Improve ECS categorization field mappings in postgresql module

- convert pipeline to yml
- event.kind
- event.category
- event.type
- related.user

Closes elastic#16177

CHANGELOG.next.asciidoc

@@ -268,6 +268,7 @@ https://github.com/elastic/beats/compare/v7.0.0-alpha2...master[Check the HEAD d
 - Enhance `elasticsearch/slowlog` fileset to handle ECS-compatible logs emitted by Elasticsearch. {issue}17715[17715] {pull}17729[17729]
 - Improve ECS categorization field mappings in misp module. {issue}16026[16026] {pull}17344[17344]
 - Added Unix stream socket support as an input source and a syslog input source. {pull}17492[17492]
+- Improve ECS categorization field mappings in postgresql module. {issue}16177[16177] {pull}17914[17914]
 
 *Heartbeat*
 

filebeat/module/postgresql/log/ingest/pipeline.yml

@@ -0,0 +1,57 @@
+description: Pipeline for parsing PostgreSQL logs.
+processors:
+- grok:
+    field: message
+    ignore_missing: true
+    patterns:
+    - '^%{DATETIME:postgresql.log.timestamp} \[%{NUMBER:process.pid:long}(-%{BASE16FLOAT:postgresql.log.core_id:long})?\]
+      ((\[%{USERNAME:user.name}\]@\[%{POSTGRESQL_DB_NAME:postgresql.log.database}\]|%{USERNAME:user.name}@%{POSTGRESQL_DB_NAME:postgresql.log.database})
+      )?%{WORD:log.level}:  (?:%{NUMBER:postgresql.log.error.code:long}|%{SPACE})(duration:
+      %{NUMBER:temp.duration:float} ms  %{POSTGRESQL_QUERY_STEP}: %{GREEDYDATA:postgresql.log.query}|:
+      %{GREEDYDATA:message}|%{GREEDYDATA:message})'
+    pattern_definitions:
+      DATETIME: '[-0-9]+ %{TIME} %{WORD:event.timezone}'
+      GREEDYDATA: |-
+        (.|
+        |	)*
+      POSTGRESQL_DB_NAME: '[a-zA-Z0-9_]+[a-zA-Z0-9_\$]*'
+      POSTGRESQL_QUERY_STEP: '%{WORD:postgresql.log.query_step}(?: <unnamed>| %{WORD:postgresql.log.query_name})?'
+- date:
+    field: postgresql.log.timestamp
+    target_field: '@timestamp'
+    formats:
+    - yyyy-MM-dd HH:mm:ss.SSS zz
+    - yyyy-MM-dd HH:mm:ss zz
+- script:
+    lang: painless
+    source: ctx.event.duration = Math.round(ctx.temp.duration * params.scale)
+    params:
+      scale: 1000000
+    if: ctx.temp?.duration != null
+- remove:
+    field: temp.duration
+    ignore_missing: true
+- set:
+    field: event.kind
+    value: event
+- append:
+    field: event.category
+    value:
+      - database
+- append:
+    field: event.type
+    value:
+      - info
+- append:
+    field: event.type
+    value:
+      - error
+    if: "ctx?.postgresql?.log?.error?.code != null && ctx.postgresql.log.error.code >= 02000"
+- append:
+    field: related.user
+    value: "{{user.name}}"
+    if: "ctx?.user?.name != null"
+on_failure:
+- set:
+    field: error.message
+    value: '{{ _ingest.on_failure_message }}'

filebeat/module/postgresql/log/manifest.yml

@@ -9,5 +9,5 @@ var:
     os.windows:
       - "c:/Program Files/PostgreSQL/*/logs/*.log*"
 
-ingest_pipeline: ingest/pipeline.json
+ingest_pipeline: ingest/pipeline.yml
 input: config/log.yml