fix(filters): Azure Event Hub normalization and rule contracts

filters/audits/azure.md

@@ -0,0 +1,40 @@
+# Azure Event Hub normalization and rule review
+
+Fix SDK configuration and field meanings; normalize result precedence, IPs, severity and HTTP counters.
+
+This draft targets UTMStack `v11`. It contains 1 filter changes
+and 0 rule changes for this technology only. Review covered
+1 filter configurations and 46 matching shipped rule files.
+Unchanged rules are listed in the regression manifest; they are not duplicated in the diff.
+
+## Contract and validation
+
+- Compared exact standard names/types with go-sdk v1.1.31 and the supplied UTMStack dictionaries.
+- Checked documented pipeline ordering, rename/move behavior, open vendor log fields,
+  event-side versus alert-side fields, and surviving fields used by affected rule predicates/history/grouping.
+- Strict SDK configuration decoding and actual CEL compilation pass for this scope.
+- 11 synthetic normalization cases pass, including SDK Event conversion and any
+  trigger predicate assertions recorded in the manifest.
+- The scoped alerts module tests and `git diff --check` pass with the shared contract runner applied.
+
+The shared alert-contract PR supplies the reusable Go runner for the manifest in
+`plugins/alerts/testdata/filter-contracts/azure.json`. Apply that support before running `go test ./...` in `plugins/alerts`.
+
+The model starts from synthetic extraction results. It does not run complex grok,
+JSON/KV/XML/CSV extraction, time conversion, dynamic plugins, historical OpenSearch
+queries, or the closed EventProcessor. Raw vendor logs and resulting alerts must
+still be checked in staging before rollout. No customer false-positive reduction
+has been measured and no production rollout is included.
+
+
+
+## References
+
+- [SDK schema](https://github.com/threatwinds/go-sdk/blob/v1.1.31/plugins/plugins.proto)
+- [Filter steps](https://github.com/threatwinds/go-sdk/wiki/Filter-Steps-Reference)
+- [Standard event schema](https://github.com/threatwinds/go-sdk/wiki/Standard-Event-Schema)
+- [Rule implementation](https://github.com/threatwinds/go-sdk/wiki/Implementing-Rules)
+
+`afterEvents`, empty noncapturing grok names, supported numeric strings, and custom
+`log.*` fields are accepted. Existing textual protocol casing and vendor action names
+are preserved unless a concrete consumer mismatch requires correction.

filters/azure/azure-eventhub.yml

@@ -7,7 +7,7 @@
 # 4- https://learn.microsoft.com/en-us/azure/event-grid/system-topics
 #
 pipeline:
-  - dataTypes: azure
+  - dataTypes: [azure]
     steps:
       - json:
           source: raw
@@ -17,13 +17,13 @@ pipeline:
       # .......................................................................#
       - rename:
           from:
-            - log.ResponseBodySize
-          to: origin.bytesSent
+          - log.ResponseBodySize
+          to: origin.bytesReceived
 
       - rename:
           from:
-            - log.ResponseHeaderSize
-          to: origin.bytesReceived
+          - log.ResponseHeaderSize
+          to: log.responseHeaderSize
 
       - rename:
           from:
@@ -32,8 +32,8 @@ pipeline:
 
       - rename:
           from:
-            - log.AccountName
-          to: origin.host
+          - log.AccountName
+          to: log.accountName
 
       - rename:
           from:
@@ -47,13 +47,13 @@ pipeline:
 
       - rename:
           from:
-            - log.StatusText
-          to: connectionStatus
+          - log.StatusText
+          to: log.statusText
 
       - rename:
           from:
-            - log.Location
-          to: origin.geolocation.country
+          - log.Location
+          to: log.location
 
       - rename:
           from:
@@ -795,23 +795,31 @@ pipeline:
             - log.properties.upstreamSourcePort
           to: log.propertiesUpstreamSourcePort
 
+      # Common Azure resource-log result (kept under log for existing consumers).
+      - grok:
+          source: log.resultType
+          patterns:
+          - fieldName: log.vendorActionResult
+            pattern: '{{.greedy}}'
+          where: exists("log.resultType")
+
       - rename:
           from:
-            - log.properties.result
-          to: actionResult
-          where: '!regexMatch("log.properties.result", "(?i)\b(?:denied|blocked|failed)\b")'
+          - log.properties.result
+          to: log.vendorActionResult
+          where: '!exists("log.vendorActionResult") && exists("log.properties.result")'
 
       - rename:
           from:
-            - log.Properties.Result
-          to: actionResult
-          where: '!regexMatch("log.properties.result", "(?i)\b(?:denied|blocked|failed)\b")'
+          - log.Properties.Result
+          to: log.vendorActionResult
+          where: '!exists("log.vendorActionResult") && exists("log.Properties.Result")'
 
       - rename:
           from:
-            - log.properties.resultType
-          to: actionResult
-          where: '!regexMatch("log.properties.result", "(?i)\b(?:denied|blocked|failed)\b")'
+          - log.properties.resultType
+          to: log.vendorActionResult
+          where: '!exists("log.vendorActionResult") && exists("log.properties.resultType")'
 
       - rename:
           from:
@@ -984,10 +992,10 @@ pipeline:
           where: '!exists("actionResult") && equalsIgnoreCase("log.data.status", "Succeeded")'
 
       - add:
-          function: 'string'
+          function: string
           params:
             key: actionResult
-            value: 'failed'
+            value: failure
           where: '!exists("actionResult") && equalsIgnoreCase("log.data.status", "Failed")'
 
       - add:
@@ -998,25 +1006,19 @@ pipeline:
           where: '!exists("actionResult") && endsWith("log.eventGridEventType", "Success")'
 
       - add:
-          function: 'string'
+          function: string
           params:
             key: actionResult
-            value: 'failed'
+            value: failure
           where: '!exists("actionResult") && endsWith("log.eventGridEventType", "Failure")'
 
-      - add:
-          function: 'string'
-          params:
-            key: actionResult
-            value: 'blocked'
-          where: '!exists("actionResult") && endsWith("log.eventGridEventType", "Cancel")'
 
       - add:
-          function: 'string'
+          function: string
           params:
             key: severity
-            value: 'medium'
-          where: '!exists("severity") && oneOf("actionResult", ["failed", "blocked"])'
+            value: warning
+          where: '!exists("severity") && oneOf("actionResult", ["failure", "denied"])'
 
       - rename:
           from:
@@ -1046,46 +1048,46 @@ pipeline:
 
       # Adding action result
       - add:
-          function: 'string'
+          function: string
           params:
             key: actionResult
-            value: 'denied'
-          where: regexMatch("log.properties.result", "(?i)\bdenied\b")
+            value: denied
+          where: regexMatch("log.vendorActionResult", "(?i)\\bdenied\\b")
 
       - add:
-          function: 'string'
+          function: string
           params:
             key: actionResult
-            value: 'blocked'
-          where: regexMatch("log.properties.result", "(?i)\bblocked\b")
+            value: denied
+          where: regexMatch("log.vendorActionResult", "(?i)\\bblocked\\b")
 
       - add:
-          function: 'string'
+          function: string
           params:
             key: actionResult
-            value: 'failed'
-          where: regexMatch("log.properties.result", "(?i)\bfailed\b")
+            value: failure
+          where: regexMatch("log.vendorActionResult", "(?i)\\bfailed\\b")
 
       # .......................................................................#
       # Adding severity based on log.level
       # .......................................................................#
       - add:
-          function: 'string'
+          function: string
           params:
             key: severity
-            value: 'high'
+            value: error
           where: oneOf("log.level", ["ERROR", "Error", "FATAL", "CRITICAL", "Critical"])
       - add:
-          function: 'string'
+          function: string
           params:
             key: severity
-            value: 'medium'
+            value: warning
           where: oneOf("log.level", ["WARN", "Warning"])
       - add:
-          function: 'string'
+          function: string
           params:
             key: severity
-            value: 'low'
+            value: info
           where: oneOf("log.level", ["Information", "Informational", "INFO", "DEBUG", "TRACE"])
 
       # .......................................................................#
@@ -1163,4 +1165,98 @@ pipeline:
           fields:
             - origin.bytesSent
             - origin.bytesReceived
-          to: float
+          to: float
+
+      # Normalize the source event severity.
+      - add:
+          function: string
+          params:
+            key: severity
+            value: critical
+          where: oneOf("log.level",["FATAL","CRITICAL","Critical"])
+      - add:
+          function: string
+          params:
+            key: severity
+            value: debug
+          where: oneOf("log.level",["DEBUG","TRACE"])
+
+      # Normalize explicit outcomes; an unknown outcome remains unset.
+      - add:
+          function: string
+          params:
+            key: actionResult
+            value: success
+          where: '!exists("actionResult") && regexMatch("log.vendorActionResult", "(?i)^(success|succeeded|successful|ok|done|accepted|accept|allowed|allow|permitted|permit|passed|pass|true)$")'
+      - add:
+          function: string
+          params:
+            key: actionResult
+            value: failure
+          where: '!equals("actionResult","denied") && regexMatch("log.vendorActionResult", "(?i)^(failure|failed|fail|error|invalid|timeout|false)$")'
+      - add:
+          function: string
+          params:
+            key: actionResult
+            value: denied
+          where: regexMatch("log.vendorActionResult", "(?i)^(denied|deny|blocked|block|dropped|drop|rejected|reject|forbidden|unauthorized|quarantined)$")
+
+      # Keep addresses in IP fields and retain other source values under log.
+      - rename:
+          from:
+          - origin.ip
+          to: log.unparsedOriginIp
+          where: exists("origin.ip") && (!(inCIDR("origin.ip","0.0.0.0/0") || inCIDR("origin.ip","::/0")) || oneOf("origin.ip",["0.0.0.0","::"]))
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: ICMP
+          where: equals("protocol",1)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: TCP
+          where: equals("protocol",6)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: UDP
+          where: equals("protocol",17)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: GRE
+          where: equals("protocol",47)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: ESP
+          where: equals("protocol",50)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: AH
+          where: equals("protocol",51)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: ICMPV6
+          where: equals("protocol",58)
+      - add:
+          function: string
+          params:
+            key: protocol
+            value: SCTP
+          where: equals("protocol",132)
+      - rename:
+          from:
+          - protocol
+          to: log.ipProtocolNumber
+          where: exists("protocol") && greaterOrEqual("protocol",0)