Add pr hyperlink and relative link scan job

.github/workflows/pr-link-scan.yml

@@ -0,0 +1,157 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check hyperlinks and relative path validity
+
+permissions:
+  contents: read
+
+on:
+  pull_request:
+    branches: [master]
+    types: [opened, reopened, ready_for_review, synchronize]
+
+jobs:
+  check-the-validity-of-hyperlinks-in-README:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo
+        uses: actions/checkout@1e31de5234b9f8995739874a8ce0492dc87873e2
+        with:
+          fetch-depth: 0
+
+      - name: Check the Validity of Hyperlinks
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          cd ${{github.workspace}}
+          delay=1
+          fail="FALSE"
+          merged_commit=$(git log -1 --format='%H')
+          changed_files="$(git diff --name-status --diff-filter=ARM $BASE_SHA ${merged_commit} | awk '/\.md$/ {print $NF}')"
+          if  [ -n "$changed_files" ]; then
+            for changed_file in $changed_files; do
+              # echo $changed_file
+              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file") || true
+              if [ -n "$url_lines" ]; then
+                for url_line in $url_lines; do
+                  # echo $url_line
+                  url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
+                  path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
+                  if [[ "$url" == "https://platform.openai.com/api-keys"* || "$url" == "https://ai.cloud.intel.com/" ]]; then
+                    echo "Link "$url" from ${{github.workspace}}/$path needs to be verified by real person."
+                  else
+                    sleep $delay
+                    response=$(curl -L -s -o /dev/null -w "%{http_code}" -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"   -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"   -H "Accept-Language: en-US,en;q=0.5" "$url")|| true
+                    if [ "$response" -ne 200 ]; then
+                      echo "**********Validation $url failed ($response), 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 $url failed ($response_retry), add simulated browser requests******"
+                        response_browser=$(curl -s -o /dev/null -w "%{http_code}" -A "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"   -H "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"   -H "Accept-Language: en-US,en;q=0.5" "$url")
+                        if [ "$response_browser" -eq 200 ]; then
+                          echo "*****Retry successfully*****"
+                        else
+                          echo -e "::error:: Invalid link ($response_retry) from ${{github.workspace}}/$(echo "$url_line"|cut -d':' -f1): $url"
+                          fail="TRUE"
+                        fi
+                      fi
+                    fi
+                  fi
+                done
+              fi
+            done
+          else
+            echo "No changed .md file."
+          fi
+
+          if [[ "$fail" == "TRUE" ]]; then
+            exit 1
+          else
+            echo "All hyperlinks are valid."
+          fi
+        shell: bash
+
+  check-the-validity-of-relative-path:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo
+        uses: actions/checkout@1e31de5234b9f8995739874a8ce0492dc87873e2
+        with:
+          fetch-depth: 0
+
+      - name: Checking Relative Path Validity
+        env:
+          REPO_NAME: ${{ github.event.pull_request.head.repo.full_name }}
+          HEAD_REF: ${{ github.event.pull_request.head.ref }}
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          cd ${{github.workspace}}
+          delay=1
+          fail="FALSE"
+          branch="https://github.com/$REPO_NAME/blob/$HEAD_REF"
+
+          merged_commit=$(git log -1 --format='%H')
+          changed_files="$(git diff --name-status --diff-filter=ARM $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=$png_path
+              elif [[ "$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=$(dirname "$refer_path")/$png_path
+              fi
+
+              if [ -e "$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|.*/neural-compressor||')$png_path
+                    sleep $delay
+                    response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
+                    if [ "$response" -ne 200 ]; then
+                      echo "**********Validation failed ($response), try again**********"
+                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url_dev")
+                      if [ "$response_retry" -eq 200 ]; then
+                        echo "*****Retry successfully*****"
+                      else
+                        echo -e "::error:: Invalid path ($response_retry) from ${{github.workspace}}/$refer_path: $png_path"
+                        fail="TRUE"
+                      fi
+                    else
+                      echo "Validation succeed $png_line"
+                    fi
+                  fi
+                fi
+              else
+                echo -e "::error:: ${{github.workspace}}/$refer_path:$png_path does not exist"
+                fail="TRUE"
+              fi
+            done
+          fi
+
+          if [[ "$fail" == "TRUE" ]]; then
+            exit 1
+          else
+            echo "All relative path are valid."
+          fi
+        shell: bash

README.md

@@ -115,7 +115,7 @@ model = load(
       <td colspan="2" align="center"><a href="./docs/source/3x/design.md#architecture">Architecture</a></td>
       <td colspan="2" align="center"><a href="./docs/source/3x/design.md#workflows">Workflow</a></td>
       <td colspan="2" align="center"><a href="https://intel.github.io/neural-compressor/latest/docs/source/api-doc/apis.html">APIs</a></td>
-      <td colspan="1" align="center"><a href="./docs/source/3x/llm_recipes.md">LLMs Recipes</a></td>
+      <td colspan="1" align="center"><a href="./docs/source/llm_recipes.md">LLMs Recipes</a></td>
       <td colspan="1" align="center"><a href="./examples/3.x_api/README.md">Examples</a></td>
     </tr>
   </tbody>