logstash-filter-aggregate 2.7.1 → 2.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: bdbd08aff733463c2cbe5f630019f92a806b4b32ba370a725f0f4ace5892cde2
-  data.tar.gz: b543a06917606bd25b3f727266bfb0e9cb0b484fe41c7f3ebcad9203fe979c3a
+SHA1:
+  metadata.gz: 15460afa4f78789d3f4ee56ae45e06e5f31b8ef4
+  data.tar.gz: f4bd241aa7207b29366d2456d6c42cb6ecc499c3
 SHA512:
-  metadata.gz: cabfccaf07cc1f909fe58f4ed155073a8575350df4a1a7310df06d04fb88c80b0dbb97dd6f83d21f9ea696fb3a136d08731b6572a0f281c29687ffe487a48d79
-  data.tar.gz: 7b25f24e009927c2b1c73960be397aee87955847d497b048d5877c8f323ea494e6acf94b9f661d29d88c63f7fd331bcbee6eea45ee7a58a17af917f881d28da2
+  metadata.gz: 10f18942af2c7cd6f343502478d6d6d2ffc530700b9462e377770a0adbd6bb38b71c2a7debeeaba832aa0aafa9eba85acd041c35a468f2876ad61d0a51566f40
+  data.tar.gz: d6c92aa3b6bf04bfdd1be6e6b3fafbeb8b31416e20db4ee2c795d3fa20ac193db9a8422634b90df90efed88f135e5941a2f7373707b0e20be886a68a30abd8c7

data/CHANGELOG.md

@@ -1,5 +1,29 @@
+## 2.9.2
+  - bugfix: remove 'default_timeout' at pipeline level (fix #112)
+  - ci: update travis ci configuration
+
+## 2.9.1
+  - bugfix: fix inactivity timeout feature when processing old logs (PR [#103](https://github.com/logstash-plugins/logstash-filter-aggregate/pull/103), thanks @jdratlif for his contribution!)
+  - docs: fix several typos in documentation
+  - docs: enhance example 4 documentation
+  - ci: enhance plugin continuous integration
+
+## 2.9.0
+  - new feature: add ability to dynamically define a custom `timeout` or `inactivity_timeout` in `code` block (fix issues [#91](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/91) and [#92](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/92))
+  - new feature: add meta informations available in `code` block through `map_meta` variable
+  - new feature: add Logstash metrics, specific to aggregate plugin: aggregate_maps, pushed_events, task_timeouts, code_errors, timeout_code_errors
+  - new feature: validate at startup that `map_action` option equals to 'create', 'update' or 'create_or_update'
+
+## 2.8.0
+  - new feature: add 'timeout_timestamp_field' option (fix issue [#81](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/81))  
+    When set, this option lets to compute timeout based on event timestamp field (and not system time).  
+    It's particularly useful when processing old logs.
+
+## 2.7.2
+  - bugfix: fix synchronisation issue at Logstash shutdown (issue [#75](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/75))
+
 ## 2.7.1
-  - Update gemspec summary
+  - docs: update gemspec summary
 
 ## 2.7.0
  - new feature: add support for multiple pipelines (for Logstash 6.0+)  
@@ -21,10 +45,11 @@
 - docs: bump patch level for doc build
 
 ## 2.6.0
-- new feature: 'inactivity_timeout'. Events for a given `task_id` will be aggregated for as long as they keep arriving within the defined `inactivity_timeout` option - the inactivity timeout is reset each time a new event happens. On the contrary, `timeout` is never reset and happens after `timeout` seconds since aggregation map creation.
+- new feature: add 'inactivity_timeout' option.  
+  Events for a given `task_id` will be aggregated for as long as they keep arriving within the defined `inactivity_timeout` option - the inactivity timeout is reset each time a new event happens. On the contrary, `timeout` is never reset and happens after `timeout` seconds since aggregation map creation.
 
 ## 2.5.2
-- bugfix: fix 'aggregate_maps_path' load (issue #62). Re-start of Logstash died when no data were provided in 'aggregate_maps_path' file for some aggregate task_id patterns
+- bugfix: fix 'aggregate_maps_path' load (issue [#62](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/62)). Re-start of Logstash died when no data were provided in 'aggregate_maps_path' file for some aggregate task_id patterns
 - enhancement: at Logstash startup, check that 'task_id' option contains a field reference expression (else raise error)
 - docs: enhance examples
 - docs: precise that tasks are tied to their task_id pattern, even if they have same task_id value
@@ -42,7 +67,7 @@
  - breaking: need Logstash 2.4 or later  
 
 ## 2.4.0
- - new feature: You can now define timeout options per task_id pattern (#42)  
+ - new feature: You can now define timeout options per task_id pattern (fix issue [#42](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/42))  
  timeout options are : `timeout, timeout_code, push_map_as_event_on_timeout, push_previous_map_as_event, timeout_task_id_field, timeout_tags`
  - validation: a configuration error is thrown at startup if you define any timeout option on several aggregate filters for the same task_id pattern
  - breaking: if you use `aggregate_maps_path` option, storage format has changed. So you have to delete `aggregate_maps_path` file before starting Logstash
@@ -76,14 +101,14 @@
  - internal,deps: New dependency requirements for logstash-core for the 5.0 release
 
 ## 2.0.3
- - bugfix: fix issue #10 : numeric task_id is now well processed
+ - bugfix: fix issue [#10](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/10) : numeric task_id is now well processed
 
 ## 2.0.2
- - bugfix: fix issue #5 : when code call raises an exception, the error is logged and the event is tagged '_aggregateexception'. It avoids logstash crash.
+ - bugfix: fix issue [#5](https://github.com/logstash-plugins/logstash-filter-aggregate/issues/5) : when code call raises an exception, the error is logged and the event is tagged '_aggregateexception'. It avoids logstash crash.
 
 ## 2.0.0
- - internal: Plugins were updated to follow the new shutdown semantic, this mainly allows Logstash to instruct input plugins to terminate gracefully, 
-   instead of using Thread.raise on the plugins' threads. Ref: https://github.com/elastic/logstash/pull/3895
+ - internal: Plugins were updated to follow the new shutdown semantic, this mainly allows Logstash to instruct input plugins to terminate gracefully, instead of using Thread.raise on the plugins' threads.  
+   Ref: https://github.com/elastic/logstash/pull/3895
  - internal,deps: Dependency on logstash-core update to 2.0
 
 ## 0.1.3

data/LICENSE

@@ -1,13 +1,202 @@
-Copyright (c) 2012-2015 Elasticsearch <http://www.elasticsearch.org>
 
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
 
-    http://www.apache.org/licenses/LICENSE-2.0
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
 
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2020 Elastic and contributors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

data/README.md

@@ -1,6 +1,6 @@
 # Aggregate Logstash Plugin
 
-[![Travis Build Status](https://travis-ci.org/logstash-plugins/logstash-filter-aggregate.svg)](https://travis-ci.org/logstash-plugins/logstash-filter-aggregate)
+[![Travis Build Status](https://travis-ci.com/logstash-plugins/logstash-filter-aggregate.svg)](https://travis-ci.com/logstash-plugins/logstash-filter-aggregate)
 
 This is a plugin for [Logstash](https://github.com/elastic/logstash).
 

data/docs/index.asciidoc

@@ -228,7 +228,7 @@ In that case, you don't want to wait task timeout to flush aggregation map.
      aggregate {
        task_id => "%{country_name}"
        code => "
-         map['country_name'] = event.get('country_name')
+         map['country_name'] ||= event.get('country_name')
          map['towns'] ||= []
          map['towns'] << {'town_name' => event.get('town_name')}
          event.cancel()
@@ -240,8 +240,9 @@ In that case, you don't want to wait task timeout to flush aggregation map.
 ----------------------------------
 
 * The key point is that each time aggregate plugin detects a new `country_name`, it pushes previous aggregate map as a new Logstash event, and then creates a new empty map for the next country
-* When 5s timeout comes, the last aggregate map is pushed as a new event
-* Finally, initial events (which are not aggregated) are dropped because useless (thanks to `event.cancel()`)
+* When 3s timeout comes, the last aggregate map is pushed as a new event
+* Initial events (which are not aggregated) are dropped because useless (thanks to `event.cancel()`)
+* Last point: if a field is not fulfilled for every event (say "town_postcode" field), the `||=` operator will let you to push into aggregate map, the first "not null" value. Example: `map['town_postcode'] ||= event.get('town_postcode')`
 
 
 [id="plugins-{type}s-{plugin}-example5"]
@@ -249,7 +250,7 @@ In that case, you don't want to wait task timeout to flush aggregation map.
 
 Fifth use case: like example #3, there is no end event.
 
-Events keep comming for an indefinite time and you want to push the aggregation map as soon as possible after the last user interaction without waiting for the `timeout`.
+Events keep coming for an indefinite time and you want to push the aggregation map as soon as possible after the last user interaction without waiting for the `timeout`.
 
 This allows to have the aggregated events pushed closer to real time.
 
@@ -260,7 +261,7 @@ We can track a user by its ID through the events, however once the user stops in
 
 There is no specific event indicating the end of the user's interaction.
 
-The user ineraction will be considered as ended when no events for the specified user (task_id) arrive after the specified inactivity_timeout`.
+The user interaction will be considered as ended when no events for the specified user (task_id) arrive after the specified inactivity_timeout`.
 
 If the user continues interacting for longer than `timeout` seconds (since first event), the aggregation map will still be deleted and pushed as a new event when timeout occurs.
 
@@ -295,7 +296,7 @@ filter {
    code => "map['clicks'] ||= 0; map['clicks'] += 1;"
    push_map_as_event_on_timeout => true
    timeout_task_id_field => "user_id"
-   timeout => 3600 # 1 hour timeout, user activity will be considered finished one hour after the first event, even if events keep comming
+   timeout => 3600 # 1 hour timeout, user activity will be considered finished one hour after the first event, even if events keep coming
    inactivity_timeout => 300 # 5 minutes timeout, user activity will be considered finished if no new events arrive 5 minutes after the last event
    timeout_tags => ['_aggregatetimeout']
    timeout_code => "event.set('several_clicks', event.get('clicks') > 1)"
@@ -326,9 +327,9 @@ filter {
 * in the final event, you can execute a last code (for instance, add map data to final event)
 * after the final event, the map attached to task is deleted (thanks to `end_of_task => true`)
 * an aggregate map is tied to one task_id value which is tied to one task_id pattern. So if you have 2 filters with different task_id patterns, even if you have same task_id value, they won't share the same aggregate map.
-* in one filter configuration, it is recommanded to define a timeout option to protect the feature against unterminated tasks. It tells the filter to delete expired maps
+* in one filter configuration, it is recommended to define a timeout option to protect the feature against unterminated tasks. It tells the filter to delete expired maps
 * if no timeout is defined, by default, all maps older than 1800 seconds are automatically deleted
-* all timeout options have to be defined in only one aggregate filter per task_id pattern (per pipeline). Timeout options are : timeout, inactivity_timeout, timeout_code, push_map_as_event_on_timeout, push_previous_map_as_event, timeout_task_id_field, timeout_tags
+* all timeout options have to be defined in only one aggregate filter per task_id pattern (per pipeline). Timeout options are : timeout, inactivity_timeout, timeout_code, push_map_as_event_on_timeout, push_previous_map_as_event, timeout_timestamp_field, timeout_task_id_field, timeout_tags
 * if `code` execution raises an exception, the error is logged and event is tagged '_aggregateexception'
 
 
@@ -362,6 +363,7 @@ This plugin supports the following configuration options plus the <<plugins-{typ
 | <<plugins-{type}s-{plugin}-timeout_code>> |<<string,string>>|No
 | <<plugins-{type}s-{plugin}-timeout_tags>> |<<array,array>>|No
 | <<plugins-{type}s-{plugin}-timeout_task_id_field>> |<<string,string>>|No
+| <<plugins-{type}s-{plugin}-timeout_timestamp_field>> |<<string,string>>|No
 |=======================================================================
 
 Also see <<plugins-{type}s-{plugin}-common-options>> for a list of options supported by all
@@ -396,11 +398,20 @@ Example:
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-The code to execute to update map, using current event.
+The code to execute to update aggregated map, using current event.
 
-Or on the contrary, the code to execute to update event, using current map.
+Or on the contrary, the code to execute to update event, using aggregated map.
 
-You will have a 'map' variable and an 'event' variable available (that is the event itself).
+Available variables are :
+
+`event`: current Logstash event
+
+`map`: aggregated map associated to `task_id`, containing key/value pairs. Data structure is a ruby http://ruby-doc.org/core-1.9.1/Hash.html[Hash]
+
+`map_meta`: meta informations associated to aggregate map. It allows to set a custom `timeout` or `inactivity_timeout`. 
+It allows also to get `creation_timestamp`, `lastevent_timestamp` and `task_id`.
+
+When option push_map_as_event_on_timeout=true, if you set `map_meta.timeout=0` in `code` block, then aggregated map is immediately pushed as a new event.
 
 Example:
 [source,ruby]
@@ -532,7 +543,7 @@ Example:
 [source,ruby]
     filter {
       aggregate {
-        timeout_tags => ["aggregate_timeout']
+        timeout_tags => ["aggregate_timeout"]
       }
     }
 
@@ -542,13 +553,43 @@ Example:
   * Value type is <<string,string>>
   * There is no default value for this setting.
 
-This option indicates the timeout generated event's field for the "task_id" value.
-The task id will then be set into the timeout event. This can help correlate which tasks have been timed out.
-
-For example, with option `timeout_task_id_field => "my_id"` ,when timeout task id is `"12345"`, the generated timeout event will contain `'my_id' => '12345'`.
+This option indicates the timeout generated event's field where the current "task_id" value will be set.
+This can help to correlate which tasks have been timed out.
 
 By default, if this option is not set, task id value won't be set into timeout generated event.
 
+Example:
+[source,ruby]
+    filter {
+      aggregate {
+        timeout_task_id_field => "task_id"
+      }
+    }
+
+[id="plugins-{type}s-{plugin}-timeout_timestamp_field"]
+===== `timeout_timestamp_field`
+
+  * Value type is <<string,string>>
+  * There is no default value for this setting.
+
+By default, timeout is computed using system time, where Logstash is running.
+
+When this option is set, timeout is computed using event timestamp field indicated in this option. 
+It means that when a first event arrives on aggregate filter and induces a map creation, map creation time will be equal to this event timestamp. 
+Then, each time a new event arrives on aggregate filter, event timestamp is compared to map creation time to check if timeout happened.
+
+This option is particularly useful when processing old logs with option `push_map_as_event_on_timeout => true`. 
+It lets to generate aggregated events based on timeout on old logs, where system time is inappropriate.
+
+Warning : so that this option works fine, it must be set on first aggregate filter.
+
+Example:
+[source,ruby]
+    filter {
+      aggregate {
+        timeout_timestamp_field => "@timestamp"
+      }
+    }
 
 
 [id="plugins-{type}s-{plugin}-common-options"]

data/lib/logstash/filters/aggregate.rb

@@ -20,7 +20,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
 
   config :code, :validate => :string, :required => true
 
-  config :map_action, :validate => :string, :default => "create_or_update"
+  config :map_action, :validate => ["create", "update", "create_or_update"], :default => "create_or_update"
 
   config :end_of_task, :validate => :boolean, :default => false
 
@@ -36,6 +36,8 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
 
   config :push_previous_map_as_event, :validate => :boolean, :required => false, :default => false
 
+  config :timeout_timestamp_field, :validate => :string, :required => false
+
   config :timeout_task_id_field, :validate => :string, :required => false
 
   config :timeout_tags, :validate => :array, :required => false, :default => []
@@ -44,11 +46,13 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
   # ################## #
   # INSTANCE VARIABLES #
   # ################## #
-  
+
 
   # pointer to current pipeline context
   attr_accessor :current_pipeline
 
+  # boolean indicating if expired maps should be checked on every flush call (typically because custom timeout has beeen set on a map)
+  attr_accessor :check_expired_maps_on_every_flush
 
   # ################ #
   # STATIC VARIABLES #
@@ -57,7 +61,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
 
   # Default timeout (in seconds) when not defined in plugin configuration
   DEFAULT_TIMEOUT = 1800
-  
+
   # Store all shared aggregate attributes per pipeline id
   @@pipelines = {}
 
@@ -77,9 +81,9 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     if !@task_id.match(/%\{.+\}/)
       raise LogStash::ConfigurationError, "Aggregate plugin: task_id pattern '#{@task_id}' must contain a dynamic expression like '%{field}'"
     end
-    
+
     # process lambda expression to call in each filter call
-    eval("@codeblock = lambda { |event, map| #{@code} }", binding, "(aggregate filter code)")
+    eval("@codeblock = lambda { |event, map, map_meta| #{@code} }", binding, "(aggregate filter code)")
 
     # process lambda expression to call in the timeout case or previous event case
     if @timeout_code
@@ -87,7 +91,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     end
 
     # init pipeline context
-    @@pipelines[pipeline_id] ||= LogStash::Filters::Aggregate::Pipeline.new();
+    @@pipelines[pipeline_id] ||= LogStash::Filters::Aggregate::Pipeline.new()
     @current_pipeline = @@pipelines[pipeline_id]
 
     @current_pipeline.mutex.synchronize do
@@ -102,24 +106,18 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
         @logger.debug("Aggregate timeout for '#{@task_id}' pattern: #{@timeout} seconds")
       end
 
-      # timeout management : define default_timeout
-      if !@timeout.nil? && (@current_pipeline.default_timeout.nil? || @timeout < @current_pipeline.default_timeout)
-        @current_pipeline.default_timeout = @timeout
-        @logger.debug("Aggregate default timeout: #{@timeout} seconds")
-      end
-
       # inactivity timeout management: make sure it is lower than timeout
-      if !@inactivity_timeout.nil? && ((!@timeout.nil? && @inactivity_timeout > @timeout) || (!@current_pipeline.default_timeout.nil? && @inactivity_timeout > @current_pipeline.default_timeout))
-        raise LogStash::ConfigurationError, "Aggregate plugin: For task_id pattern #{@task_id}, inactivity_timeout must be lower than timeout"
+      if @inactivity_timeout && ((@timeout && @inactivity_timeout > @timeout) || (@timeout.nil? && @inactivity_timeout > DEFAULT_TIMEOUT))
+        raise LogStash::ConfigurationError, "Aggregate plugin: For task_id pattern #{@task_id}, inactivity_timeout (#{@inactivity_timeout}) must be lower than timeout (#{@timeout})"
       end
 
       # reinit pipeline_close_instance (if necessary)
-      if !@current_pipeline.aggregate_maps_path_set && !@current_pipeline.pipeline_close_instance.nil?
+      if !@current_pipeline.aggregate_maps_path_set && @current_pipeline.pipeline_close_instance
         @current_pipeline.pipeline_close_instance = nil
       end
 
       # check if aggregate_maps_path option has already been set on another instance else set @current_pipeline.aggregate_maps_path_set
-      if !@aggregate_maps_path.nil?
+      if @aggregate_maps_path
         if @current_pipeline.aggregate_maps_path_set
           @current_pipeline.aggregate_maps_path_set = false
           raise LogStash::ConfigurationError, "Aggregate plugin: Option 'aggregate_maps_path' must be set on only one aggregate filter"
@@ -130,7 +128,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
       end
 
       # load aggregate maps from file (if option defined)
-      if !@aggregate_maps_path.nil? && File.exist?(@aggregate_maps_path)
+      if @aggregate_maps_path && File.exist?(@aggregate_maps_path)
         File.open(@aggregate_maps_path, "r") { |from_file| @current_pipeline.aggregate_maps.merge!(Marshal.load(from_file)) }
         File.delete(@aggregate_maps_path)
         @logger.info("Aggregate maps loaded from : #{@aggregate_maps_path}")
@@ -138,8 +136,8 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
 
       # init aggregate_maps
       @current_pipeline.aggregate_maps[@task_id] ||= {}
-      
-      
+      update_aggregate_maps_metric()
+
     end
   end
 
@@ -156,7 +154,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
       # store aggregate maps to file (if option defined)
       @current_pipeline.mutex.synchronize do
         @current_pipeline.aggregate_maps.delete_if { |key, value| value.empty? }
-        if !@aggregate_maps_path.nil? && !@current_pipeline.aggregate_maps.empty?
+        if @aggregate_maps_path && !@current_pipeline.aggregate_maps.empty?
           File.open(@aggregate_maps_path, "w"){ |to_file| Marshal.dump(@current_pipeline.aggregate_maps, to_file) }
           @logger.info("Aggregate maps stored to : #{@aggregate_maps_path}")
         end
@@ -182,28 +180,40 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     # protect aggregate_maps against concurrent access, using a mutex
     @current_pipeline.mutex.synchronize do
 
+      # if timeout is based on event timestamp, check if task_id map is expired and should be removed
+      if @timeout_timestamp_field
+        event_to_yield = remove_expired_map_based_on_event_timestamp(task_id, event)
+      end
+
       # retrieve the current aggregate map
       aggregate_maps_element = @current_pipeline.aggregate_maps[@task_id][task_id]
 
-
-      # create aggregate map, if it doesn't exist
+      # case where aggregate map isn't already created
       if aggregate_maps_element.nil?
         return if @map_action == "update"
+
         # create new event from previous map, if @push_previous_map_as_event is enabled
         if @push_previous_map_as_event && !@current_pipeline.aggregate_maps[@task_id].empty?
           event_to_yield = extract_previous_map_as_event()
         end
-        aggregate_maps_element = LogStash::Filters::Aggregate::Element.new(Time.now);
+
+        # create aggregate map
+        creation_timestamp = reference_timestamp(event)
+        aggregate_maps_element = LogStash::Filters::Aggregate::Element.new(creation_timestamp, task_id)
         @current_pipeline.aggregate_maps[@task_id][task_id] = aggregate_maps_element
+        update_aggregate_maps_metric()
       else
         return if @map_action == "create"
       end
-      map = aggregate_maps_element.map
+
       # update last event timestamp
-      aggregate_maps_element.lastevent_timestamp = Time.now
+      aggregate_maps_element.lastevent_timestamp = reference_timestamp(event)
+      aggregate_maps_element.difference_from_lastevent_to_now = (Time.now - aggregate_maps_element.lastevent_timestamp).to_i
+
       # execute the code to read/update map and event
+      map = aggregate_maps_element.map
       begin
-        @codeblock.call(event, map)
+        @codeblock.call(event, map, aggregate_maps_element)
         @logger.debug("Aggregate successful filter code execution", :code => @code)
         noError = true
       rescue => exception
@@ -213,10 +223,17 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
                       :map => map,
                       :event_data => event.to_hash_with_metadata)
         event.tag("_aggregateexception")
+        metric.increment(:code_errors)
       end
 
       # delete the map if task is ended
       @current_pipeline.aggregate_maps[@task_id].delete(task_id) if @end_of_task
+      update_aggregate_maps_metric()
+
+      # process custom timeout set by code block
+      if (aggregate_maps_element.timeout || aggregate_maps_element.inactivity_timeout)
+        event_to_yield = process_map_timeout(aggregate_maps_element)
+      end
 
     end
 
@@ -224,8 +241,26 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     filter_matched(event) if noError
 
     # yield previous map as new event if set
-    yield event_to_yield unless event_to_yield.nil?
+    yield event_to_yield if event_to_yield
+  end
 
+  # Process a custom timeout defined in aggregate map element
+  # Returns an event to yield if timeout=0 and push_map_as_event_on_timeout=true
+  def process_map_timeout(element)
+    event_to_yield = nil
+    init_pipeline_timeout_management()
+    if (element.timeout == 0 || element.inactivity_timeout == 0)
+      @current_pipeline.aggregate_maps[@task_id].delete(element.task_id)
+      if @current_pipeline.flush_instance_map[@task_id].push_map_as_event_on_timeout
+        event_to_yield = create_timeout_event(element.map, element.task_id)
+      end
+      @logger.debug("Aggregate remove expired map with task_id=#{element.task_id} and custom timeout=0")
+      metric.increment(:task_timeouts)
+      update_aggregate_maps_metric()
+    else
+      @current_pipeline.flush_instance_map[@task_id].check_expired_maps_on_every_flush ||= true
+    end
+    return event_to_yield
   end
 
   # Create a new event from the aggregation_map and the corresponding task_id
@@ -245,7 +280,8 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
 
     LogStash::Util::Decorators.add_tags(@timeout_tags, event_to_yield, "filters/#{self.class.name}")
 
-    # Call code block if available
+
+    # Call timeout code block if available
     if @timeout_code
       begin
         @timeout_codeblock.call(event_to_yield)
@@ -255,9 +291,12 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
                       :timeout_code => @timeout_code,
                       :timeout_event_data => event_to_yield.to_hash_with_metadata)
         event_to_yield.tag("_aggregateexception")
+        metric.increment(:timeout_code_errors)
       end
     end
 
+    metric.increment(:pushed_events)
+
     return event_to_yield
   end
 
@@ -266,6 +305,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     previous_entry = @current_pipeline.aggregate_maps[@task_id].shift()
     previous_task_id = previous_entry[0]
     previous_map = previous_entry[1].map
+    update_aggregate_maps_metric()
     return create_timeout_event(previous_map, previous_task_id)
   end
 
@@ -277,31 +317,23 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
   # This method is invoked by LogStash every 5 seconds.
   def flush(options = {})
 
-    @logger.debug("Aggregate flush call with #{options}")
+    @logger.trace("Aggregate flush call with #{options}")
 
-    # Protection against no timeout defined by Logstash conf : define a default eviction instance with timeout = DEFAULT_TIMEOUT seconds
-    if @current_pipeline.default_timeout.nil?
-      @current_pipeline.default_timeout = DEFAULT_TIMEOUT
-    end
-    if !@current_pipeline.flush_instance_map.has_key?(@task_id)
-      @current_pipeline.flush_instance_map[@task_id] = self
-      @timeout = @current_pipeline.default_timeout
-    elsif @current_pipeline.flush_instance_map[@task_id].timeout.nil?
-      @current_pipeline.flush_instance_map[@task_id].timeout = @current_pipeline.default_timeout
-    end
-
-    if @current_pipeline.flush_instance_map[@task_id].inactivity_timeout.nil?
-      @current_pipeline.flush_instance_map[@task_id].inactivity_timeout = @current_pipeline.flush_instance_map[@task_id].timeout
-    end
-
-    # Launch timeout management only every interval of (@inactivity_timeout / 2) seconds or at Logstash shutdown
-    if @current_pipeline.flush_instance_map[@task_id] == self && !@current_pipeline.aggregate_maps[@task_id].nil? && (!@current_pipeline.last_flush_timestamp_map.has_key?(@task_id) || Time.now > @current_pipeline.last_flush_timestamp_map[@task_id] + @inactivity_timeout / 2 || options[:final])
+    # init flush/timeout properties for current pipeline
+    init_pipeline_timeout_management()
+    
+    # launch timeout management only every interval of (@inactivity_timeout / 2) seconds or at Logstash shutdown
+    if @current_pipeline.flush_instance_map[@task_id] == self && @current_pipeline.aggregate_maps[@task_id] && (!@current_pipeline.last_flush_timestamp_map.has_key?(@task_id) || Time.now > @current_pipeline.last_flush_timestamp_map[@task_id] + @inactivity_timeout / 2 || options[:final] || @check_expired_maps_on_every_flush)
       events_to_flush = remove_expired_maps()
 
       # at Logstash shutdown, if push_previous_map_as_event is enabled, it's important to force flush (particularly for jdbc input plugin)
-      if options[:final] && @push_previous_map_as_event && !@current_pipeline.aggregate_maps[@task_id].empty?
-        events_to_flush << extract_previous_map_as_event()
+      @current_pipeline.mutex.synchronize do
+        if options[:final] && @push_previous_map_as_event && !@current_pipeline.aggregate_maps[@task_id].empty?
+          events_to_flush << extract_previous_map_as_event()
+        end
       end
+      
+      update_aggregate_maps_metric()
 
       # tag flushed events, indicating "final flush" special event
       if options[:final]
@@ -316,35 +348,92 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
     else
       return []
     end
-
   end
+  
+  # init flush/timeout properties for current pipeline
+  def init_pipeline_timeout_management()
+    
+    # Define default flush instance that manages timeout (if not defined by user)
+    if !@current_pipeline.flush_instance_map.has_key?(@task_id)
+      @current_pipeline.flush_instance_map[@task_id] = self
+    end
 
+    # Define timeout and inactivity_timeout (if not defined by user)
+    if @current_pipeline.flush_instance_map[@task_id] == self
+      if @timeout.nil?
+        @timeout = DEFAULT_TIMEOUT
+        @logger.debug("Aggregate timeout for '#{@task_id}' pattern: #{@timeout} seconds (default value)")
+      end
+      if @inactivity_timeout.nil?
+        @inactivity_timeout = @timeout
+      end
+    end
+
+  end
 
   # Remove the expired Aggregate maps from @current_pipeline.aggregate_maps if they are older than timeout or if no new event has been received since inactivity_timeout.
   # If @push_previous_map_as_event option is set, or @push_map_as_event_on_timeout is set, expired maps are returned as new events to be flushed to Logstash pipeline.
   def remove_expired_maps()
     events_to_flush = []
-    min_timestamp = Time.now - @timeout
-    min_inactivity_timestamp = Time.now - @inactivity_timeout
+    default_min_timestamp = Time.now - @timeout
+    default_min_inactivity_timestamp = Time.now - @inactivity_timeout
 
     @current_pipeline.mutex.synchronize do
 
       @logger.debug("Aggregate remove_expired_maps call with '#{@task_id}' pattern and #{@current_pipeline.aggregate_maps[@task_id].length} maps")
 
       @current_pipeline.aggregate_maps[@task_id].delete_if do |key, element|
-        if element.creation_timestamp < min_timestamp || element.lastevent_timestamp < min_inactivity_timestamp
+        min_timestamp = element.timeout ? Time.now - element.timeout : default_min_timestamp
+        min_inactivity_timestamp = element.inactivity_timeout ? Time.now - element.inactivity_timeout : default_min_inactivity_timestamp
+        if element.creation_timestamp + element.difference_from_creation_to_now < min_timestamp || element.lastevent_timestamp + element.difference_from_lastevent_to_now < min_inactivity_timestamp
           if @push_previous_map_as_event || @push_map_as_event_on_timeout
             events_to_flush << create_timeout_event(element.map, key)
           end
+          @logger.debug("Aggregate remove expired map with task_id=#{key}")
+          metric.increment(:task_timeouts)
           next true
         end
         next false
       end
     end
+    
+    # disable check_expired_maps_on_every_flush if there is not anymore maps
+    if @current_pipeline.aggregate_maps[@task_id].length == 0 && @check_expired_maps_on_every_flush
+      @check_expired_maps_on_every_flush = nil
+    end
 
     return events_to_flush
   end
 
+  # Remove the expired Aggregate map associated to task_id if it is older than timeout or if no new event has been received since inactivity_timeout (relative to current event timestamp).
+  # If @push_previous_map_as_event option is set, or @push_map_as_event_on_timeout is set, expired map is returned as new event to be flushed to Logstash pipeline.
+  def remove_expired_map_based_on_event_timestamp(task_id, event)
+
+    @logger.debug("Aggregate remove_expired_map_based_on_event_timestamp call with task_id : '#{@task_id}'")
+
+    # get aggregate map element
+    element = @current_pipeline.aggregate_maps[@task_id][task_id]
+    return nil if element.nil?
+
+    init_pipeline_timeout_management()
+
+    event_to_flush = nil
+    event_timestamp = reference_timestamp(event)
+    min_timestamp = element.timeout ? event_timestamp - element.timeout : event_timestamp - @timeout
+    min_inactivity_timestamp = element.inactivity_timeout ? event_timestamp - element.inactivity_timeout : event_timestamp - @inactivity_timeout
+
+    if element.creation_timestamp < min_timestamp || element.lastevent_timestamp < min_inactivity_timestamp
+      if @push_previous_map_as_event || @push_map_as_event_on_timeout
+        event_to_flush = create_timeout_event(element.map, task_id)
+      end
+      @current_pipeline.aggregate_maps[@task_id].delete(task_id)
+      @logger.debug("Aggregate remove expired map with task_id=#{task_id}")
+      metric.increment(:task_timeouts)
+    end
+
+    return event_to_flush
+  end
+
   # return if this filter instance has any timeout option enabled in logstash configuration
   def has_timeout_options?()
     return (
@@ -353,6 +442,7 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
       timeout_code ||
       push_map_as_event_on_timeout ||
       push_previous_map_as_event ||
+      timeout_timestamp_field ||
       timeout_task_id_field ||
       !timeout_tags.empty?
     )
@@ -366,17 +456,32 @@ class LogStash::Filters::Aggregate < LogStash::Filters::Base
       "timeout_code",
       "push_map_as_event_on_timeout",
       "push_previous_map_as_event",
+      "timeout_timestamp_field",
       "timeout_task_id_field",
       "timeout_tags"
     ].join(", ")
   end
-  
+
   # return current pipeline id
   def pipeline_id()
     if @execution_context
       return @execution_context.pipeline_id
     else
-      return pipeline_id = "main"
+      return "main"
+    end
+  end
+
+  # compute and return "reference" timestamp to compute timeout :
+  # by default "system current time" or event timestamp if timeout_timestamp_field option is defined
+  def reference_timestamp(event)
+    return (@timeout_timestamp_field) ? event.get(@timeout_timestamp_field).time : Time.now
+  end
+
+  # update "aggregate_maps" metric, with aggregate maps count associated to configured taskid pattern 
+  def update_aggregate_maps_metric()
+    aggregate_maps = @current_pipeline.aggregate_maps[@task_id]
+    if aggregate_maps
+      metric.gauge(:aggregate_maps, aggregate_maps.length)
     end
   end
 
@@ -385,40 +490,42 @@ end # class LogStash::Filters::Aggregate
 # Element of "aggregate_maps"
 class LogStash::Filters::Aggregate::Element
 
-  attr_accessor :creation_timestamp, :lastevent_timestamp, :map
+  attr_accessor :creation_timestamp, :lastevent_timestamp, :difference_from_creation_to_now, :difference_from_lastevent_to_now, :timeout, :inactivity_timeout, :task_id, :map
 
-  def initialize(creation_timestamp)
+  def initialize(creation_timestamp, task_id)
     @creation_timestamp = creation_timestamp
-    @lastevent_timestamp = creation_timestamp
+    @lastevent_timestamp = creation_timestamp    
+    @difference_from_creation_to_now = (Time.now - creation_timestamp).to_i
+    @difference_from_lastevent_to_now = @difference_from_creation_to_now
+    @timeout = nil
+    @inactivity_timeout = nil
+    @task_id = task_id
     @map = {}
   end
 end
 
 # shared aggregate attributes for each pipeline
 class LogStash::Filters::Aggregate::Pipeline
-  
-  attr_accessor :aggregate_maps, :mutex, :default_timeout, :flush_instance_map, :last_flush_timestamp_map, :aggregate_maps_path_set, :pipeline_close_instance
+
+  attr_accessor :aggregate_maps, :mutex, :flush_instance_map, :last_flush_timestamp_map, :aggregate_maps_path_set, :pipeline_close_instance
 
   def initialize()
     # Stores all aggregate maps, per task_id pattern, then per task_id value
     @aggregate_maps = {}
-  
+
     # Mutex used to synchronize access to 'aggregate_maps'
     @mutex = Mutex.new
-  
-    # Default timeout for task_id patterns where timeout is not defined in Logstash filter configuration
-    @default_timeout = nil
-  
+
     # For each "task_id" pattern, defines which Aggregate instance will process flush() call, processing expired Aggregate elements (older than timeout)
     # For each entry, key is "task_id pattern" and value is "aggregate instance"
     @flush_instance_map = {}
-  
+
     # last time where timeout management in flush() method was launched, per "task_id" pattern
     @last_flush_timestamp_map = {}
-  
+
     # flag indicating if aggregate_maps_path option has been already set on one aggregate instance
     @aggregate_maps_path_set = false
-  
+
     # defines which Aggregate instance will close Aggregate variables associated to current pipeline
     @pipeline_close_instance = nil
   end

data/logstash-filter-aggregate.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name = 'logstash-filter-aggregate'
-  s.version         = '2.7.1'
+  s.version         = '2.9.2'
   s.licenses = ['Apache License (2.0)']
   s.summary = "Aggregates information from several events originating with a single task"
   s.description = 'This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program'

data/spec/filters/aggregate_spec.rb

@@ -163,6 +163,7 @@ describe LogStash::Filters::Aggregate do
     describe "no timeout defined in none filter" do
       it "defines a default timeout on a default filter" do
         reset_timeout_management()
+        @end_filter.timeout = nil
         expect(taskid_eviction_instance).to be_nil
         @end_filter.flush()
         expect(taskid_eviction_instance).to eq(@end_filter)
@@ -332,7 +333,10 @@ describe LogStash::Filters::Aggregate do
       it "should push previous map as new event" do
         push_filter = setup_filter({ "task_id" => "%{ppm_id}", "code" => "map['ppm_id'] = event.get('ppm_id')", "push_previous_map_as_event" => true, "timeout" => 5, "timeout_task_id_field" => "timeout_task_id_field" })
         push_filter.filter(event({"ppm_id" => "1"})) { |yield_event| fail "task 1 shouldn't have yield event" }
-        push_filter.filter(event({"ppm_id" => "2"})) { |yield_event| expect(yield_event.get("ppm_id")).to eq("1") ; expect(yield_event.get("timeout_task_id_field")).to eq("1") }
+        push_filter.filter(event({"ppm_id" => "2"})) do |yield_event| 
+          expect(yield_event.get("ppm_id")).to eq("1")
+          expect(yield_event.get("timeout_task_id_field")).to eq("1")
+        end
         expect(aggregate_maps["%{ppm_id}"].size).to eq(1)
       end
     end
@@ -367,5 +371,53 @@ describe LogStash::Filters::Aggregate do
     end
   end
 
+  context "timeout_timestamp_field option is defined, " do
+    describe "when 3 old events arrive, " do
+      it "should push a new aggregated event using timeout based on events timestamp" do
+        agg_filter = setup_filter({ "task_id" => "%{ppm_id}", "code" => "map['sql_duration'] ||= 0; map['sql_duration'] += event.get('duration')", "timeout_timestamp_field" => "@timestamp", "push_map_as_event_on_timeout" => true, "timeout" => 120 })
+        agg_filter.filter(event({"ppm_id" => "1", "duration" => 2, "@timestamp" => timestamp("2018-01-31T00:00:00Z")})) { |yield_event| fail "it shouldn't have yield event" }
+        agg_filter.filter(event({"ppm_id" => "1", "duration" => 3, "@timestamp" => timestamp("2018-01-31T00:00:01Z")})) { |yield_event| fail "it shouldn't have yield event" }
+        events_to_flush = agg_filter.flush()
+        expect(events_to_flush).to be_empty
+        agg_filter.filter(event({"ppm_id" => "1", "duration" => 4, "@timestamp" => timestamp("2018-01-31T00:05:00Z")})) do |yield_event| 
+          expect(yield_event).not_to be_nil
+          expect(yield_event.get("sql_duration")).to eq(5)
+        end
+        expect(aggregate_maps["%{ppm_id}"].size).to eq(1)
+        expect(aggregate_maps["%{ppm_id}"]["1"].map["sql_duration"]).to eq(4)
+      end
+    end
+  end
+
+  context "custom timeout on map_meta, " do
+    describe "when map_meta.timeout=0, " do
+      it "should push a new aggregated event immediately" do
+        agg_filter = setup_filter({ "task_id" => "%{ppm_id}", "code" => "map['sql_duration'] = 2; map_meta.timeout = 0", "push_map_as_event_on_timeout" => true, "timeout" => 120 })
+        agg_filter.filter(event({"ppm_id" => "1"})) do |yield_event| 
+          expect(yield_event).not_to be_nil
+          expect(yield_event.get("sql_duration")).to eq(2)
+        end
+        expect(aggregate_maps["%{ppm_id}"]).to be_empty
+      end
+    end
+    describe "when map_meta.timeout=0 and push_map_as_event_on_timeout=false, " do
+      it "should just remove expired map and not push an aggregated event" do
+        agg_filter = setup_filter({ "task_id" => "%{ppm_id}", "code" => "map_meta.timeout = 0", "push_map_as_event_on_timeout" => false, "timeout" => 120 })
+        agg_filter.filter(event({"ppm_id" => "1"}))  { |yield_event| fail "it shouldn't have yield event" } 
+        expect(aggregate_maps["%{ppm_id}"]).to be_empty
+      end
+    end
+    describe "when map_meta.inactivity_timeout=1, " do
+      it "should push a new aggregated event at next flush call" do
+        agg_filter = setup_filter({ "task_id" => "%{ppm_id}", "code" => "map['sql_duration'] = 2; map_meta.inactivity_timeout = 1", "push_map_as_event_on_timeout" => true, "timeout" => 120 })
+        agg_filter.filter(event({"ppm_id" => "1"})) { |yield_event| fail "it shouldn't have yield event" }
+        expect(aggregate_maps["%{ppm_id}"].size).to eq(1)
+        sleep(2)
+        events_to_flush = agg_filter.flush()
+        expect(events_to_flush.size).to eq(1)
+        expect(aggregate_maps["%{ppm_id}"]).to be_empty
+      end
+    end
+  end
 
 end

data/spec/filters/aggregate_spec_helper.rb

@@ -5,6 +5,10 @@ def event(data = {})
 	LogStash::Event.new(data)
 end
 
+def timestamp(iso8601)
+  LogStash::Timestamp.new(iso8601)
+end
+
 def start_event(data = {})
 	data["logger"] = "TASK_START"
 	event(data)
@@ -58,7 +62,6 @@ def aggregate_maps_path_set()
 end
 
 def reset_timeout_management()
-  current_pipeline().default_timeout = nil
   current_pipeline().flush_instance_map.clear()
   current_pipeline().last_flush_timestamp_map.clear()
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: logstash-filter-aggregate
 version: !ruby/object:Gem::Version
-  version: 2.7.1
+  version: 2.9.2
 platform: ruby
 authors:
 - Elastic
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-11-07 00:00:00.000000000 Z
+date: 2021-04-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
@@ -45,9 +45,7 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-description: This gem is a Logstash plugin required to be installed on top of the
-  Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This
-  gem is not a stand-alone program
+description: This gem is a Logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/logstash-plugin install gemname. This gem is not a stand-alone program
 email: info@elastic.co
 executables: []
 extensions: []
@@ -87,7 +85,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.6.11
+rubygems_version: 2.4.8
 signing_key:
 specification_version: 4
 summary: Aggregates information from several events originating with a single task