From b5c016b16ad4175915603ff00fc59f3c5badf0d5 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Tue, 21 Jan 2025 19:23:09 +0100
Subject: [PATCH] Update links.yml (#152)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
---
 .github/workflows/links.yml | 52 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/links.yml b/.github/workflows/links.yml
index 959605a89c..fcf304fc6e 100644
--- a/.github/workflows/links.yml
+++ b/.github/workflows/links.yml
@@ -13,6 +13,7 @@ name: Check Website links
 
 on:
   workflow_dispatch:
+  pull_request:
   schedule:
     - cron: "0 0 * * *" # runs at 00:00 UTC every day
 
@@ -86,6 +87,39 @@ jobs:
           --no-verbose \
           --force-directories
 
+      - name: Run codespell on downloaded pages
+        id: codespell
+        continue-on-error: true  # Ensure the workflow continues even if spelling errors are found
+        run: |
+          pip install codespell
+          CODESPELL_OUTPUT=$(find ${{ matrix.website }} -type f -name "*.html" -print0 | xargs -0 codespell \
+          --ignore-words-list "crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall,skelton,goin,referer,pre,uint,dto,linkedin,webp,webgl,href,onclick,github,api,http,png,svg,gif,jpg,jpeg,href,js" \
+          --skip "*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,*lock*,__pycache__*,*.ico,*.jpg,*.png,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml" \
+          2>&1 || true)
+          echo "$CODESPELL_OUTPUT"
+
+          # Process CODESPELL_OUTPUT
+          MODIFIED_OUTPUT=$(echo "$CODESPELL_OUTPUT" | sed 's#\(.*/\)[^/]*:[0-9]*: \(.*\)#\1  \2#')
+          echo "$MODIFIED_OUTPUT"
+
+          # Check for spelling errors
+          if [[ "$CODESPELL_OUTPUT" == *"==>"* ]]; then
+            echo "Spelling errors found ⚠️"
+
+            echo "CODESPELL_SUMMARY<<EOF" >> $GITHUB_ENV
+            echo "## 📝 Spelling Errors" >> $GITHUB_ENV
+            # Use MODIFIED_OUTPUT here instead of CODESPELL_OUTPUT
+            echo "$MODIFIED_OUTPUT" >> $GITHUB_ENV
+            echo "EOF" >> $GITHUB_ENV
+
+            # Set output for Slack notification
+            echo "CODESPELL_ERRORS=$CODESPELL_SUMMARY" >> $GITHUB_OUTPUT
+            echo "CODESPELL_FAILED=true" >> $GITHUB_OUTPUT
+          else
+            echo "No spelling errors found ✅"
+            echo "CODESPELL_FAILED=false" >> $GITHUB_OUTPUT
+          fi
+
       - name: Run Broken Link Checks on Website
         id: lychee
         uses: ultralytics/actions/retry@main
@@ -139,7 +173,12 @@ jobs:
               exit 1
             fi
 
-      - name: Check for failure and notify
+      - name: Add spelling errors to GitHub Summary
+        if: always() && steps.codespell.outputs.CODESPELL_FAILED == 'true'
+        run: |
+          echo "${{ env.CODESPELL_SUMMARY }}" >> $GITHUB_STEP_SUMMARY
+
+      - name: Notify Slack for broken links
         if: always() && steps.lychee.outcome == 'failure' && github.event_name == 'schedule' && github.run_attempt == '1'
         uses: slackapi/slack-github-action@v2.0.0
         with:
@@ -147,3 +186,14 @@ jobs:
           webhook: ${{ matrix.website == 'www.ultralytics.com' && secrets.SLACK_WEBHOOK_URL_WEBSITE || secrets.SLACK_WEBHOOK_URL_YOLO }}
           payload: |
             text: "GitHub Actions: Errors found in ${{ github.workflow }} for ${{ matrix.website }} ❌\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* ${{ github.event_name }}\n\n\n${{ env.SUMMARY }}\n"
+
+      - name: Notify Slack for spelling errors
+        if: always() && steps.codespell.outputs.CODESPELL_FAILED == 'true' && github.event_name == 'schedule' && github.run_attempt == '1'
+        uses: slackapi/slack-github-action@v2.0.0
+        with:
+          webhook-type: incoming-webhook
+          webhook: ${{ matrix.website == 'www.ultralytics.com' && secrets.SLACK_WEBHOOK_URL_WEBSITE || secrets.SLACK_WEBHOOK_URL_YOLO }}
+          payload: |
+            {
+              "text": "GitHub Actions: Spelling errors found in ${{ github.workflow }} for ${{ matrix.website }} ❌\n\n\n*Repository:* https://github.com/${{ github.repository }}\n*Action:* https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}\n*Author:* ${{ github.actor }}\n*Event:* ${{ github.event_name }}\n\n\n*Misspelled words:*\n${{ steps.codespell.outputs.CODESPELL_ERRORS }}\n"
+            }