From 3f20765c4a75615960335bd2a6dad262b67d126e Mon Sep 17 00:00:00 2001
From: Adnan Hasnat <78582230+Tridecatrix@users.noreply.github.com>
Date: Thu, 17 Oct 2024 18:54:25 +1100
Subject: [PATCH] Port Lychee link checker to user documentation (#531)

---
 .github/workflows/check-links.yaml | 37 +++++++++++++++++++++++-------
 .lycheeignore                      | 16 +++++++++++++
 mlc_config.json                    | 31 -------------------------
 3 files changed, 45 insertions(+), 39 deletions(-)
 create mode 100644 .lycheeignore
 delete mode 100644 mlc_config.json

diff --git a/.github/workflows/check-links.yaml b/.github/workflows/check-links.yaml
index 648e7558e..1603a1832 100644
--- a/.github/workflows/check-links.yaml
+++ b/.github/workflows/check-links.yaml
@@ -1,16 +1,37 @@
-name: Check Markdown links
+name: Check external href links in the documentation
 
 on:
+  push:
+    paths:
+      - '.github/workflows/check-links.yml'
+      - '.lycheeignore'
+      - 'lychee.toml'
+      - '**/*.md'
+  schedule:
+    # Run on the first of each month at 9:00 AM (See https://pubs.opengroup.org/onlinepubs/9699919799/utilities/crontab.html#tag_20_25_07)
+    - cron: "0 9 1 * *"
   workflow_dispatch:
 
+concurrency:
+  group: "${{ github.workflow }}-${{ github.head_ref || github.ref }}"
+  cancel-in-progress: true
+
 jobs:
-  markdown-link-check:
+  lychee:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: gaurav-nelson/github-action-markdown-link-check@v1
+      - uses: actions/checkout@v4
+        with:
+          show-progress: 'false'
+      - name: Restore lychee cache
+        uses: actions/cache@v4
+        with:
+          path: .lycheecache
+          key: cache-lychee-${{ github.sha }}
+          restore-keys: cache-lychee-
+      - name: Link Checker
+        id: lychee
+        uses: lycheeverse/lychee-action@v2.0.2
         with:
-          use-quiet-mode: 'yes'
-          use-verbose-mode: 'no'
-          config-file: 'mlc_config.json'
-          folder-path: 'en'
+          fail: true
+          args: --accept '200,201,202,203,204,403,429,500' --max-concurrency 1 --cache --no-progress --exclude-all-private './**/*.md'
\ No newline at end of file
diff --git a/.lycheeignore b/.lycheeignore
new file mode 100644
index 000000000..06d882b58
--- /dev/null
+++ b/.lycheeignore
@@ -0,0 +1,16 @@
+https://arxiv.org/
+https://chrome.google.com/
+https://contribute.jabref.org/
+https://donations.jabref.org/
+https://pubs.acs.org/
+https://scholar.archive.org/
+https://web.archive.org/
+https://www.researchgate.net/privacy-policy
+https://www.sciencedirect.com/
+
+https://github.com/koppor/jabref/issue
+https://github.com/koppor/jabref/pull
+https://github.com/JabRef/jabref/issue
+https://github.com/JabRef/jabref/pull
+
+0005-example.md
\ No newline at end of file
diff --git a/mlc_config.json b/mlc_config.json
deleted file mode 100644
index 3c775a554..000000000
--- a/mlc_config.json
+++ /dev/null
@@ -1,31 +0,0 @@
-{
-    "ignorePatterns": [
-        {
-            "pattern": "^https://.*\\.crossref\\.org"
-        },
-        {
-            "pattern": "^https://.*\\.github\\.com"
-        },
-        {
-            "pattern": "^https://dl\\.acm\\.org"
-        },
-        {
-            "pattern": "^http://purl\\.org/net/bibteXMP"
-        },
-        {
-            "pattern": "^https://.*\\.jabref\\.org"
-        },
-        {
-            "pattern": "\\.tex\\.ac\\.uk/"
-        },
-        {
-          "pattern": "gitignore\\.io"
-        },
-        {
-          "pattern": "en\\.wikipedia\\.org"
-        },
-        {
-            "pattern": "^https://web.archive.org/"
-        }
-    ]
-}