feat(replays): Enable pii scrubbing for urls field (#2143)

Fixes getsentry/sentry#49495

Author: cmanallen

CHANGELOG.md

@@ -12,6 +12,7 @@
 
 - Mark all URL transactions as `sanitized` when `txNameReady` flag is set. ([#2128](https://github.com/getsentry/relay/pull/2128), [#2139](https://github.com/getsentry/relay/pull/2139))
 - Tag incoming errors with the new `sampled` field in case their DSC is sampled. ([#2026](https://github.com/getsentry/relay/pull/2026))
+- Enable PII scrubbing for urls field ([#2143](https://github.com/getsentry/relay/pull/2143))
 
 ## 23.5.0
 

relay-general/src/protocol/replay.rs

@@ -156,6 +156,7 @@ pub struct Replay {
     pub replay_start_timestamp: Annotated<Timestamp>,
 
     /// A list of URLs visted during the lifetime of the segment.
+    #[metastructure(pii = "true", bag_size = "large")]
     pub urls: Annotated<Array<String>>,
 
     /// A list of error-ids discovered during the lifetime of the segment.
@@ -553,6 +554,17 @@ mod tests {
             .get("credit-card");
 
         assert_eq!(maybe_credit_card, Some("[Filtered]"));
+
+        // Assert URLs field scrubs array items.
+        let maybe_url_0 = replay.value().unwrap().urls.value().unwrap().get(0);
+        let maybe_url_1 = replay.value().unwrap().urls.value().unwrap().get(1);
+        let maybe_url_2 = replay.value().unwrap().urls.value().unwrap().get(2);
+        assert_eq!(
+            maybe_url_0.map(|i| i.as_str()),
+            Some(Some("sentry.io?ssn=[Filtered]"))
+        );
+        assert_eq!(maybe_url_1.map(|i| i.as_str()), Some(Some("[Filtered]")));
+        assert_eq!(maybe_url_2.map(|i| i.as_str()), Some(Some("[Filtered]")));
     }
 
     #[test]

relay-general/tests/fixtures/replays/replay.json

@@ -7,7 +7,9 @@
     "timestamp": 1597977777.6189718,
     "replay_start_timestamp": 1597976392.6542819,
     "urls": [
-        "sentry.io"
+        "sentry.io?ssn=111-11-1111",
+        "4111-1111-1111-1111",
+        "111-11-1111"
     ],
     "error_ids": [
         "1",