fix(pii): Mark sentry_user field as PII (#3948)

This marks `User::sentry_user` as PII so it gets scrubbed correctly.

relay-event-schema/src/protocol/user.rs

@@ -68,6 +68,14 @@ pub struct User {
     #[metastructure(pii = "true", max_chars = 128, skip_serialization = "empty")]
     pub name: Annotated<String>,
 
+    /// The user string representation as handled in Sentry.
+    ///
+    /// This field is computed by concatenating the name of specific fields of the `User`
+    /// struct with their value. For example, if `id` is set, `sentry_user` will be equal to
+    /// `"id:id-of-the-user".
+    #[metastructure(pii = "true", skip_serialization = "empty")]
+    pub sentry_user: Annotated<String>,
+
     /// Approximate geographical location of the end user or device.
     #[metastructure(skip_serialization = "empty")]
     pub geo: Annotated<Geo>,
@@ -76,14 +84,6 @@ pub struct User {
     #[metastructure(skip_serialization = "empty")]
     pub segment: Annotated<String>,
 
-    /// The user string representation as handled in Sentry.
-    ///
-    /// This field is computed by concatenating the name of specific fields of the `User`
-    /// struct with their value. For example, if `id` is set, `sentry_user` will be equal to
-    /// `"id:id-of-the-user".
-    #[metastructure(skip_serialization = "empty")]
-    pub sentry_user: Annotated<String>,
-
     /// Additional arbitrary fields, as stored in the database (and sometimes as sent by clients).
     /// All data from `self.other` should end up here after store normalization.
     #[metastructure(pii = "true", skip_serialization = "empty")]

relay-pii/src/processor.rs

@@ -622,6 +622,33 @@ mod tests {
         assert_debug_snapshot!(&data);
     }
 
+    #[test]
+    fn test_sentry_user() {
+        let mut data = Event::from_value(
+            json!({
+                "user": {
+                    "ip_address": "73.133.27.120",
+                    "sentry_user": "ip:73.133.27.120",
+                },
+            })
+            .into(),
+        );
+
+        let scrubbing_config = DataScrubbingConfig {
+            scrub_data: true,
+            scrub_ip_addresses: true,
+            scrub_defaults: true,
+            ..Default::default()
+        };
+
+        let pii_config = to_pii_config(&scrubbing_config).unwrap();
+        let mut pii_processor = PiiProcessor::new(pii_config.compiled());
+
+        process_value(&mut data, &mut pii_processor, ProcessingState::root()).unwrap();
+
+        assert_debug_snapshot!(&data);
+    }
+
     #[test]
     fn test_basic_stripping() {
         let config = serde_json::from_str::<PiiConfig>(

relay-pii/src/snapshots/relay_pii__processor__tests__scrub_original_value.snap

@@ -71,9 +71,9 @@ Event {
             },
         ),
         name: ~,
+        sentry_user: ~,
         geo: ~,
         segment: ~,
-        sentry_user: ~,
         data: ~,
         other: {},
     },

relay-pii/src/snapshots/relay_pii__processor__tests__sentry_user.snap

@@ -0,0 +1,112 @@
+---
+source: relay-pii/src/processor.rs
+expression: "&data"
+---
+Event {
+    id: ~,
+    level: ~,
+    version: ~,
+    ty: ~,
+    fingerprint: ~,
+    culprit: ~,
+    transaction: ~,
+    transaction_info: ~,
+    time_spent: ~,
+    logentry: ~,
+    logger: ~,
+    modules: ~,
+    platform: ~,
+    timestamp: ~,
+    start_timestamp: ~,
+    received: ~,
+    server_name: ~,
+    release: ~,
+    dist: ~,
+    environment: ~,
+    site: ~,
+    user: User {
+        id: ~,
+        email: ~,
+        ip_address: Meta {
+            remarks: [
+                Remark {
+                    ty: Substituted,
+                    rule_id: "@ip:replace",
+                    range: Some(
+                        (
+                            0,
+                            4,
+                        ),
+                    ),
+                },
+                Remark {
+                    ty: Removed,
+                    rule_id: "@anything:remove",
+                    range: None,
+                },
+            ],
+            errors: [],
+            original_length: Some(
+                13,
+            ),
+            original_value: None,
+        },
+        username: ~,
+        name: ~,
+        sentry_user: Annotated(
+            "ip:[ip]",
+            Meta {
+                remarks: [
+                    Remark {
+                        ty: Substituted,
+                        rule_id: "@ip:replace",
+                        range: Some(
+                            (
+                                3,
+                                7,
+                            ),
+                        ),
+                    },
+                ],
+                errors: [],
+                original_length: Some(
+                    16,
+                ),
+                original_value: None,
+            },
+        ),
+        geo: ~,
+        segment: ~,
+        data: ~,
+        other: {},
+    },
+    request: ~,
+    contexts: ~,
+    breadcrumbs: ~,
+    exceptions: ~,
+    stacktrace: ~,
+    template: ~,
+    threads: ~,
+    tags: ~,
+    extra: ~,
+    debug_meta: ~,
+    client_sdk: ~,
+    ingest_path: ~,
+    errors: ~,
+    key_id: ~,
+    project: ~,
+    grouping_config: ~,
+    checksum: ~,
+    csp: ~,
+    hpkp: ~,
+    expectct: ~,
+    expectstaple: ~,
+    spans: ~,
+    measurements: ~,
+    breakdowns: ~,
+    scraping_attempts: ~,
+    _metrics: ~,
+    _metrics_summary: ~,
+    _dsc: ~,
+    other: {},
+}