Optimize path and link validity check. (#462)

* Optimize path and link validity check. Signed-off-by: ZePan110 <[email protected]> * debug Signed-off-by: ZePan110 <[email protected]> * debug2 Signed-off-by: ZePan110 <[email protected]> * Fix issue Signed-off-by: ZePan110 <[email protected]> * Remove debug output Signed-off-by: ZePan110 <[email protected]> * test Signed-off-by: ZePan110 <[email protected]> * Fix issue. Signed-off-by: ZePan110 <[email protected]> * Fix issue Signed-off-by: ZePan110 <[email protected]> * Restore test file Signed-off-by: ZePan110 <[email protected]> --------- Signed-off-by: ZePan110 <[email protected]>
opea-project · Oct 9, 2024 · 91bd163 · 91bd163
1 parent 881e2b5
commit 91bd163
Showing 1 changed file with 51 additions and 36 deletions.
diff --git a/.github/workflows/pr-path-detection.yml b/.github/workflows/pr-path-detection.yml
@@ -17,28 +17,38 @@ jobs:
 
       - name: Checkout Repo GenAIInfra
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Check the Validity of Hyperlinks
         run: |
           cd ${{github.workspace}}
           fail="FALSE"
-          url_lines=$(grep -Eo '\]\(http[s]?://[^)]+\)' --include='*.md' -r .|grep -Ev 'GenAIEval/blob/main')
-          if [ -n "$url_lines" ]; then
-            for url_line in $url_lines; do
-              url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
-              path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
-              response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")
-              if [ "$response" -ne 200 ]; then
-                echo "**********Validation failed, try again**********"
-                response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
-                if [ "$response_retry" -eq 200 ]; then
-                  echo "*****Retry successfully*****"
-                else
-                  echo "Invalid link from ${{github.workspace}}/$path: $url"
-                  fail="TRUE"
-                fi
+          merged_commit=$(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 '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'GenAIEval/blob/main')
+              if [ -n "$url_lines" ]; then
+                for url_line in $url_lines; do
+                  url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
+                  path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
+                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")
+                  if [ "$response" -ne 200 ]; then
+                    echo "**********Validation failed, try again**********"
+                    response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
+                    if [ "$response_retry" -eq 200 ]; then
+                      echo "*****Retry successful*****"
+                    else
+                      echo "Invalid link from ${{github.workspace}}/$path: $url"
+                      fail="TRUE"
+                    fi
+                  fi
+                done
               fi
             done
+          else
+            echo "No changed .md file."
           fi
 
           if [[ "$fail" == "TRUE" ]]; then
@@ -56,6 +66,8 @@ jobs:
 
       - name: Checkout Repo GenAIInfra
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
 
       - name: Checking Relative Path Validity
         run: |
@@ -69,48 +81,51 @@ jobs:
             branch="https://github.com/opea-project/GenAIInfra/blob/${{ github.event.pull_request.head.ref }}"
           fi
           link_head="https://github.com/opea-project/GenAIInfra/blob/main"
+
+          merged_commit=$(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')
           if [ -n "$png_lines" ]; then
             for png_line in $png_lines; do
               refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
               png_path=$(echo "$png_line"|cut -d '(' -f2 | cut -d ')' -f1)
               if [[ "${png_path:0:1}" == "/" ]]; then
-                check_path=${{github.workspace}}$png_path
-              elif [[ "${png_path:0:1}" == "#" ]]; then
-                check_path=${{github.workspace}}/$refer_path$png_path
+                check_path=$png_path
+              elif [[ "$png_path" == *#* ]]; then
+                relative_path=$(echo "$png_path" | cut -d '#' -f1)
+                if [ -n "$relative_path" ]; then
+                  check_path=$(dirname "$refer_path")/$relative_path
+                  png_path=$(echo "$png_path" | awk -F'#' '{print "#" $2}')
+                else
+                  check_path=$refer_path
+                fi
               else
-                check_path=${{github.workspace}}/$(dirname "$refer_path")/$png_path
+                check_path=$(dirname "$refer_path")/$png_path
               fi
-              real_path=$(realpath $check_path)
-              if [ $? -ne 0 ]; then
-                echo "Path $png_path in file ${{github.workspace}}/$refer_path does not exist"
-                fail="TRUE"
-              else
-                url=$link_head$(echo "$real_path" | sed 's|.*/GenAIInfra||')
-                response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url")
-                if [ "$response" -ne 200 ]; then
-                  echo "**********Validation failed, try again**********"
-                  response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
-                  if [ "$response_retry" -eq 200 ]; then
-                    echo "*****Retry successfully*****"
-                  else
-                    echo "Retry failed. Check branch ${{ github.event.pull_request.head.ref }}"
-                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIInfra||')
+
+              if [ -e "$check_path" ]; then
+                real_path=$(realpath $check_path)
+                if [[ "$png_line" == *#* ]]; then
+                  if [ -n "changed_files" ] && echo "$changed_files" | grep -q "^${refer_path}$"; then
+                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIComps||')$png_path
                     response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
                     if [ "$response" -ne 200 ]; then
                       echo "**********Validation failed, try again**********"
                       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"
+                        echo "Invalid path from ${{github.workspace}}/$refer_path: $png_path, link: $url_dev"
                         fail="TRUE"
                       fi
                     else
-                      echo "Check branch ${{ github.event.pull_request.head.ref }} successfully."
+                      echo "Validation succeed $png_line"
                     fi
                   fi
                 fi
+              else
+                echo "$check_path does not exist"
+                fail="TRUE"
               fi
             done
           fi