dejunk 0.2.0 → 0.5.0
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.
- checksums.yaml +4 -4
- data/.circleci/config.yml +19 -0
- data/dejunk.gemspec +3 -2
- data/lib/dejunk/version.rb +1 -1
- data/lib/dejunk.rb +1 -4
- metadata +9 -9
- data/circle.yml +0 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f1ab7cd51156a993d232efbc68bfeb4ea1657f0e112878a4d03ae8963122d359
|
4
|
+
data.tar.gz: 456178beb94060ea3589c5917ee978aa9e96f6534eeb2db97d97fab05175e823
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 122869629a43aa3885a942a63b76536eac52fbe0c83a311921feee498987b99e591d9c42c496c2129ec718c37e0c2b753eff562a4a707375ea49375c5038ec73
|
7
|
+
data.tar.gz: cfd3126d2d94102ca27c28f36d5543c39c0629a7717b2c13a35d4588e487bb8103471661b6dbf418839ed8c19392a235aa259f2dd3a382d72c603d08aa6ce384
|
@@ -0,0 +1,19 @@
|
|
1
|
+
version: 2.1
|
2
|
+
|
3
|
+
orbs:
|
4
|
+
ruby: circleci/ruby@1.4.0
|
5
|
+
|
6
|
+
jobs:
|
7
|
+
build:
|
8
|
+
docker:
|
9
|
+
- image: cimg/ruby:3.0.1
|
10
|
+
steps:
|
11
|
+
- checkout
|
12
|
+
- ruby/install-deps
|
13
|
+
- ruby/rspec-test
|
14
|
+
|
15
|
+
workflows:
|
16
|
+
version: 2
|
17
|
+
build_and_test:
|
18
|
+
jobs:
|
19
|
+
- build
|
data/dejunk.gemspec
CHANGED
@@ -6,6 +6,7 @@ require 'dejunk/version'
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
7
|
spec.name = "dejunk"
|
8
8
|
spec.version = Dejunk::VERSION
|
9
|
+
spec.required_ruby_version = '>= 2.3'
|
9
10
|
spec.authors = ["David Judd"]
|
10
11
|
spec.email = ["david@academia.edu"]
|
11
12
|
|
@@ -19,7 +20,7 @@ Gem::Specification.new do |spec|
|
|
19
20
|
|
20
21
|
spec.add_dependency 'activesupport'
|
21
22
|
|
22
|
-
spec.add_development_dependency "bundler", "~>
|
23
|
-
spec.add_development_dependency "rake", "~>
|
23
|
+
spec.add_development_dependency "bundler", "~> 2.0"
|
24
|
+
spec.add_development_dependency "rake", "~> 12.3.3"
|
24
25
|
spec.add_development_dependency "rspec"
|
25
26
|
end
|
data/lib/dejunk/version.rb
CHANGED
data/lib/dejunk.rb
CHANGED
@@ -146,7 +146,7 @@ module Dejunk
|
|
146
146
|
def normalize_for_comparison(string)
|
147
147
|
string.
|
148
148
|
mb_chars.
|
149
|
-
|
149
|
+
unicode_normalize(:nfkd).
|
150
150
|
gsub(/\p{Mn}+/, ''.freeze).
|
151
151
|
gsub(/[^[:alnum:]]+/, ''.freeze).
|
152
152
|
downcase
|
@@ -229,9 +229,6 @@ module Dejunk
|
|
229
229
|
def mashing_probability(bigram)
|
230
230
|
if (f = mashing_bigram_frequencies[bigram])
|
231
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
232
|
else
|
236
233
|
# An arbitrary (non-ASCII) bigram with mashing is slightly more probable than with legit strings
|
237
234
|
1e-6
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: dejunk
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- David Judd
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-06-01 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|
@@ -30,28 +30,28 @@ dependencies:
|
|
30
30
|
requirements:
|
31
31
|
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '2.0'
|
34
34
|
type: :development
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '
|
40
|
+
version: '2.0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: rake
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
45
|
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version:
|
47
|
+
version: 12.3.3
|
48
48
|
type: :development
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
52
|
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version:
|
54
|
+
version: 12.3.3
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: rspec
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
@@ -73,6 +73,7 @@ executables: []
|
|
73
73
|
extensions: []
|
74
74
|
extra_rdoc_files: []
|
75
75
|
files:
|
76
|
+
- ".circleci/config.yml"
|
76
77
|
- ".gitignore"
|
77
78
|
- ".rspec"
|
78
79
|
- ".travis.yml"
|
@@ -82,7 +83,6 @@ files:
|
|
82
83
|
- Rakefile
|
83
84
|
- bin/console
|
84
85
|
- bin/setup
|
85
|
-
- circle.yml
|
86
86
|
- dejunk.gemspec
|
87
87
|
- lib/dejunk.rb
|
88
88
|
- lib/dejunk/version.rb
|
@@ -98,14 +98,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
98
98
|
requirements:
|
99
99
|
- - ">="
|
100
100
|
- !ruby/object:Gem::Version
|
101
|
-
version: '
|
101
|
+
version: '2.3'
|
102
102
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
103
103
|
requirements:
|
104
104
|
- - ">="
|
105
105
|
- !ruby/object:Gem::Version
|
106
106
|
version: '0'
|
107
107
|
requirements: []
|
108
|
-
rubygems_version: 3.
|
108
|
+
rubygems_version: 3.2.33
|
109
109
|
signing_key:
|
110
110
|
specification_version: 4
|
111
111
|
summary: Detect keyboard mashing and other junk in your data.
|