Merge branch 'main' of https://github.com/umbraco/UmbracoDocs into update-block-custom-view

Author: LanThuyNguyen

.github/lychee.toml

@@ -31,10 +31,18 @@ timeout = 10
 retry_wait_time = 1
 
 # Accept more status codes (follow redirects automatically)
-accept = ["200..=204", "301..=308", "429"]
+# Note: 522 and 502 are server errors, not broken links
+accept = [
+  "200..=204", 
+  "301..=308",
+  "403",  # Forbidden (Microsoft/LinkedIn block automated tools)
+  "429",
+  "502",  # Bad Gateway
+  "522"   # Connection timed out (Cloudflare)
+]
 
-# Avoid false fragment errors
-include_fragments = false  
+# Don't check fragments/anchors - they cause false positives
+include_fragments = false
 
 # Only test links with the given schemes (e.g. https and http)
 scheme = ["https", "http"]
@@ -52,9 +60,26 @@ exclude = [
   '^mailto:',
   '^https?://localhost',
   '^https?://127\\.0\\.0\\.1',
-  '^https://www\.linkedin\.com',
-  '^https?://issues\.umbraco\.org/',
-  '^https?://web\\.archive\\.org/web/'
+  '^https://www\\.linkedin\\.com',
+
+   # Exclude Microsoft authentication and Entra portals
+  'entra\\.microsoft\\.com',
+  'login\\.microsoftonline\\.com',
+  'portal\\.azure\\.com',
+  
+  # Exclude all issues.umbraco.org - unreliable and often returns 522
+  'http://issues\\.umbraco\\.org',
+  'https://issues\\.umbraco\\.org',
+  
+  # Exclude umbraco.com blog posts that return errors
+  'https://umbraco\\.com/blog/',
+  
+  # Exclude web archive links
+  'web\\.archive\\.org/web/',
+  
+  # Exclude internal links with version anchors
+  'version-specific#umbraco-',
+  'README\\.md#umbraco-[0-9]',
 ]
 
 # Exclude these filesystem paths from getting checked.

.github/workflows/check-broken-pr-links.yml

@@ -1,7 +1,7 @@
 name: Check Links in Pull Requests
 
 on:
-  pull_request:
+  pull_request:           # changed from pull_request
     branches:
       - main
     paths:
@@ -59,21 +59,36 @@ jobs:
             /^Errors in / {
               file=$3
               gsub("^/home/runner/work/UmbracoDocs/UmbracoDocs/", "", file)
-              print "\n**Broken links found in: " file "**" >> "lychee/comment.md"
+              current_file = file
+              has_errors = 0
               next
             }
 
-            /\[ERROR\]/ {
+            /Error: ERROR\]/ {
+              # Skip anchor errors for #umbraco-[number] patterns
+              if ($0 ~ /#umbraco-[0-9]+/) next
+              
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
               msg = $0
-              sub(/^- \[ \] /, "", msg)
-              sub(/^\[ERROR\] /, "", msg)
+              sub(/^Error: ERROR\] /, "", msg)
               gsub("^file:///home/runner/work/UmbracoDocs/UmbracoDocs/", "", msg)
               gsub(/\|/, "\\|", msg)   # escape Markdown pipe
               print "\n⚓ Anchor not found → " msg "\n" >> "lychee/comment.md"
               next
             }
 
             /\[404\]/ {
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
               msg = $0
               sub(/^- \[ \] /, "", msg)
               sub(/^\[404\] /, "", msg)
@@ -83,6 +98,12 @@ jobs:
             }
 
             /\[301\]|\[302\]/ {
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
               msg = $0
               sub(/^- \[ \] /, "", msg)
               sub(/^\[(301|302)\] /, "", msg)
@@ -91,7 +112,49 @@ jobs:
               next
             }
 
+            /\[522\]/ {
+              # Skip 522 errors from issues.umbraco.org
+              if ($0 ~ /issues\.umbraco\.org/) next
+              
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
+              msg = $0
+              sub(/^- \[ \] /, "", msg)
+              sub(/^\[522\] /, "", msg)
+              gsub(/\|/, "\\|", msg)
+              print "\n⚠ Server error (522) → " msg "\n" >> "lychee/comment.md"
+              next
+            }
+
+            /\[502\]/ {
+              # Skip 502 errors from umbraco.com
+              if ($0 ~ /umbraco\.com/) next
+              
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
+              msg = $0
+              sub(/^- \[ \] /, "", msg)
+              sub(/^\[502\] /, "", msg)
+              gsub(/\|/, "\\|", msg)
+              print "\n⚠ Server error (502) → " msg "\n" >> "lychee/comment.md"
+              next
+            }
+
             /Timeout/ && !/Timeouts/ {
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
               msg = $0
               sub(/^- \[ \] /, "", msg)
               gsub(/\|/, "\\|", msg)   # escape pipe just in case
@@ -101,6 +164,12 @@ jobs:
 
             # catch-all for any other errors
             /^\- \[ \] \[[0-9]+\]/ {
+              # Print file header if this is the first error for this file
+              if (current_file != "" && has_errors == 0) {
+                print "\n**Broken links found in: " current_file "**" >> "lychee/comment.md"
+                has_errors = 1
+              }
+              
               msg = $0
               sub(/^- \[ \] /, "", msg)
               gsub(/\|/, "|", msg)
@@ -131,4 +200,4 @@ jobs:
         if: steps.format-report.outputs.has_content == 'true'
         run: |
           echo "❌ Broken links detected. Please review the PR comment for details."
-          exit 1
+          exit 1