dejunk 0.2.0 → 0.3.0

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: c544a625c931feb25e33682bb9a2c7ad243b57acaab1d1643d8ad410f7cbec69
4
- data.tar.gz: dbae0776455be08aa508c2699bdc9c4041d23fc7d627a8fb99a985a05f5c16b7
3
+ metadata.gz: 1c27554d9b8b375cd041796a404ea48e28c6c9ce2a772f27af21e83f78117cd8
4
+ data.tar.gz: 5464e9f63e8b3729f155280bbb167baf1810549b3f05e8d9343f6f8c16c0d420
5
5
  SHA512:
6
- metadata.gz: 48728d90252fa4b29bb38d165a0920325c1d4bd13a54f70be637fbd36b572df49458446bf4caaaefb5e7289ca1a5ec990b46d917734f10be8e2783edaae7f4ff
7
- data.tar.gz: ca738d822697a164101f3e832e94a95cdf98e59180930bb0bd48c467e7999f0ad47da014b13e59ba36ce0d50326f17201eeb1b3a9357ab2469643ae0fd8fc5c4
6
+ metadata.gz: 5c425a21416fe2532e665cb9b10b8fbf081134ab6705f4b60b2487104b043e6120aa0cab2bc77832b231c631795b2bd8a5124184c96d861b7d28f3d7abf1336e
7
+ data.tar.gz: 37cedff6a300bab1c2dc75fbdae68473b44c2fbf688f78f0811194de812bf47e8e2d278b4f7cd279ec6af1cf17f40e0f05dc83c2b299f3a2b7cdaeba13195d6e
@@ -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
 
@@ -146,7 +146,7 @@ module Dejunk
146
146
  def normalize_for_comparison(string)
147
147
  string.
148
148
  mb_chars.
149
- normalize(:kd).
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
@@ -1,3 +1,3 @@
1
1
  module Dejunk
2
- VERSION = "0.2.0"
2
+ VERSION = "0.3.0"
3
3
  end
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: 0.2.0
4
+ version: 0.3.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - David Judd
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2019-04-09 00:00:00.000000000 Z
11
+ date: 2020-08-07 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: activesupport
@@ -96,16 +96,16 @@ require_paths:
96
96
  - lib
97
97
  required_ruby_version: !ruby/object:Gem::Requirement
98
98
  requirements:
99
- - - ">="
99
+ - - "~>"
100
100
  - !ruby/object:Gem::Version
101
- version: '0'
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: 3.0.1
108
+ rubygems_version: 3.0.3
109
109
  signing_key:
110
110
  specification_version: 4
111
111
  summary: Detect keyboard mashing and other junk in your data.