build(jscpd): validate branch name before running CI (#6124)

## Problem
...

## Solution
- (title)
- Refactor github actions such that JSCPD requires `lint-commits`. 
- Add step to `lint-commits` that verifies branch name according to
rules here:
https://docs.github.com/en/get-started/using-git/dealing-with-special-characters-in-branch-and-tag-names#naming-branches-and-tags
- Note this means that no CI tasks will run on PRs with branches that
don't fit naming conventions.

---

<!--- REMINDER: Ensure that your PR meets the guidelines in
CONTRIBUTING.md -->

License: I confirm that my contribution is made under the terms of the
Apache 2.0 license.

Author: Hweinstock

.github/workflows/copyPasteDetection.yml

@@ -0,0 +1,67 @@
+// Check that branch name conforms to GitHub naming convention:
+// https://docs.github.com/en/get-started/using-git/dealing-with-special-characters-in-branch-and-tag-names#naming-branches-and-tags
+
+// To run self-tests,
+// node lintbranch.js test
+// TODO: deduplicate code from lintbranch.js and lintcommit.js.
+
+function isValid(branchName) {
+    const branchNameRegex = /^[a-zA-Z][a-zA-Z0-9._/-]*$/
+
+    return branchNameRegex.test(branchName)
+}
+
+function run(branchName) {
+    if (isValid(branchName)) {
+        console.log(`Branch name "${branchName}" is valid.`)
+        process.exit(0)
+    } else {
+        const helpUrl =
+            'https://docs.github.com/en/get-started/using-git/dealing-with-special-characters-in-branch-and-tag-names#naming-branches-and-tags'
+        console.log(`Branch name "${branchName}" is invalid see ${helpUrl} for more information.`)
+        process.exit(1)
+    }
+}
+
+function _test() {
+    const tests = {
+        'feature/branch-name': true,
+        feature_123: true,
+        'my-branch': true,
+        '123invalid-start': false,
+        '!invalid@start': false,
+        '': false,
+        'another/valid-name134': true,
+        'feature/123";id;{echo,Y2F0IC9ldGMvcGFzc3dk}|{base64,-d}|{bash,-i};#': false,
+    }
+
+    let passed = 0
+    let failed = 0
+
+    for (const [branchName, expected] of Object.entries(tests)) {
+        const result = isValid(branchName)
+        if (result === expected) {
+            console.log(`✅ Test passed for "${branchName}"`)
+            passed++
+        } else {
+            console.log(`❌ Test failed for "${branchName}" (expected "${expected}", got "${result}")`)
+            failed++
+        }
+    }
+
+    console.log(`\n${passed} tests passed, ${failed} tests failed`)
+}
+
+function main() {
+    const mode = process.argv[2]
+
+    if (mode === 'test') {
+        _test()
+    } else if (mode === 'run') {
+        run(process.argv[3])
+    } else {
+        throw new Error(`Unknown mode: ${mode}`)
+    }
+}
+
+main()

.github/workflows/lintbranch.js

@@ -32,6 +32,11 @@ jobs:
             - uses: actions/setup-node@v4
               with:
                   node-version: '20'
+            - name: Check Branch title
+              env:
+                  BRANCH_NAME: ${{ github.head_ref }}
+              run: |
+                  node "$GITHUB_WORKSPACE/.github/workflows/lintbranch.js" run "$BRANCH_NAME"
             - name: Check PR title
               run: |
                   node "$GITHUB_WORKSPACE/.github/workflows/lintcommit.js"
@@ -55,6 +60,87 @@ jobs:
             - run: npm run testCompile
             - run: npm run lint
 
+    jscpd:
+        needs: lint-commits
+        if: ${{ github.event_name == 'pull_request'}}
+        runs-on: ubuntu-latest
+        strategy:
+            matrix:
+                node-version: [18.x]
+        env:
+            NODE_OPTIONS: '--max-old-space-size=8192'
+
+        steps:
+            - uses: actions/checkout@v4
+              with:
+                  fetch-depth: 0
+
+            - name: Use Node.js ${{ matrix.node-version }}
+              uses: actions/setup-node@v4
+              with:
+                  node-version: ${{ matrix.node-version }}
+
+            - name: Fetch fork upstream
+              env:
+                  REPO_NAME: ${{ github.event.pull_request.head.repo.full_name }}
+              run: |
+                  git remote add forkUpstream https://github.com/$REPO_NAME  # URL of the fork
+                  git fetch forkUpstream  # Fetch fork
+
+            - name: Compute git diff
+              env:
+                  CURRENT_BRANCH: ${{ github.head_ref }}
+                  TARGET_BRANCH: ${{ github.event.pull_request.base.ref }}
+              run: git diff --name-only origin/$TARGET_BRANCH forkUpstream/$CURRENT_BRANCH > diff_output.txt
+
+            - run: npm install -g jscpd
+
+            - run: jscpd --config "$GITHUB_WORKSPACE/.github/workflows/jscpd.json"
+
+            - if: always()
+              uses: actions/upload-artifact@v4
+              with:
+                  name: unfiltered-jscpd-report
+                  path: ./jscpd-report.json
+
+            - name: Filter jscpd report for changed files
+              run: |
+                  if [ ! -f ./jscpd-report.json ]; then
+                    echo "jscpd-report.json not found"
+                    exit 1
+                  fi
+                  echo "Filtering jscpd report for changed files..."
+                  CHANGED_FILES=$(jq -R -s -c 'split("\n")[:-1]' diff_output.txt)
+                  echo "Changed files: $CHANGED_FILES"
+                  jq --argjson changed_files "$CHANGED_FILES" '
+                  .duplicates | map(select(
+                      (.firstFile?.name as $fname | $changed_files | any(. == $fname)) or
+                      (.secondFile?.name as $sname | $changed_files | any(. == $sname))
+                  ))
+                  ' ./jscpd-report.json > filtered-jscpd-report.json
+                  cat filtered-jscpd-report.json
+
+            - name: Check for duplicates
+              run: |
+                  if [ $(wc -l < ./filtered-jscpd-report.json) -gt 1 ]; then
+                    echo "filtered_report_exists=true" >> $GITHUB_ENV
+                  else
+                    echo "filtered_report_exists=false" >> $GITHUB_ENV
+                  fi
+            - name: upload filtered report (if applicable)
+              if: env.filtered_report_exists == 'true'
+              uses: actions/upload-artifact@v4
+              with:
+                  name: filtered-jscpd-report
+                  path: ./filtered-jscpd-report.json
+
+            - name: Fail and log found duplicates.
+              if: env.filtered_report_exists == 'true'
+              run: |
+                  cat ./filtered-jscpd-report.json
+                  echo "Duplications found, failing the check."
+                  exit 1
+
     macos:
         needs: lint-commits
         name: test macOS