Class: Searchkick::Index
- Inherits:
-
Object
- Object
- Searchkick::Index
- Defined in:
- lib/searchkick/index.rb,
lib/searchkick/logging.rb
Instance Attribute Summary collapse
-
#name ⇒ Object
readonly
Returns the value of attribute name.
-
#options ⇒ Object
readonly
Returns the value of attribute options.
Instance Method Summary collapse
- #alias_exists? ⇒ Boolean
-
#clean_indices ⇒ Object
remove old indices that start w/ index_name.
- #create(options = {}) ⇒ Object
-
#create_index(options = {}) ⇒ Object
reindex.
- #delete ⇒ Object
- #exists? ⇒ Boolean
- #import(records) ⇒ Object
- #import_scope(scope) ⇒ Object
- #import_with_instrumentation(records) ⇒ Object
- #index_options ⇒ Object
-
#initialize(name, options = {}) ⇒ Index
constructor
A new instance of Index.
- #klass_document_type(klass) ⇒ Object
- #mapping ⇒ Object
- #refresh ⇒ Object
- #reindex_record(record) ⇒ Object
- #reindex_record_async(record) ⇒ Object
- #reindex_scope(scope, options = {}) ⇒ Object
- #remove(record) ⇒ Object
- #remove_with_instrumentation(record) ⇒ Object
- #retrieve(record) ⇒ Object
-
#search_model(searchkick_klass, term = nil, options = {}, &block) ⇒ Object
search.
- #similar_record(record, options = {}) ⇒ Object
-
#store(record) ⇒ Object
record based.
- #store_with_instrumentation(record) ⇒ Object
- #swap(new_name) ⇒ Object
-
#tokens(text, options = {}) ⇒ Object
other.
Constructor Details
#initialize(name, options = {}) ⇒ Index
Returns a new instance of Index.
5 6 7 8 |
# File 'lib/searchkick/index.rb', line 5 def initialize(name, = {}) @name = name @options = end |
Instance Attribute Details
#name ⇒ Object (readonly)
Returns the value of attribute name.
3 4 5 |
# File 'lib/searchkick/index.rb', line 3 def name @name end |
#options ⇒ Object (readonly)
Returns the value of attribute options.
3 4 5 |
# File 'lib/searchkick/index.rb', line 3 def @options end |
Instance Method Details
#alias_exists? ⇒ Boolean
26 27 28 |
# File 'lib/searchkick/index.rb', line 26 def alias_exists? client.indices.exists_alias name: name end |
#clean_indices ⇒ Object
remove old indices that start w/ index_name
147 148 149 150 151 152 153 154 |
# File 'lib/searchkick/index.rb', line 147 def clean_indices all_indices = client.indices.get_aliases indices = all_indices.select { |k, v| (v.empty? || v["aliases"].empty?) && k =~ /\A#{Regexp.escape(name)}_\d{14,17}\z/ }.keys indices.each do |index| Searchkick::Index.new(index).delete end indices end |
#create(options = {}) ⇒ Object
10 11 12 |
# File 'lib/searchkick/index.rb', line 10 def create( = {}) client.indices.create index: name, body: end |
#create_index(options = {}) ⇒ Object
reindex
139 140 141 142 143 144 |
# File 'lib/searchkick/index.rb', line 139 def create_index( = {}) = [:index_options] || self. index = Searchkick::Index.new("#{name}_#{Time.now.strftime('%Y%m%d%H%M%S%L')}", @options) index.create() index end |
#delete ⇒ Object
14 15 16 |
# File 'lib/searchkick/index.rb', line 14 def delete client.indices.delete index: name end |
#exists? ⇒ Boolean
18 19 20 |
# File 'lib/searchkick/index.rb', line 18 def exists? client.indices.exists index: name end |
#import(records) ⇒ Object
67 68 69 70 71 72 73 74 75 76 77 78 79 |
# File 'lib/searchkick/index.rb', line 67 def import(records) records.group_by { |r| document_type(r) }.each do |type, batch| response = client.bulk( index: name, type: type, body: batch.map { |r| {index: {_id: search_id(r), data: search_data(r)}} } ) if response["errors"] raise Searchkick::ImportError, response["items"].first["index"]["error"] end end end |
#import_scope(scope) ⇒ Object
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
# File 'lib/searchkick/index.rb', line 186 def import_scope(scope) batch_size = @options[:batch_size] || 1000 # use scope for import scope = scope.search_import if scope.respond_to?(:search_import) if scope.respond_to?(:find_in_batches) scope.find_in_batches batch_size: batch_size do |batch| import batch.select(&:should_index?) end else # https://github.com/karmi/tire/blob/master/lib/tire/model/import.rb # use cursor for Mongoid items = [] scope.all.each do |item| items << item if item.should_index? if items.length == batch_size import items items = [] end end import items end end |
#import_with_instrumentation(records) ⇒ Object
40 41 42 43 44 45 46 47 48 49 50 |
# File 'lib/searchkick/logging.rb', line 40 def import_with_instrumentation(records) if records.any? event = { name: "#{records.first.searchkick_klass.name} Import", count: records.size } ActiveSupport::Notifications.instrument("request.searchkick", event) do import_without_instrumentation(records) end end end |
#index_options ⇒ Object
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 |
# File 'lib/searchkick/index.rb', line 210 def = @options language = [:language] language = language.call if language.respond_to?(:call) if [:mappings] && ![:merge_mappings] settings = [:settings] || {} mappings = [:mappings] else settings = { analysis: { analyzer: { searchkick_keyword: { type: "custom", tokenizer: "keyword", filter: ["lowercase"] + ([:stem_conversions] == false ? [] : ["searchkick_stemmer"]) }, default_index: { type: "custom", # character filters -> tokenizer -> token filters # https://www.elastic.co/guide/en/elasticsearch/guide/current/analysis-intro.html char_filter: ["ampersand"], tokenizer: "standard", # synonym should come last, after stemming and shingle # shingle must come before searchkick_stemmer filter: ["standard", "lowercase", "asciifolding", "searchkick_index_shingle", "searchkick_stemmer"] }, searchkick_search: { type: "custom", char_filter: ["ampersand"], tokenizer: "standard", filter: ["standard", "lowercase", "asciifolding", "searchkick_search_shingle", "searchkick_stemmer"] }, searchkick_search2: { type: "custom", char_filter: ["ampersand"], tokenizer: "standard", filter: ["standard", "lowercase", "asciifolding", "searchkick_stemmer"] }, # https://github.com/leschenko/elasticsearch_autocomplete/blob/master/lib/elasticsearch_autocomplete/analyzers.rb searchkick_autocomplete_index: { type: "custom", tokenizer: "searchkick_autocomplete_ngram", filter: ["lowercase", "asciifolding"] }, searchkick_autocomplete_search: { type: "custom", tokenizer: "keyword", filter: ["lowercase", "asciifolding"] }, searchkick_word_search: { type: "custom", tokenizer: "standard", filter: ["lowercase", "asciifolding"] }, searchkick_suggest_index: { type: "custom", tokenizer: "standard", filter: ["lowercase", "asciifolding", "searchkick_suggest_shingle"] }, searchkick_text_start_index: { type: "custom", tokenizer: "keyword", filter: ["lowercase", "asciifolding", "searchkick_edge_ngram"] }, searchkick_text_middle_index: { type: "custom", tokenizer: "keyword", filter: ["lowercase", "asciifolding", "searchkick_ngram"] }, searchkick_text_end_index: { type: "custom", tokenizer: "keyword", filter: ["lowercase", "asciifolding", "reverse", "searchkick_edge_ngram", "reverse"] }, searchkick_word_start_index: { type: "custom", tokenizer: "standard", filter: ["lowercase", "asciifolding", "searchkick_edge_ngram"] }, searchkick_word_middle_index: { type: "custom", tokenizer: "standard", filter: ["lowercase", "asciifolding", "searchkick_ngram"] }, searchkick_word_end_index: { type: "custom", tokenizer: "standard", filter: ["lowercase", "asciifolding", "reverse", "searchkick_edge_ngram", "reverse"] } }, filter: { searchkick_index_shingle: { type: "shingle", token_separator: "" }, # lucky find http://web.archiveorange.com/archive/v/AAfXfQ17f57FcRINsof7 searchkick_search_shingle: { type: "shingle", token_separator: "", output_unigrams: false, output_unigrams_if_no_shingles: true }, searchkick_suggest_shingle: { type: "shingle", max_shingle_size: 5 }, searchkick_edge_ngram: { type: "edgeNGram", min_gram: 1, max_gram: 50 }, searchkick_ngram: { type: "nGram", min_gram: 1, max_gram: 50 }, searchkick_stemmer: { # use stemmer if language is lowercase, snowball otherwise # TODO deprecate language option in favor of stemmer type: language == language.to_s.downcase ? "stemmer" : "snowball", language: language || "English" } }, char_filter: { # https://www.elastic.co/guide/en/elasticsearch/guide/current/custom-analyzers.html # &_to_and ampersand: { type: "mapping", mappings: ["&=> and "] } }, tokenizer: { searchkick_autocomplete_ngram: { type: "edgeNGram", min_gram: 1, max_gram: 50 } } } } if Searchkick.env == "test" settings.merge!(number_of_shards: 1, number_of_replicas: 0) end if [:similarity] settings[:similarity] = {default: {type: [:similarity]}} end settings.deep_merge!([:settings] || {}) # synonyms synonyms = [:synonyms] || [] synonyms = synonyms.call if synonyms.respond_to?(:call) if synonyms.any? settings[:analysis][:filter][:searchkick_synonym] = { type: "synonym", synonyms: synonyms.select { |s| s.size > 1 }.map { |s| s.join(",") } } # choosing a place for the synonym filter when stemming is not easy # https://groups.google.com/forum/#!topic/elasticsearch/p7qcQlgHdB8 # TODO use a snowball stemmer on synonyms when creating the token filter # http://elasticsearch-users.115913.n3.nabble.com/synonym-multi-words-search-td4030811.html # I find the following approach effective if you are doing multi-word synonyms (synonym phrases): # - Only apply the synonym expansion at index time # - Don't have the synonym filter applied search # - Use directional synonyms where appropriate. You want to make sure that you're not injecting terms that are too general. settings[:analysis][:analyzer][:default_index][:filter].insert(4, "searchkick_synonym") settings[:analysis][:analyzer][:default_index][:filter] << "searchkick_synonym" %w(word_start word_middle word_end).each do |type| settings[:analysis][:analyzer]["searchkick_#{type}_index".to_sym][:filter].insert(2, "searchkick_synonym") end end if [:wordnet] settings[:analysis][:filter][:searchkick_wordnet] = { type: "synonym", format: "wordnet", synonyms_path: Searchkick.wordnet_path } settings[:analysis][:analyzer][:default_index][:filter].insert(4, "searchkick_wordnet") settings[:analysis][:analyzer][:default_index][:filter] << "searchkick_wordnet" %w(word_start word_middle word_end).each do |type| settings[:analysis][:analyzer]["searchkick_#{type}_index".to_sym][:filter].insert(2, "searchkick_wordnet") end end if [:special_characters] == false settings[:analysis][:analyzer].each do |_, analyzer_settings| analyzer_settings[:filter].reject! { |f| f == "asciifolding" } end end mapping = {} # conversions if (conversions_field = [:conversions]) mapping[conversions_field] = { type: "nested", properties: { query: {type: "string", analyzer: "searchkick_keyword"}, count: {type: "integer"} } } end = Hash[ [:autocomplete, :suggest, :word, :text_start, :text_middle, :text_end, :word_start, :word_middle, :word_end, :highlight, :searchable] .map { |type| [type, ([type] || []).map(&:to_s)] } ] word = [:word] != false && (![:match] || [:match] == :word) .values.flatten.uniq.each do |field| field_mapping = { type: "multi_field", fields: { field => {type: "string", index: "not_analyzed"} } } if ![:searchable] || [:searchable].include?(field) if word field_mapping[:fields]["analyzed"] = {type: "string", index: "analyzed"} if [:highlight].include?(field) field_mapping[:fields]["analyzed"][:term_vector] = "with_positions_offsets" end end .except(:highlight, :searchable).each do |type, fields| if [:match] == type || fields.include?(field) field_mapping[:fields][type] = {type: "string", index: "analyzed", analyzer: "searchkick_#{type}_index"} end end end mapping[field] = field_mapping end ([:locations] || []).map(&:to_s).each do |field| mapping[field] = { type: "geo_point" } end ([:unsearchable] || []).map(&:to_s).each do |field| mapping[field] = { type: "string", index: "no" } end routing = {} if [:routing] routing = {required: true, path: [:routing].to_s} end dynamic_fields = { # analyzed field must be the default field for include_in_all # http://www.elasticsearch.org/guide/reference/mapping/multi-field-type/ # however, we can include the not_analyzed field in _all # and the _all index analyzer will take care of it "{name}" => {type: "string", index: "not_analyzed", include_in_all: ![:searchable]} } unless [:searchable] if [:match] && [:match] != :word dynamic_fields[[:match]] = {type: "string", index: "analyzed", analyzer: "searchkick_#{[:match]}_index"} end if word dynamic_fields["analyzed"] = {type: "string", index: "analyzed"} end end mappings = { _default_: { properties: mapping, _routing: routing, # https://gist.github.com/kimchy/2898285 dynamic_templates: [ { string_template: { match: "*", match_mapping_type: "string", mapping: { # http://www.elasticsearch.org/guide/reference/mapping/multi-field-type/ type: "multi_field", fields: dynamic_fields } } } ] } }.deep_merge([:mappings] || {}) end { settings: settings, mappings: mappings } end |
#klass_document_type(klass) ⇒ Object
527 528 529 530 531 532 533 |
# File 'lib/searchkick/index.rb', line 527 def klass_document_type(klass) if klass.respond_to?(:document_type) klass.document_type else klass.model_name.to_s.underscore end end |
#mapping ⇒ Object
30 31 32 |
# File 'lib/searchkick/index.rb', line 30 def mapping client.indices.get_mapping index: name end |
#refresh ⇒ Object
22 23 24 |
# File 'lib/searchkick/index.rb', line 22 def refresh client.indices.refresh index: name end |
#reindex_record(record) ⇒ Object
89 90 91 92 93 94 95 96 97 98 99 |
# File 'lib/searchkick/index.rb', line 89 def reindex_record(record) if record.destroyed? || !record.should_index? begin remove(record) rescue Elasticsearch::Transport::Transport::Errors::NotFound # do nothing end else store(record) end end |
#reindex_record_async(record) ⇒ Object
101 102 103 104 105 106 107 |
# File 'lib/searchkick/index.rb', line 101 def reindex_record_async(record) if defined?(Searchkick::ReindexV2Job) Searchkick::ReindexV2Job.perform_later(record.class.name, record.id.to_s) else Delayed::Job.enqueue Searchkick::ReindexJob.new(record.class.name, record.id.to_s) end end |
#reindex_scope(scope, options = {}) ⇒ Object
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
# File 'lib/searchkick/index.rb', line 158 def reindex_scope(scope, = {}) skip_import = [:import] == false clean_indices index = create_index(index_options: scope.) # check if alias exists if alias_exists? # import before swap index.import_scope(scope) unless skip_import # get existing indices to remove swap(index.name) clean_indices else delete if exists? swap(index.name) # import after swap index.import_scope(scope) unless skip_import end index.refresh true end |
#remove(record) ⇒ Object
56 57 58 59 60 61 62 63 64 65 |
# File 'lib/searchkick/index.rb', line 56 def remove(record) id = search_id(record) unless id.blank? client.delete( index: name, type: document_type(record), id: id ) end end |
#remove_with_instrumentation(record) ⇒ Object
29 30 31 32 33 34 35 36 37 |
# File 'lib/searchkick/logging.rb', line 29 def remove_with_instrumentation(record) event = { name: "#{record.searchkick_klass.name} Remove", id: search_id(record) } ActiveSupport::Notifications.instrument("request.searchkick", event) do remove_without_instrumentation(record) end end |
#retrieve(record) ⇒ Object
81 82 83 84 85 86 87 |
# File 'lib/searchkick/index.rb', line 81 def retrieve(record) client.get( index: name, type: document_type(record), id: search_id(record) )["_source"] end |
#search_model(searchkick_klass, term = nil, options = {}, &block) ⇒ Object
search
127 128 129 130 131 132 133 134 135 |
# File 'lib/searchkick/index.rb', line 127 def search_model(searchkick_klass, term = nil, = {}, &block) query = Searchkick::Query.new(searchkick_klass, term, ) block.call(query.body) if block if [:execute] == false query else query.execute end end |
#similar_record(record, options = {}) ⇒ Object
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
# File 'lib/searchkick/index.rb', line 109 def similar_record(record, = {}) like_text = retrieve(record).to_hash .keep_if { |k, _| ![:fields] || [:fields].map(&:to_s).include?(k) } .values.compact.join(" ") # TODO deep merge method [:where] ||= {} [:where][:_id] ||= {} [:where][:_id][:not] = record.id.to_s [:limit] ||= 10 [:similar] = true # TODO use index class instead of record class search_model(record.class, like_text, ) end |
#store(record) ⇒ Object
record based
47 48 49 50 51 52 53 54 |
# File 'lib/searchkick/index.rb', line 47 def store(record) client.index( index: name, type: document_type(record), id: search_id(record), body: search_data(record) ) end |
#store_with_instrumentation(record) ⇒ Object
18 19 20 21 22 23 24 25 26 |
# File 'lib/searchkick/logging.rb', line 18 def store_with_instrumentation(record) event = { name: "#{record.searchkick_klass.name} Store", id: search_id(record) } ActiveSupport::Notifications.instrument("request.searchkick", event) do store_without_instrumentation(record) end end |
#swap(new_name) ⇒ Object
34 35 36 37 38 39 40 41 42 43 |
# File 'lib/searchkick/index.rb', line 34 def swap(new_name) old_indices = begin client.indices.get_alias(name: name).keys rescue Elasticsearch::Transport::Transport::Errors::NotFound [] end actions = old_indices.map { |old_name| {remove: {index: old_name, alias: name}} } + [{add: {index: new_name, alias: name}}] client.indices.update_aliases body: {actions: actions} end |
#tokens(text, options = {}) ⇒ Object
other
523 524 525 |
# File 'lib/searchkick/index.rb', line 523 def tokens(text, = {}) client.indices.analyze({text: text, index: name}.merge())["tokens"].map { |t| t["token"] } end |