Articles plagiarism check implementation

.github/workflows/plagiarism-check.yml

@@ -0,0 +1,61 @@
+on:
+  issue_comment:
+    types: [created]
+
+permissions:
+  contents: read
+  issues: read
+  pull-requests: write
+
+jobs:
+  permission-check-job:
+    runs-on: ubuntu-latest
+    if: |
+      github.event.issue.pull_request &&
+      contains(github.event.comment.body, '/plagiarismcheck')
+    outputs:
+      permission: ${{ steps.permissions-check.outputs.defined }}
+    steps:
+      - name: Check for Secret availability
+        id: permissions-check
+        shell: bash
+        run: |
+          echo "defined=${{ contains(fromJSON(secrets.WIKI_REVIEWERS), github.actor) }}" >> $GITHUB_OUTPUT;
+
+
+  plagiarism-check:
+    runs-on: ubuntu-latest
+    name: "Checks a new article from a PR for plagiarism"
+    needs: [ permission-check-job ]
+    if: needs.permission-check-job.outputs.permission == 'true'
+    env:
+          GH_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
+
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Go to PR files
+        run: gh pr checkout "${{ github.event.issue.number }}"
+
+      - name: Save article contents
+        run: |
+          pr_number="${{ github.event.issue.number }}"
+          file_path="$(gh pr diff --name-only $pr_number | grep '\.md' | head -n 1)"
+          if [ -n "$file_path" ]; then
+            cat "$file_path" > article.txt
+          else
+            gh pr comment "${{ github.event.issue.number }}" --body "No .md file found in the PR."
+            exit 1
+          fi
+      - name: Check for plagiarism
+        run: |
+          content="$(cat article.txt)"
+          escaped_content=$(jq -Rs . <<<"$content")
+          result="$(curl -X POST "${{ secrets.WORKER_URL }}" -H "Content-Type: application/json" -d "{\"text\": $escaped_content}")"
+          echo "$result" > results.txt
+      - name: Format and post response
+        run: |
+          response=$(cat results.txt)
+          results=$(echo "$response" | jq -r '.results')
+          gh pr comment "${{ github.event.issue.number }}" --body "$results"

tools/plagiarism-checker/.gitignore

@@ -0,0 +1,33 @@
+# prod
+dist/
+
+# dev
+.yarn/
+!.yarn/releases
+.vscode/*
+!.vscode/launch.json
+!.vscode/*.code-snippets
+.idea/workspace.xml
+.idea/usage.statistics.xml
+.idea/shelf
+
+# deps
+node_modules/
+.wrangler
+
+# env
+.env
+.env.production
+.dev.vars
+
+# logs
+logs/
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+# misc
+.DS_Store

tools/plagiarism-checker/README.md

@@ -0,0 +1,28 @@
+# Plagiarism Checker
+
+This service does plagiarism evaluation throw a Cloudflare Worker.
+
+### Setup
+
+- Get Google API key and search engine ID from [here](https://developers.google.com/custom-search/v1/overview#api_key)
+
+- Set up wrangler.toml according to your Cloudflare credentials and add two of following enviromental variables:
+
+  - **GOOGLE_SEARCH_ENGINE_CX**
+
+  - **GOOGLE_API_KEY**
+
+- Instal dependencies and deploy Worker
+
+```bash
+npm i
+npm run deploy
+```
+
+- Save a deployed worker URL.
+
+- Add a **WORKER_URL** enviromental variable to your repository secrets, so Github Actions can access the service.
+
+### Usage
+
+Leave a comment with *"/plagiarismcheck"* in a pull request with new article to activate bot.