[chore] Refcache refresh, oldest link is now 2024-08-06 (#6167)

Co-authored-by: Tiffany Hrabusa <30397949+tiffany76@users.noreply.github.com>

.github/workflows/check-links.yml

@@ -104,7 +104,9 @@ jobs:
       - name: Fail when refcache contains entries with HTTP status 4XX
         run: |
           if grep -B 1 -e '"StatusCode": 4' static/refcache.json; then
-            echo "Run 'npx gulp prune' to remove 4xx entries from the refcache"
+            echo "Run 'npm run _refcache:prune' to remove 404 entries from refcache.json,"
+            echo "or run './scripts/double-check-refcache-400s.mjs' locally to address"
+            echo "other 400-status entries."
             exit 1
           fi
       - name: Does the refcache need updating?

content/en/docs/kubernetes/operator/troubleshooting/target-allocator.md

@@ -5,7 +5,7 @@ cSpell:ignore: bleh targetallocator
 
 If you’ve enabled
 [Target Allocator](/docs/kubernetes/operator/target-allocator/) service
-discovery on the [OpenTelemetry Operator](/docs/kubernetes/operator), and the
+discovery on the [OpenTelemetry Operator](/docs/kubernetes/operator/), and the
 Target Allocator is failing to discover scrape targets, there are a few
 troubleshooting steps that you can take to help you understand what’s going on
 and restore normal operation.
@@ -21,9 +21,8 @@ Kubernetes cluster.
 
 After you’ve deployed all of your resources to Kubernetes, make sure that the
 Target Allocator is discovering scrape targets from your
-[`ServiceMonitor`](https://prometheus-operator.dev/docs/operator/design/#servicemonitor)(s)
-or
-[`PodMonitor`](https://prometheus-operator.dev/docs/user-guides/getting-started/#using-podmonitors)(s).
+[`ServiceMonitor`](https://prometheus-operator.dev/docs/getting-started/design/#servicemonitor)(s)
+or [PodMonitor]s.
 
 Suppose that you have this `ServiceMonitor` definition:
 
@@ -386,9 +385,7 @@ Allocator will fail to discover scrape targets from that `ServiceMonitor`.
 
 {{% alert title="Tip" %}}
 
-The same applies if you’re using a
-[PodMonitor](https://prometheus-operator.dev/docs/user-guides/getting-started/#using-podmonitors).
-In that case, you would use a
+The same applies if you’re using a [PodMonitor]. In that case, you would use a
 [`podMonitorSelector`](https://github.com/open-telemetry/opentelemetry-operator/blob/main/docs/api.md#opentelemetrycollectorspectargetallocatorprometheuscr)
 instead of a `serviceMonitorSelector`.
 
@@ -513,3 +510,6 @@ If you’re using `PodMonitor`, the same applies, except that it picks up
 Kubernetes pods that match on labels, namespaces, and named ports.
 
 {{% /alert %}}
+
+[PodMonitor]:
+  https://prometheus-operator.dev/docs/developer/getting-started/#using-podmonitors

data/ecosystem/vendors.yaml

@@ -55,7 +55,7 @@
 - name: Causely
   distribution: false
   nativeOTLP: true
-  url: https://github.com/Causely/documentation
+  url: https://www.causely.ai/blog/using-opentelemetry-and-the-otel-collector-for-logs-metrics-and-traces
   contact: support@causely.io
   oss: false
   commercial: true
@@ -68,7 +68,7 @@
 - name: Chronosphere
   distribution: false
   nativeOTLP: true
-  url: https://docs.chronosphere.io/ingest/otel/otel-ingest
+  url: https://docs.chronosphere.io/ingest/
   contact: support@chronosphere.io
   oss: false
   commercial: true
@@ -314,7 +314,7 @@
   commercial: true
 - name: Red Hat
   nativeOTLP: true
-  url: https://docs.openshift.com/container-platform/4.14/otel/otel-release-notes.html
+  url: https://docs.redhat.com/en/documentation/openshift_container_platform/4.17/html/red_hat_build_of_opentelemetry/
   contact: ploffay@redhat.com
   oss: true
   commercial: true

scripts/double-check-refcache-400s.mjs

@@ -20,13 +20,18 @@ async function writeRefcache(cache) {
   console.log(`Updated ${CACHE_FILE} with fixed links.`);
 }
 
-async function retry404sAndUpdateCache() {
+// Retry HTTP status check for refcache URLs with non-200s and not 404
+async function retry400sAndUpdateCache() {
   const cache = await readRefcache();
   let updated = false;
 
   for (const [url, details] of Object.entries(cache)) {
     const { StatusCode, LastSeen } = details;
     if (isHttp2XX(StatusCode)) continue;
+    if (StatusCode === 404) {
+      console.log(`Skipping 404: ${url} (last seen ${LastSeen}).`);
+      continue;
+    }
 
     process.stdout.write(`Checking: ${url} (was ${StatusCode})... `);
     const status = await getUrlStatus(url);
@@ -49,4 +54,4 @@ async function retry404sAndUpdateCache() {
   }
 }
 
-await retry404sAndUpdateCache();
+await retry400sAndUpdateCache();

scripts/get-url-status.mjs

@@ -67,7 +67,7 @@ export function isHttp2XX(status) {
 }
 
 export async function getUrlStatus(url) {
-  let status = 0; // await getUrlHeadless(url);
+  let status = await getUrlHeadless(url);
   if (!isHttp2XX(status)) {
     status = await getUrlInBrowser(url);
   }