character_set 1.3.0 → 1.6.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitattributes +1 -1
- data/.github/workflows/gouteur.yml +20 -0
- data/.github/workflows/lint.yml +29 -0
- data/.github/workflows/tests.yml +26 -0
- data/.gitignore +1 -0
- data/.gouteur.yml +2 -0
- data/.rubocop.yml +17 -0
- data/BENCHMARK.md +35 -31
- data/CHANGELOG.md +50 -1
- data/Gemfile +14 -0
- data/README.md +35 -9
- data/Rakefile +6 -3
- data/benchmarks/delete_in.rb +5 -1
- data/benchmarks/keep_in.rb +5 -1
- data/benchmarks/shared.rb +5 -1
- data/character_set.gemspec +6 -9
- data/ext/character_set/character_set.c +61 -93
- data/ext/character_set/unicode_casefold_table.h +44 -1
- data/lib/character_set/character.rb +1 -1
- data/lib/character_set/core_ext/regexp_ext.rb +1 -1
- data/lib/character_set/core_ext/string_ext.rb +2 -2
- data/lib/character_set/expression_converter.rb +25 -24
- data/lib/character_set/parser.rb +1 -1
- data/lib/character_set/predefined_sets/assigned.cps +51 -40
- data/lib/character_set/predefined_sets/emoji.cps +12 -11
- data/lib/character_set/predefined_sets.rb +11 -0
- data/lib/character_set/ruby_fallback/character_set_methods.rb +5 -6
- data/lib/character_set/ruby_fallback/set_methods.rb +23 -15
- data/lib/character_set/ruby_fallback.rb +5 -1
- data/lib/character_set/set_method_adapters.rb +4 -3
- data/lib/character_set/shared_methods.rb +24 -10
- data/lib/character_set/version.rb +1 -1
- data/lib/character_set/writer.rb +98 -27
- metadata +14 -122
- data/.travis.yml +0 -9
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e216e6c199ac9443cda9180a9e35d5ed92b50b45c12e7f64f45d74ecd2cf08d6
|
4
|
+
data.tar.gz: 5f3634d426dc33875d6c197ce75466544d97808b1e8b1858ac56d93422b226e8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: d24cfaa40b6e4e472e1f76cc8b6f7f3f1282e6830c0cbf76c4810c0f6f365c7419a19816d0b741cee99eb428dae03fc1d60eecab7d1ba6d210015f0cf2d5ee14
|
7
|
+
data.tar.gz: 2bd7ea63b286e106358293b1428a687374d0cd2cdc985b2da5b5cf1f45c6c541cb0ddde5b06477243cf4011065cfac7fa6bb8a521fb144a750c90039d268f03b
|
data/.gitattributes
CHANGED
@@ -0,0 +1,20 @@
|
|
1
|
+
name: gouteur
|
2
|
+
|
3
|
+
on: [push, pull_request]
|
4
|
+
|
5
|
+
jobs:
|
6
|
+
build:
|
7
|
+
runs-on: ubuntu-latest
|
8
|
+
|
9
|
+
steps:
|
10
|
+
- uses: actions/checkout@v2
|
11
|
+
- name: Set up Ruby
|
12
|
+
uses: ruby/setup-ruby@v1
|
13
|
+
with:
|
14
|
+
ruby-version: 2.7
|
15
|
+
- name: Prepare
|
16
|
+
run: |
|
17
|
+
bundle install --jobs 4
|
18
|
+
bundle exec rake compile
|
19
|
+
- name: Test
|
20
|
+
run: bundle exec gouteur
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# based on https://github.com/rails/rails/blob/4a78dcb/.github/workflows/rubocop.yml
|
2
|
+
|
3
|
+
name: rubocop linting
|
4
|
+
|
5
|
+
on: [push, pull_request]
|
6
|
+
|
7
|
+
jobs:
|
8
|
+
build:
|
9
|
+
runs-on: ubuntu-latest
|
10
|
+
|
11
|
+
steps:
|
12
|
+
- uses: actions/checkout@v2
|
13
|
+
- name: Set up Ruby
|
14
|
+
uses: ruby/setup-ruby@v1
|
15
|
+
with:
|
16
|
+
ruby-version: 2.7
|
17
|
+
- name: Cache gems
|
18
|
+
uses: actions/cache@v1
|
19
|
+
with:
|
20
|
+
path: vendor/bundle
|
21
|
+
key: ${{ runner.os }}-rubocop-${{ hashFiles('**/Gemfile.lock') }}
|
22
|
+
restore-keys: |
|
23
|
+
${{ runner.os }}-rubocop-
|
24
|
+
- name: Install gems
|
25
|
+
run: |
|
26
|
+
bundle config path vendor/bundle
|
27
|
+
bundle install --jobs 4 --retry 3
|
28
|
+
- name: Run rubocop
|
29
|
+
run: bundle exec rubocop --lint
|
@@ -0,0 +1,26 @@
|
|
1
|
+
name: tests
|
2
|
+
|
3
|
+
on:
|
4
|
+
push:
|
5
|
+
pull_request:
|
6
|
+
schedule:
|
7
|
+
- cron: '11 11 14 * *' # at 11:11 am on the 14th of every month
|
8
|
+
|
9
|
+
jobs:
|
10
|
+
build:
|
11
|
+
runs-on: ubuntu-latest
|
12
|
+
|
13
|
+
strategy:
|
14
|
+
matrix:
|
15
|
+
ruby: [ '2.2', '2.7', '3.0', '3.1', 'ruby-head', 'jruby-head' ]
|
16
|
+
|
17
|
+
steps:
|
18
|
+
- uses: actions/checkout@v2
|
19
|
+
- name: Set up Ruby ${{ matrix.ruby }}
|
20
|
+
uses: ruby/setup-ruby@v1
|
21
|
+
with:
|
22
|
+
ruby-version: ${{ matrix.ruby }}
|
23
|
+
- name: Install dependencies
|
24
|
+
run: bundle install --jobs 4
|
25
|
+
- name: Test with Rake
|
26
|
+
run: bundle exec rake
|
data/.gitignore
CHANGED
data/.gouteur.yml
ADDED
data/.rubocop.yml
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
AllCops:
|
2
|
+
Exclude:
|
3
|
+
- '**/doc/*'
|
4
|
+
- '**/pkg/*'
|
5
|
+
- '**/spec/ruby-spec/**/*'
|
6
|
+
- '**/vendor/**/*' # vendored dependencies
|
7
|
+
NewCops: enable
|
8
|
+
RubyInterpreters:
|
9
|
+
- ruby
|
10
|
+
- rake
|
11
|
+
TargetRubyVersion: 2.5 # really 2.1, but 2.5 is lowest supported by rubocop
|
12
|
+
|
13
|
+
Lint/AmbiguousOperatorPrecedence:
|
14
|
+
Enabled: false
|
15
|
+
|
16
|
+
Lint/AmbiguousRegexpLiteral:
|
17
|
+
Enabled: false
|
data/BENCHMARK.md
CHANGED
@@ -1,86 +1,90 @@
|
|
1
|
-
Results of `rake:benchmark` on ruby 2.
|
1
|
+
Results of `rake:benchmark` on ruby 3.2.0dev (2022-02-14T14:35:54Z master 26187a8520) [arm64-darwin21]
|
2
2
|
|
3
3
|
```
|
4
4
|
Counting non-letters
|
5
5
|
|
6
|
-
CharacterSet#count_in:
|
7
|
-
String#count:
|
6
|
+
CharacterSet#count_in: 14794607.9 i/s
|
7
|
+
String#count: 3875939.3 i/s - 3.82x slower
|
8
8
|
```
|
9
9
|
```
|
10
10
|
Detecting non-whitespace
|
11
11
|
|
12
|
-
CharacterSet#cover?:
|
13
|
-
Regexp#match?:
|
12
|
+
CharacterSet#cover?: 17448329.0 i/s
|
13
|
+
Regexp#match?: 13089358.1 i/s - 1.33x slower
|
14
14
|
```
|
15
15
|
```
|
16
16
|
Detecting non-letters
|
17
17
|
|
18
|
-
CharacterSet#cover?:
|
19
|
-
Regexp#match?:
|
18
|
+
CharacterSet#cover?: 17565596.9 i/s
|
19
|
+
Regexp#match?: 7951108.0 i/s - 2.21x slower
|
20
20
|
```
|
21
21
|
```
|
22
|
-
Removing whitespace
|
22
|
+
Removing ASCII whitespace
|
23
23
|
|
24
|
-
CharacterSet#delete_in:
|
25
|
-
|
24
|
+
CharacterSet#delete_in: 6306078.2 i/s
|
25
|
+
String#tr: 4734401.0 i/s - 1.33x slower
|
26
|
+
String#gsub: 211631.8 i/s - 29.80x slower
|
26
27
|
```
|
27
28
|
```
|
28
29
|
Removing whitespace, emoji and umlauts
|
29
30
|
|
30
|
-
CharacterSet#delete_in:
|
31
|
-
|
31
|
+
CharacterSet#delete_in: 5984149.6 i/s
|
32
|
+
String#tr: 363643.1 i/s - 16.46x slower
|
33
|
+
String#gsub: 317201.7 i/s - 18.87x slower
|
32
34
|
```
|
33
35
|
```
|
34
36
|
Removing non-whitespace
|
35
37
|
|
36
|
-
CharacterSet#keep_in:
|
37
|
-
String#gsub:
|
38
|
+
CharacterSet#keep_in: 7650925.6 i/s
|
39
|
+
String#gsub: 207374.6 i/s - 36.89x slower
|
40
|
+
String#tr: 12.3 i/s - 619745.60x slower
|
38
41
|
```
|
39
42
|
```
|
40
|
-
|
43
|
+
Keeping only emoji
|
41
44
|
|
42
|
-
CharacterSet#keep_in:
|
43
|
-
String#gsub:
|
45
|
+
CharacterSet#keep_in: 7272940.1 i/s
|
46
|
+
String#gsub: 177993.8 i/s - 40.86x slower
|
47
|
+
String#tr: 12.3 i/s - 590222.71x slower
|
44
48
|
```
|
45
49
|
```
|
46
50
|
Extracting emoji to an Array
|
47
51
|
|
48
|
-
CharacterSet#scan:
|
49
|
-
String#scan:
|
52
|
+
CharacterSet#scan: 2978285.0 i/s
|
53
|
+
String#scan: 865793.8 i/s - 3.44x slower
|
50
54
|
```
|
51
55
|
```
|
52
56
|
Detecting whitespace
|
53
57
|
|
54
|
-
CharacterSet#used_by?:
|
55
|
-
Regexp#match?:
|
58
|
+
CharacterSet#used_by?: 17292338.4 i/s
|
59
|
+
Regexp#match?: 11705563.9 i/s - 1.48x slower
|
56
60
|
```
|
57
61
|
```
|
58
62
|
Detecting emoji in a large string
|
59
63
|
|
60
|
-
CharacterSet#used_by?:
|
61
|
-
Regexp#match?:
|
64
|
+
CharacterSet#used_by?: 340444.1 i/s
|
65
|
+
Regexp#match?: 180549.8 i/s - 1.89x slower
|
62
66
|
```
|
63
67
|
```
|
64
68
|
Adding entries
|
65
69
|
|
66
|
-
CharacterSet#add:
|
67
|
-
SortedSet#add:
|
70
|
+
CharacterSet#add: 4951781.4 i/s
|
71
|
+
SortedSet#add: 1019637.9 i/s - 4.86x slower
|
68
72
|
```
|
69
73
|
```
|
70
74
|
Removing entries
|
71
75
|
|
72
|
-
CharacterSet#delete:
|
73
|
-
SortedSet#delete:
|
76
|
+
CharacterSet#delete: 5006337.6 i/s
|
77
|
+
SortedSet#delete: 3922752.2 i/s - same-ish
|
74
78
|
```
|
75
79
|
```
|
76
80
|
Merging entries
|
77
81
|
|
78
|
-
CharacterSet#merge:
|
79
|
-
SortedSet#merge:
|
82
|
+
CharacterSet#merge: 661.8 i/s
|
83
|
+
SortedSet#merge: 3.9 i/s - 167.82x slower
|
80
84
|
```
|
81
85
|
```
|
82
86
|
Getting the min and max
|
83
87
|
|
84
|
-
CharacterSet#minmax:
|
85
|
-
SortedSet#minmax:
|
88
|
+
CharacterSet#minmax: 1212462.2 i/s
|
89
|
+
SortedSet#minmax: 844.4 i/s - 1435.93x slower
|
86
90
|
```
|
data/CHANGELOG.md
CHANGED
@@ -4,7 +4,56 @@ All notable changes to this project will be documented in this file.
|
|
4
4
|
The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
|
5
5
|
and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
|
6
6
|
|
7
|
-
##
|
7
|
+
## [1.6.0] - 2022-02-16
|
8
|
+
|
9
|
+
### Added
|
10
|
+
|
11
|
+
- `::of` now supports both `String` and `Regexp` arguments
|
12
|
+
|
13
|
+
### Fixed
|
14
|
+
|
15
|
+
- fixed segfault during `String` manipulation on Ruby 3.2.0-dev
|
16
|
+
- improved performance for `String` manipulation
|
17
|
+
- allow usage in Ractors
|
18
|
+
- predefined sets must be pre-initialized for this, though
|
19
|
+
- e.g. `CharacterSet.ascii`, `keep_character_set(:ascii)` etc.
|
20
|
+
- call them once in the main Ractor to trigger initialization
|
21
|
+
|
22
|
+
## [1.5.0] - 2021-12-05
|
23
|
+
|
24
|
+
### Added
|
25
|
+
|
26
|
+
- new codepoints for `::assigned` and `::emoji` predefined sets, as in Ruby 3.1.0
|
27
|
+
- latest unicode case-folding data (for `#case_insensitive`)
|
28
|
+
- support for passing any Enumerable to `#disjoint?`, `#intersect?`
|
29
|
+
- this matches recent broadening of these methods in `ruby/set`
|
30
|
+
- new instance method `#secure_token` (see README)
|
31
|
+
- class method `::of` now accepts more than one `String`
|
32
|
+
- `CharacterSet::ExpressionConverter` can now build output of any Set-like class
|
33
|
+
|
34
|
+
### Fixed
|
35
|
+
|
36
|
+
- `CharacterSet::Pure::of_expression` now returns a `CharacterSet::Pure`
|
37
|
+
- it used to return a regular `CharacterSet`
|
38
|
+
|
39
|
+
## [1.4.1] - 2020-01-10
|
40
|
+
|
41
|
+
### Fixed
|
42
|
+
- multiple fixes for Ruby 3
|
43
|
+
- fixed segfault for some `String` manipulation cases
|
44
|
+
- added `sorted_set` as dependency, so `CharacterSet::Pure` (non-C fallback) works
|
45
|
+
- fixed error when parsing a `Regexp` with an empty intersection (e.g. `/[a&&]/`)
|
46
|
+
|
47
|
+
## [1.4.0] - 2019-06-07
|
48
|
+
|
49
|
+
### Added
|
50
|
+
- `#to_s_with_surrogate_ranges` / `Writer::write_surrogate_ranges`
|
51
|
+
- allows for much shorter astral plane representations e.g. in JavaScript
|
52
|
+
- thanks to https://github.com/singpolyma for the suggestion and groundwork (#1)
|
53
|
+
- improved performance for `#to_s` / `Writer` by avoiding bugged `Range#minmax`
|
54
|
+
|
55
|
+
### Fixed
|
56
|
+
- '/' is now escaped by default when stringifying so as to work with //-regexp syntax
|
8
57
|
|
9
58
|
## [1.3.0] - 2019-04-26
|
10
59
|
|
data/Gemfile
CHANGED
@@ -4,3 +4,17 @@ git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
|
|
4
4
|
|
5
5
|
# Specify your gem's dependencies in character_set.gemspec
|
6
6
|
gemspec
|
7
|
+
|
8
|
+
gem 'benchmark-ips', '~> 2.7'
|
9
|
+
gem 'get_process_mem', '~> 0.2.3'
|
10
|
+
gem 'rake', '~> 13.0'
|
11
|
+
gem 'rake-compiler', '~> 1.1'
|
12
|
+
gem 'range_compressor', '~> 1.0'
|
13
|
+
gem 'regexp_parser', '~> 2.1'
|
14
|
+
gem 'regexp_property_values', '~> 1.0'
|
15
|
+
gem 'rspec', '~> 3.8'
|
16
|
+
if RUBY_VERSION.to_f >= 2.7
|
17
|
+
gem 'codecov', '~> 0.2.12'
|
18
|
+
gem 'gouteur', '~> 1.0.0'
|
19
|
+
gem 'rubocop', '~> 1.8'
|
20
|
+
end
|
data/README.md
CHANGED
@@ -1,18 +1,21 @@
|
|
1
1
|
# CharacterSet
|
2
2
|
|
3
3
|
[![Gem Version](https://badge.fury.io/rb/character_set.svg)](http://badge.fury.io/rb/character_set)
|
4
|
-
[![Build Status](https://
|
4
|
+
[![Build Status](https://github.com/jaynetics/character_set/workflows/tests/badge.svg)](https://github.com/jaynetics/character_set/actions)
|
5
|
+
[![Build Status](https://github.com/jaynetics/character_set/workflows/gouteur/badge.svg)](https://github.com/jaynetics/character_set/actions)
|
5
6
|
[![codecov](https://codecov.io/gh/jaynetics/character_set/branch/master/graph/badge.svg)](https://codecov.io/gh/jaynetics/character_set)
|
6
7
|
|
7
|
-
This is a C-extended Ruby gem to work with sets of Unicode codepoints.
|
8
|
+
This is a C-extended Ruby gem to work with sets of Unicode codepoints.
|
8
9
|
|
9
|
-
It
|
10
|
+
It can [read](#parseinitialize) and [write](#write) sets of codepoints in various formats and it implements the stdlib `Set` interface for them.
|
11
|
+
|
12
|
+
It also offers a [way of scrubbing and scanning characters in Strings](#interact-with-strings) that is more semantic and consistently offers better performance than `Regexp` and `String` methods from the stdlib for this (see [benchmarks](./BENCHMARK.md)).
|
10
13
|
|
11
14
|
Many parts can be used independently, e.g.:
|
12
15
|
- `CharacterSet::Character`
|
16
|
+
- `CharacterSet::ExpressionConverter`
|
13
17
|
- `CharacterSet::Parser`
|
14
18
|
- `CharacterSet::Writer`
|
15
|
-
- [`RangeCompressor`](https://github.com/jaynetics/range_compressor)
|
16
19
|
|
17
20
|
## Usage
|
18
21
|
|
@@ -40,9 +43,10 @@ CharacterSet.parse('[a-c]')
|
|
40
43
|
CharacterSet.parse('\U00000061-\U00000063')
|
41
44
|
```
|
42
45
|
|
43
|
-
If the gems [`regexp_parser`](https://github.com/ammar/regexp_parser) and [`regexp_property_values`](https://github.com/jaynetics/regexp_property_values) are installed,
|
46
|
+
If the gems [`regexp_parser`](https://github.com/ammar/regexp_parser) and [`regexp_property_values`](https://github.com/jaynetics/regexp_property_values) are installed, `Regexp` and unicode property names can also be read. Regexp intersections, negations, and set nesting are covered, but the `i`-flag is ignored; call `#case_insensitive` on the result if needed.
|
44
47
|
|
45
48
|
```ruby
|
49
|
+
CharacterSet.of(/./) # => #<CharacterSet (size: 1112064)>
|
46
50
|
CharacterSet.of_property('Thai') # => #<CharacterSet (size: 86)>
|
47
51
|
|
48
52
|
require 'character_set/core_ext/regexp_ext'
|
@@ -143,6 +147,7 @@ CharacterSet['1', 'A'].case_insensitive # => CharacterSet['1', 'A', 'a']
|
|
143
147
|
```
|
144
148
|
|
145
149
|
### Write
|
150
|
+
|
146
151
|
```ruby
|
147
152
|
set = CharacterSet['a', 'b', 'c', 'j', '-']
|
148
153
|
|
@@ -167,11 +172,32 @@ set.to_s(escape_all: true) { |c| "<#{c.hex}>" } # => "<61>-<63><258><1F929>"
|
|
167
172
|
# disable abbreviation (grouping of codepoints in ranges)
|
168
173
|
set.to_s(abbreviate: false) # => "abc\u0258\u{1F929}"
|
169
174
|
|
170
|
-
#
|
171
|
-
|
175
|
+
# astral members require some trickery if we want to target environments
|
176
|
+
# that are based on UTF-16 or "UCS-2 with surrogates", such as JavaScript.
|
177
|
+
set = CharacterSet['a', 'b', '🤩', '🤪', '🤫']
|
178
|
+
|
179
|
+
# Use #to_s_with_surrogate_ranges e.g. for JavaScript:
|
180
|
+
set.to_s_with_surrogate_ranges
|
181
|
+
# => '(?:[ab]|\uD83E[\uDD29-\uDD2B])'
|
182
|
+
|
183
|
+
# Or use #to_s_with_surrogate_alternation if such surrogate set pairs
|
184
|
+
# don't work in your target environment:
|
185
|
+
set.to_s_with_surrogate_alternation
|
186
|
+
# => '(?:[ab]|\uD83E\uDD29|\uD83E\uDD2A|\uD83E\uDD2B)'
|
187
|
+
```
|
188
|
+
|
189
|
+
### Other features
|
190
|
+
|
191
|
+
#### Secure tokens
|
192
|
+
|
193
|
+
Generate secure random strings of characters from a set:
|
194
|
+
|
195
|
+
```ruby
|
196
|
+
CharacterSet.new('a'..'z').secure_token(8) # => "ugwpujmt"
|
197
|
+
CharacterSet.crypt.secure_token # => "8.1w7aBT737/pMfcMoO4y2y8/=0xtmo:"
|
172
198
|
```
|
173
199
|
|
174
|
-
|
200
|
+
#### Unicode planes
|
175
201
|
|
176
202
|
There are some methods to check for planes and to handle ASCII, [BMP](https://en.wikipedia.org/wiki/Plane_%28Unicode%29#Basic_Multilingual_Plane) and astral parts:
|
177
203
|
```Ruby
|
@@ -188,6 +214,6 @@ CharacterSet['a', 'ü', '🤩'].member_in_plane?(7) # => false
|
|
188
214
|
CharacterSet::Character.new('a').plane # => 0
|
189
215
|
```
|
190
216
|
|
191
|
-
|
217
|
+
## Contributions
|
192
218
|
|
193
219
|
Feel free to send suggestions, point out issues, or submit pull requests.
|
data/Rakefile
CHANGED
@@ -126,7 +126,7 @@ task :sync_predefined_sets do
|
|
126
126
|
%w[assigned emoji whitespace].each do |prop|
|
127
127
|
require 'regexp_property_values'
|
128
128
|
ranges = RegexpPropertyValues[prop].matched_ranges
|
129
|
-
str = ranges.map { |r| r.
|
129
|
+
str = ranges.map { |r| "#{r.min.to_s(16)},#{r.max.to_s(16)}\n" }.join.upcase
|
130
130
|
File.write("./lib/character_set/predefined_sets/#{prop}.cps", str, mode: 'w')
|
131
131
|
end
|
132
132
|
end
|
@@ -147,8 +147,11 @@ namespace :benchmark do
|
|
147
147
|
f.puts "Results of `rake:benchmark` on #{RUBY_DESCRIPTION}", ''
|
148
148
|
|
149
149
|
$store_comparison_results.each do |caption, result|
|
150
|
-
f.puts '```',
|
151
|
-
|
150
|
+
f.puts '```',
|
151
|
+
caption,
|
152
|
+
'',
|
153
|
+
result.strip.gsub(/ \(±[^)]+\) /, '').gsub(/(same-ish).*$/, '\1').lines[1..-1],
|
154
|
+
'```'
|
152
155
|
end
|
153
156
|
end
|
154
157
|
end
|
data/benchmarks/delete_in.rb
CHANGED
@@ -2,24 +2,28 @@ require_relative './shared'
|
|
2
2
|
|
3
3
|
str = 'Lorem ipsum et dolorem'
|
4
4
|
rx = /\s/
|
5
|
+
trt = "\t\n\v\f\r\s"
|
5
6
|
cs = CharacterSet.whitespace
|
6
7
|
|
7
8
|
benchmark(
|
8
|
-
caption: 'Removing whitespace',
|
9
|
+
caption: 'Removing ASCII whitespace',
|
9
10
|
cases: {
|
10
11
|
'String#gsub' => -> { str.gsub(rx, '') },
|
12
|
+
'String#tr' => -> { str.tr(trt, '') },
|
11
13
|
'CharacterSet#delete_in' => -> { cs.delete_in(str) },
|
12
14
|
}
|
13
15
|
)
|
14
16
|
|
15
17
|
str = 'Lörem ipsüm ⛷ et dölörem'
|
16
18
|
rx = /[\s\p{emoji}äüö]/
|
19
|
+
trt = "\t\n\v\f\r\s😀-🙏äüö"
|
17
20
|
cs = CharacterSet.whitespace + CharacterSet.emoji + CharacterSet['ä', 'ö', 'ü']
|
18
21
|
|
19
22
|
benchmark(
|
20
23
|
caption: 'Removing whitespace, emoji and umlauts',
|
21
24
|
cases: {
|
22
25
|
'String#gsub' => -> { str.gsub(rx, '') },
|
26
|
+
'String#tr' => -> { str.tr(trt, '') },
|
23
27
|
'CharacterSet#delete_in' => -> { cs.delete_in(str) },
|
24
28
|
}
|
25
29
|
)
|
data/benchmarks/keep_in.rb
CHANGED
@@ -2,24 +2,28 @@ require_relative './shared'
|
|
2
2
|
|
3
3
|
str = 'Lorem ipsum et dolorem'
|
4
4
|
rx = /\S/
|
5
|
+
trt = "\u{0080}-\u{10FFFF}" # approximation
|
5
6
|
cs = CharacterSet.whitespace
|
6
7
|
|
7
8
|
benchmark(
|
8
9
|
caption: 'Removing non-whitespace',
|
9
10
|
cases: {
|
10
11
|
'String#gsub' => -> { str.gsub(rx, '') },
|
12
|
+
'String#tr' => -> { str.tr(trt, '') },
|
11
13
|
'CharacterSet#keep_in' => -> { cs.keep_in(str) },
|
12
14
|
}
|
13
15
|
)
|
14
16
|
|
15
17
|
str = 'Lorem ipsum ⛷ et dolorem'
|
16
18
|
rx = /\p{^emoji}/
|
19
|
+
trt = "\u0000-\u{1F599}\u{1F650}-\u{10FFFF}"
|
17
20
|
cs = CharacterSet.emoji
|
18
21
|
|
19
22
|
benchmark(
|
20
|
-
caption: '
|
23
|
+
caption: 'Keeping only emoji',
|
21
24
|
cases: {
|
22
25
|
'String#gsub' => -> { str.gsub(rx, '') },
|
26
|
+
'String#tr' => -> { str.tr(trt, '') },
|
23
27
|
'CharacterSet#keep_in' => -> { cs.keep_in(str) },
|
24
28
|
}
|
25
29
|
)
|
data/benchmarks/shared.rb
CHANGED
@@ -3,7 +3,11 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
3
3
|
|
4
4
|
require 'benchmark/ips'
|
5
5
|
require 'character_set'
|
6
|
-
|
6
|
+
if RUBY_VERSION.to_f >= 3.0 && !RUBY_PLATFORM[/java/i]
|
7
|
+
require 'sorted_set'
|
8
|
+
else
|
9
|
+
require 'set'
|
10
|
+
end
|
7
11
|
|
8
12
|
def benchmark(caption: nil, cases: {})
|
9
13
|
puts caption
|
data/character_set.gemspec
CHANGED
@@ -22,13 +22,10 @@ Gem::Specification.new do |s|
|
|
22
22
|
|
23
23
|
s.required_ruby_version = '>= 2.1.0'
|
24
24
|
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
s.add_development_dependency 'regexp_parser', '~> 1.3'
|
32
|
-
s.add_development_dependency 'regexp_property_values', '~> 0.3.5'
|
33
|
-
s.add_development_dependency 'rspec', '~> 3.8'
|
25
|
+
# SortedSet, needed for RubyFallback, was moved to a gem in Ruby 3.
|
26
|
+
# This dependency is only used if the C extension is unavailable.
|
27
|
+
# JRuby has it in the stdlib.
|
28
|
+
if RUBY_VERSION.to_f >= 3.0 && !RUBY_PLATFORM[/java/i]
|
29
|
+
s.add_dependency 'sorted_set', '~> 1.0'
|
30
|
+
end
|
34
31
|
end
|