├── .dockerignore ├── .gitignore ├── LICENSE.txt ├── NOTICE.txt ├── README.md ├── VERSION.txt ├── build.gradle ├── docker ├── Dockerfile ├── compose-bash.sh ├── compose-build.sh ├── compose-down.sh ├── compose-logs.sh ├── compose-test.sh ├── compose-up.sh └── docker-compose.yml ├── examples ├── position_match.sh └── position_multi_match.sh ├── gradle.properties ├── gradle └── wrapper │ ├── gradle-wrapper.jar │ └── gradle-wrapper.properties ├── gradlew ├── scripts ├── install-plugin.sh └── remove-plugin.sh └── src └── main └── java └── org └── elasticsearch ├── index └── query │ ├── PositionMatchQuery.java │ ├── PositionMatchQueryBuilder.java │ ├── PositionMatchScorer.java │ └── PositionMatchWeight.java └── plugin └── PositionSimilarityPlugin.java /.dockerignore: -------------------------------------------------------------------------------- 1 | # Exclude everything: 2 | # 3 | * 4 | 5 | # Un-exclude what we need: 6 | # 7 | !gradle 8 | !examples 9 | !scripts 10 | !src 11 | !build.gradle 12 | !gradle.properties 13 | !gradlew 14 | !LICENSE.txt 15 | !NOTICE.txt 16 | !VERSION.txt 17 | 18 | # Exclude what we don't need: 19 | # 20 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | *.iml 3 | *.ipr 4 | *.iws 5 | build 6 | .gradle 7 | target 8 | .DS_Score 9 | .bloop 10 | .metals 11 | .vscode 12 | bin 13 | -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | 203 | -------------------------------------------------------------------------------- /NOTICE.txt: -------------------------------------------------------------------------------- 1 | This product includes software developed by The Apache Software 2 | Foundation (http://www.apache.org/). 3 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 6 | 7 | # Elasticsearch term position similarity plugin 8 | 9 | Elasticsearch custom similarity plugin to calculate score based on term position and payload so that terms closer to the beginning of a field have higher scores. 10 | 11 | ## Build docker image with Elasticsearch and plugin 12 | ```bash 13 | git clone https://github.com/sdauletau/elasticsearch-position-similarity.git 14 | cd elasticsearch-position-similarity 15 | ./docker/compose-build.sh 16 | ``` 17 | 18 | ## Start docker container with Elasticsearch and plugin 19 | ```bash 20 | ./docker/compose-up.sh 21 | ``` 22 | 23 | ## Review container logs 24 | ```bash 25 | ./docker/compose-logs.sh 26 | ``` 27 | 28 | ## Connect to docker container shell and run examples 29 | ```bash 30 | ./docker/compose-test.sh 31 | ``` 32 | 33 | ## Stop docker container with Elasticsearch and plugin 34 | ```bash 35 | ./docker/compose-down.sh 36 | ``` 37 | 38 | --- 39 | 40 | # Advanced Scoring with Elasticsearch Similarity Plugins 41 | 42 | ## What are Plugins 43 | 44 | > Plugins are a way to enhance the core Elasticsearch functionality in a custom manner. 45 | 46 | https://www.elastic.co/guide/en/elasticsearch/plugins/current/intro.html 47 | 48 | 49 | ## What is Similarity 50 | 51 | >A **similarity** (scoring/ranking model) defines how matching documents are scored. Similarity is per field, meaning that via the mapping one can define a different similarity per field. 52 | > 53 | >Configuring a custom similarity is considered an expert feature and the builtin similarities are most likely sufficient. 54 | 55 | https://www.elastic.co/guide/en/elasticsearch/reference/current/index-modules-similarity.html 56 | 57 | ## BM25 Similarity Scoring Formula 58 | 59 | **BM25** is a default similarity in Elasticsearch 7.x. 60 | 61 | ``` 62 | score(q,d) = 63 | ∑ ( 64 | (k1 + 1) 65 | · idf(t) 66 | · tf(t in d) / [ tf(t in d) + k1 · (1 - b + b · document_length / avg(document_length)) ] 67 | ) (t in q) 68 | ``` 69 | 70 | --- 71 | Let's index some documents, run a match query and look at the explanation. 72 | 73 | ## Build docker image with Elasticsearch and plugin 74 | ```bash 75 | git clone https://github.com/sdauletau/elasticsearch-position-similarity.git 76 | cd elasticsearch-position-similarity 77 | ./docker/compose-build.sh 78 | ``` 79 | 80 | ## Start docker container with Elasticsearch and plugin 81 | ```bash 82 | ./docker/compose-up.sh 83 | ``` 84 | 85 | ## Connect to docker container shell and run examples 86 | ```bash 87 | ./docker/compose-bash.sh 88 | ``` 89 | 90 | ## Create Elasticsearch Index 91 | 92 | ```bash 93 | curl --header "Content-Type:application/json" -s -XDELETE "http://localhost:9200/test_index" 94 | 95 | curl --header "Content-Type:application/json" -s -XPUT "http://localhost:9200/test_index" -d ' 96 | { 97 | "settings": { 98 | "index": { 99 | "number_of_shards": 1, 100 | "number_of_replicas": 0, 101 | "similarity": { 102 | "default": { 103 | "type": "BM25" 104 | } 105 | } 106 | } 107 | } 108 | } 109 | ' 110 | ``` 111 | 112 | ## Create Mapping 113 | 114 | ```bash 115 | curl --header "Content-Type:application/json" -XPUT 'localhost:9200/test_index/_mapping' -d ' 116 | { 117 | "properties": { 118 | "field1": { 119 | "type": "text" 120 | } 121 | } 122 | } 123 | ' 124 | ``` 125 | 126 | ## Index Documents 127 | 128 | ```bash 129 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/1" -d ' 130 | {"field1" : "bar foo"} 131 | ' 132 | 133 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/2" -d ' 134 | {"field1" : "foo bar bar"} 135 | ' 136 | 137 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/3" -d ' 138 | {"field1" : "bar bar foo foo"} 139 | ' 140 | 141 | curl --header "Content-Type:application/json" -s -XPOST "http://localhost:9200/test_index/_refresh" 142 | ``` 143 | 144 | doc id|foo freq|doc length 145 | ------|--------|---------- 146 | 1|1|2 147 | 2|1|3 148 | 3|2|4 149 | 150 | ## Match Query 151 | 152 | ```bash 153 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 154 | { 155 | "query": { 156 | "match": { 157 | "field1": "foo" 158 | } 159 | } 160 | } 161 | ' 162 | ``` 163 | 164 | ## Match Query Results 165 | 166 | ```json 167 | { 168 | "hits" : { 169 | "total" : { 170 | "value" : 3, 171 | "relation" : "eq" 172 | }, 173 | "max_score" : 0.16786805, 174 | "hits" : [ 175 | { 176 | "_index" : "test_index", 177 | "_type" : "_doc", 178 | "_id" : "3", 179 | "_score" : 0.16786805, 180 | "_source" : { 181 | "field1" : "bar bar foo foo" 182 | } 183 | }, 184 | { 185 | "_index" : "test_index", 186 | "_type" : "_doc", 187 | "_id" : "1", 188 | "_score" : 0.1546153, 189 | "_source" : { 190 | "field1" : "bar foo" 191 | } 192 | }, 193 | { 194 | "_index" : "test_index", 195 | "_type" : "_doc", 196 | "_id" : "2", 197 | "_score" : 0.13353139, 198 | "_source" : { 199 | "field1" : "foo bar bar" 200 | } 201 | } 202 | ] 203 | } 204 | } 205 | ``` 206 | 207 | - Document 3 has the highest score because it has higher foo frequency than Document 1 and Document 2. 208 | 209 | - Document 1 and 2 have the same foo frequency but Document 1 has less terms. 210 | 211 | ## Match Query Explanation 212 | 213 | ```bash 214 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 215 | { 216 | "explain": true, 217 | "query": { 218 | "match": { 219 | "field1": "foo" 220 | } 221 | } 222 | } 223 | ' 224 | ``` 225 | 226 | Note, that explanation is part of Lucene API. Document id mentioned in explanation is a Lucene document id and it can be different from Elacticsearch _id field. 227 | 228 | ```json 229 | { 230 | "_explanation": { 231 | "value": 0.16786805, 232 | "description": "weight(field1:foo in 2) [PerFieldSimilarity], result of:", 233 | "details": [ 234 | { 235 | "value": 0.16786805, 236 | "description": "score(freq=2.0), product of:", 237 | "details": [ 238 | { 239 | "value": 2.2, 240 | "description": "boost", 241 | "details": [] 242 | }, 243 | { 244 | "value": 0.13353139, 245 | "description": "idf, computed as log(1 + (N - n + 0.5) / (n + 0.5)) from:", 246 | "details": [ 247 | { 248 | "value": 3, 249 | "description": "n, number of documents containing term", 250 | "details": [] 251 | }, 252 | { 253 | "value": 3, 254 | "description": "N, total number of documents with field", 255 | "details": [] 256 | } 257 | ] 258 | }, 259 | { 260 | "value": 0.5714286, 261 | "description": "tf, computed as freq / (freq + k1 * (1 - b + b * dl / avgdl)) from:", 262 | "details": [ 263 | { 264 | "value": 2, 265 | "description": "freq, occurrences of term within document", 266 | "details": [] 267 | }, 268 | { 269 | "value": 1.2, 270 | "description": "k1, term saturation parameter", 271 | "details": [] 272 | }, 273 | { 274 | "value": 0.75, 275 | "description": "b, length normalization parameter", 276 | "details": [] 277 | }, 278 | { 279 | "value": 4, 280 | "description": "dl, length of field", 281 | "details": [] 282 | }, 283 | { 284 | "value": 3, 285 | "description": "avgdl, average length of field", 286 | "details": [] 287 | } 288 | ] 289 | } 290 | ] 291 | } 292 | ] 293 | } 294 | } 295 | ``` 296 | 297 | ## We Need a Better Score 298 | 299 | The default scoring model works good but the best scoring model will always be application specific. 300 | Let's say that we want to score documents based on a position of a matching term. 301 | For our example, we want to score Document 2 higher than Document 1 and 3. 302 | 303 | ## Similarity Plugins 304 | 305 | Similarity plugins extend Elasticsearch by adding new similarities (scoring/ranking models) to Elasticsearch. 306 | 307 | There are several steps necessary to implement a scoring plugin that will **use term positions and payloads** and **ignore term frequency, inverse document frequency and normalization**. 308 | 309 | >TODO: Needs explanation 310 | 311 | ## Create Elasticsearch Index 312 | 313 | ```bash 314 | curl --header "Content-Type:application/json" -s -XDELETE "http://localhost:9200/test_index" 315 | 316 | curl --header "Content-Type:application/json" -s -XPUT "http://localhost:9200/test_index" -d ' 317 | { 318 | "settings": { 319 | "index": { 320 | "number_of_shards": 1, 321 | "number_of_replicas": 0, 322 | "similarity": { 323 | "default": { 324 | "type": "BM25" 325 | } 326 | } 327 | }, 328 | "analysis": { 329 | "analyzer": { 330 | "positionPayloadAnalyzer": { 331 | "type": "custom", 332 | "tokenizer": "whitespace", 333 | "filter": [ 334 | "lowercase", 335 | "asciifolding", 336 | "positionPayloadFilter" 337 | ] 338 | } 339 | }, 340 | "filter": { 341 | "positionPayloadFilter": { 342 | "delimiter": "|", 343 | "encoding": "int", 344 | "type": "delimited_payload" 345 | } 346 | } 347 | } 348 | } 349 | } 350 | ' 351 | ``` 352 | 353 | ## Create Mapping 354 | 355 | ```bash 356 | curl --header "Content-Type:application/json" -XPUT 'localhost:9200/test_index/_mapping' -d ' 357 | { 358 | "properties": { 359 | "field1": { 360 | "type": "text" 361 | }, 362 | "field2": { 363 | "type": "text", 364 | "term_vector": "with_positions_offsets_payloads", 365 | "analyzer": "positionPayloadAnalyzer" 366 | } 367 | } 368 | } 369 | ' 370 | ``` 371 | 372 | ## Index Documents 373 | 374 | ```bash 375 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/1" -d ' 376 | {"field1" : "bar foo", "field2" : "bar|0 foo|1"} 377 | ' 378 | 379 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/2" -d ' 380 | {"field1" : "foo bar bar", "field2" : "foo|0 bar|1 bar|3"} 381 | ' 382 | 383 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/3" -d ' 384 | {"field1" : "bar bar foo foo", "field2" : "bar|0 bar|1 foo|2 foo|3"} 385 | ' 386 | 387 | curl --header "Content-Type:application/json" -s -XPOST "http://localhost:9200/test_index/_refresh" 388 | ``` 389 | 390 | doc id|foo freq|doc length|foo position 391 | ------|--------|----------|------------ 392 | 1|1|2|1 393 | 2|1|3|0 394 | 3|2|4|2 395 | 396 | ## Match Query 397 | 398 | ```bash 399 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 400 | { 401 | "query": { 402 | "position_match": { 403 | "query": { 404 | "match": { 405 | "field2": "foo" 406 | } 407 | } 408 | } 409 | } 410 | } 411 | ' 412 | ``` 413 | 414 | ## Match Query Results 415 | 416 | ```json 417 | { 418 | "hits" : { 419 | "total" : { 420 | "value" : 3, 421 | "relation" : "eq" 422 | }, 423 | "max_score" : 1.0, 424 | "hits" : [ 425 | { 426 | "_index" : "test_index", 427 | "_type" : "_doc", 428 | "_id" : "2", 429 | "_score" : 1.0, 430 | "_source" : { 431 | "field1" : "foo bar bar", 432 | "field2" : "foo|0 bar|1 bar|3" 433 | } 434 | }, 435 | { 436 | "_index" : "test_index", 437 | "_type" : "_doc", 438 | "_id" : "1", 439 | "_score" : 0.8333333, 440 | "_source" : { 441 | "field1" : "bar foo", 442 | "field2" : "bar|0 foo|1" 443 | } 444 | }, 445 | { 446 | "_index" : "test_index", 447 | "_type" : "_doc", 448 | "_id" : "3", 449 | "_score" : 0.71428573, 450 | "_source" : { 451 | "field1" : "bar bar foo foo", 452 | "field2" : "bar|0 bar|1 foo|2 foo|3" 453 | } 454 | } 455 | ] 456 | } 457 | } 458 | ``` 459 | 460 | - Document 2 has the highest score because term foo has the lowest position. 461 | 462 | ## Match Query Explanation 463 | 464 | ```bash 465 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 466 | { 467 | "explain": true, 468 | "query": { 469 | "position_match": { 470 | "query": { 471 | "match": { 472 | "field2": "foo" 473 | } 474 | } 475 | } 476 | } 477 | } 478 | ' 479 | ``` 480 | 481 | Note, that explanation is part of Lucene API. Document id mentioned in explanation is a Lucene document id and it can be different from Elacticsearch _id field. 482 | 483 | ```json 484 | { 485 | "_shard": "[test_index][0]", 486 | "_node": "Raak6LCoRluN_7MJpzKDJA", 487 | "_index": "test_index", 488 | "_type": "_doc", 489 | "_id": "2", 490 | "_score": 1, 491 | "_source": { 492 | "field1": "foo bar bar", 493 | "field2": "foo|0 bar|1 bar|3" 494 | }, 495 | "_explanation": { 496 | "value": 1, 497 | "description": "score(doc=1), sum of:", 498 | "details": [ 499 | { 500 | "value": 1, 501 | "description": "score(field=field2, term=foo, pos=0, func=5/(5+0))", 502 | "details": [] 503 | } 504 | ] 505 | } 506 | } 507 | ``` 508 | -------------------------------------------------------------------------------- /VERSION.txt: -------------------------------------------------------------------------------- 1 | ES_VERSION=8.7.0 -------------------------------------------------------------------------------- /build.gradle: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | buildscript { 16 | repositories { 17 | gradlePluginPortal() 18 | } 19 | 20 | def es_version = rootProject.file('VERSION.txt').text.trim().split("=")[1] 21 | 22 | dependencies { 23 | classpath "org.elasticsearch.gradle:build-tools:${es_version}" 24 | } 25 | } 26 | 27 | repositories { 28 | mavenCentral() 29 | } 30 | 31 | apply plugin: 'elasticsearch.esplugin' 32 | 33 | esplugin { 34 | description 'Elasticsearch scoring plugin based on matching a term or a phrase relative to a position of the term in a searched field.' 35 | classname 'org.elasticsearch.plugin.PositionSimilarityPlugin' 36 | name 'elasticsearch-position-similarity' 37 | licenseFile rootProject.file('LICENSE.txt') 38 | noticeFile rootProject.file('NOTICE.txt') 39 | } 40 | 41 | test.enabled = false 42 | -------------------------------------------------------------------------------- /docker/Dockerfile: -------------------------------------------------------------------------------- 1 | ARG ES_VERSION 2 | FROM docker.elastic.co/elasticsearch/elasticsearch:${ES_VERSION} AS builder-image 3 | 4 | WORKDIR /elasticsearch-position-similarity 5 | COPY ../ . 6 | 7 | ENV JAVA_HOME /usr/share/elasticsearch/jdk 8 | ENV PATH $JAVA_HOME/bin:$PATH 9 | RUN ./gradlew clean build 10 | RUN ./scripts/install-plugin.sh 11 | 12 | ARG ES_VERSION 13 | FROM docker.elastic.co/elasticsearch/elasticsearch:${ES_VERSION} 14 | 15 | COPY --from=builder-image /usr/share/elasticsearch/plugins/elasticsearch-position-similarity/ /usr/share/elasticsearch/plugins/elasticsearch-position-similarity/ 16 | COPY --from=builder-image /elasticsearch-position-similarity/examples/ /elasticsearch-position-similarity/examples/ 17 | 18 | WORKDIR /elasticsearch-position-similarity 19 | -------------------------------------------------------------------------------- /docker/compose-bash.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml exec es /bin/bash 6 | 7 | -------------------------------------------------------------------------------- /docker/compose-build.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml build 6 | -------------------------------------------------------------------------------- /docker/compose-down.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml down 6 | -------------------------------------------------------------------------------- /docker/compose-logs.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml logs es -f 6 | 7 | -------------------------------------------------------------------------------- /docker/compose-test.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml exec es ./examples/position_match.sh 6 | -------------------------------------------------------------------------------- /docker/compose-up.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | set -eux 4 | 5 | docker-compose -p esps --env-file VERSION.txt -f docker/docker-compose.yml up -d 6 | 7 | # Wait for Elasticsearch to start 8 | while ! timeout 1 bash -c "curl -fs http://127.0.0.1:9200" &> /dev/null; do sleep 5; done; 9 | -------------------------------------------------------------------------------- /docker/docker-compose.yml: -------------------------------------------------------------------------------- 1 | version: '3' 2 | 3 | services: 4 | es: 5 | image: elasticsearch-position-similarity:${ES_VERSION} 6 | container_name: es 7 | build: 8 | context: ../ 9 | dockerfile: docker/Dockerfile 10 | args: 11 | - ES_VERSION 12 | environment: 13 | - node.name=es 14 | - cluster.name=es-cluster 15 | - discovery.type=single-node 16 | - bootstrap.memory_lock=true 17 | - mem_limit=2048m 18 | - xpack.security.enabled=false 19 | - xpack.security.http.ssl.enabled=false 20 | - xpack.security.transport.ssl.enabled=false 21 | ports: 22 | - 9200:9200 23 | ulimits: 24 | memlock: 25 | soft: -1 26 | hard: -1 27 | volumes: 28 | - esdata:/usr/share/elasticsearch/data 29 | 30 | volumes: 31 | esdata: 32 | -------------------------------------------------------------------------------- /examples/position_match.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | echo 4 | 5 | echo 'Delete index' 6 | curl --header "Content-Type:application/json" -s -XDELETE "http://localhost:9200/test_index" 7 | echo 8 | echo 9 | 10 | echo 'Create index' 11 | curl --header "Content-Type:application/json" -s -XPUT "http://localhost:9200/test_index" -d ' 12 | { 13 | "settings": { 14 | "index": { 15 | "number_of_shards": 1, 16 | "number_of_replicas": 0, 17 | "similarity": { 18 | "default": { 19 | "type": "BM25" 20 | } 21 | } 22 | } 23 | } 24 | } 25 | ' 26 | echo 27 | 28 | echo 'Create mappings' 29 | curl --header "Content-Type:application/json" -XPUT 'localhost:9200/test_index/_mapping' -d ' 30 | { 31 | "properties": { 32 | "field1": { 33 | "type": "text" 34 | } 35 | } 36 | } 37 | ' 38 | echo 39 | 40 | echo 'Index documents and refresh index' 41 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/1" -d ' 42 | {"field1" : "bar foo"} 43 | ' 44 | 45 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/2" -d ' 46 | {"field1" : "foo bar bar"} 47 | ' 48 | 49 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/3" -d ' 50 | {"field1" : "bar bar foo foo"} 51 | ' 52 | 53 | curl --header "Content-Type:application/json" -s -XPOST "http://localhost:9200/test_index/_refresh" 54 | echo 55 | 56 | echo 57 | echo 'Expecting document with _id 3 to have highest score' 58 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 59 | { 60 | "explain": true, 61 | "query": { 62 | "match": { 63 | "field1": "foo" 64 | } 65 | } 66 | } 67 | ' 68 | echo 69 | 70 | echo 'Delete index' 71 | curl --header "Content-Type:application/json" -s -XDELETE "http://localhost:9200/test_index" 72 | echo 73 | echo 74 | 75 | echo 'Create index' 76 | curl --header "Content-Type:application/json" -s -XPUT "http://localhost:9200/test_index" -d ' 77 | { 78 | "settings": { 79 | "index": { 80 | "number_of_shards": 1, 81 | "number_of_replicas": 0, 82 | "similarity": { 83 | "default": { 84 | "type": "BM25" 85 | } 86 | } 87 | }, 88 | "analysis": { 89 | "analyzer": { 90 | "positionPayloadAnalyzer": { 91 | "type": "custom", 92 | "tokenizer": "whitespace", 93 | "filter": [ 94 | "lowercase", 95 | "asciifolding", 96 | "positionPayloadFilter" 97 | ] 98 | } 99 | }, 100 | "filter": { 101 | "positionPayloadFilter": { 102 | "delimiter": "|", 103 | "encoding": "int", 104 | "type": "delimited_payload" 105 | } 106 | } 107 | } 108 | } 109 | } 110 | ' 111 | echo 112 | 113 | echo 'Create mappings' 114 | curl --header "Content-Type:application/json" -XPUT 'localhost:9200/test_index/_mapping' -d ' 115 | { 116 | "properties": { 117 | "field1": { 118 | "type": "text" 119 | }, 120 | "field2": { 121 | "type": "text", 122 | "term_vector": "with_positions_offsets_payloads", 123 | "analyzer": "positionPayloadAnalyzer" 124 | } 125 | } 126 | } 127 | ' 128 | echo 129 | 130 | echo 'Index documents and refresh index' 131 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/1" -d ' 132 | {"field1" : "bar foo", "field2" : "bar|0 foo|1"} 133 | ' 134 | 135 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/2" -d ' 136 | {"field1" : "foo bar bar", "field2" : "foo|0 bar|1 bar|3"} 137 | ' 138 | 139 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/3" -d ' 140 | {"field1" : "bar bar foo foo", "field2" : "bar|0 bar|1 foo|2 foo|3"} 141 | ' 142 | 143 | curl --header "Content-Type:application/json" -s -XPOST "http://localhost:9200/test_index/_refresh" 144 | echo 145 | 146 | echo 147 | echo 'Expecting document with _id 2 to have highest score' 148 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 149 | { 150 | "explain": true, 151 | "query": { 152 | "position_match": { 153 | "query": { 154 | "match": { 155 | "field2": "foo" 156 | } 157 | } 158 | } 159 | } 160 | } 161 | ' 162 | echo 163 | -------------------------------------------------------------------------------- /examples/position_multi_match.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | echo 4 | 5 | echo 'Delete index' 6 | curl --header "Content-Type:application/json" -s -XDELETE "http://localhost:9200/test_index" 7 | echo 8 | echo 9 | 10 | echo 'Create index' 11 | curl --header "Content-Type:application/json" -s -XPUT "http://localhost:9200/test_index" -d ' 12 | { 13 | "settings": { 14 | "index": { 15 | "number_of_shards": 1, 16 | "number_of_replicas": 0, 17 | "similarity": { 18 | "default": { 19 | "type": "BM25" 20 | } 21 | } 22 | }, 23 | "analysis": { 24 | "analyzer": { 25 | "positionPayloadAnalyzer": { 26 | "type": "custom", 27 | "tokenizer": "whitespace", 28 | "filter": [ 29 | "lowercase", 30 | "asciifolding", 31 | "positionPayloadFilter" 32 | ] 33 | } 34 | }, 35 | "filter": { 36 | "positionPayloadFilter": { 37 | "delimiter": "|", 38 | "encoding": "int", 39 | "type": "delimited_payload" 40 | } 41 | } 42 | } 43 | } 44 | } 45 | ' 46 | echo 47 | 48 | echo 'Create mappings' 49 | curl --header "Content-Type:application/json" -XPUT 'localhost:9200/test_index/_mapping' -d ' 50 | { 51 | "properties": { 52 | "field1": { 53 | "type": "text" 54 | }, 55 | "field2": { 56 | "type": "text", 57 | "term_vector": "with_positions_offsets_payloads", 58 | "analyzer": "positionPayloadAnalyzer" 59 | } 60 | } 61 | } 62 | ' 63 | echo 64 | 65 | echo 'Index documents and refresh index' 66 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/1" -d ' 67 | {"field1" : "bar foo", "field2" : "bar|0 foo|1"} 68 | ' 69 | 70 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/2" -d ' 71 | {"field1" : "foo foo bar bar bar", "field2" : "foo|0 foo|1 bar|3 bar|4 bar|5"} 72 | ' 73 | 74 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/3" -d ' 75 | {"field1" : "bar bar foo too", "field2" : "bar|0 bar|1 foo|2 too|3"} 76 | ' 77 | 78 | curl --header "Content-Type:application/json" -s -XPUT "localhost:9200/test_index/_doc/4" -d ' 79 | {"field1" : "bar bar too", "field2" : "bar|0 bar|1 too|2"} 80 | ' 81 | 82 | curl --header "Content-Type:application/json" -s -XPOST "http://localhost:9200/test_index/_refresh" 83 | echo 84 | 85 | echo 86 | echo 'Expecting document with _id 4 to have highest score' 87 | curl --header "Content-Type:application/json" -s "localhost:9200/test_index/_search?pretty=true" -d ' 88 | { 89 | "explain": true, 90 | "from": 0, 91 | "size": 1, 92 | "query": { 93 | "position_match": { 94 | "query": { 95 | "multi_match": { 96 | "query": "bar too", 97 | "fields": ["field1","field2"] 98 | } 99 | } 100 | } 101 | } 102 | } 103 | ' 104 | echo 105 | -------------------------------------------------------------------------------- /gradle.properties: -------------------------------------------------------------------------------- 1 | org.gradle.daemon=false 2 | org.gradle.jvmargs=-Xmx2g 3 | options.forkOptions.memoryMaximumSize=2g 4 | -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sdauletau/elasticsearch-position-similarity/c9ae6076b12cf1354da1578f8b1beb4fbe52b785/gradle/wrapper/gradle-wrapper.jar -------------------------------------------------------------------------------- /gradle/wrapper/gradle-wrapper.properties: -------------------------------------------------------------------------------- 1 | distributionBase=GRADLE_USER_HOME 2 | distributionPath=wrapper/dists 3 | distributionUrl=https\://services.gradle.org/distributions/gradle-7.6.1-all.zip 4 | zipStoreBase=GRADLE_USER_HOME 5 | zipStorePath=wrapper/dists 6 | -------------------------------------------------------------------------------- /gradlew: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env sh 2 | 3 | ############################################################################## 4 | ## 5 | ## Gradle start up script for UN*X 6 | ## 7 | ############################################################################## 8 | 9 | # Attempt to set APP_HOME 10 | # Resolve links: $0 may be a link 11 | PRG="$0" 12 | # Need this for relative symlinks. 13 | while [ -h "$PRG" ] ; do 14 | ls=`ls -ld "$PRG"` 15 | link=`expr "$ls" : '.*-> \(.*\)$'` 16 | if expr "$link" : '/.*' > /dev/null; then 17 | PRG="$link" 18 | else 19 | PRG=`dirname "$PRG"`"/$link" 20 | fi 21 | done 22 | SAVED="`pwd`" 23 | cd "`dirname \"$PRG\"`/" >/dev/null 24 | APP_HOME="`pwd -P`" 25 | cd "$SAVED" >/dev/null 26 | 27 | APP_NAME="Gradle" 28 | APP_BASE_NAME=`basename "$0"` 29 | 30 | # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script. 31 | DEFAULT_JVM_OPTS='"-Xmx64m"' 32 | 33 | # Use the maximum available, or set MAX_FD != -1 to use that query. 34 | MAX_FD="maximum" 35 | 36 | warn () { 37 | echo "$*" 38 | } 39 | 40 | die () { 41 | echo 42 | echo "$*" 43 | echo 44 | exit 1 45 | } 46 | 47 | # OS specific support (must be 'true' or 'false'). 48 | cygwin=false 49 | msys=false 50 | darwin=false 51 | nonstop=false 52 | case "`uname`" in 53 | CYGWIN* ) 54 | cygwin=true 55 | ;; 56 | Darwin* ) 57 | darwin=true 58 | ;; 59 | MINGW* ) 60 | msys=true 61 | ;; 62 | NONSTOP* ) 63 | nonstop=true 64 | ;; 65 | esac 66 | 67 | CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar 68 | 69 | # Determine the Java command to use to start the JVM. 70 | if [ -n "$JAVA_HOME" ] ; then 71 | if [ -x "$JAVA_HOME/jre/sh/java" ] ; then 72 | # IBM's JDK on AIX uses strange locations for the executables 73 | JAVACMD="$JAVA_HOME/jre/sh/java" 74 | else 75 | JAVACMD="$JAVA_HOME/bin/java" 76 | fi 77 | if [ ! -x "$JAVACMD" ] ; then 78 | die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME 79 | 80 | Please set the JAVA_HOME variable in your environment to match the 81 | location of your Java installation." 82 | fi 83 | else 84 | JAVACMD="java" 85 | which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH. 86 | 87 | Please set the JAVA_HOME variable in your environment to match the 88 | location of your Java installation." 89 | fi 90 | 91 | # Increase the maximum file descriptors if we can. 92 | if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then 93 | MAX_FD_LIMIT=`ulimit -H -n` 94 | if [ $? -eq 0 ] ; then 95 | if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then 96 | MAX_FD="$MAX_FD_LIMIT" 97 | fi 98 | ulimit -n $MAX_FD 99 | if [ $? -ne 0 ] ; then 100 | warn "Could not set maximum file descriptor limit: $MAX_FD" 101 | fi 102 | else 103 | warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT" 104 | fi 105 | fi 106 | 107 | # For Darwin, add options to specify how the application appears in the dock 108 | if $darwin; then 109 | GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\"" 110 | fi 111 | 112 | # For Cygwin, switch paths to Windows format before running java 113 | if $cygwin ; then 114 | APP_HOME=`cygpath --path --mixed "$APP_HOME"` 115 | CLASSPATH=`cygpath --path --mixed "$CLASSPATH"` 116 | JAVACMD=`cygpath --unix "$JAVACMD"` 117 | 118 | # We build the pattern for arguments to be converted via cygpath 119 | ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null` 120 | SEP="" 121 | for dir in $ROOTDIRSRAW ; do 122 | ROOTDIRS="$ROOTDIRS$SEP$dir" 123 | SEP="|" 124 | done 125 | OURCYGPATTERN="(^($ROOTDIRS))" 126 | # Add a user-defined pattern to the cygpath arguments 127 | if [ "$GRADLE_CYGPATTERN" != "" ] ; then 128 | OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)" 129 | fi 130 | # Now convert the arguments - kludge to limit ourselves to /bin/sh 131 | i=0 132 | for arg in "$@" ; do 133 | CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -` 134 | CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option 135 | 136 | if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition 137 | eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"` 138 | else 139 | eval `echo args$i`="\"$arg\"" 140 | fi 141 | i=$((i+1)) 142 | done 143 | case $i in 144 | (0) set -- ;; 145 | (1) set -- "$args0" ;; 146 | (2) set -- "$args0" "$args1" ;; 147 | (3) set -- "$args0" "$args1" "$args2" ;; 148 | (4) set -- "$args0" "$args1" "$args2" "$args3" ;; 149 | (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;; 150 | (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;; 151 | (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;; 152 | (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;; 153 | (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;; 154 | esac 155 | fi 156 | 157 | # Escape application args 158 | save () { 159 | for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done 160 | echo " " 161 | } 162 | APP_ARGS=$(save "$@") 163 | 164 | # Collect all arguments for the java command, following the shell quoting and substitution rules 165 | eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS" 166 | 167 | # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong 168 | if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then 169 | cd "$(dirname "$0")" 170 | fi 171 | 172 | exec "$JAVACMD" "$@" 173 | -------------------------------------------------------------------------------- /scripts/install-plugin.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | /usr/share/elasticsearch/bin/elasticsearch-plugin install file:///${PWD}/build/distributions/elasticsearch-position-similarity.zip 6 | -------------------------------------------------------------------------------- /scripts/remove-plugin.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | set -eux 4 | 5 | /usr/share/elasticsearch/bin/elasticsearch-plugin remove elasticsearch-position-similarity 6 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/index/query/PositionMatchQuery.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | package org.elasticsearch.index.query; 16 | 17 | import org.apache.lucene.index.IndexReader; 18 | import org.apache.lucene.search.IndexSearcher; 19 | import org.apache.lucene.search.Query; 20 | import org.apache.lucene.search.QueryVisitor; 21 | import org.apache.lucene.search.ScoreMode; 22 | import org.apache.lucene.search.Weight; 23 | 24 | import java.io.IOException; 25 | import java.util.Objects; 26 | 27 | public class PositionMatchQuery extends Query { 28 | public static final String NAME = "position_match"; 29 | 30 | private final Query query; 31 | 32 | PositionMatchQuery(Query query) { 33 | this.query = query; 34 | } 35 | 36 | @Override 37 | public Query rewrite(IndexReader reader) throws IOException { 38 | Query newQ = query.rewrite(reader); 39 | if ((newQ != query)) { 40 | return new PositionMatchQuery(newQ); 41 | } 42 | return super.rewrite(reader); 43 | } 44 | 45 | @Override 46 | public String toString(String field) { 47 | return NAME + "(" + query.toString(field) + ")"; 48 | } 49 | 50 | @Override 51 | public PositionMatchWeight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException { 52 | Weight weight = query.createWeight(searcher, ScoreMode.COMPLETE, boost); 53 | return new PositionMatchWeight(query, weight); 54 | } 55 | 56 | @Override 57 | public boolean equals(Object obj) { 58 | if (!sameClassAs(obj)) { 59 | return false; 60 | } 61 | PositionMatchQuery other = (PositionMatchQuery) obj; 62 | return Objects.equals(query, other.query); 63 | } 64 | 65 | @Override 66 | public int hashCode() { 67 | return Objects.hash(classHash(), query); 68 | } 69 | 70 | @Override 71 | public void visit(QueryVisitor visitor) { 72 | query.visit(visitor); 73 | } 74 | } 75 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/index/query/PositionMatchQueryBuilder.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | package org.elasticsearch.index.query; 16 | 17 | import org.apache.lucene.search.Query; 18 | import org.elasticsearch.TransportVersion; 19 | import org.elasticsearch.common.io.stream.StreamInput; 20 | import org.elasticsearch.common.io.stream.StreamOutput; 21 | import org.elasticsearch.xcontent.XContentBuilder; 22 | import org.elasticsearch.xcontent.XContentParser; 23 | 24 | import java.io.IOException; 25 | import java.util.Objects; 26 | 27 | public class PositionMatchQueryBuilder extends AbstractQueryBuilder { 28 | public static PositionMatchQueryBuilder fromXContent(XContentParser parser) throws IOException { 29 | QueryBuilder queryBuilder = null; 30 | 31 | XContentParser.Token token; 32 | while ((token = parser.nextToken()) != XContentParser.Token.END_OBJECT) { 33 | if (token == XContentParser.Token.START_OBJECT) { 34 | queryBuilder = parseInnerQueryBuilder(parser); 35 | } 36 | } 37 | 38 | return new PositionMatchQueryBuilder(queryBuilder); 39 | } 40 | 41 | private final QueryBuilder queryBuilder; 42 | 43 | private PositionMatchQueryBuilder(QueryBuilder queryBuilder) { 44 | if (queryBuilder == null) { 45 | throw new IllegalArgumentException("Expecting query object in [" + PositionMatchQuery.NAME + "]"); 46 | } 47 | this.queryBuilder = queryBuilder; 48 | } 49 | 50 | public PositionMatchQueryBuilder(StreamInput in) throws IOException { 51 | super(in); 52 | queryBuilder = in.readNamedWriteable(QueryBuilder.class); 53 | } 54 | 55 | @Override 56 | protected void doWriteTo(StreamOutput out) throws IOException { 57 | out.writeNamedWriteable(queryBuilder); 58 | } 59 | 60 | @Override 61 | protected void doXContent(XContentBuilder builder, Params params) throws IOException { 62 | builder.startObject(PositionMatchQuery.NAME); 63 | queryBuilder.toXContent(builder, params); 64 | boostAndQueryNameToXContent(builder); 65 | builder.endObject(); 66 | } 67 | 68 | @Override 69 | protected Query doToQuery(SearchExecutionContext context) throws IOException { 70 | Query query = queryBuilder.toQuery(context); 71 | return new PositionMatchQuery(query); 72 | } 73 | 74 | @Override 75 | protected int doHashCode() { 76 | return Objects.hash(queryBuilder); 77 | } 78 | 79 | @Override 80 | protected boolean doEquals(PositionMatchQueryBuilder other) { 81 | return Objects.equals(queryBuilder, other.queryBuilder); 82 | } 83 | 84 | @Override 85 | public String getWriteableName() { 86 | return PositionMatchQuery.NAME; 87 | } 88 | 89 | @Override 90 | public TransportVersion getMinimalSupportedVersion() { 91 | return TransportVersion.MINIMUM_COMPATIBLE; 92 | } 93 | } 94 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/index/query/PositionMatchScorer.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | package org.elasticsearch.index.query; 16 | 17 | import org.apache.logging.log4j.LogManager; 18 | import org.apache.lucene.analysis.payloads.PayloadHelper; 19 | import org.apache.lucene.index.*; 20 | import org.apache.lucene.search.DocIdSetIterator; 21 | import org.apache.lucene.search.Explanation; 22 | import org.apache.lucene.search.QueryVisitor; 23 | import org.apache.lucene.search.Scorer; 24 | import org.apache.lucene.util.BytesRef; 25 | 26 | import java.io.IOException; 27 | import java.util.ArrayList; 28 | import java.util.HashSet; 29 | import java.util.List; 30 | import java.util.Set; 31 | 32 | public class PositionMatchScorer extends Scorer { 33 | private final int NOT_FOUND_POSITION = -1; 34 | private final int HALF_SCORE_POSITION = 5; // position where score should decrease by 50% 35 | 36 | private final LeafReaderContext context; 37 | private final Scorer scorer; 38 | 39 | PositionMatchScorer(PositionMatchWeight weight, LeafReaderContext context) throws IOException { 40 | super(weight); 41 | this.context = context; 42 | this.scorer = weight.weight.scorer(context); 43 | } 44 | 45 | @Override 46 | public DocIdSetIterator iterator() { 47 | return scorer.iterator(); 48 | } 49 | 50 | @Override 51 | public float getMaxScore(int upTo) throws IOException { 52 | return scorer.getMaxScore(upTo); 53 | } 54 | 55 | @Override 56 | public float score() { 57 | int doc = docID(); 58 | float totalScore = 0.0f; 59 | 60 | Set terms = new HashSet<>(); 61 | weight.getQuery().visit(QueryVisitor.termCollector(terms)); 62 | 63 | for (Term term : terms) { 64 | totalScore += scoreTerm(doc, term); 65 | } 66 | 67 | return totalScore; 68 | } 69 | 70 | Explanation explain(int docID) { 71 | List explanations = new ArrayList<>(); 72 | 73 | float totalScore = 0.0f; 74 | 75 | Set terms = new HashSet<>(); 76 | weight.getQuery().visit(QueryVisitor.termCollector(terms)); 77 | 78 | for (Term term : terms) { 79 | Explanation termExplanation = explainTerm(docID, term); 80 | explanations.add(termExplanation); 81 | totalScore += termExplanation.getValue().floatValue(); 82 | } 83 | 84 | return Explanation.match( 85 | totalScore, 86 | String.format("score(doc=%d), sum of:", docID), 87 | explanations 88 | ); 89 | } 90 | 91 | @Override 92 | public int docID() { 93 | return scorer.docID(); 94 | } 95 | 96 | private float scoreTerm(int docID, Term term) { 97 | float termScore = 0.0f; // default score 98 | int termPosition = position(docID, term); 99 | if (NOT_FOUND_POSITION != termPosition) termScore = ((float) HALF_SCORE_POSITION) / (HALF_SCORE_POSITION + termPosition); 100 | return termScore; 101 | } 102 | 103 | private Explanation explainTerm(int docID, Term term) { 104 | int termPosition = position(docID, term); 105 | if (NOT_FOUND_POSITION == termPosition) { 106 | return Explanation.noMatch( 107 | String.format("no matching terms for field=%s, term=%s", term.field(), term.text()) 108 | ); 109 | } else { 110 | float termScore = ((float) HALF_SCORE_POSITION) / (HALF_SCORE_POSITION + termPosition); 111 | String func = HALF_SCORE_POSITION + "/(" + HALF_SCORE_POSITION + "+" + termPosition + ")"; 112 | return Explanation.match( 113 | termScore, 114 | String.format("score(field=%s, term=%s, pos=%d, func=%s)", term.field(), term.text(), termPosition, func) 115 | ); 116 | } 117 | } 118 | 119 | private int position(int docID, Term term) { 120 | try { 121 | TermVectors termVectors = context.reader().termVectors(); 122 | if (termVectors == null) { 123 | return NOT_FOUND_POSITION; 124 | } 125 | 126 | Fields vectors = termVectors.get(docID); 127 | if (vectors == null) { 128 | return NOT_FOUND_POSITION; 129 | } 130 | 131 | Terms terms = vectors.terms(term.field()); 132 | if (terms == null) { 133 | return NOT_FOUND_POSITION; 134 | } 135 | 136 | TermsEnum termsEnum = terms.iterator(); 137 | if (!termsEnum.seekExact(term.bytes())) { 138 | return NOT_FOUND_POSITION; 139 | } 140 | 141 | PostingsEnum dpEnum = termsEnum.postings(null, PostingsEnum.ALL); 142 | dpEnum.nextDoc(); 143 | dpEnum.nextPosition(); 144 | BytesRef payload = dpEnum.getPayload(); 145 | if (payload == null) { 146 | return NOT_FOUND_POSITION; 147 | } 148 | 149 | return PayloadHelper.decodeInt(payload.bytes, payload.offset); 150 | } catch (UnsupportedOperationException ex) { 151 | LogManager.getLogger(this.getClass()).error("Unsupported operation, returning position = " + 152 | NOT_FOUND_POSITION + " for field = " + term.field()); 153 | return NOT_FOUND_POSITION; 154 | } catch (Exception ex) { 155 | LogManager.getLogger(this.getClass()).error("Unexpected exception, returning position = " + 156 | NOT_FOUND_POSITION + " for field = " + term.field()); 157 | return NOT_FOUND_POSITION; 158 | } 159 | } 160 | } 161 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/index/query/PositionMatchWeight.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | package org.elasticsearch.index.query; 16 | 17 | import org.apache.lucene.index.LeafReaderContext; 18 | import org.apache.lucene.index.Term; 19 | import org.apache.lucene.search.Explanation; 20 | import org.apache.lucene.search.Query; 21 | import org.apache.lucene.search.QueryVisitor; 22 | import org.apache.lucene.search.Weight; 23 | 24 | import java.io.IOException; 25 | import java.util.Set; 26 | 27 | public class PositionMatchWeight extends Weight { 28 | final Weight weight; 29 | final Query query; 30 | 31 | PositionMatchWeight(Query query, Weight weight) { 32 | super(query); 33 | this.weight = weight; 34 | this.query = query; 35 | } 36 | 37 | public void collectTerms(Set terms) { 38 | query.visit(QueryVisitor.termCollector(terms)); 39 | } 40 | 41 | @Override 42 | public Explanation explain(LeafReaderContext context, int docID) throws IOException { 43 | return scorer(context).explain(docID); 44 | } 45 | 46 | @Override 47 | public PositionMatchScorer scorer(LeafReaderContext context) throws IOException { 48 | return new PositionMatchScorer(this, context); 49 | } 50 | 51 | @Override 52 | public boolean isCacheable(LeafReaderContext context) { 53 | return false; 54 | } 55 | } 56 | -------------------------------------------------------------------------------- /src/main/java/org/elasticsearch/plugin/PositionSimilarityPlugin.java: -------------------------------------------------------------------------------- 1 | /* 2 | * Licensed under the Apache License, Version 2.0 (the "License"); 3 | * you may not use this file except in compliance with the License. 4 | * You may obtain a copy of the License at 5 | * 6 | * http://www.apache.org/licenses/LICENSE-2.0 7 | * 8 | * Unless required by applicable law or agreed to in writing, software 9 | * distributed under the License is distributed on an "AS IS" BASIS, 10 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 11 | * See the License for the specific language governing permissions and 12 | * limitations under the License. 13 | */ 14 | 15 | package org.elasticsearch.plugin; 16 | 17 | import org.elasticsearch.index.query.PositionMatchQuery; 18 | import org.elasticsearch.index.query.PositionMatchQueryBuilder; 19 | import org.elasticsearch.plugins.Plugin; 20 | import org.elasticsearch.plugins.SearchPlugin; 21 | 22 | import java.util.List; 23 | 24 | import static java.util.Collections.singletonList; 25 | 26 | public class PositionSimilarityPlugin extends Plugin implements SearchPlugin { 27 | 28 | @Override 29 | public List> getQueries() { 30 | return singletonList(new QuerySpec<>(PositionMatchQuery.NAME, PositionMatchQueryBuilder::new, PositionMatchQueryBuilder::fromXContent)); 31 | } 32 | 33 | } 34 | --------------------------------------------------------------------------------