├── LICENSE.txt ├── README.md ├── bin ├── postgres2elastic.linux └── postgres2elastic.mac └── main.go /LICENSE.txt: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## postgres2elasticsearch 2 | 3 | Handy little program to bulk insert large postgres databases into elasticsearch. It uses postgres's row_to_json function to 4 | select the table columns as JSON and upload them using the bulk insert API. It was modeled after the grest jdbc bulk loader here: https://github.com/jprante/elasticsearch-jdbc 5 | 6 | However, it waits for a response from ElasticSearch which prevents falied inserts when the ElasticSearch bulk loader queue is full. 7 | 8 | #### Requirements 9 | 10 | - Postgres 9.2 or greater (for JSON functions) 11 | 12 | #### Usage 13 | 14 | ``` 15 | $ postgres2elasticsearch [number_of_workers] 16 | ``` 17 | 18 | Sample config file: 19 | 20 | ``` 21 | { 22 | "url" : "http://localhost:9200", 23 | "index" : "cats", 24 | "type" : "house", 25 | "max_bulk_actions" : 1000, 26 | "db" : { 27 | "host" : "localhost", 28 | "port" : 5432, 29 | "user" : "postgres", 30 | "password" : "thisisapassword", 31 | "database" : "postgres", 32 | "table" : "cats" 33 | }, 34 | "mappings" : [{ 35 | "house" : { 36 | "properties" : { 37 | "name" : { 38 | "type" : "string", 39 | "index" : "not_analyzed" 40 | } 41 | } 42 | } 43 | }] 44 | } 45 | ``` 46 | 47 | #### Troubleshooting 48 | 49 | If you start to get failed insert requests, try decreasing the number of workers. Also, **max_bulk_actions** correlates to the number of inserts in a bulk request. So increasing that number might help some. However, to big of a number and the elasticsearch thread might take too long and timeout. 50 | -------------------------------------------------------------------------------- /bin/postgres2elastic.linux: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/coreycollins/postgres2elasticsearch/e2fc94cff812ba6c4f8f0bfb937950403690393d/bin/postgres2elastic.linux -------------------------------------------------------------------------------- /bin/postgres2elastic.mac: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/coreycollins/postgres2elasticsearch/e2fc94cff812ba6c4f8f0bfb937950403690393d/bin/postgres2elastic.mac -------------------------------------------------------------------------------- /main.go: -------------------------------------------------------------------------------- 1 | package main 2 | 3 | import ( 4 | "database/sql" 5 | "encoding/json" 6 | "errors" 7 | "fmt" 8 | _ "github.com/lib/pq" 9 | "gopkg.in/olivere/elastic.v2" 10 | "io/ioutil" 11 | "log" 12 | "os" 13 | "strconv" 14 | "sync" 15 | "sync/atomic" 16 | ) 17 | 18 | // Options 19 | type options struct { 20 | URI string `json:"url"` 21 | MaxBulkActions int `json:"max_bulk_actions"` 22 | MaxFetchRows int `json:"max_fetch_rows"` 23 | Timeout string `json:"timeout"` 24 | DB struct { 25 | Host string `json:"host"` 26 | Port int `json:"port"` 27 | Database string `json:"database"` 28 | User string `json:"user"` 29 | Password string `json:"password"` 30 | Table string `json:"table"` 31 | } `json:"db"` 32 | Index string `json:"index"` 33 | Type string `json:"type"` 34 | Mappings []json.RawMessage `json:"mappings"` 35 | } 36 | 37 | // Create buffered channel to send inserts through 38 | var indexQ chan string 39 | var status = make(chan int) 40 | 41 | // Global counters 42 | var succeded, failed uint64 43 | 44 | func sendBulkService(bulkService *elastic.BulkService) { 45 | trying := bulkService.NumberOfActions() 46 | if bulkResponse, err := bulkService.Do(); err != nil { 47 | atomic.AddUint64(&failed, uint64(trying)) 48 | } else { 49 | atomic.AddUint64(&succeded, uint64(len(bulkResponse.Succeeded()))) 50 | atomic.AddUint64(&failed, uint64(len(bulkResponse.Failed()))) 51 | } 52 | status <- 1 53 | } 54 | 55 | // Index worker function to insert docs 56 | func index(wg *sync.WaitGroup, opts options) { 57 | 58 | // Connect client 59 | client, err := elastic.NewClient(elastic.SetURL(opts.URI), elastic.SetSniff(false)) 60 | 61 | if err != nil { 62 | log.Fatalln(err.Error()) 63 | } 64 | 65 | // Create new bulk service request 66 | bulkService := elastic.NewBulkService(client).Index(opts.Index).Type(opts.Type).Timeout(opts.Timeout) 67 | for doc := range indexQ { 68 | 69 | //Add index to request 70 | bIndex := elastic.NewBulkIndexRequest().Index(opts.Index).OpType("create").Doc(doc) 71 | bulkService.Add(bIndex) 72 | 73 | // Send request after MaxBulkActions limit is reached 74 | if bulkService.NumberOfActions() > opts.MaxBulkActions-1 { 75 | sendBulkService(bulkService) 76 | } 77 | 78 | } 79 | 80 | // Send last indexes 81 | if bulkService.NumberOfActions() > 0 { 82 | sendBulkService(bulkService) 83 | } 84 | 85 | wg.Done() 86 | } 87 | 88 | func empty(str string) bool { 89 | return len(str) == 0 90 | } 91 | 92 | // Make sure all required options are passed 93 | func check(opts options) error { 94 | 95 | if empty(opts.Index) { 96 | return errors.New("No elastic index found in options.") 97 | } 98 | 99 | if empty(opts.Type) { 100 | return errors.New("No elastic type found in options.") 101 | } 102 | 103 | if empty(opts.URI) { 104 | return errors.New("No elastic url found in options.") 105 | } 106 | 107 | if empty(opts.DB.Host) { 108 | return errors.New("No postgres host found in options.") 109 | } 110 | 111 | if opts.DB.Port == 0 { 112 | return errors.New("No postgres dataportbase found in options.") 113 | } 114 | 115 | if empty(opts.DB.User) { 116 | return errors.New("No postgres user found in options.") 117 | } 118 | 119 | if empty(opts.DB.Database) { 120 | return errors.New("No postgres database found in options.") 121 | } 122 | 123 | if empty(opts.DB.Password) { 124 | return errors.New("No postgres password found in options.") 125 | } 126 | 127 | if empty(opts.DB.Table) { 128 | return errors.New("No table found in options.") 129 | } 130 | 131 | return nil 132 | } 133 | 134 | func print() { 135 | s := atomic.LoadUint64(&succeded) 136 | f := atomic.LoadUint64(&failed) 137 | fmt.Printf("\rSucceded: %d Failed: %d", s, f) 138 | } 139 | 140 | func setup(opts options) { 141 | // Connect client 142 | client, err := elastic.NewClient(elastic.SetURL(opts.URI), elastic.SetSniff(false)) 143 | 144 | if err != nil { 145 | log.Fatalln(err.Error()) 146 | } 147 | 148 | // Create index if does not exist 149 | fmt.Print("Checking is index exists...") 150 | exs := client.IndexExists(opts.Index) 151 | if ok, err := exs.Do(); !ok { 152 | if err != nil { 153 | log.Fatalln(err.Error()) 154 | } 155 | 156 | fmt.Print("no. Creating...") 157 | newIndex := elastic.NewIndexService(client).Index(opts.Index) 158 | _, err := newIndex.Do() 159 | if err != nil { 160 | log.Fatalln(err.Error()) 161 | } 162 | fmt.Println("done.") 163 | } else { 164 | fmt.Println("yes") 165 | } 166 | 167 | //Create mappings 168 | fmt.Print("Putting mappings...") 169 | for _, mapping := range opts.Mappings { 170 | 171 | // Send raw json from options 172 | _, err := client.PutMapping().Index(opts.Index).Type(opts.Type).BodyString(string(mapping)).Do() 173 | if err != nil { 174 | log.Fatalln(err.Error()) 175 | } 176 | } 177 | fmt.Println("done.") 178 | 179 | client.Stop() 180 | 181 | fmt.Println("\nSetup finished.") 182 | } 183 | 184 | func main() { 185 | 186 | if len(os.Args) < 2 { 187 | log.Fatalln("Usage: postgres2elasticsearch [number of workers]") 188 | } 189 | 190 | workers := 1 191 | if len(os.Args) >= 3 { 192 | var err error 193 | workers, err = strconv.Atoi(os.Args[2]) 194 | if err != nil { 195 | log.Fatalln(err.Error()) 196 | } 197 | } 198 | 199 | //Load Input File 200 | file, err := ioutil.ReadFile(os.Args[1]) 201 | if err != nil { 202 | log.Fatalln(err.Error()) 203 | } 204 | 205 | // Load options 206 | var opts options 207 | if err := json.Unmarshal(file, &opts); err != nil { 208 | log.Fatalln(err.Error()) 209 | } 210 | 211 | // Check options for required 212 | if err := check(opts); err != nil { 213 | log.Fatalln(err.Error()) 214 | } 215 | 216 | if opts.MaxBulkActions == 0 { 217 | opts.MaxBulkActions = 1000 // Default to 1000 insert actions at one time 218 | } 219 | 220 | limit := "ALL" 221 | if opts.MaxFetchRows > 0 { 222 | limit = strconv.Itoa(opts.MaxFetchRows) 223 | } 224 | 225 | db, err := sql.Open("postgres", fmt.Sprintf("host=%s port=%d dbname=%s user=%s sslmode=disable password=%s", opts.DB.Host, opts.DB.Port, opts.DB.Database, opts.DB.User, opts.DB.Password)) 226 | if err != nil { 227 | log.Fatalln(err.Error()) 228 | } 229 | 230 | // Setup index 231 | setup(opts) 232 | 233 | wg := new(sync.WaitGroup) 234 | 235 | indexQ = make(chan string, opts.MaxBulkActions*workers) 236 | 237 | for i := 0; i < workers; i++ { 238 | wg.Add(1) 239 | go index(wg, opts) 240 | } 241 | 242 | go func() { 243 | for { 244 | <-status 245 | print() 246 | } 247 | }() 248 | 249 | // Print start of progress 250 | status <- 1 251 | 252 | //Postgres go library doesn't allow dynamic table placeholders 253 | statement := fmt.Sprintf("SELECT row_to_json(t) FROM %s as t LIMIT %s", opts.DB.Table, limit) 254 | rows, err := db.Query(statement) 255 | if err != nil { 256 | log.Fatalln(err.Error()) 257 | } 258 | defer rows.Close() 259 | 260 | for rows.Next() { 261 | 262 | var doc string 263 | if err := rows.Scan(&doc); err != nil { 264 | fmt.Println(err) 265 | } 266 | 267 | indexQ <- doc 268 | 269 | } 270 | if err := rows.Err(); err != nil { 271 | log.Fatalln(err.Error()) 272 | } 273 | 274 | close(indexQ) 275 | 276 | wg.Wait() 277 | 278 | print() // Print last update 279 | fmt.Println("\n\nFinished") 280 | } 281 | --------------------------------------------------------------------------------