Allow overriding network dataset name in hotblocks-retain config NET-433

README.md

@@ -38,10 +38,11 @@ This repo contains Rust crates for blockchain data processing, indexing, and que
 | [`sqd-archive`](crates/archive/) | Archive service for ingesting and storing data to S3 with layout management, progress tracking, and Prometheus metrics |
 | [`sqd-bds`](crates/bds/) | Big Data Service (WIP) - Cassandra-based data storage |
 | [`sqd-hotblocks`](crates/hotblocks/) | Hotblocks database with portal-like API |
+| [`sqd-hotblocks-retain`](crates/hotblocks-retain/) | Retention coordinator that applies Hotblocks retain points based on scheduling status updates |
 
 ## Building Docker image
 
 The ["docker"](/.github/workflows/docker.yaml) workflow should be triggered manually with the following inputs:
-- `target` — either `hotblocks` or `sqd-archive`.
+- `target` — one of `hotblocks`, `hotblocks-retain`, or `sqd-archive`.
 - `tag` — a 8-byte hash of the commit. This will be the published docker tag.
 - `platforms` — platforms to build for. Using only `linux/amd64` instead of default values can save a lot of building time.

crates/hotblocks-retain/src/main.rs

@@ -150,13 +150,22 @@ impl HotblocksRetain {
         let mut all_success = true;
 
         for (dataset, props) in &self.datasets {
+            let network_dataset = props
+                .as_ref()
+                .and_then(|p| p.network_dataset.as_deref())
+                .unwrap_or(dataset.as_str());
+
             let dataset_id = if let Some(id) = props.as_ref().and_then(|p| p.id.as_deref()) {
                 id
             } else {
-                match self.name_to_id.get(dataset) {
+                match self.name_to_id.get(network_dataset) {
                     Some(id) => id.as_str(),
                     None => {
-                        tracing::warn!(dataset, "dataset not found in manifest, skipping");
+                        tracing::warn!(
+                            dataset,
+                            network_dataset,
+                            "dataset not found in manifest, skipping"
+                        );
                         continue;
                     }
                 }

crates/hotblocks-retain/src/types.rs

@@ -6,6 +6,8 @@ pub type DatasetId = String; // s3://<bucket-name>
 #[derive(Debug, Clone, Deserialize)]
 pub struct DatasetProps {
     pub id: Option<DatasetId>,
+    #[serde(rename = "name", alias = "network_dataset")]
+    pub network_dataset: Option<String>,
 }
 
 pub type DatasetsConfig = HashMap<String, Option<DatasetProps>>;