scalastic 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: fd3dbca7672a601bba49bc18531c66f5d4427710
-  data.tar.gz: 3669c3673f0ded567a2acec6993028195a3b2c44
+  metadata.gz: e03696369ef2695acb79cad272e8f6fedc263c37
+  data.tar.gz: 606aeeb6040d291368bf23fcb5ba0ee9fad63b6c
 SHA512:
-  metadata.gz: d5ea03aa00e7513b8c33359480d1d3e49edeaf62e5408362ed4d156666adc4573dbb89872fa3824c838570407768f65ddd0dba52cf723621d969e6ad6602aeb3
-  data.tar.gz: 46cfbf9227dc75f94e6e2ea0defa7979e8ddf55cd38f31817b047e043b979983badf578d10e098ed784f317186a8ea4162ee69e40f8a5b6743d7270a355d2b68
+  metadata.gz: 37c76201da581d93675e0a792d8f5287ccf21ed7746a344e5b7959e0e6ca383eb5f4dc6a25b9270f34aa8f96bcb46949e97f444f9c4b38a64846236b8d022f59
+  data.tar.gz: f157f7cf2226f63a34fa13e711ad81df849370986fba6f3ef077bd041fa0288462c557357a6d34fd78b6c859225cfdc99098c912390a93e4c1056f68b01be275

data/.gitignore

@@ -7,3 +7,4 @@
 /pkg/
 /spec/reports/
 /tmp/
+/*.gem

data/README.md

@@ -196,6 +196,29 @@ count = partition.search(search_type: 'count')['hits']['total']
 raise 'Some documents were not removed' unless count == 0
 ```
 
+### Deleting by query
+Scalastic partitions support delete_by_query, but because it is no longer available in Elasticsearch core, we use our own implementation which uses scan/scroll searches and bulk operations for deletion.
+```ruby
+client = Elasticsearch::Client.new
+partitions = client.partitions
+
+client.indices.create(index: 'delete_by_query')
+partitions.prepare_index(index: 'delete_by_query')
+
+p = partitions.create(index: 'delete_by_query', id: 1)
+p.index(id: 1, type: 'test')
+p.index(id: 2, type: 'test')
+p.index(id: 3, type: 'test')
+client.indices.flush(index: 'delete_by_query')
+
+p.delete_by_query(body:{query:{terms:{_id: [1,3]}}})
+client.indices.flush(index: 'delete_by_query')
+
+expected_hits = [{'_index' => 'delete_by_query', '_type' => 'test', '_id' => '2', '_score' => 1.0, '_source' => {'scalastic_partition_id' => 1}}]
+actual_hits = p.search['hits']['hits']
+raise "Unexpected results!: #{actual_hits}" unless actual_hits == expected_hits
+```
+
 ### Notes
 * Indices must be *prepared* before they can be used by Scalastic by calling "prepare" on the partitions client; doing so will create critical field mappings. Each index must be prepared only once. 
 * All hash keys in arguments must be symbols; using anything else may result in unexpected behavior.

data/lib/scalastic/partition.rb

@@ -62,6 +62,18 @@ module Scalastic
       es_client.bulk(args)
     end
 
+    def delete_by_query(args)
+      args = args.merge(index: config.search_endpoint(id), search_type: 'scan', scroll: '1m', size: 500, fields: [])
+      results = es_client.search(args)
+      loop do
+        scroll_id = results['_scroll_id']
+        results = es_client.scroll(scroll_id: scroll_id, scroll: '1m')
+        ops = results['hits']['hits'].map{|h| delete_op(h)}
+        break if ops.empty?
+        es_client.bulk(body: ops)
+      end
+    end
+
     def inspect
       "ES partition #{id}"
     end
@@ -98,5 +110,9 @@ module Scalastic
       end
       entry
     end
+
+    def delete_op(hit)
+      {delete: {_index: hit['_index'], _type: hit['_type'], _id: hit['_id']}}
+    end
   end
 end

data/lib/scalastic/version.rb

@@ -1,3 +1,3 @@
 module Scalastic
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

data/scalastic.gemspec

@@ -25,5 +25,4 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "simplecov", "~> 0.11"
 
   spec.add_dependency "elasticsearch", "~> 1.0"
-  spec.add_dependency "multi_json", "~> 1.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: scalastic
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - Aliaksei Baturytski
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-01-18 00:00:00.000000000 Z
+date: 2016-02-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -80,20 +80,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.0'
-- !ruby/object:Gem::Dependency
-  name: multi_json
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
 description: Elasticsearch alias-based partitions for scalable indexing and searching
 email:
 - abaturytski@gmail.com