rtesseract 2.2.0 → 3.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.document +1 -2
- data/.gitignore +12 -0
- data/.rspec +2 -0
- data/.travis.yml +13 -10
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +4 -17
- data/Gemfile.lock +40 -85
- data/LICENSE.txt +18 -17
- data/README.md +137 -0
- data/Rakefile +4 -48
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/rtesseract.rb +22 -220
- data/lib/rtesseract/box.rb +15 -60
- data/lib/rtesseract/check.rb +14 -0
- data/lib/rtesseract/command.rb +41 -0
- data/lib/rtesseract/configuration.rb +15 -64
- data/lib/rtesseract/pdf.rb +18 -0
- data/lib/rtesseract/text.rb +9 -0
- data/lib/rtesseract/tsv.rb +18 -0
- data/lib/rtesseract/version.rb +3 -0
- data/rtesseract.gemspec +27 -98
- metadata +36 -85
- data/README.rdoc +0 -156
- data/VERSION +0 -1
- data/lib/processors/mini_magick.rb +0 -43
- data/lib/processors/none.rb +0 -34
- data/lib/processors/rmagick.rb +0 -46
- data/lib/rtesseract/blob.rb +0 -34
- data/lib/rtesseract/box_char.rb +0 -31
- data/lib/rtesseract/errors.rb +0 -21
- data/lib/rtesseract/mixed.rb +0 -54
- data/lib/rtesseract/processor.rb +0 -19
- data/lib/rtesseract/utils.rb +0 -44
- data/lib/rtesseract/uzn.rb +0 -47
- data/spec/configs/eng.user-words.txt +0 -13
- data/spec/images/README.pdf +0 -0
- data/spec/images/blank.tif +0 -0
- data/spec/images/mixed.tif +0 -0
- data/spec/images/orientation_reverse.png +0 -0
- data/spec/images/test with spaces.tif +0 -0
- data/spec/images/test-pdf.png +0 -0
- data/spec/images/test.bmp +0 -0
- data/spec/images/test.jpg +0 -0
- data/spec/images/test.png +0 -0
- data/spec/images/test.tif +0 -0
- data/spec/images/test1.tif +0 -0
- data/spec/images/test_words.png +0 -0
- data/spec/rtesseract_box_char_spec.rb +0 -82
- data/spec/rtesseract_box_spec.rb +0 -36
- data/spec/rtesseract_mixed_spec.rb +0 -49
- data/spec/rtesseract_spec.rb +0 -282
- data/spec/rtesseract_uzn_spec.rb +0 -56
- data/spec/spec_helper.rb +0 -21
data/Rakefile
CHANGED
@@ -1,50 +1,6 @@
|
|
1
|
-
|
1
|
+
require "bundler/gem_tasks"
|
2
|
+
require "rspec/core/rake_task"
|
2
3
|
|
3
|
-
|
4
|
-
require 'bundler'
|
5
|
-
begin
|
6
|
-
Bundler.setup(:default, :development)
|
7
|
-
rescue Bundler::BundlerError => e
|
8
|
-
$stderr.puts e.message
|
9
|
-
$stderr.puts 'Run `bundle install` to install missing gems'
|
10
|
-
exit e.status_code
|
11
|
-
end
|
12
|
-
require 'rake'
|
4
|
+
RSpec::Core::RakeTask.new(:spec)
|
13
5
|
|
14
|
-
|
15
|
-
Jeweler::Tasks.new do |gem|
|
16
|
-
# gem is a Gem::Specification... see http://guides.rubygems.org/specification-reference/ for more options
|
17
|
-
gem.name = 'rtesseract'
|
18
|
-
gem.homepage = 'http://github.com/dannnylo/rtesseract'
|
19
|
-
gem.license = 'MIT'
|
20
|
-
gem.summary = 'Ruby library for working with the Tesseract OCR.'
|
21
|
-
gem.description = 'Ruby library for working with the Tesseract OCR.'
|
22
|
-
gem.email = 'dannnylo@gmail.com'
|
23
|
-
gem.authors = ['Danilo Jeremias da Silva']
|
24
|
-
# dependencies defined in Gemfile
|
25
|
-
end
|
26
|
-
Jeweler::RubygemsDotOrgTasks.new
|
27
|
-
|
28
|
-
require 'rspec/core'
|
29
|
-
require 'rspec/core/rake_task'
|
30
|
-
RSpec::Core::RakeTask.new(:spec) do |spec|
|
31
|
-
spec.pattern = FileList['spec/**/*_spec.rb']
|
32
|
-
end
|
33
|
-
|
34
|
-
desc 'Code coverage detail'
|
35
|
-
task :simplecov do
|
36
|
-
ENV['COVERAGE'] = 'true'
|
37
|
-
Rake::Task['spec'].execute
|
38
|
-
end
|
39
|
-
|
40
|
-
task default: :spec
|
41
|
-
|
42
|
-
require 'rdoc/task'
|
43
|
-
Rake::RDocTask.new do |rdoc|
|
44
|
-
version = File.exist?('VERSION') ? File.read('VERSION') : ''
|
45
|
-
|
46
|
-
rdoc.rdoc_dir = 'rdoc'
|
47
|
-
rdoc.title = "rtesseract #{version}"
|
48
|
-
rdoc.rdoc_files.include('README*')
|
49
|
-
rdoc.rdoc_files.include('lib/**/*.rb')
|
50
|
-
end
|
6
|
+
task :default => :spec
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "rtesseract"
|
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/setup
ADDED
data/lib/rtesseract.rb
CHANGED
@@ -1,244 +1,46 @@
|
|
1
|
-
|
2
|
-
require
|
3
|
-
require
|
1
|
+
require "rtesseract/check"
|
2
|
+
require "rtesseract/configuration"
|
3
|
+
require "rtesseract/command"
|
4
|
+
require "rtesseract/text"
|
5
|
+
require "rtesseract/pdf"
|
6
|
+
require "rtesseract/box"
|
7
|
+
require "rtesseract/tsv"
|
4
8
|
|
5
|
-
require 'rtesseract/utils'
|
6
|
-
require 'rtesseract/configuration'
|
7
|
-
require 'rtesseract/errors'
|
8
|
-
|
9
|
-
# Ruby wrapper for Tesseract OCR
|
10
9
|
class RTesseract
|
11
|
-
|
12
|
-
attr_reader :processor
|
13
|
-
attr_reader :source
|
14
|
-
|
15
|
-
def initialize(src = '', options = {})
|
16
|
-
self.configuration = RTesseract.local_config(options)
|
17
|
-
@options = options || {}
|
18
|
-
@points = {}
|
19
|
-
@processor = RTesseract::Processor.choose_processor!(configuration.processor)
|
20
|
-
self.source = src
|
21
|
-
initialize_hook
|
22
|
-
end
|
23
|
-
|
24
|
-
# Hook to end of initialize method
|
25
|
-
def initialize_hook
|
26
|
-
end
|
27
|
-
|
28
|
-
# Define the source
|
29
|
-
def source=(src)
|
30
|
-
@value = nil
|
31
|
-
@pdf_path = nil
|
32
|
-
@source = @processor.image?(src) ? src : Pathname.new(src)
|
33
|
-
end
|
34
|
-
|
35
|
-
# Crop image to convert
|
36
|
-
def crop!(points = {})
|
37
|
-
@value = nil
|
38
|
-
@points = points
|
39
|
-
self
|
40
|
-
end
|
41
|
-
|
42
|
-
# Select the language
|
43
|
-
# ===Languages
|
44
|
-
## * eng - English
|
45
|
-
## * deu - German
|
46
|
-
## * deu-f - German fraktur
|
47
|
-
## * fra - French
|
48
|
-
## * ita - Italian
|
49
|
-
## * nld - Dutch
|
50
|
-
## * por - Portuguese
|
51
|
-
## * spa - Spanish
|
52
|
-
## * vie - Vietnamese
|
53
|
-
## Note: Make sure you have installed the language to tesseract
|
54
|
-
def lang
|
55
|
-
language = (configuration.lang || 'eng').to_s.strip.downcase
|
56
|
-
" -l #{LANGUAGES[language] || language} "
|
57
|
-
rescue
|
58
|
-
''
|
59
|
-
end
|
60
|
-
|
61
|
-
# Convert option to command
|
62
|
-
def option_to_string(prefix, value = nil)
|
63
|
-
(value.nil? ? '' : " #{prefix} #{value} ")
|
64
|
-
rescue
|
65
|
-
''
|
66
|
-
end
|
67
|
-
|
68
|
-
# Page Segment Mode
|
69
|
-
def psm
|
70
|
-
option_to_string('-psm', configuration.psm)
|
71
|
-
end
|
72
|
-
|
73
|
-
# Engine Mode
|
74
|
-
def oem
|
75
|
-
option_to_string '--oem', configuration.oem
|
76
|
-
end
|
77
|
-
|
78
|
-
# Tessdata Dir
|
79
|
-
def tessdata_dir
|
80
|
-
option_to_string('--tessdata-dir', configuration.tessdata_dir)
|
81
|
-
end
|
82
|
-
|
83
|
-
# User Words
|
84
|
-
def user_words
|
85
|
-
option_to_string('--user-words', configuration.user_words)
|
86
|
-
end
|
87
|
-
|
88
|
-
# User Patterns
|
89
|
-
def user_patterns
|
90
|
-
option_to_string('--user-patterns', configuration.user_patterns)
|
91
|
-
end
|
92
|
-
|
93
|
-
# Options on line
|
94
|
-
def options_cmd
|
95
|
-
configuration.options_cmd
|
96
|
-
end
|
97
|
-
|
98
|
-
# Hook to before config
|
99
|
-
def config_hook
|
100
|
-
end
|
101
|
-
|
102
|
-
# Convert configurations
|
103
|
-
def config
|
104
|
-
@options ||= {}
|
105
|
-
config_hook
|
106
|
-
@options.map { |k, v| "#{k} #{v}" }.join("\n")
|
107
|
-
end
|
10
|
+
class Error < StandardError; end
|
108
11
|
|
109
|
-
|
110
|
-
def config_file
|
111
|
-
config_hook
|
112
|
-
return '' if @options == {}
|
113
|
-
conf = Tempfile.new('config')
|
114
|
-
conf.write(config)
|
115
|
-
conf.flush
|
116
|
-
conf.path
|
117
|
-
end
|
118
|
-
|
119
|
-
# TODO: Clear console for MacOS or Windows
|
120
|
-
def clear_console_output
|
121
|
-
return '' if configuration.debug
|
122
|
-
return '2>/dev/null' if File.exist?('/dev/null') # Linux console clear
|
123
|
-
end
|
124
|
-
|
125
|
-
# Get image
|
126
|
-
def image
|
127
|
-
(@image = @processor.image_to_tif(@source, @points)).path
|
128
|
-
end
|
129
|
-
|
130
|
-
# Extension of file
|
131
|
-
def file_ext
|
132
|
-
'.txt'
|
133
|
-
end
|
134
|
-
|
135
|
-
# Detect version number
|
136
|
-
def tesseract_version
|
137
|
-
RTesseract::Utils.version_number
|
138
|
-
end
|
139
|
-
|
140
|
-
|
141
|
-
# Rand file path
|
142
|
-
def file_dest
|
143
|
-
@file_dest = Pathname.new(Dir.tmpdir).join("#{Time.now.to_f}#{rand(1500)}").to_s
|
144
|
-
end
|
145
|
-
|
146
|
-
# Full path of file with txt extension
|
147
|
-
def file_with_ext(ext = nil)
|
148
|
-
[@file_dest, ext || file_ext].join('')
|
149
|
-
end
|
150
|
-
|
151
|
-
# Run command
|
152
|
-
def convert_command
|
153
|
-
`#{configuration.command} "#{image}" "#{file_dest}" #{lang} #{oem} #{psm} #{tessdata_dir} #{user_words} #{user_patterns} #{config_file} #{clear_console_output} #{options_cmd.join(' ')}`
|
154
|
-
end
|
12
|
+
check_version!
|
155
13
|
|
156
|
-
|
157
|
-
def pdf?
|
158
|
-
options_cmd.include? 'pdf'
|
159
|
-
end
|
14
|
+
attr_reader :config, :source
|
160
15
|
|
161
|
-
|
162
|
-
|
163
|
-
@
|
16
|
+
def initialize(src = '', options = {})
|
17
|
+
@source = src
|
18
|
+
@config = RTesseract.config.merge(options)
|
164
19
|
end
|
165
20
|
|
166
|
-
|
167
|
-
|
168
|
-
@pdf_path = file_with_ext('.pdf')
|
21
|
+
def to_box
|
22
|
+
Box.run(@source, config)
|
169
23
|
end
|
170
24
|
|
171
|
-
|
172
|
-
|
173
|
-
if pdf?
|
174
|
-
convert_pdf
|
175
|
-
else
|
176
|
-
convert_text
|
177
|
-
RTesseract::Utils.remove_files([@image, file_with_ext])
|
178
|
-
end
|
25
|
+
def words
|
26
|
+
to_box.map { |word| word[:word] }
|
179
27
|
end
|
180
28
|
|
181
|
-
|
182
|
-
|
29
|
+
def to_pdf
|
30
|
+
Pdf.run(@source, config)
|
183
31
|
end
|
184
32
|
|
185
|
-
|
186
|
-
|
187
|
-
convert_command
|
188
|
-
after_convert_hook
|
189
|
-
convert_result
|
190
|
-
rescue => error
|
191
|
-
raise RTesseract::ConversionError.new(error), error, caller
|
33
|
+
def to_tsv
|
34
|
+
Tsv.run(@source, config)
|
192
35
|
end
|
193
36
|
|
194
37
|
# Output value
|
195
38
|
def to_s
|
196
|
-
|
197
|
-
|
198
|
-
if @processor.image?(@source) || @source.file?
|
199
|
-
convert
|
200
|
-
@value
|
201
|
-
else
|
202
|
-
fail RTesseract::ImageNotSelectedError.new(@source)
|
203
|
-
end
|
39
|
+
Text.run(@source, config)
|
204
40
|
end
|
205
41
|
|
206
42
|
# Remove spaces and break-lines
|
207
43
|
def to_s_without_spaces
|
208
44
|
to_s.gsub(/\s/, '')
|
209
45
|
end
|
210
|
-
|
211
|
-
# Output pdf path
|
212
|
-
def to_pdf
|
213
|
-
return @pdf_path if @pdf_path
|
214
|
-
|
215
|
-
fail TesseractVersionError.new if tesseract_version.nil? || tesseract_version < 3.03
|
216
|
-
|
217
|
-
if @processor.image?(@source) || @source.file?
|
218
|
-
options_cmd << 'pdf'
|
219
|
-
convert
|
220
|
-
options_cmd.delete('pdf')
|
221
|
-
@pdf_path
|
222
|
-
else
|
223
|
-
fail RTesseract::ImageNotSelectedError.new(@source)
|
224
|
-
end
|
225
|
-
end
|
226
|
-
|
227
|
-
# Destroy pdf file
|
228
|
-
def clean
|
229
|
-
RTesseract::Utils.remove_files([@pdf_path])
|
230
|
-
end
|
231
|
-
|
232
46
|
end
|
233
|
-
|
234
|
-
require 'rtesseract/mixed'
|
235
|
-
require 'rtesseract/uzn'
|
236
|
-
require 'rtesseract/box'
|
237
|
-
require 'rtesseract/box_char'
|
238
|
-
require 'rtesseract/blob'
|
239
|
-
require 'rtesseract/processor'
|
240
|
-
|
241
|
-
# Processors
|
242
|
-
require 'processors/rmagick.rb'
|
243
|
-
require 'processors/mini_magick.rb'
|
244
|
-
require 'processors/none.rb'
|
data/lib/rtesseract/box.rb
CHANGED
@@ -1,73 +1,28 @@
|
|
1
|
-
# encoding: UTF-8
|
2
1
|
require 'nokogiri'
|
3
|
-
require '
|
2
|
+
require 'tmpdir'
|
4
3
|
|
5
|
-
# RTesseract
|
6
4
|
class RTesseract
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
def initialize_hook
|
11
|
-
@value = []
|
5
|
+
module Box
|
6
|
+
def self.temp_dir
|
7
|
+
@file_path = Pathname.new(Dir.tmpdir)
|
12
8
|
end
|
13
9
|
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
end
|
18
|
-
|
19
|
-
# Words converted
|
20
|
-
def words
|
21
|
-
convert if @value == []
|
22
|
-
@value
|
23
|
-
end
|
24
|
-
|
25
|
-
# Extension of file
|
26
|
-
def file_ext
|
27
|
-
'.hocr'
|
28
|
-
end
|
29
|
-
|
30
|
-
# Read the result file
|
31
|
-
def parse_file
|
32
|
-
html = Nokogiri::HTML(File.read(file_with_ext))
|
33
|
-
html.css('span.ocrx_word, span.ocr_word')
|
34
|
-
end
|
35
|
-
|
36
|
-
# Return words to value
|
37
|
-
def convert_text
|
38
|
-
text_objects = []
|
39
|
-
parse_file.each { |word| text_objects << BoxParser.new(word).to_h }
|
40
|
-
@value = text_objects
|
41
|
-
end
|
10
|
+
def self.run(source, options)
|
11
|
+
name = "rtesseract_#{SecureRandom.uuid}"
|
12
|
+
options.tessedit_create_hocr = 1
|
42
13
|
|
43
|
-
|
44
|
-
def after_convert_hook
|
45
|
-
FileUtils.mv(file_with_ext('.html'), file_with_ext) rescue nil
|
46
|
-
end
|
14
|
+
RTesseract::Command.new(source, temp_dir.join(name).to_s, options).run
|
47
15
|
|
48
|
-
|
49
|
-
def to_s
|
50
|
-
return @value.map { |word| word[:word] } if @value != []
|
51
|
-
if @processor.image?(@source) || @source.file?
|
52
|
-
convert
|
53
|
-
@value.map { |word| word[:word] }.join(' ')
|
54
|
-
else
|
55
|
-
fail RTesseract::ImageNotSelectedError.new(@source)
|
56
|
-
end
|
16
|
+
parse(temp_dir.join("#{name}.hocr").read)
|
57
17
|
end
|
58
18
|
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
@
|
63
|
-
title = @word.attributes['title'].value.to_s
|
64
|
-
@attributes = title.gsub(';', '').split(' ')
|
65
|
-
end
|
19
|
+
def self.parse(content)
|
20
|
+
html = Nokogiri::HTML(content)
|
21
|
+
html.css('span.ocrx_word, span.ocr_word').map do |word|
|
22
|
+
@attributes = word.attributes['title'].value.to_s.gsub(';', '').split(' ')
|
66
23
|
|
67
|
-
# Hash of word and position
|
68
|
-
def to_h
|
69
24
|
{
|
70
|
-
word:
|
25
|
+
word: word.text,
|
71
26
|
x_start: @attributes[1].to_i,
|
72
27
|
y_start: @attributes[2].to_i,
|
73
28
|
x_end: @attributes[3].to_i,
|
@@ -76,4 +31,4 @@ class RTesseract
|
|
76
31
|
end
|
77
32
|
end
|
78
33
|
end
|
79
|
-
end
|
34
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
|
2
|
+
class RTesseract
|
3
|
+
class << self
|
4
|
+
def tesseract_version
|
5
|
+
Open3.capture2e(RTesseract.config.command, "--version").first.to_s.match(/\d+.\d+/)[0].to_f
|
6
|
+
rescue Errno::ENOENT
|
7
|
+
0
|
8
|
+
end
|
9
|
+
|
10
|
+
def check_version!
|
11
|
+
raise RTesseract::Error.new('Tesseract OCR 3.5 or later not installed') if RTesseract.tesseract_version < 3.05
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|