
+ "test/test_rtesseract.rb"
29
+ ]
30
+ s.homepage = %q{http://github.com/dannnylo/rtesseract}
31
+ s.rdoc_options = ["--charset=UTF-8"]
32
+ s.require_paths = ["lib"]
33
+ s.rubygems_version = %q{1.3.7}
34
+ s.summary = %q{Ruby library for working with the Tesseract OCR.}
35
+ s.test_files = [
36
+ "test/helper.rb",
37
+ "test/test_rtesseract.rb"
38
+ ]
39
+
40
+ if s.respond_to? :specification_version then
41
+ current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
42
+ s.specification_version = 3
43
+
44
+ if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
45
+ s.add_development_dependency(%q<thoughtbot-shoulda>, [">= 0"])
46
+ s.add_development_dependency(%q<rmagick>, [">= 2.13.1"])
47
+ else
48
+ s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
49
+ s.add_dependency(%q<rmagick>, [">= 2.13.1"])
50
+ end
51
+ else
52
+ s.add_dependency(%q<thoughtbot-shoulda>, [">= 0"])
53
+ s.add_dependency(%q<rmagick>, [">= 2.13.1"])
54
+ end
55
+ end
56
+
@@ -0,0 +1,10 @@
1
+ require 'rubygems'
2
+ require 'test/unit'
3
+ require 'shoulda'
4
+
5
+ $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
6
+ $LOAD_PATH.unshift(File.dirname(__FILE__))
7
+ require 'rtesseract'
8
+
9
+ class Test::Unit::TestCase
10
+ end
@@ -0,0 +1,7 @@
1
+ require 'helper'
2
+
3
+ class TestRtesseract < Test::Unit::TestCase
4
+ should "probably rename this file and start testing for real" do
5
+ flunk "hey buddy, you should probably rename this file and start testing for real"
6
+ end
7
+ end
metadata ADDED
@@ -0,0 +1,106 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: rtesseract
3
+ version: !ruby/object:Gem::Version
4
+ hash: 29
5
+ prerelease: false
6
+ segments:
7
+ - 0
8
+ - 0
9
+ - 1
10
+ version: 0.0.1
11
+ platform: ruby
12
+ authors:
13
+ - Danilo Jeremias da Silva
14
+ autorequire:
15
+ bindir: bin
16
+ cert_chain: []
17
+
18
+ date: 2010-08-25 00:00:00 -03:00
19
+ default_executable:
20
+ dependencies:
21
+ - !ruby/object:Gem::Dependency
22
+ name: thoughtbot-shoulda
23
+ prerelease: false
24
+ requirement: &id001 !ruby/object:Gem::Requirement
25
+ none: false
26
+ requirements:
27
+ - - ">="
28
+ - !ruby/object:Gem::Version
29
+ hash: 3
30
+ segments:
31
+ - 0
32
+ version: "0"
33
+ type: :development
34
+ version_requirements: *id001
35
+ - !ruby/object:Gem::Dependency
36
+ name: rmagick
37
+ prerelease: false
38
+ requirement: &id002 !ruby/object:Gem::Requirement
39
+ none: false
40
+ requirements:
41
+ - - ">="
42
+ - !ruby/object:Gem::Version
43
+ hash: 57
44
+ segments:
45
+ - 2
46
+ - 13
47
+ - 1
48
+ version: 2.13.1
49
+ type: :development
50
+ version_requirements: *id002
51
+ description: Ruby library for working with the Tesseract OCR.
52
+ email: dannnylo@gmail.com
53
+ executables: []
54
+
55
+ extensions: []
56
+
57
+ extra_rdoc_files:
58
+ - LICENSE
59
+ - README.rdoc
60
+ files:
61
+ - .document
62
+ - .gitignore
63
+ - LICENSE
64
+ - README.rdoc
65
+ - Rakefile
66
+ - lib/rtesseract.rb
67
+ - rtesseract.gemspec
68
+ - test/helper.rb
69
+ - test/test_rtesseract.rb
70
+ has_rdoc: true
71
+ homepage: http://github.com/dannnylo/rtesseract
72
+ licenses: []
73
+
74
+ post_install_message:
75
+ rdoc_options:
76
+ - --charset=UTF-8
77
+ require_paths:
78
+ - lib
79
+ required_ruby_version: !ruby/object:Gem::Requirement
80
+ none: false
81
+ requirements:
82
+ - - ">="
83
+ - !ruby/object:Gem::Version
84
+ hash: 3
85
+ segments:
86
+ - 0
87
+ version: "0"
88
+ required_rubygems_version: !ruby/object:Gem::Requirement
89
+ none: false
90
+ requirements:
91
+ - - ">="
92
+ - !ruby/object:Gem::Version
93
+ hash: 3
94
+ segments:
95
+ - 0
96
+ version: "0"
97
+ requirements: []
98
+
99
+ rubyforge_project:
100
+ rubygems_version: 1.3.7
101
+ signing_key:
102
+ specification_version: 3
103
+ summary: Ruby library for working with the Tesseract OCR.
104
+ test_files:
105
+ - test/helper.rb
106
+ - test/test_rtesseract.rb