LittleWeasel 3.0.4 → 5.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.github/workflows/codeql-analysis.yml +72 -0
- data/.gitignore +19 -17
- data/.reek.yml +17 -0
- data/.rspec +4 -2
- data/.rubocop.yml +187 -0
- data/.ruby-version +1 -1
- data/.yardopts +2 -0
- data/CHANGELOG.md +21 -1
- data/Gemfile +3 -1
- data/Gemfile.lock +114 -0
- data/Jenkinsfile +20 -0
- data/LittleWeasel.gemspec +31 -18
- data/README.md +408 -42
- data/Rakefile +296 -3
- data/lib/LittleWeasel/block_results.rb +81 -0
- data/lib/LittleWeasel/configure.rb +98 -0
- data/lib/LittleWeasel/dictionary.rb +125 -0
- data/lib/LittleWeasel/dictionary_key.rb +48 -0
- data/lib/LittleWeasel/dictionary_manager.rb +91 -0
- data/lib/LittleWeasel/errors/dictionary_file_already_loaded_error.rb +9 -0
- data/lib/LittleWeasel/errors/dictionary_file_empty_error.rb +8 -0
- data/lib/LittleWeasel/errors/dictionary_file_not_found_error.rb +8 -0
- data/lib/LittleWeasel/errors/dictionary_file_too_large_error.rb +16 -0
- data/lib/LittleWeasel/errors/language_required_error.rb +8 -0
- data/lib/LittleWeasel/errors/must_override_error.rb +8 -0
- data/lib/LittleWeasel/filters/en_us/currency_filter.rb +19 -0
- data/lib/LittleWeasel/filters/en_us/numeric_filter.rb +19 -0
- data/lib/LittleWeasel/filters/en_us/single_character_word_filter.rb +21 -0
- data/lib/LittleWeasel/filters/word_filter.rb +59 -0
- data/lib/LittleWeasel/filters/word_filter_managable.rb +80 -0
- data/lib/LittleWeasel/filters/word_filter_validatable.rb +31 -0
- data/lib/LittleWeasel/filters/word_filterable.rb +19 -0
- data/lib/LittleWeasel/filters/word_filters_validatable.rb +29 -0
- data/lib/LittleWeasel/metadata/dictionary_metadata.rb +145 -0
- data/lib/LittleWeasel/metadata/invalid_words_metadata.rb +134 -0
- data/lib/LittleWeasel/metadata/invalid_words_service_results.rb +45 -0
- data/lib/LittleWeasel/metadata/metadata_observable_validatable.rb +22 -0
- data/lib/LittleWeasel/metadata/metadata_observerable.rb +90 -0
- data/lib/LittleWeasel/metadata/metadatable.rb +134 -0
- data/lib/LittleWeasel/modules/class_name_to_symbol.rb +26 -0
- data/lib/LittleWeasel/modules/configurable.rb +26 -0
- data/lib/LittleWeasel/modules/deep_dup.rb +11 -0
- data/lib/LittleWeasel/modules/dictionary_cache_keys.rb +34 -0
- data/lib/LittleWeasel/modules/dictionary_cache_servicable.rb +26 -0
- data/lib/LittleWeasel/modules/dictionary_cache_validatable.rb +18 -0
- data/lib/LittleWeasel/modules/dictionary_creator_servicable.rb +27 -0
- data/lib/LittleWeasel/modules/dictionary_file_loader.rb +67 -0
- data/lib/LittleWeasel/modules/dictionary_key_validatable.rb +17 -0
- data/lib/LittleWeasel/modules/dictionary_keyable.rb +24 -0
- data/lib/LittleWeasel/modules/dictionary_metadata_servicable.rb +29 -0
- data/lib/LittleWeasel/modules/dictionary_metadata_validatable.rb +15 -0
- data/lib/LittleWeasel/modules/dictionary_source_validatable.rb +15 -0
- data/lib/LittleWeasel/modules/dictionary_sourceable.rb +86 -0
- data/lib/LittleWeasel/modules/dictionary_validatable.rb +18 -0
- data/lib/LittleWeasel/modules/language.rb +24 -0
- data/lib/LittleWeasel/modules/language_validatable.rb +14 -0
- data/lib/LittleWeasel/modules/locale.rb +23 -0
- data/lib/LittleWeasel/modules/order_validatable.rb +16 -0
- data/lib/LittleWeasel/modules/orderable.rb +17 -0
- data/lib/LittleWeasel/modules/region.rb +24 -0
- data/lib/LittleWeasel/modules/region_validatable.rb +14 -0
- data/lib/LittleWeasel/modules/tag_validatable.rb +14 -0
- data/lib/LittleWeasel/modules/taggable.rb +31 -0
- data/lib/LittleWeasel/modules/word_results_validatable.rb +28 -0
- data/lib/LittleWeasel/preprocessors/en_us/capitalize_preprocessor.rb +22 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_word.rb +29 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_word_validatable.rb +56 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_words.rb +59 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_words_validatable.rb +28 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessable.rb +19 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessor.rb +123 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessor_managable.rb +114 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessor_validatable.rb +40 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessors_validatable.rb +24 -0
- data/lib/LittleWeasel/services/dictionary_cache_service.rb +211 -0
- data/lib/LittleWeasel/services/dictionary_creator_service.rb +94 -0
- data/lib/LittleWeasel/services/dictionary_file_loader_service.rb +37 -0
- data/lib/LittleWeasel/services/dictionary_killer_service.rb +35 -0
- data/lib/LittleWeasel/services/dictionary_metadata_service.rb +116 -0
- data/lib/LittleWeasel/services/invalid_words_service.rb +59 -0
- data/lib/LittleWeasel/version.rb +3 -1
- data/lib/LittleWeasel/word_results.rb +146 -0
- data/lib/LittleWeasel.rb +72 -186
- data/spec/factories/dictionary.rb +43 -0
- data/spec/factories/dictionary_cache_service.rb +95 -0
- data/spec/factories/dictionary_creator_service.rb +16 -0
- data/spec/factories/dictionary_file_loader_service.rb +13 -0
- data/spec/factories/dictionary_hash.rb +39 -0
- data/spec/factories/dictionary_key.rb +14 -0
- data/spec/factories/dictionary_killer_service.rb +14 -0
- data/spec/factories/dictionary_manager.rb +10 -0
- data/spec/factories/dictionary_metadata.rb +16 -0
- data/spec/factories/dictionary_metadata_service.rb +16 -0
- data/spec/factories/numeric_filter.rb +12 -0
- data/spec/factories/preprocessed_word.rb +16 -0
- data/spec/factories/preprocessed_words.rb +41 -0
- data/spec/factories/single_character_word_filter.rb +12 -0
- data/spec/factories/word_results.rb +16 -0
- data/spec/lib/LittleWeasel/block_results_spec.rb +248 -0
- data/spec/lib/LittleWeasel/configure_spec.rb +74 -0
- data/spec/lib/LittleWeasel/dictionary_key_spec.rb +118 -0
- data/spec/lib/LittleWeasel/dictionary_manager_spec.rb +166 -0
- data/spec/lib/LittleWeasel/dictionary_spec.rb +289 -0
- data/spec/lib/LittleWeasel/filters/en_us/currency_filter_spec.rb +80 -0
- data/spec/lib/LittleWeasel/filters/en_us/numeric_filter_spec.rb +66 -0
- data/spec/lib/LittleWeasel/filters/en_us/single_character_word_filter_spec.rb +58 -0
- data/spec/lib/LittleWeasel/filters/word_filter_managable_spec.rb +180 -0
- data/spec/lib/LittleWeasel/filters/word_filter_spec.rb +151 -0
- data/spec/lib/LittleWeasel/filters/word_filter_validatable_spec.rb +94 -0
- data/spec/lib/LittleWeasel/filters/word_filters_validatable_spec.rb +48 -0
- data/spec/lib/LittleWeasel/integraton_tests/dictionary_integration_spec.rb +201 -0
- data/spec/lib/LittleWeasel/metadata/dictionary_creator_servicable_spec.rb +54 -0
- data/spec/lib/LittleWeasel/metadata/dictionary_metadata_spec.rb +209 -0
- data/spec/lib/LittleWeasel/metadata/invalid_words_metadata_spec.rb +155 -0
- data/spec/lib/LittleWeasel/metadata/metadata_observerable_spec.rb +31 -0
- data/spec/lib/LittleWeasel/metadata/metadatable_spec.rb +35 -0
- data/spec/lib/LittleWeasel/modules/class_name_to_symbol_spec.rb +21 -0
- data/spec/lib/LittleWeasel/modules/dictionary_file_loader_spec.rb +125 -0
- data/spec/lib/LittleWeasel/modules/dictionary_sourceable_spec.rb +81 -0
- data/spec/lib/LittleWeasel/modules/language_spec.rb +112 -0
- data/spec/lib/LittleWeasel/modules/locale_spec.rb +95 -0
- data/spec/lib/LittleWeasel/modules/region_spec.rb +112 -0
- data/spec/lib/LittleWeasel/preprocessors/en_us/capitalize_preprocessor_spec.rb +34 -0
- data/spec/lib/LittleWeasel/preprocessors/preprocessed_word_spec.rb +105 -0
- data/spec/lib/LittleWeasel/preprocessors/preprocessed_word_validatable_spec.rb +143 -0
- data/spec/lib/LittleWeasel/preprocessors/preprocessed_words_spec.rb +77 -0
- data/spec/lib/LittleWeasel/preprocessors/preprocessed_words_validatable_spec.rb +58 -0
- data/spec/lib/LittleWeasel/preprocessors/word_preprocessor_managable_spec.rb +242 -0
- data/spec/lib/LittleWeasel/preprocessors/word_preprocessor_spec.rb +218 -0
- data/spec/lib/LittleWeasel/preprocessors/word_preprocessor_validatable_spec.rb +109 -0
- data/spec/lib/LittleWeasel/preprocessors/word_preprocessors_validatable_spec.rb +49 -0
- data/spec/lib/LittleWeasel/services/dictionary_cache_service_spec.rb +444 -0
- data/spec/lib/LittleWeasel/services/dictionary_creator_service_spec.rb +119 -0
- data/spec/lib/LittleWeasel/services/dictionary_file_loader_service_spec.rb +71 -0
- data/spec/lib/LittleWeasel/services/dictionary_metadata_service_spec.rb +279 -0
- data/spec/lib/LittleWeasel/word_results_spec.rb +275 -0
- data/spec/lib/LittleWeasel/workflow/workflow_spec.rb +20 -0
- data/spec/spec_helper.rb +117 -6
- data/spec/support/factory_bot.rb +15 -0
- data/spec/support/file_helpers.rb +46 -0
- data/spec/support/files/empty-dictionary.txt +0 -0
- data/{lib/dictionary → spec/support/files/en-US-big.txt} +262156 -31488
- data/spec/support/files/en-US-tagged.txt +26 -0
- data/spec/support/files/en-US.txt +26 -0
- data/spec/support/files/en.txt +26 -0
- data/spec/support/files/es-ES.txt +27 -0
- data/spec/support/files/es.txt +27 -0
- data/spec/support/general_helpers.rb +68 -0
- data/spec/support/shared_contexts.rb +107 -0
- data/spec/support/shared_examples.rb +105 -0
- metadata +418 -70
- data/spec/checker/checker_spec.rb +0 -286
data/Rakefile
CHANGED
@@ -1,13 +1,306 @@
|
|
1
|
-
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'active_support/core_ext/object/try.rb'
|
4
|
+
require 'active_support/inflector'
|
5
|
+
require 'benchmark/ips'
|
6
|
+
require 'bundler/gem_tasks'
|
7
|
+
require 'pry'
|
8
|
+
|
9
|
+
require_relative 'lib/LittleWeasel'
|
10
|
+
require_relative 'spec/support/file_helpers'
|
11
|
+
require_relative 'spec/support/general_helpers'
|
12
|
+
|
13
|
+
DictionaryResultsHelpers = Support::GeneralHelpers::DictionaryResultsHelpers
|
14
|
+
|
15
|
+
def file_from(dictionary_key)
|
16
|
+
Support::FileHelpers.dictionary_path_for(file_name: dictionary_key.key)
|
17
|
+
end
|
2
18
|
|
3
19
|
begin
|
4
20
|
require 'rspec/core/rake_task'
|
5
21
|
RSpec::Core::RakeTask.new(:spec)
|
6
22
|
rescue LoadError => e
|
7
|
-
task
|
23
|
+
task 'spec' do
|
8
24
|
puts "RSpec not loaded - make sure it's installed and you're using bundle exec"
|
9
25
|
exit 1
|
10
26
|
end
|
11
27
|
end
|
12
28
|
|
13
|
-
|
29
|
+
#
|
30
|
+
# Tasks related to the #word_results API
|
31
|
+
|
32
|
+
namespace 'word_results' do
|
33
|
+
# Creates a dictionary from a file on disk
|
34
|
+
task :basic do
|
35
|
+
LittleWeasel.configure do |config|
|
36
|
+
# TODO: Configure as needed here.
|
37
|
+
end
|
38
|
+
|
39
|
+
# Create a Dictionary Manager.
|
40
|
+
dictionary_manager = LittleWeasel::DictionaryManager.new
|
41
|
+
|
42
|
+
# Create our unique key for the dictionary.
|
43
|
+
en_us_key = LittleWeasel::DictionaryKey.new(language: :en, region: :us)
|
44
|
+
|
45
|
+
file = Support::FileHelpers.dictionary_path_for file_name: en_us_key.key
|
46
|
+
|
47
|
+
# Create a dictionary of names from memory.
|
48
|
+
en_us_names_dictionary = dictionary_manager.create_dictionary_from_file(
|
49
|
+
dictionary_key: en_us_key,
|
50
|
+
file: file)
|
51
|
+
|
52
|
+
# Get some word results...
|
53
|
+
|
54
|
+
# Get results for a word we know exists.
|
55
|
+
word = 'apple'
|
56
|
+
word_results = en_us_names_dictionary.word_results word
|
57
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "found (#{word} is in the dictionary)"
|
58
|
+
|
59
|
+
# Get results for a word we know DOES NOT exist.
|
60
|
+
word = 'dapple'
|
61
|
+
word_results = en_us_names_dictionary.word_results word
|
62
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "not found (#{word} is not in the dictionary)"
|
63
|
+
rescue StandardError => e
|
64
|
+
task 'word_results:basic' do
|
65
|
+
puts "LittleWeasel task word_results:basic not loaded: #{e.message}"
|
66
|
+
exit 1
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
# Creates a dictionary of names from memory
|
71
|
+
task :from_memory do
|
72
|
+
LittleWeasel.configure do |config|
|
73
|
+
# TODO: Configure as needed here.
|
74
|
+
end
|
75
|
+
|
76
|
+
# Create a Dictionary Manager.
|
77
|
+
dictionary_manager = LittleWeasel::DictionaryManager.new
|
78
|
+
|
79
|
+
# Create our unique key for the dictionary.
|
80
|
+
en_us_names_key = LittleWeasel::DictionaryKey.new(language: :en, region: :us, tag: :names)
|
81
|
+
|
82
|
+
# Create a dictionary of names from memory.
|
83
|
+
en_us_names_dictionary = dictionary_manager.create_dictionary_from_memory(
|
84
|
+
dictionary_key: en_us_names_key, dictionary_words: %w(Abel Bartholomew Cain Deborah Elijah))
|
85
|
+
|
86
|
+
# Get some word results...
|
87
|
+
|
88
|
+
# Get results for a name we know exists.
|
89
|
+
word = 'Abel'
|
90
|
+
word_results = en_us_names_dictionary.word_results word
|
91
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "found (#{word} is in the dictionary)"
|
92
|
+
|
93
|
+
# Get results for a name we know DOES NOT exist.
|
94
|
+
word = 'Henry'
|
95
|
+
word_results = en_us_names_dictionary.word_results word
|
96
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "not found (#{word} is not in the dictionary)"
|
97
|
+
rescue StandardError => e
|
98
|
+
task 'word_results:from_memory' do
|
99
|
+
puts "LittleWeasel task word_results:from_memory not loaded: #{e.message}"
|
100
|
+
exit 1
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
# Shows application of word filters and word preprocessors.
|
105
|
+
task :advanced do
|
106
|
+
LittleWeasel.configure do |config|
|
107
|
+
# TODO: Configure as needed here.
|
108
|
+
end
|
109
|
+
|
110
|
+
# Create a Dictionary Manager.
|
111
|
+
dictionary_manager = LittleWeasel::DictionaryManager.new
|
112
|
+
|
113
|
+
# Create our unique key for the dictionary.
|
114
|
+
en_us_names_key = LittleWeasel::DictionaryKey.new(language: :en, region: :us, tag: :names)
|
115
|
+
|
116
|
+
# Create a Henry word filter.
|
117
|
+
class HenryFilter < LittleWeasel::Filters::WordFilter
|
118
|
+
class << self
|
119
|
+
def filter_match?(word)
|
120
|
+
word== 'Henry'
|
121
|
+
end
|
122
|
+
end
|
123
|
+
end
|
124
|
+
word_filters = [HenryFilter.new]
|
125
|
+
|
126
|
+
# Add a word preprocessor.
|
127
|
+
word_preprocessors = [LittleWeasel::Preprocessors::EnUs::CapitalizePreprocessor.new]
|
128
|
+
|
129
|
+
# Create a dictionary of names from memory.
|
130
|
+
en_us_names_dictionary = dictionary_manager.create_dictionary_from_memory(
|
131
|
+
dictionary_key: en_us_names_key,
|
132
|
+
dictionary_words: %w(Abel Bartholomew Cain Deborah Elijah),
|
133
|
+
word_filters: word_filters,
|
134
|
+
word_preprocessors: word_preprocessors)
|
135
|
+
|
136
|
+
puts '# Turning off our word filters and word preprocessors to start...'
|
137
|
+
puts
|
138
|
+
|
139
|
+
en_us_names_dictionary.filters_on = false
|
140
|
+
en_us_names_dictionary.preprocessors_on = false
|
141
|
+
|
142
|
+
# Get results for a name we know DOES NOT exist.
|
143
|
+
word = 'Henry'
|
144
|
+
word_results = en_us_names_dictionary.word_results word
|
145
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "not found, #success? == false, word_valid? == false (#{word} is not in the dictionary)"
|
146
|
+
|
147
|
+
puts '# Turning word filters on...'
|
148
|
+
puts
|
149
|
+
|
150
|
+
en_us_names_dictionary.filters_on = true
|
151
|
+
|
152
|
+
# Get results for Henry again - it should be found due to the filter.
|
153
|
+
word = 'Henry'
|
154
|
+
word_results = en_us_names_dictionary.word_results word
|
155
|
+
DictionaryResultsHelpers.print_word_results word, word_results, '#success? == true due to the HenryFilter'
|
156
|
+
|
157
|
+
# Get results for a name we know DOES NOT exist.
|
158
|
+
word = 'henry'
|
159
|
+
word_results = en_us_names_dictionary.word_results word
|
160
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "not found, #success? == false (#{word} is not in the dictionary and henry is lower case, no filter match)"
|
161
|
+
|
162
|
+
puts '# Turning preprocessors on so that henry is converted to Henry '
|
163
|
+
puts "# and consequently, the filter will match..."
|
164
|
+
puts
|
165
|
+
|
166
|
+
en_us_names_dictionary.preprocessors_on = true
|
167
|
+
|
168
|
+
word = 'henry'
|
169
|
+
word_results = en_us_names_dictionary.word_results word
|
170
|
+
DictionaryResultsHelpers.print_word_results word, word_results, "#success? == true, #filter_match? == true (#{word} is not in the dictionary but the word preprocessor and word filter work together to get a filter match and consider the name valid)"
|
171
|
+
rescue StandardError => e
|
172
|
+
task 'word_results:advanced' do
|
173
|
+
puts "LittleWeasel task word_results:advanced not loaded: #{e.message}"
|
174
|
+
exit 1
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
task :word_filters do
|
179
|
+
LittleWeasel.configure do |config|
|
180
|
+
# TODO: Configure as needed here.
|
181
|
+
end
|
182
|
+
dictionary_manager = LittleWeasel::DictionaryManager.new
|
183
|
+
dictionary_key = LittleWeasel::DictionaryKey.new(language: :en, region: :us)
|
184
|
+
file = Support::FileHelpers.dictionary_path_for file_name: dictionary_key.key
|
185
|
+
word_filters = [
|
186
|
+
LittleWeasel::Filters::EnUs::NumericFilter.new,
|
187
|
+
LittleWeasel::Filters::EnUs::CurrencyFilter.new,
|
188
|
+
LittleWeasel::Filters::EnUs::SingleCharacterWordFilter.new
|
189
|
+
]
|
190
|
+
word_preprocessors = nil
|
191
|
+
dictionary_words = Support::FileHelpers.dictionary_words_for dictionary_file_path: file
|
192
|
+
dictionary = dictionary_manager.create_dictionary_from_memory(dictionary_key: dictionary_key, dictionary_words: dictionary_words, word_filters: word_filters, word_preprocessors: word_preprocessors)
|
193
|
+
dictionary_words << 'A'.dup
|
194
|
+
dictionary_words << 'I'.dup
|
195
|
+
dictionary_words << '1000'.dup
|
196
|
+
dictionary_words << '1,000'.dup
|
197
|
+
dictionary_words << '10,000.00'.dup
|
198
|
+
dictionary_words << '+100.00'.dup
|
199
|
+
dictionary_words << '-200,000.00'.dup
|
200
|
+
dictionary_words << '$100,000'.dup
|
201
|
+
dictionary_words << '+$100,000,000.10'.dup
|
202
|
+
dictionary_words << '-$999,000,000.10'.dup
|
203
|
+
dictionary_words.each do |word|
|
204
|
+
word.strip!
|
205
|
+
word_results = dictionary.word_results word
|
206
|
+
DictionaryResultsHelpers.print_word_results word, word_results
|
207
|
+
end
|
208
|
+
rescue StandardError => e
|
209
|
+
task 'word_results:word_filters' do
|
210
|
+
puts "LittleWeasel task word_results:word_filters not loaded: #{e.message}"
|
211
|
+
exit 1
|
212
|
+
end
|
213
|
+
end
|
214
|
+
end
|
215
|
+
|
216
|
+
#
|
217
|
+
# Tasks related to the #block_results API
|
218
|
+
|
219
|
+
namespace 'block_results' do
|
220
|
+
task :basic do
|
221
|
+
LittleWeasel.configure do |config|
|
222
|
+
# TODO: Configure as needed here.
|
223
|
+
end
|
224
|
+
|
225
|
+
# Create a Dictionary Manager.
|
226
|
+
dictionary_manager = LittleWeasel::DictionaryManager.new
|
227
|
+
|
228
|
+
# Create our unique key for the dictionary.
|
229
|
+
en_us_key = LittleWeasel::DictionaryKey.new(language: :en, region: :us, tag: :big)
|
230
|
+
|
231
|
+
# Create a dictionary from a file on disk. The below assumes the
|
232
|
+
# dictionary file name matches the dictionary key (e.g. en-US-big).
|
233
|
+
en_us_dictionary = dictionary_manager.create_dictionary_from_file(
|
234
|
+
dictionary_key: en_us_key, file: file_from(en_us_key))
|
235
|
+
|
236
|
+
word_block = "This is a word-block of 8 words and 2 numbers."
|
237
|
+
|
238
|
+
# Add a word filter so that numbers are considered valid.
|
239
|
+
en_us_dictionary.add_filters word_filters: [
|
240
|
+
LittleWeasel::Filters::EnUs::NumericFilter.new
|
241
|
+
]
|
242
|
+
|
243
|
+
block_results = en_us_dictionary.block_results word_block
|
244
|
+
|
245
|
+
# Returns a LittleWeasel::BlockResults object.
|
246
|
+
DictionaryResultsHelpers.print_block_results word_block, block_results
|
247
|
+
rescue StandardError => e
|
248
|
+
task 'block_results:basic' do
|
249
|
+
puts "LittleWeasel task block_results:basic not loaded: #{e.message}"
|
250
|
+
exit 1
|
251
|
+
end
|
252
|
+
end
|
253
|
+
end
|
254
|
+
|
255
|
+
namespace :bm do
|
256
|
+
task :hash do
|
257
|
+
STRING_LOCALE = { 'en-US' => 'en-us' }
|
258
|
+
SYMBOL_LOCALE = { 'en-US' => :enUS }
|
259
|
+
|
260
|
+
puts 'String variable vs. normal String.'
|
261
|
+
Benchmark.ips do |x|
|
262
|
+
string_variable = 'string_variable'
|
263
|
+
x.report('string variable') { STRING_LOCALE[string_variable] }
|
264
|
+
x.report('normal') { STRING_LOCALE['en-US'] }
|
265
|
+
end
|
266
|
+
|
267
|
+
puts 'String#freeze vs. normal String.'
|
268
|
+
Benchmark.ips do |x|
|
269
|
+
x.report('freeze') { STRING_LOCALE['en-US'.freeze] }
|
270
|
+
x.report('normal') { STRING_LOCALE['en-US'] }
|
271
|
+
end
|
272
|
+
|
273
|
+
puts 'String vs Symbol'
|
274
|
+
Benchmark.ips do |x|
|
275
|
+
x.report('string') { STRING_LOCALE['en-US'] }
|
276
|
+
x.report('symbol') { SYMBOL_LOCALE[:enUS] }
|
277
|
+
end
|
278
|
+
|
279
|
+
puts 'String#freeze vs. Symbol'
|
280
|
+
Benchmark.ips do |x|
|
281
|
+
x.report('string') { STRING_LOCALE['en-US'.freeze] }
|
282
|
+
x.report('symbol') { SYMBOL_LOCALE[:enUS] }
|
283
|
+
end
|
284
|
+
rescue StandardError => e
|
285
|
+
task 'hash' do
|
286
|
+
puts "LittleWeasel task bm:hash not loaded: #{e.message}"
|
287
|
+
exit 1
|
288
|
+
end
|
289
|
+
end
|
290
|
+
|
291
|
+
task :dictionary_key do
|
292
|
+
puts 'DictionaryKey test'
|
293
|
+
Benchmark.ips do |x|
|
294
|
+
x.report('DictionaryKey') do
|
295
|
+
DictionaryKey.key(language: :en, region: :us, tag: :tag)
|
296
|
+
end
|
297
|
+
end
|
298
|
+
rescue StandardError => e
|
299
|
+
task 'locale' do
|
300
|
+
puts "LittleWeasel task bm:dictionary_key not loaded: #{e.message}"
|
301
|
+
exit 1
|
302
|
+
end
|
303
|
+
end
|
304
|
+
end
|
305
|
+
|
306
|
+
task default: :spec
|
@@ -0,0 +1,81 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'active_support/core_ext/module/delegation'
|
4
|
+
require_relative 'word_results'
|
5
|
+
|
6
|
+
module LittleWeasel
|
7
|
+
# This class represents the results of gathering information about a word
|
8
|
+
# block (group of words).
|
9
|
+
class BlockResults
|
10
|
+
# :reek:Attribute - Ignored, it doesn't make sense to create a formal setter method.
|
11
|
+
attr_reader :original_word_block, :word_results
|
12
|
+
|
13
|
+
def initialize(original_word_block:)
|
14
|
+
self.original_word_block = original_word_block
|
15
|
+
self.word_results = []
|
16
|
+
end
|
17
|
+
|
18
|
+
def <<(word_result)
|
19
|
+
unless word_result.is_a? WordResults
|
20
|
+
raise ArgumentError, "Argument word_result is not a WordResults object: #{word_result.class}"
|
21
|
+
end
|
22
|
+
|
23
|
+
word_results << word_result
|
24
|
+
end
|
25
|
+
|
26
|
+
# Calls #success? on all WordResults objects. Returns true if all
|
27
|
+
# WordResults return true; false is returned otherwise.
|
28
|
+
def success?
|
29
|
+
return false unless word_results.present?
|
30
|
+
|
31
|
+
word_results.all?(&:success?)
|
32
|
+
end
|
33
|
+
|
34
|
+
# Returns true if all WordResults object words are valid (#word_valid?);
|
35
|
+
# false otherwise.
|
36
|
+
def words_valid?
|
37
|
+
return false unless word_results.present?
|
38
|
+
|
39
|
+
word_results.all?(&:word_valid?)
|
40
|
+
end
|
41
|
+
|
42
|
+
# Returns true if all WordResults object words have filter matches (#filters_match?);
|
43
|
+
# false otherwise.
|
44
|
+
def filters_match?
|
45
|
+
return false unless word_results.present?
|
46
|
+
|
47
|
+
word_results.all?(&:filter_match?)
|
48
|
+
end
|
49
|
+
|
50
|
+
# Returns true if all WordResults object words have been preprocessed (#preprocessed_words?);
|
51
|
+
# false otherwise.
|
52
|
+
def preprocessed_words?
|
53
|
+
return false unless word_results.present?
|
54
|
+
|
55
|
+
word_results.all?(&:preprocessed_word?)
|
56
|
+
end
|
57
|
+
|
58
|
+
# Returns an Array of the results of calling
|
59
|
+
# #preprocessed_word_or_original_word on all WordResults objects.
|
60
|
+
|
61
|
+
# Calls #preprocessed_word_or_original_word on all WordResults objects.
|
62
|
+
# An Array of the results is returned.
|
63
|
+
def preprocessed_words_or_original_words
|
64
|
+
return [] unless word_results.present?
|
65
|
+
|
66
|
+
word_results.map(&:preprocessed_word_or_original_word)
|
67
|
+
end
|
68
|
+
|
69
|
+
# Returns true if all WordResults object words have been cached (#words_cached?);
|
70
|
+
# false otherwise.
|
71
|
+
def words_cached?
|
72
|
+
return false unless word_results.present?
|
73
|
+
|
74
|
+
word_results.all?(&:word_cached?)
|
75
|
+
end
|
76
|
+
|
77
|
+
private
|
78
|
+
|
79
|
+
attr_writer :original_word_block, :word_results
|
80
|
+
end
|
81
|
+
end
|
@@ -0,0 +1,98 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# This is the configuration for LittleWeasel.
|
4
|
+
module LittleWeasel
|
5
|
+
class << self
|
6
|
+
attr_reader :configuration
|
7
|
+
|
8
|
+
# Returns the application configuration object.
|
9
|
+
#
|
10
|
+
# @return [Configuration] the application Configuration object.
|
11
|
+
def configure
|
12
|
+
self.configuration ||= Configuration.new
|
13
|
+
yield(configuration)
|
14
|
+
end
|
15
|
+
|
16
|
+
private
|
17
|
+
|
18
|
+
attr_writer :configuration
|
19
|
+
end
|
20
|
+
|
21
|
+
# This class encapsulates the configuration properties for this gem and
|
22
|
+
# provides methods and attributes that allow for management of the same.
|
23
|
+
#
|
24
|
+
# attr_reader :max_dictionary_file_megabytes, :max_invalid_words_bytesize, :metadata_observers
|
25
|
+
class Configuration
|
26
|
+
attr_reader :max_dictionary_file_megabytes,
|
27
|
+
:max_invalid_words_bytesize, :metadata_observers, :word_block_regex
|
28
|
+
|
29
|
+
# The constructor; calls {#reset}.
|
30
|
+
def initialize
|
31
|
+
reset
|
32
|
+
end
|
33
|
+
|
34
|
+
# Resets the configuration settings to their default values.
|
35
|
+
#
|
36
|
+
# @return [void]
|
37
|
+
def reset
|
38
|
+
@max_dictionary_file_megabytes = 5
|
39
|
+
@max_invalid_words_bytesize = 25_000
|
40
|
+
@metadata_observers = [
|
41
|
+
LittleWeasel::Metadata::InvalidWordsMetadata
|
42
|
+
]
|
43
|
+
# TODO: Is this the correct regex to use, or is there something better?
|
44
|
+
# @word_block_regex = /\s+(?=(?:[^"]*"[^"]*")*[^"]*$)/
|
45
|
+
# @word_block_regex = /(?:(?:[\-A-Za-z0-9]|\d(?!\d|\b))+(?:'[\-A-Za-z0-9]+)?)/
|
46
|
+
# @word_block_regex = /(?:(?:[\-a-z0-9]|\d(?!\d|\b))+(?:'[\-a-z0-9]+)?)/i
|
47
|
+
@word_block_regex = /[[[:word:]]'-]+/
|
48
|
+
end
|
49
|
+
|
50
|
+
# Returns the maximum consumable dictionary size in bytes. Dictionaries
|
51
|
+
# larger than {#max_dictionary_file_bytes} will raise an error.
|
52
|
+
#
|
53
|
+
# The default is 5 megabytes.
|
54
|
+
#
|
55
|
+
# @return [Integer] the maximum number of bytes for a dictionary.
|
56
|
+
def max_dictionary_file_bytes
|
57
|
+
@max_dictionary_file_megabytes * 1_000_000
|
58
|
+
end
|
59
|
+
|
60
|
+
# If {#max_invalid_words_bytesize} is > 0, true will be returned; false
|
61
|
+
# otherwise.
|
62
|
+
#
|
63
|
+
# @return [true, false] based on {#max_invalid_words_bytesize}.
|
64
|
+
def max_invalid_words_bytesize?
|
65
|
+
max_invalid_words_bytesize.positive?
|
66
|
+
end
|
67
|
+
|
68
|
+
# rubocop: disable Style/TrivialAccessors
|
69
|
+
def max_dictionary_file_megabytes=(value)
|
70
|
+
@max_dictionary_file_megabytes = value
|
71
|
+
end
|
72
|
+
|
73
|
+
# Sets the maximum cache size (in bytes) for invalid words. If
|
74
|
+
# less than or equal to 0, invalid words will NOT be cached.
|
75
|
+
#
|
76
|
+
# If greater than 0, invalid words will be cached up to and including
|
77
|
+
# {#max_invalid_words_bytesize} bytes.
|
78
|
+
#
|
79
|
+
# @see #max_invalid_words_bytesize?
|
80
|
+
def max_invalid_words_bytesize=(value)
|
81
|
+
value = 0 if value.negative?
|
82
|
+
@max_invalid_words_bytesize = value
|
83
|
+
end
|
84
|
+
|
85
|
+
def metadata_observers=(value)
|
86
|
+
raise ArgumentError, "Argument value is not an Array: #{value.class}" unless value.is_a? Array
|
87
|
+
|
88
|
+
# TODO: Limit the amount of observer classes, exploits?
|
89
|
+
|
90
|
+
@metadata_observers = value
|
91
|
+
end
|
92
|
+
|
93
|
+
def word_block_regex=(value)
|
94
|
+
@word_block_regex = value
|
95
|
+
end
|
96
|
+
# rubocop: enable Style/TrivialAccessors
|
97
|
+
end
|
98
|
+
end
|
@@ -0,0 +1,125 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'block_results'
|
4
|
+
require_relative 'filters/word_filter_managable'
|
5
|
+
require_relative 'metadata/dictionary_metadata'
|
6
|
+
require_relative 'modules/configurable'
|
7
|
+
require_relative 'modules/dictionary_cache_servicable'
|
8
|
+
require_relative 'modules/dictionary_keyable'
|
9
|
+
require_relative 'modules/dictionary_metadata_servicable'
|
10
|
+
require_relative 'preprocessors/word_preprocessor_managable'
|
11
|
+
require_relative 'word_results'
|
12
|
+
|
13
|
+
module LittleWeasel
|
14
|
+
class Dictionary
|
15
|
+
include Filters::WordFilterManagable
|
16
|
+
include Modules::Configurable
|
17
|
+
include Modules::DictionaryCacheServicable
|
18
|
+
include Modules::DictionaryKeyable
|
19
|
+
include Modules::DictionaryMetadataServicable
|
20
|
+
include Preprocessors::WordPreprocessorManagable
|
21
|
+
|
22
|
+
attr_reader :dictionary_metadata_object, :dictionary_words
|
23
|
+
|
24
|
+
def initialize(dictionary_key:, dictionary_words:, dictionary_cache:,
|
25
|
+
dictionary_metadata:, word_filters: nil, word_preprocessors: nil)
|
26
|
+
validate_dictionary_key dictionary_key: dictionary_key
|
27
|
+
self.dictionary_key = dictionary_key
|
28
|
+
|
29
|
+
validate_dictionary_cache dictionary_cache: dictionary_cache
|
30
|
+
self.dictionary_cache = dictionary_cache
|
31
|
+
|
32
|
+
validate_dictionary_metadata dictionary_metadata: dictionary_metadata
|
33
|
+
self.dictionary_metadata = dictionary_metadata
|
34
|
+
|
35
|
+
unless dictionary_words.is_a?(Array)
|
36
|
+
raise ArgumentError,
|
37
|
+
"Argument dictionary_words is not an Array: #{dictionary_words.class}"
|
38
|
+
end
|
39
|
+
|
40
|
+
# Set up the dictionary metadata object and observers
|
41
|
+
self.dictionary_words = self.class.to_hash(dictionary_words: dictionary_words)
|
42
|
+
self.dictionary_metadata_object = create_dictionary_metadata
|
43
|
+
dictionary_metadata_object.add_observers
|
44
|
+
|
45
|
+
add_filters word_filters: word_filters || []
|
46
|
+
add_preprocessors word_preprocessors: word_preprocessors || []
|
47
|
+
end
|
48
|
+
|
49
|
+
class << self
|
50
|
+
def to_hash(dictionary_words:)
|
51
|
+
dictionary_words.each_with_object(Hash.new(false)) { |word, hash| hash[word] = true; }
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
def word_results(word)
|
56
|
+
# TODO: Make max word size configurable.
|
57
|
+
raise ArgumentError, "Argument word is not a String: #{word.class}" unless word.is_a?(String)
|
58
|
+
|
59
|
+
preprocessed_words = preprocess(word: word)
|
60
|
+
preprocessed_word = preprocessed_words.preprocessed_word
|
61
|
+
filters_matched = filters_matched(preprocessed_word || word)
|
62
|
+
word_results = WordResults.new(original_word: word,
|
63
|
+
filters_matched: filters_matched,
|
64
|
+
preprocessed_words: preprocessed_words,
|
65
|
+
word_cached: dictionary_words.include?(preprocessed_word || word),
|
66
|
+
word_valid: dictionary_words[preprocessed_word || word] || false)
|
67
|
+
|
68
|
+
dictionary_metadata_object.notify(action: :word_search,
|
69
|
+
params: { word_results: word_results })
|
70
|
+
|
71
|
+
word_results
|
72
|
+
end
|
73
|
+
|
74
|
+
def block_results(word_block)
|
75
|
+
# TODO: Make max word_block size configurable.
|
76
|
+
raise ArgumentError, "Argument word_block is not a String: #{word_block.class}" unless word_block.is_a?(String)
|
77
|
+
raise ArgumentError, "Argument word_block is empty: #{word_block.class}" unless word_block.present?
|
78
|
+
|
79
|
+
BlockResults.new(original_word_block: word_block).tap do |block_results|
|
80
|
+
word_block.scan(config.word_block_regex)&.map do |word|
|
81
|
+
block_results << word_results(word)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
85
|
+
|
86
|
+
# This method returns true if this dictionary object is detached from the
|
87
|
+
# dictionary cache; this can happen if the dictionary object is unloaded
|
88
|
+
# from the dictionary cache(DictionaryManager#unload_dictionary) or the
|
89
|
+
# dictionary is killed (DictionaryManager#kill_dictionary).
|
90
|
+
def detached?
|
91
|
+
!dictionary_cache_service.dictionary_object?
|
92
|
+
end
|
93
|
+
|
94
|
+
# This method returns a count of VALID words in the dictionary.
|
95
|
+
def count
|
96
|
+
dictionary_words.each_pair.count { |_word, valid| valid }
|
97
|
+
end
|
98
|
+
|
99
|
+
# This method returns a count of all VALID and INVALID words in
|
100
|
+
# the dictionary.
|
101
|
+
def count_all_words
|
102
|
+
dictionary_words.count
|
103
|
+
end
|
104
|
+
|
105
|
+
# This method returns a count of all INVALID words in the dictionary.
|
106
|
+
def count_invalid_words
|
107
|
+
dictionary_words.each_pair.count { |_word, valid| !valid }
|
108
|
+
end
|
109
|
+
|
110
|
+
private
|
111
|
+
|
112
|
+
attr_writer :dictionary_metadata_object, :dictionary_words
|
113
|
+
|
114
|
+
def create_dictionary_metadata
|
115
|
+
# We unconditionally attach metadata to this dictionary. DictionaryMetadata
|
116
|
+
# only attaches the metadata services that are turned "on".
|
117
|
+
Metadata::DictionaryMetadata.new(
|
118
|
+
dictionary_words: dictionary_words,
|
119
|
+
dictionary_key: dictionary_key,
|
120
|
+
dictionary_cache: dictionary_cache,
|
121
|
+
dictionary_metadata: dictionary_metadata
|
122
|
+
)
|
123
|
+
end
|
124
|
+
end
|
125
|
+
end
|
@@ -0,0 +1,48 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'modules/language_validatable'
|
4
|
+
require_relative 'modules/locale'
|
5
|
+
require_relative 'modules/region_validatable'
|
6
|
+
require_relative 'modules/taggable'
|
7
|
+
|
8
|
+
module LittleWeasel
|
9
|
+
# This class describes a unique key associated with a particular dictionary
|
10
|
+
# file. Dictionary keys are used to identify a dictionary on which an action
|
11
|
+
# should be performed.
|
12
|
+
class DictionaryKey
|
13
|
+
include Modules::LanguageValidatable
|
14
|
+
include Modules::Locale
|
15
|
+
include Modules::RegionValidatable
|
16
|
+
include Modules::Taggable
|
17
|
+
|
18
|
+
attr_reader :language, :region
|
19
|
+
|
20
|
+
def initialize(language:, region: nil, tag: nil)
|
21
|
+
validate_language language: language
|
22
|
+
self.language = normalize_language language
|
23
|
+
|
24
|
+
validate_region region: region
|
25
|
+
self.region = normalize_region region
|
26
|
+
|
27
|
+
validate_tag tag: tag
|
28
|
+
self.tag = tag
|
29
|
+
end
|
30
|
+
|
31
|
+
def key
|
32
|
+
return locale unless tagged?
|
33
|
+
|
34
|
+
"#{locale}-#{tag}"
|
35
|
+
end
|
36
|
+
alias to_s key
|
37
|
+
|
38
|
+
class << self
|
39
|
+
def key(language:, region: nil, tag: nil)
|
40
|
+
new(language: language, region: region, tag: tag).key
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
private
|
45
|
+
|
46
|
+
attr_writer :language, :region
|
47
|
+
end
|
48
|
+
end
|