Module: MiniSearch
- Defined in:
- lib/mini_search.rb,
lib/mini_search/tf.rb,
lib/mini_search/idf.rb,
lib/mini_search/bm_25.rb,
lib/mini_search/version.rb,
lib/mini_search/pipeline.rb,
lib/mini_search/strip_filter.rb,
lib/mini_search/inverted_index.rb,
lib/mini_search/stemmer_filter.rb,
lib/mini_search/downcase_filter.rb,
lib/mini_search/ngram_tokenizer.rb,
lib/mini_search/synonyms_filter.rb,
lib/mini_search/stop_words_filter.rb,
lib/mini_search/compound_tokenizer.rb,
lib/mini_search/stemmer/portuguese.rb,
lib/mini_search/inverted_index_spec.rb,
lib/mini_search/remove_punctuation_filter.rb,
lib/mini_search/language_support/portuguese.rb,
lib/mini_search/standard_whitespace_tokenizer.rb
Defined Under Namespace
Modules: LanguageSupport, Stemmer
Classes: Bm25, CompoundTokenizer, DowncaseFilter, Idf, InvertedIndex, NgramTokenizer, Pipeline, RemovePunctuationFilter, StandardWhitespaceTokenizer, StemmerFilter, StopWordsFilter, StripFilter, SynonymsFilter, Tf
Constant Summary
collapse
- LANGUAGE_SUPPORTS =
{
pt: MiniSearch::LanguageSupport::Portuguese
}
- VERSION =
"1.2.0"
Class Method Summary
collapse
Class Method Details
.from_config_file(file) ⇒ Object
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
# File 'lib/mini_search.rb', line 81
def self.from_config_file(file)
raise "file not found '#{file}'" unless File.exists?(file)
cores = YAML.load_file(file)['cores']
cores.map do |core|
lang = core['lang'].to_sym
new_localized_index(
lang,
stop_words: core['stop_words'],
synonyms_map: core['synonyms_map'].transform_values { |v| v.split(',') }
)
end
end
|
.new(indexing_pipeline, querying_pipeline) ⇒ Object
25
26
27
|
# File 'lib/mini_search.rb', line 25
def self.new(indexing_pipeline, querying_pipeline)
MiniSearch::InvertedIndex.new(indexing_pipeline, querying_pipeline)
end
|
.new_index(stop_words: [], synonyms_map: {}, stemmer: nil, ngrams: nil) ⇒ Object
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
# File 'lib/mini_search.rb', line 29
def self.new_index(stop_words: [], synonyms_map: {}, stemmer: nil, ngrams: nil)
tokenizer =
if ngrams
NgramTokenizer.new(ngrams)
else
StandardWhitespaceTokenizer.new
end
strip_filter = StripFilter.new
remove_punctuation_filter = RemovePunctuationFilter.new
downcase_filter = DowncaseFilter.new
stop_words_filter = StopWordsFilter.new(stop_words)
stemmer_filter = StemmerFilter.new(stemmer)
synonyms_filter = SynonymsFilter.new(synonyms_map)
indexing_pipeline = Pipeline.new(
tokenizer,
[
strip_filter,
remove_punctuation_filter,
downcase_filter,
stop_words_filter,
stemmer_filter
]
)
querying_pipeline = Pipeline.new(
tokenizer,
[
strip_filter,
remove_punctuation_filter,
downcase_filter,
stop_words_filter,
stemmer_filter,
synonyms_filter
]
)
new(indexing_pipeline, querying_pipeline)
end
|
.new_localized_index(lang, synonyms_map: {}, stop_words: [], ngrams: nil) ⇒ Object
70
71
72
73
74
75
76
77
78
79
|
# File 'lib/mini_search.rb', line 70
def self.new_localized_index(lang, synonyms_map: {}, stop_words: [], ngrams: nil)
language_support = find_language_support(lang, stop_words)
new_index(
stop_words: language_support.stop_words,
stemmer: language_support.stemmer,
synonyms_map: synonyms_map,
ngrams: ngrams
)
end
|