encoding_estimator 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 +2 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +121 -0
- data/Rakefile +2 -0
- data/bin/encest-detect +62 -0
- data/bin/encest-gen +105 -0
- data/encoding_estimator.gemspec +31 -0
- data/lib/encoding_estimator/builder/model_builder.rb +70 -0
- data/lib/encoding_estimator/builder/parallel_model_builder.rb +45 -0
- data/lib/encoding_estimator/conversion.rb +108 -0
- data/lib/encoding_estimator/detection.rb +49 -0
- data/lib/encoding_estimator/detector.rb +156 -0
- data/lib/encoding_estimator/distribution.rb +49 -0
- data/lib/encoding_estimator/lang/de.json +1 -0
- data/lib/encoding_estimator/lang/en.json +1 -0
- data/lib/encoding_estimator/lang/es.json +1 -0
- data/lib/encoding_estimator/lang/fr.json +1 -0
- data/lib/encoding_estimator/lang/ru.json +1 -0
- data/lib/encoding_estimator/language_model.rb +73 -0
- data/lib/encoding_estimator/parallel_support.rb +49 -0
- data/lib/encoding_estimator/version.rb +3 -0
- data/lib/encoding_estimator.rb +66 -0
- metadata +142 -0
@@ -0,0 +1,66 @@
|
|
1
|
+
require_relative 'encoding_estimator/version'
|
2
|
+
|
3
|
+
require_relative 'encoding_estimator/builder/parallel_model_builder'
|
4
|
+
require_relative 'encoding_estimator/detector'
|
5
|
+
require_relative 'encoding_estimator/language_model'
|
6
|
+
|
7
|
+
module EncodingEstimator
|
8
|
+
|
9
|
+
# Convert a string to a UTF-8 string by performing the conversion that
|
10
|
+
# is automatically detected by EncodingEstimator
|
11
|
+
#
|
12
|
+
# @param [String] data String to convert to UTF-8
|
13
|
+
# @param [Array<Symbol|String>] languages List of languages the data might originate from, two-letter-codes, e.g. [:de, :en]
|
14
|
+
# @param [Array<String>] encodings List of encodings to test, e.g. [ 'UTF-8', 'ISO-8859-1' ].
|
15
|
+
# The order defines the priority when choosing from encodings with same detection score
|
16
|
+
# @param [Array<Symbol>] operations Choose which operations (encoding to/decoding from an encoding to UTF-8) to test
|
17
|
+
# @param [Float] penalty Penalty threshold to define when chars are weighted negative
|
18
|
+
# @param [Integer] num_cores Number of threads to use for detection. Use "nil" to use single threaded implementation
|
19
|
+
# @param [Boolean] include_default Include "keep as is" conversion when testing, e.g. check if the string is
|
20
|
+
# already UTF-8 encoded
|
21
|
+
#
|
22
|
+
# @return [String] UTF-8 string
|
23
|
+
def EncodingEstimator.ensure_utf8( data, config = {} )
|
24
|
+
|
25
|
+
params = {
|
26
|
+
languages: [ :de, :en ],
|
27
|
+
encodings: %w(iso-8859-1 utf-16le windows-1251),
|
28
|
+
operations: [Conversion::Operation::DECODE],
|
29
|
+
include_default: true,
|
30
|
+
penalty: 0.01,
|
31
|
+
num_cores: nil,
|
32
|
+
}.merge config
|
33
|
+
|
34
|
+
EncodingEstimator.detect( data, params ).result.perform( data )
|
35
|
+
end
|
36
|
+
|
37
|
+
# Let the EncodingEstimator detect how the input string is encoded
|
38
|
+
#
|
39
|
+
# @param [String] data String to convert to UTF-8
|
40
|
+
# @param [Array<Symbol>] languages List of languages the data might originate from, two-letter-codes, e.g. [:de, :en]
|
41
|
+
# @param [Array<String>] encodings List of encodings to test, e.g. [ 'UTF-8', 'ISO-8859-1' ].
|
42
|
+
# The order defines the priority when choosing from encodings with same detection score
|
43
|
+
# @param [Array<Symbol>] operations Choose which operations (encoding to/decoding from an encoding to UTF-8) to test
|
44
|
+
# @param [Float] penalty Penalty threshold to define when chars are weighted negative
|
45
|
+
# @param [Integer] num_cores Number of threads to use for detection. Use "nil" to use single threaded implementation
|
46
|
+
# @param [Boolean] include_default Include "keep as is" conversion when testing, e.g. check if the string is
|
47
|
+
# already UTF-8 encoded
|
48
|
+
#
|
49
|
+
# @return [EncodingEstimator::Detection] Detection result with scores for all conversions
|
50
|
+
def EncodingEstimator.detect( data, config )
|
51
|
+
|
52
|
+
params = {
|
53
|
+
languages: [ :de, :en ],
|
54
|
+
encodings: %w(iso-8859-1 utf-16le windows-1251),
|
55
|
+
operations: [Conversion::Operation::DECODE],
|
56
|
+
include_default: true,
|
57
|
+
penalty: 0.01,
|
58
|
+
num_cores: nil,
|
59
|
+
}.merge config
|
60
|
+
|
61
|
+
Detector.new(
|
62
|
+
Conversion.generate( params[ :encodings ], params[ :operations ], params[ :include_default ] ),
|
63
|
+
params[ :languages ].map { |l| EncodingEstimator::LanguageModel.new( l ) }, params[ :penalty ], params[:num_cores]
|
64
|
+
).detect data
|
65
|
+
end
|
66
|
+
end
|
metadata
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: encoding_estimator
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Oskar Kirmis
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-26 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: '1.13'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.13'
|
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: htmlentities
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '4.3'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '4.3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: json
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '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: '2.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: slop
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '4.4'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '4.4'
|
83
|
+
description: This gem allows you to detect the encoding of a string based on their
|
84
|
+
content. It uses character distribution statistics to check which encoding is the
|
85
|
+
one that gives you the best results.
|
86
|
+
email:
|
87
|
+
- kirmis@st.ovgu.de
|
88
|
+
executables:
|
89
|
+
- encest-detect
|
90
|
+
- encest-gen
|
91
|
+
extensions: []
|
92
|
+
extra_rdoc_files: []
|
93
|
+
files:
|
94
|
+
- ".gitignore"
|
95
|
+
- CODE_OF_CONDUCT.md
|
96
|
+
- Gemfile
|
97
|
+
- LICENSE.txt
|
98
|
+
- README.md
|
99
|
+
- Rakefile
|
100
|
+
- bin/encest-detect
|
101
|
+
- bin/encest-gen
|
102
|
+
- encoding_estimator.gemspec
|
103
|
+
- lib/encoding_estimator.rb
|
104
|
+
- lib/encoding_estimator/builder/model_builder.rb
|
105
|
+
- lib/encoding_estimator/builder/parallel_model_builder.rb
|
106
|
+
- lib/encoding_estimator/conversion.rb
|
107
|
+
- lib/encoding_estimator/detection.rb
|
108
|
+
- lib/encoding_estimator/detector.rb
|
109
|
+
- lib/encoding_estimator/distribution.rb
|
110
|
+
- lib/encoding_estimator/lang/de.json
|
111
|
+
- lib/encoding_estimator/lang/en.json
|
112
|
+
- lib/encoding_estimator/lang/es.json
|
113
|
+
- lib/encoding_estimator/lang/fr.json
|
114
|
+
- lib/encoding_estimator/lang/ru.json
|
115
|
+
- lib/encoding_estimator/language_model.rb
|
116
|
+
- lib/encoding_estimator/parallel_support.rb
|
117
|
+
- lib/encoding_estimator/version.rb
|
118
|
+
homepage: https://git.iftrue.de/okirmis/encoding_estimator
|
119
|
+
licenses:
|
120
|
+
- MIT
|
121
|
+
metadata: {}
|
122
|
+
post_install_message:
|
123
|
+
rdoc_options: []
|
124
|
+
require_paths:
|
125
|
+
- lib
|
126
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
requirements: []
|
137
|
+
rubyforge_project:
|
138
|
+
rubygems_version: 2.6.8
|
139
|
+
signing_key:
|
140
|
+
specification_version: 4
|
141
|
+
summary: Detect encoding of an input string using character count statistics.
|
142
|
+
test_files: []
|