add: link checker job (#512)

.github/workflows/link-checker.yaml

@@ -0,0 +1,29 @@
+name: Check Links
+
+on:
+  schedule:
+    - cron: '0 1 * * 4' # every Thursday, at 1AM
+  workflow_dispatch:
+
+jobs:
+  check-links:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Install Muffet
+        run: |
+          sudo apt-get update
+          sudo apt-get install muffet
+
+      - name: Run check links
+        run: |
+          make check-links-logs
+
+      - name: Upload logs
+        uses: actions/upload-artifact@v3
+        with:
+          name: check-links-log
+          path: scripts/check_links.log

.gitignore

@@ -31,3 +31,6 @@
 npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
+
+# logs
+check_links.log

Makefile

@@ -57,3 +57,9 @@ cloud-list:
 
 delete-unused-images:
 	node "$(SCRIPTS)/delete_unused_images.js"
+
+check-links-logs:
+	sh "$(SCRIPTS)/check_links.sh" >> check_links.log
+
+check-links:
+	sh "$(SCRIPTS)/check_links.sh"

docs/platform/howto/byoc/create-custom-cloud.md

@@ -52,7 +52,7 @@ needs for accessing your GCP account only with permissions that are required.
 
 :::note
 Privilege-bearing service account (SA) is an
-[identifier](https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/google_service_account#id)
+[identifier](https://registry.terraform.io/providers/hashicorp/google/latest/docs/resources/google_service_account)
 of the [service account](https://cloud.google.com/iam/docs/service-account-types#user-managed)
 created when running the IaC template in your Google account. Aiven [impersonates this
 service account](https://cloud.google.com/iam/docs/create-short-lived-credentials-direct)
@@ -600,10 +600,10 @@ view, copy, or download it. Now, you can use the template to
 #### Deploy the template{#deploy-template}
 
 Role ARN is an [identifier of the
-role](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles)
+role](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles.html)
 created when running the infrastructure template in your AWS account.
 Aiven uses Role ARN to [assume the
-role](https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRole)
+role](https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRole.html)
 and run operations such as creating VMs for service nodes in your BYOC
 account.
 

docs/products/kafka/kafka-connect/howto/debezium-source-connector-pg.md

@@ -23,7 +23,7 @@ Before you begin, gather the necessary information about your source PostgreSQL
 -   `PG_PASSWORD`: The database password for the `PG_USER`
 -   `PG_DATABASE_NAME`: The database name
 -   `SSL_MODE`: The [SSL
-    mode](https://www.postgresql.org/docs/current/libpq-ssl)
+    mode](https://www.postgresql.org/docs/current/libpq-ssl.html)
 -   `PLUGIN_NAME`: The [logical decoding
     plugin](https://debezium.io/documentation/reference/stable/connectors/postgresql.html),
     possible values are `decoderbufs` and `pgoutput`.
@@ -35,7 +35,7 @@ Before you begin, gather the necessary information about your source PostgreSQL
     `schema_name1.table_name1,schema_name2.table_name2`
 -   `PG_PUBLICATION_NAME`: The name of the [PostgreSQL logical
     replication
-    publication](https://www.postgresql.org/docs/current/logical-replication-publication),
+    publication](https://www.postgresql.org/docs/current/logical-replication-publication.html),
     if left empty, `debezium` is used as default
 -   `PG_SLOT_NAME`: name of the [PostgreSQL replication
     slot](/docs/products/postgresql/howto/setup-logical-replication),

docs/products/postgresql/reference/list-of-extensions.md

@@ -78,10 +78,10 @@ for more information.
 
 ## Geographical features
 
--   [address_standardizer](https://postgis.net/docs/standardize_address).
+-   [address_standardizer](https://postgis.net/docs/standardize_address.html).
     Used to parse an address into constituent elements. Generally used
     to support geocoding address normalization step.
--   [address_standardizer_data_us](https://postgis.net/docs/standardize_address).
+-   [address_standardizer_data_us](https://postgis.net/docs/standardize_address.html).
     `Address standardizer` US dataset example.
 -   [earthdistance](https://www.postgresql.org/docs/current/earthdistance.html).
     Calculate great-circle distances on the surface of the Earth.
@@ -95,13 +95,13 @@ for more information.
     spatial types and functions.
 -   [postgis_legacy](https://postgis.net/). Legacy functions for
     PostGIS.
--   [postgis_raster](https://postgis.net/docs/RT_reference).
+-   [postgis_raster](https://postgis.net/docs/RT_reference.html).
     PostGIS raster types and functions.
--   [postgis_sfcgal](http://postgis.net/docs/reference#reference_sfcgal).
+-   [postgis_sfcgal](https://postgis.net/docs/reference_sfcgal.html).
     PostGIS SFCGAL functions.
--   [postgis_tiger_geocoder](https://postgis.net/docs/Extras#Tiger_Geocoder).
+-   [postgis_tiger_geocoder](https://postgis.net/docs/Extras.html#Tiger_Geocoder).
     PostGIS tiger geocoder and reverse geocoder.
--   [postgis_topology](https://postgis.net/docs/Topology). PostGIS
+-   [postgis_topology](https://postgis.net/docs/Topology.html). PostGIS
     topology spatial types and functions.
 
 ## Procedural language
@@ -160,7 +160,7 @@ for more information.
     Information about SSL certificates.
 -   [tablefunc](https://www.postgresql.org/docs/current/tablefunc.html).
     Functions that manipulate whole tables, including `crosstab`.
--   [timetravel](https://www.postgresql.org/docs/6.3/c0503.htm.html).
+-   [timetravel](https://www.postgresql.org/docs/6.3/c0503.htm).
     Functions for implementing time travel.
     `PG11 and earlier`
 -   [tsm_system_rows](https://www.postgresql.org/docs/current/tsm-system-rows.html).
@@ -188,7 +188,7 @@ not generally available**.
     Functions for tracking who changed a table.
 -   [moddatetime](https://www.postgresql.org/docs/10/contrib-spi.html).
     Functions for tracking last modification time.
--   [old_snapshot](https://www.postgresql.org/docs/current/oldsnapshot.html).
+-   [old_snapshot](https://www.postgresql.org/docs/14/oldsnapshot.html).
     Utilities in support of old_snapshot_threshold.
     `PG14 only`
 -   [pageinspect](https://www.postgresql.org/docs/current/pageinspect.html).

scripts/check_links.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+excludeList=(
+    "aiven.io/?!docs"
+	  "aiven.io/docs/assets"
+	  "aiven.io/docs/images"
+    "aiven.io/community"
+    "aiven.io/build"
+    ".*cdn.sanity.io"
+    ".*console.cloud.google.com"
+    ".*docs.npmjs.com"
+    ".*github.com"
+    ".*linkedin.com"
+    ".*maven.apache.org"
+    ".*uptime.aiven.io"
+    ".*docker.com"
+    ".*php.net"
+  )
+
+acceptedResponses="--accepted-status-codes=200..404"
+address="https://aiven.io/docs/"
+bufferSize="--buffer-size=8192"
+limitConnections="--max-connections=9"
+rateLimit="--rate-limit=30"
+redirectionLimit="--max-redirections=5"
+timeout="--timeout=4000"
+
+muffet ${acceptedResponses} \
+       ${bufferSize} \
+       ${excludeList[@]/#/--exclude } \
+       ${limitConnections} \
+       ${rateLimit} \
+       ${redirectionLimit} \
+       ${timeout} \
+       "--color=always" \
+       ${address};