From 8e8e861d5f1c261a80df1ceca7c07d2b01fc5b5a Mon Sep 17 00:00:00 2001
From: Markus Rudy <mr@edgeless.systems>
Date: Fri, 5 Jan 2024 14:07:33 +0100
Subject: [PATCH] ci: ignore Wireguard pdf in lychee (#2797)

* ci: use a config file for lychee

* ci: don't pass token to lychee action

* ci: ignore wireguard.pdf in lychee
---
 .github/workflows/check-links.yml    |  4 +--
 .gitignore                           |  3 ++
 .lychee.toml                         | 47 ++++++++++++++++++++++++++++
 .lycheeignore                        |  7 -----
 docs/docs/overview/performance/io.md |  2 +-
 5 files changed, 52 insertions(+), 11 deletions(-)
 create mode 100644 .lychee.toml
 delete mode 100644 .lycheeignore

diff --git a/.github/workflows/check-links.yml b/.github/workflows/check-links.yml
index f9d436240..3607ce9a0 100644
--- a/.github/workflows/check-links.yml
+++ b/.github/workflows/check-links.yml
@@ -27,7 +27,5 @@ jobs:
       - name: Link Checker
         uses: lycheeverse/lychee-action@ec3ed119d4f44ad2673a7232460dc7dff59d2421 # v1.8.0
         with:
-          args: "--verbose --no-progress --max-concurrency 5 --exclude-path './internal/constellation/helm/charts/cilium' './**/*.md' './**/*.html'"
+          args: "--config ./.lychee.toml './**/*.md' './**/*.html'"
           fail: true
-        env:
-          GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
diff --git a/.gitignore b/.gitignore
index 3d97460a6..ee46abb50 100644
--- a/.gitignore
+++ b/.gitignore
@@ -70,3 +70,6 @@ __pycache__/
 # s3proxy misc files
 port-forward.log
 s3proxy-ca.crt
+
+# Lychee link checker
+.lycheecache
diff --git a/.lychee.toml b/.lychee.toml
new file mode 100644
index 000000000..60439bd56
--- /dev/null
+++ b/.lychee.toml
@@ -0,0 +1,47 @@
+# Verbose program output
+# Accepts log level: "error", "warn", "info", "debug", "trace"
+verbose = "info"
+
+# Don't show interactive progress bar while checking links.
+no_progress = true
+
+# Enable link caching. This can be helpful to avoid checking the same links on
+# multiple runs.
+cache = true
+
+# Discard all cached requests older than this duration.
+max_cache_age = "10m"
+
+# Maximum number of concurrent link checks.
+max_concurrency = 5
+
+# Comma-separated list of accepted status codes for valid links.
+# accept = ["200"]
+
+# Request method
+method = "get"
+
+# Check links inside `<code>` and `<pre>` blocks as well as Markdown code
+# blocks.
+include_verbatim = false
+
+# Exclude URLs and mail addresses from checking (supports regex).
+exclude = [
+    # Blocked for robots.
+    '^https://twitter\.com',
+    # Only available when logged in.
+    '^https://portal\.azure\.com/',
+    # The Wireguard PDF sproadically returns 500.
+    'wireguard\.pdf$',
+]
+
+# Exclude these filesystem paths from getting checked.
+exclude_path = ["internal/constellation/helm/charts/cilium"]
+
+# Exclude all private IPs from checking.
+# Equivalent to setting `exclude_private`, `exclude_link_local`, and
+# `exclude_loopback` to true.
+exclude_all_private = true
+
+# Check mail addresses
+include_mail = false
diff --git a/.lycheeignore b/.lycheeignore
deleted file mode 100644
index 128bc8384..000000000
--- a/.lycheeignore
+++ /dev/null
@@ -1,7 +0,0 @@
-http://localhost:
-# TODO: Remove when site fixed their TLS chain (<https://github.com/edgelesssys/constellation/pull/430>)
-https://www.ntia.gov/SBOM
-# Twitter times out on request, maybe someone pulled the plug of this subsystem
-https://twitter.com/EdgelessSystems
-# Azure portal internal link, will return 403 for crawlers, or error when not logged in
-https://portal.azure.com/#view/HubsExtension/BrowseResource/resourceType/Microsoft.Compute%2Fgalleries
diff --git a/docs/docs/overview/performance/io.md b/docs/docs/overview/performance/io.md
index dc7cf3d8b..3ae796f8a 100644
--- a/docs/docs/overview/performance/io.md
+++ b/docs/docs/overview/performance/io.md
@@ -58,7 +58,7 @@ The following infrastructure configurations was used:
 This section gives a thorough analysis of the network performance of Constellation, specifically focusing on measuring TCP and UDP bandwidth.
 The benchmark measured the bandwidth of pod-to-pod and pod-to-service connections between two different nodes using [`iperf`](https://iperf.fr/).
 
-GKE and Constellation on GCP had a maximum network bandwidth of [10 Gbps](https://cloud.google.com/compute/docs/general-purpose-machines#n2d_machineshttps://cloud.google.com/compute/docs/general-purpose-machines#n2d_machines).
+GKE and Constellation on GCP had a maximum network bandwidth of [10 Gbps](https://cloud.google.com/compute/docs/general-purpose-machines#n2d_machines).
 AKS with `Standard_D4as_v5` machines a maximum network bandwidth of [12.5 Gbps](https://learn.microsoft.com/en-us/azure/virtual-machines/dasv5-dadsv5-series#dasv5-series).
 The Confidential VM equivalent `Standard_DC4as_v5` currently  has a network bandwidth of [1.25 Gbps](https://learn.microsoft.com/en-us/azure/virtual-machines/dcasv5-dcadsv5-series#dcasv5-series-products).
 Therefore, to make the test comparable, both AKS and Constellation on Azure were running with `Standard_DC4as_v5` machines and 1.25 Gbps bandwidth.