Skip to content

docs-2978: separate link-check skip lists and warn on broken anchors #2839

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ctauchen wants to merge 3 commits into
base: main
Choose a base branch
from
Open

docs-2978: separate link-check skip lists and warn on broken anchors #2839

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e821630
docs-2978: move link-check skip lists to one config file
ctauchen Jul 8, 2026
cc7e1c0
docs-2978: warn on broken anchors
ctauchen Jul 8, 2026
7ea4d41
docs-2978: correct header comment (skip and ignore lists)
ctauchen Jul 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
179 changes: 1 addition & 178 deletions __tests__/crawler.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ const { test, expect } = require('@playwright/test');
const { CheerioCrawler, downloadListOfUrls, extractUrls, EnqueueStrategy, Configuration, sleep } = require('crawlee');
import { decode } from 'html-entities';
const linkChecker = require('../src/utils/linkChecker');
const { crawlerSkipList: skipList, skipOriginsForLC } = require('../src/utils/link-check-config');
import YAML from 'yaml';
import needle from 'needle';

Expand Down Expand Up @@ -31,184 +32,6 @@ test('Crawl the docs and execute tests', async () => {
{ regex: /\/calico-cloud\/get-help\/support$/i, processContent: true },
{ regex: /\/calico-cloud\/get-started\/connect\/connect-cluster$/i, processContent: true },
];
const skipOriginsForLC = [
// All origins to skip link checking (literal or regex)
// Examples:
// /\/reference\/legal\/felix$/,
// 'http://localhost:4242/calico/3.24/reference/legal/felix',

// Skip this license attribution file, since we need to include the text of licenses unmodified,
// and some have dead links
'http://localhost:4242/calico/3.24/reference/legal/projectcalico',
'http://localhost:4242/calico/3.25/reference/legal/projectcalico',
'http://localhost:4242/calico/3.26/reference/legal/projectcalico',
'http://localhost:4242/calico/latest/reference/legal/projectcalico',
'http://localhost:4242/calico/next/reference/legal/projectcalico',
'http://localhost:4242/calico/3.25/reference/legal/node',
];
const skipList = [
/^https?:\/\/([\w-]+\.)?example\.com/,
/^https:\/\/kubernetes\.io\/docs\/reference\/generated\/kubernetes-api\/v1\.18/i,
/^https:\/\/v1-(15|16|17|18)\.docs\.kubernetes\.io\/docs\/reference\/generated\/kubernetes-api\/v1\.(15|16|17|18)/i,
/^https:\/\/github\.com\/projectcalico\/calico\/tree\/master\/[\w/.-]+\.md$/i,
/^https:\/\/www\.linkedin\.com\/company\/tigera\/?$/,
/^https:\/\/installer\.calicocloud\.io\/manifests\/.+\/manifests/,
'http://etcd.co',
'https://www.tigera.io/project-calico/community',
'https://openid.net/connect/',
'https://fedoraproject.org/wiki/EPEL',
'http://kubernetes.io/docs/user-guide/identifiers#names',
'http://kubernetes.io/docs/user-guide/volumes#emptydir',
'http://kubernetes.io/docs/user-guide/labels',
'https://nvd.nist.gov/vuln/detail/CVE-2017-5638',
'http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod',
'http://kubernetes.io/docs/user-guide/annotations',
'https://git.io/getLatestIstio',
'https://sns.us-east-2.amazonaws.com',
'https://success.docker.com/article/docker-ee-best-practices',
`https://installer.calicocloud.io/`,
`https://installer.calicocloud.io/charts`,
`https://docs.tigera.io/calico/charts`,
'https://downloads.tigera.io/ee/charts',
'https://Q4GSZWRKBA-dsn.algolia.net',
'http://backend.stars:6379/status',
'http://client.client:9000/status',
'http://frontend.stars:80/status',
`https://github.com/projectcalico/calico/releases/download/master/ocp.tgz`,
`https://downloads.tigera.io/ee/master/download/binaries/master/calicoctl`,
`https://github.com/projectcalico/calico/releases/download/master/install-calico-windows.ps1`,
`https://downloads.tigera.io/ee/master/download/binaries/master/calicoq`,
`https://en.wikipedia.org/wiki/Autonomous_System_(Internet)%3E`,
//`https://installer.calicocloud.io/manifests/v3.15.1-8/manifests`,
//`https://installer.calicocloud.io/manifests/v3.16.1-0/manifests`,
//`https://installer.calicocloud.io/manifests/v3.16.1-5/manifests`,
//`https://installer.calicocloud.io/manifests/v3.16.1-11/manifests`,
//`https://installer.calicocloud.io/manifests/v3.17.1-0/manifests`,
//`https://installer.calicocloud.io/manifests/v3.17.1-3/manifests`,
//`https://installer.calicocloud.io/manifests/v3.17.1-4/manifests`,
`https://d881b853ae312e00302a84f1e346a77.gr7.us-west-2.eks.amazonaws.com`,
/^https:\/\/fonts\.googleapis\.com\/css2/, // Google Fonts URLs with semicolons confuse the link checker
`https://www.googletagmanager.com`,
'https://www.googletagmanager.com/gtm.js?id=',
'https://twitter.com/tigeraio',
'https://twitter.com/projectcalico',
'https://csrc.nist.gov/publications/detail/fips/140/2/final',
/^https?:\/\/csrc\.nist\.gov\/projects\/cryptographic-module-validation-program\/certificate\/\d+$/,
/^https:\/\/installer\.calicocloud\.io:[0-9]{3,4}$/,
'https://help.ubuntu.com/community/NetworkManager', //==>Origin: http://localhost:4242/calico-enterprise/3.14/operations/troubleshoot/troubleshooting
'http://dpdk.org/git/dpdk', //==>Origin: https://raw.githubusercontent.com/projectcalico/vpp-dataplane/master/scripts/init_eks.sh
'http://dpdk.org/git/dpdk-kmods', //==>Origin: https://raw.githubusercontent.com/projectcalico/vpp-dataplane/master/scripts/init_eks.sh
//For frustrating 503 errors:
'https://nvd.nist.gov/vuln-metrics/cvss/v3-calculator',
/^https:\/\/amd64\.ocp\.releases\.ci\.openshift\.org\/?$/, //==>Origin: http://localhost:4242/calico-enterprise/latest/getting-started/install-on-clusters/openshift/hostedcontrolplanes
//temp
/^https:\/\/v1-21\.docs\.kubernetes\.io\/docs\/reference\/generated\/kubernetes-api\/v1\.21\//,
'https://dl.fedoraproject.org/pub/epel/epel-release-latest-7.noarch.rpm',
'https://www.iana.org/assignments/service-names', //==>Origin: https://downloads.tigera.io/ee/v3.15.2/manifests/tigera-operator.yaml'
'https://stedolan.github.io/jq/',
`http://kubernetes.io/docs/user-guide/secrets/`,
`https://github.com/coreos/flannel/blob/master/Documentation/kube-flannel-rbac.yml`,
`https://kubernetes.io/docs/tasks/access-application-cluster/configure-cloud-provider-firewall/`,
`https://raw.githubusercontent.com/projectcalico/calico//node/windows-packaging/CalicoWindows/kubernetes/kube-proxy-service.ps1`,
`https://projectcalico.docs.tigera.io/master/reference/installation/api#operator.tigera.io/v1.APIServer`,
`https://projectcalico.docs.tigera.io/master/reference/installation/api#operator.tigera.io/v1.Installation`,
'https://downloads.tigera.io/ee/master/download/binaries/master/calicoctl-darwin-amd64', //==>Origin: http://localhost:4242/calico-enterprise/next/operations/clis/calicoctl/install
'https://downloads.tigera.io/ee/master/download/binaries/master/calicoctl-windows-amd64.exe', //==>Origin: http://localhost:4242/calico-enterprise/next/operations/clis/calicoctl/install
'http://www.iana.org/assignments/service-names', //==>Origin: https://downloads.tigera.io/ee/v3.14.4/manifests/tigera-operator.yaml
'http://docs.openstack.org/',
'http://docs.openstack.org', //This seems to be temporarily down.
'https://docs.openstack.org/install-guide/environment-etcd.html', // 403 from OpenStack docs WAF in Netlify build environment
'https://tools.ietf.org/html/rfc5925',
'https://datatracker.ietf.org/doc/html/rfc1149',
'https://datatracker.ietf.org/doc/html/rfc7938',
'https://tools.ietf.org/html/rfc5890',
'https://tools.ietf.org/html/rfc1123',
'http://cr.yp.to/libtai/tai64.html#tai64n',
'https://thenewstack.io/faster-troubleshooting-with-dynamic-packet-capture/', //==>Origin: http://localhost:4242/calico-cloud/visibility/packetcapture
'https://golang.org/pkg/crypto/tls/#ClientAuthType', //==>Origin: https://downloads.tigera.io/ee/v3.17.0/manifests/tigera-prometheus-operator.yaml. The dead link is automatically redirected to a working page, so no fix needed in the origin.
'https://downloads.tigera.io/ee/archives/release-master-master.tgz', //==> This started after redesigning the archive procedure.
'http://nginx-svc.curl-ns.svc.cluster.local:80',
'http://nginx-svc.service-ns.svc.cluster.local:80',
'https://calicousers.slack.com/',
'https://calicousers.slack.com/archives/C017220EXU1',
'https://tigera-manager.mycompany.com',
'https://kb.isc.org/article/AA-01141/31/How-to-workaround-IPv6-prefix-length-issues-with-ISC-DHCP-clients.html',
'https://www.snort.org/documents',
'https://www.snort.org/downloads/#rule-downloads',
'https://www.projectcalico.org/everything-you-need-to-know-about-kubernetes-networking-on-azure/',
'https://www.tigera.io/calico-support/',
'https://www.tigera.io/legal/calico-cloud-support-policy',
'https://www.tigera.io/tutorials/?_sf_s=Deploy%20Service%20Mesh',
'https://www.projectcalico.org/comparing-kube-proxy-modes-iptables-or-ipvs/',
'https://www.projectcalico.org/hands-on-with-calicos-ebpf-service-handling/',
'https://www.tigera.io/blog/?_sft_post_tag=project-calico',
'https://www.tigera.io/tutorials/?_sf_s=%27calico%20ebpf%20and%20xdp%27,',
'https://www.tigera.io/tutorials/?_sf_s=Calico%20Basics',
'https://www.tigera.io/tutorials/?_sf_s=WireGuard',
'https://www.elastic.co/guide/en/apm/server/current/configuring-howto-apm-server.html',
'https://www.elastic.co/guide/en/elasticsearch/reference/current/vm-max-map-count.html',
/^https:\/\/www\.wireguard\.com\/.+/,
'https://godoc.org/time#Duration',
'https://www.tigera.io/contact',
'https://www.projectcalico.org/contact',
'https://hub.docker.com/_/microsoft-windows-servercore',
'https://github.com/tigera/operator/blob/master/pkg/render/applicationlayer/modsec-core-ruleset/modsecdefault.conf',
'https://github.com/tigera/operator/blob/master/pkg/render/applicationlayer/modsec-core-ruleset/crs-setup.conf',
'https://github.com/tigera/operator/tree/master/pkg/render/applicationlayer/modsec-core-ruleset',
'https://kubernetes.io/docs/setup/production-environment/tools/kops/#2-5-create-a-route53-domain-for-your-cluster',
'https://pkgs.k8s.io/',
'https://apt.kubernetes.io/',
'https://docs.tigera.io/calico-enterprise/3.15/about-calico-enterprise',
'https://your-jira-instance-name.atlassian.net/rest/api/2/issue/',
'https://bugzilla.netfilter.org/show_bug.cgi?id=1119',
'https://webexapis.com/v1/messages',
'https://www.projectcalico.org/everything-you-need-to-know-about-kubernetes-ingress-networking/',
'https://www.projectcalico.org/everything-you-need-to-know-about-kubernetes-networking-on-google-cloud/',
'https://www.projectcalico.org/everything-you-need-to-know-about-kubernetes-pod-networking-on-aws/',
'https://www.projectcalico.org/everything-you-need-to-know-about-kubernetes-services-networking/',
'https://www.projectcalico.org/introducing-the-calico-ebpf-dataplane/',
'https://www.projectcalico.org/kubernetes-service-ip-route-advertisement/',
'https://www.projectcalico.org/live-migration-from-flannel-to-calico/',
'https://www.projectcalico.org/why-bgp/',
'https://www.tigera.io/blog/calico-ipam-explained-and-enhanced/',
'https://www.tigera.io/blog/faster-troubleshooting-of-microservices-containers-and-kubernetes-with-dynamic-packet-capture/',
'https://www.tigera.io/blog/hands-on-guide-how-to-scan-and-block-container-images-to-mitigate-sbom-attacks/',
'https://www.tigera.io/blog/kubernetes-security-policy-10-critical-best-practices/',
'https://www.tigera.io/blog/when-linux-conntrack-is-no-longer-your-friend/',
'https://www.tigera.io/blog/why-bgp/',
'https://docs.nginx.com/nginx-ingress-controller/configuration/',
'https://docs.nginx.com/nginx-ingress-controller/configuration/global-configuration/configmap-resource',
'https://prometheus.io/docs/prometheus/latest/disabled_features/', // ==>Origin: https://downloads.tigera.io/ee/v3.17.4/manifests/tigera-prometheus-operator.yaml
'https://prometheus.io/docs/prometheus/latest/feature_flags/', // ==>Origin: https://downloads.tigera.io/ee/v3.20.0-1.0/manifests/tigera-prometheus-operator.yaml
'https://docs.fluentd.org/filter/grep',
'https://techcommunity.microsoft.com/t5/networking-blog/direct-server-return-dsr-in-a-nutshell/ba-p/693710',
'https://www.f5.com/glossary/cookie-poisoning', //TEMPORARY
'https://www.f5.com/glossary/cross-site-scripting', //TEMPORARY
'https://www.f5.com/glossary/sql-injection', //TEMPORARY
'https://www.f5.com/labs/articles/threat-intelligence/application-protection-report-2019--episode-2--2018-breach-trend', //TEMPORARY
'https://installer.calicocloud.io/manifests/cc-operator/latest/deploy-with-container-security.yaml', //TEMPORARY
'https://stackoverflow.com/questions/tagged/calico',
/^https?:\/\/github\.com\//,
/^https?:\/\/(git|examples)\.k8s\.io\//,
'https://console.developers.google.com/apis/library/admin.googleapis.com/',
'https://docs.splunk.com/Documentation/Splunk/8.0.0/Data/UsetheHTTPEventCollector',
'https://guardian.calico-system.svc',
'https://developer.hashicorp.com/terraform',
'https://www.terraform.io/',
'http://developer.openstack.org/api-ref-networking-v2.html',
'https://docs.openstack.org/kolla-ansible/rocky/user/multi-regions.html',
'https://archive.istio.io/v1.15/docs/setup/additional-setup/sidecar-injection/#automatic-sidecar-injection',
'https://istio.io/v1.15/docs/reference/config/security/peer_authentication/',
'https://istio.io/v1.15/docs/setup/install/',
'https://sysctl-explorer.net/net/ipv4/fib_multipath_hash_policy/',
'https://calico-docs.mcp.kapa.ai',
'https://docs.tigera.io/img/calico-logo-2026-badge.png',
'http://www.w3.org/2000/svg', // Appears in SVG file 'xmlns', doesn't need checking
'https://www.w3.org/Protocols/rfc2616/rfc2616-sec9.html', // TEMP
'https://review.openstack.org/#/c/344008/',
'http://www.faqs.org/rfcs/rfc1966.html',
'http://www.faqs.org/rfcs/rfc4893.html'
];

const lc = linkChecker();
if (isLocalHost) lc.setLocalhost(DOCS);
Expand Down
2 changes: 1 addition & 1 deletion docusaurus.config.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ export default async function createAsyncConfig() {
tagline: 'Unified network security and observability for Kubernetes',
url: 'https://docs.tigera.io',
baseUrl: '/',
onBrokenAnchors: 'ignore',
onBrokenAnchors: 'warn',
onBrokenLinks: 'throw',
favicon: 'img/calico-logo-2026-badge.png',
markdown: {
Expand Down
Loading