From 8b2128c1d2dbf4b5e99a637487d86b3a47b00f7d Mon Sep 17 00:00:00 2001
From: yushijie_27 <yushijie0627@163.com>
Date: Thu, 4 Jun 2026 15:00:23 +0800
Subject: [PATCH 1/2] feat: add crawler-based in-site link and broken image
 checking

---
 .github/workflows/link-check-cron-crawler.yml | 17 +++++++
 .github/workflows/link-check-pr-crawler.yml   | 44 +++++++++++++++++++
 2 files changed, 61 insertions(+)
 create mode 100644 .github/workflows/link-check-cron-crawler.yml
 create mode 100644 .github/workflows/link-check-pr-crawler.yml

diff --git a/.github/workflows/link-check-cron-crawler.yml b/.github/workflows/link-check-cron-crawler.yml
new file mode 100644
index 0000000000000..c9da9df8ddfde
--- /dev/null
+++ b/.github/workflows/link-check-cron-crawler.yml
@@ -0,0 +1,17 @@
+name: link-check-cron-crawler
+
+on:
+  schedule:
+    - cron: '0 2 * * *'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  cron-crawler:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Run Crawler Link Checker
+        run: |
+          npx linkinator https://doris.apache.org --recurse --check-images --skip "^(?!https?://(www\.)?doris\.apache\.org)"
diff --git a/.github/workflows/link-check-pr-crawler.yml b/.github/workflows/link-check-pr-crawler.yml
new file mode 100644
index 0000000000000..60b4c53ee9877
--- /dev/null
+++ b/.github/workflows/link-check-pr-crawler.yml
@@ -0,0 +1,44 @@
+name: link-check-pr-crawler
+
+on:
+  pull_request:
+    paths:
+      - 'docs/**'
+      - 'i18n/**'
+      - 'src/**'
+      - 'static/**'
+      - 'docusaurus.config.js'
+      - 'sidebars.ts'
+
+concurrency:
+  group: link-check-pr-crawler-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  pr-crawler:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Use Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'yarn'
+
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+
+      - name: Build website
+        run: yarn build
+
+      - name: Serve build folder and scan for 404s/broken images
+        run: |
+          npx serve build -l 3000 &
+          # Wait for server to start
+          sleep 5
+          npx linkinator http://localhost:3000 --recurse --check-images --skip "^(?!http://localhost:3000)"

From dfd5831e2015f1d15fd34f80d9346ced339b6b22 Mon Sep 17 00:00:00 2001
From: yushijie_27 <yushijie0627@163.com>
Date: Thu, 4 Jun 2026 17:38:28 +0800
Subject: [PATCH 2/2] feat: add crawler-based in-site link and image checker
 workflows

---
 .github/workflows/link-check-cron-crawler.yml | 2 +-
 .github/workflows/link-check-pr-crawler.yml   | 7 +++++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/link-check-cron-crawler.yml b/.github/workflows/link-check-cron-crawler.yml
index c9da9df8ddfde..c3b5053b46333 100644
--- a/.github/workflows/link-check-cron-crawler.yml
+++ b/.github/workflows/link-check-cron-crawler.yml
@@ -14,4 +14,4 @@ jobs:
     steps:
       - name: Run Crawler Link Checker
         run: |
-          npx linkinator https://doris.apache.org --recurse --check-images --skip "^(?!https?://(www\.)?doris\.apache\.org)"
+          npx -y linkinator https://doris.apache.org --recurse --check-images --skip "^(?!https?://(www\.)?doris\.apache\.org)"
diff --git a/.github/workflows/link-check-pr-crawler.yml b/.github/workflows/link-check-pr-crawler.yml
index 60b4c53ee9877..3bbe63e4a62bf 100644
--- a/.github/workflows/link-check-pr-crawler.yml
+++ b/.github/workflows/link-check-pr-crawler.yml
@@ -4,11 +4,14 @@ on:
   pull_request:
     paths:
       - 'docs/**'
+      - 'versioned_docs/**'
       - 'i18n/**'
       - 'src/**'
       - 'static/**'
       - 'docusaurus.config.js'
       - 'sidebars.ts'
+      - 'versioned_sidebars/**'
+      - 'versions.json'
 
 concurrency:
   group: link-check-pr-crawler-${{ github.event.pull_request.number || github.ref }}
@@ -38,7 +41,7 @@ jobs:
 
       - name: Serve build folder and scan for 404s/broken images
         run: |
-          npx serve build -l 3000 &
+          npx -y serve build -l 3000 &
           # Wait for server to start
           sleep 5
-          npx linkinator http://localhost:3000 --recurse --check-images --skip "^(?!http://localhost:3000)"
+          npx -y linkinator http://localhost:3000 --recurse --check-images --skip "^(?!http://localhost:3000)"