ci: run link checker on PRs

.github/workflows/linkcheck.yaml

@@ -1,33 +1,60 @@
-name: Links
+name: Link checks
 
 on:
+  workflow_dispatch:
   schedule:
     - cron: "00 18 1 * *"
+  pull_request:
 
-# Uncomment the following line while testing links in a single PR. Recomment when
-# done. Be sure to comment out the 'Create Issue from File' section while testing.
-# pull_request
+permissions: {}
+
+env:
+  # Single definition to simplify any future changes to the linkcheck configuration.
+  LYCHEE_ARGS: --accept '100..=103,200..=299,401,403,429,999' --verbose --no-progress .
 
 jobs:
-  linkChecker:
+  linkchecker-pr:
+    if: ${{ github.event_name == 'pull_request' }}
+    name: PR - Link Checker
     runs-on: ubuntu-latest
     permissions:
-      issues: write # required for peter-evans/create-issue-from-file
+      contents: read
     steps:
       - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
 
       - name: Link Checker
-        id: lychee
         uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
         with:
-          args: --accept '100..=103,200..=299,401,403,429,999' --verbose --no-progress .
+          args: ${{ env.LYCHEE_ARGS }}
           fail: false
           jobSummary: true
 
-# If testing links on pull_request, comment these lines out!
+  linkchecker-scheduled:
+    if: ${{ github.event_name != 'pull_request' }}
+    name: Monthly Link Checker
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      # required for peter-evans/create-issue-from-file
+      issues: write
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+
+      - name: Link Checker
+        id: lychee
+        uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
+        with:
+          args: ${{ env.LYCHEE_ARGS }}
+          # Do not fail scheduled runs; report by issue when links are broken.
+          fail: false
+          jobSummary: true
 
       - name: Create Issue From File
-        if: steps.lychee.outputs.exit_code != 0
+        if: ${{ steps.lychee.outputs.exit_code != 0 }}
         uses: peter-evans/create-issue-from-file@fca9117c27cdc29c6c4db3b86c48e4115a786710 # v6.0.0
         with:
           title: Link Checker Report

.lycheeignore

@@ -0,0 +1,5 @@
+# Ignore certain landing pages for link checking, these may change redirects to internally
+https://console.treasuredata.com/users/sign_in
+https://app.datadoghq.com/logs/activation
+# Ignore the redirects for Github logins when creating custom issues
+^https:\/\/github\.com\/fluent\/fluent-bit\/issues\/new\?.*

administration/transport-security.md

@@ -35,7 +35,7 @@ Both input and output plugins that perform Network I/O can optionally enable TLS
 
 {% hint style="info" %}
 
-When the connection target is an IP address (IPv4 or IPv6), Fluent Bit doesn't include the TLS Server Name Indication (SNI) extension, which is consistent with [RFC 6066](https://www.rfc-editor.org/rfc/rfc6066). Certificate validation still applies against the IP address. If the server requires SNI or uses a hostname-based certificate, use a hostname as the connection target and set `tls.vhost` if needed.
+When the connection target is an IP address (IPv4 or IPv6), Fluent Bit doesn't include the TLS Server Name Indication (SNI) extension, which is consistent with [RFC 6066](https://www.rfc-editor.org/info/rfc6066/). Certificate validation still applies against the IP address. If the server requires SNI or uses a hostname-based certificate, use a hostname as the connection target and set `tls.vhost` if needed.
 
 {% endhint %}
 

installation/downloads/source.md

@@ -11,7 +11,7 @@ https://github.com/fluent/fluent-bit/archive/refs/tags/v<release version>.
 https://github.com/fluent/fluent-bit/archive/refs/tags/v<release version>.zip
 ```
 
-For example, for version 1.8.12 the link is: [https://github.com/fluent/fluent-bit/archive/refs/tags/v1.8.12.tar.gz](https://github.com/fluent/fluent-bit/archive/refs/tags/v1.8.12.tar.gz)
+For example, for version 1.8.12 the link is: [https://github.com/fluent/fluent-bit/archive/refs/tags/v1.8.12.tar.gz](https://codeload.github.com/fluent/fluent-bit/tar.gz/refs/tags/v1.8.12)
 
 ## Development
 

pipeline/outputs/dynatrace.md

@@ -83,7 +83,7 @@ pipeline:
 
 <!-- vale FluentBit.Simplicity = NO -->
 
-- [Dynatrace Fluent Bit documentation](https://docs.dynatrace.com/docs/shortlink/lma-stream-logs-with-fluent-bit)
+- [Dynatrace Fluent Bit documentation](https://docs.dynatrace.com/docs/analyze-explore-automate/logs/lma-log-ingestion/lma-stream-logs-with-fluent-bit)
 - [Fluent Bit integration in Dynatrace Hub](https://www.dynatrace.com/hub/detail/fluent-bit/?filter=log-management-and-analytics)
 - [Video: Stream a Log File to Dynatrace using Fluent Bit](https://www.youtube.com/watch?v=JJJNxhtJ6R0)
 - [Blog: Easily stream logs from Fluent Bit to Dynatrace](https://docs.dynatrace.com/docs/analyze-explore-automate/logs/lma-log-ingestion/lma-stream-logs-with-fluent-bit)

pipeline/outputs/kinesis.md

@@ -132,7 +132,7 @@ You can use the Fluent Bit SSM Public Parameters to find the Amazon ECR image UR
 aws ssm get-parameters-by-path --path /aws/service/aws-for-fluent-bit/
 ```
 
-For more details, see the [Amazon ECR Public official doc](https://docs.aws.amazon.com/AmazonECR/latest/public/get-set-up-for-amazon-ecr.html).
+For more details, see the [Amazon ECR Public official doc](https://docs.aws.amazon.com/AmazonECR/latest/public/what-is-ecr.html).
 
 ### Docker Hub
 

pipeline/outputs/s3.md

@@ -713,7 +713,7 @@ If you see errors for image pull limits, try signing in to public ECR with your
 aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws
 ```
 
-See the [Amazon ECR Public official documentation](https://docs.aws.amazon.com/AmazonECR/latest/public/get-set-up-for-amazon-ecr.html) for more details.
+See the [Amazon ECR Public official documentation](https://docs.aws.amazon.com/AmazonECR/latest/public/what-is-ecr.html) for more details.
 
 ### Docker Hub
 

scripts/run-link-checker.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+set -euo pipefail
+
+# This script is used to run the Lychee link checker in the same way that CI does in the GitHub Actions workflow.
+
+SOURCE=${BASH_SOURCE[0]}
+while [ -L "$SOURCE" ]; do
+  SCRIPT_DIR=$( cd -P "$( dirname "$SOURCE" )" >/dev/null 2>&1 && pwd )
+  SOURCE=$(readlink "$SOURCE")
+  [[ $SOURCE != /* ]] && SOURCE=$SCRIPT_DIR/$SOURCE
+done
+SCRIPT_DIR=$( cd -P "$( dirname "$SOURCE" )" >/dev/null 2>&1 && pwd )
+REPO_DIR=${REPO_DIR:-$SCRIPT_DIR/..}
+
+CONTAINER_IMAGE=${CONTAINER_IMAGE:-"ghcr.io/lycheeverse/lychee:latest"}
+CONTAINER_RUNTIME=${CONTAINER_RUNTIME:-docker}
+
+# Always pull the latest Lychee image to ensure we are validating against the most recent version.
+if ! $CONTAINER_RUNTIME pull "$CONTAINER_IMAGE" &>/dev/null; then
+    echo "ERROR: Failed to pull container image $CONTAINER_IMAGE" >&2
+    exit 1
+fi
+
+# Matches the values in the GitHub Actions workflow for consistency.
+LYCHEE_ARGS=${LYCHEE_ARGS:-"--accept '100..=103,200..=299,401,403,429,999' --verbose --no-progress ."}
+
+# Run the Lychee link checker in a container with the same arguments as the GitHub Actions workflow.
+# Note we do want arguments to be expanded here, so we don't quote $LYCHEE_ARGS.
+# shellcheck disable=SC2086
+"$CONTAINER_RUNTIME" run --init -it -v "$REPO_DIR":/input:ro -e GITHUB_TOKEN="${GITHUB_TOKEN:-}" "$CONTAINER_IMAGE" $LYCHEE_ARGS

stream-processing/tutorial.md

@@ -7,7 +7,7 @@ Follow this tutorial to learn more about stream processing.
 This tutorial requires the following components:
 
 * Fluent Bit
-* [Docker Engine](https://www.docker.com/products/docker-engine)
+* [Docker Engine](https://docs.docker.com/engine/) and the `docker` CLI
 * A stream processing [sample file](https://raw.githubusercontent.com/fluent/fluent-bit-docs/37b477786d6e28eb223e08611c26ec93671a34ac/stream-processing/samples/sp-samples-1k.log)
 
 ## Steps