Update Broken-links-checker-final.yml

Author: Vamshi-Microsoft

.github/workflows/Broken-links-checker-final.yml

@@ -12,22 +12,28 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - name: Checkout Repository
+      - name: Checkout Repo
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
-      # === PR MODE ===
+      - name: Mirror Repo to sanitized_md/
+        run: |
+          rsync -av --exclude '.git' --exclude 'node_modules' ./ sanitized_md/
+
+      # ‣ PR: get only changed .md files
       - name: Get Changed Markdown Files (PR)
         id: changed-files
         if: github.event_name == 'pull_request'
         run: |
           git fetch origin ${{ github.base_ref }}
-          files=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep '\.md$' || true)
+          files=$(git diff --name-only origin/${{ github.base_ref }}...HEAD \
+                  | grep '\.md$' || true)
           echo "md_files<<EOF" >> $GITHUB_OUTPUT
           echo "$files" >> $GITHUB_OUTPUT
           echo "EOF" >> $GITHUB_OUTPUT
 
+      # ‣ PR: initial Lychee run
       - name: Initial Lychee Check on Changed Files (PR)
         if: github.event_name == 'pull_request' && steps.changed-files.outputs.md_files != ''
         uses: lycheeverse/[email protected]
@@ -39,28 +45,31 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
+      # ‣ PR: extract only the .md files with errors
       - name: Extract Affected Files (PR)
         if: github.event_name == 'pull_request'
         id: affected-pr
         run: |
           mkdir -p sanitized_md
-          affected=$(grep -Eo 'file://[^ ]+\.md' lychee/pr.out | sed 's|file://||' | sort -u)
-          echo "$affected"
+          grep -Eo 'file://[^ ]+\.md' lychee/pr.out \
+            | sed 's|file://||' \
+            | sort -u \
+            | tee affected.txt
           echo "affected_files<<EOF" >> $GITHUB_OUTPUT
-          echo "$affected" >> $GITHUB_OUTPUT
+          cat affected.txt >> $GITHUB_OUTPUT
           echo "EOF" >> $GITHUB_OUTPUT
 
+      # ‣ PR: strip comments **in the copies**
       - name: Strip HTML Comments from Affected Files (PR)
         if: steps.affected-pr.outputs.affected_files != ''
         run: |
-          echo "${{ steps.affected-pr.outputs.affected_files }}" | while read -r file; do
-            if [ -f "$file" ]; then
-              target="sanitized_md/$file"
-              mkdir -p "$(dirname "$target")"
-              perl -0777 -pe 's/<!--.*?-->//gs' "$file" > "$target"
-            fi
-          done
+          while read -r file; do
+            src="sanitized_md/$file"
+            perl -0777 -pe 's/<!--.*?-->//gs' "$src" > "$src.tmp" \
+              && mv "$src.tmp" "$src"
+          done < affected.txt
 
+      # ‣ PR: **re-run** Lychee on the **sanitized** files
       - name: Re-check Sanitized Affected Files (PR)
         if: steps.affected-pr.outputs.affected_files != ''
         uses: lycheeverse/[email protected]
@@ -71,7 +80,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
-      # === MANUAL MODE ===
+      # --- Manual Dispatch: same two-pass logic ---
       - name: Initial Lychee Check on All Markdown (Manual)
         if: github.event_name == 'workflow_dispatch'
         uses: lycheeverse/[email protected]
@@ -88,22 +97,22 @@ jobs:
         id: affected-manual
         run: |
           mkdir -p sanitized_md
-          affected=$(grep -Eo 'file://[^ ]+\.md' lychee/manual.out | sed 's|file://||' | sort -u)
-          echo "$affected"
+          grep -Eo 'file://[^ ]+\.md' lychee/manual.out \
+            | sed 's|file://||' \
+            | sort -u \
+            | tee affected-manual.txt
           echo "affected_files<<EOF" >> $GITHUB_OUTPUT
-          echo "$affected" >> $GITHUB_OUTPUT
+          cat affected-manual.txt >> $GITHUB_OUTPUT
           echo "EOF" >> $GITHUB_OUTPUT
 
-      - name: Strip HTML Comments from Affected Files (Manual)
+      - name: Strip HTML Comments (Manual)
         if: steps.affected-manual.outputs.affected_files != ''
         run: |
-          echo "${{ steps.affected-manual.outputs.affected_files }}" | while read -r file; do
-            if [ -f "$file" ]; then
-              target="sanitized_md/$file"
-              mkdir -p "$(dirname "$target")"
-              perl -0777 -pe 's/<!--.*?-->//gs' "$file" > "$target"
-            fi
-          done
+          while read -r file; do
+            src="sanitized_md/$file"
+            perl -0777 -pe 's/<!--.*?-->//gs' "$src" > "$src.tmp" \
+              && mv "$src.tmp" "$src"
+          done < affected-manual.txt
 
       - name: Re-check Sanitized Affected Files (Manual)
         if: steps.affected-manual.outputs.affected_files != ''