LittleWeasel 3.0.4 → 4.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.gitignore +3 -0
- data/.reek.yml +17 -0
- data/.rspec +4 -2
- data/.rubocop.yml +187 -0
- data/.ruby-version +1 -1
- data/.yardopts +2 -0
- data/Gemfile +3 -1
- data/LittleWeasel.gemspec +31 -18
- data/README.md +408 -42
- data/Rakefile +296 -3
- data/lib/LittleWeasel.rb +5 -184
- 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 +85 -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 +136 -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 +20 -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 +19 -0
- data/lib/LittleWeasel/modules/dictionary_keyable.rb +24 -0
- data/lib/LittleWeasel/modules/dictionary_loader_servicable.rb +27 -0
- data/lib/LittleWeasel/modules/dictionary_metadata_servicable.rb +29 -0
- data/lib/LittleWeasel/modules/dictionary_metadata_validatable.rb +17 -0
- data/lib/LittleWeasel/modules/dictionary_sourceable.rb +26 -0
- data/lib/LittleWeasel/modules/dictionary_validatable.rb +30 -0
- data/lib/LittleWeasel/modules/language.rb +23 -0
- data/lib/LittleWeasel/modules/language_validatable.rb +16 -0
- data/lib/LittleWeasel/modules/locale.rb +40 -0
- data/lib/LittleWeasel/modules/order_validatable.rb +18 -0
- data/lib/LittleWeasel/modules/orderable.rb +17 -0
- data/lib/LittleWeasel/modules/region.rb +23 -0
- data/lib/LittleWeasel/modules/region_validatable.rb +16 -0
- data/lib/LittleWeasel/modules/tag_validatable.rb +16 -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 +28 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_word_validatable.rb +55 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_words.rb +55 -0
- data/lib/LittleWeasel/preprocessors/preprocessed_words_validatable.rb +27 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessable.rb +19 -0
- data/lib/LittleWeasel/preprocessors/word_preprocessor.rb +122 -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 +262 -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_loader_service.rb +59 -0
- data/lib/LittleWeasel/services/dictionary_metadata_service.rb +114 -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/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_loader_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 +116 -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 +44 -0
- data/spec/lib/LittleWeasel/modules/language_spec.rb +52 -0
- data/spec/lib/LittleWeasel/modules/locale_spec.rb +140 -0
- data/spec/lib/LittleWeasel/modules/region_spec.rb +52 -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 +216 -0
- data/spec/lib/LittleWeasel/preprocessors/word_preprocessor_spec.rb +175 -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_loader_service_spec.rb +50 -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 +32 -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 +108 -0
- data/spec/support/shared_examples.rb +105 -0
- metadata +408 -65
- data/spec/checker/checker_spec.rb +0 -286
@@ -0,0 +1,114 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'word_preprocessable'
|
4
|
+
require_relative 'word_preprocessor_validatable'
|
5
|
+
|
6
|
+
module LittleWeasel
|
7
|
+
module Preprocessors
|
8
|
+
# This module provides methods and functionality to manage word
|
9
|
+
# preprocessors. A "word preprocessor" is an object that manipulates a word
|
10
|
+
# before it is passed to any word filters and before it is compared against
|
11
|
+
# the dictionary for validity.
|
12
|
+
#
|
13
|
+
# When creating your own word preprocessors, here are some things you
|
14
|
+
# need to consider:
|
15
|
+
#
|
16
|
+
# Multiple word preprocessors can be applied to a given word. Word
|
17
|
+
# processors will be applied to a word in
|
18
|
+
# Preprocessors::WordPreprocessor#order order (ascending). Even though this
|
19
|
+
# is the case, it doesn't mean you should seek to apply more than one word
|
20
|
+
# preprocessor at a time. However, if you do, write and order your word
|
21
|
+
# preprocessors in such a way that each preprocessor manipulates the word
|
22
|
+
# in a complimentary rather than contridictionary way. For example,
|
23
|
+
# applying one word preprocessor that convert a word to uppercase and a
|
24
|
+
# second that converts the word to lowercase, contradict each other.
|
25
|
+
#
|
26
|
+
# Another thing you need to consider, is whether or not metadata observers
|
27
|
+
# should be notified of the preprocessed word (now that it has been
|
28
|
+
# potentially manipulated) or if they should be notified of the original
|
29
|
+
# word; this is because, the original word may not be found as a valid word
|
30
|
+
# in the dictionary, while the preprocessed word might and vise versa.
|
31
|
+
module WordPreprocessorManagable
|
32
|
+
include WordPreprocessable
|
33
|
+
include WordPreprocessorsValidatable
|
34
|
+
|
35
|
+
# Override attr_reader word_preprocessor found in WordPreprocessable
|
36
|
+
# so that we don't raise nil errors when using word_preprocessors.
|
37
|
+
def word_preprocessors
|
38
|
+
@word_preprocessors ||= []
|
39
|
+
end
|
40
|
+
|
41
|
+
def clear_preprocessors
|
42
|
+
self.word_preprocessors = []
|
43
|
+
end
|
44
|
+
|
45
|
+
# Appends word preprocessors to the #word_preprocessors Array.
|
46
|
+
#
|
47
|
+
# If Argument word_preprocessor is nil, a block must be passed to populate
|
48
|
+
# the word_preprocessors with an Array of valid word preprocessor objects.
|
49
|
+
#
|
50
|
+
# This method is used for adding/appending word preprocessors to the
|
51
|
+
# word_preprocessors Array. To replace word preprocessors, use #replace_preprocessors;
|
52
|
+
# to perform any other manipulation of the word_preprocessors Array,
|
53
|
+
# use #word_preprocessors directly.
|
54
|
+
def add_preprocessors(word_preprocessors: nil)
|
55
|
+
return if word_preprocessors.is_a?(Array) && word_preprocessors.blank?
|
56
|
+
|
57
|
+
unless word_preprocessors.present? || block_given?
|
58
|
+
raise 'A block is required if argument word_preprocessors is nil'
|
59
|
+
end
|
60
|
+
|
61
|
+
word_preprocessors ||= []
|
62
|
+
yield word_preprocessors if block_given?
|
63
|
+
|
64
|
+
concat_and_sort_word_preprocessors! word_preprocessors
|
65
|
+
end
|
66
|
+
alias append_preprocessors add_preprocessors
|
67
|
+
|
68
|
+
def replace_preprocessors(word_preprocessors:)
|
69
|
+
clear_preprocessors
|
70
|
+
add_preprocessors word_preprocessors: word_preprocessors
|
71
|
+
end
|
72
|
+
|
73
|
+
def preprocessors_on=(on)
|
74
|
+
raise ArgumentError, "Argument on is not true or false: #{on.class}" unless [true, false].include?(on)
|
75
|
+
|
76
|
+
word_preprocessors.each { |word_preprocessor| word_preprocessor.preprocessor_on = on }
|
77
|
+
end
|
78
|
+
|
79
|
+
# Returns a Preprocessors::PreprocessedWords object.
|
80
|
+
def preprocess(word:)
|
81
|
+
preprocessed_words = preprocessed_words word: word
|
82
|
+
PreprocessedWords.new(original_word: word, preprocessed_words: preprocessed_words)
|
83
|
+
end
|
84
|
+
|
85
|
+
def preprocessed_words(word:)
|
86
|
+
word_preprocessors.map do |word_preprocessor|
|
87
|
+
word_preprocessor.preprocess(word).tap do |processed_word|
|
88
|
+
word = processed_word.preprocessed_word
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|
93
|
+
# Returns the final (or last) preprocessed word in the Array of
|
94
|
+
# preprocessed words. The final preprocessed word is the word that has
|
95
|
+
# passed through all the word preprocessors.
|
96
|
+
def preprocessed_word(word:)
|
97
|
+
preprocessed_words = self.preprocessed_words word: word
|
98
|
+
preprocessed_words.max_by(&:preprocessor_order).preprocessed_word unless preprocessed_words.blank?
|
99
|
+
end
|
100
|
+
|
101
|
+
private
|
102
|
+
|
103
|
+
# This method concatinates preprocessors to #word_preprocessors,
|
104
|
+
# sorts #word_preprocessors by WordPreprocessor#order and
|
105
|
+
# returns the results.
|
106
|
+
def concat_and_sort_word_preprocessors!(preprocessors)
|
107
|
+
validate_word_preprocessors word_preprocessors: preprocessors
|
108
|
+
|
109
|
+
word_preprocessors.concat preprocessors
|
110
|
+
word_preprocessors.sort_by!(&:order)
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module LittleWeasel
|
4
|
+
module Preprocessors
|
5
|
+
# This module validates word preprocessor types.
|
6
|
+
# rubocop: disable Layout/LineLength
|
7
|
+
module WordPreprocessorValidatable
|
8
|
+
module_function
|
9
|
+
|
10
|
+
# :reek:ManualDispatch - ignored, this is duck-typing not 'simulated polymorphism'
|
11
|
+
# :reek:TooManyStatements - ignored, "too many statements" is easier to understand than arbitrarily breaking all this down into individual methods
|
12
|
+
def validate_word_preprocessor(word_preprocessor:)
|
13
|
+
# You can use your own word preprocessor types as long as they quack
|
14
|
+
# correctly; however, you are responsible for the behavior of these
|
15
|
+
# required methods/ attributes. It's probably better to follow the
|
16
|
+
# pattern of existing word preprocessor objects and inherit from
|
17
|
+
# Preprocessors::WordPreprocessor.
|
18
|
+
|
19
|
+
word_preprocessor_class = word_preprocessor.class
|
20
|
+
|
21
|
+
# class methods
|
22
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '.preprocess') unless word_preprocessor_class.respond_to?(:preprocess)
|
23
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '.preprocess?') unless word_preprocessor_class.respond_to?(:preprocess?)
|
24
|
+
|
25
|
+
# instance methods
|
26
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocess') unless word_preprocessor.respond_to?(:preprocess)
|
27
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocess?') unless word_preprocessor.respond_to?(:preprocess?)
|
28
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocessor_off?') unless word_preprocessor.respond_to?(:preprocessor_off?)
|
29
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocessor_on') unless word_preprocessor.respond_to?(:preprocessor_on)
|
30
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocessor_on=') unless word_preprocessor.respond_to?(:preprocessor_on=)
|
31
|
+
raise validation_error_message(object: word_preprocessor_class, respond_to: '#preprocessor_on?') unless word_preprocessor.respond_to?(:preprocessor_on?)
|
32
|
+
end
|
33
|
+
|
34
|
+
def validation_error_message(object:, respond_to:)
|
35
|
+
"Argument word_preprocessor: does not respond to: #{object}#{respond_to}"
|
36
|
+
end
|
37
|
+
end
|
38
|
+
# rubocop: enable Layout/LineLength
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'word_preprocessor_validatable'
|
4
|
+
|
5
|
+
module LittleWeasel
|
6
|
+
module Preprocessors
|
7
|
+
# This module provides methods to validate an Array of word preprocessor
|
8
|
+
# objects.
|
9
|
+
module WordPreprocessorsValidatable
|
10
|
+
module_function
|
11
|
+
|
12
|
+
def validate_word_preprocessors(word_preprocessors:)
|
13
|
+
return if word_preprocessors.blank?
|
14
|
+
|
15
|
+
raise ArgumentError, "Argument word_preprocessors is not an Array: #{word_preprocessors.class}" \
|
16
|
+
unless word_preprocessors.is_a? Array
|
17
|
+
|
18
|
+
word_preprocessors.each do |word_preprocessor|
|
19
|
+
WordPreprocessorValidatable.validate_word_preprocessor word_preprocessor: word_preprocessor
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,262 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative '../modules/dictionary_cache_keys'
|
4
|
+
require_relative '../modules/dictionary_cache_validatable'
|
5
|
+
require_relative '../modules/dictionary_keyable'
|
6
|
+
require_relative '../modules/dictionary_sourceable'
|
7
|
+
require_relative '../modules/dictionary_validatable'
|
8
|
+
|
9
|
+
module LittleWeasel
|
10
|
+
module Services
|
11
|
+
# This class provides methods and attributes that can be used to manage the
|
12
|
+
# dictionary cache. The "dictionary cache" is a simple Hash that provides
|
13
|
+
# access to informaiton related to dictionaries through a dictionary "key".
|
14
|
+
# A dictionary "key" is a unique key comprised of a locale and
|
15
|
+
# optional "tag" (see Modules::Taggable and DictionaryKey for more
|
16
|
+
# information). The dictionary cache also provides a way for dictionary
|
17
|
+
# objects to share dictionary information, in particular, the dictionary
|
18
|
+
# file and dictionary metadata.
|
19
|
+
class DictionaryCacheService
|
20
|
+
include Modules::DictionaryKeyable
|
21
|
+
include Modules::DictionaryCacheValidatable
|
22
|
+
include Modules::DictionaryCacheKeys
|
23
|
+
include Modules::DictionarySourceable
|
24
|
+
include Modules::DictionaryValidatable
|
25
|
+
|
26
|
+
attr_reader :dictionary_cache
|
27
|
+
|
28
|
+
# This class produces the following (example) Hash that represents the
|
29
|
+
# dictionary cache structure:
|
30
|
+
#
|
31
|
+
# @example This is an example:
|
32
|
+
#
|
33
|
+
# {
|
34
|
+
# 'dictionary_cache' =>
|
35
|
+
# {
|
36
|
+
# 'dictionary_references' =>
|
37
|
+
# {
|
38
|
+
# 'en' =>
|
39
|
+
# {
|
40
|
+
# 'dictionary_id' => 19ec7845
|
41
|
+
# },
|
42
|
+
# 'en-US' =>
|
43
|
+
# {
|
44
|
+
# 'dictionary_id' => 0987a3f2
|
45
|
+
# },
|
46
|
+
# 'en-US-temp' =>
|
47
|
+
# {
|
48
|
+
# 'dictionary_id' => 9273eac6
|
49
|
+
# }
|
50
|
+
# },
|
51
|
+
# 'dictionaries' =>
|
52
|
+
# {
|
53
|
+
# 19ec7845 =>
|
54
|
+
# {
|
55
|
+
# 'source' => '/en.txt',
|
56
|
+
# 'dictionary_object' => {}
|
57
|
+
# },
|
58
|
+
# 0987a3f2 =>
|
59
|
+
# {
|
60
|
+
# 'source' => '/en-US.txt',
|
61
|
+
# 'dictionary_object' => {}
|
62
|
+
# },
|
63
|
+
# 9273eac6 =>
|
64
|
+
# {
|
65
|
+
# 'source' => '*736ed423',
|
66
|
+
# 'dictionary_object' => {}
|
67
|
+
# }
|
68
|
+
# }
|
69
|
+
# }
|
70
|
+
# }
|
71
|
+
def initialize(dictionary_key:, dictionary_cache:)
|
72
|
+
validate_dictionary_key dictionary_key: dictionary_key
|
73
|
+
self.dictionary_key = dictionary_key
|
74
|
+
|
75
|
+
validate_dictionary_cache dictionary_cache: dictionary_cache
|
76
|
+
self.dictionary_cache = dictionary_cache
|
77
|
+
|
78
|
+
self.class.init(dictionary_cache: dictionary_cache) unless dictionary_cache[DICTIONARY_CACHE]
|
79
|
+
end
|
80
|
+
|
81
|
+
class << self
|
82
|
+
# This method resets dictionary_cache to its initialized state.
|
83
|
+
# This class method is different from the #init instance method
|
84
|
+
# in that ALL dictionary references and ALL dictionaries are
|
85
|
+
# initialized.
|
86
|
+
def init(dictionary_cache:)
|
87
|
+
Modules::DictionaryCacheKeys.initialize_dictionary_cache dictionary_cache: dictionary_cache
|
88
|
+
end
|
89
|
+
|
90
|
+
# Returns true if the dictionary cache is initialized; that
|
91
|
+
# is, if the given dictionary_cache is in the same state the
|
92
|
+
# dictionary cache would be in after .init were called.
|
93
|
+
def init?(dictionary_cache:)
|
94
|
+
initialized_dictionary_cache = init(dictionary_cache: {})
|
95
|
+
dictionary_cache.eql?(initialized_dictionary_cache)
|
96
|
+
end
|
97
|
+
|
98
|
+
# Returns the number of dictionaries currently in the cache.
|
99
|
+
def count(dictionary_cache:)
|
100
|
+
dictionary_cache.dig(self::DICTIONARY_CACHE, self::DICTIONARIES)&.keys&.count || 0
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
# This method resets the dictionary cache for the given key. This method
|
105
|
+
# is different from the .init class method in that ONLY the dictionary
|
106
|
+
# reference and dictionary specific to the given key is initialized.
|
107
|
+
def init
|
108
|
+
# TODO: Do not delete the dictionary if it is being pointed to by
|
109
|
+
# another dictionary reference.
|
110
|
+
dictionary_cache_hash = dictionary_cache[DICTIONARY_CACHE]
|
111
|
+
dictionary_cache_hash[DICTIONARIES]&.delete(dictionary_id)
|
112
|
+
dictionary_cache_hash[DICTIONARY_REFERENCES]&.delete(key)
|
113
|
+
self
|
114
|
+
end
|
115
|
+
|
116
|
+
# Returns true if the dictionary reference exists for the given key; false
|
117
|
+
# otherwise. This method is only concerned with the dictionary reference
|
118
|
+
# and has nothing to do with whether or not the associated dictionary
|
119
|
+
# is actually loaded into the dictionary cache.
|
120
|
+
def dictionary_reference?
|
121
|
+
dictionary_reference&.present? || false
|
122
|
+
end
|
123
|
+
|
124
|
+
# Returns true if a dictionaries Hash key exists for the given dictionary_id
|
125
|
+
# in the dictionary cache. This method is only concerned with the existance of
|
126
|
+
# the key and has nothing to do with whether or not file/memory sources are
|
127
|
+
# present or the presence of a dictionary object.
|
128
|
+
def dictionary?
|
129
|
+
dictionary_cache[DICTIONARY_CACHE][DICTIONARIES].key? dictionary_id
|
130
|
+
end
|
131
|
+
|
132
|
+
# Adds a dictionary source. A "dictionary source" specifies the source from which
|
133
|
+
# the dictionary ultimately obtains its words.
|
134
|
+
#
|
135
|
+
# @param source [String] the dictionary source. This can be a file path
|
136
|
+
# or a memory source indicator to signify that the dictionary was created
|
137
|
+
# dynamically from memory.
|
138
|
+
def add_dictionary_source(source:)
|
139
|
+
validate_dictionary_source_does_not_exist dictionary_cache_service: self
|
140
|
+
|
141
|
+
dictionary_id = dictionary_id_for_dictionary_source(source: source)
|
142
|
+
self.dictionary_reference = dictionary_id
|
143
|
+
# Only set the dictionary source if it doesn't already exist because settings
|
144
|
+
# the dictionary source wipes out the #dictionary_object; dictionary objects
|
145
|
+
# can have more than one dictionary reference pointing to them, and we don't
|
146
|
+
# want to blow away the #dictionary_object, metadata, or any other data
|
147
|
+
# associated with it if it already exists.
|
148
|
+
self.dictionary_source = source unless dictionary?
|
149
|
+
self
|
150
|
+
end
|
151
|
+
|
152
|
+
# Returns the dictionary id if there is a dictionary id in the dictionary
|
153
|
+
# cache associated with the given key; nil otherwise.
|
154
|
+
def dictionary_id
|
155
|
+
dictionary_cache.dig(DICTIONARY_CACHE, DICTIONARY_REFERENCES, key, DICTIONARY_ID)
|
156
|
+
end
|
157
|
+
|
158
|
+
# Returns the dictionary id if there is a dictionary id in the dictionary
|
159
|
+
# cache associated with the given key. This method raises an error if the
|
160
|
+
# dictionary id cannot be found.
|
161
|
+
def dictionary_id!
|
162
|
+
return dictionary_id if dictionary_id?
|
163
|
+
|
164
|
+
raise ArgumentError, "A dictionary id could not be found for key '#{key}'."
|
165
|
+
end
|
166
|
+
|
167
|
+
def dictionary_source!
|
168
|
+
raise ArgumentError, "A dictionary source could not be found for key '#{key}'." unless dictionary_reference?
|
169
|
+
|
170
|
+
dictionary_cache[DICTIONARY_CACHE][DICTIONARIES][dictionary_id!][SOURCE]
|
171
|
+
end
|
172
|
+
alias dictionary_file! dictionary_source!
|
173
|
+
|
174
|
+
def dictionary_source
|
175
|
+
dictionary_cache.dig(DICTIONARY_CACHE, DICTIONARIES, dictionary_id, SOURCE)
|
176
|
+
end
|
177
|
+
alias dictionary_file dictionary_source
|
178
|
+
|
179
|
+
# This method returns true if the dictionary associated with the
|
180
|
+
# given dictionary key is loaded/cached. If this is the case,
|
181
|
+
# a dictionary object is available in the dictionary cache.
|
182
|
+
def dictionary_object?
|
183
|
+
dictionary_object.present?
|
184
|
+
end
|
185
|
+
alias dictionary_exists? dictionary_object?
|
186
|
+
|
187
|
+
# Returns the dictionary object from the dictionary cache for the given
|
188
|
+
# key. This method raises an error if the dictionary is not in the cache;
|
189
|
+
# that is, if the dictionary was not previously loaded from disk or memory.
|
190
|
+
def dictionary_object!
|
191
|
+
unless dictionary_object?
|
192
|
+
raise ArgumentError,
|
193
|
+
"The dictionary object associated with argument key '#{key}' is not in the cache."
|
194
|
+
end
|
195
|
+
|
196
|
+
dictionary_object
|
197
|
+
end
|
198
|
+
|
199
|
+
def dictionary_object
|
200
|
+
dictionary_cache.dig(DICTIONARY_CACHE, DICTIONARIES, dictionary_id, DICTIONARY_OBJECT)
|
201
|
+
end
|
202
|
+
|
203
|
+
def dictionary_object=(object)
|
204
|
+
raise ArgumentError, 'Argument object is not a Dictionary object' unless object.is_a? Dictionary
|
205
|
+
|
206
|
+
unless dictionary_reference?
|
207
|
+
raise ArgumentError,
|
208
|
+
"The dictionary reference associated with key '#{key}' could not be found."
|
209
|
+
end
|
210
|
+
return if object.equal? dictionary_object
|
211
|
+
|
212
|
+
if dictionary_exists?
|
213
|
+
raise ArgumentError,
|
214
|
+
"The dictionary is already loaded/cached for key '#{key}'; use #unload or #kill first."
|
215
|
+
end
|
216
|
+
|
217
|
+
dictionary_cache[DICTIONARY_CACHE][DICTIONARIES][dictionary_id!][DICTIONARY_OBJECT] = object
|
218
|
+
end
|
219
|
+
|
220
|
+
private
|
221
|
+
|
222
|
+
attr_writer :dictionary_cache
|
223
|
+
|
224
|
+
def dictionary_reference
|
225
|
+
dictionary_cache.dig(DICTIONARY_CACHE, DICTIONARY_REFERENCES, key)
|
226
|
+
end
|
227
|
+
|
228
|
+
def dictionary_reference=(dictionary_id)
|
229
|
+
dictionary_cache[DICTIONARY_CACHE][DICTIONARY_REFERENCES][key] = {
|
230
|
+
DICTIONARY_ID => dictionary_id
|
231
|
+
}
|
232
|
+
end
|
233
|
+
|
234
|
+
# Returns the dictionary_id for the source if it exists in dictionaries;
|
235
|
+
# otherwise, returns the new dictionary id that should be used.
|
236
|
+
def dictionary_id_for_dictionary_source(source:)
|
237
|
+
dictionary_source?(source: source) || SecureRandom.uuid[0..7]
|
238
|
+
end
|
239
|
+
|
240
|
+
# Returns the dictionary_id associated with source if source exists;
|
241
|
+
# nil otherwise.
|
242
|
+
def dictionary_source?(source:)
|
243
|
+
dictionaries = dictionary_cache.dig(DICTIONARY_CACHE, DICTIONARIES)
|
244
|
+
dictionaries&.each_pair do |dictionary_id, dictionary_hash|
|
245
|
+
return dictionary_id if source == dictionary_hash[SOURCE]
|
246
|
+
end
|
247
|
+
nil
|
248
|
+
end
|
249
|
+
|
250
|
+
def dictionary_source=(source)
|
251
|
+
dictionary_cache[DICTIONARY_CACHE][DICTIONARIES][dictionary_id!] = {
|
252
|
+
SOURCE => source,
|
253
|
+
DICTIONARY_OBJECT => {}
|
254
|
+
}
|
255
|
+
end
|
256
|
+
|
257
|
+
def dictionary_id?
|
258
|
+
dictionary_id.present?
|
259
|
+
end
|
260
|
+
end
|
261
|
+
end
|
262
|
+
end
|
@@ -0,0 +1,94 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative '../dictionary'
|
4
|
+
require_relative '../filters/word_filterable'
|
5
|
+
require_relative '../filters/word_filters_validatable'
|
6
|
+
require_relative '../metadata/dictionary_metadata'
|
7
|
+
require_relative '../modules/dictionary_cache_servicable'
|
8
|
+
require_relative '../modules/dictionary_creator_servicable'
|
9
|
+
require_relative '../modules/dictionary_keyable'
|
10
|
+
require_relative '../modules/dictionary_metadata_servicable'
|
11
|
+
require_relative '../modules/dictionary_sourceable'
|
12
|
+
require_relative '../preprocessors/word_preprocessor_managable'
|
13
|
+
require_relative 'dictionary_file_loader_service'
|
14
|
+
|
15
|
+
module LittleWeasel
|
16
|
+
module Services
|
17
|
+
# This class provides a service to load dictionaries from disk, create
|
18
|
+
# and return a Dictionary object.
|
19
|
+
class DictionaryCreatorService
|
20
|
+
include Filters::WordFilterable
|
21
|
+
include Filters::WordFiltersValidatable
|
22
|
+
include Modules::DictionaryCacheServicable
|
23
|
+
include Modules::DictionaryKeyable
|
24
|
+
include Modules::DictionaryMetadataServicable
|
25
|
+
include Modules::DictionarySourceable
|
26
|
+
include Preprocessors::WordPreprocessorManagable
|
27
|
+
|
28
|
+
def initialize(dictionary_key:, dictionary_cache:, dictionary_metadata:,
|
29
|
+
word_filters: nil, word_preprocessors: nil)
|
30
|
+
validate_dictionary_key dictionary_key: dictionary_key
|
31
|
+
self.dictionary_key = dictionary_key
|
32
|
+
|
33
|
+
validate_dictionary_cache dictionary_cache: dictionary_cache
|
34
|
+
self.dictionary_cache = dictionary_cache
|
35
|
+
|
36
|
+
validate_dictionary_metadata dictionary_metadata: dictionary_metadata
|
37
|
+
self.dictionary_metadata = dictionary_metadata
|
38
|
+
|
39
|
+
validate_word_filters word_filters: word_filters unless word_filters.blank?
|
40
|
+
self.word_filters = word_filters
|
41
|
+
|
42
|
+
validate_word_preprocessors word_preprocessors: word_preprocessors unless word_preprocessors.blank?
|
43
|
+
self.word_preprocessors = word_preprocessors
|
44
|
+
end
|
45
|
+
|
46
|
+
def from_file_source(file:)
|
47
|
+
add_dictionary_file_source file: file
|
48
|
+
dictionary_words = dictionary_file_loader_service.execute
|
49
|
+
create_dictionary dictionary_words: dictionary_words
|
50
|
+
end
|
51
|
+
|
52
|
+
def from_memory_source(dictionary_words:)
|
53
|
+
add_dictionary_memory_source
|
54
|
+
create_dictionary dictionary_words: dictionary_words
|
55
|
+
end
|
56
|
+
|
57
|
+
private
|
58
|
+
|
59
|
+
def dictionary_file_loader_service
|
60
|
+
Services::DictionaryFileLoaderService.new dictionary_key: dictionary_key, dictionary_cache: dictionary_cache
|
61
|
+
end
|
62
|
+
|
63
|
+
def create_dictionary(dictionary_words:)
|
64
|
+
Dictionary.new(dictionary_key: dictionary_key, dictionary_cache: dictionary_cache,
|
65
|
+
dictionary_metadata: dictionary_metadata, dictionary_words: dictionary_words, word_filters: word_filters,
|
66
|
+
word_preprocessors: word_preprocessors).tap do |dictionary|
|
67
|
+
dictionary_cache_service.dictionary_object = dictionary
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
# Adds a dictionary file source. A "file source" is a file path that
|
72
|
+
# indicates that the dictionary words associated with this dictionary are
|
73
|
+
# located on disk. This file path is used to locate and load the
|
74
|
+
# dictionary words into the dictionary cache for use.
|
75
|
+
#
|
76
|
+
# @param file [String] a file path pointing to the dictionary file to load and use.
|
77
|
+
#
|
78
|
+
# @return returns a reference to self.
|
79
|
+
def add_dictionary_file_source(file:)
|
80
|
+
dictionary_cache_service.add_dictionary_source(source: file)
|
81
|
+
end
|
82
|
+
|
83
|
+
# Adds a dictionary memory source. A "memory source" indicates that the
|
84
|
+
# dictionary words associated with this dictionary were created
|
85
|
+
# dynamically and will be located in memory, as opposed to loaded from
|
86
|
+
# a file on disk.
|
87
|
+
#
|
88
|
+
# @return returns a reference to self.
|
89
|
+
def add_dictionary_memory_source
|
90
|
+
dictionary_cache_service.add_dictionary_source(source: memory_source)
|
91
|
+
end
|
92
|
+
end
|
93
|
+
end
|
94
|
+
end
|