CI URL checker: fix + minor improvements

- fix: fork name != "docs"
- check URLs only once
- more error output
- shorter timeouts

Signed-off-by: Eero Tamminen <[email protected]>

Author: eero-t

.github/workflows/pr-path-detection.yml

@@ -23,14 +23,15 @@ jobs:
       - name: Check the Validity of Hyperlinks
         run: |
           cd ${{github.workspace}}
+          timeout=15 # max connect timeout
           fail="FALSE"
           retry="FALSE"
           # url_lines=$(grep -Eo '\]\(http[s]?://[^)]+\)' --include='*.md' -r .|grep -Ev 'linkedin')
           merged_commit=$(git log -1 --format='%H')
           changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
           if  [ -n "$changed_files" ]; then
             for changed_file in $changed_files; do
-              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'linkedin') || true
+              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | sort -u | grep -Ev 'linkedin') || true
               if [ -n "$url_lines" ]; then
                 for url_line in $url_lines; do
                   url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
@@ -39,10 +40,10 @@ jobs:
                     echo "Link "$url" from ${{github.workspace}}/$path need to be verified by a real person."
                     retry="FALSE"
                   else
-                    response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")
+                    response=$(curl --connect-timeout $timeout -L -s -o /dev/null -w "%{http_code}" "$url")
                     if [ "$response" -ne 200 ]; then
                       echo "**********Validation failed, status code: $response, try again**********"
-                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
+                      response_retry=$(curl --connect-timeout $timeout -s -o /dev/null -w "%{http_code}" "$url")
                       if [ "$response_retry" -eq 200 ]; then
                         echo "*****Retry successful*****"
                       else
@@ -105,15 +106,15 @@ jobs:
           fail="FALSE"
           repo_name=${{ github.event.pull_request.head.repo.full_name }}
           if [ "$(echo "$repo_name"|cut -d'/' -f1)" != "opea-project" ]; then
-            owner=$(echo "${{ github.event.pull_request.head.repo.full_name }}" |cut -d'/' -f1)
-            branch="https://github.com/$owner/docs/tree/${{ github.event.pull_request.head.ref }}"
+            repo_fork=$(echo "${{ github.event.pull_request.head.repo.full_name }}" |cut -d'/' -f2)
+            branch="https://github.com/$repo_fork/tree/${{ github.event.pull_request.head.ref }}"
           else
             branch="https://github.com/opea-project/docs/blob/${{ github.event.pull_request.head.ref }}"
           fi
           link_head="https://github.com/opea-project/docs/blob/main"
           merged_commit=$(git log -1 --format='%H')
           changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
-          png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|grep -Ev 'http'|grep -Ev 'mailto'|grep -Ev 'portal.azure.com')
+          png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|sort -u|grep -Ev 'http'|grep -Ev 'mailto'|grep -Ev 'portal.azure.com')
           if [ -n "$png_lines" ]; then
             for png_line in $png_lines; do
               refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
@@ -138,12 +139,12 @@ jobs:
                     url_dev=$branch$(echo "$real_path" | sed 's|.*/docs||')$png_path
                     response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
                     if [ "$response" -ne 200 ]; then
-                      echo "**********Validation failed, try again**********"
+                      echo "**********Validation failed, status code: $response, try again**********"
                       response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url_dev")
                       if [ "$response_retry" -eq 200 ]; then
                         echo "*****Retry successfully*****"
                       else
-                        echo "Invalid path from ${{github.workspace}}/$refer_path: $png_path, link: $url_dev"
+                        echo "Status code: $response_retry => invalid path from ${{github.workspace}}/$refer_path: $png_path, link: $url_dev"
                         fail="TRUE"
                       fi
                     else