dejunk 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/.travis.yml +4 -0
- data/Gemfile +4 -0
- data/LICENSE +202 -0
- data/README.md +73 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +7 -0
- data/dejunk.gemspec +25 -0
- data/lib/dejunk.rb +270 -0
- data/lib/dejunk/version.rb +3 -0
- data/resources/bigram_frequencies.yml +3438 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 11a02210b2135091e658c20aea3611ccb4b22627
|
4
|
+
data.tar.gz: 6bd647976a92dff85ade9fca15f45848ed577118
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b6f54d2dd4a8ec45dd8209d34ee6bbc1eb6ba76819f25720cec74f3a0af4233eb71c4059dfe58b33ec668bec0a19a616eadf6a822648485a714b610254d338dc
|
7
|
+
data.tar.gz: 5e92d10677561fa1b2b3afdf4e6ba582098266c9a51a92053e7cc80eb13107a54cec524c1921fbf4ad46937b0f44e37e00b88533d3d5992fec08d3c7b07141e7
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,202 @@
|
|
1
|
+
Apache License
|
2
|
+
Version 2.0, January 2004
|
3
|
+
http://www.apache.org/licenses/
|
4
|
+
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
6
|
+
|
7
|
+
1. Definitions.
|
8
|
+
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
11
|
+
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
13
|
+
the copyright owner that is granting the License.
|
14
|
+
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
16
|
+
other entities that control, are controlled by, or are under common
|
17
|
+
control with that entity. For the purposes of this definition,
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
19
|
+
direction or management of such entity, whether by contract or
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
22
|
+
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
24
|
+
exercising permissions granted by this License.
|
25
|
+
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
27
|
+
including but not limited to software source code, documentation
|
28
|
+
source, and configuration files.
|
29
|
+
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
31
|
+
transformation or translation of a Source form, including but
|
32
|
+
not limited to compiled object code, generated documentation,
|
33
|
+
and conversions to other media types.
|
34
|
+
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
36
|
+
Object form, made available under the License, as indicated by a
|
37
|
+
copyright notice that is included in or attached to the work
|
38
|
+
(an example is provided in the Appendix below).
|
39
|
+
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
46
|
+
the Work and Derivative Works thereof.
|
47
|
+
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
49
|
+
the original version of the Work and any modifications or additions
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
61
|
+
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
64
|
+
subsequently incorporated within the Work.
|
65
|
+
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
72
|
+
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
78
|
+
where such license applies only to those patent claims licensable
|
79
|
+
by such Contributor that are necessarily infringed by their
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
82
|
+
institute patent litigation against any entity (including a
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
85
|
+
or contributory patent infringement, then any patent licenses
|
86
|
+
granted to You under this License for that Work shall terminate
|
87
|
+
as of the date such litigation is filed.
|
88
|
+
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
91
|
+
modifications, and in Source or Object form, provided that You
|
92
|
+
meet the following conditions:
|
93
|
+
|
94
|
+
(a) You must give any other recipients of the Work or
|
95
|
+
Derivative Works a copy of this License; and
|
96
|
+
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
98
|
+
stating that You changed the files; and
|
99
|
+
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
102
|
+
attribution notices from the Source form of the Work,
|
103
|
+
excluding those notices that do not pertain to any part of
|
104
|
+
the Derivative Works; and
|
105
|
+
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
108
|
+
include a readable copy of the attribution notices contained
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
111
|
+
of the following places: within a NOTICE text file distributed
|
112
|
+
as part of the Derivative Works; within the Source form or
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
114
|
+
within a display generated by the Derivative Works, if and
|
115
|
+
wherever such third-party notices normally appear. The contents
|
116
|
+
of the NOTICE file are for informational purposes only and
|
117
|
+
do not modify the License. You may add Your own attribution
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
120
|
+
that such additional attribution notices cannot be construed
|
121
|
+
as modifying the License.
|
122
|
+
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
124
|
+
may provide additional or different license terms and conditions
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
128
|
+
the conditions stated in this License.
|
129
|
+
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
133
|
+
this License, without any additional terms or conditions.
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
135
|
+
the terms of any separate license agreement you may have executed
|
136
|
+
with Licensor regarding such Contributions.
|
137
|
+
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
140
|
+
except as required for reasonable and customary use in describing the
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
142
|
+
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
152
|
+
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
158
|
+
incidental, or consequential damages of any character arising as a
|
159
|
+
result of this License or out of the use or inability to use the
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
162
|
+
other commercial damages or losses), even if such Contributor
|
163
|
+
has been advised of the possibility of such damages.
|
164
|
+
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
168
|
+
or other liability obligations and/or rights consistent with this
|
169
|
+
License. However, in accepting such obligations, You may act only
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
174
|
+
of your accepting any such warranty or additional liability.
|
175
|
+
|
176
|
+
END OF TERMS AND CONDITIONS
|
177
|
+
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
179
|
+
|
180
|
+
To apply the Apache License to your work, attach the following
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "{}"
|
182
|
+
replaced with your own identifying information. (Don't include
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
184
|
+
comment syntax for the file format. We also recommend that a
|
185
|
+
file or class name and description of purpose be included on the
|
186
|
+
same "printed page" as the copyright notice for easier
|
187
|
+
identification within third-party archives.
|
188
|
+
|
189
|
+
Copyright {yyyy} {name of copyright owner}
|
190
|
+
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
192
|
+
you may not use this file except in compliance with the License.
|
193
|
+
You may obtain a copy of the License at
|
194
|
+
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
196
|
+
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
200
|
+
See the License for the specific language governing permissions and
|
201
|
+
limitations under the License.
|
202
|
+
|
data/README.md
ADDED
@@ -0,0 +1,73 @@
|
|
1
|
+
# Dejunk
|
2
|
+
|
3
|
+
Detect keyboard mashing and other junk in your data.
|
4
|
+
|
5
|
+
For example, if you allow user-entered tags, but want to hide bad ones. Or if
|
6
|
+
you want to detect user frustration filling out a particular field, and do
|
7
|
+
something about it!
|
8
|
+
|
9
|
+
Uses a variety of heuristics, the most sophisticated being a comparison of
|
10
|
+
bigrams in the input to the frequencies in a "known-good" corpus vs. their
|
11
|
+
proximity on a keyboard. Achieves pretty good precision on Academia.edu's data,
|
12
|
+
but might need adjustment for yours.
|
13
|
+
|
14
|
+
## Installation
|
15
|
+
|
16
|
+
Add this line to your application's Gemfile:
|
17
|
+
|
18
|
+
```ruby
|
19
|
+
gem 'dejunk'
|
20
|
+
```
|
21
|
+
|
22
|
+
And then execute:
|
23
|
+
|
24
|
+
$ bundle
|
25
|
+
|
26
|
+
Or install it yourself as:
|
27
|
+
|
28
|
+
$ gem install dejunk
|
29
|
+
|
30
|
+
## Usage
|
31
|
+
|
32
|
+
The main interface is `Dejunk.is_junk?`. Pass a string, and get a truthy value
|
33
|
+
if it looks junky, and false otherwise.
|
34
|
+
|
35
|
+
```ruby
|
36
|
+
$ Dejunk.is_junk?('Hello World')
|
37
|
+
=> false
|
38
|
+
$ Dejunk.is_junk?('qwefqwef')
|
39
|
+
=> :mashing_bigrams
|
40
|
+
|
41
|
+
$ Dejunk.is_junk?('asdf')
|
42
|
+
=> :asdf_row
|
43
|
+
$ Dejunk.is_junk?('fads')
|
44
|
+
=> false
|
45
|
+
|
46
|
+
$ Dejunk.is_junk?('Hi')
|
47
|
+
=> :too_short
|
48
|
+
$ Dejunk.is_junk?('Hi', whitelist_regexes: [/\Ahi\z/i])
|
49
|
+
=> false
|
50
|
+
```
|
51
|
+
|
52
|
+
Returns a reason when junk is detected for aid in debugging. Optional parameters
|
53
|
+
are `min_alnum_chars` (defaults to 3), and `whitelist_strings` and
|
54
|
+
`whitelist_regexes` (both default to none).
|
55
|
+
|
56
|
+
## Development
|
57
|
+
|
58
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run
|
59
|
+
`rake spec` to run the tests. You can also run `bin/console` for an interactive
|
60
|
+
prompt that will allow you to experiment.
|
61
|
+
|
62
|
+
To install this gem onto your local machine, run `bundle exec rake install`.
|
63
|
+
To release a new version, update the version number in `version.rb`, and then run
|
64
|
+
`bundle exec rake release`, which will create a git tag for the version,
|
65
|
+
push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
66
|
+
|
67
|
+
## Contributing
|
68
|
+
|
69
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/academia-edu/dejunk
|
70
|
+
|
71
|
+
## License
|
72
|
+
|
73
|
+
Apache 2.0
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "dejunk"
|
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/dejunk.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'dejunk/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "dejunk"
|
8
|
+
spec.version = Dejunk::VERSION
|
9
|
+
spec.authors = ["David Judd"]
|
10
|
+
spec.email = ["david@academia.edu"]
|
11
|
+
|
12
|
+
spec.summary = 'Detect keyboard mashing and other junk in your data.'
|
13
|
+
spec.homepage = 'https://github.com/academia-edu/dejunk'
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
16
|
+
spec.bindir = "exe"
|
17
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_dependency 'activesupport'
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.10"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_development_dependency "rspec"
|
25
|
+
end
|
data/lib/dejunk.rb
ADDED
@@ -0,0 +1,270 @@
|
|
1
|
+
require "dejunk/version"
|
2
|
+
require "yaml"
|
3
|
+
require "active_support/core_ext/string"
|
4
|
+
|
5
|
+
module Dejunk
|
6
|
+
extend self
|
7
|
+
|
8
|
+
# All characters on the middle row of a QWERTY keyboard
|
9
|
+
MASH_CHARS = 'ASDFGHJKLasdfghjkl;: '
|
10
|
+
|
11
|
+
# All neighboring key pairs on a QWERTY keyboard, except "er" and "re" which
|
12
|
+
# each make up >1% of bigrams in our "good" sample, plus each letter repeated
|
13
|
+
# or with a space
|
14
|
+
MASH_BIGRAMS = (
|
15
|
+
("abcdefghijklmnopqrstuvwxyz".chars.flat_map { |l| ["#{l} ", "#{l}#{l}"] }) +
|
16
|
+
%w( qw we rt ty yu ui op as sd df fg gh hj jk kl zx xd cv vb bn nm qa az ws sx ed dc rf fv tg gb yh hn uj jm ik ol )
|
17
|
+
).flat_map { |bigram| [bigram, bigram.reverse] }.to_set.freeze
|
18
|
+
|
19
|
+
def is_junk?(string, min_alnum_chars: 3, whitelist_regexes: [], whitelist_strings: [])
|
20
|
+
if string && (whitelist_strings.include?(string) || whitelist_regexes.any? { |re| string =~ re })
|
21
|
+
return false
|
22
|
+
end
|
23
|
+
|
24
|
+
return :no_alpha if string.nil? || string !~ /[[:alpha:]]/
|
25
|
+
|
26
|
+
normed = normalize_for_comparison(string)
|
27
|
+
|
28
|
+
return :too_short if too_few_alphanumeric_chars?(normed, min_alnum_chars)
|
29
|
+
return :one_char_repeat if excessive_single_character_repeats?(string, normed)
|
30
|
+
return :starts_with_punct if starts_with_disallowed_punctuation?(string)
|
31
|
+
return :too_many_short_words if too_many_short_words?(string)
|
32
|
+
return :three_chars_repeat_twice if three_plus_chars_repeat_twice?(string)
|
33
|
+
return :fuck if string =~ /\bfuck/i
|
34
|
+
return :missing_vowels if missing_vowels?(string, normed)
|
35
|
+
return :asdf_row if asdf_row_and_suspicious?(string)
|
36
|
+
|
37
|
+
ascii_proportion = string.chars.count { |c| c.ord < 128 }.to_f / string.length
|
38
|
+
|
39
|
+
# The bigrams look like the ones you'd get from keyboard mashing
|
40
|
+
# (the probability shouldn't be taken too literally, > 0.25 is almost all
|
41
|
+
# mashing in practice on our corpus)
|
42
|
+
if string.length > 1 && ascii_proportion > 0.8
|
43
|
+
if probability_of_keyboard_mashing(string) > 0.25
|
44
|
+
return :mashing_bigrams
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
# The bigrams don't look like the bigrams in legitimate strings
|
49
|
+
if string.length > 6 && ascii_proportion > 0.8
|
50
|
+
corpus_similarity = bigram_similarity_to_corpus(string)
|
51
|
+
|
52
|
+
# The similarity is more accurate for longer strings, and with more ASCII,
|
53
|
+
# so increase the value (= lower the threshold) for shorter strings and
|
54
|
+
# strings with less ASCII.
|
55
|
+
score = corpus_similarity * (1.0/ascii_proportion**2) * (1.0/(1 - Math.exp(-0.1*string.length)))
|
56
|
+
|
57
|
+
if score < 0.03
|
58
|
+
return :unlikely_bigrams
|
59
|
+
elsif score < 0.08 && string !~ /\A([[:upper:]][[:lower:]]+ )*[[:upper:]][[:lower:]]+\z/
|
60
|
+
# The similarity ignores casing, so instead use a higher threshold if
|
61
|
+
# the casing looks wrong
|
62
|
+
return :unlikely_bigrams
|
63
|
+
elsif score < bigram_similarity_to_mashing(string)
|
64
|
+
return :mashing_bigrams
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
false
|
69
|
+
end
|
70
|
+
|
71
|
+
# Cosine similarity between vector of frequencies of bigrams within string,
|
72
|
+
# and vector of frequencies of all bigrams within corpus
|
73
|
+
def bigram_similarity_to_corpus(string)
|
74
|
+
bigrams = bigrams(string)
|
75
|
+
|
76
|
+
freqs = bigrams.
|
77
|
+
each_with_object(Hash.new(0)) { |bigram, counts| counts[bigram] += 1 }.
|
78
|
+
each_with_object({}) do |(bigram,count), freqs|
|
79
|
+
freqs[bigram] = count.to_f / bigrams.length
|
80
|
+
end
|
81
|
+
|
82
|
+
numerator = freqs.
|
83
|
+
map{ |bigram, freq| corpus_bigram_frequencies[bigram].to_f * freq }.inject(&:+)
|
84
|
+
denominator = corpus_bigram_magnitude * ((freqs.values.map{ |v| v**2 }.inject(&:+)) ** 0.5)
|
85
|
+
|
86
|
+
numerator / denominator
|
87
|
+
end
|
88
|
+
|
89
|
+
# Cosine similarity between vector of frequencies of bigrams within string,
|
90
|
+
# and vector which assumes all bigrams made of neighboring pairs on the keyboard
|
91
|
+
# are equally likely, and no others appear
|
92
|
+
def bigram_similarity_to_mashing(string)
|
93
|
+
bigrams = bigrams(string)
|
94
|
+
|
95
|
+
freqs = bigrams.
|
96
|
+
each_with_object(Hash.new(0)) { |bigram, counts| counts[bigram] += 1 }.
|
97
|
+
each_with_object({}) do |(bigram,count), freqs|
|
98
|
+
freqs[bigram] = count.to_f / bigrams.length
|
99
|
+
end
|
100
|
+
|
101
|
+
numerator = freqs.map{ |bigram, freq| freq * mashing_bigram_frequencies[bigram].to_f }.inject(&:+)
|
102
|
+
denominator = mashing_bigram_magnitude * ((freqs.values.map{ |v| v**2 }.inject(&:+)) ** 0.5)
|
103
|
+
|
104
|
+
numerator / denominator
|
105
|
+
end
|
106
|
+
|
107
|
+
def bigrams(string)
|
108
|
+
return [] if string.nil?
|
109
|
+
|
110
|
+
string = string.strip
|
111
|
+
return [] if string.length < 2
|
112
|
+
|
113
|
+
string.
|
114
|
+
chars.
|
115
|
+
zip(string.chars[1..-1]).
|
116
|
+
map { |c1,c2| "#{c1.mb_chars.downcase}#{c2.mb_chars.downcase}" if c1 && c2 }.
|
117
|
+
compact.
|
118
|
+
map { |bigram| bigram.gsub(/[0-9]/, '0'.freeze) }.
|
119
|
+
map { |bigram| bigram.gsub(/[[:space:]]/, ' '.freeze) }
|
120
|
+
end
|
121
|
+
|
122
|
+
# The Bayesian probability of a string being keyboard mashing, given the
|
123
|
+
# probability of each bigram if drawn either from the legit corpus or from
|
124
|
+
# mashing, and an a priori probability of mashing.
|
125
|
+
#
|
126
|
+
# The probability shouldn't be taken too literally, but it's a useful
|
127
|
+
# indicator.
|
128
|
+
def probability_of_keyboard_mashing(string, apriori_probability_of_mashing: 0.1)
|
129
|
+
bigrams = bigrams(string)
|
130
|
+
|
131
|
+
return 0 unless bigrams.present?
|
132
|
+
|
133
|
+
prob_bigrams_given_mashing = bigrams.
|
134
|
+
map { |bigram| BigDecimal.new(mashing_probability(bigram).to_s) }.
|
135
|
+
inject(&:*)
|
136
|
+
|
137
|
+
prob_bigrams_given_corpus = bigrams.
|
138
|
+
map { |bigram| BigDecimal.new(corpus_probability(bigram).to_s) }.
|
139
|
+
inject(&:*)
|
140
|
+
|
141
|
+
numerator = prob_bigrams_given_mashing * apriori_probability_of_mashing
|
142
|
+
|
143
|
+
numerator / (numerator + prob_bigrams_given_corpus * (1 - apriori_probability_of_mashing))
|
144
|
+
end
|
145
|
+
|
146
|
+
def normalize_for_comparison(string)
|
147
|
+
string.
|
148
|
+
mb_chars.
|
149
|
+
normalize(:kd).
|
150
|
+
gsub(/\p{Mn}+/, ''.freeze).
|
151
|
+
gsub(/[^[:alnum:]]+/, ''.freeze).
|
152
|
+
downcase
|
153
|
+
end
|
154
|
+
|
155
|
+
private
|
156
|
+
|
157
|
+
def missing_vowels?(string, normed)
|
158
|
+
# Missing vowels (and doesn't look like acronym, and is ASCII so we can tell)
|
159
|
+
unless normed.chars.any? { |c| c.ord >= 128 } || string == string.upcase
|
160
|
+
return true if normed !~ /[aeiouy]/i
|
161
|
+
end
|
162
|
+
|
163
|
+
false
|
164
|
+
end
|
165
|
+
|
166
|
+
# One character repeated 5 or more times, or 3 or more times and not an
|
167
|
+
# acronym, roman numeral, or www
|
168
|
+
def excessive_single_character_repeats?(string, normed)
|
169
|
+
return true if normed.chars.uniq.count == 1
|
170
|
+
|
171
|
+
if string =~ /([^[:space:]i])\1\1/i
|
172
|
+
return true if normed =~ /([^0-9])\1\1\1\1/i
|
173
|
+
|
174
|
+
string.split(/[[:space:][:punct:]]/).each do |word|
|
175
|
+
return true if word =~ /([^iw0-9])\1\1/i && word != word.upcase
|
176
|
+
end
|
177
|
+
end
|
178
|
+
|
179
|
+
false
|
180
|
+
end
|
181
|
+
|
182
|
+
def three_plus_chars_repeat_twice?(string)
|
183
|
+
# At least 3 characters repeated at least twice in a row (but only on short
|
184
|
+
# strings, otherwise there are false positives)
|
185
|
+
string.length < 80 && string =~ /(....*)[[:space:][:punct:]]*\1[[:space:][:punct:]]*\1/
|
186
|
+
end
|
187
|
+
|
188
|
+
def asdf_row_and_suspicious?(string)
|
189
|
+
# All characters from the same row of the keyboard is suspicious, but we
|
190
|
+
# need additional confirmation
|
191
|
+
if string.chars.all? { |c| MASH_CHARS.include?(c) }
|
192
|
+
return true if string.length >= 16
|
193
|
+
return true if string =~ /(...).*\1/ # Three-plus characters, repeated
|
194
|
+
return true if string =~ /(..).*\1.*\1/ # Two characters, repeated twice
|
195
|
+
return true if string =~ /\b[sdfghjkl]\b/ # Stray lowercase letter
|
196
|
+
return true if string =~ /[^aeiouy]{3}/i && (string.length > 5 || string != string.upcase) # Three consonants in a row, non-acronym
|
197
|
+
end
|
198
|
+
|
199
|
+
false
|
200
|
+
end
|
201
|
+
|
202
|
+
def too_few_alphanumeric_chars?(normed, min_alnum_chars)
|
203
|
+
# Too short (unless we're dealing with a large alphabet with legitimate
|
204
|
+
# single-char words)
|
205
|
+
if normed.length < min_alnum_chars
|
206
|
+
unless normed =~ /\p{Han}|\p{Hangul}|\p{Hiragana}|\p{Katakana}/
|
207
|
+
return true
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
false
|
212
|
+
end
|
213
|
+
|
214
|
+
def starts_with_disallowed_punctuation?(string)
|
215
|
+
# Starting punctuation, except opening parens or quote
|
216
|
+
string =~ /\A[[:punct:]]/ && string !~ /\A(\p{Pi}|\p{Ps}|['"¿»’]).+/
|
217
|
+
end
|
218
|
+
|
219
|
+
def too_many_short_words?(string)
|
220
|
+
words = string.split
|
221
|
+
two_chars = words.select { |w| w.length < 3 }.count
|
222
|
+
if two_chars > 2 && two_chars > 0.75 * words.length
|
223
|
+
return true
|
224
|
+
end
|
225
|
+
|
226
|
+
false
|
227
|
+
end
|
228
|
+
|
229
|
+
def mashing_probability(bigram)
|
230
|
+
if (f = mashing_bigram_frequencies[bigram])
|
231
|
+
f
|
232
|
+
elsif f =~ /[a-z]{2}/i
|
233
|
+
# 26**2 = 676, so 1 in 2k seems a reasonable probability for an arbitrary two-letter bigram given mashing
|
234
|
+
0.0005
|
235
|
+
else
|
236
|
+
# An arbitrary (non-ASCII) bigram with mashing is slightly more probable than with legit strings
|
237
|
+
1e-6
|
238
|
+
end
|
239
|
+
end
|
240
|
+
|
241
|
+
def corpus_probability(bigram)
|
242
|
+
corpus_bigram_frequencies[bigram] || 1e-7 # Around the smallest frequency we store for the corpus
|
243
|
+
end
|
244
|
+
|
245
|
+
def corpus_bigram_frequencies
|
246
|
+
@corpus_bigram_frequencies ||= YAML.load_file(File.expand_path('../../resources/bigram_frequencies.yml', __FILE__)).freeze
|
247
|
+
end
|
248
|
+
|
249
|
+
def corpus_bigram_magnitude
|
250
|
+
@corpus_bigram_magnitude ||= (corpus_bigram_frequencies.values.map{ |v| v**2 }.inject(&:+)) ** 0.5
|
251
|
+
end
|
252
|
+
|
253
|
+
def mashing_bigram_frequencies
|
254
|
+
# This is a guess because we don't have a good corpus, but we assume that
|
255
|
+
# 50% of mashing bigrams are a neighboring pair on the ASDF row or a duplicate
|
256
|
+
# and the rest are evenly distributed among other neighboring pairs or char-
|
257
|
+
# plus-space.
|
258
|
+
@mashing_bigram_frequencies ||= MASH_BIGRAMS.each_with_object({}) do |bigram, freqs|
|
259
|
+
if bigram.first == bigram.last || bigram.chars.all? { |c| c != ' '.freeze && MASH_CHARS.include?(c) }
|
260
|
+
freqs[bigram] = 0.5 / (16 + 26)
|
261
|
+
else
|
262
|
+
freqs[bigram] = 0.5 / (MASH_BIGRAMS.length - 16 - 26)
|
263
|
+
end
|
264
|
+
end
|
265
|
+
end
|
266
|
+
|
267
|
+
def mashing_bigram_magnitude
|
268
|
+
@mashing_bigram_magnitude ||= (mashing_bigram_frequencies.values.map{ |v| v**2 }.inject(&:+)) ** 0.5
|
269
|
+
end
|
270
|
+
end
|