ci(jscpd): improve output format aws#6373

## Problem
The output format of clones found in `jscpd` can be difficult to parse.
As an example, see
https://github.com/aws/aws-toolkit-vscode/actions/runs/12778633640/job/35621822359?pr=6370.
Additionally, it mentions file names and line numbers, but doesn't
provide a way to get to those files.

## Solution
- reduce friction by linking directly to the duplicates

Author: Hweinstock

.github/workflows/filterDuplicates.js

@@ -4,7 +4,7 @@
  * the program exits with an error and logs the filtered report to console.
  *
  * Usage:
- *      node filterDuplicates.js run [path_to_git_diff] [path_to_jscpd_report]
+ *      node filterDuplicates.js run [path_to_git_diff] [path_to_jscpd_report] [commit_hash] [repo_name]
  *
  * Tests:
  *      node filterDuplicates.js test
@@ -84,25 +84,40 @@ function filterDuplicates(report, changes) {
     return duplicates
 }
 
+function formatDuplicates(duplicates, commitHash, repoName) {
+    const baseUrl = `https://github.com/${repoName}`
+    return duplicates.map((dupe) => {
+        return {
+            first: formUrl(dupe.firstFile, commitHash),
+            second: formUrl(dupe.secondFile, commitHash),
+            numberOfLines: dupe.lines,
+        }
+    })
+    function formUrl(file, commitHash) {
+        return `${baseUrl}/blob/${commitHash}/${file.name}#L${file.start}-L${file.end}`
+    }
+}
+
 async function run() {
     const rawDiffPath = process.argv[3]
     const jscpdReportPath = process.argv[4]
+    const commitHash = process.argv[5]
+    const repoName = process.argv[6]
     const changes = await parseDiff(rawDiffPath)
     const jscpdReport = JSON.parse(await fs.readFile(jscpdReportPath, 'utf8'))
     const filteredDuplicates = filterDuplicates(jscpdReport, changes)
 
     console.log('%s files changes', changes.size)
     console.log('%s duplicates found', filteredDuplicates.length)
     if (filteredDuplicates.length > 0) {
-        console.log(filteredDuplicates)
+        console.log(formatDuplicates(filteredDuplicates, commitHash, repoName))
         process.exit(1)
     }
 }
 
 /**
  * Mini-test Suite
  */
-console.log(__dirname)
 const testDiffFile = path.resolve(__dirname, 'test/test_diff.txt')
 let testCounter = 0
 function assertEqual(actual, expected) {

.github/workflows/node.js.yml

@@ -101,7 +101,10 @@ jobs:
                   path: ./jscpd-report.json
 
             - name: Check for Duplicates
-              run: node "$GITHUB_WORKSPACE/.github/workflows/filterDuplicates.js" run diff_output.txt jscpd-report.json
+              env:
+                  COMMIT_HASH: ${{ github.sha}}
+                  REPO_NAME: ${{ github.repository }}
+              run: node "$GITHUB_WORKSPACE/.github/workflows/filterDuplicates.js" run diff_output.txt jscpd-report.json $COMMIT_HASH $REPO_NAME
 
     macos:
         needs: lint-commits